cli 0.1.49

Add node state, customizable graph input and output schemas

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -1,5 +1,5 @@
 name: "\U0001F41B Bug Report"
-description: Report a bug in LangChain. To report a security issue, please instead use the security option below. For questions, please use the GitHub Discussions.
+description: Report a bug in LangGraph. To report a security issue, please instead use the security option below. For questions, please use the GitHub Discussions.
 labels: ["02 Bug Report"]
 body:
   - type: markdown
@@ -15,11 +15,11 @@ body:
         Relevant links to check before filing a bug report to see if your issue has already been reported, fixed or
         if there's another way to solve your problem:
         
+        [LangGraph documentation](https://langchain-ai.github.io/langgraph/).
         [LangChain documentation with the integrated search](https://python.langchain.com/docs/get_started/introduction),
-        [API Reference](https://api.python.langchain.com/en/stable/),
-        [GitHub search](https://github.com/langchain-ai/langchain),
-        [LangChain Github Discussions](https://github.com/langchain-ai/langchain/discussions),
-        [LangChain Github Issues](https://github.com/langchain-ai/langchain/issues?q=is%3Aissue),
+        [GitHub search](https://github.com/langchain-ai/langgraph),
+        [LangChain Github Discussions](https://github.com/langchain-ai/langgraph/discussions),
+        [LangChain Github Issues](https://github.com/langchain-ai/langgraph/issues),
         [LangChain ChatBot](https://chat.langchain.com/)
   - type: checkboxes
     id: checks
@@ -54,13 +54,13 @@ body:
         * Avoid screenshots when possible, as they are hard to read and (more importantly) don't allow others to copy-and-paste your code.
 
       placeholder: |
-        from langchain_core.runnables import RunnableLambda
+        from langgraph.graph import StateGraph
 
         def bad_code(inputs) -> int:
           raise NotImplementedError('For demo purpose')
           
-          chain = RunnableLambda(bad_code)
-          chain.invoke('Hello!')
+        chain = StateGraph(list)
+        chain.invoke('Hello!')
       render: python
   - type: textarea
     id: error
@@ -82,7 +82,7 @@ body:
 
         Write a short description telling what you are doing, what you expect to happen, and what is currently happening.
       placeholder: |
-        * I'm trying to use the `langchain` library to do X.
+        * I'm trying to use the `langgraph` library to do X.
         * I expect to see Y.
         * Instead, it does Z.
     validations:
@@ -102,7 +102,7 @@ body:
         
         python -m langchain_core.sys_info
       placeholder: |
-        "pip freeze | grep langchain"
+        "pip freeze | grep langgraph"
         platform
         python version
         

.github/ISSUE_TEMPLATE/config.yml

@@ -3,13 +3,13 @@ version: 2.1
 contact_links:
   - name: 🤔 Question or Problem
     about: Ask a question or ask about a problem in GitHub Discussions.
-    url: https://www.github.com/langchain-ai/langchain/discussions/categories/q-a
-  - name: Discord
-    url: https://discord.gg/6adMQxSpJS
-    about: General community discussions
+    url: https://github.com/langchain-ai/langgraph/discussions/categories/q-a
   - name: Feature Request
-    url: https://www.github.com/langchain-ai/langchain/discussions/categories/ideas
+    url: https://github.com/langchain-ai/langgraph/discussions/categories/ideas
     about: Suggest a feature or an idea
   - name: Show and tell
     about: Show what you built with LangChain
-    url: https://www.github.com/langchain-ai/langchain/discussions/categories/show-and-tell
+    url: https://github.com/langchain-ai/langgraph/discussions/categories/show-and-tell
+  - name: Slack
+    url:  https://www.langchain.com/join-community
+    about: General community discussions

.github/ISSUE_TEMPLATE/documentation.yml

@@ -1,5 +1,5 @@
 name: Documentation
-description: Report an issue related to the LangChain documentation.
+description: Report an issue related to the LangGraph documentation.
 title: "DOC: <Please write a comprehensive title after the 'DOC: ' prefix>"
 labels: [03 - Documentation]
 

.github/workflows/_integration_test.yml

@@ -12,6 +12,7 @@ jobs:
     strategy:
       matrix:
         python-version:
+          - "3.10"
           - "3.11"
     name: "CLI integration test"
     defaults:
@@ -30,7 +31,6 @@ jobs:
         with:
           python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: libs/cli
           cache-key: integration-test-cli
       - name: Setup env
         if: steps.changed-files.outputs.all
@@ -42,42 +42,19 @@ jobs:
       - name: Start service A
         if: steps.changed-files.outputs.all
         run: |
-          langgraph up -c examples/langgraph.json --wait --verbose
-      - name: Stop service A
-        if: steps.changed-files.outputs.all
-        run: |
-          langgraph down -c examples/langgraph.json
-          sudo rm -rf .langgraph-data
+          timeout 60 langgraph test -c examples/langgraph.json --verbose || (exit "$(($? == 124 ? 0 : $?))")
       - name: Start service B
         if: steps.changed-files.outputs.all
         working-directory: libs/cli/examples/graphs
         run: |
-          langgraph up --wait --verbose
-      - name: Stop service B
-        if: steps.changed-files.outputs.all
-        working-directory: libs/cli/examples/graphs
-        run: |
-          langgraph down
-          sudo rm -rf .langgraph-data
+          timeout 60 langgraph test --verbose || (exit "$(($? == 124 ? 0 : $?))")
       - name: Start service C
         if: steps.changed-files.outputs.all
         working-directory: libs/cli/examples/graphs_reqs_a
         run: |
-          langgraph up --wait -d compose.yml --verbose
-      - name: Stop service C
-        if: steps.changed-files.outputs.all
-        working-directory: libs/cli/examples/graphs_reqs_a
-        run: |
-          langgraph down
-          sudo rm -rf .langgraph-data
+          timeout 60 langgraph test --verbose || (exit "$(($? == 124 ? 0 : $?))")
       - name: Start service D
         if: steps.changed-files.outputs.all
         working-directory: libs/cli/examples/graphs_reqs_b
         run: |
-          langgraph up --wait -d compose.yml --verbose
-      - name: Stop service D
-        if: steps.changed-files.outputs.all
-        working-directory: libs/cli/examples/graphs_reqs_b
-        run: |
-          langgraph down
-          sudo rm -rf .langgraph-data
+          timeout 60 langgraph test --verbose || (exit "$(($? == 124 ? 0 : $?))")

.github/workflows/link_check.yml

@@ -1,4 +1,4 @@
-name: Check Links
+name: Check Docs & Links
 
 on:
   pull_request:
@@ -26,10 +26,10 @@ jobs:
       - name: Check links in Markdown files
         uses: gaurav-nelson/github-action-markdown-link-check@v1
         with:
-          folder-path: 'examples/'
+          folder-path: "examples/,docs/"
           check-modified-files-only: ${{ github.event_name != 'schedule' }}
-          file-path: './README.md'
-          config-file: './.markdown-link-check.config.json'
+          file-path: "./README.md"
+          config-file: "./.markdown-link-check.config.json"
 
   notebook-link-check:
     runs-on: ubuntu-latest
@@ -49,18 +49,39 @@ jobs:
           poetry install --with docs
           poetry run pip install -U pytest pytest-check-links langsmith langchain GitPython
 
-      # - name: Check links in notebooks
-      #   env:
-      #     LANGCHAIN_API_KEY: test
-      #   run: |
-      #     if [ "${{ github.event_name }}" != "schedule" ]; then
-      #       git fetch origin main
-      #       CHANGED_FILES=$(git diff --name-only origin/main | grep '\.ipynb$')
-      #       if [ -n "$CHANGED_FILES" ]; then
-      #         poetry run pytest -o python_files=non_python_only --check-links --check-links-ignore "https://(api|web)\.smith\.langchain\.com/.*" --check-links-ignore "https://x.com/.*" $CHANGED_FILES 
-      #       else
-      #         echo "No notebook files changed."
-      #       fi
-      #     else
-      #       poetry run pytest -o python_files=non_python_only --check-links --ignore="*.py" -k .ipynb --check-links-ignore "https://(api|web)\.smith\.langchain\.com/.*" --check-links-ignore "https://x.com/.*" ./examples
-      #     fi
+      - name: Check links in notebooks
+        env:
+          LANGCHAIN_API_KEY: test
+        run: |
+          if [ "${{ github.event_name }}" == "schedule" ] || [ "${{ github.event_name }}" == "workflow_dispatch" ] || ([ "${{ github.event_name }}" == "push" ] && [ "${{ github.ref }}" == "refs/heads/main" ]); then
+            echo "Running link check on all notebooks in examples directory..."
+            poetry run pytest -v --check-links-ignore "https://(api|web)\.smith\.langchain\.com/.*" --check-links-ignore "https://x.com/.*" --check-links examples
+          else
+            echo "Fetching changes from origin/main..."
+            git fetch origin main
+            echo "Checking for changed notebook files..."
+            CHANGED_FILES=$(git diff --name-only --diff-filter=d origin/main | grep '\.ipynb$' || true)
+            echo "Changed files: ${CHANGED_FILES}"
+            if [ -n "${CHANGED_FILES}" ]; then
+              echo "Running link check on changed notebook files..."
+              poetry run pytest -v --check-links-ignore "https://(api|web)\.smith\.langchain\.com/.*" --check-links-ignore "https://x.com/.*" --check-links ${CHANGED_FILES} || ([ $? = 5 ] && exit 0 || exit $?)
+            else
+              echo "No notebook files changed."
+            fi
+          fi
+  check-readmes-synced:
+    # This checks that the repo README.md is identical to the libs/langgraph/README.md
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Check README.md is in sync
+        run: |
+            if ! diff -q README.md libs/langgraph/README.md >/dev/null; then
+            echo "README.md is out of sync with libs/langgraph/README.md"
+            diff -C 3 README.md libs/langgraph/README.md
+            exit 1
+            fi

.github/workflows/release.yml

@@ -19,6 +19,7 @@ jobs:
 
     outputs:
       pkg-name: ${{ steps.check-version.outputs.pkg-name }}
+      short-pkg-name: ${{ steps.check-version.outputs.short-pkg-name }}
       version: ${{ steps.check-version.outputs.version }}
       tag: ${{ steps.check-version.outputs.tag }}
 
@@ -68,6 +69,7 @@ jobs:
             TAG="${SHORT_PKG_NAME}==${VERSION}"
           fi
           echo pkg-name="$PKG_NAME" >> $GITHUB_OUTPUT
+          echo short-pkg-name="$SHORT_PKG_NAME" >> $GITHUB_OUTPUT
           echo version="$VERSION" >> $GITHUB_OUTPUT
           echo tag="$TAG" >> $GITHUB_OUTPUT
 
@@ -92,12 +94,18 @@ jobs:
         working-directory: langgraph/${{ inputs.working-directory }}
         env:
           PKG_NAME: ${{ needs.build.outputs.pkg-name }}
+          SHORT_PKG_NAME: ${{ needs.build.outputs.short-pkg-name }}
           VERSION: ${{ needs.build.outputs.version }}
           TAG: ${{ needs.build.outputs.tag }}
         run: |
-          REGEX="^$PKG_NAME==\\d+\\.\\d+\\.\\d+\$"
+          if [ -z $SHORT_PKG_NAME ]; then
+            REGEX="^\\d+\\.\\d+\\.\\d+((a|b|rc)\\d+)?\$"
+          else
+            REGEX="^$SHORT_PKG_NAME==\\d+\\.\\d+\\.\\d+((a|b|rc)\\d+)?\$"
+          fi
           echo $REGEX
-          PREV_TAG=$(git tag --sort=-creatordate | grep -P $REGEX || true | head -1)
+          PREV_TAG=$(git tag --sort=-creatordate | grep -P $REGEX | head -1)
+          echo $PREV_TAG
           if [ "$TAG" == "$PREV_TAG" ]; then
             echo "No new version to release"
             exit 1
@@ -114,13 +122,12 @@ jobs:
         run: |
           {
             echo 'release-body<<EOF'
-            echo "# Release $TAG"
             if [ -z "$PREV_TAG" ]; then
               echo "Initial release"
             else
               echo "Changes since $PREV_TAG"
               echo
-              git log --format="%s" "$PREV_TAG"..HEAD -- $WORKING_DIR
+              git log --format="%s" "$PREV_TAG"..HEAD -- $WORKING_DIR | awk '{print "* " $0}'
             fi
             echo EOF
           } >> "$GITHUB_OUTPUT"
@@ -129,6 +136,7 @@ jobs:
     needs:
       - build
       - release-notes
+    permissions: write-all
     uses:
       ./.github/workflows/_test_release.yml
     with:

CONTRIBUTING.md

@@ -0,0 +1,293 @@
+# Contributing to LangGraph
+
+Thank you for being interested in contributing to LangGraph!
+
+## General guidelines
+
+Here are some things to keep in mind for all types of contributions:
+
+- Follow the ["fork and pull request"](https://docs.github.com/en/get-started/exploring-projects-on-github/contributing-to-a-project) workflow.
+- Fill out the checked-in pull request template when opening pull requests. Note related issues and tag relevant maintainers.
+- Ensure your PR passes formatting, linting, and testing checks before requesting a review.
+  - If you would like comments or feedback, please open an issue or discussion and tag a maintainer.
+- Backwards compatibility is key. Your changes must not be breaking, except in case of critical bug and security fixes.
+- Look for duplicate PRs or issues that have already been opened before opening a new one.
+- Keep scope as isolated as possible. As a general rule, your changes should not affect more than one package at a time.
+
+### Bugfixes
+
+For bug fixes, please open up an issue before proposing a fix to ensure the proposal properly addresses the underlying problem. In general, bug fixes should all have an accompanying unit test that fails before the fix.
+
+### New features
+
+For new features, please start a new [discussion](https://github.com/langchain-ai/langgraph/discussions), where the maintainers will help with scoping out the necessary changes.
+
+## Contribute Documentation
+
+Documentation is a vital part of LangGraph. We welcome both new documentation for new features and
+community improvements to our current documentation. Please read the resources below before getting started:
+
+- [Documentation style guide](#documentation-style-guide)
+- [Documentation setup](#setup)
+
+## Documentation Style Guide
+
+As LangGraph continues to grow, the surface area of documentation required to cover it continues to grow too.
+This page provides guidelines for anyone writing documentation for LangGraph, as well as some of our philosophies around organization and structure.
+
+## Philosophy
+
+LangGraph's documentation follows the [Diataxis framework](https://diataxis.fr).
+Under this framework, all documentation falls under one of four categories: [Tutorials](#tutorials),
+[How-to guides](#how-to-guides),
+[References](#references), and [Explanations (aka conceptual guides)](#conceptual-guide).
+
+### Tutorials
+
+Tutorials are lessons that take the reader through a practical activity. Their purpose is to help the user
+gain understanding of concepts and how they interact by showing one way to achieve some goal in a hands-on way.
+
+They should **avoid** giving
+multiple permutations of ways to achieve that goal in-depth. Choice is burdensome. Instead, they should guide a new user through a recommended path to accomplishing a concrete goal. While the end result of a tutorial does not necessarily need to
+be completely production-ready, it should be useful and practically satisfy the the goal that you clearly stated in the tutorial's introduction.
+
+To quote the Diataxis website:
+
+> A tutorial serves the user’s *acquisition* of skills and knowledge - their study. Its purpose is not to help the user get something done, but to help them learn.
+
+In LangGraph, these are often higher level guides that show off end-to-end use cases.
+
+Some examples include:
+
+- [Build a Customer Support Bot](https://langchain-ai.github.io/langgraph/tutorials/customer-support/customer-support/)
+- [Build a SQL Agent](https://langchain-ai.github.io/langgraph/tutorials/sql-agent/)
+
+Here are some high-level tips on writing a good tutorial:
+
+- Focus on guiding the user to get something done, but keep in mind the end-goal is more to impart principles than to create a perfect production system.
+- Be specific, not abstract and follow one path.
+  - No need to go deeply into alternative approaches, but it’s ok to reference them, ideally with a link to an appropriate how-to guide.
+- Get "a point on the board" as soon as possible - something the user can run that outputs something.
+  - You can iterate and expand afterwards.
+  - Try to frequently checkpoint at given steps where the user can run code and see progress.
+- Focus on results, not technical explanation.
+  - Crosslink heavily to appropriate conceptual/reference pages
+- The first time you mention a LangGraph concept, use its full name (e.g. "human-in-the-loop"), and link to its conceptual/other documentation page.
+  - It's also helpful to add a prerequisite callout that links to any pages with necessary background information.
+- End with a recap/next steps section summarizing what the tutorial covered and future reading, such as related how-to guides.
+- Use phrases like "Next we can run X & Y. We will expect Z.". Then afterwards, use language like "Notice Z" that recalls our expectations and directs the reader's attention to the topic we are trying to teach.
+- Do not shy away from repetition.
+
+### How-to guides
+
+A how-to guide, as the name implies, demonstrates how to do something discrete and specific.
+It should assume that the user is already familiar with underlying concepts, and is trying to solve an immediate problem, but
+should still give some background or list the scenarios where the information contained within can be relevant.
+They can and should discuss alternatives if one approach may be better than another in certain cases.
+
+To quote the Diataxis website:
+
+> A how-to guide serves the work of the already-competent user, whom you can assume to know what they want to do, and to be able to follow your instructions correctly.
+
+Some examples include:
+
+- [How to add persistence to your graph](https://langchain-ai.github.io/langgraph/how-tos/persistence/)
+- [How to view and update past graph state](https://langchain-ai.github.io/langgraph/how-tos/human_in_the_loop/time-travel/)
+
+Here are some high-level tips on writing a good how-to guide:
+
+- Clearly explain what you are guiding the user through at the start
+- Assume higher intent than a tutorial and show what the user needs to do to get that task done
+- Assume familiarity of concepts, but explain why suggested actions are helpful
+  - Crosslink heavily to conceptual/reference pages
+- Discuss alternatives and responses to real-world tradeoffs that may arise when solving a problem
+- Use lots of example code, ideally within complete code blocks that the reader can copy and run.
+- End with a recap/next steps section summarizing what the tutorial covered and future reading, such as other related how-to guides
+
+### Conceptual guides
+
+LangGraph's conceptual guides fall under the **Explanation** quadrant of Diataxis. They should cover LangChain terms and concepts
+in a more abstract way than how-to guides or tutorials, and should be geared towards curious users interested in
+gaining a deeper understanding of the framework. Try to avoid excessively large code examples. The goal here is to
+impart perspective to the user rather than to finish a practical project. These guides should cover **why** things work they way they do.
+
+
+To quote the Diataxis website:
+
+> The perspective of explanation is higher and wider than that of the other types. It does not take the user’s eye-level view, as in a how-to guide, or a close-up view of the machinery, like reference material. Its scope in each case is a topic - “an area of knowledge”, that somehow has to be bounded in a reasonable, meaningful way.
+
+Some examples include:
+
+- [What does it mean to be agentic?](https://langchain-ai.github.io/langgraph/concepts/high_level/)
+- [Tool calling](https://langchain-ai.github.io/langgraph/concepts/agentic_concepts/#tool-calling)
+
+Here are some high-level tips on writing a good conceptual guide:
+
+- Explain design decisions. Why does concept X exist and why was it designed this way?
+- Use analogies and reference other concepts and alternatives
+- Avoid blending in too much reference content
+- You can and should reference content covered in other guides, but make sure to link to them
+
+### References
+
+References contain detailed, low-level information that describes exactly what functionality exists and how to use it.
+In LangGraph, this is mainly our API reference pages, which are populated from docstrings within code.
+References pages are generally not read end-to-end, but are consulted as necessary when a user needs to know
+how to use something specific.
+
+To quote the Diataxis website:
+
+> The only purpose of a reference guide is to describe, as succinctly as possible, and in an orderly way. Whereas the content of tutorials and how-to guides are led by needs of the user, reference material is led by the product it describes.
+
+Many of the reference pages in LangChain are automatically generated from code,
+but here are some high-level tips on writing a good docstring:
+
+- Be concise
+- Discuss special cases and deviations from a user's expectations
+- Go into detail on required inputs and outputs
+- Light details on when one might use the feature are fine, but in-depth details belong in other sections.
+
+Each category serves a distinct purpose and requires a specific approach to writing and structuring the content.
+
+## General guidelines
+
+Here are some other guidelines you should think about when writing and organizing documentation.
+
+We generally do not merge new tutorials from outside contributors without an actue need.
+We welcome updates as well as new integration docs, how-tos, and references.
+
+### Avoid duplication
+
+Multiple pages that cover the same material in depth are difficult to maintain and cause confusion. There should
+be only one (very rarely two), canonical pages for a given concept or feature. Instead, you should link to other guides.
+
+### Link to other sections
+
+Because sections of the docs do not exist in a vacuum, it is important to link to other sections as often as possible
+to allow a developer to learn more about an unfamiliar topic inline.
+
+This includes linking to the API references as well as conceptual sections!
+
+### Be concise
+
+In general, take a less-is-more approach. If a section with a good explanation of a concept already exists, you should link to it rather than
+re-explain it, unless the concept you are documenting presents some new wrinkle.
+
+Be concise, including in code samples.
+
+### General style
+
+- Use active voice and present tense whenever possible
+- Use examples and code snippets to illustrate concepts and usage
+- Use appropriate header levels (`#`, `##`, `###`, etc.) to organize the content hierarchically
+- Use fewer cells with more code to make copy/paste easier
+- Use bullet points and numbered lists to break down information into easily digestible chunks
+- Use tables (especially for **Reference** sections) and diagrams often to present information visually
+- Include the table of contents for longer documentation pages to help readers navigate the content, but hide it for shorter pages
+
+## Setup
+
+LangChain documentation consists of two components:
+
+1. Main Documentation: Hosted at [https://langchain-ai.github.io](https://langchain-ai.github.io/langgraph/),
+this comprehensive resource serves as the primary user-facing documentation.
+It covers a wide array of topics, including tutorials, use cases, integrations,
+and more, offering extensive guidance on building with LangGraph.
+The content for this documentation lives in the `/docs` directory of the monorepo.
+2. In-code Documentation: This is documentation of the codebase itself, which is also
+used to generate the externally facing [API Reference](https://langchain-ai.github.io/langgraph/reference/graphs/).
+The content for the API reference is autogenerated by scanning the docstrings in the codebase. For this reason we ask that developers document their code well.
+
+We appreciate all contributions to the documentation, whether it be fixing a typo,
+adding a new tutorial or example and whether it be in the main documentation or the API Reference.
+
+### 📜 Main Documentation
+
+The content for the main documentation is located in the `/docs` directory of the monorepo.
+
+The documentation is written using a combination of ipython notebooks (`.ipynb` files)
+and markdown (`.md` files). The notebooks are converted to markdown
+and then built using [MkDocs](https://www.mkdocs.org/).
+
+Feel free to make contributions to the main documentation! 🥰
+
+After modifying the documentation:
+
+1. Run the linting and formatting commands (see below) to ensure that the documentation is well-formatted and free of errors.
+2. Optionally build the documentation locally to verify that the changes look good.
+3. Make a pull request with the changes.
+
+### ⚒️ Linting and Building Documentation Locally
+
+After writing up the documentation, you may want to lint and build the documentation
+locally to ensure that it looks good and is free of errors.
+
+If you're unable to build it locally that's okay as well, as you will be able to
+see a preview of the documentation on the pull request page.
+
+From the **monorepo root**, run the following command to install the dependencies:
+
+```bash
+poetry install --with docs --no-root
+```
+
+#### Building
+
+The code that builds the documentation is located in the `/docs` directory of the monorepo.
+
+Before building the documentation, it is always a good idea to clean the build directory:
+
+```bash
+make clean-docs
+```
+
+You can build and preview the documentation as outlined below:
+
+```bash
+make serve-docs
+```
+
+#### Linting
+
+The documentation is linted from the **monorepo root**. To lint it, run the following from there:
+
+```bash
+make spellcheck
+```
+
+### ️In-code Documentation
+
+The in-code documentation is autogenerated from docstrings.
+
+For the API reference to be useful, the codebase must be well-documented. This means that all functions, classes, and methods should have a docstring that explains what they do, what the arguments are, and what the return value is. This is a good practice in general, but it is especially important for LangChain because the API reference is the primary resource for developers to understand how to use the codebase.
+
+We generally follow the [Google Python Style Guide](https://google.github.io/styleguide/pyguide.html#38-comments-and-docstrings) for docstrings.
+
+Here is an example of a well-documented function:
+
+```python
+
+def my_function(arg1: int, arg2: str) -> float:
+    """This is a short description of the function. (It should be a single sentence.)
+
+    This is a longer description of the function. It should explain what
+    the function does, what the arguments are, and what the return value is.
+    It should wrap at 88 characters.
+
+    Examples:
+        This is a section for examples of how to use the function.
+
+        .. code-block:: python
+
+            my_function(1, "hello")
+
+    Args:
+        arg1: This is a description of arg1. We do not need to specify the type since
+            it is already specified in the function signature.
+        arg2: This is a description of arg2.
+
+    Returns:
+        This is a description of the return value.
+    """
+    return 3.14
+```

README.md

@@ -11,6 +11,9 @@
 > [!NOTE]
 > Looking for the JS version? Click [here](https://github.com/langchain-ai/langgraphjs) ([JS docs](https://langchain-ai.github.io/langgraphjs/)).
 
+> [!TIP]
+> Looking to deploy your LangGraph application? [Join the waitlist](https://www.langchain.com/langgraph-cloud-beta) for [LangGraph Cloud](https://langchain-ai.github.io/langgraph/cloud/), our managed service for deploying and hosting LangGraph applications.
+
 ## Overview
 
 [LangGraph](https://langchain-ai.github.io/langgraph/) is a library for building stateful, multi-actor applications with LLMs, used to create agent and multi-agent workflows. Compared to other LLM frameworks, it offers these core benefits: cycles, controllability, and persistence. LangGraph allows you to define flows that involve cycles, essential for most agentic architectures, differentiating it from DAG-based solutions. As a very low-level framework, it provides fine-grained control over both the flow and state of your application, crucial for creating reliable agents. Additionally, LangGraph includes built-in persistence, enabling advanced human-in-the-loop and memory features.
@@ -36,43 +39,52 @@ pip install -U langgraph
 
 One of the central concepts of LangGraph is state. Each graph execution creates a state that is passed between nodes in the graph as they execute, and each node updates this internal state with its return value after it executes. The way that the graph updates its internal state is defined by either the type of graph chosen or a custom function.
 
-Let's take a look at a simple example of an agent that can search the web using [Tavily Search API](https://tavily.com/).
+Let's take a look at a simple example of an agent that can use a search tool.
 
 ```shell
-pip install langchain_openai langchain_community
+pip install langchain-anthropic
 ```
 
 ```shell
-export OPENAI_API_KEY=sk-...
-export TAVILY_API_KEY=tvly-...
+export ANTHROPIC_API_KEY=sk-...
 ```
 
 Optionally, we can set up [LangSmith](https://docs.smith.langchain.com/) for best-in-class observability.
 
 ```shell
-export LANGCHAIN_TRACING_V2="true"
-export LANGCHAIN_API_KEY=ls__...
+export LANGSMITH_TRACING=true
+export LANGSMITH_API_KEY=lsv2_sk_...
 ```
 
 ```python
 from typing import Annotated, Literal, TypedDict
 
 from langchain_core.messages import HumanMessage
-from langchain_community.tools.tavily_search import TavilySearchResults
-from langchain_openai import ChatOpenAI
+from langchain_anthropic import ChatAnthropic
+from langchain_core.tools import tool
 from langgraph.checkpoint import MemorySaver
 from langgraph.graph import END, StateGraph, MessagesState
 from langgraph.prebuilt import ToolNode
 
 
 # Define the tools for the agent to use
-tools = [TavilySearchResults(max_results=1)]
+@tool
+def search(query: str):
+    """Call to surf the web."""
+    # This is a placeholder, but don't tell the LLM that...
+    if "sf" in query.lower() or "san francisco" in query.lower():
+        return ["It's 60 degrees and foggy."]
+    return ["It's 90 degrees and sunny."]
+
+
+tools = [search]
+
 tool_node = ToolNode(tools)
 
-model = ChatOpenAI(temperature=0).bind_tools(tools)
+model = ChatAnthropic(model="claude-3-5-sonnet-20240620", temperature=0).bind_tools(tools)
 
 # Define the function that determines whether to continue or not
-def should_continue(state: AgentState) -> Literal["tools", END]:
+def should_continue(state: MessagesState) -> Literal["tools", END]:
     messages = state['messages']
     last_message = messages[-1]
     # If the LLM makes a tool call, then we route to the "tools" node
@@ -83,7 +95,7 @@ def should_continue(state: AgentState) -> Literal["tools", END]:
 
 
 # Define the function that calls the model
-def call_model(state: AgentState):
+def call_model(state: MessagesState):
     messages = state['messages']
     response = model.invoke(messages)
     # We return a list, because this will get added to the existing list
@@ -132,7 +144,7 @@ final_state["messages"][-1].content
 ```
 
 ```
-'The current weather in San Francisco is as follows:\n- Temperature: 60.1°F (15.6°C)\n- Condition: Partly cloudy\n- Wind: 5.6 mph (9.0 kph) from SSW\n- Humidity: 83%\n- Visibility: 9.0 miles (16.0 km)\n- UV Index: 4.0\n\nFor more details, you can visit [Weather API](https://www.weatherapi.com/).'
+"Based on the search results, I can tell you that the current weather in San Francisco is:\n\nTemperature: 60 degrees Fahrenheit\nConditions: Foggy\n\nSan Francisco is known for its microclimates and frequent fog, especially during the summer months. The temperature of 60°F (about 15.5°C) is quite typical for the city, which tends to have mild temperatures year-round. The fog, often referred to as "Karl the Fog" by locals, is a characteristic feature of San Francisco\'s weather, particularly in the mornings and evenings.\n\nIs there anything else you\'d like to know about the weather in San Francisco or any other location?"
 ```
 
 Now when we pass the same `"thread_id"`, the conversation context is retained via the saved state (i.e. stored list of messages)
@@ -146,7 +158,7 @@ final_state["messages"][-1].content
 ```
 
 ```
-'The current weather in New York is as follows:\n- Temperature: 20.3°C (68.5°F)\n- Condition: Overcast\n- Wind: 2.2 mph from the north\n- Humidity: 65%\n- Cloud Cover: 100%\n- UV Index: 5.0\n\nFor more details, you can visit [Weather API](https://www.weatherapi.com/).'
+"Based on the search results, I can tell you that the current weather in New York City is:\n\nTemperature: 90 degrees Fahrenheit (approximately 32.2 degrees Celsius)\nConditions: Sunny\n\nThis weather is quite different from what we just saw in San Francisco. New York is experiencing much warmer temperatures right now. Here are a few points to note:\n\n1. The temperature of 90°F is quite hot, typical of summer weather in New York City.\n2. The sunny conditions suggest clear skies, which is great for outdoor activities but also means it might feel even hotter due to direct sunlight.\n3. This kind of weather in New York often comes with high humidity, which can make it feel even warmer than the actual temperature suggests.\n\nIt's interesting to see the stark contrast between San Francisco's mild, foggy weather and New York's hot, sunny conditions. This difference illustrates how varied weather can be across different parts of the United States, even on the same day.\n\nIs there anything else you'd like to know about the weather in New York or any other location?"
 ```
 
 ### Step-by-step Breakdown
@@ -154,8 +166,8 @@ final_state["messages"][-1].content
 1. <details>
     <summary>Initialize the model and tools.</summary>
 
-    - we use `ChatOpenAI` as our LLM. **NOTE:** we need make sure the model knows that it has these tools available to call. We can do this by converting the LangChain tools into the format for OpenAI tool calling using the `.bind_tools()` method.
-    - we define the tools we want to use - a web search tool in our case. It is really easy to create your own tools - see documentation here on how to do that [here](https://python.langchain.com/docs/modules/agents/tools/custom_tools).
+    - we use `ChatAnthropic` as our LLM. **NOTE:** we need make sure the model knows that it has these tools available to call. We can do this by converting the LangChain tools into the format for OpenAI tool calling using the `.bind_tools()` method.
+    - we define the tools we want to use - a search tool in our case. It is really easy to create your own tools - see documentation here on how to do that [here](https://python.langchain.com/docs/modules/agents/tools/custom_tools).
    </details>
 
 2. <details>
@@ -216,4 +228,8 @@ final_state["messages"][-1].content
 * [How-to Guides](https://langchain-ai.github.io/langgraph/how-tos/): Accomplish specific things within LangGraph, from streaming, to adding memory & persistence, to common design patterns (branching, subgraphs, etc.), these are the place to go if you want to copy and run a specific code snippet.
 * [Conceptual Guides](https://langchain-ai.github.io/langgraph/concepts/): In-depth explanations of the key concepts and principles behind LangGraph, such as nodes, edges, state and more.
 * [API Reference](https://langchain-ai.github.io/langgraph/reference/graphs/): Review important classes and methods, simple examples of how to use the graph and checkpointing APIs, higher-level prebuilt components and more.
-* [Cloud (alpha)](https://langchain-ai.github.io/langgraph/cloud/): With one click, deploy LangGraph applications to LangGraph Cloud.
+* [Cloud (beta)](https://langchain-ai.github.io/langgraph/cloud/): With one click, deploy LangGraph applications to LangGraph Cloud.
+
+## Contributing
+
+For more information on how to contribute, see [here](https://github.com/langchain-ai/langgraph/blob/main/CONTRIBUTING.md).

docs/_scripts/copy_notebooks.py

@@ -1,4 +1,6 @@
+import json
 import os
+import re
 import shutil
 from pathlib import Path
 
@@ -13,19 +15,31 @@ cloud_sdk_dir = docs_dir / "cloud"
 
 _MANUAL = {
     "how-tos": [
+        "state-context-key.ipynb",
         "async.ipynb",
         "stream-values.ipynb",
         "stream-updates.ipynb",
         "stream-multiple.ipynb",
         "streaming-tokens.ipynb",
+        "streaming-tokens-without-langchain.ipynb",
         "streaming-content.ipynb",
         "streaming-events-from-within-tools.ipynb",
+        "streaming-events-from-within-tools-without-langchain.ipynb",
+        "streaming-from-final-node.ipynb",
         "persistence.ipynb",
+        "memory/manage-conversation-history.ipynb",
+        "memory/delete-messages.ipynb",
+        "memory/add-summary-conversation-history.ipynb",
+        "persistence_postgres.ipynb",
+        "persistence_mongodb.ipynb",
+        "persistence_redis.ipynb",
         "visualization.ipynb",
         "state-model.ipynb",
         "subgraph.ipynb",
         "force-calling-a-tool-first.ipynb",
         "pass-run-time-values-to-tools.ipynb",
+        "tool-calling.ipynb",
+        "tool-calling-errors.ipynb",
         "dynamic-returning-direct.ipynb",
         "managing-agent-steps.ipynb",
         "respond-in-format.ipynb",
@@ -51,13 +65,9 @@ _MANUAL = {
 }
 _MANUAL_INVERSE = {v: docs_dir / k for k, vs in _MANUAL.items() for v in vs}
 _HOW_TOS = {"agent_executor", "chat_agent_executor_with_function_calling", "docs"}
-_MAP = {
-    "persistence_postgres.ipynb": "tutorial",
-}
 _HIDE = set(
     str(examples_dir / f)
     for f in [
-        "persistence_postgres.ipynb",
         "agent_executor/base.ipynb",
         "agent_executor/force-calling-a-tool-first.ipynb",
         "agent_executor/high-level.ipynb",
@@ -77,6 +87,17 @@ _HIDE = set(
         "rag/langgraph_rag_agent_llama3_local.ipynb",
         "rag/langgraph_self_rag_pinecone_movies.ipynb",
         "rag/langgraph_adaptive_rag_cohere.ipynb",
+        "dynamically-returning-directly.ipynb",
+        "force-calling-a-tool-first.ipynb",
+        "managing-agent-steps.ipynb",
+        "respond-in-format.ipynb",
+        "quickstart.ipynb",
+        "human-in-the-loop.ipynb",
+        "learning.ipynb",
+        "docs/quickstart.ipynb",
+        "tutorials/rag-agent-testing.ipynb",
+        "time-travel.ipynb",
+        "code_assistant/langgraph_code_assistant_mistral.ipynb",
     ]
 )
 
@@ -98,6 +119,44 @@ def clean_notebooks():
                 os.rmdir(root)
 
 
+def update_notebook_links(notebook_path):
+    with open(notebook_path, "r", encoding="utf-8") as f:
+        notebook = json.load(f)
+
+    for cell in notebook["cells"]:
+        if cell["cell_type"] == "markdown":
+            for i, source in enumerate(cell["source"]):
+                # Update relative notebook links
+                cell["source"][i] = re.sub(
+                    r"\[([^\]]+)\]\(([^:)]+\.ipynb)\)",
+                    lambda m: transform_link(m.group(1), m.group(2)),
+                    source,
+                )
+
+    with open(notebook_path, "w", encoding="utf-8") as f:
+        json.dump(notebook, f, indent=2)
+
+
+def transform_link(text, link):
+    dir_path, filename = os.path.split(link)
+
+    # Remove the .ipynb extension
+    filename_without_ext = os.path.splitext(filename)[0]
+
+    # If it's a local link (starts with ./)
+    if link.startswith("./"):
+        # Change to parent directory and remove ./ prefix
+        new_link = f"../{filename_without_ext}/"
+    elif dir_path:
+        # If there's a directory path, keep it and add one more level up
+        new_link = f"../{dir_path}/{filename_without_ext}/"
+    else:
+        # If it's just a filename, simply go one level up
+        new_link = f"../{filename_without_ext}/"
+
+    return f"[{text}]({new_link})"
+
+
 def copy_notebooks():
     # Nested ones are mostly tutorials rn
     for root, dirs, files in os.walk(examples_dir):
@@ -116,8 +175,6 @@ def copy_notebooks():
         for file in files:
             dst_dir_ = dst_dir
             if file.endswith((".ipynb", ".png")):
-                if file in _MAP:
-                    dst_dir = os.path.join(dst_dir, _MAP[file])
                 src_path = os.path.join(root, file)
                 if src_path in _HIDE:
                     print("Hiding:", src_path)
@@ -148,17 +205,9 @@ def copy_notebooks():
                     content = content.replace('src=\\"./img/', 'src=\\"../img/')
                     with open(dst_path, "w") as f:
                         f.write(content)
+                    update_notebook_links(dst_path)
                 dst_dir = dst_dir_
 
-    # Top level notebooks are "how-to's"
-    # for file in examples_dir.iterdir():
-    #     if file.suffix.endswith(".ipynb") and not os.path.isdir(
-    #         os.path.join(examples_dir, file)
-    #     ):
-    #         src_path = os.path.join(examples_dir, file)
-    #         dst_path = os.path.join(docs_dir, "how-tos", file.name)
-    #         shutil.copy(src_path, dst_path)
-
 
 if __name__ == "__main__":
     clean_notebooks()

docs/docs/cloud/concepts/api.md

@@ -1,20 +1,29 @@
 # API Concepts
+
 This page describes the high-level concepts of the LangGraph Cloud API. The conceptual guide of LangGraph (Python library) is [here](../../concepts/index.md).
 
 ## Data Models
+
 The LangGraph Cloud API consists of a few core data models: [Assistants](#assistants), [Threads](#threads), [Runs](#runs), and [Cron Jobs](#cron-jobs).
 
 ### Assistants
-An assistant is a configured instance of a [`CompiledGraph`](../../../reference/graphs/#compiledgraph). It abstracts the cognitive architecture of the graph and contains instance specific configuration and metadata. Multiple assistants can reference the same graph but can contain different configuration and metadata, which may differentiate the behavior of the assistants. An assistant (i.e. the graph) is invoked as part of a run.
+
+An assistant is a configured instance of a [`CompiledGraph`][compiledgraph]. It abstracts the cognitive architecture of the graph and contains instance specific configuration and metadata. Multiple assistants can reference the same graph but can contain different configuration and metadata, which may differentiate the behavior of the assistants. An assistant (i.e. the graph) is invoked as part of a run.
 
 The LangGraph Cloud API provides several endpoints for creating and managing assistants. See the <a href="../reference/api/api_ref.html#tag/assistantscreate" target="_blank">API reference</a> for more details.
 
 ### Threads
-A thread contains the accumulated state of a group of runs. If a run is executed on a thread, then the [state](../../../concepts/#persistence) of the underlying graph of the assistant will be persisted to the thread. A thread's current and historical state can be retrieved. To persist state, a thread must be created prior to executing a run.
+
+A thread contains the accumulated state of a group of runs. If a run is executed on a thread, then the [state][state] of the underlying graph of the assistant will be persisted to the thread. A thread's current and historical state can be retrieved. To persist state, a thread must be created prior to executing a run.
+
+The state of a thread at a particular point in time is called a checkpoint.
+
+For more on threads and checkpoints, see this section of the [LangGraph conceptual guide](../../concepts/low_level.md#checkpointer).
 
 The LangGraph Cloud API provides several endpoints for creating and managing threads and thread state. See the <a href="../reference/api/api_ref.html#tag/threadscreate" target="_blank">API reference</a> for more details.
 
 ### Runs
+
 A run is an invocation of an assistant. Each run may have its own input, configuration, and metadata, which may affect execution and output of the underlying graph. A run can optionally be executed on a thread.
 
 The LangGraph Cloud API provides several endpoints for creating and managing runs. See the <a href="../reference/api/api_ref.html#tag/runscreate" target="_blank">API reference</a> for more details.
@@ -26,36 +35,40 @@ It's often useful to run graphs on some schedule. LangGraph Cloud supports cron
 - Create a new thread with the specified assistant
 - Send the specified input to that thread
 
-Note that this sends the same input to the thread every time. See the [How-to Guide](../how-tos/cloud_examples/cron_jobs/) for creating cron jobs.
+Note that this sends the same input to the thread every time. See the [how-to guide](../how-tos/cloud_examples/cron_jobs.ipynb) for creating cron jobs.
 
 The LangGraph Cloud API provides several endpoints for creating and managing cron jobs. See the <a href="../reference/api/api_ref.html#tag/runscreate/POST/threads/{thread_id}/runs/crons" target="_blank">API reference</a> for more details.
 
 ## Features
+
 The LangGraph Cloud API offers several features to support complex agent architectures.
 
 ### Streaming
-Streaming is critical for making LLM applications feel responsive to end users. When creating a streaming run, the streaming mode determines what data is streamed back to the API client. The LangGraph Cloud API supports five streaming modes. 
 
-- `values`: Stream the full state of the graph after each node is executed. See the [How-to Guide](../how-tos/cloud_examples/stream_values/) for streaming values.
-- `messages`: Stream complete messages (at the end of node execution) as well as tokens for any messages generated inside a node. This mode is primarily meant for powering chat applications. This is only an option if your graph contains a `messages` key. See the [How-to Guide](../how-tos/cloud_examples/stream_messages/) for streaming messages.
-- `updates`: Streams updates to the state of the graph after each node is executed. See the [How-to Guide](../how-tos/cloud_examples/stream_updates/) for streaming updates.
-- `events`: Stream all events (including the state of the graph) after each node is executed. See the [How-to Guide](../how-tos/cloud_examples/stream_events/) for streaming events. This can be used to do token-by-token streaming for LLMs.
-- `debug`: Stream debug events after each node is executed. See the [How-to Guide](../how-tos/cloud_examples/stream_debug/) for streaming debug events.
+Streaming is critical for making LLM applications feel responsive to end users. When creating a streaming run, the streaming mode determines what data is streamed back to the API client. The LangGraph Cloud API supports five streaming modes.
 
-You can also specify multiple streaming modes at the same time. See the [How-to Guide](../how-tos/cloud_examples/stream_multiple/) for configuring multiple streaming modes at the same time.
+- `values`: Stream the full state of the graph after each node is executed. See the [how-to guide](../how-tos/stream_values.md) for streaming values.
+- `messages`: Stream complete messages (at the end of node execution) as well as tokens for any messages generated inside a node. This mode is primarily meant for powering chat applications. This is only an option if your graph contains a `messages` key. See the [how-to guide](../how-tos/stream_messages.md) for streaming messages.
+- `updates`: Streams updates to the state of the graph after each node is executed. See the [how-to guide](../how-tos/stream_updates.md) for streaming updates.
+- `events`: Stream all events (including the state of the graph) after each node is executed. See the [how-to guide](../how-tos/stream_events.md) for streaming events. This can be used to do token-by-token streaming for LLMs.
+- `debug`: Stream debug events after each node is executed. See the [how-to guide](../how-tos/stream_debug.md) for streaming debug events.
+
+You can also specify multiple streaming modes at the same time. See the [how-to guide](../how-tos/stream_multiple.md) for configuring multiple streaming modes at the same time.
 
 See the <a href="../reference/api/api_ref.html#tag/runscreate/POST/threads/{thread_id}/runs/stream" target="_blank">API reference</a> for how to create streaming runs.
 
 ### Human-in-the-Loop
-There are many occasions where the graph cannot run completely autonomously. For instance, the user might need to input some additional arguments to a function call, or select the next edge for the graph to continue on. In these instances, we need to insert some human in the loop interaction, which you can learn about in the [human in the loop how-tos](../how-tos/cloud_examples/human_in_the_loop_breakpoint).
+
+There are many occasions where the graph cannot run completely autonomously. For instance, the user might need to input some additional arguments to a function call, or select the next edge for the graph to continue on. In these instances, we need to insert some human in the loop interaction, which you can learn about in the [human in the loop how-tos](../how-tos/index.md#human-in-the-loop).
 
 ### Double Texting
-Many times users might interact with your graph in unintended ways. For instance, a user may send one message and before the graph has finished running send a second message. To solve this issue of "double-texting" (i.e. prompting the graph a second time before the first run has finished), Langgraph has provided four different solutions, all of which are covered in the [Double Texting how-tos](../how-tos/cloud_examples/interrupt_concurrent/). These options are:
 
-- `reject`: This is the simplest option, this just rejects any follow up runs and does not allow double texting. See the [How-to Guide](../how-tos/cloud_examples/reject_concurrent/) for configuring the reject double text option.
-- `enqueue`: This is a relatively simple option which continues the first run until it completes the whole run, then sends the new input as a separate run. See the [How-to Guide](../how-tos/cloud_examples/enqueue_concurrent/) for configuring the enqueue double text option.
-- `interrupt`: This option interrupts the current execution but saves all the work done up until that point. It then inserts the user input and continues from there. If you enable this option, your graph should be able to handle weird edge cases that may arise. See the [How-to Guide](../how-tos/cloud_examples/interrupt_concurrent/) for configuring the interrupt double text option.
-- `rollback`: This option rolls back all work done up until that point. It then sends the user input in, basically as if it just followed the original run input. See the [How-to Guide](../how-tos/cloud_examples/rollback_concurrent/) for configuring the rollback double text option.
+Many times users might interact with your graph in unintended ways. For instance, a user may send one message and before the graph has finished running send a second message. To solve this issue of "double-texting" (i.e. prompting the graph a second time before the first run has finished), LangGraph has provided four different solutions, all of which are covered in the [Double Texting how-tos](../how-tos/index.md#double-texting). These options are:
+
+- `reject`: This is the simplest option, this just rejects any follow up runs and does not allow double texting. See the [how-to guide](../how-tos/reject_concurrent.md) for configuring the reject double text option.
+- `enqueue`: This is a relatively simple option which continues the first run until it completes the whole run, then sends the new input as a separate run. See the [how-to guide](../how-tos/enqueue_concurrent.md) for configuring the enqueue double text option.
+- `interrupt`: This option interrupts the current execution but saves all the work done up until that point. It then inserts the user input and continues from there. If you enable this option, your graph should be able to handle weird edge cases that may arise. See the [how-to guide](../how-tos/interrupt_concurrent.md) for configuring the interrupt double text option.
+- `rollback`: This option rolls back all work done up until that point. It then sends the user input in, basically as if it just followed the original run input. See the [how-to guide](../how-tos/rollback_concurrent.md) for configuring the rollback double text option.
 
 ### Stateless Runs
 
@@ -69,10 +82,17 @@ All runs use the built-in checkpointer to store checkpoints for runs. However, i
 Stateless runs are still retried as regular retries are per node, while everything still in memory, so doesn't use checkpoints.
 
 The only difference is in stateless background runs, if the task worker dies halfway (not because the run itself failed, for some external reason) then the whole run will be retried like any background run, but
+
 - whereas a stateful background run would retry from the last successful checkpoint
 - a stateless background run would retry from the beginning
 
-See the [How-to Guide](../how-tos/cloud_examples/stateless_runs/) for creating stateless runs.
+See the [how-to guide](../how-tos/cloud_examples/stateless_runs.ipynb) for creating stateless runs.
+
+### Webhooks
+
+For all types of runs, langgraph cloud supports completion webhooks. When you create the run you can pass a webhook URL to be called when the completes (successfully or not). This is especially useful for background runs and cron jobs, as the webhook can give you an indication the run has completed and you can perform further actions for your appilcation.
+
+See this [how-to guide](../how-tos/cloud_examples/webhooks.ipynb) to learn about how to use webhooks with LangGraph Cloud.
 
 ## Deployment
 
@@ -81,3 +101,7 @@ The LangGraph Cloud offers several features to support secure and robost deploym
 ### Authentication
 
 LangGraph applications deployed to LangGraph Cloud are automatically configured with LangSmith authentication. In order to call the API, a valid <a href="https://docs.smith.langchain.com/how_to_guides/setup/create_account_api_key#api-keys" target="_blank">LangSmith API key</a> is required.
+
+### Local Testing
+
+Before deploying your app in production to LangGraph Cloud, you may wish to test out your graph locally in order to ensure that everything is running as expected. Luckily, LangGraph makes this easy for you through use of the LangGraph CLI. Read more in this [how-to guide](../deployment/test_locally.md) or look at the [CLI reference](../reference/cli.md) to learn more.

docs/docs/cloud/concepts/cloud.md

@@ -0,0 +1,28 @@
+# Cloud Concepts
+
+This page describes the high-level concepts of the LangGraph Cloud deployment.
+
+## Deployment
+
+A deployment is an instance of a LangGraph API. A single deployment can have many [revisions](#revision). When a deployment is created, all of the necessary infrastructure (e.g. database, containers, secrets store) are automatically provisioned. See the [architecture diagram](#architecture) below for more details.
+
+See the [how-to guide](../deployment/cloud.md#create-new-deployment) for creating a new deployment.
+
+## Revision
+
+A revision is an iteration of a [deployment](#deployment). When a new deployment is created, an initial revision is automatically created. To deploy new code changes or update environment variable configurations for a deployment, a new revision must be created. When a revision is created, a new container image is built automatically.
+
+See the [how-to guide](../deployment/cloud.md#create-new-revision) for creating a new revision.
+
+## Asynchronous Deployment
+
+Infrastructure for [deployments](#deployment) and [revisions](#revision) are provisioned and deployed asynchronously. They are not deployed immediately after submission. Currently, deployment can take up to several minutes.
+
+## Architecture
+
+!!! warning "Subject to Change"
+    The LangGraph Cloud deployment architecture may change in the future.
+
+A high-level diagram of a LangGraph Cloud deployment.
+
+![diagram](langgraph_cloud_architecture.png)

docs/docs/cloud/deployment/cloud.md

@@ -2,9 +2,10 @@
 
 LangGraph Cloud is available within <a href="https://www.langchain.com/langsmith" target="_blank">LangSmith</a>. To deploy a LangGraph Cloud API, navigate to the <a href="https://smith.langchain.com/" target="_blank">LangSmith UI</a>.
 
-## Setup GitHub Repository
+## Prerequisites
 
-LangGraph Cloud applications are deployed from GitHub repositories. Configure and upload a LangGraph Cloud application to a GitHub repository in order to deploy it to LangGraph Cloud.
+1. LangGraph Cloud applications are deployed from GitHub repositories. Configure and upload a LangGraph Cloud application to a GitHub repository in order to deploy it to LangGraph Cloud.
+1. [Verify that the LangGraph API runs locally](test_locally.md). If the API does not build and run successfully (i.e. `langgraph up`), deploying to LangGraph Cloud will fail as well.
 
 ## Create New Deployment
 
@@ -29,7 +30,7 @@ Starting from the <a href="https://smith.langchain.com/" target="_blank">LangSmi
 
 ## Create New Revision
 
-When [creating a new deployment](#create-a-new-deployment), a new revision is created by default. Subsequent revisions can be created to deploy new code changes.
+When [creating a new deployment](#create-new-deployment), a new revision is created by default. Subsequent revisions can be created to deploy new code changes.
 
 Starting from the <a href="https://smith.langchain.com/" target="_blank">LangSmith UI</a>...
 
@@ -45,8 +46,33 @@ Starting from the <a href="https://smith.langchain.com/" target="_blank">LangSmi
         1. Update the value of existing secrets or environment variables.
 1. Select `Submit`. After a few seconds, the `New Revision` modal will close and the new revision will be queued for deployment.
 
-## Asynchronous Deployment
+## View Build and Deployment Logs
 
-New [deployments](#create-new-deployment) and [revisions](#create-new-revision) are provisioned and deployed asynchronously. They are not deployed immediately after submission. Currently, deployment can take up to several minutes.
+Build and deployment logs are available for each revision.
 
-The `Deployment` view continually updates the status of pending revisions.
+Starting from the `Deployment` view...
+
+1. Select the desired revision from the `Revisions` table. A panel slides open from the right-hand side and the `Build` tab is selected by default, which displays build logs for the revision.
+1. In the panel, select the `Deploy` tab to view deployment logs for the revision.
+1. Within the `Deploy` tab, adjust the date/time range picker as needed. By default, the date/time range picker is set to the `Last 15 minutes`.
+
+## Interrupt Revision
+
+Interrupting a revision will stop deployment of the revision.
+
+!!! warning "Undefined Behavior"
+    Interrupted revisions have undefined behavior. This is only useful if you need to deploy a new revision and you already have a revision "stuck" in progress. In the future, this feature may be removed.
+
+Starting from the `Deployment` view...
+
+1. Select the menu icon (three dots) on the right-hand side of the row for the desired revision from the `Revisions` table.
+1. Select `Interrupt` from the menu.
+1. A modal will appear. Review the confirmation message. Select `Interrupt revision`.
+
+## Delete Deployment
+
+Starting from the <a href="https://smith.langchain.com/" target="_blank">LangSmith UI</a>...
+
+1. In the left-hand navigation panel, select `Deployments`. The `Deployments` view contains a list of existing LangGraph Cloud deployments.
+1. Select the menu icon (three dots) on the right-hand side of the row for the desired deployment and select `Delete`.
+1. A `Confirmation` modal will appear. Select `Delete`.

docs/docs/cloud/deployment/self_hosted.md

@@ -1,3 +1,35 @@
 # How to Self-Host LangGraph Cloud API
 
-Coming soon...
+!!! warning "Enterprise License Required"
+    Self-hosting LangGraph Cloud API requires a license key. Please contact sales@langchain.dev for more details.
+
+LangGraph Cloud APIs can be self-hosted with a valid LangGraph Cloud license key. Self-hosted deployments are built with Docker and deployed with Helm (on Kubernetes) or with Docker Compose. Ensure that the [Docker CLI](https://docs.docker.com/engine/reference/commandline/cli/) is installed.
+
+LangGraph Cloud license key should be passed to the service as an environment variable named LANGGRAPH_CLOUD_LICENSE_KEY.
+
+## Build Docker Image
+
+1. Follow the [How-to Guide](setup.md) for setting up a LangGraph application for deployment. Your LangGraph application will vary from the example in the How-to Guide. However, ensure that the [LangGraph API configuration file](../reference/cli.md#configuration-file) is created.
+1. Install the [LangGraph CLI](../reference/cli.md#installation).
+1. Run the following LangGraph CLI `build` command to build a Docker image. Specify the image tag (`-t`) and other desired [options](../reference/cli.md#build).
+
+        langgraph build -t tag_name
+
+!!! info "Build Platform"
+    When building the Docker image, ensure that the image is built for the platform of the target Kubernetes cluster: `langgraph build -t tag_name --platform linux/amd64,linux/arm64`
+
+## Self-Host on Kubernetes
+
+This section is for self-hosting LangGraph Cloud API on Kubernetes via Helm. A Kubernetes cluster must be provisioned before proceeding with these steps. The public Helm chart for LangGraph Cloud is available [here](https://github.com/langchain-ai/helm/tree/main/charts/langgraph-cloud).
+
+1. Publish the built Docker image to a repository that can be accessed by the target Kubernetes cluster.
+1. Ensure that the [Helm client](https://github.com/helm/helm?tab=readme-ov-file#install) is installed.
+1. Make note of all environment variables that are needed for the application. These values will need to be set in the Helm `values` YAML configuration.
+1. Follow [these instructions](https://github.com/langchain-ai/helm/tree/main/charts/langgraph-cloud#readme) to configure the Helm chart and deploy to Kubernetes.
+
+## Self-Host with Docker
+
+!!! warning "Under Construction"
+    This section of the documentation is in progress.
+
+Docker Compose can be used to deploy LangGraph Cloud to the compute infrastructure of your choice (e.g. VM).

docs/docs/cloud/deployment/setup.md

@@ -1,12 +1,23 @@
 # How to Set Up a LangGraph Application for Deployment
 
-A LangGraph application must be configured with a [LangGraph API configuration file](../reference/cli.md#configuration-file) in order to be deployed to LangGraph Cloud (or to be self-hosted). This how-to guide discusses the basic steps to setup a LangGraph application for deployment.
+A LangGraph application must be configured with a [LangGraph API configuration file](../reference/cli.md#configuration-file) in order to be deployed to LangGraph Cloud (or to be self-hosted). This how-to guide discusses the basic steps to setup a LangGraph application for deployment using `requirements.txt` to specify project dependencies. If you prefer using poetry for dependency management, check out [this how-to guide](./setup_pyproject.md) on using `pyproject.toml` for LangGraph Cloud.
+
+The final repo structure will look something like this:
+
+```bash
+my-app/
+|-- requirements.txt    # package dependencies
+|-- .env                # environment variables
+|-- openai_agent.py     # code for an agent
+|-- anthropic_agent.py  # code for another agent
+|-- langgraph.json      # configuration file for LangGraph
+```
 
 After each step, an example file directory is provided to demonstrate how code can be organized.
 
 ## Specify Dependencies
 
-Dependencies can optionally be specified in one of the following files: `pyproject.toml`, `setup.py`, or `requirements.txt`. If neither of these files is created, then dependencies can be specified later in the [LangGraph API configuration file](#create-langgraph-api-config).
+Dependencies can optionally be specified in one of the following files: `pyproject.toml`, `setup.py`, or `requirements.txt`. If none of these files is created, then dependencies can be specified later in the [LangGraph API configuration file](#create-langgraph-api-config).
 
 Example `requirements.txt` file:
 ```
@@ -28,6 +39,7 @@ Example `.env` file:
 ```
 MY_ENV_VAR_1=foo
 MY_ENV_VAR_2=bar
+OPENAI_API_KEY=key
 ```
 
 Example file directory:
@@ -39,7 +51,7 @@ my-app/
 
 ## Define Graphs
 
-Implement your graphs! Graphs can be defined in a single file or multiple files. Make note of the variable names of each [CompiledGraph](../../../reference/graphs/#compiledgraph) to be included in the LangGraph application. The variable names will be used later when creating the [LangGraph API configuration file](../reference/cli.md#configuration-file).
+Implement your graphs! Graphs can be defined in a single file or multiple files. Make note of the variable names of each [CompiledGraph][compiledgraph] to be included in the LangGraph application. The variable names will be used later when creating the [LangGraph API configuration file](../reference/cli.md#configuration-file).
 
 Example `openai_agent.py` file:
 ```python
@@ -77,20 +89,24 @@ Example `langgraph.json` file:
 ```json
 {
     "dependencies": [
-        "./my-app"
+        "."
     ],
     "graphs": {
         "openai_agent": "./openai_agent.py:agent",
         "anthropic_agent": "./anthropic_agent.py:agent"
     },
-    "env": ".env"
+    "env": "./.env"
 }
 ```
 
 Note that the variable name of the `CompiledGraph` appears at the end of the value of each subkey in the top-level `graphs` key (i.e. `:<variable_name>`).
 
+!!! warning "Configuration Location"
+    The LangGraph API configuration file must be placed in a directory that is at the same level or higher than the Python files that contain compiled graphs and associated dependencies.
+
 Example file directory:
-```
+
+```bash
 my-app/
 |-- requirements.txt
 |-- .env
@@ -102,3 +118,7 @@ my-app/
 ## Upload to GitHub
 
 To deploy the LangGraph application to LangGraph Cloud, the code must be uploaded to a GitHub repository.
+
+## Next
+
+After you setup your repo, it's time to [deploy your app](./cloud.md).

docs/docs/cloud/deployment/setup_pyproject.md

@@ -0,0 +1,157 @@
+# How to Set Up a LangGraph Application for Deployment
+
+A LangGraph application must be configured with a [LangGraph API configuration file](../reference/cli.md#configuration-file) in order to be deployed to LangGraph Cloud (or to be self-hosted). This how-to guide discusses the basic steps to setup a LangGraph application for deployment using `pyproject.toml` to define your package's dependencies. If you prefer using `requirements.txt` for dependency management, check out [this how-to guide](./setup.md).
+
+The final repo structure will look something like this:
+
+```bash
+my-app/
+├── my_agent # all project code lies within here
+│   ├── __init__.py
+│   └── agent.py # code for your graph
+│-- .env # environment variables
+│-- langgraph.json  # configuration file for LangGraph
+└── pyproject.toml # dependencies for your project
+```
+
+After each step, an example file directory is provided to demonstrate how code can be organized.
+
+## Specify Dependencies
+
+Dependencies can optionally be specified in one of the following files: `pyproject.toml`, `setup.py`, or `requirements.txt`. If none of these files is created, then dependencies can be specified later in the [LangGraph API configuration file](#create-langgraph-api-config).
+
+Example `pyproject.toml` file:
+
+```toml
+[tool.poetry]
+name = "my-agent"
+version = "0.0.1"
+description = "An excellent agent build for LangGraph cloud."
+authors = ["Polly the parrot <1223+polly@users.noreply.github.com>"]
+license = "MIT"
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = ">=3.9.0,<3.13"
+langgraph = "^0.1.0"
+langchain-fireworks = "^0.1.3"
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+```
+
+Example file directory:
+
+```bash
+my-app/
+├── my_agent
+│   ├── __init__.py
+│   └── agent.py
+└── pyproject.toml   # Python packages required for your graph
+```
+
+## Specify Environment Variables
+
+Environment variables can optionally be specified in a file (e.g. `.env`). See the [Environment Variables reference](../reference/env_var.md) to configure additional variables for a deployment.
+
+Example `.env` file:
+
+```
+MY_ENV_VAR_1=foo
+MY_ENV_VAR_2=bar
+FIREWORKS_API_KEY=key
+```
+
+Example file directory:
+
+```bash
+my-app/
+├── my_agent
+│   ├── __init__.py
+│   └── agent.py
+|-- .env             # file with environment variables
+└── pyproject.toml
+```
+
+## Define Graphs
+
+Implement your graphs! Graphs can be defined in a single file or multiple files. Make note of the variable names of each [CompiledGraph][compiledgraph] to be included in the LangGraph application. The variable names will be used later when creating the [LangGraph API configuration file](../reference/cli.md#configuration-file).
+
+Example `agent.py` file:
+
+```python
+# my_agent/agent.py
+from langchain_fireworks import ChatFireworks
+from langgraph.graph import END, StateGraph, add_messages
+from typing_extensions import TypedDict, Annotated
+
+model = ChatFireworks(model="accounts/fireworks/models/firefunction-v2", temperature=0)
+
+class State(TypedDict):
+    messages: Annotated[list, add_messages]
+
+graph_workflow = StateGraph(State)
+
+graph_workflow.add_node("agent", model)
+graph_workflow.add_edge("agent", END)
+graph_workflow.set_entry_point("agent")
+
+agent = graph_workflow.compile()
+```
+
+!!! warning "Assign `CompiledGraph` to Variable"
+    The build process for LangGraph Cloud requires that the `CompiledGraph` object be assigned to a variable at the top-level of a Python module.
+
+Example file directory:
+
+```bash
+my-app/
+├── my_agent
+│   ├── __init__.py
+│   └── agent.py # code for your graph
+|-- .env
+└── pyproject.toml
+```
+
+## Create LangGraph API Config
+
+Create a [LangGraph API configuration file](../reference/cli.md#configuration-file) called `langgraph.json`. See the [LangGraph CLI reference](../reference/cli.md#configuration-file) for detailed explanations of each key in the JSON object of the configuration file.
+
+Example `langgraph.json` file:
+
+```json
+{
+  "dependencies": ["."],
+  "graphs": {
+    "my_fantastic_agent": "./my_agent/agent.py:agent"
+  },
+  "env": "./.env"
+}
+```
+
+Note that the variable name of the `CompiledGraph` appears at the end of the value of each subkey in the top-level `graphs` key (i.e. `:<variable_name>`).
+
+!!! warning "Configuration Location"
+    The LangGraph API configuration file must be placed in a directory that is at the same level or higher than the Python files that contain compiled graphs and associated dependencies.
+
+Example file directory:
+
+```bash
+my-app/
+├── my_agent
+│   ├── __init__.py
+│   └── agent.py # code for your graph
+│-- .env
+│-- langgraph.json      # configuration file for LangGraph
+└── pyproject.toml
+```
+
+## Upload to GitHub
+
+To deploy the LangGraph application to LangGraph Cloud, the code must be uploaded to a GitHub repository.
+
+## Next
+
+After you setup your repo, it's time to [deploy your app](./cloud.md).

docs/docs/cloud/deployment/studio.md

@@ -1,44 +0,0 @@
-# How to Test with LangGraph Studio
-
-LangGraph applications can be tested with LangGraph Studio. LangGraph Studio is a robust UI for testing and exercising functionality of the graphs in a LangGraph application. The LangGraph Studio UI connects directly to a LangGraph Cloud deployments or to a local LangGraph API instance.
-
-The LangGraph Studio UI is available within <a href="https://www.langchain.com/langsmith" target="_blank">LangSmith</a>. To test a LangGraph application, navigate to the <a href="https://smith.langchain.com/" target="_blank">LangSmith UI</a>.
-
-## Test Cloud Deployment
-
-The LangGraph Studio UI connects directly to LangGraph Cloud deployments.
-
-Starting from the <a href="https://smith.langchain.com/" target="_blank">LangSmith UI</a>...
-
-1. In the left-hand navigation panel, select `Deployments`. The `Deployments` view contains a list of existing LangGraph Cloud deployments.
-1. Select an existing deployment to test with LangGraph Studio.
-1. In the top-right corner, select `Open LangGraph Studio`.
-1. [Invoke an assistant](#invoke-assistant) or [view an existing thread](#view-thread).
-
-## Test Local Instance
-
-The LangGraph Studio UI connects directly to local LangGraph API instances. This is helpful for quickly iterating and testing during the development process.
-
-Starting from the <a href="https://smith.langchain.com/" target="_blank">LangSmith UI</a>...
-
-1. Find the hostname of the local LangGraph API instance. For example, `http://localhost:9123`.
-1. Navigate to the URL `/studio/thread/` and set the `baseUrl` query parameter to the hostname. For example, `https://smith.langchain.com/studio/thread?baseUrl=http://localhost:9123`.
-1. [Invoke an assistant](#invoke-assistant) or [view an existing thread](#view-thread).
-
-## Invoke Assistant
-
-1. The LangGraph Studio UI displays a visualization of the selected assistant.
-    1. In the top-right dropdown menu of the left-hand pane, select an assistant.
-    1. In the bottom of the left-hand pane, edit the `Input` and `Configure` the assistant.
-    1. Select `Submit` to invoke the selected assistant.
-1. View output of the invocation in the right-hand pane.
-
-## View Thread
-
-1. In the top of the right-hand pane, select the `New Thread` dropdown menu to view existing threads.
-1. View the state of the thread (i.e. the output) in the right-hand pane.
-1. To create a new thread, select `+ New Thread`.
-
-## Edit Thread State
-
-The LangGraph Studio UI contains features for editing thread state. Explore these features in the right-hand pane. Select the `Edit` icon, modify the desired state, and then select `Fork` to invoke the assistant with the updated state.

docs/docs/cloud/deployment/test_locally.md

@@ -0,0 +1,99 @@
+# How to test a LangGraph app locally
+
+This guide assumes you have a LangGraph app correctly set up with a proper configuration file and a corresponding compiled graph, and that you have a proper LangChain API key.
+
+Testing locally ensures that there are no errors or conflicts with Python dependencies and confirms that the configuration file is specified correctly.
+
+## Setup
+
+Install the proper packages:
+
+```shell
+pip install langgraph-cli
+```
+
+Ensure you have an API key, which you can create from the LangSmith UI (Settings > API Keys). This is required to authenticate that you have LangGraph Cloud access. After you have saved the key to a safe place, place the following line in your `.env` file:
+
+```python
+LANGCHAIN_API_KEY = *********
+```
+
+## Start the API server
+
+Once you have downloaded the CLI, you can run the following command to start the API server for local testing:
+
+```shell
+langgraph up
+```
+
+This will start up the LangGraph API server locally. If this runs successfully, you should see something like:
+
+```shell
+Ready!
+- API: http://localhost:8123
+2024-06-26 19:20:41,056:INFO:uvicorn.access 127.0.0.1:44138 - "GET /ok HTTP/1.1" 200
+```
+
+### Interact with the server
+
+We can now interact with the API server using the LangGraph SDK. First, we need to start our client, select our assistant (in this case a graph we called "agent", make sure to select the proper assistant you wish to test).
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    # only pass the url argument to get_client() if you changed the default port when calling langgraph up
+    client = get_client()
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    // only set the apiUrl if you changed the default port when calling langgraph up
+    const client = new Client();
+    const assistantId = "agent"
+    const thread = await client.threads.create();
+    ```
+
+Now we can invoke our graph to ensure it is working. Make sure to change the input to match the proper schema for your graph. 
+
+=== "Python"
+
+    ```python
+    input = {"messages": [{"role": "human", "content": "what's the weather in sf"}]}
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant_id,
+        input=input,
+        stream_mode="updates",
+    ):
+        print(f"Receiving new event of type: {chunk.event}...")
+        print(chunk.data)
+        print("\n\n")
+    ```
+=== "Javascript"
+
+    ```js
+    const input = { "messages": [{ "role": "human", "content": "what's the weather in sf"}] }
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantId,
+      {
+        input: input,
+        streamMode: "updates",
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(`Receiving new event of type: ${chunk.event}...`);
+      console.log(chunk.data);
+      console.log("\n\n");
+    }
+    ```
+
+If your graph works correctly, you should see your graph output displayed in the console. Of course, there are many more ways you might need to test your graph, for a full list of commands you can send with the SDK, see the [Python](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/python_sdk_ref/) and [JS/TS](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/) references.

docs/docs/cloud/how-tos/enqueue_concurrent.md

@@ -0,0 +1,183 @@
+## Enqueue
+
+This guide assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide](../concepts/api.md#double-texting).
+
+The guide covers the `enqueue` option for double texting, which adds the interruptions to a queue and executes them in the order they are received by the client. Below is a quick example of using the `enqueue` option.
+
+
+First, we will define a quick helper function for printing out JS model outputs (you can skip this if using Python):
+
+```js
+function prettyPrint(m) {
+  const padded = " " + m['type'] + " ";
+  const sepLen = Math.floor((80 - padded.length) / 2);
+  const sep = "=".repeat(sepLen);
+  const secondSep = sep + (padded.length % 2 ? "=" : "");
+  
+  console.log(`${sep}${padded}${secondSep}`);
+  console.log("\n\n");
+  console.log(m.content);
+}
+```
+
+Then, let's import our required packages and instantiate our client, assistant, and thread.
+
+=== "Python"
+
+    ```python
+    import asyncio
+
+    import httpx
+    from langchain_core.messages import convert_to_messages
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+    
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    const assistantId = "agent";
+    const thread = await client.threads.create();
+    ```
+
+Now let's start two runs, with the second interrupting the first one with a multitask strategy of "enqueue":
+
+=== "Python"
+
+    ```python
+    first_run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "human", "content": "what's the weather in sf?"}]},
+    )
+    second_run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "human", "content": "what's the weather in nyc?"}]},
+        multitask_strategy="enqueue",
+    )
+    ```
+
+=== "Javascript"
+
+    ```js
+    const firstRun = await client.runs.create(
+      thread["thread_id"],
+      assistantId,
+      input={"messages": [{"role": "human", "content": "what's the weather in sf?"}]},
+    )
+
+    const secondRun = await client.runs.create(
+      thread["thread_id"],
+      assistantId,
+      input={"messages": [{"role": "human", "content": "what's the weather in nyc?"}]},
+      multitask_strategy="enqueue",
+    )
+    ```
+
+Verify that the thread has data from both runs:
+
+=== "Python"
+
+    ```python
+    # wait until the second run completes
+    await client.runs.join(thread["thread_id"], second_run["run_id"])
+
+    state = await client.threads.get_state(thread["thread_id"])
+
+    for m in convert_to_messages(state["values"]["messages"]):
+        m.pretty_print()
+    ```
+
+=== "Javascript"
+
+    ```js
+    await client.runs.join(thread["thread_id"], secondRun["run_id"]);
+
+    const state = await client.threads.getState(thread["thread_id"]);
+
+    for (const m of state["values"]["messages"]) {
+      prettyPrint(m);
+    }
+    ```
+
+Output:
+
+    ================================ Human Message =================================
+    
+    what's the weather in sf?
+    ================================== Ai Message ==================================
+    
+    [{'id': 'toolu_01Dez1sJre4oA2Y7NsKJV6VT', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
+    Tool Calls:
+      tavily_search_results_json (toolu_01Dez1sJre4oA2Y7NsKJV6VT)
+     Call ID: toolu_01Dez1sJre4oA2Y7NsKJV6VT
+      Args:
+        query: weather in san francisco
+    ================================= Tool Message =================================
+    Name: tavily_search_results_json
+    
+    [{"url": "https://www.accuweather.com/en/us/san-francisco/94103/weather-forecast/347629", "content": "Get the current and future weather conditions for San Francisco, CA, including temperature, precipitation, wind, air quality and more. See the hourly and 10-day outlook, radar maps, alerts and allergy information."}]
+    ================================== Ai Message ==================================
+    
+    According to AccuWeather, the current weather conditions in San Francisco are:
+    
+    Temperature: 57°F (14°C)
+    Conditions: Mostly Sunny
+    Wind: WSW 10 mph
+    Humidity: 72%
+    
+    The forecast for the next few days shows partly sunny skies with highs in the upper 50s to mid 60s F (14-18°C) and lows in the upper 40s to low 50s F (9-11°C). Typical mild, dry weather for San Francisco this time of year.
+    
+    Some key details from the AccuWeather forecast:
+    
+    Today: Mostly sunny, high of 62°F (17°C)
+    Tonight: Partly cloudy, low of 49°F (9°C) 
+    Tomorrow: Partly sunny, high of 59°F (15°C)
+    Saturday: Mostly sunny, high of 64°F (18°C)
+    Sunday: Partly sunny, high of 61°F (16°C)
+    
+    So in summary, expect seasonable spring weather in San Francisco over the next several days, with a mix of sun and clouds and temperatures ranging from the upper 40s at night to the low 60s during the days. Typical dry conditions with no rain in the forecast.
+    ================================ Human Message =================================
+    
+    what's the weather in nyc?
+    ================================== Ai Message ==================================
+    
+    [{'text': 'Here are the current weather conditions and forecast for New York City:', 'type': 'text'}, {'id': 'toolu_01FFft5Sx9oS6AdVJuRWWcGp', 'input': {'query': 'weather in new york city'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
+    Tool Calls:
+      tavily_search_results_json (toolu_01FFft5Sx9oS6AdVJuRWWcGp)
+     Call ID: toolu_01FFft5Sx9oS6AdVJuRWWcGp
+      Args:
+        query: weather in new york city
+    ================================= Tool Message =================================
+    Name: tavily_search_results_json
+    
+    [{"url": "https://www.weatherapi.com/", "content": "{'location': {'name': 'New York', 'region': 'New York', 'country': 'United States of America', 'lat': 40.71, 'lon': -74.01, 'tz_id': 'America/New_York', 'localtime_epoch': 1718734479, 'localtime': '2024-06-18 14:14'}, 'current': {'last_updated_epoch': 1718733600, 'last_updated': '2024-06-18 14:00', 'temp_c': 29.4, 'temp_f': 84.9, 'is_day': 1, 'condition': {'text': 'Sunny', 'icon': '//cdn.weatherapi.com/weather/64x64/day/113.png', 'code': 1000}, 'wind_mph': 2.2, 'wind_kph': 3.6, 'wind_degree': 158, 'wind_dir': 'SSE', 'pressure_mb': 1025.0, 'pressure_in': 30.26, 'precip_mm': 0.0, 'precip_in': 0.0, 'humidity': 63, 'cloud': 0, 'feelslike_c': 31.3, 'feelslike_f': 88.3, 'windchill_c': 28.3, 'windchill_f': 82.9, 'heatindex_c': 29.6, 'heatindex_f': 85.3, 'dewpoint_c': 18.4, 'dewpoint_f': 65.2, 'vis_km': 16.0, 'vis_miles': 9.0, 'uv': 7.0, 'gust_mph': 16.5, 'gust_kph': 26.5}}"}]
+    ================================== Ai Message ==================================
+    
+    According to the weather data from WeatherAPI:
+    
+    Current Conditions in New York City (as of 2:00 PM local time):
+    - Temperature: 85°F (29°C)
+    - Conditions: Sunny
+    - Wind: 2 mph (4 km/h) from the SSE
+    - Humidity: 63%
+    - Heat Index: 85°F (30°C)
+    
+    The forecast shows sunny and warm conditions persisting over the next few days:
+    
+    Today: Sunny, high of 85°F (29°C)
+    Tonight: Clear, low of 68°F (20°C)
+    Tomorrow: Sunny, high of 88°F (31°C) 
+    Thursday: Mostly sunny, high of 90°F (32°C)
+    Friday: Partly cloudy, high of 87°F (31°C)
+    
+    So New York City is experiencing beautiful sunny weather with seasonably warm temperatures in the mid-to-upper 80s Fahrenheit (around 30°C). Humidity is moderate in the 60% range. Overall, ideal late spring/early summer conditions for being outdoors in the city over the next several days.
+

docs/docs/cloud/how-tos/human_in_the_loop_breakpoint.md

@@ -0,0 +1,103 @@
+# How to Add Breakpoints
+
+When creating LangGraph agents, it is often nice to add a human-in-the-loop component.
+This can be helpful when giving them access to tools.
+Often in these situations you may want to manually approve an action before taking.
+
+This can be in several ways, but the primary supported way is to add an "interrupt" before a node is executed.
+This interrupts execution at that node.
+You can then resume from that spot to continue.  
+
+## Setup
+
+### Code for your graph
+
+In this how-to we use a simple ReAct style hosted graph (you can see the full code for defining it [here](../../how-tos/human_in_the_loop/breakpoints.ipynb)). The important thing is that there are two nodes (one named `agent` that calls the LLM, and one named `action` that calls the tool), and a routing function from `agent` that determines whether to call `action` next or just end the graph run (the `action` node always calls the `agent` node after execution).
+
+### SDK Initialization
+
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+    client = get_client(url="whatever-your-deployment-url-is")
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    const assistantId = "agent"
+    const thread = await client.threads.create();
+    ```
+
+## Adding a breakpoint
+
+We now want to add a breakpoint in our graph run, which we will do before a tool is called.
+We can do this by adding `interrupt_before=["action"]`, which tells us to interrupt before calling the action node.
+We can do this either when compiling the graph or when kicking off a run.
+Here we will do it when kicking of a run, if you would like to to do it at compile time you need to edit the python file where your graph is defined and add the `interrupt_before` parameter when you call `.compile`.
+
+First let's access our hosted LangGraph instance through the SDK:
+
+And, now let's compile it with a breakpoint before the tool node:
+
+=== "Python"
+
+    ```python
+    input = {"messages": [{"role": "human", "content": "what's the weather in sf"}]}
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant_id,
+        input=input,
+        stream_mode="updates",
+        interrupt_before=["action"],
+    ):
+        print(f"Receiving new event of type: {chunk.event}...")
+        print(chunk.data)
+        print("\n\n")
+    ```
+=== "Javascript"
+
+    ```js
+    const input = { "messages": [{ "role": "human", "content": "what's the weather in sf"}] }
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantId,
+      {
+        input: input,
+        streamMode: "updates",
+        interruptBefore: ["action"],
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(`Receiving new event of type: ${chunk.event}...`);
+      console.log(chunk.data);
+      console.log("\n\n");
+    }
+    ```
+
+Output:
+
+    Receiving new event of type: metadata...
+    {'run_id': '3b77ef83-687a-4840-8858-0371f91a92c3'}
+    
+    
+    
+    Receiving new event of type: data...
+    {'agent': {'messages': [{'content': [{'id': 'toolu_01HwZqM1ptX6E15A5LAmyZTB', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-e5d17791-4d37-4ad2-815f-a0c4cba62585', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in san francisco'}, 'id': 'toolu_01HwZqM1ptX6E15A5LAmyZTB'}], 'invalid_tool_calls': []}]}}
+    
+    
+    
+    Receiving new event of type: end...
+    None
+    
+    
+    
+

docs/docs/cloud/how-tos/human_in_the_loop_edit_state.md

@@ -0,0 +1,182 @@
+# How to Edit State of a Deployed Graph
+
+When creating LangGraph agents, it is often nice to add a human-in-the-loop component. This can be helpful when giving them access to tools. Often in these situations you may want to edit the graph state before continuing (for example, to edit what tool is being called, or how it is being called).
+
+This can be in several ways, but the primary supported way is to add an "interrupt" before a node is executed. This interrupts execution at that node. You can then use update_state to update the state, and then resume from that spot to continue.
+
+## Setup
+
+We are not going to show the full code for the graph we are hosting, but you can see it [here](../../how-tos/human_in_the_loop/edit-graph-state.ipynb#build-the-agent) if you want to. Once this graph is hosted, we are ready to invoke it and wait for user input. 
+
+### SDK initialization
+
+First, we need to setup our client so that we can communicate with our hosted graph:
+
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+    client = get_client(url="whatever-your-deployment-url-is")
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    const assistantId = "agent";
+    const thread = await client.threads.create();
+    ```
+
+## Editing state
+
+### Initial invocation
+
+Now let's invoke our graph, making sure to interrupt before the `action` node.
+
+=== "Python"
+
+    ```python
+    input = { 'messages':[{ "role":"user", "content":"search for weather in SF" }] }
+
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant_id,
+        input=input,
+        stream_mode="updates",
+        interrupt_before=["action"],
+    ):
+        if chunk.data and chunk.event != "metadata": 
+            print(chunk.data)
+    ```
+
+=== "Javascript"
+
+    ```js
+    const input = {"messages": [{ "role": "human", "content": "search for weather in SF"}] }
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantId,
+      {
+        input: input,
+        streamMode: "updates",
+        interruptBefore: ["action"],
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.data && chunk.event !== "metadata") {
+        console.log(chunk.data);
+      }
+    }
+    ```
+
+Output:
+
+    {'agent': {'messages': [{'content': [{'text': "Certainly! I'll search for the current weather in San Francisco for you using the search function. Here's how I'll do that:", 'type': 'text'}, {'id': 'toolu_01KEJMBFozSiZoS4mAcPZeqQ', 'input': {'query': 'current weather in San Francisco'}, 'name': 'search', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-6dbb0167-f8f6-4e2a-ab68-229b2d1fbb64', 'example': False, 'tool_calls': [{'name': 'search', 'args': {'query': 'current weather in San Francisco'}, 'id': 'toolu_01KEJMBFozSiZoS4mAcPZeqQ'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+
+
+### Edit the state
+
+Now, let's assume we actually meant to search for the weather in Sidi Frej (another city with the initials SF). We can edit the state to properly reflect that:
+
+
+=== "Python"
+
+    ```python
+    # First, lets get the current state
+    current_state = await client.threads.get_state(thread['thread_id'])
+
+    # Let's now get the last message in the state
+    # This is the one with the tool calls that we want to update
+    last_message = current_state['values']['messages'][-1]
+
+    # Let's now update the args for that tool call
+    last_message['tool_calls'][0]['args'] = {'query': 'current weather in Sidi Frej'}
+
+    # Let's now call `update_state` to pass in this message in the `messages` key
+    # This will get treated as any other update to the state
+    # It will get passed to the reducer function for the `messages` key
+    # That reducer function will use the ID of the message to update it
+    # It's important that it has the right ID! Otherwise it would get appended
+    # as a new message
+    await client.threads.update_state(thread['thread_id'], {"messages": last_message})
+    ```
+
+=== "Javascript"
+
+    ```js
+    // First, lets get the current state
+    const currentState = await client.threads.getState(thread['thread_id']);
+
+    // Let's now get the last message in the state
+    // This is the one with the tool calls that we want to update
+    let lastMessage = currentState['values']['messages'][-1];
+
+    // Let's now update the args for that tool call
+    lastMessage['tool_calls'][0]['args'] = {'query': 'current weather in Sidi Frej'};
+
+    // Let's now call `update_state` to pass in this message in the `messages` key
+    // This will get treated as any other update to the state
+    // It will get passed to the reducer function for the `messages` key
+    // That reducer function will use the ID of the message to update it
+    // It's important that it has the right ID! Otherwise it would get appended
+    // as a new message
+    await client.threads.updateState(thread['thread_id'], {values:{"messages": lastMessage}});
+    ```
+
+Output:
+
+    {'configurable': {'thread_id': '88d58d3f-4151-47a9-a8e0-e42fdd3527b8',
+      'thread_ts': '1ef3274b-a809-6913-8002-91536ce6554d'}}
+
+
+
+### Resume invocation
+
+Now we can resume our graph run but with the updated state:
+
+
+=== "Python"
+
+    ```python
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant_id,
+        input=None,
+        stream_mode="updates",
+    ):
+        if chunk.data and chunk.event != "metadata": 
+            print(chunk.data)
+    ```
+=== "Javascript"
+
+    ```js
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantId,
+      {
+        input: null,
+        streamMode: "updates",
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.data && chunk.event !== "metadata") {
+        console.log(chunk.data);
+      }
+    }
+    ```
+
+Output:
+
+    {'action': {'messages': [{'content': '["I looked up: current weather in Sidi Frej. Result: It\'s sunny in San Francisco, but you better look out if you\'re a Gemini 😈."]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '1161b8d1-bee4-4188-9be8-698aecb69f10', 'tool_call_id': 'toolu_01KEJMBFozSiZoS4mAcPZeqQ'}]}}
+    {'agent': {'messages': [{'content': [{'text': 'I apologize for the confusion in my search query. It seems the search function interpreted "SF" as "Sidi Frej" instead of "San Francisco" as we intended. Let me search again with the full city name to get the correct information:', 'type': 'text'}, {'id': 'toolu_0111rrwgfAcmurHZn55qjqTR', 'input': {'query': 'current weather in San Francisco'}, 'name': 'search', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-b8c25779-cfb4-46fc-a421-48553551242f', 'example': False, 'tool_calls': [{'name': 'search', 'args': {'query': 'current weather in San Francisco'}, 'id': 'toolu_0111rrwgfAcmurHZn55qjqTR'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+    {'action': {'messages': [{'content': '["I looked up: current weather in San Francisco. Result: It\'s sunny in San Francisco, but you better look out if you\'re a Gemini 😈."]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '6bc632ae-5ee6-4d01-9532-79c524a2d443', 'tool_call_id': 'toolu_0111rrwgfAcmurHZn55qjqTR'}]}}
+    {'agent': {'messages': [{'content': "Now, based on the search results, I can provide you with information about the current weather in San Francisco:\n\nThe weather in San Francisco is currently sunny. \n\nIt's worth noting that the search result included an unusual comment about Gemini, which doesn't seem directly related to the weather. This might be due to the search engine including some astrological information or a joke in its results. However, for the purpose of weather information, we can focus on the fact that it's sunny in San Francisco right now.\n\nIs there anything else you'd like to know about the weather in San Francisco or any other location?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-227a042b-dd97-476e-af32-76a3703af5d8', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+
+
+As you can see it now looks up the current weather in Sidi Frej (although our dummy search node still returns results for SF because we don't actually do a search in this example, we just return the same "It's sunny in San Francisco ..." result every time).

docs/docs/cloud/how-tos/human_in_the_loop_time_travel.md

@@ -0,0 +1,226 @@
+# How to Replay and Branch from Prior States
+
+With LangGraph Cloud you have the ability to return to any of your prior states and either re-run the graph to reproduce issues noticed during testing, or branch out in a different way from what was originally done in the prior states. In this guide we will show a quick example of how to rerun past states and how to branch off from previous states as well.
+
+## Setup
+
+We are not going to show the full code for the graph we are hosting, but you can see it [here](../../how-tos/human_in_the_loop/time-travel.ipynb#build-the-agent) if you want to. Once this graph is hosted, we are ready to invoke it and wait for user input. 
+
+### SDK initialization
+
+First, we need to setup our client so that we can communicate with our hosted graph:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+    client = get_client(url="whatever-your-deployment-url-is")
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    const assistantId = agent;
+    const thread = await client.threads.create();
+    ```
+
+## Replay a state
+
+### Initial invocation
+
+Before replaying a state - we need to create states to replay from! In order to do this, let's invoke our graph with a simple message:
+
+=== "Python"
+
+    ```python
+    input = { 'messages':[{ "role":"user", "content":"Please search the weather in SF" }] }
+
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant_id, # graph_id
+        input=input,
+        stream_mode="updates",
+    ):
+        if chunk.data and chunk.event != "metadata": 
+            print(chunk.data)
+    ```
+
+=== "Javascript"
+
+    ```js
+    const input = {"messages": [{ "role": "human", "content": "Please search the weather in SF"}] }
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantId,
+      {
+        input: input,
+        streamMode: "updates",
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.data && chunk.event !== "metadata") {
+        console.log(chunk.data);
+      }
+    }
+    ```
+    
+Output:
+
+    {'agent': {'messages': [{'content': [{'text': "Certainly! I'll use the search function to look up the current weather in San Francisco for you. Let me do that now.", 'type': 'text'}, {'id': 'toolu_011vroKUtWU7SBdrngpgpFMn', 'input': {'query': 'current weather in San Francisco'}, 'name': 'search', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ee639877-d97d-40f8-96dc-d0d1ae22d203', 'example': False, 'tool_calls': [{'name': 'search', 'args': {'query': 'current weather in San Francisco'}, 'id': 'toolu_011vroKUtWU7SBdrngpgpFMn'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+    {'action': {'messages': [{'content': '["I looked up: current weather in San Francisco. Result: It\'s sunny in San Francisco, but you better look out if you\'re a Gemini 😈."]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '7bad0e72-5ebe-4b08-9b8a-b99b0fe22fb7', 'tool_call_id': 'toolu_011vroKUtWU7SBdrngpgpFMn'}]}}
+    {'agent': {'messages': [{'content': "Based on the search results, I can provide you with information about the current weather in San Francisco:\n\nThe weather in San Francisco is currently sunny. This is great news for outdoor activities and enjoying the city's beautiful sights.\n\nIt's worth noting that the search result included an unusual comment about Geminis, which isn't typically part of a weather report. This might be due to the search engine including some astrological information or a joke in its results. However, for the purpose of answering your question about the weather, we can focus on the fact that it's sunny in San Francisco.\n\nIf you need any more specific information about the weather in San Francisco, such as temperature, wind speed, or forecast for the coming days, please let me know, and I'd be happy to search for that information for you.", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-dbac539a-33c8-4f0c-9e20-91f318371e7c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+
+
+Now let's get our list of states, and invoke from the third state (right before the tool get called):
+
+
+=== "Python"
+
+    ```python
+    states = await client.threads.get_history(thread['thread_id'])
+
+    # We can confirm that this state is correct by checking the 'next' attribute and seeing that it is the tool call node
+    state_to_replay = states[2]
+    print(state_to_replay['next'])
+    ```
+
+=== "Javascript"
+
+    ```js
+    const states = await client.threads.getHistory(thread['thread_id']);
+
+    // We can confirm that this state is correct by checking the 'next' attribute and seeing that it is the tool call node
+    const stateToReplay = states[2];
+    console.log(stateToReplay['next']);
+    ```
+
+Output:
+
+    ['action']
+
+
+
+To rerun from a state, we need to pass in the `checkpoint_id` into the config of the run like follows:
+
+=== "Python"
+
+    ```python
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant_id, # graph_id
+        input=None,
+        stream_mode="updates",
+        config={"configurable": {"thread_ts": state_to_replay['checkpoint_id']}}
+    ):
+        if chunk.data and chunk.event != "metadata": 
+            print(chunk.data)
+    ```
+
+=== "Javascript"
+
+    ```js
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantId,
+      {
+        input: null,
+        streamMode: "updates",
+        config: {"configurable": {"thread_ts": stateToReplay['checkpoint_id']}},
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.data && chunk.event !== "metadata") {
+        console.log(chunk.data);
+      }
+    }
+    ```
+
+Output:
+
+    {'action': {'messages': [{'content': '["I looked up: current weather in San Francisco. Result: It\'s sunny in San Francisco, but you better look out if you\'re a Gemini 😈."]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': 'eba650e5-400e-4938-8508-f878dcbcc532', 'tool_call_id': 'toolu_011vroKUtWU7SBdrngpgpFMn'}]}}
+    {'agent': {'messages': [{'content': "Based on the search results, I can provide you with information about the current weather in San Francisco:\n\nThe weather in San Francisco is currently sunny. This is great news if you're planning any outdoor activities or simply want to enjoy a pleasant day in the city.\n\nIt's worth noting that the search result included an unusual comment about Geminis, which doesn't seem directly related to the weather. This appears to be a playful or humorous addition to the weather report, possibly from the source where this information was obtained.\n\nIs there anything else you'd like to know about the weather in San Francisco or any other information you need?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-bc6dca3f-a1e2-4f59-a69b-fe0515a348bb', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+
+
+As we can see, the graph restarted from the tool node with the same input as our original graph run.
+
+## Branch off from previous state
+
+Using LangGraph's checkpointing, you can do more than just replay past states. You can branch off previous locations to let the agent explore alternate trajectories or to let a user "version control" changes in a workflow.
+
+Let's show how to do this to edit the state at a particular point in time. Let's update the state to change the input to the tool
+
+=== "Python"
+
+    ```python
+    # Let's now get the last message in the state
+    # This is the one with the tool calls that we want to update
+    last_message = state_to_replay['values']['messages'][-1]
+
+    # Let's now update the args for that tool call
+    last_message['tool_calls'][0]['args'] = {'query': 'current weather in SF'}
+
+    new_state = await client.threads.update_state(thread['thread_id'],{"messages":[last_message]},checkpoint_id=state_to_replay['checkpoint_id'])
+    ```
+
+=== "Javascript"
+
+    ```js
+    // Let's now get the last message in the state
+    // This is the one with the tool calls that we want to update
+    let lastMessage = stateToReplay['values']['messages'][-1];
+
+    // Let's now update the args for that tool call
+    lastMessage['tool_calls'][0]['args'] = {'query': 'current weather in SF'};
+
+    const newState = await client.threads.updateState(thread['thread_id'],{values:{"messages":[lastMessage]},checkpointId:stateToReplay['checkpoint_id']});
+    ```
+
+Now we can rerun our graph with this new config, starting from the `new_state`, which is a branch of our `state_to_replay`:
+
+=== "Python"
+
+    ```python
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant["assistant_id"], # graph_id
+        input=None,
+        stream_mode="updates",
+        config={"configurable": {"thread_ts": new_state['configurable']['thread_ts']}}
+    ):
+        if chunk.data and chunk.event != "metadata": 
+            print(chunk.data)
+    ```
+
+=== "Javascript"
+
+    ```js
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistant["assistant_id"],
+      {
+        input: null,
+        streamMode: "updates",
+        config: {"configurable": {"thread_ts": newState['configurable']['thread_ts']}},
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.data && chunk.event !== "metadata") {
+        console.log(chunk.data);
+      }
+    }
+    ```
+
+Output:
+
+
+    {'action': {'messages': [{'content': '["I looked up: current weather in SF. Result: It\'s sunny in San Francisco, but you better look out if you\'re a Gemini 😈."]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '2baf9941-4fda-4081-9f87-d76795d289f1', 'tool_call_id': 'toolu_011vroKUtWU7SBdrngpgpFMn'}]}}
+    {'agent': {'messages': [{'content': "Based on the search results, I can provide you with information about the current weather in San Francisco (SF):\n\nThe weather in San Francisco is currently sunny. This means it's a clear day with plenty of sunshine. \n\nIt's worth noting that the specific temperature wasn't provided in the search result, but sunny weather in San Francisco typically means comfortable temperatures. San Francisco is known for its mild climate, so even on sunny days, it's often not too hot.\n\nThe search result also included a playful reference to astrological signs, mentioning Gemini. However, this is likely just a joke or part of the search engine's presentation and not related to the actual weather conditions.\n\nIs there any specific information about the weather in San Francisco you'd like to know more about? I'd be happy to perform another search if you need details on temperature, wind conditions, or the forecast for the coming days.", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-a83de52d-ed18-4402-9384-75c462485743', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+
+
+As we can see, the search query changed from San Francisco to SF, just as we had hoped!

docs/docs/cloud/how-tos/human_in_the_loop_user_input.md

@@ -0,0 +1,166 @@
+# How to Wait for User Input
+
+One of the main human-in-the-loop interaction patterns is waiting for human input. A key use case involves asking the user clarifying questions. One way to accomplish this is simply go to the `END` node and exit the graph. Then, any user response comes back in as fresh invocation of the graph. This is basically just creating a chatbot architecture.
+
+The issue with this is it is tough to resume back in a particular point in the graph. Often times the agent is halfway through some process, and just needs a bit of a user input. Although it is possible to design your graph in such a way where you have a `conditional_entry_point` to route user messages back to the right place, that is not super scalable (as it essentially involves having a routing function that can end up almost anywhere).
+
+A separate way to do this is to have a node explicitly for getting user input. This is easy to implement in a notebook setting - you just put an `input()` call in the node. But that isn't exactly production ready.
+
+Luckily, LangGraph makes it possible to do similar things in a production way. The basic idea is:
+
+- Set up a node that represents human input. This can have specific incoming/outgoing edges (as you desire). There shouldn't actually be any logic inside this node.
+- Add a breakpoint before the node. This will stop the graph before this node executes (which is good, because there's no real logic in it anyways)
+- Use `.update_state` to update the state of the graph. Pass in whatever human response you get. The key here is to use the `as_node` parameter to apply this update **as if you were that node**. This will have the effect of making it so that when you resume execution next it resumes as if that node just acted, and not from the beginning.
+
+## Setup
+
+We are not going to show the full code for the graph we are hosting, but you can see it [here](../../how-tos/human_in_the_loop/wait-user-input.ipynb#build-the-agent) if you want to. Once this graph is hosted, we are ready to invoke it and wait for user input. 
+
+### SDK initialization
+
+First, we need to setup our client so that we can communicate with our hosted graph:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+    client = get_client(url="whatever-your-deployment-url-is")
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    const assistantId = "agent";
+    const thread = await client.threads.create();
+    ```
+
+## Waiting for user input
+
+### Initial invocation
+
+Now, let's invoke our graph by interrupting before `ask_human` node:
+
+=== "Python"
+
+    ```python
+    input = { 'messages':[{ "role":"user", "content":"Use the search tool to ask the user where they are, then look up the weather there" }] }
+
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant_id,
+        input=input,
+        stream_mode="updates",
+        interrupt_before=["ask_human"],
+    ):
+        if chunk.data and chunk.event != "metadata": 
+            print(chunk.data)
+    ```
+=== "Javascript"
+
+    ```js
+    const input = { "messages":[{ "role":"human", "content": "Use the search tool to ask the user where they are, then look up the weather there"}] }
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantId,
+      {
+        input: input,
+        streamMode: "updates",
+        interruptBefore: ["ask_human"],
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.data && chunk.event !== "metadata") {
+        console.log(chunk.data);
+      }
+    }
+    ```
+    
+Output:
+
+    {'agent': {'messages': [{'content': [{'text': "Certainly! I'll use the AskHuman function to ask the user about their location, and then I'll use the search function to look up the weather for that location. Let's start by asking the user where they are.", 'type': 'text'}, {'id': 'toolu_01RFahzYPvnPWTb2USk2RdKR', 'input': {'question': 'Where are you currently located?'}, 'name': 'AskHuman', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-a8422215-71d3-4093-afb4-9db141c94ddb', 'example': False, 'tool_calls': [{'name': 'AskHuman', 'args': {'question': 'Where are you currently located?'}, 'id': 'toolu_01RFahzYPvnPWTb2USk2RdKR'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+
+
+### Adding user input to state
+
+We now want to update this thread with a response from the user. We then can kick off another run.
+
+Because we are treating this as a tool call, we will need to update the state as if it is a response from a tool call. In order to do this, we will need to check the state to get the ID of the tool call.
+
+
+=== "Python"
+
+    ```python
+    state = await client.threads.get_state(thread['thread_id'])
+    tool_call_id = state['values']['messages'][-1]['tool_calls'][0]['id']
+
+    # We now create the tool call with the id and the response we want
+    tool_message = [{"tool_call_id": tool_call_id, "type": "tool", "content": "san francisco"}]
+
+    await client.threads.update_state(thread['thread_id'], {"messages": tool_message}, as_node="ask_human")
+    ```
+
+=== "Javascript"
+
+    ```js
+    const state = await client.threads.getState(thread['thread_id']);
+    const toolCallId = state['values']['messages'][-1]['tool_calls'][0]['id'];
+
+    # We now create the tool call with the id and the response we want
+    const toolMessage = [{"tool_call_id": toolCallId, "type": "tool", "content": "san francisco"}];
+
+    await client.threads.updateState(thread['thread_id'], {values: {"messages": toolMessage}, asNode:"ask_human"})
+    ```
+
+Output:
+
+    {'configurable': {'thread_id': '10d0ee61-db47-48fc-a58c-109a1e68cd73',
+      'thread_ts': '1ef32729-3cc3-6647-8002-14dcb621b46e'}}
+
+
+
+### Invoking after receiving human input
+
+We can now tell the agent to continue. We can just pass in None as the input to the graph, since no additional input is needed:
+
+=== "Python"
+
+    ```python
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant_id, # graph_id
+        input=None,
+        stream_mode="updates",
+    ):
+        if chunk.data and chunk.event != "metadata": 
+            print(chunk.data)
+    ```
+=== "Javascript"
+
+    ```js
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantId,
+      {
+        input: null,
+        streamMode: "updates",
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.data && chunk.event !== "metadata") {
+        console.log(chunk.data);
+      }
+    }
+    ```
+
+Output:
+
+    {'agent': {'messages': [{'content': [{'text': "Thank you for letting me know that you're in San Francisco. Now, I'll use the search function to look up the weather in San Francisco.", 'type': 'text'}, {'id': 'toolu_01K57ofmgG2wyJ8tYJjbq5k7', 'input': {'query': 'current weather in San Francisco'}, 'name': 'search', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-241baed7-db5e-44ce-ac3c-56431705c22b', 'example': False, 'tool_calls': [{'name': 'search', 'args': {'query': 'current weather in San Francisco'}, 'id': 'toolu_01K57ofmgG2wyJ8tYJjbq5k7'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+    {'action': {'messages': [{'content': '["I looked up: current weather in San Francisco. Result: It\'s sunny in San Francisco, but you better look out if you\'re a Gemini 😈."]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '8b699b95-8546-4557-8e66-14ea71a15ed8', 'tool_call_id': 'toolu_01K57ofmgG2wyJ8tYJjbq5k7'}]}}
+    {'agent': {'messages': [{'content': "Based on the search results, I can provide you with information about the current weather in San Francisco:\n\nThe weather in San Francisco is currently sunny. It's a beautiful day in the city! \n\nHowever, I should note that the search result included an unusual comment about Gemini zodiac signs. This appears to be either a joke or potentially irrelevant information added by the search engine. For accurate and detailed weather information, you might want to check a reliable weather service or app for San Francisco.\n\nIs there anything else you'd like to know about the weather or San Francisco?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-b4d7309f-f849-46aa-b6ef-475bcabd2be9', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+

docs/docs/cloud/how-tos/index.md

@@ -0,0 +1,73 @@
+---
+hide:
+  - toc
+---
+
+# How-to Guides
+
+Welcome to the LangGraph Cloud how-to guides! These guides provide practical, step-by-step instructions for accomplishing key tasks in LangGraph Cloud.
+
+## Deployment
+
+LangGraph Cloud gives you best in class observability, testing, and hosting services. Read more about them in these how to guides:
+
+- [How to set up app for deployment (requirements.txt)](../deployment/setup.md)
+- [How to set up app for deployment (pyproject.toml)](../deployment/setup_pyproject.md)
+- [How to test locally](../deployment/test_locally.md)
+- [How to deploy to LangGraph cloud](../deployment/cloud.md)
+- [How to self-host](../deployment/self_hosted.md)
+
+
+## Streaming
+
+Streaming the results of your LLM application is vital for ensuring a good user experience, especially when your graph may call multiple models and take a long time to fully complete a run. Read about how to stream values from your graph in these how to guides:
+
+- [How to stream values](./stream_values.md)
+- [How to stream updates](./stream_updates.md)
+- [How to stream messages](./stream_messages.md)
+- [How to stream events](./stream_events.md)
+- [How to stream in debug mode](./stream_debug.md)
+- [How to stream multiple modes](./stream_multiple.md)
+
+## Double-texting
+
+Graph execution can take a while, and sometimes users may change their mind about the input they wanted to send before their original input has finished running. For example, a user might notice a typo in their original request and will edit the prompt and resend it. Deciding what to do in these cases is important for ensuring a smooth user experience and preventing your graphs from behaving in unexpected ways. The following how-to guides provide information on the various options LangGraph Cloud gives you for dealing with double-texting:
+
+- [How to use the interrupt option](./interrupt_concurrent.md)
+- [How to use the rollback option](./rollback_concurrent.md)
+- [How to use the reject option](./reject_concurrent.md)
+- [How to use the enqueue option](./enqueue_concurrent.md)
+
+## Human-in-the-loop
+
+When creating complex graphs, leaving every decision up to the LLM can be dangerous, especially when the decisions involve invoking certain tools or accessing specific documents. To remedy this, LangGraph allows you to insert human-in-the-loop behavior to ensure your graph does not have undesired outcomes. Read more about the different ways you can add human-in-the-loop capabilities to your LangGraph Cloud projects in these how-to guides:
+
+- [How to add a breakpoint](./human_in_the_loop_breakpoint.md)
+- [How to wait for user input](./human_in_the_loop_user_input.md)
+- [How to edit graph state](./human_in_the_loop_edit_state.md)
+- [How to replay and branch from prior states](./human_in_the_loop_time_travel.md)
+
+## LangGraph Studio
+
+LangGraph Studio is a built-in UI for visualizing, testing, and debugging your agents.
+
+- [How to enter LangGraph Studio](./test_deployment.md)
+- [How to test your graph in LangGraph Studio](./invoke_studio.md)
+- [Interact with threads in LangGraph Studio](./threads_studio.md)
+
+## Different Types of Runs:
+
+LangGraph Cloud supports multiple types of runs besides streaming runs.
+
+- [How to run an agent in the background](cloud_examples/background_run.ipynb)
+- [How to run multiple agents in the same thread](cloud_examples/same-thread.ipynb)
+- [How to create cron jobs](cloud_examples/cron_jobs.ipynb)
+- [How to create stateless runs](cloud_examples/stateless_runs.ipynb)
+
+## Other 
+
+Other guides that may prove helpful!
+
+- [How to configure agents](cloud_examples/configuration_cloud.ipynb)
+- [How to convert LangGraph calls to LangGraph cloud calls](cloud_examples/langgraph_to_langgraph_cloud.ipynb)
+- [How to integrate webhooks](cloud_examples/webhooks.ipynb)

docs/docs/cloud/how-tos/interrupt_concurrent.md

@@ -0,0 +1,176 @@
+## Interrupt
+
+This guide assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide](../concepts/api.md#double-texting).
+
+The guide covers the `interrupt` option for double texting, which interrupts the prior run of the graph and starts a new one with the double-text. This option does not delete the first run, but rather keeps it in the database but sets its status to `interrupted`. Below is a quick example of using the `interrupt` option.
+
+First, we will define a quick helper function for printing out JS model outputs (you can skip this if using Python):
+
+```js
+function prettyPrint(m) {
+  const padded = " " + m['type'] + " ";
+  const sepLen = Math.floor((80 - padded.length) / 2);
+  const sep = "=".repeat(sepLen);
+  const secondSep = sep + (padded.length % 2 ? "=" : "");
+  
+  console.log(`${sep}${padded}${secondSep}`);
+  console.log("\n\n");
+  console.log(m.content);
+}
+```
+
+Now, let's import our required packages and instantiate our client, assistant, and thread.
+
+=== "Python"
+
+    ```python
+    import asyncio
+
+    from langchain_core.messages import convert_to_messages
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    const assistantId = "agent";
+    const thread = await client.threads.create();
+    ```
+
+Now we can start our two runs and join the second on euntil it has completed:
+
+=== "Python"
+
+    ```python
+    # the first run will be interrupted
+    interrupted_run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "human", "content": "what's the weather in sf?"}]},
+    )
+    await asyncio.sleep(2)
+    run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "human", "content": "what's the weather in nyc?"}]},
+        multitask_strategychrom="interrupt",
+    )
+    # wait until the second run completes
+    await client.runs.join(thread["thread_id"], run["run_id"])
+    ```
+
+=== "Javascript"
+
+    ```js
+    // the first run will be interrupted
+    let interruptedRun = await client.runs.create(
+      thread["thread_id"],
+      assistantId,
+      { input: { messages: [{ role: "human", content: "what's the weather in sf?" }] } }
+    );
+    await new Promise(resolve => setTimeout(resolve, 2000)); 
+
+    let run = await client.runs.create(
+      thread["thread_id"],
+      assistantId,
+      { 
+        input: { messages: [{ role: "human", content: "what's the weather in nyc?" }] },
+        multitaskStrategy: "interrupt" 
+      }
+    );
+
+    // wait until the second run completes
+    await client.runs.join(thread["thread_id"], run["run_id"]);
+    ```
+
+We can see that the thread has partial data from the first run + data from the second run
+
+
+=== "Python"
+
+    ```python
+    state = await client.threads.get_state(thread["thread_id"])
+
+    for m in convert_to_messages(state["values"]["messages"]):
+        m.pretty_print()
+    ```
+
+=== "Javascript"
+
+    ```js
+    const state = await client.threads.getState(thread["thread_id"]);
+
+    for (const m of state['values']['messages']) {
+      prettyPrint(m);
+    }
+    ```
+
+Output:
+
+    ================================ Human Message =================================
+    
+    what's the weather in sf?
+    ================================== Ai Message ==================================
+    
+    [{'id': 'toolu_01MjNtVJwEcpujRGrf3x6Pih', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
+    Tool Calls:
+      tavily_search_results_json (toolu_01MjNtVJwEcpujRGrf3x6Pih)
+     Call ID: toolu_01MjNtVJwEcpujRGrf3x6Pih
+      Args:
+        query: weather in san francisco
+    ================================= Tool Message =================================
+    Name: tavily_search_results_json
+    
+    [{"url": "https://www.wunderground.com/hourly/us/ca/san-francisco/KCASANFR2002/date/2024-6-18", "content": "High 64F. Winds W at 10 to 20 mph. A few clouds from time to time. Low 49F. Winds W at 10 to 20 mph. Temp. San Francisco Weather Forecasts. Weather Underground provides local & long-range weather ..."}]
+    ================================ Human Message =================================
+    
+    what's the weather in nyc?
+    ================================== Ai Message ==================================
+    
+    [{'id': 'toolu_01KtE1m1ifPLQAx4fQLyZL9Q', 'input': {'query': 'weather in new york city'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
+    Tool Calls:
+      tavily_search_results_json (toolu_01KtE1m1ifPLQAx4fQLyZL9Q)
+     Call ID: toolu_01KtE1m1ifPLQAx4fQLyZL9Q
+      Args:
+        query: weather in new york city
+    ================================= Tool Message =================================
+    Name: tavily_search_results_json
+    
+    [{"url": "https://www.accuweather.com/en/us/new-york/10021/june-weather/349727", "content": "Get the monthly weather forecast for New York, NY, including daily high/low, historical averages, to help you plan ahead."}]
+    ================================== Ai Message ==================================
+    
+    The search results provide weather forecasts and information for New York City. Based on the top result from AccuWeather, here are some key details about the weather in NYC:
+    
+    - This is a monthly weather forecast for New York City for the month of June.
+    - It includes daily high and low temperatures to help plan ahead.
+    - Historical averages for June in NYC are also provided as a reference point.
+    - More detailed daily or hourly forecasts with precipitation chances, humidity, wind, etc. can be found by visiting the AccuWeather page.
+    
+    So in summary, the search provides a convenient overview of the expected weather conditions in New York City over the next month to give you an idea of what to prepare for if traveling or making plans there. Let me know if you need any other details!
+
+
+Verify that the original, interrupted run was interrupted
+
+=== "Python"
+
+    ```python
+    print((await client.runs.get(thread["thread_id"], interrupted_run["run_id"]))["status"])
+    ```
+
+=== "Javascript"
+
+    ```js
+    console.log((await client.runs.get(thread['thread_id'], interruptedRun["run_id"]))["status"])
+    ```
+
+Output:
+
+    'interrupted'
+

docs/docs/cloud/how-tos/invoke_studio.md

@@ -0,0 +1,13 @@
+# Invoke Assistant
+
+The LangGraph Studio lets you test different configurations and inputs to your graph. The UI allows you to see exactly how your 
+
+1. The LangGraph Studio UI displays a visualization of the selected assistant.
+    1. In the top-right dropdown menu of the left-hand pane, select an assistant.
+    1. In the bottom of the left-hand pane, edit the `Input` and `Configure` the assistant.
+    1. Select `Submit` to invoke the selected assistant.
+1. View output of the invocation in the right-hand pane.
+
+The following GIF shows these exact steps being carried out:
+
+![Using LangGraph Studio](./img/studio_input.gif)

docs/docs/cloud/how-tos/reject_concurrent.md

@@ -0,0 +1,155 @@
+## Reject
+
+This guide assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide][double-texting].
+
+The guide covers the `reject` option for double texting, which rejects the new run of the graph by throwing an error and continues with the original run until completion. Below is a quick example of using the `reject` option.
+
+First, we will define a quick helper function for printing out JS model outputs (you can skip this if using Python):
+
+```js
+function prettyPrint(m) {
+  const padded = " " + m['type'] + " ";
+  const sepLen = Math.floor((80 - padded.length) / 2);
+  const sep = "=".repeat(sepLen);
+  const secondSep = sep + (padded.length % 2 ? "=" : "");
+  
+  console.log(`${sep}${padded}${secondSep}`);
+  console.log("\n\n");
+  console.log(m.content);
+}
+```
+
+Now, let's import our required packages and instantiate our client, assistant, and thread.
+
+=== "Python"
+
+    ```python
+    import httpx
+    from langchain_core.messages import convert_to_messages
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    const assistantId = "agent";
+    const thread = await client.threads.create();
+    ```
+
+Now we can run a thread and try to run a second one with the "reject" option, which should fail since we have already started a run:
+
+
+=== "Python"
+
+    ```python
+    run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "human", "content": "what's the weather in sf?"}]},
+    )
+    try:
+        await client.runs.create(
+            thread["thread_id"],
+            assistant_id,
+            input={
+                "messages": [{"role": "human", "content": "what's the weather in nyc?"}]
+            },
+            multitask_strategy="reject",
+        )
+    except httpx.HTTPStatusError as e:
+        print("Failed to start concurrent run", e)
+    ```
+
+=== "Javascript"
+
+    ```js
+    const run = await client.runs.create(
+      thread["thread_id"],
+      assistantId,
+      input={"messages": [{"role": "human", "content": "what's the weather in sf?"}]},
+    );
+    
+    try {
+      await client.runs.create(
+        thread["thread_id"],
+        assistantId,
+        { 
+          input: {"messages": [{"role": "human", "content": "what's the weather in nyc?"}]},
+          multitask_strategy:"reject"
+        },
+      );
+    } catch (e) {
+      console.error("Failed to start concurrent run", e);
+    }
+    ```
+
+    Failed to start concurrent run Client error '409 Conflict' for url 'http://localhost:8123/threads/f9e7088b-8028-4e5c-88d2-9cc9a2870e50/runs'
+    For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/409
+
+
+We can verify that the original thread finished executing:
+
+=== "Python"
+
+    ```python
+    # wait until the original run completes
+    await client.runs.join(thread["thread_id"], run["run_id"])
+
+    state = await client.threads.get_state(thread["thread_id"])
+
+    for m in convert_to_messages(state["values"]["messages"]):
+        m.pretty_print()
+    ```
+
+=== "Javascript"
+
+    ```js
+    await client.runs.join(thread["thread_id"], run["run_id"]);
+
+    const state = await client.threads.getState(thread["thread_id"]);
+
+    for (const m of state["values"]["messages"]) {
+      prettyPrint(m);
+    }
+    ```
+
+Output:
+
+    ================================ Human Message =================================
+    
+    what's the weather in sf?
+    ================================== Ai Message ==================================
+    
+    [{'id': 'toolu_01CyewEifV2Kmi7EFKHbMDr1', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
+    Tool Calls:
+      tavily_search_results_json (toolu_01CyewEifV2Kmi7EFKHbMDr1)
+     Call ID: toolu_01CyewEifV2Kmi7EFKHbMDr1
+      Args:
+        query: weather in san francisco
+    ================================= Tool Message =================================
+    Name: tavily_search_results_json
+    
+    [{"url": "https://www.accuweather.com/en/us/san-francisco/94103/june-weather/347629", "content": "Get the monthly weather forecast for San Francisco, CA, including daily high/low, historical averages, to help you plan ahead."}]
+    ================================== Ai Message ==================================
+    
+    According to the search results from Tavily, the current weather in San Francisco is:
+    
+    The average high temperature in San Francisco in June is around 65°F (18°C), with average lows around 54°F (12°C). June tends to be one of the cooler and foggier months in San Francisco due to the marine layer of fog that often blankets the city during the summer months.
+    
+    Some key points about the typical June weather in San Francisco:
+    
+    - Mild temperatures with highs in the 60s F and lows in the 50s F
+    - Foggy mornings that often burn off to sunny afternoons
+    - Little to no rainfall, as June falls in the dry season
+    - Breezy conditions, with winds off the Pacific Ocean
+    - Layers are recommended for changing weather conditions
+    
+    So in summary, you can expect mild, foggy mornings giving way to sunny but cool afternoons in San Francisco this time of year. The marine layer keeps temperatures moderate compared to other parts of California in June.
+

docs/docs/cloud/how-tos/rollback_concurrent.md

@@ -0,0 +1,161 @@
+## Rollback
+
+This guide assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide][double-texting].
+
+The guide covers the `rollback` option for double texting, which interrupts the prior run of the graph and starts a new one with the double-text. This option is very similar to the `interrupt` option, but in this case the first run is completely deleted from the database and cannot be restarted. Below is a quick example of using the `rollback` option.
+
+First, we will define a quick helper function for printing out JS model outputs (you can skip this if using Python):
+
+```js
+function prettyPrint(m) {
+  const padded = " " + m['type'] + " ";
+  const sepLen = Math.floor((80 - padded.length) / 2);
+  const sep = "=".repeat(sepLen);
+  const secondSep = sep + (padded.length % 2 ? "=" : "");
+  
+  console.log(`${sep}${padded}${secondSep}`);
+  console.log("\n\n");
+  console.log(m.content);
+}
+```
+
+Now, let's import our required packages and instantiate our client, assistant, and thread.
+
+=== "Python"
+
+    ```python
+    import asyncio
+
+    import httpx
+    from langchain_core.messages import convert_to_messages
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    const assistantId = "agent";
+    const thread = await client.threads.create();
+    ```
+
+Now let's run a thread with the multitask parameter set to "rollback":
+
+=== "Python"
+
+    ```python
+    # the first run will be rolled back
+    rolled_back_run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "human", "content": "what's the weather in sf?"}]},
+    )
+    await asyncio.sleep(2)
+    run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "human", "content": "what's the weather in nyc?"}]},
+        multitask_strategy="rollback",
+    )
+    # wait until the second run completes
+    await client.runs.join(thread["thread_id"], run["run_id"])
+    ```
+
+=== "Javascript"
+
+    ```js
+    // the first run will be interrupted
+    let rolledBackRun = await client.runs.create(
+      thread["thread_id"],
+      assistantId,
+      { input: { messages: [{ role: "human", content: "what's the weather in sf?" }] } }
+    );
+    await new Promise(resolve => setTimeout(resolve, 2000)); 
+
+    let run = await client.runs.create(
+      thread["thread_id"],
+      assistant_id,
+      { 
+        input: { messages: [{ role: "human", content: "what's the weather in nyc?" }] },
+        multitaskStrategy: "rollback" 
+      }
+    );
+
+    // wait until the second run completes
+    await client.runs.join(thread["thread_id"], run["run_id"]);
+    ```
+
+We can see that the thread has data only from the second run
+
+=== "Python"
+
+    ```python
+    state = await client.threads.get_state(thread["thread_id"])
+
+    for m in convert_to_messages(state["values"]["messages"]):
+        m.pretty_print()
+    ```
+
+=== "Javascript"
+
+    ```js
+    const state = await client.threads.getState(thread["thread_id"]);
+
+    for (const m of state['values']['messages']) {
+      prettyPrint(m);
+    }
+    ```
+
+Output:
+
+    ================================ Human Message =================================
+    
+    what's the weather in nyc?
+    ================================== Ai Message ==================================
+    
+    [{'id': 'toolu_01JzPqefao1gxwajHQ3Yh3JD', 'input': {'query': 'weather in nyc'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
+    Tool Calls:
+      tavily_search_results_json (toolu_01JzPqefao1gxwajHQ3Yh3JD)
+     Call ID: toolu_01JzPqefao1gxwajHQ3Yh3JD
+      Args:
+        query: weather in nyc
+    ================================= Tool Message =================================
+    Name: tavily_search_results_json
+    
+    [{"url": "https://www.weatherapi.com/", "content": "{'location': {'name': 'New York', 'region': 'New York', 'country': 'United States of America', 'lat': 40.71, 'lon': -74.01, 'tz_id': 'America/New_York', 'localtime_epoch': 1718734479, 'localtime': '2024-06-18 14:14'}, 'current': {'last_updated_epoch': 1718733600, 'last_updated': '2024-06-18 14:00', 'temp_c': 29.4, 'temp_f': 84.9, 'is_day': 1, 'condition': {'text': 'Sunny', 'icon': '//cdn.weatherapi.com/weather/64x64/day/113.png', 'code': 1000}, 'wind_mph': 2.2, 'wind_kph': 3.6, 'wind_degree': 158, 'wind_dir': 'SSE', 'pressure_mb': 1025.0, 'pressure_in': 30.26, 'precip_mm': 0.0, 'precip_in': 0.0, 'humidity': 63, 'cloud': 0, 'feelslike_c': 31.3, 'feelslike_f': 88.3, 'windchill_c': 28.3, 'windchill_f': 82.9, 'heatindex_c': 29.6, 'heatindex_f': 85.3, 'dewpoint_c': 18.4, 'dewpoint_f': 65.2, 'vis_km': 16.0, 'vis_miles': 9.0, 'uv': 7.0, 'gust_mph': 16.5, 'gust_kph': 26.5}}"}]
+    ================================== Ai Message ==================================
+    
+    The weather API results show that the current weather in New York City is sunny with a temperature of around 85°F (29°C). The wind is light at around 2-3 mph from the south-southeast. Overall it looks like a nice sunny summer day in NYC.
+
+
+Verify that the original, rolled back run was deleted
+
+=== "Python"
+
+    ```python
+    try:
+        await client.runs.get(thread["thread_id"], rolled_back_run["run_id"])
+    except httpx.HTTPStatusError as _:
+        print("Original run was correctly deleted")
+    ```
+
+=== "Javascript"
+
+    ```js
+    try {
+      await client.runs.get(thread["thread_id"], rolledBackRun["run_id"]);
+    } catch (e) {
+      console.log("Original run was correctly deleted");
+    }
+    ```
+
+Output:
+
+    Original run was correctly deleted
+

docs/docs/cloud/how-tos/stream_debug.md

@@ -0,0 +1,161 @@
+# How to stream debug events
+
+This guide covers how to stream debug events from your graph (`stream_mode="debug"`).
+
+First let's set up our client and thread:
+
+=== "Python"
+    
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    # create thread
+    thread = await client.threads.create()
+    print(thread)
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    // create thread
+    const thread = await client.threads.create();
+    console.log(thread)
+    ```
+
+
+Output:
+
+    {'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3',
+     'created_at': '2024-06-21T22:10:27.696862+00:00',
+     'updated_at': '2024-06-21T22:10:27.696862+00:00',
+     'metadata': {}}
+
+Streaming debug events produces responses containing `type` and `timestamp` keys. Debug events correspond to different steps in the graph's execution (e.g. `task`, `task_result`, `checkpoint`).
+
+
+=== "Python"
+
+    ```python
+    # create input
+    input = {
+        "messages": [
+            {
+                "role": "human",
+                "content": "What's the weather in SF?",
+            }
+        ]
+    }
+
+    # stream debug
+    async for chunk in client.runs.stream(
+        thread_id=thread["thread_id"],
+        assistant_id="agent",
+        input=input,
+        stream_mode="debug",
+    ):
+        print(f"Receiving new event of type: {chunk.event}...")
+        print(chunk.data)
+        print("\n\n")
+    ```
+
+=== "Javascript"
+
+    ```js
+    // create input
+    const input = {
+        "messages": [
+            {
+                "role": "human",
+                "content": "What's the weather in SF?",
+            }
+        ]
+    }
+
+    // stream debug
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      "agent",
+      {
+        input,
+        streamMode: "debug"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(f"Receiving new event of type: {chunk.event}...")
+      console.log(chunk.data)
+      console.log("\n\n")
+    }
+    ```
+
+Output:
+
+    Receiving new event of type: metadata...
+    {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.256850+00:00', 'step': -1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a2e-6bb6-bfff-8423bcf47561', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'messages': []}, 'metadata': {'source': 'input', 'step': -1, 'writes': {'messages': [{'role': 'human', 'content': "What's the weather in SF?"}]}}}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.259723+00:00', 'step': 0, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a35-6c86-8000-f4a85315dbeb', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}]}, 'metadata': {'source': 'loop', 'step': 0, 'writes': None}}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task', 'timestamp': '2024-06-21T22:11:09.260021+00:00', 'step': 1, 'payload': {'id': '12ab1026-a551-5f96-9ad3-43424f094774', 'name': 'agent', 'input': {'some_bytes': None, 'some_byte_array': None, 'dict_with_bytes': None, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}], 'sleep': None}, 'triggers': ['start:agent']}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task_result', 'timestamp': '2024-06-21T22:11:09.267632+00:00', 'step': 1, 'payload': {'id': '12ab1026-a551-5f96-9ad3-43424f094774', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.268469+00:00', 'step': 1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a4b-60ae-8001-dd378f965bf7', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 1, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task', 'timestamp': '2024-06-21T22:11:09.268659+00:00', 'step': 2, 'payload': {'id': '494ad427-fe8d-5654-91e6-50495a2699f5', 'name': 'tool', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}, 'triggers': ['branch:agent:should_continue:tool']}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task_result', 'timestamp': '2024-06-21T22:11:09.272916+00:00', 'step': 2, 'payload': {'id': '494ad427-fe8d-5654-91e6-50495a2699f5', 'name': 'tool', 'result': [['messages', [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}]]]}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.273113+00:00', 'step': 2, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a56-6832-8002-8ab17e662980', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}]}, 'metadata': {'source': 'loop', 'step': 2, 'writes': {'tool': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}]}}}}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task', 'timestamp': '2024-06-21T22:11:09.273192+00:00', 'step': 3, 'payload': {'id': '677de327-99b7-5d97-9bbd-0092abb62d46', 'name': 'agent', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}], 'sleep': None}, 'triggers': ['tool']}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task_result', 'timestamp': '2024-06-21T22:11:09.277262+00:00', 'step': 3, 'payload': {'id': '677de327-99b7-5d97-9bbd-0092abb62d46', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-006e1758-b1ca-4c90-9ff3-d2e75b9ca9a7', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.277519+00:00', 'step': 3, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a61-6462-8003-1316d9875b7f', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-006e1758-b1ca-4c90-9ff3-d2e75b9ca9a7', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 3, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-006e1758-b1ca-4c90-9ff3-d2e75b9ca9a7', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}
+    
+    
+    
+    Receiving new event of type: end...
+    None
+    
+    
+    
+

docs/docs/cloud/how-tos/stream_events.md

@@ -0,0 +1,298 @@
+# How to stream events
+This guide covers how to stream events from your graph (`stream_mode="events"`). Depending on the use case and user experience of your LangGraph application, your application may process event types differently.
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    # create thread
+    thread = await client.threads.create()
+    print(thread)
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    // create thread
+    const thread = await client.threads.create();
+    console.log(thread)
+    ```
+
+
+Output:
+
+
+    {'thread_id': '3f4c64e0-f792-4a5e-aa07-a4404e06e0bd',
+     'created_at': '2024-06-24T22:16:29.301522+00:00',
+     'updated_at': '2024-06-24T22:16:29.301522+00:00',
+     'metadata': {}}
+
+
+
+Streaming events produces responses containing an `event` key (in addition to other keys such as `data`). See the LangChain [`Runnable.astream_events()` reference](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable.astream_events) for all event types.
+
+
+=== "Python"
+
+    ```python
+    # create input
+    input = {
+        "messages": [
+            {
+                "role": "human",
+                "content": "What's the weather in SF?",
+            }
+        ]
+    }
+
+    # stream events
+    async for chunk in client.runs.stream(
+        thread_id=thread["thread_id"],
+        assistant_id="agent",
+        input=input,
+        stream_mode="events",
+    ):
+        print(f"Receiving new event of type: {chunk.event}...")
+        print(chunk.data)
+        print("\n\n")
+    ```
+
+=== "Javascript"
+
+    ```js
+    // create input
+    const input = {
+        "messages": [
+            {
+                "role": "human",
+                "content": "What's the weather in SF?",
+            }
+        ]
+    }
+
+    // stream events
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      "agent",
+      {
+        input,
+        streamMode: "events"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(f"Receiving new event of type: {chunk.event}...")
+      console.log(chunk.data)
+      console.log("\n\n")
+    }
+    ```
+
+Output:
+
+    Receiving new event of type: metadata...
+    {'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8'}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {'input': {'messages': [{'role': 'human', 'content': "What's the weather in SF?"}]}}, 'name': 'LangGraph', 'tags': [], 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {}, 'name': 'agent', 'tags': ['graph:step:6'], 'run_id': '7bb08493-d507-4e28-b9e6-4a5eda9d04f0', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_start', 'data': {'input': {'messages': [[{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}]]}}, 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'b', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'g', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'i', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'n', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_end', 'data': {'output': {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, 'input': {'messages': [[{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}]]}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {'input': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'name': 'should_continue', 'tags': ['seq:step:3'], 'run_id': 'c7fe4d2d-3fb8-4e53-946d-03de13527853', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': 'tool', 'input': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'run_id': 'c7fe4d2d-3fb8-4e53-946d-03de13527853', 'name': 'should_continue', 'tags': ['seq:step:3'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '7bb08493-d507-4e28-b9e6-4a5eda9d04f0', 'name': 'agent', 'tags': ['graph:step:6'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}], 'sleep': None}}, 'run_id': '7bb08493-d507-4e28-b9e6-4a5eda9d04f0', 'name': 'agent', 'tags': ['graph:step:6'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {}, 'name': 'tool', 'tags': ['graph:step:7'], 'run_id': 'f044fd3d-7271-488f-b8aa-e01572ff9112', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 7, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': 'f044fd3d-7271-488f-b8aa-e01572ff9112', 'name': 'tool', 'tags': ['graph:step:7'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 7, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': None, 'tool_call_id': 'tool_call_id'}]}}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}]}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}}, 'run_id': 'f044fd3d-7271-488f-b8aa-e01572ff9112', 'name': 'tool', 'tags': ['graph:step:7'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 7, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {}, 'name': 'agent', 'tags': ['graph:step:8'], 'run_id': '1f4f95d0-0ce1-4061-85d4-946446bbd3e5', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_start', 'data': {'input': {'messages': [[{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}]]}}, 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'n', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'd', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_end', 'data': {'output': {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, 'input': {'messages': [[{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}]]}}, 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {'input': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'name': 'should_continue', 'tags': ['seq:step:3'], 'run_id': 'f2b2dfaf-475d-422b-8bf5-02a31bcc7d1a', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': '__end__', 'input': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'run_id': 'f2b2dfaf-475d-422b-8bf5-02a31bcc7d1a', 'name': 'should_continue', 'tags': ['seq:step:3'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1f4f95d0-0ce1-4061-85d4-946446bbd3e5', 'name': 'agent', 'tags': ['graph:step:8'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}], 'sleep': None}}, 'run_id': '1f4f95d0-0ce1-4061-85d4-946446bbd3e5', 'name': 'agent', 'tags': ['graph:step:8'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}, 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'name': 'LangGraph', 'tags': [], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: end...
+    None
+    
+    
+    
+
+
+## Token-by-Token Streaming
+
+Token-by-token streaming can be implemented with the `events` streaming mode. The `on_chat_model_stream` event type should be processed to stream LLM responses token-by-token.
+
+=== "Python"
+
+    ```python
+    llm_response = ""
+
+    # stream token-by-token
+    async for chunk in client.runs.stream(
+        thread_id=thread["thread_id"],
+        assistant_id="agent",
+        input=input,
+        stream_mode="events",
+    ):
+        if (
+            chunk.event == "events" and
+            chunk.data["event"] == "on_chat_model_stream"
+        ):
+            llm_response += chunk.data["data"]["chunk"]["content"]
+            print(llm_response)
+    ```
+
+=== "Javascript"
+
+    ```js
+    const llmResponse = "";
+    // stream events
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      "agent",
+      {
+        input,
+        streamMode: "events"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.event === "events" && chunk.data.event === "on_chat_model_stream") {
+        llmResponse += chunk.data.data.chunk.content;
+        console.log(llmResponse);
+      }
+    }
+    ```
+
+Output:
+
+    b
+    be
+    beg
+    begi
+    begin
+    begine
+    beginen
+    beginend
+

docs/docs/cloud/how-tos/stream_messages.md

@@ -0,0 +1,390 @@
+# How to stream messages from your graph
+
+LangGraph Cloud supports multiple streaming modes. The main ones are:
+
+- `values`: This streaming mode streams back values of the graph. This is the **full state of the graph** after each node is called.
+- `updates`: This streaming mode streams back updates to the graph. This is the **update to the state of the graph** after each node is called.
+- `messages`: This streaming mode streams back messages - both complete messages (at the end of a node) as well as **tokens** for any messages generated inside a node. This mode is primarily meant for powering chat applications.
+
+
+This guide covers `stream_mode="messages"`.
+
+In order to use this mode, the state of the graph you are interacting with MUST have a `messages` key that is a list of messages.
+E.g., the state should look something like:
+
+=== "Python"
+
+    ```python
+    from typing import TypedDict, Annotated
+    from langgraph.graph import add_messages
+    from langchain_core.messages import AnyMessage
+
+    class State(TypedDict):
+        messages: Annotated[list[AnyMessage], add_messages]
+    ```
+
+
+Alternatively, you can use an instance or subclass of `from langgraph.graph import MessagesState` (`MessagesState` is equivalent to the implementation above).
+
+> [!NOTE]
+> LangGraph Cloud only supports hosting graphs written in Python at the moment.
+
+With `stream_mode="messages"` two things will be streamed back:
+
+- It outputs messages produced by any chat model called inside (unless tagged in a special way)
+- It outputs messages returned from nodes (to allow for nodes to return `ToolMessages` and the like
+
+First let's set up our client and thread:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    # create thread
+    thread = await client.threads.create()
+    print(thread)
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    // create thread
+    const thread = await client.threads.create();
+    console.log(thread)
+    ```
+
+Output:
+
+    {'thread_id': 'e1431c95-e241-4d1d-a252-27eceb1e5c86',
+     'created_at': '2024-06-21T15:48:59.808924+00:00',
+     'updated_at': '2024-06-21T15:48:59.808924+00:00',
+     'metadata': {}}
+
+Let's also define a helper function for better formatting of the tool calls in messages
+
+=== "Python"
+
+    ```python
+    def format_tool_calls(tool_calls):
+        if tool_calls:
+            formatted_calls = []
+            for call in tool_calls:
+                formatted_calls.append(
+                    f"Tool Call ID: {call['id']}, Function: {call['name']}, Arguments: {call['args']}"
+                )
+            return "\n".join(formatted_calls)
+        return "No tool calls"
+    ```
+
+=== "Javascript"
+
+    ```js
+    function formatToolCalls(toolCalls) {
+      if (toolCalls && toolCalls.length > 0) {
+        const formattedCalls = toolCalls.map(call => {
+          return `Tool Call ID: ${call.id}, Function: ${call.name}, Arguments: ${call.args}`;
+        });
+        return formattedCalls.join("\n");
+      }
+      return "No tool calls";
+    }
+    ```
+
+Now we can stream by messages, which will return complete messages (at the end of node execution) as well as tokens for any messages generated inside a node:
+
+=== "Python"
+
+    ```python
+    input = {"messages": [{"role": "user", "content": "what's the weather in sf"}]}
+    config = {"configurable": {"model_name": "openai"}}
+
+    async for event in client.runs.stream(
+        thread["thread_id"],
+        assistant_id="agent",
+        input=input,
+        config=config,
+        stream_mode="messages",
+    ):
+        if event.event == "metadata":
+            print(f"Metadata: Run ID - {event.data['run_id']}")
+            print("-" * 50)
+        elif event.event == "messages/partial":
+            for data_item in event.data:
+                if "role" in data_item and data_item["role"] == "user":
+                    print(f"Human: {data_item['content']}")
+                else:
+                    tool_calls = data_item.get("tool_calls", [])
+                    invalid_tool_calls = data_item.get("invalid_tool_calls", [])
+                    content = data_item.get("content", "")
+                    response_metadata = data_item.get("response_metadata", {})
+
+                    if content:
+                        print(f"AI: {content}")
+
+                    if tool_calls:
+                        print("Tool Calls:")
+                        print(format_tool_calls(tool_calls))
+
+                    if invalid_tool_calls:
+                        print("Invalid Tool Calls:")
+                        print(format_tool_calls(invalid_tool_calls))
+
+                    if response_metadata:
+                        finish_reason = response_metadata.get("finish_reason", "N/A")
+                        print(f"Response Metadata: Finish Reason - {finish_reason}")
+            print("-" * 50)
+    ```
+
+=== "Javascript"
+
+    ```js
+    const input = {
+      "messages": [
+        {
+          "role": "human",
+          "content": "What's the weather in sf",
+        }
+      ]
+    }
+    const config = {"configurable": {"model_name": "openai"}}
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      "agent",
+      {
+        input,
+        config,
+        streamMode: "messages"
+      }
+    );
+    for await (const event of streamResponse) {
+      if (event.event === "metadata") {
+        console.log(`Metadata: Run ID - ${event.data.run_id}`);
+        console.log("-".repeat(50));
+      } else if (event.event === "messages/partial") {
+        event.data.forEach(dataItem => {
+          if (dataItem.role && dataItem.role === "user") {
+            console.log(`Human: ${dataItem.content}`);
+          } else {
+            const toolCalls = dataItem.tool_calls || [];
+            const invalidToolCalls = dataItem.invalid_tool_calls || [];
+            const content = dataItem.content || "";
+            const responseMetadata = dataItem.response_metadata || {};
+
+            if (content) {
+              console.log(`AI: ${content}`);
+            }
+
+            if (toolCalls.length > 0) {
+              console.log("Tool Calls:");
+              console.log(formatToolCalls(toolCalls));
+            }
+
+            if (invalidToolCalls.length > 0) {
+              console.log("Invalid Tool Calls:");
+              console.log(formatToolCalls(invalidToolCalls));
+            }
+
+            if (responseMetadata) {
+              const finishReason = responseMetadata.finish_reason || "N/A";
+              console.log(`Response Metadata: Finish Reason - ${finishReason}`);
+            }
+          }
+        });
+        console.log("-".repeat(50));
+      }
+    }
+    ```
+
+Output:
+
+    Metadata: Run ID - 1ef2fe5c-6a1d-6575-bc09-d7832711c17e
+    --------------------------------------------------
+    Invalid Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: 
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': ''}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current'}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather'}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in'}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in San'}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in San Francisco'}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in San Francisco'}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in San Francisco'}
+    Response Metadata: Finish Reason - tool_calls
+    --------------------------------------------------
+    --------------------------------------------------
+    AI: The
+    --------------------------------------------------
+    AI: The current
+    --------------------------------------------------
+    AI: The current weather
+    --------------------------------------------------
+    AI: The current weather in
+    --------------------------------------------------
+    AI: The current weather in San
+    --------------------------------------------------
+    AI: The current weather in San Francisco
+    --------------------------------------------------
+    AI: The current weather in San Francisco is
+    --------------------------------------------------
+    AI: The current weather in San Francisco is over
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F).
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-s
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-south
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 k
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph).
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%,
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles).
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is 
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is 3
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is 3.
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is 3.
+    Response Metadata: Finish Reason - stop
+    --------------------------------------------------
+

docs/docs/cloud/how-tos/stream_multiple.md

@@ -0,0 +1,440 @@
+# How to configure multiple streaming modes at the same time
+
+This guide covers how to configure multiple streaming modes at the same time.
+
+First let's set up our client and thread:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    # create thread
+    thread = await client.threads.create()
+    print(thread)
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    // create thread
+    const thread = await client.threads.create();
+    console.log(thread)
+    ```
+
+
+Output:
+
+    {'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4',
+     'created_at': '2024-06-24T21:30:07.980789+00:00',
+     'updated_at': '2024-06-24T21:30:07.980789+00:00',
+     'metadata': {}}
+
+When configuring multiple streaming modes for a run, responses for each respective mode will be produced. In the following example, note that a `list` of modes (`messages`, `events`, `debug`) is passed to the `stream_mode` parameter and the response contains `events`, `debug`, `messages/complete`, `messages/metadata`, and `messages/partial` event types.
+
+=== "Python"
+
+    ```python
+    # create input
+    input = {
+        "messages": [
+            {
+                "role": "human",
+                "content": "What's the weather in SF?",
+            }
+        ]
+    }
+
+    # stream events with multiple streaming modes
+    async for chunk in client.runs.stream(
+        thread_id=thread["thread_id"],
+        assistant_id="agent",
+        input=input,
+        stream_mode=["messages", "events", "debug"],
+    ):
+        print(f"Receiving new event of type: {chunk.event}...")
+        print(chunk.data)
+        print("\n\n")
+    ```
+
+=== "Javascript"
+
+    ```js
+    // create input
+    const input = {
+      "messages": [
+        {
+          "role": "human",
+          "content": "What's the weather in SF?",
+        }
+      ]
+    }
+
+    // stream events with multiple streaming modes
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      "agent",
+      {
+        input,
+        streamMode: ["messages", "events", "debug"]
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(f"Receiving new event of type: {chunk.event}...")
+      console.log(chunk.data)
+      console.log("\n\n")
+    }
+    ```
+
+Output:
+
+    Receiving new event of type: metadata...
+    {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {'input': {'messages': [{'role': 'human', 'content': "What's the weather in SF?"}]}}, 'name': 'LangGraph', 'tags': [], 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.116009+00:00', 'step': -1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc7c-6daa-bfff-6b9027c1a50e', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'messages': []}, 'metadata': {'source': 'input', 'step': -1, 'writes': {'messages': [{'role': 'human', 'content': "What's the weather in SF?"}]}}}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.116009+00:00', 'step': -1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc7c-6daa-bfff-6b9027c1a50e', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'messages': []}, 'metadata': {'source': 'input', 'step': -1, 'writes': {'messages': [{'role': 'human', 'content': "What's the weather in SF?"}]}}}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['values', {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: messages/complete...
+    [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.117924+00:00', 'step': 0, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc81-68c8-8000-4e18ae7d67a5', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]}, 'metadata': {'source': 'loop', 'step': 0, 'writes': None}}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.117924+00:00', 'step': 0, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc81-68c8-8000-4e18ae7d67a5', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]}, 'metadata': {'source': 'loop', 'step': 0, 'writes': None}}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task', 'timestamp': '2024-06-24T21:34:06.118042+00:00', 'step': 1, 'payload': {'id': '212ed9c2-a454-50c5-a202-12066bbbe7b8', 'name': 'agent', 'input': {'some_bytes': None, 'some_byte_array': None, 'dict_with_bytes': None, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}], 'sleep': None}, 'triggers': ['start:agent']}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task', 'timestamp': '2024-06-24T21:34:06.118042+00:00', 'step': 1, 'payload': {'id': '212ed9c2-a454-50c5-a202-12066bbbe7b8', 'name': 'agent', 'input': {'some_bytes': None, 'some_byte_array': None, 'dict_with_bytes': None, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}], 'sleep': None}, 'triggers': ['start:agent']}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {}, 'name': 'agent', 'tags': ['graph:step:1'], 'run_id': '72b74d24-5792-48da-a887-102100d6e2c0', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_start', 'data': {'input': {'messages': [[{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]]}}, 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'b', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: messages/metadata...
+    {'run-2424dd6d-5cf5-4244-8d98-357640ce6e12': {'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}}}
+    
+    
+    
+    Receiving new event of type: messages/partial...
+    [{'content': 'b', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: messages/partial...
+    [{'content': 'be', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'g', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: messages/partial...
+    [{'content': 'beg', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'i', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: messages/partial...
+    [{'content': 'begi', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'n', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: messages/partial...
+    [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_end', 'data': {'output': {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, 'input': {'messages': [[{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]]}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {'input': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'name': 'should_continue', 'tags': ['seq:step:3'], 'run_id': '227afb0f-f909-4d54-a042-556ca6d98a69', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': 'tool', 'input': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'run_id': '227afb0f-f909-4d54-a042-556ca6d98a69', 'name': 'should_continue', 'tags': ['seq:step:3'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '72b74d24-5792-48da-a887-102100d6e2c0', 'name': 'agent', 'tags': ['graph:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}, 'input': {'some_bytes': None, 'some_byte_array': None, 'dict_with_bytes': None, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}], 'sleep': None}}, 'run_id': '72b74d24-5792-48da-a887-102100d6e2c0', 'name': 'agent', 'tags': ['graph:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.124350+00:00', 'step': 1, 'payload': {'id': '212ed9c2-a454-50c5-a202-12066bbbe7b8', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.124350+00:00', 'step': 1, 'payload': {'id': '212ed9c2-a454-50c5-a202-12066bbbe7b8', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['values', {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: messages/complete...
+    [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.124510+00:00', 'step': 1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc91-6a34-8001-26353c117c25', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 1, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.124510+00:00', 'step': 1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc91-6a34-8001-26353c117c25', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 1, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task', 'timestamp': '2024-06-24T21:34:06.124572+00:00', 'step': 2, 'payload': {'id': '44139125-a1be-57c2-9cb2-19eb62bbaf2f', 'name': 'tool', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}, 'triggers': ['branch:agent:should_continue:tool']}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task', 'timestamp': '2024-06-24T21:34:06.124572+00:00', 'step': 2, 'payload': {'id': '44139125-a1be-57c2-9cb2-19eb62bbaf2f', 'name': 'tool', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}, 'triggers': ['branch:agent:should_continue:tool']}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {}, 'name': 'tool', 'tags': ['graph:step:2'], 'run_id': '91575720-886e-485e-ae2d-d6817e5346bf', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 2, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '91575720-886e-485e-ae2d-d6817e5346bf', 'name': 'tool', 'tags': ['graph:step:2'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 2, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': None, 'tool_call_id': 'tool_call_id'}]}}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}}, 'run_id': '91575720-886e-485e-ae2d-d6817e5346bf', 'name': 'tool', 'tags': ['graph:step:2'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 2, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.126828+00:00', 'step': 2, 'payload': {'id': '44139125-a1be-57c2-9cb2-19eb62bbaf2f', 'name': 'tool', 'result': [['messages', [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]]]}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.126828+00:00', 'step': 2, 'payload': {'id': '44139125-a1be-57c2-9cb2-19eb62bbaf2f', 'name': 'tool', 'result': [['messages', [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]]]}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['values', {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: messages/complete...
+    [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.126966+00:00', 'step': 2, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc97-6a06-8002-8e9ffc1ea75a', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}, 'metadata': {'source': 'loop', 'step': 2, 'writes': {'tool': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}}}}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.126966+00:00', 'step': 2, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc97-6a06-8002-8e9ffc1ea75a', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}, 'metadata': {'source': 'loop', 'step': 2, 'writes': {'tool': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}}}}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task', 'timestamp': '2024-06-24T21:34:06.127034+00:00', 'step': 3, 'payload': {'id': 'f1ccf371-63b3-5268-a837-7f360a93c4ec', 'name': 'agent', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}], 'sleep': None}, 'triggers': ['tool']}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task', 'timestamp': '2024-06-24T21:34:06.127034+00:00', 'step': 3, 'payload': {'id': 'f1ccf371-63b3-5268-a837-7f360a93c4ec', 'name': 'agent', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}], 'sleep': None}, 'triggers': ['tool']}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {}, 'name': 'agent', 'tags': ['graph:step:3'], 'run_id': 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_start', 'data': {'input': {'messages': [[{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]]}}, 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}
+    
+    
+    
+    Receiving new event of type: messages/metadata...
+    {'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575': {'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}}}
+    
+    
+    
+    Receiving new event of type: messages/partial...
+    [{'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'n', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}
+    
+    
+    
+    Receiving new event of type: messages/partial...
+    [{'content': 'en', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'd', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}
+    
+    
+    
+    Receiving new event of type: messages/partial...
+    [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_end', 'data': {'output': {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, 'input': {'messages': [[{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]]}}, 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {'input': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'name': 'should_continue', 'tags': ['seq:step:3'], 'run_id': '8af814e9-8136-4aab-acbc-dffc5bcafdfd', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': '__end__', 'input': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'run_id': '8af814e9-8136-4aab-acbc-dffc5bcafdfd', 'name': 'should_continue', 'tags': ['seq:step:3'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e', 'name': 'agent', 'tags': ['graph:step:3'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}], 'sleep': None}}, 'run_id': 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e', 'name': 'agent', 'tags': ['graph:step:3'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.133991+00:00', 'step': 3, 'payload': {'id': 'f1ccf371-63b3-5268-a837-7f360a93c4ec', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.133991+00:00', 'step': 3, 'payload': {'id': 'f1ccf371-63b3-5268-a837-7f360a93c4ec', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['values', {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: messages/complete...
+    [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.134190+00:00', 'step': 3, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bca9-6418-8003-8d0d0b06845c', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 3, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.134190+00:00', 'step': 3, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bca9-6418-8003-8d0d0b06845c', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 3, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: end...
+    None
+    
+    
+    
+

docs/docs/cloud/how-tos/stream_updates.md

@@ -0,0 +1,119 @@
+# How to stream state updates of your graph
+
+LangGraph Cloud supports multiple streaming modes. The main ones are:
+
+- `values`: This streaming mode streams back values of the graph. This is the **full state of the graph** after each node is called.
+- `updates`: This streaming mode streams back updates to the graph. This is the **update to the state of the graph** after each node is called.
+- `messages`: This streaming mode streams back messages - both complete messages (at the end of a node) as well as **tokens** for any messages generated inside a node. This mode is primarily meant for powering chat applications.
+
+
+This guide covers `stream_mode="updates"`.
+
+First let's set up our client and thread:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    # create thread
+    thread = await client.threads.create()
+    print(thread)
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    // create thread
+    const thread = await client.threads.create();
+    console.log(thread)
+    ```
+
+
+Output:
+
+    {'thread_id': '979e3c89-a702-4882-87c2-7a59a250ce16',
+     'created_at': '2024-06-21T15:22:07.453100+00:00',
+     'updated_at': '2024-06-21T15:22:07.453100+00:00',
+     'metadata': {}}
+
+Now we can stream by updates, which outputs updates made to the state by each node after it has executed:
+
+
+=== "Python"
+
+    ```python
+    input = {
+        "messages": [
+            {
+                "role": "human",
+                "content": "what's the weather in la"
+            }
+        ]
+    }
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        "agent",
+        input=input,
+        stream_mode="updates",
+    ):
+        print(f"Receiving new event of type: {chunk.event}...")
+        print(chunk.data)
+        print("\n\n")
+    ```
+
+=== "Javascript"
+
+    ```js
+    const input = {
+      "messages": [
+        {
+          "role": "human",
+          "content": "What's the weather in la",
+        }
+      ]
+    }
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      "agent",
+      {
+        input,
+        streamMode: "updates"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(f"Receiving new event of type: {chunk.event}...")
+      console.log(chunk.data)
+      console.log("\n\n")
+    }
+    ```
+
+Output:
+
+    Receiving new event of type: metadata...
+    {'run_id': 'cfc96c16-ed9a-44bd-b5bb-c30e3c0725f0'}
+    
+    
+    
+    Receiving new event of type: data...
+    {'agent': {'messages': [{'content': [{'id': 'toolu_0148tMmDK51iLQfG1yaNwRHM', 'input': {'query': 'weather in los angeles'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-1a9d32b0-7007-4a36-abde-8df812a0ed94', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in los angeles'}, 'id': 'toolu_0148tMmDK51iLQfG1yaNwRHM'}], 'invalid_tool_calls': []}]}}
+    
+    
+    
+    Receiving new event of type: data...
+    {'action': {'messages': [{'content': '[{"url": "https://www.weatherapi.com/", "content": "{\'location\': {\'name\': \'Los Angeles\', \'region\': \'California\', \'country\': \'United States of America\', \'lat\': 34.05, \'lon\': -118.24, \'tz_id\': \'America/Los_Angeles\', \'localtime_epoch\': 1716062239, \'localtime\': \'2024-05-18 12:57\'}, \'current\': {\'last_updated_epoch\': 1716061500, \'last_updated\': \'2024-05-18 12:45\', \'temp_c\': 18.9, \'temp_f\': 66.0, \'is_day\': 1, \'condition\': {\'text\': \'Overcast\', \'icon\': \'//cdn.weatherapi.com/weather/64x64/day/122.png\', \'code\': 1009}, \'wind_mph\': 2.2, \'wind_kph\': 3.6, \'wind_degree\': 10, \'wind_dir\': \'N\', \'pressure_mb\': 1017.0, \'pressure_in\': 30.02, \'precip_mm\': 0.0, \'precip_in\': 0.0, \'humidity\': 65, \'cloud\': 100, \'feelslike_c\': 18.9, \'feelslike_f\': 66.0, \'vis_km\': 16.0, \'vis_miles\': 9.0, \'uv\': 6.0, \'gust_mph\': 7.5, \'gust_kph\': 12.0}}"}]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'tavily_search_results_json', 'id': 'a36e8cd1-0e96-4417-9c15-f10a945d2b42', 'tool_call_id': 'toolu_0148tMmDK51iLQfG1yaNwRHM'}]}}
+    
+    
+    
+    Receiving new event of type: data...
+    {'agent': {'messages': [{'content': 'The weather in Los Angeles is currently overcast with a temperature of around 66°F (18.9°C). There are light winds from the north at around 2-3 mph. The humidity is 65% and visibility is good at 9 miles. Overall, mild spring weather conditions in LA.', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-d5c1c2f0-b12d-41ce-990b-f36570e7483d', 'example': False, 'tool_calls': [], 'invalid_tool_calls': []}]}}
+    
+    
+    
+    Receiving new event of type: end...
+    None

docs/docs/cloud/how-tos/stream_values.md

@@ -0,0 +1,190 @@
+# How to stream full state of your graph
+
+LangGraph Cloud supports multiple streaming modes. The main ones are:
+
+- `values`: This streaming mode streams back values of the graph. This is the **full state of the graph** after each node is called.
+- `updates`: This streaming mode streams back updates to the graph. This is the **update to the state of the graph** after each node is called.
+- `messages`: This streaming mode streams back messages - both complete messages (at the end of a node) as well as **tokens** for any messages generated inside a node. This mode is primarily meant for powering chat applications.
+
+
+This guide covers `stream_mode="values"`.
+
+First let's set up our client and thread:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    # create thread
+    thread = await client.threads.create()
+    print(thread)
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl: "whatever-your-deployment-url-is" });
+    // create thread
+    const thread = await client.threads.create();
+    console.log(thread)
+    ```
+
+Output:
+
+    {'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4',
+     'created_at': '2024-06-24T21:30:07.980789+00:00',
+     'updated_at': '2024-06-24T21:30:07.980789+00:00',
+     'metadata': {}}
+
+Now we can stream by values, which streams the full state of the graph after each node has finished executing:
+
+=== "Python"
+
+    ```python
+    input = {"messages": [{"role": "human", "content": "what's the weather in la"}]}
+
+    # stream values
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        "agent", 
+        input=input,
+        stream_mode="values"
+    ):
+        print(f"Receiving new event of type: {chunk.event}...")
+        print(chunk.data)
+        print("\n\n")
+    ```
+
+=== "Javascript"
+    
+
+    ```js
+    const input = {"messages": [{"role": "human", "content": "what's the weather in la"}]}
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      "agent",
+      {
+        input,
+        streamMode: "values"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(f"Receiving new event of type: {chunk.event}...")
+      console.log(chunk.data)
+      console.log("\n\n")
+    }
+    ```
+
+
+Output:
+
+    Receiving new event of type: metadata...
+    {'run_id': 'f08791ce-0a3d-44e0-836c-ff62cd2e2786'}
+    
+    
+    
+    Receiving new event of type: values...
+    {'messages': [{'role': 'human', 'content': 'what's the weather in la'}]}
+    
+    
+    
+    Receiving new event of type: values...
+    {'messages': [{'content': 'what's the weather in la', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'faa15565-8823-4aa1-87af-e21b40526fae', 'example': False}, {'content': [{'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g', 'input': {'query': 'weather in los angeles'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-3fe1db7a-6b8d-4d83-ba07-8657190ad811', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in los angeles'}, 'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}], 'invalid_tool_calls': []}]}
+    
+    
+    
+    Receiving new event of type: values...
+    {'messages': [{'content': 'what's the weather in la', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'faa15565-8823-4aa1-87af-e21b40526fae', 'example': False}, {'content': [{'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g', 'input': {'query': 'weather in los angeles'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-3fe1db7a-6b8d-4d83-ba07-8657190ad811', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in los angeles'}, 'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}], 'invalid_tool_calls': []}, {'content': '[{"url": "https://www.weatherapi.com/", "content": "{\'location\': {\'name\': \'Los Angeles\', \'region\': \'California\', \'country\': \'United States of America\', \'lat\': 34.05, \'lon\': -118.24, \'tz_id\': \'America/Los_Angeles\', \'localtime_epoch\': 1716310320, \'localtime\': \'2024-05-21 9:52\'}, \'current\': {\'last_updated_epoch\': 1716309900, \'last_updated\': \'2024-05-21 09:45\', \'temp_c\': 16.7, \'temp_f\': 62.1, \'is_day\': 1, \'condition\': {\'text\': \'Overcast\', \'icon\': \'//cdn.weatherapi.com/weather/64x64/day/122.png\', \'code\': 1009}, \'wind_mph\': 8.1, \'wind_kph\': 13.0, \'wind_degree\': 250, \'wind_dir\': \'WSW\', \'pressure_mb\': 1015.0, \'pressure_in\': 29.97, \'precip_mm\': 0.0, \'precip_in\': 0.0, \'humidity\': 65, \'cloud\': 100, \'feelslike_c\': 16.7, \'feelslike_f\': 62.1, \'vis_km\': 16.0, \'vis_miles\': 9.0, \'uv\': 5.0, \'gust_mph\': 12.5, \'gust_kph\': 20.2}}"}]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'tavily_search_results_json', 'id': '0d5dab31-5ff8-4ae2-a560-bc4bcba7c9d7', 'tool_call_id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}]}
+    
+    
+    
+    Receiving new event of type: values...
+    {'messages': [{'content': 'what's the weather in la', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'faa15565-8823-4aa1-87af-e21b40526fae', 'example': False}, {'content': [{'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g', 'input': {'query': 'weather in los angeles'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-3fe1db7a-6b8d-4d83-ba07-8657190ad811', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in los angeles'}, 'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}], 'invalid_tool_calls': []}, {'content': '[{"url": "https://www.weatherapi.com/", "content": "{\'location\': {\'name\': \'Los Angeles\', \'region\': \'California\', \'country\': \'United States of America\', \'lat\': 34.05, \'lon\': -118.24, \'tz_id\': \'America/Los_Angeles\', \'localtime_epoch\': 1716310320, \'localtime\': \'2024-05-21 9:52\'}, \'current\': {\'last_updated_epoch\': 1716309900, \'last_updated\': \'2024-05-21 09:45\', \'temp_c\': 16.7, \'temp_f\': 62.1, \'is_day\': 1, \'condition\': {\'text\': \'Overcast\', \'icon\': \'//cdn.weatherapi.com/weather/64x64/day/122.png\', \'code\': 1009}, \'wind_mph\': 8.1, \'wind_kph\': 13.0, \'wind_degree\': 250, \'wind_dir\': \'WSW\', \'pressure_mb\': 1015.0, \'pressure_in\': 29.97, \'precip_mm\': 0.0, \'precip_in\': 0.0, \'humidity\': 65, \'cloud\': 100, \'feelslike_c\': 16.7, \'feelslike_f\': 62.1, \'vis_km\': 16.0, \'vis_miles\': 9.0, \'uv\': 5.0, \'gust_mph\': 12.5, \'gust_kph\': 20.2}}"}]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'tavily_search_results_json', 'id': '0d5dab31-5ff8-4ae2-a560-bc4bcba7c9d7', 'tool_call_id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}, {'content': 'Based on the weather API results, the current weather in Los Angeles is overcast with a temperature of around 62°F (17°C). There are light winds from the west-southwest around 8-13 mph. The humidity is 65% and visibility is good at 9 miles. Overall, mild spring weather conditions in LA.', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-4d6d4c23-5aad-4042-b0d9-19407a9e08e3', 'example': False, 'tool_calls': [], 'invalid_tool_calls': []}]}
+    
+    
+    
+    Receiving new event of type: end...
+    None
+    
+    
+    
+
+
+If we want to just get the final result, we can use this endpoint and just keep track of the last value we received
+
+
+=== "Python"
+
+    ```python
+    final_answer = None
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        "agent",
+        input=input,
+        stream_mode="values"
+    ):
+        if chunk.event == "values":
+            final_answer = chunk.data
+    ```
+
+=== "Javascript"
+
+    ```js
+    let finalAnswer;
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      "agent",
+      {
+        input,
+        streamMode: "values"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      finalAnswer = chunk.data;
+    }
+    ```
+
+Output:
+
+    {'messages': [{'content': 'what's the weather in la',
+       'additional_kwargs': {},
+       'response_metadata': {},
+       'type': 'human',
+       'name': None,
+       'id': 'e78c2f94-d810-42fc-a399-11f6bb1b1092',
+       'example': False},
+      {'content': [{'id': 'toolu_01SBMoAGr4U9x3ibztm2UUom',
+         'input': {'query': 'weather in los angeles'},
+         'name': 'tavily_search_results_json',
+         'type': 'tool_use'}],
+       'additional_kwargs': {},
+       'response_metadata': {},
+       'type': 'ai',
+       'name': None,
+       'id': 'run-80767ab8-09fc-40ec-9e45-657ddef5e0b1',
+       'example': False,
+       'tool_calls': [{'name': 'tavily_search_results_json',
+         'args': {'query': 'weather in los angeles'},
+         'id': 'toolu_01SBMoAGr4U9x3ibztm2UUom'}],
+       'invalid_tool_calls': []},
+      {'content': '[{"url": "https://www.weatherapi.com/", "content": "{\'location\': {\'name\': \'Los Angeles\', \'region\': \'California\', \'country\': \'United States of America\', \'lat\': 34.05, \'lon\': -118.24, \'tz_id\': \'America/Los_Angeles\', \'localtime_epoch\': 1716310320, \'localtime\': \'2024-05-21 9:52\'}, \'current\': {\'last_updated_epoch\': 1716309900, \'last_updated\': \'2024-05-21 09:45\', \'temp_c\': 16.7, \'temp_f\': 62.1, \'is_day\': 1, \'condition\': {\'text\': \'Overcast\', \'icon\': \'//cdn.weatherapi.com/weather/64x64/day/122.png\', \'code\': 1009}, \'wind_mph\': 8.1, \'wind_kph\': 13.0, \'wind_degree\': 250, \'wind_dir\': \'WSW\', \'pressure_mb\': 1015.0, \'pressure_in\': 29.97, \'precip_mm\': 0.0, \'precip_in\': 0.0, \'humidity\': 65, \'cloud\': 100, \'feelslike_c\': 16.7, \'feelslike_f\': 62.1, \'vis_km\': 16.0, \'vis_miles\': 9.0, \'uv\': 5.0, \'gust_mph\': 12.5, \'gust_kph\': 20.2}}"}]',
+       'additional_kwargs': {},
+       'response_metadata': {},
+       'type': 'tool',
+       'name': 'tavily_search_results_json',
+       'id': 'af25e94a-c119-48c3-bbd3-096e42f472ac',
+       'tool_call_id': 'toolu_01SBMoAGr4U9x3ibztm2UUom'},
+      {'content': 'Based on the weather API results, the current weather in Los Angeles is overcast with a temperature of around 62°F (17°C). There are light winds from the west-southwest around 8-13 mph. The humidity is 65% and visibility is good at 9 miles. Overall, mild spring weather conditions in LA.',
+       'additional_kwargs': {},
+       'response_metadata': {},
+       'type': 'ai',
+       'name': None,
+       'id': 'run-b90f0037-e56a-4f3b-ad92-00d10d079a9e',
+       'example': False,
+       'tool_calls': [],
+       'invalid_tool_calls': []}]}

docs/docs/cloud/how-tos/test_deployment.md

@@ -0,0 +1,14 @@
+# Test Cloud Deployment
+
+The LangGraph Studio UI connects directly to LangGraph Cloud deployments.
+
+Starting from the <a href="https://smith.langchain.com/" target="_blank">LangSmith UI</a>...
+
+1. In the left-hand navigation panel, select `Deployments`. The `Deployments` view contains a list of existing LangGraph Cloud deployments.
+1. Select an existing deployment to test with LangGraph Studio.
+1. In the top-right corner, select `Open LangGraph Studio`.
+1. [Invoke an assistant](./invoke_studio.md) or [view an existing thread](./threads_studio.md).
+
+The following GIF shows these exact steps being carried out:
+
+![Using LangGraph Studio](./img/studio_usage.gif)

docs/docs/cloud/how-tos/threads_studio.md

@@ -0,0 +1,19 @@
+# Interacting with Threads in Studio
+
+## View Thread
+
+1. In the top of the right-hand pane, select the `New Thread` dropdown menu to view existing threads.
+1. View the state of the thread (i.e. the output) in the right-hand pane.
+1. To create a new thread, select `+ New Thread`.
+
+The following GIF shows these exact steps being carried out:
+
+![Using LangGraph Studio](./img/studio_threads.gif)
+
+## Edit Thread State
+
+The LangGraph Studio UI contains features for editing thread state. Explore these features in the right-hand pane. Select the `Edit` icon, modify the desired state, and then select `Fork` to invoke the assistant with the updated state.
+
+The following GIF shows how to edit a thread in the studio:
+
+![Using LangGraph Studio](./img/studio_forks.gif)

docs/docs/cloud/index.md

@@ -1,16 +1,18 @@
-# LangGraph Cloud (alpha)
+# LangGraph Cloud (beta)
 
 !!! danger "Important"
-    LangGraph Cloud is a closed source, paid product in an invite-only stage. We are currently focused on providing high bandwidth support to make our select early customers successful. If you are interested in applying for access, please fill out [this form](https://airtable.com/app5PiMJxXukqPLq3/pagveJsW7XOjDspqw/form).
+    LangGraph Cloud is a closed source, paid product in an invite-only stage. We are currently focused on providing high bandwidth support to make our select early customers successful. If you are interested in applying for access, please fill out [this form](https://www.langchain.com/langgraph-cloud-beta).
 
 !!! warning "Under Construction"
     LangGraph Cloud documentation is under construction. Contents may change until general availability.
 
+![GIF](./how-tos/img/studio_input.gif)
+
 ## Overview
 
-LangGraph Cloud is a managed service for deploying and hosting LangGraph applications. Deploying applications with LangGraph Cloud shortens the time-to-market for developers. With one click, deploy a production-ready API with built-in persistence for your LangGraph application. LangGraph Cloud APIs are horizatonally scalable and deployed with durable storage.
+LangGraph Cloud is a managed service for deploying and hosting LangGraph applications. Deploying applications with LangGraph Cloud shortens the time-to-market for developers. With one click, deploy a production-ready API with built-in persistence for your LangGraph application. LangGraph Cloud APIs are horizontally scalable and deployed with durable storage.
 
-The LangGraph Cloud API exposes functionality of your LangGraph application through [Assistants](./concepts/index.md#assistants). An assistant abstracts the cognitive architecture of your graph. Invoke an assistant by calling the pre-built [API endpoints](./reference/api/api_ref.md).
+The LangGraph Cloud API exposes functionality of your LangGraph application through [Assistants](./concepts/api.md#assistants). An assistant abstracts the cognitive architecture of your graph. Invoke an assistant by calling the pre-built [API endpoints](./reference/api/api_ref.md).
 
 LangGraph Cloud is seamlessly integrated with [LangSmith](https://www.langchain.com/langsmith) and is accessible from within the LangSmith UI.
 
@@ -28,6 +30,6 @@ The LangGraph Cloud API supports key LangGraph features in addition to new funct
 ## Documentation
 
 - [Tutorials](./quick_start.md): Learn to build and deploy applications for LangGraph Cloud.
-- [How-to Guides](./deployment/setup/): Learn how to set up a LangGraph application for deployment and implement features of the LangGraph Cloud API such as streaming tokens, configuring double texting, and creating cron jobs. Go here if you want to copy and run a specific code snippet.
-- [Conceptual Guides](./concepts/): In-depth explanations of the core data models (e.g. assistants) and key features (e.g. double texting) of the LangGraph Cloud API.
+- [How-to Guides](./how-tos/index.md): Learn how to set up a LangGraph application for deployment and implement features of the LangGraph Cloud API such as streaming tokens, configuring double texting, and creating cron jobs. Go here if you want to copy and run a specific code snippet.
+- [Conceptual Guides](./concepts/api.md): In-depth explanations of the core data models (e.g. assistants), key features of the LangGraph Cloud API (e.g. double texting), and the architecture of a LangGraph Cloud deployment.
 - [Reference](./reference/api/api_ref.md): References for the LangGraph Cloud API, the corresponding Python and JS/TS SDKs, the LangGraph CLI, and deployment environment variables.

docs/docs/cloud/quick_start.md

@@ -1,11 +1,18 @@
 # Quick Start
-This quick start guide will cover how to develop an application for LangGraph Cloud, run it locally in Docker, and call the APIs to invoke a graph.
 
-Alternatively, clone or fork the [`langgraph/example`](https://github.com/langchain-ai/langgraph-example) GitHub repository and follow the instructions in the `README`.
+This quick start guide will cover how to build a simple agent that can look up things on the internet. We will then deploy it to LangGraph Cloud, use the LangGraph Studio to visualize and test it out, and use the LangGraph SDK to interact with it.
+
+## Set up requirements
+
+This tutorial will use:
+
+- Anthropic for the LLM - sign up and get an API key [here](https://console.anthropic.com/)
+- Tavily for the search engine - sign up and get an API key [here](https://app.tavily.com/)
+- LangSmith for hosting - sign up and get an API key [here](https://smith.langchain.com/)
 
 ## Set up local files
 
-1. Create a new application with the following directory and files:
+1.  Create a new application with the following directory and files:
 
         <my-app>/
         |-- agent.py            # code for your LangGraph agent
@@ -13,149 +20,133 @@ Alternatively, clone or fork the [`langgraph/example`](https://github.com/langch
         |-- langgraph.json      # configuration file for LangGraph
         |-- .env                # environment files with API keys
 
-2. The `agent.py` file should contain Python code for defining your graph. The following code is a simple example, the important thing is that at somepoint in your file you compile your graph and assign that Runnable to a variable (in this case the `graph` variable). 
+2.  The `agent.py` file should contain Python code for defining your graph. The following code is a simple example, the important thing is that at some point in your file you compile your graph and assign the compiled graph to a variable (in this case the `graph` variable). This example code uses `create_react_agent`, a prebuilt agent, read more about it [here](..//concepts/agentic_concepts.md#react-agent).
 
     ```python
-    from langchain_openai import ChatOpenAI
-    from langgraph.graph import END, MessageGraph
+    from langchain_anthropic import ChatAnthropic
+    from langchain_community.tools.tavily_search import TavilySearchResults
+    from langgraph.prebuilt import create_react_agent
 
-    model = ChatOpenAI(temperature=0)
+    model = ChatAnthropic(model="claude-3-5-sonnet-20240620")
 
-    graph_workflow = MessageGraph()
+    tools = [TavilySearchResults(max_results=2)]
 
-    graph_workflow.add_node("agent", model)
-    graph_workflow.add_edge("agent", END)
-    graph_workflow.set_entry_point("agent")
-
-    graph = graph_workflow.compile()
+    graph = create_react_agent(model, tools)
     ```
 
-3. The `requirements.txt` file should contain any dependencies for your graph(s). In this case we only require two packages for our graph to run:
+3.  The `requirements.txt` file should contain any dependencies for your graph(s). In this case we only require four packages for our graph to run:
 
         langgraph
-        langchain_openai
+        langchain_anthropic
+        tavily-python
+        langchain_community
 
-4. The `langgraph.json` file is a configuration file that describes what graph you are going to host. It is important to note that you can host multiple graphs at a time. In this case we only host one: the `graph` Runnable from `agent.py`, but we could have defined multiple different graphs within `agent.py` to host, or written multiple python files to each host one or more graphs. Each graph you wish to host should have a unique identifier.
+4.  The [`langgraph.json`][langgraph.json] file is a configuration file that describes what graph(s) you are going to host. In this case we only have one graph to host: the compiled `graph` object from `agent.py`.
 
     ```json
     {
-        "dependencies": ["."],
-        "graphs": {
-            "agent": "./agent.py:graph"
-        },
-        "env": ".env"
+      "dependencies": ["."],
+      "graphs": {
+        "agent": "./agent.py:graph"
+      },
+      "env": ".env"
     }
     ```
 
     Learn more about the LangGraph CLI configuration file [here](./reference/cli.md#configuration-file).
 
-5. The `.env` file should contain the environment variables that are needed to run your graph. In this case we just need to specify the OpenAI API key, as well as the authentication type for langgraph.  
+5.  The `.env` file should have any environment variables needed to run your graph. This will only be used for local testing, so if you are not testing locally you can skip this step. NOTE: if you do add this, you should NOT check this into git. For this graph, we need two environment variables:
 
-        OPENAI_API_KEY=<add your key here>
-        LANGGRAPH_AUTH_TYPE=noop
+    ```shell
+    ANTHROPIC_API_KEY=...
+    TAVILY_API_KEY=...
+    ```
 
-    !!! warning "Disable Authentication"
-        When testing locally, set `LANGGRAPH_AUTH_TYPE` to `noop` to disable authentication.
+Now that we have set everything up on our local file system, we are ready to host our graph.
 
-Now that we have set everything up on our local file system, we are ready to host our graph. 
+## Test the graph build locally
 
-## Run Locally
+Before deploying to the cloud, we probably want to test the building of our graph locally. This is useful to make sure we have configured our [CLI configuration file][langgraph.json] correctly and our graph runs.
 
-1. Install the [LangGraph CLI](./reference/cli.md#installation).
+In order to do this we can first install the LangGraph CLI
 
-2. Run the following command to start the API server in Docker:
+```shell
+pip install langgraph-cli
+```
 
-        langgraph up -c langgraph.json
+We can then test our API server locally. This requires access to LangGraph closed beta. In order to run the server locally, you will need to add your `LANGSMITH_API_KEY` to the .env file so we can validate you have access to LangGraph closed beta.
 
-3. The API server is now running at `http://localhost:8123`. Navigate to [`http://localhost:8123/docs`](http://localhost:8123/docs) to view the API docs.
+```shell
+langgraph up
+```
 
-4. You can now test that your deployment is working as intended by invoking some of the cURL commands from the API docs.
+This will start up the LangGraph API server locally. If this runs successfully, you should see something like:
 
-First, let's test that the assistant we are hosting is indeed retrievable by the API, which we can do by using the "assistants/search" endpoint:
+```shell
+Ready!
+- API: http://localhost:8123
+2024-06-26 19:20:41,056:INFO:uvicorn.access 127.0.0.1:44138 - "GET /ok HTTP/1.1" 200
+```
 
-    curl --request POST \
-        --url http://localhost:8123/assistants/search \
-        --header 'Content-Type: application/json' \
-        --data '{
-        "metadata": {},
-        "limit": 10,
-        "offset": 0
-    }
+You can now test this out! **Note: this local server is intended SOLELY for local testing purposes and is not performant enough for production applications, so please do not use it as such.** To test it out, you can go to another terminal window and run:
 
-If the hosting is working as expected, you should receive a 200 response which looks something like this example response:
-
-    [
-        {
-            "assistant_id": "123e4567-e89b-12d3-a456-426614174000",
-            "graph_id": "agent",
-            "config": {
-            "tags": [
-                "…"
-            ],
-            "recursion_limit": 1,
-            "configurable": {}
-            },
-            "created_at": "2024-06-24T19:21:47.514Z",
-            "updated_at": "2024-06-24T19:21:47.514Z",
-            "metadata": {}
-        }
-    ]
-
-If you are hosting multiple graphs, you should see all of them in this response. Once you have verified that this step is working as intended, you can test out that invoking your hosted graphs works as intended without any bugs. You can do this by calling the a version of the following cURL command:
-
-    curl --request POST \
-        --url http://localhost:8123/runs/stream \
-        --header 'Content-Type: application/json' \
-        --data '{
-        "assistant_id": "123e4567-e89b-12d3-a456-426614174000",
-        "input": {     
-            "messages": [
-            {               
+```shell
+curl --request POST \
+    --url http://localhost:8123/runs/stream \
+    --header 'Content-Type: application/json' \
+    --data '{
+    "assistant_id": "agent",
+    "input": {
+        "messages": [
+            {
                 "role": "user",
                 "content": "How are you?"
-            }           
-            ]       
-        },
-        "metadata": {},
-        "config": {
-            "configurable": {}
-        },
-        "multitask_strategy": "reject",
-        "stream_mode": [
-            "values"
+            }
         ]
-    }'
+    },
+    "metadata": {},
+    "config": {
+        "configurable": {}
+    },
+    "multitask_strategy": "reject",
+    "stream_mode": [
+        "values"
+    ]
+}'
+```
 
-Make sure to edit the `input` and `assistant_id` fields to match what assistant you want to test. If you receive a 200 response then congratulations your graph has run successfully and you are ready to move on to hosting on Langgraph Cloud!
+If you get back a valid response, then all is functioning properly!
 
 ## Deploy to Cloud
 
 ### Push your code to GitHub
 
-Create a git repo in the `<my-app>` directory, and verify it’s existence. You can use the GitHub CLI if you like, or just create a repo manually.
+Turn the `<my-app>` directory into a GitHub repo. You can use the GitHub CLI if you like, or just create a repo manually (if unfamiliar, instructions [here](https://docs.github.com/en/migrations/importing-source-code/using-the-command-line-to-import-source-code/adding-locally-hosted-code-to-github)).
 
 ### Deploy from GitHub with LangGraph Cloud
 
-Once you have created your github repository with a Python file containing your compiled graph as well as a `langgraph.json` file containing the configuration for hosting your graph, you can head over to LangSmith and click on the 🚀 icon on the left navbar to create a new deployment. Click the `+ New Deployment` button. 
+Once you have created your github repository with a Python file containing your compiled graph as well as a `langgraph.json` file containing the configuration for hosting your graph, you can head over to LangSmith and click on the 🚀 icon on the left navbar to create a new deployment. Then click the `+ New Deployment` button.
 
-***If you have not deployed to LangGraph Cloud before:*** there will be a button that shows up saying Import from GitHub. You’ll need to follow that flow to connect LangGraph Cloud to GitHub.
+![Langsmith Workflow](./img/cloud_deployment.png)
 
-***Once you have set up your GitHub connection:*** the new deployment page will look as follows
+**_If you have not deployed to LangGraph Cloud before:_** there will be a button that shows up saying Import from GitHub. You’ll need to follow that flow to connect LangGraph Cloud to GitHub.
 
-![Screenshot 2024-06-11 at 1.17.03 PM.png](./deployment/img/deployment_page.png)
+**_Once you have set up your GitHub connection:_** the new deployment page will look as follows:
+
+![Deployment before being filled out](./deployment/img/deployment_page.png)
 
 To deploy your application, you should do the following:
 
 1. Select your GitHub username or organization from the selector
 2. Search for your repo to deploy in the search bar and select it
 3. Choose any name
-4. In the `LangGraph API config file` field, enter the path to your `langgraph.json` file (if left blank langsmith will automatically search for it on deployment)
-5. For Git Reference, you can select either the git branch for the code you want to deploy, or the exact commit SHA. 
-6. If your chain relies on environment variables (for example, an OPENAI_API_KEY), add those in. They will be propagated to the underlying server so your code can access them.
+4. In the `LangGraph API config file` field, enter the path to your `langgraph.json` file (which in this case is just `langgraph.json`)
+5. For Git Reference, you can select either the git branch for the code you want to deploy, or the exact commit SHA.
+6. If your chain relies on environment variables, add those in. They will be propagated to the underlying server so your code can access them. In this case, we need `ANTHROPIC_API_KEY` and `TAVILY_API_KEY`.
 
 Putting this all together, you should have something as follows for your deployment details:
 
-![Screenshot 2024-06-11 at 1.21.52 PM.png](./deployment/img/deploy_filled_out.png)
+![Deployment filled out](./deployment/img/deploy_filled_out.png)
 
 Hit `Submit` and your application will start deploying!
 
@@ -165,9 +156,9 @@ Hit `Submit` and your application will start deploying!
 
 After your deployment is complete, your deployments page should look as follows:
 
-![Screenshot 2024-06-11 at 2.03.34 PM.png](./deployment/img/deployed_page.png)
+![Deployed page](./deployment/img/deployed_page.png)
 
-You can see that by default, you get access to the `Trace Count` monitoring chart and `Recent Traces` run view. These are powered by LangSmith. 
+You can see that by default, you get access to the `Trace Count` monitoring chart and `Recent Traces` run view. These are powered by LangSmith.
 
 You can click on `All Charts` to view all monitoring info for your server, or click on `See tracing project` to get more information on an individual trace.
 
@@ -175,20 +166,87 @@ You can click on `All Charts` to view all monitoring info for your server, or cl
 
 You can access the docs by clicking on the API docs link, which should send you to a page that looks like this:
 
-![Screenshot 2024-06-19 at 2.27.24 PM.png](./deployment/img/api_page.png)
+![API Docs page](./deployment/img/api_page.png)
 
-You won’t actually be able to test any of the API endpoints without authorizing first. To do so, click on the Authorize button in the top right corner, input your `LANGCHAIN_API_KEY`  in the `API Key` box, and then click `Authorize`  to finish the process. You should now be able to select any of the API endpoints, click `Try it out` , enter the parameters you would like to pass, and then click `Execute` to view the results of the API call.
+You won’t actually be able to test any of the API endpoints without authorizing first. To do so, grab your Langsmith API key and add it at the top where it says `API KEY (X-API-KEY)`. You should now be able to select any of the API endpoints, click `Test Request`, enter the parameters you would like to pass, and then click `Send` to view the results of the API call.
 
 ## Interact with your deployment via LangGraph Studio
 
-### Access Studio
-
 If you click on your deployment you should see a blue button in the top right that says `LangGraph Studio`. Clicking on this button will take you to a page that looks like this:
 
-![Screenshot 2024-06-11 at 2.51.51 PM.png](./deployment/img/graph_visualization.png)
+![Studio UI before being run](./deployment/img/graph_visualization.png)
 
 On this page you can test out your graph by passing in starting states and clicking `Start Run` (this should behave identically to calling `.invoke`). You will then be able to look into the execution thread for each run and explore the steps your graph is taking to produce its output.
 
+![Studio UI once being run](./deployment/img/graph_run.png)
+
 ## Use with the SDK
 
-Once you have tested that your hosted graph works as expected using Langgraph Studio, you can start using your hosted graph all over your organization by using the Langgraph SDK. You can learn about how to do that by following [this how-to guide](./sdk/python_sdk.ipynb)
+Once you have tested that your hosted graph works as expected using LangGraph Studio, you can start using your hosted graph all over your organization by using the LangGraph SDK. Let's see how we can access our hosted graph and execute our run from a python file.
+
+First, make sure you have the SDK installed by calling `pip install langgraph_sdk`.
+
+Before using, you need to get the URL of your LangGraph deployment. You can find this in the `Deployment` view. Click the URL to copy it to the clipboard.
+
+You also need to make sure you have set up your API key properly so you can authenticate with LangGraph Cloud.
+
+```shell
+export LANGSMITH_API_KEY=...
+```
+
+The first thing to do when using the SDK is to setup our client, access our assistant, and create a thread to execute a run on:
+
+```python
+from langgraph_sdk import get_client
+
+# Replace this with the URL of your own deployed graph
+URL = "https://chatbot-23a570f3210f52a7b167f09f6158e3b3-ffoprvkqsa-uc.a.run.app"
+client = get_client(url=URL)
+
+# Search all hosted graphs
+assistants = await client.assistants.search()
+# In this example we select the first assistant since we are only hosting a single graph
+assistant = assistants[0]
+
+# We create a thread for tracking the state of our run
+thread = await client.threads.create()
+```
+
+We can then execute a run on the thread:
+
+```python
+input = {"messages":[{"role": "user", "content": "Hello! My name is Bagatur and I am 26 years old."}]}
+
+async for chunk in client.runs.stream(
+        thread['thread_id'],
+        assistant["assistant_id"],
+        input=input,
+        stream_mode="updates",
+    ):
+    if chunk.data and chunk.event != "metadata":
+        print(chunk.data)
+```
+
+    {'agent': {'messages': [{'content': "Hi Bagatur! It's nice to meet you. How can I assist you today?", 'additional_kwargs': {}, 'response_metadata': {'finish_reason': 'stop', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_9cb5d38cf7'}, 'type': 'ai', 'name': None, 'id': 'run-c89118b7-1b1e-42b9-a85d-c43fe99881cd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+
+## What's Next
+
+Congratulations! If you've worked your way through this tutorial you are well on your way to becoming a LangGraph Cloud expert. Here are some other resources to check out to help you out on the path to expertise:
+
+### LangGraph Cloud How-tos
+
+If you want to learn more about streaming from hosted graphs, check out the Streaming [how-to guides](how-tos/index.md#streaming).
+
+To learn more about double-texting and all the ways you can handle it in your application, read up on these [how-to guides](how-tos/index.md#double-texting).
+
+To learn about how to include different human-in-the-loop behavior in your graph, take a look at [these how-tos](how-tos/index.md#human-in-the-loop).
+
+### LangGraph Tutorials
+
+Before hosting, you have to write a graph to host. Here are some tutorials to get you more comfortable with writing LangGraph graphs and give you inspiration for the types of graphs you want to host.
+
+[This tutorial](../tutorials/customer-support/customer-support.ipynb) walks you through how to write a customer support bot using LangGraph.
+
+If you are interested in writing a SQL agent, check out [this tutorial](../tutorials/sql-agent.ipynb).
+
+Check out the [LangGraph tutorials](../tutorials/index.md) page to read about more exciting use cases.

docs/docs/cloud/reference/api/openapi.json

@@ -59,7 +59,7 @@
           "content": {
             "application/json": {
               "schema": {
-                "$ref": "#/components/schemas/SearchRequest"
+                "$ref": "#/components/schemas/AssistantSearchRequest"
               }
             }
           },
@@ -388,7 +388,7 @@
           "content": {
             "application/json": {
               "schema": {
-                "$ref": "#/components/schemas/SearchRequest"
+                "$ref": "#/components/schemas/ThreadSearchRequest"
               }
             }
           },
@@ -1463,6 +1463,52 @@
         }
       }
     },
+    "/runs/crons/search": {
+      "post": {
+        "tags": [
+          "crons/search"
+        ],
+        "summary": "Search Crons",
+        "description": "Search all active crons",
+        "operationId": "search_crons_runs_crons_post",
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CronSearch"
+              }
+            }
+          },
+          "required": true
+        },
+        "responses": {
+          "200": {
+            "description": "Successful Response",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "items": {
+                    "$ref": "#/components/schemas/Cron"
+                  },
+                  "type": "array",
+                  "title": "Response Search Crons Search Post"
+                }
+              }
+            }
+          },
+          "422": {
+            "description": "Validation Error",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/HTTPValidationError"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
     "/runs/stream": {
       "post": {
         "tags": [
@@ -1543,6 +1589,46 @@
         }
       }
     },
+    "/runs": {
+      "post": {
+        "tags": [
+          "runs/create"
+        ],
+        "summary": "Run Stateless",
+        "description": "Create a stateless run that will run in the background.",
+        "operationId": "run_stateless_runs_post",
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/RunCreate"
+              }
+            }
+          },
+          "required": true
+        },
+        "responses": {
+          "200": {
+            "description": "Successful Response",
+            "content": {
+              "application/json": {
+                "schema": {}
+              }
+            }
+          },
+          "422": {
+            "description": "Validation Error",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/HTTPValidationError"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
     "/runs/crons/{cron_id}": {
       "delete": {
         "tags": [
@@ -1880,6 +1966,39 @@
         "title": "CronCreate",
         "description": "Payload for creating a cron."
       },
+      "CronSearch" : {
+        "properties": {
+          "assistant_id": {
+            "type": "string",
+            "format": "uuid",
+            "title": "Assistant Id"
+          },
+          "thread_id": {
+            "type": "string",
+            "format": "uuid",
+            "title": "Thread Id"
+          },
+          "limit": {
+            "type": "integer",
+            "title": "Limit",
+            "description": "Maximum number to return.",
+            "default": 10,
+            "minimum": 1,
+            "maximum": 1000
+          },
+          "offset": {
+            "type": "integer",
+            "title": "Offset",
+            "description": "Offset to start from.",
+            "default": 0,
+            "minimum": 0
+          }
+        },
+        "type": "object",
+        "required" : [],
+        "title": "CronSearch",
+        "description": "Payload for listing crons"
+      },
       "GraphSchema": {
         "properties": {
           "graph_id": {
@@ -2295,7 +2414,76 @@
         },
         "type": "object",
         "title": "SearchRequest",
-        "description": "Payload for listing assistants/threads/runs."
+        "description": "Payload for listing runs."
+      },
+      "AssistantSearchRequest": {
+        "properties": {
+          "metadata": {
+            "type": "object",
+            "title": "Metadata",
+            "description": "Metadata to search for."
+          },
+          "graph_id": {
+            "type": "string",
+            "title": "Graph Id",
+            "description": "Filter by graph ID."
+          },
+          "limit": {
+            "type": "integer",
+            "title": "Limit",
+            "description": "Maximum number to return.",
+            "default": 10,
+            "minimum": 1,
+            "maximum": 1000
+          },
+          "offset": {
+            "type": "integer",
+            "title": "Offset",
+            "description": "Offset to start from.",
+            "default": 0,
+            "minimum": 0
+          }
+        },
+        "type": "object",
+        "title": "SearchRequest",
+        "description": "Payload for listing assistants."
+      },
+      "ThreadSearchRequest": {
+        "properties": {
+          "metadata": {
+            "type": "object",
+            "title": "Metadata",
+            "description": "Metadata to search for."
+          },
+          "status": {
+            "type": "string",
+            "enum": [
+              "idle",
+              "busy",
+              "interrupted"
+            ],
+            "title": "Status",
+            "description": "Filter by thread status."
+          },
+          "limit": {
+            "type": "integer",
+            "title": "Limit",
+            "description": "Maximum number to return.",
+            "default": 10,
+            "minimum": 1,
+            "maximum": 1000
+          },
+          "offset": {
+            "type": "integer",
+            "title": "Offset",
+            "description": "Offset to start from.",
+            "default": 0,
+            "minimum": 0
+          }
+        },
+        "type": "object",
+        "title": "SearchRequest",
+        "description": "Payload for listing threads."
       },
       "Thread": {
         "properties": {
@@ -2317,6 +2505,15 @@
           "metadata": {
             "type": "object",
             "title": "Metadata"
+          },
+          "status": {
+            "type": "string",
+            "enum": [
+              "idle",
+              "busy",
+              "interrupted"
+            ],
+            "title": "Status"
           }
         },
         "type": "object",

docs/docs/cloud/reference/cli.md

@@ -3,9 +3,10 @@ The LangGraph CLI includes commands to build and run a LangGraph Cloud API serve
 
 ## Installation
 1. Ensure that Docker is installed (e.g. `docker --version`).
-1. Install the `langgraph-cli` Python package (e.g. `pip install langgraph-cli`).
-1. Run the command `langgraph --help` to confirm that the CLI is installed.
+2. Install the `langgraph-cli` Python package (e.g. `pip install langgraph-cli`).
+3. Run the command `langgraph --help` to confirm that the CLI is installed.
 
+[](){#langgraph.json}
 ## Configuration File
 The LangGraph CLI requires a JSON configuration file with the following keys:
 
@@ -82,44 +83,8 @@ langgraph build [OPTIONS]
 | `-c, --config FILE` | `langgraph.json` | Path to configuration file declaring dependencies, graphs and environment variables. |
 | `--help` | | Display command documentation. |
 
-### `down`
-Stop LangGraph Cloud API server.
-
-**Usage**
-```
-langgraph down [OPTIONS]
-```
-
-**Options**
-
-| Option | Default | Description |
-| ------ | ------- | ----------- |
-| `--debugger-port INTEGER` | | Pull the debugger image locally and serve the UI on specified port. |
-| `--verbose` | | Show more output from the server logs. |
-| `-c, --config FILE` | `langgraph.json` | Path to configuration file declaring dependencies, graphs and environment variables. |
-| `-d, --docker-compose FILE` | | Advanced. Path to `docker-compose.yml` file with additional services to launch. |
-| `-p, --port INTEGER` | `8123` | Port to expose. Example: `langgraph up --port 8000` |
-| `--help` | | Display command documentation. |
-
-### `logs`
-Show LangGraph Cloud API server logs.
-
-**Usage**
-```
-langgraph logs [OPTIONS]
-```
-
-**Options**
-
-| Option | Default | Description |
-| ------ | ------- | ----------- |
-| `-f, --follow` | | Follow logs. |
-| `-c, --config FILE` | `langgraph.json` | Path to configuration file declaring dependencies, graphs and environment variables. |
-| `-d, --docker-compose FILE` | | Advanced. Path to `docker-compose.yml` file with additional services to launch. |
-| `--help` | | Display command documentation. |
-
 ### `up`
-Start LangGraph Cloud API server.
+Start langgraph API server. For local testing, requires a LangSmith API key with access to LangGraph Cloud closed beta. Requires a license key for production use.
 
 **Usage**
 ```
@@ -130,13 +95,33 @@ langgraph up [OPTIONS]
 
 | Option | Default | Description |
 | ------ | ------- | ----------- |
-| `--wait` | | Wait for services to start before returning. Implies `--detach`. |
-| `--watch` | | Restart on file changes. |
-| `--debugger-port INTEGER` | | Pull the debugger image locally and serve the UI on specified port. |
+| `--wait` | | Wait for services to start before returning. Implies --detach |
+| `--postgres-uri TEXT` | Local database | Postgres URI to use for the database. |
+| `--watch` | | Restart on file changes |
+| `--debugger-base-url TEXT` | `http://127.0.0.1:[PORT]` | URL used by the debugger to access LangGraph API. |
+| `--debugger-port INTEGER` | | Pull the debugger image locally and serve the UI on specified port |
 | `--verbose` | | Show more output from the server logs. |
 | `-c, --config FILE` | `langgraph.json` | Path to configuration file declaring dependencies, graphs and environment variables. |
-| `-d, --docker-compose FILE` | | Advanced. Path to `docker-compose.yml` file with additional services to launch. |
-| `-p, --port INTEGER` | `8123` | Port to expose. Example: `langgraph up --port 8000` |
-| `--pull / --no-pull` | `--pull` | Build with latest remote Docker image. Use `--no-pull` for running the LangGraph Cloud API server with locally built images. |
-| `--recreate / --no-recreate` | `--no-recreate` | Recreate containers even if their configuration and image haven't changed. |
-| `--help` | | Display command documentation. |
+| `-d, --docker-compose FILE` | | Path to docker-compose.yml file with additional services to launch. |
+| `-p, --port INTEGER` | `8123` | Port to expose. Example: `langgraph test --port 8000` |
+| `--pull / --no-pull` | `pull` | Pull latest images. Use --no-pull for running the server with locally-built images. Example: `langgraph up --no-pull` |
+| `--recreate / --no-recreate` | `no-recreate` | Recreate containers even if their configuration and image haven't changed |
+| `--help` | | Display command documentation. | 
+
+### `test`
+Test your LangGraph in the cloud. The only function you can call from the SDK after testing your graph is `client.runs.stream(thread_id=None, ...)`
+
+**Usage**
+```
+langgraph test [OPTIONS]
+```
+
+**Options**
+
+| Option | Default | Description |
+| ------ | ------- | ----------- |
+| `--verbose` | | Show more output from the server logs. |
+| `-c, --config FILE` | `langgraph.json` | Path to configuration file declaring dependencies, graphs and environment variables. |
+| `-p, --port INTEGER` | `8123` | Port to expose. Example: `langgraph test --port 8000` |
+| `--pull / --no-pull` | `pull` | Pull latest images. Use --no-pull for running the server with locally-built images. Example: `langgraph up --no-pull` |
+| `--help` | | Display command documentation. |

docs/docs/concepts/agentic_concepts.md

@@ -16,17 +16,21 @@ Since LangGraph nodes can be arbitrary Python functions, you can do this however
 
 Memory is a key concept to agentic applications. Memory is important because end users often expect the application they are interacting with remember previous interactions. The most simple example of this is chatbots - they clearly need to remember previous messages in a conversation.
 
-LangGraph is perfectly suited to give you full control over the memory of your application. With user defined [`State`](#state) you can specify the exact schema of the memory you want to retain. With [checkpointers](#checkpointer) you can store checkpoints of previous interactions and resume from there in follow up interactions.
+LangGraph is perfectly suited to give you full control over the memory of your application. With user defined [`State`](./low_level.md#state) you can specify the exact schema of the memory you want to retain. With [checkpointers](./low_level.md#checkpointer) you can store checkpoints of previous interactions and resume from there in follow up interactions.
+
+See [this guide](../how-tos/persistence.ipynb) for how to add memory to your graph.
 
 ## Human-in-the-loop
 
-Agentic systems often require some human-in-the-loop (or "on-the-loop") interaction patterns. This is because agentic systems are still not super reliable, so having a human involved is required for any sensitive tasks/actions. These are all easily enabled in LangGraph, largely due to [checkpointers](#checkpointer). The reason a checkpointer is necessary is that a lot of these interaction patterns involve running a graph up until a certain point, waiting for some sort of human feedback, and then continuing. When you want to "continue" you will need to access the state of the graph previous to getting interrupted, and checkpointers are a built in, highly convenient way to do that.
+Agentic systems often require some human-in-the-loop (or "on-the-loop") interaction patterns. This is because agentic systems are still not super reliable, so having a human involved is required for any sensitive tasks/actions. These are all easily enabled in LangGraph, largely due to [checkpointers](./low_level.md#checkpointer). The reason a checkpointer is necessary is that a lot of these interaction patterns involve running a graph up until a certain point, waiting for some sort of human feedback, and then continuing. When you want to "continue" you will need to access the state of the graph previous to getting interrupted, and checkpointers are a built in, highly convenient way to do that.
 
 There are a few common human-in-the-loop interaction patterns we see emerging.
 
 ### Approval
 
-A basic one is to have the agent wait for approval before executing certain tools. This may be all tools, or just a subset of tools. This is generally recommend for more sensitive actions (like writing to a database). This can easily be done in LangGraph by setting a [breakpoint](#breakpoints) before specific nodes.
+A basic one is to have the agent wait for approval before executing certain tools. This may be all tools, or just a subset of tools. This is generally recommend for more sensitive actions (like writing to a database). This can easily be done in LangGraph by setting a [breakpoint](./low_level.md#breakpoints) before specific nodes.
+
+See [this guide](../how-tos/human_in_the_loop/breakpoints.ipynb) for how do this in LangGraph.
 
 ### Wait for input
 
@@ -38,21 +42,27 @@ A similar one is to have the agent wait for human input. This can be done by:
 4. Update the state with that user input, acting as that node
 5. Resume execution
 
+See [this guide](../how-tos/human_in_the_loop/wait-user-input.ipynb) for how do this in LangGraph.
+
 ### Edit agent actions
 
-This is a more advanced interaction pattern. In this interaction pattern the human can actually edit some of the agent's previous decisions. This can be done either during the flow (after a [breakpoint](#breakpoints), part of the [approval](#approval) flow) or after the fact (as part of [time-travel](#time-travel))
+This is a more advanced interaction pattern. In this interaction pattern the human can actually edit some of the agent's previous decisions. This can be done either during the flow (after a [breakpoint](./low_level.md#breakpoints), part of the [approval](#approval) flow) or after the fact (as part of [time-travel](#time-travel))
+
+See [this guide](../how-tos/human_in_the_loop/edit-graph-state.ipynb) for how do this in LangGraph.
 
 ### Time travel
 
 This is a pretty advanced interaction pattern. In this interaction pattern, the human can look back at the list of previous checkpoints, find one they like, optionally [edit it](#edit-agent-actions), and then resume execution from there.
 
+See [this guide](../how-tos/human_in_the_loop/time-travel.ipynb) for how to do this in LangGraph.
+
 ## Map-Reduce
 
 A common pattern in agents is to generate a list of objects, do some work on each of those objects, and then combine the results. This is very similar to the common [map-reduce](https://en.wikipedia.org/wiki/MapReduce) operation. This can be tricky for a few reasons. First, it can be tough to define a structured graph ahead of time because the length of the list of objects may be unknown. Second, in order to do this map-reduce you need multiple versions of the state to exist... but the graph shares a common shared state, so how can this be?
 
-LangGraph supports this via the [Send](#send) api. This can be used to allow a conditional edge to Send multiple different states to multiple nodes. The state it sends can be different from the state of the core graph.
+LangGraph supports this via the [Send](./low_level.md#send) api. This can be used to allow a conditional edge to Send multiple different states to multiple nodes. The state it sends can be different from the state of the core graph.
 
-See a how-to guide for this [here](https://langchain-ai.github.io/langgraph/how-tos/map-reduce/)
+See a how-to guide for this [here](../how-tos/map-reduce.ipynb)
 
 ## Multi-agent
 
@@ -76,7 +86,7 @@ This "reflection" step often uses an LLM, but doesn't have to. A good example of
 
 One of the most common agent architectures is what is commonly called the ReAct agent architecture. In this architecture, an LLM is called repeatedly in a while-loop. At each step the agent decides which tools to call, and what the inputs to those tools should be. Those tools are then executed, and the outputs are fed back into the LLM as observations. The while-loop terminates when the agent decides it is not worth calling any more tools.
 
-One of the few high level, pre-built agents we have in LangGraph - you can use it with [`create_react_agent`](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent)
+One of the few high level, pre-built agents we have in LangGraph - you can use it with [`create_react_agent`](../reference/prebuilt.md#create_react_agent)
 
 This is named after and based on the [ReAct](https://arxiv.org/abs/2210.03629) paper. However, there are several differences between this paper and our implementation:
 
@@ -85,3 +95,5 @@ This is named after and based on the [ReAct](https://arxiv.org/abs/2210.03629) p
 - Third, the paper required all inputs to the tools to be a single string. This was largely due to LLMs not being super capable at the time, and only really being able to generate a single input. Our implementation allows for using tools that require multiple inputs.
 - Forth, the paper only looks at calling a single tool at the time, largely due to limitations in LLMs performance at the time. Our implementation allows for calling multiple tools at a time.
 - Finally, the paper asked the LLM to explicitly generate a "Thought" step before deciding which tools to call. This is the "Reasoning" part of "ReAct". Our implementation does not do this by default, largely because LLMs have gotten much better and that is not as necessary. Of course, if you wish to prompt it do so, you certainly can.
+
+See [this guide](../how-tos/human_in_the_loop/time-travel.ipynb) for a full walkthrough of how to use the prebuilt ReAct agent.

docs/docs/concepts/faq.md

@@ -0,0 +1,15 @@
+# FAQ
+
+Common questions and their answers!
+
+## Do I need to use LangChain in order to use LangGraph?
+
+No! LangGraph is a general-purpose framework - the nodes and edges are nothing more than Python functions. You can use LangChain, raw HTTP requests, or even other frameworks inside these nodes and edges.
+
+## Does LangGraph work with LLMs that don't support tool calling?
+
+Yes! You can use LangGraph with any LLMs. The main reason we use LLMs that support tool calling is that this is often the most convenient way to have the LLM make its decision about what to do. If your LLM does not support tool calling, you can still use it - you just need to write a bit of logic to convert the raw LLM string response to a decision about what to do.
+
+## Does LangGraph work with OSS LLMs?
+
+Yes! LangGraph is totally ambivalent to what LLMs are used under the hood. The main reason we use closed LLMs in most of the tutorials is that they seamlessly support tool calling, while OSS LLMs often don't. But tool calling is not necessary (see [this section](#does-langgraph-work-with-llms-that-dont-support-tool-calling)) so you can totally use LangGraph with OSS LLMs.

docs/docs/concepts/high_level.md

@@ -17,18 +17,18 @@ If these decisions are being made in a loop, then its even more agentic!
 
 There are other concepts often associated with being agentic, but we would argue these are a by-product of the above definition:
 
-- Tool calling: this is often how LLMs make decisions
+- [Tool calling](agentic_concepts.md#tool-calling): this is often how LLMs make decisions
 - Action taking: often times, the LLMs' outputs are used as the input to an action
-- Memory: reliable systems need to have knowledge of things that occurred
-- Planning: planning steps (either explicit or implicit) are useful for ensuring that the LLM, when making decisions, makes them in the highest fidelity way.
+- [Memory](agentic_concepts.md#memory): reliable systems need to have knowledge of things that occurred
+- [Planning](agentic_concepts.md#planning): planning steps (either explicit or implicit) are useful for ensuring that the LLM, when making decisions, makes them in the highest fidelity way.
 
 ## Why LangGraph?
 
 LangGraph has several core principles that we believe make it the most suitable framework for building agentic applications:
 
-- Controllability
-- Human-in-the-Loop
-- Streaming First
+- [Controllability](../how-tos/index.md#controllability)
+- [Human-in-the-Loop](../how-tos/index.md#human-in-the-loop)
+- [Streaming First](../how-tos/index.md#streaming)
 
 **Controllability**
 
@@ -40,7 +40,7 @@ LangGraph comes with a built-in persistence layer as a first-class concept. This
 
 **Streaming First**
 
-LangGraph comes with first class support for streaming. Agentic applications often take a while to run, and so giving the user some idea of what is happening is important, and streaming is a great way to do that. LangGraph supports streaming of both events (like a tool call being taken) as well as of tokens that an LLM may emit.
+LangGraph comes with first class support for streaming. Agentic applications often take a while to run, and so giving the user some idea of what is happening is important, and streaming is a great way to do that. LangGraph supports streaming of both events ([like a tool call being taken](../how-tos/stream-updates.ipynb)) as well as of [tokens that an LLM may emit](../how-tos/streaming-tokens.ipynb).
 
 ## Deployment
 
@@ -48,8 +48,8 @@ So you've built your LangGraph object - now what?
 
 Now you need to deploy it. 
 There are many ways to deploy LangGraph objects, and the right solution depends on your needs and use case.
-We'll highlight two ways here: using [LangGraph Cloud](/langgraph/cloud) or rolling your own solution.
+We'll highlight two ways here: using [LangGraph Cloud](../cloud/index.md) or rolling your own solution.
 
-[LangGraph Cloud](/langgraph/cloud) is an opinionated way to deploy LangGraph objects from the LangChain team. Please see the [LangGraph Cloud documentation](/langgraph/cloud) for all the details about what it involves, to see if it is a good fit for you.
+[LangGraph Cloud](../cloud/index.md) is an opinionated way to deploy LangGraph objects from the LangChain team. Please see the [LangGraph Cloud documentation](../cloud/index.md) for all the details about what it involves, to see if it is a good fit for you.
 
 If it is not a good fit, you may want to roll your own deployment. In this case, we would recommend using [FastAPI](https://fastapi.tiangolo.com/) to stand up a server. You can then call this graph from inside the FastAPI server as you see fit.

docs/docs/concepts/index.md

@@ -1,57 +1,57 @@
 # Conceptual Guides
 
-In this guide we will explore the concepts behind build agentic and multi-agent systems with LangGraph. We assume you have already learned the basic covered in the [introduction tutorial](https://langchain-ai.github.io/langgraph/tutorials/introduction) and want to deepen your understanding of LangGraph's underlying design and inner workings.
+In this guide we will explore the concepts behind build agentic and multi-agent systems with LangGraph. We assume you have already learned the basic covered in the [introduction tutorial](../tutorials/introduction.ipynb) and want to deepen your understanding of LangGraph's underlying design and inner workings.
 
-There are three main parts to this concept guide. First, we'll discuss at a very high level what it means to be agentic. Next, we'll look at lower-level concepts in LangGraph that are core for understanding how to build your own agentic systems. Finally, we'll discuss common agentic patterns and how you can achieve those with LangGraph. These will be mostly conceptual guides - for more technical, hands-on guides see our [how-to guides](https://langchain-ai.github.io/langgraph/how-tos/)
+There are three main parts to this concept guide. First, we'll discuss at a very high level what it means to be agentic. Next, we'll look at lower-level concepts in LangGraph that are core for understanding how to build your own agentic systems. Finally, we'll discuss common agentic patterns and how you can achieve those with LangGraph. These will be mostly conceptual guides - for more technical, hands-on guides see our [how-to guides](../how-tos/index.md)
 
 
 LangGraph for Agentic Applications
 
-- [What does it mean to be agentic?](high_level#what-does-it-mean-to-be-agentic)
-- [Why LangGraph](high_level#why-langgraph)
-- [Deployment](high_level#deployment)
+- [What does it mean to be agentic?](high_level.md#what-does-it-mean-to-be-agentic)
+- [Why LangGraph](high_level.md#why-langgraph)
+- [Deployment](high_level.md#deployment)
 
 Low Level Concepts
 
-- [Graphs](low_level#graphs)
-  - [StateGraph](low_level#stategraph)
-  - [MessageGraph](low_level#messagegraph)
-  - [Compiling Your Graph](low_level#compiling-your-graph)
-- [State](low_level#state)
-  - [Schema](low_level#schema)
-  - [Reducers](low_level#reducers)
-  - [MessageState](low_level#messagestate)
-- [Nodes](low_level#nodes)
-  - [`START` node](low_level#start-node)
-  - [`END` node](low_level#end-node)
-- [Edges](low_level#edges)
-  - [Normal Edges](low_level#normal-edges)
-  - [Conditional Edges](low_level#conditional-edges)
-  - [Entry Point](low_level#entry-point)
-  - [Conditional Entry Point](low_level#conditional-entry-point)
-- [Send](low_level#send)
-- [Checkpointer](low_level#checkpointer)
-- [Threads](low_level#threads)
-- [Checkpointer states](low_level#checkpointer-state)
-  - [Get state](low_level#get-state)
-  - [Get state history](low_level#get-state-history)
-  - [Update state](low_level#update-state)
-- [Configuration](low_level#configuration)
-- [Visualization](low_level#visualization)
-- [Streaming](low_level#streaming)
+- [Graphs](low_level.md#graphs)
+    - [StateGraph](low_level.md#stategraph)
+    - [MessageGraph](low_level.md#messagegraph)
+    - [Compiling Your Graph](low_level.md#compiling-your-graph)
+- [State](low_level.md#state)
+    - [Schema](low_level.md#schema)
+    - [Reducers](low_level.md#reducers)
+    - [MessageState](low_level.md#messagestate)
+- [Nodes](low_level.md#nodes)
+    - [`START` node](low_level.md#start-node)
+    - [`END` node](low_level.md#end-node)
+- [Edges](low_level.md#edges)
+    - [Normal Edges](low_level.md#normal-edges)
+    - [Conditional Edges](low_level.md#conditional-edges)
+    - [Entry Point](low_level.md#entry-point)
+    - [Conditional Entry Point](low_level.md#conditional-entry-point)
+- [Send](low_level.md#send)
+- [Checkpointer](low_level.md#checkpointer)
+- [Threads](low_level.md#threads)
+- [Checkpointer states](low_level.md#checkpointer-state)
+    - [Get state](low_level.md#get-state)
+    - [Get state history](low_level.md#get-state-history)
+    - [Update state](low_level.md#update-state)
+- [Configuration](low_level.md#configuration)
+- [Visualization](low_level.md#visualization)
+- [Streaming](low_level.md#streaming)
 
 Common Agentic Patterns
 
-- [Structured output](agentic_concepts#structured-output)
-- [Tool calling](agentic_concepts#tool-calling)
-- [Memory](agentic_concepts#memory)
-- [Human in the loop](agentic_concepts#human-in-the-loop)
-  - [Approval](agentic_concepts#approval)
-  - [Wait for input](agentic_concepts#wait-for-input)
-  - [Edit agent actions](agentic_concepts#edit-agent-actions)
-  - [Time travel](agentic_concepts#time-travel)
-- [Map-Reduce](agentic_concepts#map-reduce)
-- [Multi-agent](agentic_concepts#multi-agent)
-- [Planning](agentic_concepts#planning)
-- [Reflection](agentic_concepts#reflection)
-- [Off-the-shelf ReAct Agent](agentic_concepts#react-agent)
+- [Structured output](agentic_concepts.md#structured-output)
+- [Tool calling](agentic_concepts.md#tool-calling)
+- [Memory](agentic_concepts.md#memory)
+- [Human in the loop](agentic_concepts.md#human-in-the-loop)
+    - [Approval](agentic_concepts.md#approval)
+    - [Wait for input](agentic_concepts.md#wait-for-input)
+    - [Edit agent actions](agentic_concepts.md#edit-agent-actions)
+    - [Time travel](agentic_concepts.md#time-travel)
+- [Map-Reduce](agentic_concepts.md#map-reduce)
+- [Multi-agent](agentic_concepts.md#multi-agent)
+- [Planning](agentic_concepts.md#planning)
+- [Reflection](agentic_concepts.md#reflection)
+- [Off-the-shelf ReAct Agent](agentic_concepts.md#react-agent)

docs/docs/concepts/low_level.md

@@ -4,17 +4,19 @@
 
 At its core, LangGraph models agent workflows as graphs. You define the behavior of your agents using three key components:
 
-1. `State`: A shared data structure that represents the current snapshot of your application. It can be any Python type, but is typically a `TypedDict` or Pydantic `BaseModel`.
+1. [`State`](#state): A shared data structure that represents the current snapshot of your application. It can be any Python type, but is typically a `TypedDict` or Pydantic `BaseModel`.
 
-2. `Nodes`: Python functions that encode the logic of your agents. They receive the current `State` as input, perform some computation or side-effect, and return an updated `State`.
+2. [`Nodes`](#nodes): Python functions that encode the logic of your agents. They receive the current `State` as input, perform some computation or side-effect, and return an updated `State`.
 
-3. `Edges`: Python functions that determine which `Node` to execute next based on the current `State`. They can be conditional branches or fixed transitions.
+3. [`Edges`](#edges): Python functions that determine which `Node` to execute next based on the current `State`. They can be conditional branches or fixed transitions.
 
 By composing `Nodes` and `Edges`, you can create complex, looping workflows that evolve the `State` over time. The real power, though, comes from how LangGraph manages that `State`. To emphasize: `Nodes` and `Edges` are nothing more than Python functions - they can contain an LLM or just good ol' Python code.
 
 In short: _nodes do the work. edges tell what to do next_.
 
-LangGraph's underlying graph algorithm uses [message passing](https://en.wikipedia.org/wiki/Message_passing) to define a general program. When a `Node` completes, it sends a message along one or more edges to other node(s). These nodes run their functions, pass the resulting messages to the next set of nodes, and on and on it goes. Inspired by [Pregel](https://research.google/pubs/pregel-a-system-for-large-scale-graph-processing/), the program proceeds in discrete "super-steps" that are all executed conceptually in parallel. Whenever the graph is run, all the nodes start in an `inactive` state. Whenever an incoming edge (or "channel") receives a new message (state), the node becomes `active`, runs the function, and responds with updates. At the end of each superstep, each node votes to `halt` by marking itself as `inactive` if it has no more incoming messages. The graph terminates when all nodes are `inactive` and when no messages are in transit.
+LangGraph's underlying graph algorithm uses [message passing](https://en.wikipedia.org/wiki/Message_passing) to define a general program. When a Node completes its operation, it sends messages along one or more edges to other node(s). These recipient nodes then execute their functions, pass the resulting messages to the next set of nodes, and the process continues. Inspired by Google's [Pregel](https://research.google/pubs/pregel-a-system-for-large-scale-graph-processing/) system, the program proceeds in discrete "super-steps."
+
+A super-step can be considered a single iteration over the graph nodes. Nodes that run in parallel are part of the same super-step, while nodes that run sequentially belong to separate super-steps. At the start of graph execution, all nodes begin in an `inactive` state. A node becomes `active` when it receives a new message (state) on any of its incoming edges (or "channels"). The active node then runs its function and responds with updates. At the end of each super-step, nodes with no incoming messages vote to `halt` by marking themselves as `inactive`. The graph execution terminates when all nodes are `inactive` and no messages are in transit.
 
 ### StateGraph
 
@@ -38,11 +40,11 @@ You **MUST** compile your graph before you can use it.
 
 ## State
 
-The first thing you do when you define a graph is define the `State` of the graph. The `State` consists of the schema of graph as well as `reducer` functions which specify how to apply updates to the state. The schema of the `State` will be the input schema to all `Nodes` and `Edges` in the graph, and can be either a `TypedDict` or a `Pydantic` model. All `Nodes` will emit updates to the `State` which are then applied using the specified `reducer` function.
+The first thing you do when you define a graph is define the `State` of the graph. The `State` consists of the [schema of the graph](#schema) as well as [`reducer` functions](#reducers) which specify how to apply updates to the state. The schema of the `State` will be the input schema to all `Nodes` and `Edges` in the graph, and can be either a `TypedDict` or a `Pydantic` model. All `Nodes` will emit updates to the `State` which are then applied using the specified `reducer` function.
 
 ### Schema
 
-The main documented way to specify the schema of a graph is by using `TypedDict`. However, we also support [using a Pydantic BaseModel](https://langchain-ai.github.io/langgraph/how-tos/state-model/) as your graph state to add **default values** and additional data validation.
+The main documented way to specify the schema of a graph is by using `TypedDict`. However, we also support [using a Pydantic BaseModel](../how-tos/state-model.ipynb) as your graph state to add **default values** and additional data validation.
 
 ### Reducers
 
@@ -60,7 +62,6 @@ class State(TypedDict):
 
 In this example, no reducer functions are specified for any key. Let's assume the input to the graph is `{"foo": 1, "bar": ["hi"]}`. Let's then assume the first `Node` returns `{"foo": 2}`. This is treated as an update to the state. Notice that the `Node` does not need to return the whole `State` schema - just an update. After applying this update, the `State` would then be `{"foo": 2, "bar": ["hi"]}`. If the second node returns `{"bar": ["bye"]}` then the `State` would then be `{"foo": 2, "bar": ["bye"]}`
 
-
 **Example B:**
 
 ```python
@@ -74,7 +75,6 @@ class State(TypedDict):
 
 In this example, we've used the `Annotated` type to specify a reducer function (`operator.add`) for the second key (`bar`). Note that the first key remains unchanged. Let's assume the input to the graph is `{"foo": 1, "bar": ["hi"]}`. Let's then assume the first `Node` returns `{"foo": 2}`. This is treated as an update to the state. Notice that the `Node` does not need to return the whole `State` schema - just an update. After applying this update, the `State` would then be `{"foo": 2, "bar": ["hi"]}`. If the second node returns `{"bar": ["bye"]}` then the `State` would then be `{"foo": 2, "bar": ["hi", "bye"]}`. Notice here that the `bar` key is updated by adding the two lists together.
 
-
 ### MessageState
 
 `MessageState` is one of the few opinionated components in LangGraph. `MessageState` is a special state designed to make it easy to use a list of messages as a key in your state. Specifically, `MessageState` is defined as:
@@ -103,7 +103,7 @@ class State(MessagesState):
 
 In LangGraph, nodes are typically python functions (sync or `async`) where the **first** positional argument is the [state](#state), and (optionally), the **second** positional argument is a "config", containing optional [configurable parameters](#configuration) (such as a `thread_id`).
 
-Similar to `NetworkX`, you add these nodes to a graph using the [add_node](https://langchain-ai.github.io/langgraph/reference/graphs/#langgraph.graph.MessageGraph) method:
+Similar to `NetworkX`, you add these nodes to a graph using the [add_node][langgraph.graph.StateGraph.add_node] method:
 
 ```python
 from langchain_core.runnables import RunnableConfig
@@ -127,7 +127,6 @@ builder.add_node("other_node", my_other_node)
 ...
 ```
 
-
 Behind the scenes, functions are converted to [RunnableLambda's](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.RunnableLambda.html#langchain_core.runnables.base.RunnableLambda), which add batch and async support to your function, along with native tracing and debugging.
 
 If you add a node to graph without specifying a name, it will be given a default name equivalent to the function name.
@@ -170,7 +169,7 @@ A node can have MULTIPLE outgoing edges. If a node has multiple out-going edges,
 
 ### Normal Edges
 
-If you **always** want to go from node A to node B, you can use the [add_edge](https://langchain-ai.github.io/langgraph/reference/graphs/#langgraph.graph.StateGraph.add_edge) method directly.
+If you **always** want to go from node A to node B, you can use the [add_edge][langgraph.graph.StateGraph.add_edge] method directly.
 
 ```python
 graph.add_edge("node_a", "node_b")
@@ -178,10 +177,10 @@ graph.add_edge("node_a", "node_b")
 
 ### Conditional Edges
 
-If you want to **optionally** route to 1 or more edges (or optionally terminate), you can use the [add_conditional_edges](https://langchain-ai.github.io/langgraph/reference/graphs/#langgraph.graph.StateGraph.add_conditional_edges) method. This method accepts the name of a node and a "routing function" to call after that node is executed:
+If you want to **optionally** route to 1 or more edges (or optionally terminate), you can use the [add_conditional_edges][langgraph.graph.StateGraph.add_conditional_edges] method. This method accepts the name of a node and a "routing function" to call after that node is executed:
 
 ```python
-graph.add_edge("node_a", routing_function)
+graph.add_conditional_edges("node_a", routing_function)
 ```
 
 Similar to nodes, the `routing_function` accept the current `state` of the graph and return a value.
@@ -191,18 +190,12 @@ By default, the return value `routing_function` is used as the name of the node
 You can optionally provide a dictionary that maps the `routing_function`'s output to the name of the next node.
 
 ```python
-graph.add_edge("node_a", routing_function, {True: "node_b", False: "node_c"})
+graph.add_conditional_edges("node_a", routing_function, {True: "node_b", False: "node_c"})
 ```
 
 ### Entry Point
 
-The entry point is first node to call when the graph starts.
-
-```python
-graph.set_entry_point("node_a")
-```
-
-This is equivalent to adding an edge between the `START` node and this node. You may want to use `START` directly when you want to have **multiple** nodes be called first.
+The entry point is the first node(s) that are run when the graph starts. You can use the [`add_edge`][langgraph.graph.StateGraph.add_edge] method from the virtual [`START`][start] node to the first node to execute to specify where to enter the graph.
 
 ```python
 from langgraph.graph import START
@@ -212,23 +205,25 @@ graph.add_edge(START, "node_a")
 
 ### Conditional Entry Point
 
-The conditional entry point is used when you want to specify a function to call to determine which node(s) should be called first.
+A conditional entry point lets you start at different nodes depending on custom logic. You can use [`add_conditional_edges`][langgraph.graph.StateGraph.add_conditional_edges] from the virtual [`START`][start] node to accomplish this.
 
 ```python
-graph.set_conditional_entry_point(routing_function)
+from langgraph.graph import START
+
+graph.add_conditional_edges(START, routing_function)
 ```
 
 You can optionally provide a dictionary that maps the `routing_function`'s output to the name of the next node.
 
 ```python
-graph.set_conditional_entry_point(routing_function, {True: "node_b", False: "node_c"})
+graph.add_conditional_edges(START, routing_function, {True: "node_b", False: "node_c"})
 ```
 
 ## `Send`
 
 By default, `Nodes` and `Edges` are defined ahead of time and operate on the same shared state. However, there can be cases where the exact edges are not known ahead of time and/or you may want different versions of `State` to exist at the same time. A common of example of this is with `map-reduce` design patterns. In this design pattern, a first node may generate a list of objects, and you may want to apply some other node to all those objects. The number of objects may be unknown ahead of time (meaning the number of edges may not be known) and the input `State` to the downstream `Node` should be different (one for each generated object).
 
-To support this design pattern, LangGraph supports returning [`Send`](https://langchain-ai.github.io/langgraph/reference/graphs/#send) objects from conditional edges. `Send` takes two arguments: first is the name of the node, and second is the state to pass to that node.
+To support this design pattern, LangGraph supports returning [`Send`](../reference/graphs.md#send) objects from conditional edges. `Send` takes two arguments: first is the name of the node, and second is the state to pass to that node.
 
 ```python
 def continue_to_jokes(state: OverallState):
@@ -239,18 +234,17 @@ graph.add_conditional_edges("node_a", continue_to_jokes)
 
 ## Checkpointer
 
-One of the main benefits of LangGraph is that it comes backed by a persistence layer. This is accomplished via [checkpointers](https://langchain-ai.github.io/langgraph/reference/checkpoints/#basecheckpointsaver).
+LangGraph has a built-in persistence layer, implemented through [checkpointers][basecheckpointsaver]. When you use a checkpointer with a graph, you can interact with the state of that graph. When you use a checkpointer with a graph, you can interact with and manage the graph's state. The checkpointer saves a _checkpoint_ of the graph state at every super-step, enabling several powerful capabilities:
 
-Checkpointers can be used to save a _checkpoint_ of the state of a graph after all steps of the graph. This allows for several things. 
+First, checkpointers facilitate [human-in-the-loop workflows](agentic_concepts.md#human-in-the-loop) workflows by allowing humans to inspect, interrupt, and approve steps.Checkpointers are needed for these workflows as the human has to be able to view the state of a graph at any point in time, and the graph has to be to resume execution after the human has made any updates to the state.
 
-First, it allows for human-in-the-loop workflows, as it allows humans to inspect, interrupt, and approve steps. Checkpointers are needed for these workflows as the human has to be able to view the state of a graph at any point in time, and the graph has to be to resume execution after the human has made any updates to the state.
+Second, it allows for ["memory"](agentic_concepts.md#memory) between interactions. You can use checkpointers to create threads and save the state of a thread after a graph executes. In the case of repeated human interactions (like conversations) any follow up messages can be sent to that checkpoint, which will retain its memory of previous ones.
 
-Second, it allows for "memory" between interactions. You can use checkpointers to create threads and save the state of a thread after a graph executes. In the case of repeated human interactions (like conversations) any follow up messages can be sent to that checkpoint, which will retain its memory of previous ones.
+See [this guide](../how-tos/persistence.ipynb) for how to add a checkpointer to your graph.
 
 ## Threads
 
-When using a checkpointer, you must specify a `thread_id` or `thread_ts` when running the graph.
-Threads are used to checkpoint multiple different runs. This can be used to enable a multi-tenant chat applications.
+Threads enable the checkpointing of multiple different runs, making them essential for multi-tenant chat applications and other scenarios where maintaining separate states is necessary. A thread is a unique ID assigned to a series of checkpoints saved by a checkpointer. When using a checkpointer, you must specify a `thread_id` or `thread_ts` when running the graph.
 
 `thread_id` is simply the ID of a thread. This is always required
 
@@ -263,16 +257,14 @@ config = {"configurable": {"thread_id": "a"}}
 graph.invoke(inputs, config=config)
 ```
 
+See [this guide](../how-tos/persistence.ipynb) for how to use threads.
+
 ## Checkpointer state
 
-When you use a checkpointer with a graph, you can interact with the state of that graph.
-This usually done when enabling different human-in-the-loop interaction patterns.
-When interacting with the checkpointer state, you must specify [thread identifiers](#threads)
+ When interacting with the checkpointer state, you must specify a [thread identifier](#threads).Each checkpoint saved by the checkpointer has two properties:
 
-Each checkpoint has two properties:
-
--**values**: This is the value of the state at this point in time.
--**next**: This is a tuple of the nodes to execute next in the graph.
+- **values**: This is the value of the state at this point in time.
+- **next**: This is a tuple of the nodes to execute next in the graph.
 
 ### Get state
 
@@ -280,7 +272,7 @@ You can get the state of a checkpointer by calling `graph.get_state(config)`. Th
 
 ### Get state history
 
-You can also call `graph.get_state_history(config)` to get a list of the history of the graph. The config should contain `thread_id`, and the state history will be fetched for that thread. 
+You can also call `graph.get_state_history(config)` to get a list of the history of the graph. The config should contain `thread_id`, and the state history will be fetched for that thread.
 
 ### Update state
 
@@ -290,7 +282,6 @@ You can also interact with the state directly and update it. This takes three di
 - values
 - `as_node`
 
-
 **config**
 
 The config should contain `thread_id` specifying which thread to update.
@@ -310,13 +301,14 @@ class State(TypedDict):
     bar: Annotated[list[str], add]
 ```
 
-Let's now assume the current state of the graph is 
+Let's now assume the current state of the graph is
 
 ```
 {"foo": 1, "bar": ["a"]}
 ```
 
 If you update the state as below:
+
 ```
 graph.update_state(config, {"foo": 2, "bar": ["b"]})
 ```
@@ -365,9 +357,11 @@ def node_a(state, config):
     ...
 ```
 
+See [this guide](../how-tos/configuration.ipynb) for a full breakdown on configuration
+
 ## Breakpoints
 
-It can often be useful to set breakpoints before or after certain nodes execute. This can be used to wait for human approval before continuing. These can be set when you ["compile" a graph](#compiling-your-graph). You can set breakpoints either *before* a node executes (using `interrupt_before`) or after a node executes (using `interrupt_after`.) 
+It can often be useful to set breakpoints before or after certain nodes execute. This can be used to wait for human approval before continuing. These can be set when you ["compile" a graph](#compiling-your-graph). You can set breakpoints either _before_ a node executes (using `interrupt_before`) or after a node executes (using `interrupt_after`.)
 
 You **MUST** use a [checkpoiner](#checkpointer) when using breakpoints. This is because your graph needs to be able to resume execution.
 
@@ -381,17 +375,18 @@ graph.invoke(inputs, config=config)
 graph.invoke(None, config=config)
 ```
 
+See [this guide](../how-tos/human_in_the_loop/breakpoints.ipynb) for a full walkthrough of how to add breakpoints.
+
 ## Visualization
 
-It's often nice to be able to visualize graphs, especially as they get more complex. LangGraph comes with several built-in ways to visualize graphs. See [this how-to guide](https://langchain-ai.github.io/langgraph/how-tos/visualization/) for more info.
+It's often nice to be able to visualize graphs, especially as they get more complex. LangGraph comes with several built-in ways to visualize graphs. See [this how-to guide](../how-tos/visualization.ipynb) for more info.
 
 ## Streaming
 
 LangGraph is built with first class support for streaming. There are several different streaming modes that LangGraph supports:
 
-- `"values"`: This streams the full value of the state after each step of the graph.
-- `"updates`: This streams the updates to the state after each step of the graph. If multiple updates are made in the same step (e.g. multiple nodes are run) then those updates are streamed separately.
+- [`"values"`](../how-tos/stream-values.ipynb): This streams the full value of the state after each step of the graph.
+- [`"updates`](../how-tos/stream-updates.ipynb): This streams the updates to the state after each step of the graph. If multiple updates are made in the same step (e.g. multiple nodes are run) then those updates are streamed separately.
 - `"debug"`: This streams as much information as possible throughout the execution of the graph.
 
-In addition, you can use the [`astream_events`](https://langchain-ai.github.io/langgraph/how-tos/streaming-tokens/) method to stream back events that happen _inside_ nodes. This is useful for streaming tokens of LLM calls.
-
+In addition, you can use the [`astream_events`](../how-tos/streaming-events-from-within-tools.ipynb) method to stream back events that happen _inside_ nodes. This is useful for [streaming tokens of LLM calls](../how-tos/streaming-tokens.ipynb).

docs/docs/how-tos/index.md

@@ -16,12 +16,24 @@ These how-to guides show how to achieve that controllability.
 - [How to create branches for parallel execution](branching.ipynb)
 - [How to create map-reduce branches for parallel execution](map-reduce.ipynb)
 
+
+## Persistence
+
+LangGraph makes it easy to persist state across graph runs. The guide below shows how to add persistence to your graph.
+
+- [How to add persistence ("memory") to your graph](persistence.ipynb)
+- [How to manage conversation history](memory/manage-conversation-history.ipynb)
+- [How to delete messages](memory/delete-messages.ipynb)
+- [How to add summary conversation memory](memory/add-summary-conversation-history.ipynb)
+- [How to create a custom checkpointer using Postgres](persistence_postgres.ipynb)
+- [How to create a custom checkpointer using MongoDB](persistence_mongodb.ipynb)
+- [How to create a custom checkpointer using Redis](persistence_redis.ipynb)
+
 ## Human in the Loop
 
 One of LangGraph's main benefits is that it makes human-in-the-loop workflows easy.
 These guides cover common examples of that.
 
-- [How to add persistence ("memory") to your graph](persistence.ipynb)
 - [How to add breakpoints](human_in_the_loop/breakpoints.ipynb)
 - [How to edit graph state](human_in_the_loop/edit-graph-state.ipynb)
 - [How to wait for user input](human_in_the_loop/wait-user-input.ipynb)
@@ -35,15 +47,26 @@ These guides show how to use different streaming modes.
 - [How to stream full state of your graph](stream-values.ipynb)
 - [How to stream state updates of your graph](stream-updates.ipynb)
 - [How to stream LLM tokens](streaming-tokens.ipynb)
+- [How to stream LLM tokens without LangChain models](streaming-tokens-without-langchain.ipynb)
 - [How to stream arbitrarily nested content](streaming-content.ipynb)
 - [How to configure multiple streaming modes at the same time](stream-multiple.ipynb)
 - [How to stream events from within a tool](streaming-events-from-within-tools.ipynb)
+- [How to stream events from within a tool without LangChain models](streaming-events-from-within-tools-without-langchain.ipynb)
+- [How to stream events from the final node](streaming-from-final-node.ipynb)
+
+## Tool calling
+
+- [How to call tools using ToolNode](tool-calling.ipynb)
+- [How to handle tool calling errors](tool-calling-errors.ipynb)
+- [How to pass graph state to tools](pass-run-time-values-to-tools.ipynb)
 
 ## Other
+
 - [How to run graph asynchronously](async.ipynb)
 - [How to visualize your graph](visualization.ipynb)
 - [How to add runtime configuration to your graph](configuration.ipynb)
 - [How to use a Pydantic model as your state](state-model.ipynb)
+- [How to use a context object in state](state-context-key.ipynb)
 
 ## Prebuilt ReAct Agent
 

docs/docs/reference/checkpoints.md

@@ -1,6 +1,6 @@
 # Checkpoints
 
-You can [compile](https://langchain-ai.github.io/langgraph/reference/graphs/#langgraph.graph.MessageGraph.compile) any LangGraph workflow with a [CheckPointer](https://langchain-ai.github.io/langgraph/reference/checkpoints/#basecheckpointsaver) to give your agent "memory" by persisting its state. This permits things like:
+You can [compile][langgraph.graph.MessageGraph.compile] any LangGraph workflow with a [CheckPointer][basecheckpointsaver] to give your agent "memory" by persisting its state. This permits things like:
 
 - Remembering things across multiple interactions
 - Interrupting to wait for user input
@@ -9,7 +9,11 @@ You can [compile](https://langchain-ai.github.io/langgraph/reference/graphs/#lan
 
 ### Checkpoint
 
-::: langgraph.checkpoint.Checkpoint
+::: langgraph.checkpoint.base.Checkpoint
+
+### CheckpointMetadata
+
+::: langgraph.checkpoint.base.CheckpointMetadata
 
 ### BaseCheckpointSaver
 

docs/docs/tutorials/index.md

@@ -7,11 +7,11 @@ hide:
 
 Welcome to the LangGraph Tutorials! These notebooks introduce LangGraph through building various language agents and applications.
 
-## Introduction to LangGraph
+## Quick Start
 
-Learn the basics of LangGraph through the onboarding tutorials.
+Learn the basics of LangGraph through a comprehensive quick start in which you will build an agent from scratch.
 
-- [Introduction to LangGraph](introduction.ipynb)
+- [Quick Start](introduction.ipynb)
 
 ## Use cases
 

docs/mkdocs.yml

@@ -1,18 +1,17 @@
-site_name: LangGraph
+site_name: ""
 site_description: Build language agents as graphs
 site_url: https://langchain-ai.github.io/langgraph/
 repo_url: https://github.com/langchain-ai/langgraph
 theme:
   name: material
   custom_dir: overrides
-  logo: static/wordmark.png
+  logo_dark_mode: static/wordmark_light.svg
+  logo_light_mode: static/wordmark_dark.svg
   favicon: static/favicon.png
   icon:
     repo: fontawesome/brands/git-alt
   features:
     - announce.dismiss
-    - content.action.edit
-    - content.action.view
     - content.code.annotate
     - content.code.copy
     - content.code.select
@@ -34,18 +33,18 @@ theme:
     - search.suggest
     - toc.follow
   palette:
-  - scheme: default
-    primary: white
-    accent: gray
-    toggle:
-      icon: material/brightness-7
-      name: Switch to dark mode
-  - scheme: slate
-    primary: grey
-    accent: white
-    toggle:
-      icon: material/brightness-4
-      name: Switch to light mode
+    - scheme: default
+      primary: white
+      accent: gray
+      toggle:
+        icon: material/brightness-7
+        name: Switch to dark mode
+    - scheme: slate
+      primary: grey
+      accent: white
+      toggle:
+        icon: material/brightness-4
+        name: Switch to light mode
   font:
     text: "Public Sans"
     code: "Roboto Mono"
@@ -60,7 +59,7 @@ plugins:
             - https://docs.python.org/3/objects.inv
             - https://api.python.langchain.com/en/latest/objects.inv
           options:
-            members_order: source 
+            members_order: source
             allow_inspection: true
             heading_level: 3
             show_bases: true
@@ -68,9 +67,9 @@ plugins:
             inherited_members: true
             # merge_init_into_class: true
             selection:
-                docstring_style: google
+              docstring_style: google
             docstring_section_style: list
-            show_root_toc_entry: false 
+            show_root_toc_entry: false
             # show_signature_annotations: true
             # show_symbol_type_heading: true
             show_symbol_type_toc: true
@@ -80,20 +79,12 @@ plugins:
       execute: false
       include_source: True
       include_requirejs: true
-  - git-committers:
-      repository: langchain-ai/langgraph
-      branch: main
-      docs_path: docs/docs/
-      token: !ENV ["MKDOCS_GIT_COMMITTERS_APIKEY"]
-  # TODO: Add minify plugin once it works alright with code block copying
-  # - minify:
-  #     minify_html: true
 nav:
-  - Home: 
-      - 'index.md'
+  - Home:
+      - "index.md"
   - Tutorials:
-      - 'tutorials/index.md'
-      - Introduction: tutorials/introduction.ipynb
+      - "tutorials/index.md"
+      - Quick Start: tutorials/introduction.ipynb
       - Chatbots:
           - Customer Support: tutorials/customer-support/customer-support.ipynb
           - Prompt Generation from User Requirements: tutorials/chatbots/information-gather-prompting.ipynb
@@ -108,115 +99,137 @@ nav:
           - Self-RAG using local LLMs: tutorials/rag/langgraph_self_rag_local.ipynb
           - SQL Agent: tutorials/sql-agent.ipynb
       - Agent Architectures:
-        - Multi-Agent Systems:
-            - Collaboration: tutorials/multi_agent/multi-agent-collaboration.ipynb
-            - Supervision: tutorials/multi_agent/agent_supervisor.ipynb
-            - Hierarchical Teams: tutorials/multi_agent/hierarchical_agent_teams.ipynb
-        - Planning Agents:
-            - Plan-and-Execute: tutorials/plan-and-execute/plan-and-execute.ipynb
-            - Reasoning without Observation: tutorials/rewoo/rewoo.ipynb
-            - LLMCompiler: tutorials/llm-compiler/LLMCompiler.ipynb
-        - Reflection & Critique:
-            - Basic Reflection: tutorials/reflection/reflection.ipynb
-            - Reflexion: tutorials/reflexion/reflexion.ipynb
-            - Language Agent Tree Search: tutorials/lats/lats.ipynb
-            - Self-Discover Agent: tutorials/self-discover/self-discover.ipynb
+          - Multi-Agent Systems:
+              - Collaboration: tutorials/multi_agent/multi-agent-collaboration.ipynb
+              - Supervision: tutorials/multi_agent/agent_supervisor.ipynb
+              - Hierarchical Teams: tutorials/multi_agent/hierarchical_agent_teams.ipynb
+          - Planning Agents:
+              - Plan-and-Execute: tutorials/plan-and-execute/plan-and-execute.ipynb
+              - Reasoning without Observation: tutorials/rewoo/rewoo.ipynb
+              - LLMCompiler: tutorials/llm-compiler/LLMCompiler.ipynb
+          - Reflection & Critique:
+              - Basic Reflection: tutorials/reflection/reflection.ipynb
+              - Reflexion: tutorials/reflexion/reflexion.ipynb
+              - Language Agent Tree Search: tutorials/lats/lats.ipynb
+              - Self-Discover Agent: tutorials/self-discover/self-discover.ipynb
       - Evaluation & Analysis:
           - Chatbot Evaluation via Simulation:
               - Agent-based: tutorials/chatbot-simulation-evaluation/agent-simulation-evaluation.ipynb
               - In LangSmith: tutorials/chatbot-simulation-evaluation/langsmith-agent-simulation-evaluation.ipynb
       - Experimental:
-        - Web Research (STORM): tutorials/storm/storm.ipynb
-        - TNT-LLM: tutorials/tnt-llm/tnt-llm.ipynb
-        - Web Navigation: tutorials/web-navigation/web_voyager.ipynb
-        - Competitive Programming: tutorials/usaco/usaco.ipynb
-        - Extract structured output: tutorials/extraction/retries.ipynb
+          - Web Research (STORM): tutorials/storm/storm.ipynb
+          - TNT-LLM: tutorials/tnt-llm/tnt-llm.ipynb
+          - Web Navigation: tutorials/web-navigation/web_voyager.ipynb
+          - Competitive Programming: tutorials/usaco/usaco.ipynb
+          - Extract structured output: tutorials/extraction/retries.ipynb
 
   - "How-to Guides":
-     - 'how-tos/index.md'
-     - Controllability:
-         - Create subgraphs: how-tos/subgraph.ipynb
-         - Create branches for parallel execution: how-tos/branching.ipynb
-         - Create map-reduce branches for parallel execution: how-tos/map-reduce.ipynb
-     - Human-in-the-loop:
-         - Add persistence ("memory"): how-tos/persistence.ipynb
-         - Add breakpoints: how-tos/human_in_the_loop/breakpoints.ipynb
-         - Wait for user input: how-tos/human_in_the_loop/wait-user-input.ipynb
-         - View and update past graph state: how-tos/human_in_the_loop/time-travel.ipynb
-         - Edit graph state: how-tos/human_in_the_loop/edit-graph-state.ipynb
-     - Streaming:
-         - Stream full state: how-tos/stream-values.ipynb
-         - Stream state updates: how-tos/stream-updates.ipynb
-         - Stream LLM tokens: how-tos/streaming-tokens.ipynb
-         - Stream arbitrarily nested content: how-tos/streaming-content.ipynb
-         - Configure multiple streaming modes: how-tos/stream-multiple.ipynb
-         - Stream events from within tools: how-tos/streaming-events-from-within-tools.ipynb
-     - Other:
-         - Run graph asynchronously: how-tos/async.ipynb
-         - Visualize your graph: how-tos/visualization.ipynb
-         - Add runtime configuration: how-tos/configuration.ipynb
-         - Use Pydantic model as state: how-tos/state-model.ipynb
-     - Prebuilt ReAct Agent:
-         - Create a ReAct agent: how-tos/create-react-agent.ipynb
-         - Add memory to a ReAct agent: how-tos/create-react-agent-memory.ipynb
-         - Add a system prompt to a ReAct agent: how-tos/create-react-agent-system-prompt.ipynb
-         - Add human-in-the-Loop to a ReAct agent: how-tos/create-react-agent-hitl.ipynb
-  - 'Conceptual Guides':
-     - 'concepts/index.md'
-     - LangGraph for Agentic Applications: concepts/high_level.md
-     - Low Level LangGraph Concepts: concepts/low_level.md
-     - Common Agentic Patterns: concepts/agentic_concepts.md
+      - "how-tos/index.md"
+      - Controllability:
+          - Create subgraphs: how-tos/subgraph.ipynb
+          - Create branches for parallel execution: how-tos/branching.ipynb
+          - Create map-reduce branches for parallel execution: how-tos/map-reduce.ipynb
+      - Persistence:
+          - Add persistence ("memory"): how-tos/persistence.ipynb
+          - Manage conversation history: how-tos/memory/manage-conversation-history.ipynb
+          - Delete messages: how-tos/memory/delete-messages.ipynb
+          - Add summary of the conversation history: how-tos/memory/add-summary-conversation-history.ipynb
+          - Create custom checkpointer using Postgres: how-tos/persistence_postgres.ipynb
+          - Create custom checkpointer using MongoDB: how-tos/persistence_mongodb.ipynb
+          - Create custom checkpointer using Redis: how-tos/persistence_redis.ipynb
+      - Human-in-the-loop:
+          - Add breakpoints: how-tos/human_in_the_loop/breakpoints.ipynb
+          - Wait for user input: how-tos/human_in_the_loop/wait-user-input.ipynb
+          - View and update past graph state: how-tos/human_in_the_loop/time-travel.ipynb
+          - Edit graph state: how-tos/human_in_the_loop/edit-graph-state.ipynb
+      - Streaming:
+          - Stream full state: how-tos/stream-values.ipynb
+          - Stream state updates: how-tos/stream-updates.ipynb
+          - Stream LLM tokens: how-tos/streaming-tokens.ipynb
+          - Stream LLM tokens without LangChain models: how-tos/streaming-tokens-without-langchain.ipynb
+          - Stream arbitrarily nested content: how-tos/streaming-content.ipynb
+          - Configure multiple streaming modes: how-tos/stream-multiple.ipynb
+          - Stream events from within tools: how-tos/streaming-events-from-within-tools.ipynb
+          - Stream events from within tools without LangChain models: how-tos/streaming-events-from-within-tools-without-langchain.ipynb
+          - Stream events from the final node: how-tos/streaming-from-final-node.ipynb
+      - Tool calling:
+          - Call tools using ToolNode: how-tos/tool-calling.ipynb
+          - Handle tool calling errors: how-tos/tool-calling-errors.ipynb
+          - Pass graph state to tools: how-tos/pass-run-time-values-to-tools.ipynb
+      - Other:
+          - Run graph asynchronously: how-tos/async.ipynb
+          - Visualize your graph: how-tos/visualization.ipynb
+          - Add runtime configuration: how-tos/configuration.ipynb
+          - Use Pydantic model as state: how-tos/state-model.ipynb
+          - Use a context object in state: how-tos/state-context-key.ipynb
+      - Prebuilt ReAct Agent:
+          - Create a ReAct agent: how-tos/create-react-agent.ipynb
+          - Add memory to a ReAct agent: how-tos/create-react-agent-memory.ipynb
+          - Add a system prompt to a ReAct agent: how-tos/create-react-agent-system-prompt.ipynb
+          - Add human-in-the-Loop to a ReAct agent: how-tos/create-react-agent-hitl.ipynb
+  - "Conceptual Guides":
+      - "concepts/index.md"
+      - LangGraph for Agentic Applications: concepts/high_level.md
+      - Low Level LangGraph Concepts: concepts/low_level.md
+      - Common Agentic Patterns: concepts/agentic_concepts.md
+      - FAQ: concepts/faq.md
   - Reference:
       - Graphs: reference/graphs.md
       - Checkpointing: reference/checkpoints.md
       - Prebuilt Components: reference/prebuilt.md
       - Errors: reference/errors.md
-  - 'Cloud (alpha)':
-      - 'cloud/index.md'
+  - "Cloud (beta)":
+      - "cloud/index.md"
       - Tutorials:
-          - Quick Start: 'cloud/quick_start.md'
-      - How-to Guides:
+          - Quick Start: "cloud/quick_start.md"
+      - How-to Guides: 
+          - "cloud/how-tos/index.md"
           - Deployment:
-              - Setup App: 'cloud/deployment/setup.md'
-              - Deploy to Cloud: 'cloud/deployment/cloud.md'
-              - Test with Studio: 'cloud/deployment/studio.md'
-              - Self-Host: 'cloud/deployment/self_hosted.md'
+              - Setup App: "cloud/deployment/setup.md"
+              - Setup App (pyproject.toml): "cloud/deployment/setup_pyproject.md"
+              - Test App Locally: "cloud/deployment/test_locally.md"
+              - Deploy to Cloud: "cloud/deployment/cloud.md"
+              - Self-Host: "cloud/deployment/self_hosted.md"
           - Streaming:
-              - Stream Values: 'cloud/how-tos/cloud_examples/stream_values.ipynb'
-              - Stream Updates: 'cloud/how-tos/cloud_examples/stream_updates.ipynb'
-              - Stream Messages: 'cloud/how-tos/cloud_examples/stream_messages.ipynb'
-              - Stream Events: 'cloud/how-tos/cloud_examples/stream_events.ipynb'
-              - Stream Debug: 'cloud/how-tos/cloud_examples/stream_debug.ipynb'
-              - Multiple Modes: 'cloud/how-tos/cloud_examples/stream_multiple.ipynb'
-          - Double Texting: 
-              - Interrupt: 'cloud/how-tos/cloud_examples/interrupt_concurrent.ipynb'
-              - Rollback: 'cloud/how-tos/cloud_examples/rollback_concurrent.ipynb'
-              - Reject: 'cloud/how-tos/cloud_examples/reject_concurrent.ipynb'
-              - Enqueue: 'cloud/how-tos/cloud_examples/enqueue_concurrent.ipynb'
-          - Run Agent in Background: 'cloud/how-tos/cloud_examples/background_run.ipynb'
-          - Run Multiple Agents in Thread: 'cloud/how-tos/cloud_examples/same-thread.ipynb'
-          - Human-in-the-Loop:
-              - Add Breakpoint: 'cloud/how-tos/cloud_examples/human_in_the_loop_breakpoint.ipynb'
-              - Wait for User Input: 'cloud/how-tos/cloud_examples/human_in_the_loop_user_input.ipynb'
-              - Edit Graph State: 'cloud/how-tos/cloud_examples/human_in_the_loop_edit_state.ipynb'
-              - Replay and Branch from Prior States: 'cloud/how-tos/cloud_examples/human_in_the_loop_time_travel.ipynb'
-          - Create Agents with Configuration: 'cloud/how-tos/cloud_examples/configuration_cloud.ipynb'
-          - Convert LangGraph calls to LangGraph Cloud calls: 'cloud/how-tos/cloud_examples/langgraph_to_langgraph_cloud.ipynb'
-          - Create Cron Jobs: 'cloud/how-tos/cloud_examples/cron_jobs.ipynb'
-          - Create Stateless Runs: 'cloud/how-tos/cloud_examples/stateless_runs.ipynb'
-          - SDK:
-              - Python: 'cloud/sdk/python_sdk.ipynb'
-              - JS/TS: 'cloud/sdk/js_sdk.ipynb'
+              - Stream Values: "cloud/how-tos/stream_values.md"
+              - Stream Updates: "cloud/how-tos/stream_updates.md"
+              - Stream Messages: "cloud/how-tos/stream_messages.md"
+              - Stream Events: "cloud/how-tos/stream_events.md"
+              - Stream Debug: "cloud/how-tos/stream_debug.md"
+              - Multiple Modes: "cloud/how-tos/stream_multiple.md"
+          - Double Texting:
+              - Interrupt: "cloud/how-tos/interrupt_concurrent.md"
+              - Rollback: "cloud/how-tos/rollback_concurrent.md"
+              - Reject: "cloud/how-tos/reject_concurrent.md"
+              - Enqueue: "cloud/how-tos/enqueue_concurrent.md"
+          - Human-in-the-Loop: 
+              - Add Breakpoint: "cloud/how-tos/human_in_the_loop_breakpoint.md"
+              - Wait for User Input: "cloud/how-tos/human_in_the_loop_user_input.md"
+              - Edit Graph State: "cloud/how-tos/human_in_the_loop_edit_state.md"
+              - Replay and Branch from Prior States: "cloud/how-tos/human_in_the_loop_time_travel.md"
+          - LangGraph Studio:
+              - Test Cloud Deployment: "cloud/how-tos/test_deployment.md"
+              - Invoke graph in LangGraph Studio: "cloud/how-tos/invoke_studio.md"
+              - Interact with threads in LangGraph Studio: "cloud/how-tos/threads_studio.md"
+          - Different Types of Runs:
+              - Run an Agent in the Background: "cloud/how-tos/cloud_examples/background_run.ipynb"
+              - Run Multiple Agents in Same Thread: "cloud/how-tos/cloud_examples/same-thread.ipynb"
+              - Create Cron Jobs: "cloud/how-tos/cloud_examples/cron_jobs.ipynb"
+              - Create Stateless Runs: "cloud/how-tos/cloud_examples/stateless_runs.ipynb"
+          - Other:
+              - Configure Agents: "cloud/how-tos/cloud_examples/configuration_cloud.ipynb"
+              - Convert LangGraph calls to LangGraph Cloud calls: "cloud/how-tos/cloud_examples/langgraph_to_langgraph_cloud.ipynb"
+              - Integrate Webhooks: 'cloud/how-tos/cloud_examples/webhooks.ipynb'
       - Conceptual Guides:
-          'cloud/concepts/index.md'
+          - API Concepts: "cloud/concepts/api.md"
+          - Cloud Concepts: "cloud/concepts/cloud.md"
       - Reference:
-          - API: 'cloud/reference/api/api_ref.md'
+          - API: "cloud/reference/api/api_ref.md"
           - SDK:
-              - Python: 'cloud/reference/sdk/python_sdk_ref.md'
-              - JS/TS: 'cloud/reference/sdk/js_ts_sdk_ref.md'
-          - CLI: 'cloud/reference/cli.md'
-          - Environment Variables: 'cloud/reference/env_var.md'
-
+              - Python: "cloud/reference/sdk/python_sdk_ref.md"
+              - JS/TS: "cloud/reference/sdk/js_ts_sdk_ref.md"
+          - CLI: "cloud/reference/cli.md"
+          - Environment Variables: "cloud/reference/env_var.md"
 
 markdown_extensions:
   - abbr
@@ -226,6 +239,9 @@ markdown_extensions:
   - def_list
   - footnotes
   - md_in_html
+  - pymdownx.superfences
+  - pymdownx.tabbed:
+      alternate_style: true
   - toc:
       permalink: true
   - pymdownx.arithmatex:
@@ -247,7 +263,7 @@ markdown_extensions:
   - pymdownx.magiclink:
       normalize_issue_symbols: true
       repo_url_shorthand: true
-      user: langchain-ai 
+      user: langchain-ai
       repo: langgraph
   - pymdownx.mark
   - pymdownx.smartsymbols
@@ -272,7 +288,7 @@ extra_css:
 
 extra:
   social:
-    - icon: fontawesome/brands/js 
+    - icon: fontawesome/brands/js
       link: https://langchain-ai.github.io/langgraphjs/
     - icon: fontawesome/brands/github
       link: https://github.com/langchain-ai/langgraph
@@ -292,5 +308,10 @@ extra:
         - icon: material/emoticon-sad-outline
           name: This page could be improved
           data: 0
-          note: >- 
+          note: >-
             Thanks for your feedback! Please help us improve this page by adding to the discussion below.
+validation:
+  omitted_files: warn
+  absolute_links: warn
+  unrecognized_links: warn
+  anchors: warn

docs/overrides/main.html

@@ -21,12 +21,6 @@
       background-color: #FFFFFF;
     }
 
-    .navbar {
-      background-color: #FFFFFF;
-      color: #333333;
-      box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);
-    }
-
     .md-footer {
       background-color: #F5F5F5;
       color: #666666;
@@ -100,6 +94,29 @@
       color: #BDBDBD;
     }
 
+    [data-md-color-scheme="slate"] .md-header {
+      background-color: #1E1E1E;
+      color: #BDBDBD;
+    }
+
+    [data-md-color-scheme="slate"] .md-tabs {
+      background-color: #1E1E1E;
+      color: #BDBDBD;
+    }
+
+    [data-md-color-scheme="slate"] .md-search__input {
+      background-color: #F5F5F5;
+      color: #333333;
+    }
+
+    [data-md-color-scheme="slate"] .md-search__icon {
+      color: #333333;
+    }
+
+    [data-md-color-scheme="slate"] .md-search__input::placeholder {
+      color: #333333;
+    }
+
     [data-md-color-scheme="slate"] .md-footer-meta {
       background-color: #1E1E1E;
     }
@@ -111,6 +128,7 @@
     [data-md-color-scheme="slate"] .md-typeset a:hover {
       color: #90CAF9;
     }
+
     .notebook-links {
       display: flex;
       justify-content: flex-end;
@@ -119,7 +137,22 @@
     .notebook-links .md-content__button {
       margin-left: 0.5rem;
     }
-    
+
+    [data-md-color-scheme=default] .logo-dark {
+      display: none !important;
+    }
+
+    [data-md-color-scheme=slate] .logo-light {
+      display: none !important;
+    }
+
+    .jupyter-wrapper .jp-CodeCell .jp-Cell-inputWrapper .jp-InputPrompt.jp-InputArea-prompt {
+      display: none !important;
+    }
+
+    .jupyter-wrapper .jp-Notebook .jp-Cell .jp-OutputPrompt {
+      display: none !important;
+    }
   </style>
 {% endblock %}
 
@@ -134,4 +167,15 @@
 </div>
 
 {{ super() }}
-{% endblock content %}
+{% endblock content %}
+
+
+{% block htmltitle %}
+  {% if page.meta and page.meta.title %}
+    <title>{{ page.meta.title }}</title>
+  {% elif page.title and not page.is_homepage %}
+    <title>{{ page.title | striptags }}</title>
+  {% else %}
+    <title>{{ config.site_name }}</title>
+  {% endif %}
+{% endblock %}

docs/overrides/partials/logo.html

@@ -0,0 +1,4 @@
+{% if config.theme.logo_light_mode %}
+  <img src="{{ config.theme.logo_light_mode | url }}" alt="logo" class="logo-light" />
+  <img src="{{ config.theme.logo_dark_mode | url }}" alt="logo" class="logo-dark" />
+{% endif %}

examples/agent_executor/base.ipynb

@@ -25,10 +25,7 @@
    "id": "fdd4ce41-4152-423b-b3f7-be3b4d568cf4",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain langchain_openai langchainhub tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain langchain_openai langchainhub tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -44,13 +41,7 @@
    "id": "6398c4c1-da78-4595-8a5a-051ed2d1de72",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nos.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\nos.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -66,10 +57,7 @@
    "id": "dcbf79ad-4de5-43b0-a3a1-25b33711e46c",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -87,23 +75,7 @@
    "id": "4499eb16-bca8-4a60-9a3a-2f34ae3f7078",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain import hub\n",
-    "from langchain.agents import create_openai_functions_agent\n",
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "from langchain_openai.chat_models import ChatOpenAI\n",
-    "\n",
-    "tools = [TavilySearchResults(max_results=1)]\n",
-    "\n",
-    "# Get the prompt to use - you can modify this!\n",
-    "prompt = hub.pull(\"hwchase17/openai-functions-agent\")\n",
-    "\n",
-    "# Choose the LLM that will drive the agent\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-1106\", streaming=True)\n",
-    "\n",
-    "# Construct the OpenAI Functions agent\n",
-    "agent_runnable = create_openai_functions_agent(llm, tools, prompt)"
-   ]
+   "source": ["from langchain import hub\nfrom langchain.agents import create_openai_functions_agent\nfrom langchain_community.tools.tavily_search import TavilySearchResults\nfrom langchain_openai.chat_models import ChatOpenAI\n\ntools = [TavilySearchResults(max_results=1)]\n\n# Get the prompt to use - you can modify this!\nprompt = hub.pull(\"hwchase17/openai-functions-agent\")\n\n# Choose the LLM that will drive the agent\nllm = ChatOpenAI(model=\"gpt-3.5-turbo-1106\", streaming=True)\n\n# Construct the OpenAI Functions agent\nagent_runnable = create_openai_functions_agent(llm, tools, prompt)"]
   },
   {
    "cell_type": "markdown",
@@ -126,27 +98,7 @@
    "id": "c941fb10-dbe5-4d6a-ab7d-133d01c33cc4",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, TypedDict, Union\n",
-    "\n",
-    "from langchain_core.agents import AgentAction, AgentFinish\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    # The input string\n",
-    "    input: str\n",
-    "    # The list of previous messages in the conversation\n",
-    "    chat_history: list[BaseMessage]\n",
-    "    # The outcome of a given call to the agent\n",
-    "    # Needs `None` as a valid type, since this is what this will start as\n",
-    "    agent_outcome: Union[AgentAction, AgentFinish, None]\n",
-    "    # List of actions and corresponding observations\n",
-    "    # Here we annotate this with `operator.add` to indicate that operations to\n",
-    "    # this state should be ADDED to the existing values (not overwrite it)\n",
-    "    intermediate_steps: Annotated[list[tuple[AgentAction, str]], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, TypedDict, Union\n\nfrom langchain_core.agents import AgentAction, AgentFinish\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    # The input string\n    input: str\n    # The list of previous messages in the conversation\n    chat_history: list[BaseMessage]\n    # The outcome of a given call to the agent\n    # Needs `None` as a valid type, since this is what this will start as\n    agent_outcome: Union[AgentAction, AgentFinish, None]\n    # List of actions and corresponding observations\n    # Here we annotate this with `operator.add` to indicate that operations to\n    # this state should be ADDED to the existing values (not overwrite it)\n    intermediate_steps: Annotated[list[tuple[AgentAction, str]], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -181,42 +133,7 @@
    "id": "d61a970d-edf4-4eef-9678-28bab7c72331",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.agents import AgentFinish\n",
-    "\n",
-    "from langgraph.prebuilt.tool_executor import ToolExecutor\n",
-    "\n",
-    "# This a helper class we have that is useful for running tools\n",
-    "# It takes in an agent action and calls that tool and returns the result\n",
-    "tool_executor = ToolExecutor(tools)\n",
-    "\n",
-    "\n",
-    "# Define the agent\n",
-    "def run_agent(data):\n",
-    "    agent_outcome = agent_runnable.invoke(data)\n",
-    "    return {\"agent_outcome\": agent_outcome}\n",
-    "\n",
-    "\n",
-    "# Define the function to execute tools\n",
-    "def execute_tools(data):\n",
-    "    # Get the most recent agent_outcome - this is the key added in the `agent` above\n",
-    "    agent_action = data[\"agent_outcome\"]\n",
-    "    output = tool_executor.invoke(agent_action)\n",
-    "    return {\"intermediate_steps\": [(agent_action, str(output))]}\n",
-    "\n",
-    "\n",
-    "# Define logic that will be used to determine which conditional edge to go down\n",
-    "def should_continue(data):\n",
-    "    # If the agent outcome is an AgentFinish, then we return `exit` string\n",
-    "    # This will be used when setting up the graph to define the flow\n",
-    "    if isinstance(data[\"agent_outcome\"], AgentFinish):\n",
-    "        return \"end\"\n",
-    "    # Otherwise, an AgentAction is returned\n",
-    "    # Here we return `continue` string\n",
-    "    # This will be used when setting up the graph to define the flow\n",
-    "    else:\n",
-    "        return \"continue\""
-   ]
+   "source": ["from langchain_core.agents import AgentFinish\n\nfrom langgraph.prebuilt.tool_executor import ToolExecutor\n\n# This a helper class we have that is useful for running tools\n# It takes in an agent action and calls that tool and returns the result\ntool_executor = ToolExecutor(tools)\n\n\n# Define the agent\ndef run_agent(data):\n    agent_outcome = agent_runnable.invoke(data)\n    return {\"agent_outcome\": agent_outcome}\n\n\n# Define the function to execute tools\ndef execute_tools(data):\n    # Get the most recent agent_outcome - this is the key added in the `agent` above\n    agent_action = data[\"agent_outcome\"]\n    output = tool_executor.invoke(agent_action)\n    return {\"intermediate_steps\": [(agent_action, str(output))]}\n\n\n# Define logic that will be used to determine which conditional edge to go down\ndef should_continue(data):\n    # If the agent outcome is an AgentFinish, then we return `exit` string\n    # This will be used when setting up the graph to define the flow\n    if isinstance(data[\"agent_outcome\"], AgentFinish):\n        return \"end\"\n    # Otherwise, an AgentAction is returned\n    # Here we return `continue` string\n    # This will be used when setting up the graph to define the flow\n    else:\n        return \"continue\""]
   },
   {
    "cell_type": "markdown",
@@ -234,50 +151,7 @@
    "id": "c4054dde-4618-49b7-998a-daa0c1d6d6c0",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", run_agent)\n",
-    "workflow.add_node(\"action\", execute_tools)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", run_agent)\nworkflow.add_node(\"action\", execute_tools)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -300,12 +174,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = {\"input\": \"what is the weather in sf\", \"chat_history\": []}\n",
-    "for s in app.stream(inputs):\n",
-    "    print(list(s.values())[0])\n",
-    "    print(\"----\")"
-   ]
+   "source": ["inputs = {\"input\": \"what is the weather in sf\", \"chat_history\": []}\nfor s in app.stream(inputs):\n    print(list(s.values())[0])\n    print(\"----\")"]
   },
   {
    "cell_type": "code",
@@ -313,7 +182,7 @@
    "id": "2eb662bc-de7d-4a57-a3e8-2f00dcf4ff8b",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/agent_executor/force-calling-a-tool-first.ipynb

@@ -30,10 +30,7 @@
    "id": "694cfc4c-22a7-495d-930d-56b21d850ff9",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain langchain_openai tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain langchain_openai tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -49,13 +46,7 @@
    "id": "30c06a84-291a-4f58-9d31-53d3b56a3def",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nos.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\nos.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -71,10 +62,7 @@
    "id": "a8fb285a-7e6e-46fc-a273-43ab1a676189",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -92,23 +80,7 @@
    "id": "4499eb16-bca8-4a60-9a3a-2f34ae3f7078",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain import hub\n",
-    "from langchain.agents import create_openai_functions_agent\n",
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "from langchain_openai.chat_models import ChatOpenAI\n",
-    "\n",
-    "tools = [TavilySearchResults(max_results=1)]\n",
-    "\n",
-    "# Get the prompt to use - you can modify this!\n",
-    "prompt = hub.pull(\"hwchase17/openai-functions-agent\")\n",
-    "\n",
-    "# Choose the LLM that will drive the agent\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-1106\", streaming=True)\n",
-    "\n",
-    "# Construct the OpenAI Functions agent\n",
-    "agent_runnable = create_openai_functions_agent(llm, tools, prompt)"
-   ]
+   "source": ["from langchain import hub\nfrom langchain.agents import create_openai_functions_agent\nfrom langchain_community.tools.tavily_search import TavilySearchResults\nfrom langchain_openai.chat_models import ChatOpenAI\n\ntools = [TavilySearchResults(max_results=1)]\n\n# Get the prompt to use - you can modify this!\nprompt = hub.pull(\"hwchase17/openai-functions-agent\")\n\n# Choose the LLM that will drive the agent\nllm = ChatOpenAI(model=\"gpt-3.5-turbo-1106\", streaming=True)\n\n# Construct the OpenAI Functions agent\nagent_runnable = create_openai_functions_agent(llm, tools, prompt)"]
   },
   {
    "cell_type": "markdown",
@@ -131,27 +103,7 @@
    "id": "c941fb10-dbe5-4d6a-ab7d-133d01c33cc4",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, TypedDict, Union\n",
-    "\n",
-    "from langchain_core.agents import AgentAction, AgentFinish\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    # The input string\n",
-    "    input: str\n",
-    "    # The list of previous messages in the conversation\n",
-    "    chat_history: list[BaseMessage]\n",
-    "    # The outcome of a given call to the agent\n",
-    "    # Needs `None` as a valid type, since this is what this will start as\n",
-    "    agent_outcome: Union[AgentAction, AgentFinish, None]\n",
-    "    # List of actions and corresponding observations\n",
-    "    # Here we annotate this with `operator.add` to indicate that operations to\n",
-    "    # this state should be ADDED to the existing values (not overwrite it)\n",
-    "    intermediate_steps: Annotated[list[tuple[AgentAction, str]], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, TypedDict, Union\n\nfrom langchain_core.agents import AgentAction, AgentFinish\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    # The input string\n    input: str\n    # The list of previous messages in the conversation\n    chat_history: list[BaseMessage]\n    # The outcome of a given call to the agent\n    # Needs `None` as a valid type, since this is what this will start as\n    agent_outcome: Union[AgentAction, AgentFinish, None]\n    # List of actions and corresponding observations\n    # Here we annotate this with `operator.add` to indicate that operations to\n    # this state should be ADDED to the existing values (not overwrite it)\n    intermediate_steps: Annotated[list[tuple[AgentAction, str]], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -186,42 +138,7 @@
    "id": "d61a970d-edf4-4eef-9678-28bab7c72331",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.agents import AgentFinish\n",
-    "\n",
-    "from langgraph.prebuilt.tool_executor import ToolExecutor\n",
-    "\n",
-    "# This a helper class we have that is useful for running tools\n",
-    "# It takes in an agent action and calls that tool and returns the result\n",
-    "tool_executor = ToolExecutor(tools)\n",
-    "\n",
-    "\n",
-    "# Define the agent\n",
-    "def run_agent(data):\n",
-    "    agent_outcome = agent_runnable.invoke(data)\n",
-    "    return {\"agent_outcome\": agent_outcome}\n",
-    "\n",
-    "\n",
-    "# Define the function to execute tools\n",
-    "def execute_tools(data):\n",
-    "    # Get the most recent agent_outcome - this is the key added in the `agent` above\n",
-    "    agent_action = data[\"agent_outcome\"]\n",
-    "    output = tool_executor.invoke(agent_action)\n",
-    "    return {\"intermediate_steps\": [(agent_action, str(output))]}\n",
-    "\n",
-    "\n",
-    "# Define logic that will be used to determine which conditional edge to go down\n",
-    "def should_continue(data):\n",
-    "    # If the agent outcome is an AgentFinish, then we return `exit` string\n",
-    "    # This will be used when setting up the graph to define the flow\n",
-    "    if isinstance(data[\"agent_outcome\"], AgentFinish):\n",
-    "        return \"end\"\n",
-    "    # Otherwise, an AgentAction is returned\n",
-    "    # Here we return `continue` string\n",
-    "    # This will be used when setting up the graph to define the flow\n",
-    "    else:\n",
-    "        return \"continue\""
-   ]
+   "source": ["from langchain_core.agents import AgentFinish\n\nfrom langgraph.prebuilt.tool_executor import ToolExecutor\n\n# This a helper class we have that is useful for running tools\n# It takes in an agent action and calls that tool and returns the result\ntool_executor = ToolExecutor(tools)\n\n\n# Define the agent\ndef run_agent(data):\n    agent_outcome = agent_runnable.invoke(data)\n    return {\"agent_outcome\": agent_outcome}\n\n\n# Define the function to execute tools\ndef execute_tools(data):\n    # Get the most recent agent_outcome - this is the key added in the `agent` above\n    agent_action = data[\"agent_outcome\"]\n    output = tool_executor.invoke(agent_action)\n    return {\"intermediate_steps\": [(agent_action, str(output))]}\n\n\n# Define logic that will be used to determine which conditional edge to go down\ndef should_continue(data):\n    # If the agent outcome is an AgentFinish, then we return `exit` string\n    # This will be used when setting up the graph to define the flow\n    if isinstance(data[\"agent_outcome\"], AgentFinish):\n        return \"end\"\n    # Otherwise, an AgentAction is returned\n    # Here we return `continue` string\n    # This will be used when setting up the graph to define the flow\n    else:\n        return \"continue\""]
   },
   {
    "cell_type": "markdown",
@@ -250,9 +167,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "tools[0].name"
-   ]
+   "source": ["tools[0].name"]
   },
   {
    "cell_type": "code",
@@ -260,21 +175,7 @@
    "id": "df25d899-2338-4f31-a8bf-0582a2eec325",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.agents import AgentActionMessageLog\n",
-    "\n",
-    "\n",
-    "def first_agent(inputs):\n",
-    "    action = AgentActionMessageLog(\n",
-    "        # We force call this tool\n",
-    "        tool=\"tavily_search_results_json\",\n",
-    "        # We just pass in the `input` key to this tool\n",
-    "        tool_input=inputs[\"input\"],\n",
-    "        log=\"\",\n",
-    "        message_log=[],\n",
-    "    )\n",
-    "    return {\"agent_outcome\": action}"
-   ]
+   "source": ["from langchain_core.agents import AgentActionMessageLog\n\n\ndef first_agent(inputs):\n    action = AgentActionMessageLog(\n        # We force call this tool\n        tool=\"tavily_search_results_json\",\n        # We just pass in the `input` key to this tool\n        tool_input=inputs[\"input\"],\n        log=\"\",\n        message_log=[],\n    )\n    return {\"agent_outcome\": action}"]
   },
   {
    "cell_type": "markdown",
@@ -296,54 +197,7 @@
    "id": "c4054dde-4618-49b7-998a-daa0c1d6d6c0",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", run_agent)\n",
-    "workflow.add_node(\"action\", execute_tools)\n",
-    "workflow.add_node(\"first_agent\", first_agent)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"first_agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# After the first agent, we want to take an action\n",
-    "workflow.add_edge(\"first_agent\", \"action\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", run_agent)\nworkflow.add_node(\"action\", execute_tools)\nworkflow.add_node(\"first_agent\", first_agent)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"first_agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# After the first agent, we want to take an action\nworkflow.add_edge(\"first_agent\", \"action\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -366,12 +220,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = {\"input\": \"what is the weather in sf\", \"chat_history\": []}\n",
-    "for s in app.stream(inputs):\n",
-    "    print(list(s.values())[0])\n",
-    "    print(\"----\")"
-   ]
+   "source": ["inputs = {\"input\": \"what is the weather in sf\", \"chat_history\": []}\nfor s in app.stream(inputs):\n    print(list(s.values())[0])\n    print(\"----\")"]
   },
   {
    "cell_type": "code",
@@ -379,7 +228,7 @@
    "id": "2eb662bc-de7d-4a57-a3e8-2f00dcf4ff8b",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/agent_executor/human-in-the-loop.ipynb

@@ -30,10 +30,7 @@
    "id": "3fa9e224-2f00-49e2-bca3-e9cb8d9f3d41",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain langchain_openai tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain langchain_openai tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -49,13 +46,7 @@
    "id": "d180f0d0-385f-4ce3-994c-11e1d64595b5",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nos.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\nos.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -71,10 +62,7 @@
    "id": "72ad0539-ecd8-4eb1-b2c1-2242e5fc556f",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -92,23 +80,7 @@
    "id": "4499eb16-bca8-4a60-9a3a-2f34ae3f7078",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain import hub\n",
-    "from langchain.agents import create_openai_functions_agent\n",
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "from langchain_openai.chat_models import ChatOpenAI\n",
-    "\n",
-    "tools = [TavilySearchResults(max_results=1)]\n",
-    "\n",
-    "# Get the prompt to use - you can modify this!\n",
-    "prompt = hub.pull(\"hwchase17/openai-functions-agent\")\n",
-    "\n",
-    "# Choose the LLM that will drive the agent\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-1106\", streaming=True)\n",
-    "\n",
-    "# Construct the OpenAI Functions agent\n",
-    "agent_runnable = create_openai_functions_agent(llm, tools, prompt)"
-   ]
+   "source": ["from langchain import hub\nfrom langchain.agents import create_openai_functions_agent\nfrom langchain_community.tools.tavily_search import TavilySearchResults\nfrom langchain_openai.chat_models import ChatOpenAI\n\ntools = [TavilySearchResults(max_results=1)]\n\n# Get the prompt to use - you can modify this!\nprompt = hub.pull(\"hwchase17/openai-functions-agent\")\n\n# Choose the LLM that will drive the agent\nllm = ChatOpenAI(model=\"gpt-3.5-turbo-1106\", streaming=True)\n\n# Construct the OpenAI Functions agent\nagent_runnable = create_openai_functions_agent(llm, tools, prompt)"]
   },
   {
    "cell_type": "markdown",
@@ -131,27 +103,7 @@
    "id": "c941fb10-dbe5-4d6a-ab7d-133d01c33cc4",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, TypedDict, Union\n",
-    "\n",
-    "from langchain_core.agents import AgentAction, AgentFinish\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    # The input string\n",
-    "    input: str\n",
-    "    # The list of previous messages in the conversation\n",
-    "    chat_history: list[BaseMessage]\n",
-    "    # The outcome of a given call to the agent\n",
-    "    # Needs `None` as a valid type, since this is what this will start as\n",
-    "    agent_outcome: Union[AgentAction, AgentFinish, None]\n",
-    "    # List of actions and corresponding observations\n",
-    "    # Here we annotate this with `operator.add` to indicate that operations to\n",
-    "    # this state should be ADDED to the existing values (not overwrite it)\n",
-    "    intermediate_steps: Annotated[list[tuple[AgentAction, str]], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, TypedDict, Union\n\nfrom langchain_core.agents import AgentAction, AgentFinish\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    # The input string\n    input: str\n    # The list of previous messages in the conversation\n    chat_history: list[BaseMessage]\n    # The outcome of a given call to the agent\n    # Needs `None` as a valid type, since this is what this will start as\n    agent_outcome: Union[AgentAction, AgentFinish, None]\n    # List of actions and corresponding observations\n    # Here we annotate this with `operator.add` to indicate that operations to\n    # this state should be ADDED to the existing values (not overwrite it)\n    intermediate_steps: Annotated[list[tuple[AgentAction, str]], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -186,21 +138,7 @@
    "id": "2b757f84-1175-445e-8f8c-e5aeb765a03d",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.agents import AgentFinish\n",
-    "\n",
-    "from langgraph.prebuilt.tool_executor import ToolExecutor\n",
-    "\n",
-    "# This a helper class we have that is useful for running tools\n",
-    "# It takes in an agent action and calls that tool and returns the result\n",
-    "tool_executor = ToolExecutor(tools)\n",
-    "\n",
-    "\n",
-    "# Define the agent\n",
-    "def run_agent(data):\n",
-    "    agent_outcome = agent_runnable.invoke(data)\n",
-    "    return {\"agent_outcome\": agent_outcome}"
-   ]
+   "source": ["from langchain_core.agents import AgentFinish\n\nfrom langgraph.prebuilt.tool_executor import ToolExecutor\n\n# This a helper class we have that is useful for running tools\n# It takes in an agent action and calls that tool and returns the result\ntool_executor = ToolExecutor(tools)\n\n\n# Define the agent\ndef run_agent(data):\n    agent_outcome = agent_runnable.invoke(data)\n    return {\"agent_outcome\": agent_outcome}"]
   },
   {
    "cell_type": "markdown",
@@ -218,30 +156,7 @@
    "id": "2fecf5e0-9604-4992-9c82-b9627466cd32",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Define the function to execute tools\n",
-    "def execute_tools(data):\n",
-    "    # Get the most recent agent_outcome - this is the key added in the `agent` above\n",
-    "    agent_action = data[\"agent_outcome\"]\n",
-    "    response = input(prompt=f\"[y/n] continue with: {agent_action}?\")\n",
-    "    if response == \"n\":\n",
-    "        raise ValueError\n",
-    "    output = tool_executor.invoke(agent_action)\n",
-    "    return {\"intermediate_steps\": [(agent_action, str(output))]}\n",
-    "\n",
-    "\n",
-    "# Define logic that will be used to determine which conditional edge to go down\n",
-    "def should_continue(data):\n",
-    "    # If the agent outcome is an AgentFinish, then we return `exit` string\n",
-    "    # This will be used when setting up the graph to define the flow\n",
-    "    if isinstance(data[\"agent_outcome\"], AgentFinish):\n",
-    "        return \"end\"\n",
-    "    # Otherwise, an AgentAction is returned\n",
-    "    # Here we return `continue` string\n",
-    "    # This will be used when setting up the graph to define the flow\n",
-    "    else:\n",
-    "        return \"continue\""
-   ]
+   "source": ["# Define the function to execute tools\ndef execute_tools(data):\n    # Get the most recent agent_outcome - this is the key added in the `agent` above\n    agent_action = data[\"agent_outcome\"]\n    response = input(prompt=f\"[y/n] continue with: {agent_action}?\")\n    if response == \"n\":\n        raise ValueError\n    output = tool_executor.invoke(agent_action)\n    return {\"intermediate_steps\": [(agent_action, str(output))]}\n\n\n# Define logic that will be used to determine which conditional edge to go down\ndef should_continue(data):\n    # If the agent outcome is an AgentFinish, then we return `exit` string\n    # This will be used when setting up the graph to define the flow\n    if isinstance(data[\"agent_outcome\"], AgentFinish):\n        return \"end\"\n    # Otherwise, an AgentAction is returned\n    # Here we return `continue` string\n    # This will be used when setting up the graph to define the flow\n    else:\n        return \"continue\""]
   },
   {
    "cell_type": "markdown",
@@ -259,50 +174,7 @@
    "id": "c4054dde-4618-49b7-998a-daa0c1d6d6c0",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", run_agent)\n",
-    "workflow.add_node(\"action\", execute_tools)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", run_agent)\nworkflow.add_node(\"action\", execute_tools)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -338,12 +210,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = {\"input\": \"what is the weather in sf\", \"chat_history\": []}\n",
-    "for s in app.stream(inputs):\n",
-    "    print(list(s.values())[0])\n",
-    "    print(\"----\")"
-   ]
+   "source": ["inputs = {\"input\": \"what is the weather in sf\", \"chat_history\": []}\nfor s in app.stream(inputs):\n    print(list(s.values())[0])\n    print(\"----\")"]
   },
   {
    "cell_type": "code",
@@ -351,7 +218,7 @@
    "id": "2eb662bc-de7d-4a57-a3e8-2f00dcf4ff8b",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/agent_executor/managing-agent-steps.ipynb

@@ -30,10 +30,7 @@
    "id": "aa752131-27e3-4bd8-9f21-d6749a7e74f4",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain langchain_openai tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain langchain_openai tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -49,13 +46,7 @@
    "id": "5732e68f-4ae2-4db9-bf9c-454b4cc9ec01",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nos.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\nos.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -71,10 +62,7 @@
    "id": "652d4600-8f95-493f-b9b9-d4095aed9218",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -92,23 +80,7 @@
    "id": "4499eb16-bca8-4a60-9a3a-2f34ae3f7078",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain import hub\n",
-    "from langchain.agents import create_openai_functions_agent\n",
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "from langchain_openai.chat_models import ChatOpenAI\n",
-    "\n",
-    "tools = [TavilySearchResults(max_results=1)]\n",
-    "\n",
-    "# Get the prompt to use - you can modify this!\n",
-    "prompt = hub.pull(\"hwchase17/openai-functions-agent\")\n",
-    "\n",
-    "# Choose the LLM that will drive the agent\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-1106\", streaming=True)\n",
-    "\n",
-    "# Construct the OpenAI Functions agent\n",
-    "agent_runnable = create_openai_functions_agent(llm, tools, prompt)"
-   ]
+   "source": ["from langchain import hub\nfrom langchain.agents import create_openai_functions_agent\nfrom langchain_community.tools.tavily_search import TavilySearchResults\nfrom langchain_openai.chat_models import ChatOpenAI\n\ntools = [TavilySearchResults(max_results=1)]\n\n# Get the prompt to use - you can modify this!\nprompt = hub.pull(\"hwchase17/openai-functions-agent\")\n\n# Choose the LLM that will drive the agent\nllm = ChatOpenAI(model=\"gpt-3.5-turbo-1106\", streaming=True)\n\n# Construct the OpenAI Functions agent\nagent_runnable = create_openai_functions_agent(llm, tools, prompt)"]
   },
   {
    "cell_type": "markdown",
@@ -131,27 +103,7 @@
    "id": "c941fb10-dbe5-4d6a-ab7d-133d01c33cc4",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, TypedDict, Union\n",
-    "\n",
-    "from langchain_core.agents import AgentAction, AgentFinish\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    # The input string\n",
-    "    input: str\n",
-    "    # The list of previous messages in the conversation\n",
-    "    chat_history: list[BaseMessage]\n",
-    "    # The outcome of a given call to the agent\n",
-    "    # Needs `None` as a valid type, since this is what this will start as\n",
-    "    agent_outcome: Union[AgentAction, AgentFinish, None]\n",
-    "    # List of actions and corresponding observations\n",
-    "    # Here we annotate this with `operator.add` to indicate that operations to\n",
-    "    # this state should be ADDED to the existing values (not overwrite it)\n",
-    "    intermediate_steps: Annotated[list[tuple[AgentAction, str]], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, TypedDict, Union\n\nfrom langchain_core.agents import AgentAction, AgentFinish\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    # The input string\n    input: str\n    # The list of previous messages in the conversation\n    chat_history: list[BaseMessage]\n    # The outcome of a given call to the agent\n    # Needs `None` as a valid type, since this is what this will start as\n    agent_outcome: Union[AgentAction, AgentFinish, None]\n    # List of actions and corresponding observations\n    # Here we annotate this with `operator.add` to indicate that operations to\n    # this state should be ADDED to the existing values (not overwrite it)\n    intermediate_steps: Annotated[list[tuple[AgentAction, str]], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -186,15 +138,7 @@
    "id": "77e3c059-e31f-4c8f-81bf-edb58688e12b",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.agents import AgentFinish\n",
-    "\n",
-    "from langgraph.prebuilt.tool_executor import ToolExecutor\n",
-    "\n",
-    "# This a helper class we have that is useful for running tools\n",
-    "# It takes in an agent action and calls that tool and returns the result\n",
-    "tool_executor = ToolExecutor(tools)"
-   ]
+   "source": ["from langchain_core.agents import AgentFinish\n\nfrom langgraph.prebuilt.tool_executor import ToolExecutor\n\n# This a helper class we have that is useful for running tools\n# It takes in an agent action and calls that tool and returns the result\ntool_executor = ToolExecutor(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -212,36 +156,7 @@
    "id": "a9f66a3e-aba1-4893-95b1-a433c7091d5e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Define the agent\n",
-    "def run_agent(data):\n",
-    "    inputs = data.copy()\n",
-    "    if len(inputs[\"intermediate_steps\"]) > 5:\n",
-    "        inputs[\"intermediate_steps\"] = inputs[\"intermediate_steps\"][-5:]\n",
-    "    agent_outcome = agent_runnable.invoke(inputs)\n",
-    "    return {\"agent_outcome\": agent_outcome}\n",
-    "\n",
-    "\n",
-    "# Define the function to execute tools\n",
-    "def execute_tools(data):\n",
-    "    # Get the most recent agent_outcome - this is the key added in the `agent` above\n",
-    "    agent_action = data[\"agent_outcome\"]\n",
-    "    output = tool_executor.invoke(agent_action)\n",
-    "    return {\"intermediate_steps\": [(agent_action, str(output))]}\n",
-    "\n",
-    "\n",
-    "# Define logic that will be used to determine which conditional edge to go down\n",
-    "def should_continue(data):\n",
-    "    # If the agent outcome is an AgentFinish, then we return `exit` string\n",
-    "    # This will be used when setting up the graph to define the flow\n",
-    "    if isinstance(data[\"agent_outcome\"], AgentFinish):\n",
-    "        return \"end\"\n",
-    "    # Otherwise, an AgentAction is returned\n",
-    "    # Here we return `continue` string\n",
-    "    # This will be used when setting up the graph to define the flow\n",
-    "    else:\n",
-    "        return \"continue\""
-   ]
+   "source": ["# Define the agent\ndef run_agent(data):\n    inputs = data.copy()\n    if len(inputs[\"intermediate_steps\"]) > 5:\n        inputs[\"intermediate_steps\"] = inputs[\"intermediate_steps\"][-5:]\n    agent_outcome = agent_runnable.invoke(inputs)\n    return {\"agent_outcome\": agent_outcome}\n\n\n# Define the function to execute tools\ndef execute_tools(data):\n    # Get the most recent agent_outcome - this is the key added in the `agent` above\n    agent_action = data[\"agent_outcome\"]\n    output = tool_executor.invoke(agent_action)\n    return {\"intermediate_steps\": [(agent_action, str(output))]}\n\n\n# Define logic that will be used to determine which conditional edge to go down\ndef should_continue(data):\n    # If the agent outcome is an AgentFinish, then we return `exit` string\n    # This will be used when setting up the graph to define the flow\n    if isinstance(data[\"agent_outcome\"], AgentFinish):\n        return \"end\"\n    # Otherwise, an AgentAction is returned\n    # Here we return `continue` string\n    # This will be used when setting up the graph to define the flow\n    else:\n        return \"continue\""]
   },
   {
    "cell_type": "markdown",
@@ -259,50 +174,7 @@
    "id": "c4054dde-4618-49b7-998a-daa0c1d6d6c0",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", run_agent)\n",
-    "workflow.add_node(\"action\", execute_tools)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", run_agent)\nworkflow.add_node(\"action\", execute_tools)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -325,12 +197,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = {\"input\": \"what is the weather in sf\", \"chat_history\": []}\n",
-    "for s in app.stream(inputs):\n",
-    "    print(list(s.values())[0])\n",
-    "    print(\"----\")"
-   ]
+   "source": ["inputs = {\"input\": \"what is the weather in sf\", \"chat_history\": []}\nfor s in app.stream(inputs):\n    print(list(s.values())[0])\n    print(\"----\")"]
   },
   {
    "cell_type": "code",
@@ -338,7 +205,7 @@
    "id": "2eb662bc-de7d-4a57-a3e8-2f00dcf4ff8b",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/async.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# How to run graph asynchronously\n",
     "\n",
-    "In this example we will build a ReAct agent with native [async](https://docs.python.org/3/library/asyncio.html) implementations of the core logic. When Chat Models have async clients, this can give us some nice performance improvements if you\n",
+    "In this example we will build a ReAct agent with native [async](https://docs.python.org/3/library/asyncio.html) implementations of the core logic. When chat models have async clients, this can give us some nice performance improvements if you\n",
     "are running concurrent branches in your graph or if your graph is running within a larger web server process.\n",
     "\n",
     "In general, you don't need to change anything about your graph to add `async` support. That's one of the beauties of [Runnables](https://python.langchain.com/docs/expression_language/interface/). \n",
@@ -37,10 +37,7 @@
    "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain_anthropic"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain_anthropic"]
   },
   {
    "cell_type": "markdown",
@@ -56,18 +53,7 @@
    "id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "\n",
-    "def _set_env(var: str):\n",
-    "    if not os.environ.get(var):\n",
-    "        os.environ[var] = getpass.getpass(f\"{var}: \")\n",
-    "\n",
-    "\n",
-    "_set_env(\"ANTHROPIC_API_KEY\")"
-   ]
+   "source": ["import getpass\nimport os\n\n\ndef _set_env(var: str):\n    if not os.environ.get(var):\n        os.environ[var] = getpass.getpass(f\"{var}: \")\n\n\n_set_env(\"ANTHROPIC_API_KEY\")"]
   },
   {
    "cell_type": "markdown",
@@ -83,10 +69,7 @@
    "id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "_set_env(\"LANGCHAIN_API_KEY\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n_set_env(\"LANGCHAIN_API_KEY\")"]
   },
   {
    "cell_type": "markdown",
@@ -112,22 +95,7 @@
    "id": "6768a3ab",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from typing import Annotated\n",
-    "\n",
-    "from typing_extensions import TypedDict\n",
-    "\n",
-    "from langgraph.graph.message import add_messages\n",
-    "\n",
-    "# Add messages essentially does this with more\n",
-    "# robust handling\n",
-    "# def add_messages(left: list, right: list):\n",
-    "#     return left + right\n",
-    "\n",
-    "\n",
-    "class State(TypedDict):\n",
-    "    messages: Annotated[list, add_messages]"
-   ]
+   "source": ["from typing import Annotated\n\nfrom typing_extensions import TypedDict\n\nfrom langgraph.graph.message import add_messages\n\n# Add messages essentially does this with more\n# robust handling\n# def add_messages(left: list, right: list):\n#     return left + right\n\n\nclass State(TypedDict):\n    messages: Annotated[list, add_messages]"]
   },
   {
    "cell_type": "markdown",
@@ -147,19 +115,7 @@
    "id": "d7ef57dd-5d6e-4ad3-9377-a92201c1310e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.tools import tool\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "def search(query: str):\n",
-    "    \"\"\"Call to surf the web.\"\"\"\n",
-    "    # This is a placeholder, but don't tell the LLM that...\n",
-    "    return [\"The answer to your question lies within.\"]\n",
-    "\n",
-    "\n",
-    "tools = [search]"
-   ]
+   "source": ["from langchain_core.tools import tool\n\n\n@tool\ndef search(query: str):\n    \"\"\"Call to surf the web.\"\"\"\n    # This is a placeholder, but don't tell the LLM that...\n    return [\"The answer to your question lies within.\"]\n\n\ntools = [search]"]
   },
   {
    "cell_type": "markdown",
@@ -176,11 +132,7 @@
    "id": "5cf3331e-ccb3-41c8-aeb9-a840a94d41e7",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolNode\n",
-    "\n",
-    "tool_node = ToolNode(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolNode\n\ntool_node = ToolNode(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -204,11 +156,7 @@
    "id": "892b54b9-75f0-4804-9ed0-88b5e5532989",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_anthropic import ChatAnthropic\n",
-    "\n",
-    "model = ChatAnthropic(model=\"claude-3-haiku-20240307\")"
-   ]
+   "source": ["from langchain_anthropic import ChatAnthropic\n\nmodel = ChatAnthropic(model=\"claude-3-haiku-20240307\")"]
   },
   {
    "cell_type": "markdown",
@@ -226,9 +174,7 @@
    "id": "cd3cbae5-d92c-4559-a4aa-44721b80d107",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "model = model.bind_tools(tools)"
-   ]
+   "source": ["model = model.bind_tools(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -267,29 +213,7 @@
    "id": "3b541bb9-900c-40d0-964d-7b5dfee30667",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from typing import Literal\n",
-    "\n",
-    "\n",
-    "# Define the function that determines whether to continue or not\n",
-    "def should_continue(state: State) -> Literal[\"end\", \"continue\"]:\n",
-    "    messages = state[\"messages\"]\n",
-    "    last_message = messages[-1]\n",
-    "    # If there is no tool call, then we finish\n",
-    "    if not last_message.tool_calls:\n",
-    "        return \"end\"\n",
-    "    # Otherwise if there is, we continue\n",
-    "    else:\n",
-    "        return \"continue\"\n",
-    "\n",
-    "\n",
-    "# Define the function that calls the model\n",
-    "async def call_model(state: State):\n",
-    "    messages = state[\"messages\"]\n",
-    "    response = await model.ainvoke(messages)\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [response]}"
-   ]
+   "source": ["from typing import Literal\n\n\n# Define the function that determines whether to continue or not\ndef should_continue(state: State) -> Literal[\"end\", \"continue\"]:\n    messages = state[\"messages\"]\n    last_message = messages[-1]\n    # If there is no tool call, then we finish\n    if not last_message.tool_calls:\n        return \"end\"\n    # Otherwise if there is, we continue\n    else:\n        return \"continue\"\n\n\n# Define the function that calls the model\nasync def call_model(state: State):\n    messages = state[\"messages\"]\n    response = await model.ainvoke(messages)\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [response]}"]
   },
   {
    "cell_type": "markdown",
@@ -307,50 +231,7 @@
    "id": "813ae66c-3b58-4283-a02a-36da72a2ab90",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(State)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "workflow.add_node(\"action\", tool_node)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(State)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", call_model)\nworkflow.add_node(\"action\", tool_node)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -369,11 +250,7 @@
      "output_type": "display_data"
     }
    ],
-   "source": [
-    "from IPython.display import Image, display\n",
-    "\n",
-    "display(Image(app.get_graph().draw_mermaid_png()))"
-   ]
+   "source": ["from IPython.display import Image, display\n\ndisplay(Image(app.get_graph().draw_mermaid_png()))"]
   },
   {
    "cell_type": "markdown",
@@ -406,12 +283,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "await app.ainvoke(inputs)"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\ninputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\nawait app.ainvoke(inputs)"]
   },
   {
    "cell_type": "markdown",
@@ -480,16 +352,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "async for output in app.astream(inputs, stream_mode=\"updates\"):\n",
-    "    # stream_mode=\"updates\" yields dictionaries with output keyed by node name\n",
-    "    for key, value in output.items():\n",
-    "        print(f\"Output from node '{key}':\")\n",
-    "        print(\"---\")\n",
-    "        print(value[\"messages\"][-1].pretty_print())\n",
-    "    print(\"\\n---\\n\")"
-   ]
+   "source": ["inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\nasync for output in app.astream(inputs, stream_mode=\"updates\"):\n    # stream_mode=\"updates\" yields dictionaries with output keyed by node name\n    for key, value in output.items():\n        print(f\"Output from node '{key}':\")\n        print(\"---\")\n        print(value[\"messages\"][-1].pretty_print())\n    print(\"\\n---\\n\")"]
   },
   {
    "cell_type": "markdown",
@@ -546,20 +409,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "async for output in app.astream_log(inputs, include_types=[\"llm\"]):\n",
-    "    # astream_log() yields the requested logs (here LLMs) in JSONPatch format\n",
-    "    for op in output.ops:\n",
-    "        if op[\"path\"] == \"/streamed_output/-\":\n",
-    "            # this is the output from .stream()\n",
-    "            ...\n",
-    "        elif op[\"path\"].startswith(\"/logs/\") and op[\"path\"].endswith(\n",
-    "            \"/streamed_output/-\"\n",
-    "        ):\n",
-    "            # because we chose to only include LLMs, these are LLM tokens\n",
-    "            print(op[\"value\"].content, end=\"|\")"
-   ]
+   "source": ["inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\nasync for output in app.astream_log(inputs, include_types=[\"llm\"]):\n    # astream_log() yields the requested logs (here LLMs) in JSONPatch format\n    for op in output.ops:\n        if op[\"path\"] == \"/streamed_output/-\":\n            # this is the output from .stream()\n            ...\n        elif op[\"path\"].startswith(\"/logs/\") and op[\"path\"].endswith(\n            \"/streamed_output/-\"\n        ):\n            # because we chose to only include LLMs, these are LLM tokens\n            print(op[\"value\"].content, end=\"|\")"]
   },
   {
    "cell_type": "code",
@@ -567,7 +417,7 @@
    "id": "08ae8246-11d5-40e1-8567-361e5bef8917",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/chat_agent_executor_with_function_calling/anthropic.ipynb

@@ -27,10 +27,7 @@
    "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langchain langchain_anthropic tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langchain langchain_anthropic tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -46,13 +43,7 @@
    "id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nos.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\nos.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -68,10 +59,7 @@
    "id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -95,11 +83,7 @@
    "id": "d7ef57dd-5d6e-4ad3-9377-a92201c1310e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "\n",
-    "tools = [TavilySearchResults(max_results=1)]"
-   ]
+   "source": ["from langchain_community.tools.tavily_search import TavilySearchResults\n\ntools = [TavilySearchResults(max_results=1)]"]
   },
   {
    "cell_type": "markdown",
@@ -123,11 +107,7 @@
    "id": "892b54b9-75f0-4804-9ed0-88b5e5532989",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_anthropic import ChatAnthropic\n",
-    "\n",
-    "model = ChatAnthropic(temperature=0, model_name=\"claude-3-opus-20240229\")"
-   ]
+   "source": ["from langchain_anthropic import ChatAnthropic\n\nmodel = ChatAnthropic(temperature=0, model_name=\"claude-3-opus-20240229\")"]
   },
   {
    "cell_type": "markdown",
@@ -154,9 +134,7 @@
      ]
     }
    ],
-   "source": [
-    "model = model.bind_tools(tools)"
-   ]
+   "source": ["model = model.bind_tools(tools)"]
   },
   {
    "cell_type": "code",
@@ -164,16 +142,7 @@
    "id": "ea793afa-2eab-4901-910d-6eed90cd6564",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, Sequence, TypedDict\n",
-    "\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    messages: Annotated[Sequence[BaseMessage], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, Sequence, TypedDict\n\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    messages: Annotated[Sequence[BaseMessage], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -208,33 +177,7 @@
    "id": "3b541bb9-900c-40d0-964d-7b5dfee30667",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolNode\n",
-    "\n",
-    "\n",
-    "# Define the function that determines whether to continue or not\n",
-    "def should_continue(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    last_message = messages[-1]\n",
-    "    # If there are no tool calls, then we finish\n",
-    "    if not last_message.tool_calls:\n",
-    "        return \"end\"\n",
-    "    # Otherwise if there is, we continue\n",
-    "    else:\n",
-    "        return \"continue\"\n",
-    "\n",
-    "\n",
-    "# Define the function that calls the model\n",
-    "def call_model(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    response = model.invoke(messages)\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [response]}\n",
-    "\n",
-    "\n",
-    "# Define the function to execute tools\n",
-    "tool_node = ToolNode(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolNode\n\n\n# Define the function that determines whether to continue or not\ndef should_continue(state):\n    messages = state[\"messages\"]\n    last_message = messages[-1]\n    # If there are no tool calls, then we finish\n    if not last_message.tool_calls:\n        return \"end\"\n    # Otherwise if there is, we continue\n    else:\n        return \"continue\"\n\n\n# Define the function that calls the model\ndef call_model(state):\n    messages = state[\"messages\"]\n    response = model.invoke(messages)\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [response]}\n\n\n# Define the function to execute tools\ntool_node = ToolNode(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -252,50 +195,7 @@
    "id": "813ae66c-3b58-4283-a02a-36da72a2ab90",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "workflow.add_node(\"action\", tool_node)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", call_model)\nworkflow.add_node(\"action\", tool_node)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "markdown",
@@ -328,12 +228,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "app.invoke(inputs)"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\ninputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\napp.invoke(inputs)"]
   },
   {
    "cell_type": "markdown",
@@ -383,16 +278,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "for output in app.stream(inputs):\n",
-    "    # stream() yields dictionaries with output keyed by node name\n",
-    "    for key, value in output.items():\n",
-    "        print(f\"Output from node '{key}':\")\n",
-    "        print(\"---\")\n",
-    "        print(value)\n",
-    "    print(\"\\n---\\n\")"
-   ]
+   "source": ["inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\nfor output in app.stream(inputs):\n    # stream() yields dictionaries with output keyed by node name\n    for key, value in output.items():\n        print(f\"Output from node '{key}':\")\n        print(\"---\")\n        print(value)\n    print(\"\\n---\\n\")"]
   }
  ],
  "metadata": {

examples/chat_agent_executor_with_function_calling/base.ipynb

@@ -26,10 +26,7 @@
    "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain langchain_openai tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain langchain_openai tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -45,13 +42,7 @@
    "id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nos.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\nos.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -67,10 +58,7 @@
    "id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -90,11 +78,7 @@
    "id": "d7ef57dd-5d6e-4ad3-9377-a92201c1310e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "\n",
-    "tools = [TavilySearchResults(max_results=1)]"
-   ]
+   "source": ["from langchain_community.tools.tavily_search import TavilySearchResults\n\ntools = [TavilySearchResults(max_results=1)]"]
   },
   {
    "cell_type": "markdown",
@@ -112,11 +96,7 @@
    "id": "5cf3331e-ccb3-41c8-aeb9-a840a94d41e7",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolExecutor\n",
-    "\n",
-    "tool_executor = ToolExecutor(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolExecutor\n\ntool_executor = ToolExecutor(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -140,13 +120,7 @@
    "id": "892b54b9-75f0-4804-9ed0-88b5e5532989",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "# We will set streaming=True so that we can stream tokens\n",
-    "# See the streaming section for more information on this.\n",
-    "model = ChatOpenAI(temperature=0, streaming=True)"
-   ]
+   "source": ["from langchain_openai import ChatOpenAI\n\n# We will set streaming=True so that we can stream tokens\n# See the streaming section for more information on this.\nmodel = ChatOpenAI(temperature=0, streaming=True)"]
   },
   {
    "cell_type": "markdown",
@@ -164,9 +138,7 @@
    "id": "cd3cbae5-d92c-4559-a4aa-44721b80d107",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "model = model.bind_tools(tools)"
-   ]
+   "source": ["model = model.bind_tools(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -192,16 +164,7 @@
    "id": "ea793afa-2eab-4901-910d-6eed90cd6564",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, Sequence, TypedDict\n",
-    "\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    messages: Annotated[Sequence[BaseMessage], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, Sequence, TypedDict\n\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    messages: Annotated[Sequence[BaseMessage], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -236,53 +199,7 @@
    "id": "3b541bb9-900c-40d0-964d-7b5dfee30667",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.messages import ToolMessage\n",
-    "\n",
-    "from langgraph.prebuilt import ToolInvocation\n",
-    "\n",
-    "\n",
-    "# Define the function that determines whether to continue or not\n",
-    "def should_continue(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    last_message = messages[-1]\n",
-    "    # If there is no function call, then we finish\n",
-    "    if not last_message.tool_calls:\n",
-    "        return \"end\"\n",
-    "    # Otherwise if there is, we continue\n",
-    "    else:\n",
-    "        return \"continue\"\n",
-    "\n",
-    "\n",
-    "# Define the function that calls the model\n",
-    "def call_model(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    response = model.invoke(messages)\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [response]}\n",
-    "\n",
-    "\n",
-    "# Define the function to execute tools\n",
-    "def call_tool(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    # Based on the continue condition\n",
-    "    # we know the last message involves a function call\n",
-    "    last_message = messages[-1]\n",
-    "    # We construct an ToolInvocation from the function_call\n",
-    "    tool_call = last_message.tool_calls[0]\n",
-    "    action = ToolInvocation(\n",
-    "        tool=tool_call[\"name\"],\n",
-    "        tool_input=tool_call[\"args\"],\n",
-    "    )\n",
-    "    # We call the tool_executor and get back a response\n",
-    "    response = tool_executor.invoke(action)\n",
-    "    # We use the response to create a FunctionMessage\n",
-    "    function_message = ToolMessage(\n",
-    "        content=str(response), name=action.tool, tool_call_id=tool_call[\"id\"]\n",
-    "    )\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [function_message]}"
-   ]
+   "source": ["from langchain_core.messages import ToolMessage\n\nfrom langgraph.prebuilt import ToolInvocation\n\n\n# Define the function that determines whether to continue or not\ndef should_continue(state):\n    messages = state[\"messages\"]\n    last_message = messages[-1]\n    # If there is no function call, then we finish\n    if not last_message.tool_calls:\n        return \"end\"\n    # Otherwise if there is, we continue\n    else:\n        return \"continue\"\n\n\n# Define the function that calls the model\ndef call_model(state):\n    messages = state[\"messages\"]\n    response = model.invoke(messages)\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [response]}\n\n\n# Define the function to execute tools\ndef call_tool(state):\n    messages = state[\"messages\"]\n    # Based on the continue condition\n    # we know the last message involves a function call\n    last_message = messages[-1]\n    # We construct an ToolInvocation from the function_call\n    tool_call = last_message.tool_calls[0]\n    action = ToolInvocation(\n        tool=tool_call[\"name\"],\n        tool_input=tool_call[\"args\"],\n    )\n    # We call the tool_executor and get back a response\n    response = tool_executor.invoke(action)\n    # We use the response to create a FunctionMessage\n    function_message = ToolMessage(\n        content=str(response), name=action.tool, tool_call_id=tool_call[\"id\"]\n    )\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [function_message]}"]
   },
   {
    "cell_type": "markdown",
@@ -300,50 +217,7 @@
    "id": "813ae66c-3b58-4283-a02a-36da72a2ab90",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "workflow.add_node(\"action\", call_tool)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", call_model)\nworkflow.add_node(\"action\", call_tool)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -362,15 +236,7 @@
      "output_type": "display_data"
     }
    ],
-   "source": [
-    "from IPython.display import Image, display\n",
-    "\n",
-    "try:\n",
-    "    display(Image(app.get_graph(xray=True).draw_mermaid_png()))\n",
-    "except Exception:\n",
-    "    # This requires some extra dependencies and is optional\n",
-    "    pass"
-   ]
+   "source": ["from IPython.display import Image, display\n\ntry:\n    display(Image(app.get_graph(xray=True).draw_mermaid_png()))\nexcept Exception:\n    # This requires some extra dependencies and is optional\n    pass"]
   },
   {
    "cell_type": "markdown",
@@ -403,12 +269,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "app.invoke(inputs)"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\ninputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\napp.invoke(inputs)"]
   },
   {
    "cell_type": "markdown",
@@ -458,16 +319,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "for output in app.stream(inputs):\n",
-    "    # stream() yields dictionaries with output keyed by node name\n",
-    "    for key, value in output.items():\n",
-    "        print(f\"Output from node '{key}':\")\n",
-    "        print(\"---\")\n",
-    "        print(value)\n",
-    "    print(\"\\n---\\n\")"
-   ]
+   "source": ["inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\nfor output in app.stream(inputs):\n    # stream() yields dictionaries with output keyed by node name\n    for key, value in output.items():\n        print(f\"Output from node '{key}':\")\n        print(\"---\")\n        print(value)\n    print(\"\\n---\\n\")"]
   },
   {
    "cell_type": "markdown",
@@ -604,21 +456,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf?\")]}\n",
-    "\n",
-    "async for output in app.astream_log(inputs, include_types=[\"llm\"]):\n",
-    "    # astream_log() yields the requested logs (here LLMs) in JSONPatch format\n",
-    "    for op in output.ops:\n",
-    "        if op[\"path\"] == \"/streamed_output/-\":\n",
-    "            # this is the output from .stream()\n",
-    "            ...\n",
-    "        elif op[\"path\"].startswith(\"/logs/\") and op[\"path\"].endswith(\n",
-    "            \"/streamed_output/-\"\n",
-    "        ):\n",
-    "            # because we chose to only include LLMs, these are LLM tokens\n",
-    "            print(op[\"value\"])"
-   ]
+   "source": ["inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf?\")]}\n\nasync for output in app.astream_log(inputs, include_types=[\"llm\"]):\n    # astream_log() yields the requested logs (here LLMs) in JSONPatch format\n    for op in output.ops:\n        if op[\"path\"] == \"/streamed_output/-\":\n            # this is the output from .stream()\n            ...\n        elif op[\"path\"].startswith(\"/logs/\") and op[\"path\"].endswith(\n            \"/streamed_output/-\"\n        ):\n            # because we chose to only include LLMs, these are LLM tokens\n            print(op[\"value\"])"]
   },
   {
    "cell_type": "code",
@@ -626,7 +464,7 @@
    "id": "08ae8246-11d5-40e1-8567-361e5bef8917",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/chat_agent_executor_with_function_calling/dynamically-returning-directly.ipynb

@@ -38,10 +38,7 @@
    "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain langchain_openai tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain langchain_openai tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -57,13 +54,7 @@
    "id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nos.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\nos.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -79,10 +70,7 @@
    "id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -106,19 +94,7 @@
    "id": "4a1b9990-3b11-4a51-bd51-76117afd38b9",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
-    "\n",
-    "\n",
-    "class SearchTool(BaseModel):\n",
-    "    \"\"\"Look up things online, optionally returning directly\"\"\"\n",
-    "\n",
-    "    query: str = Field(description=\"query to look up online\")\n",
-    "    return_direct: bool = Field(\n",
-    "        description=\"Whether or the result of this should be returned directly to the user without you seeing what it is\",\n",
-    "        default=False,\n",
-    "    )"
-   ]
+   "source": ["from langchain_core.pydantic_v1 import BaseModel, Field\n\n\nclass SearchTool(BaseModel):\n    \"\"\"Look up things online, optionally returning directly\"\"\"\n\n    query: str = Field(description=\"query to look up online\")\n    return_direct: bool = Field(\n        description=\"Whether or the result of this should be returned directly to the user without you seeing what it is\",\n        default=False,\n    )"]
   },
   {
    "cell_type": "code",
@@ -126,12 +102,7 @@
    "id": "d7ef57dd-5d6e-4ad3-9377-a92201c1310e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "\n",
-    "search_tool = TavilySearchResults(max_results=1, args_schema=SearchTool)\n",
-    "tools = [search_tool]"
-   ]
+   "source": ["from langchain_community.tools.tavily_search import TavilySearchResults\n\nsearch_tool = TavilySearchResults(max_results=1, args_schema=SearchTool)\ntools = [search_tool]"]
   },
   {
    "cell_type": "markdown",
@@ -149,11 +120,7 @@
    "id": "5cf3331e-ccb3-41c8-aeb9-a840a94d41e7",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolExecutor\n",
-    "\n",
-    "tool_executor = ToolExecutor(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolExecutor\n\ntool_executor = ToolExecutor(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -177,13 +144,7 @@
    "id": "892b54b9-75f0-4804-9ed0-88b5e5532989",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "# We will set streaming=True so that we can stream tokens\n",
-    "# See the streaming section for more information on this.\n",
-    "model = ChatOpenAI(temperature=0, streaming=True)"
-   ]
+   "source": ["from langchain_openai import ChatOpenAI\n\n# We will set streaming=True so that we can stream tokens\n# See the streaming section for more information on this.\nmodel = ChatOpenAI(temperature=0, streaming=True)"]
   },
   {
    "cell_type": "markdown",
@@ -201,9 +162,7 @@
    "id": "cd3cbae5-d92c-4559-a4aa-44721b80d107",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "model = model.bind_tools(tools)"
-   ]
+   "source": ["model = model.bind_tools(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -229,16 +188,7 @@
    "id": "ea793afa-2eab-4901-910d-6eed90cd6564",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, Sequence, TypedDict\n",
-    "\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    messages: Annotated[Sequence[BaseMessage], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, Sequence, TypedDict\n\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    messages: Annotated[Sequence[BaseMessage], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -273,11 +223,7 @@
    "id": "03308b6b-de72-4cdc-b6c6-47e654df340e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.messages import ToolMessage\n",
-    "\n",
-    "from langgraph.prebuilt import ToolInvocation"
-   ]
+   "source": ["from langchain_core.messages import ToolMessage\n\nfrom langgraph.prebuilt import ToolInvocation"]
   },
   {
    "cell_type": "markdown",
@@ -295,22 +241,7 @@
    "id": "55e088b1-f3c8-4798-9ca8-5b0be961b49a",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Define the function that determines whether to continue or not\n",
-    "def should_continue(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    last_message = messages[-1]\n",
-    "    # If there is no function call, then we finish\n",
-    "    if not last_message.tool_calls:\n",
-    "        return \"end\"\n",
-    "    # Otherwise if there is, we check if it's suppose to return direct\n",
-    "    else:\n",
-    "        arguments = last_message.tool_calls[0][\"args\"]\n",
-    "        if arguments.get(\"return_direct\", False):\n",
-    "            return \"final\"\n",
-    "        else:\n",
-    "            return \"continue\""
-   ]
+   "source": ["# Define the function that determines whether to continue or not\ndef should_continue(state):\n    messages = state[\"messages\"]\n    last_message = messages[-1]\n    # If there is no function call, then we finish\n    if not last_message.tool_calls:\n        return \"end\"\n    # Otherwise if there is, we check if it's suppose to return direct\n    else:\n        arguments = last_message.tool_calls[0][\"args\"]\n        if arguments.get(\"return_direct\", False):\n            return \"final\"\n        else:\n            return \"continue\""]
   },
   {
    "cell_type": "code",
@@ -318,14 +249,7 @@
    "id": "2b45da72-1afa-4cd7-9b7f-49a7c99cdb8a",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Define the function that calls the model\n",
-    "def call_model(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    response = model.invoke(messages)\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [response]}"
-   ]
+   "source": ["# Define the function that calls the model\ndef call_model(state):\n    messages = state[\"messages\"]\n    response = model.invoke(messages)\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [response]}"]
   },
   {
    "cell_type": "markdown",
@@ -343,33 +267,7 @@
    "id": "dd876f5d-88d6-4f93-b1d0-f2f0b6f4d991",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Define the function to execute tools\n",
-    "def call_tool(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    # Based on the continue condition\n",
-    "    # we know the last message involves a function call\n",
-    "    last_message = messages[-1]\n",
-    "    # We construct an ToolInvocation from the function_call\n",
-    "    tool_call = last_message.tool_calls[0]\n",
-    "    tool_name = tool_call[\"name\"]\n",
-    "    arguments = tool_call[\"args\"]\n",
-    "    if tool_name == \"tavily_search_results_json\":\n",
-    "        if \"return_direct\" in arguments:\n",
-    "            del arguments[\"return_direct\"]\n",
-    "    action = ToolInvocation(\n",
-    "        tool=tool_name,\n",
-    "        tool_input=arguments,\n",
-    "    )\n",
-    "    # We call the tool_executor and get back a response\n",
-    "    response = tool_executor.invoke(action)\n",
-    "    # We use the response to create a ToolMessage\n",
-    "    tool_message = ToolMessage(\n",
-    "        content=str(response), name=action.tool, tool_call_id=tool_call[\"id\"]\n",
-    "    )\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [tool_message]}"
-   ]
+   "source": ["# Define the function to execute tools\ndef call_tool(state):\n    messages = state[\"messages\"]\n    # Based on the continue condition\n    # we know the last message involves a function call\n    last_message = messages[-1]\n    # We construct an ToolInvocation from the function_call\n    tool_call = last_message.tool_calls[0]\n    tool_name = tool_call[\"name\"]\n    arguments = tool_call[\"args\"]\n    if tool_name == \"tavily_search_results_json\":\n        if \"return_direct\" in arguments:\n            del arguments[\"return_direct\"]\n    action = ToolInvocation(\n        tool=tool_name,\n        tool_input=arguments,\n    )\n    # We call the tool_executor and get back a response\n    response = tool_executor.invoke(action)\n    # We use the response to create a ToolMessage\n    tool_message = ToolMessage(\n        content=str(response), name=action.tool, tool_call_id=tool_call[\"id\"]\n    )\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [tool_message]}"]
   },
   {
    "cell_type": "markdown",
@@ -391,54 +289,7 @@
    "id": "813ae66c-3b58-4283-a02a-36da72a2ab90",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "workflow.add_node(\"action\", call_tool)\n",
-    "workflow.add_node(\"final\", call_tool)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Final call\n",
-    "        \"final\": \"final\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "workflow.add_edge(\"final\", END)\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", call_model)\nworkflow.add_node(\"action\", call_tool)\nworkflow.add_node(\"final\", call_tool)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Final call\n        \"final\": \"final\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\nworkflow.add_edge(\"final\", END)\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -457,15 +308,7 @@
      "output_type": "display_data"
     }
    ],
-   "source": [
-    "from IPython.display import Image, display\n",
-    "\n",
-    "try:\n",
-    "    display(Image(app.get_graph(xray=True).draw_mermaid_png()))\n",
-    "except Exception:\n",
-    "    # This requires some extra dependencies and is optional\n",
-    "    pass"
-   ]
+   "source": ["from IPython.display import Image, display\n\ntry:\n    display(Image(app.get_graph(xray=True).draw_mermaid_png()))\nexcept Exception:\n    # This requires some extra dependencies and is optional\n    pass"]
   },
   {
    "cell_type": "markdown",
@@ -509,18 +352,7 @@
      ]
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "for output in app.stream(inputs):\n",
-    "    # stream() yields dictionaries with output keyed by node name\n",
-    "    for key, value in output.items():\n",
-    "        print(f\"Output from node '{key}':\")\n",
-    "        print(\"---\")\n",
-    "        print(value)\n",
-    "    print(\"\\n---\\n\")"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\ninputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\nfor output in app.stream(inputs):\n    # stream() yields dictionaries with output keyed by node name\n    for key, value in output.items():\n        print(f\"Output from node '{key}':\")\n        print(\"---\")\n        print(value)\n    print(\"\\n---\\n\")"]
   },
   {
    "cell_type": "code",
@@ -547,24 +379,7 @@
      ]
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "inputs = {\n",
-    "    \"messages\": [\n",
-    "        HumanMessage(\n",
-    "            content=\"what is the weather in sf? return this result directly by setting return_direct = True\"\n",
-    "        )\n",
-    "    ]\n",
-    "}\n",
-    "for output in app.stream(inputs):\n",
-    "    # stream() yields dictionaries with output keyed by node name\n",
-    "    for key, value in output.items():\n",
-    "        print(f\"Output from node '{key}':\")\n",
-    "        print(\"---\")\n",
-    "        print(value)\n",
-    "    print(\"\\n---\\n\")"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\ninputs = {\n    \"messages\": [\n        HumanMessage(\n            content=\"what is the weather in sf? return this result directly by setting return_direct = True\"\n        )\n    ]\n}\nfor output in app.stream(inputs):\n    # stream() yields dictionaries with output keyed by node name\n    for key, value in output.items():\n        print(f\"Output from node '{key}':\")\n        print(\"---\")\n        print(value)\n    print(\"\\n---\\n\")"]
   },
   {
    "cell_type": "code",
@@ -572,7 +387,7 @@
    "id": "49ccc134-4abe-4982-8ecd-d70fc56a4d2d",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/chat_agent_executor_with_function_calling/force-calling-a-tool-first.ipynb

@@ -30,10 +30,7 @@
    "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain_openai tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain_openai tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -49,18 +46,7 @@
    "id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "\n",
-    "def _set_env(var: str):\n",
-    "    if not os.environ.get(var):\n",
-    "        os.environ[var] = getpass.getpass(f\"{var}: \")\n",
-    "\n",
-    "\n",
-    "_set_env(\"OPENAI_API_KEY\")"
-   ]
+   "source": ["import getpass\nimport os\n\n\ndef _set_env(var: str):\n    if not os.environ.get(var):\n        os.environ[var] = getpass.getpass(f\"{var}: \")\n\n\n_set_env(\"OPENAI_API_KEY\")"]
   },
   {
    "cell_type": "markdown",
@@ -76,10 +62,7 @@
    "id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "_set_env(\"LANGCHAIN_API_KEY\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n_set_env(\"LANGCHAIN_API_KEY\")"]
   },
   {
    "cell_type": "markdown",
@@ -99,19 +82,7 @@
    "id": "d7ef57dd-5d6e-4ad3-9377-a92201c1310e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.tools import tool\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "def search(query: str):\n",
-    "    \"\"\"Call to surf the web.\"\"\"\n",
-    "    # This is a placeholder, but don't tell the LLM that...\n",
-    "    return [\"The answer to your question lies within.\"]\n",
-    "\n",
-    "\n",
-    "tools = [search]"
-   ]
+   "source": ["from langchain_core.tools import tool\n\n\n@tool\ndef search(query: str):\n    \"\"\"Call to surf the web.\"\"\"\n    # This is a placeholder, but don't tell the LLM that...\n    return [\"The answer to your question lies within.\"]\n\n\ntools = [search]"]
   },
   {
    "cell_type": "markdown",
@@ -129,11 +100,7 @@
    "id": "5cf3331e-ccb3-41c8-aeb9-a840a94d41e7",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolExecutor\n",
-    "\n",
-    "tool_executor = ToolExecutor(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolExecutor\n\ntool_executor = ToolExecutor(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -157,11 +124,7 @@
    "id": "892b54b9-75f0-4804-9ed0-88b5e5532989",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "model = ChatOpenAI(temperature=0)"
-   ]
+   "source": ["from langchain_openai import ChatOpenAI\n\nmodel = ChatOpenAI(temperature=0)"]
   },
   {
    "cell_type": "markdown",
@@ -179,9 +142,7 @@
    "id": "cd3cbae5-d92c-4559-a4aa-44721b80d107",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "model = model.bind_tools(tools)"
-   ]
+   "source": ["model = model.bind_tools(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -207,16 +168,7 @@
    "id": "ea793afa-2eab-4901-910d-6eed90cd6564",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, Sequence, TypedDict\n",
-    "\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    messages: Annotated[Sequence[BaseMessage], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, Sequence, TypedDict\n\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    messages: Annotated[Sequence[BaseMessage], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -251,69 +203,7 @@
    "id": "3b541bb9-900c-40d0-964d-7b5dfee30667",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.messages import ToolMessage\n",
-    "\n",
-    "from langgraph.prebuilt import ToolInvocation\n",
-    "\n",
-    "\n",
-    "# Define the function that determines whether to continue or not\n",
-    "def should_continue(state: AgentState):\n",
-    "    messages = state[\"messages\"]\n",
-    "    last_message = messages[-1]\n",
-    "    # If there is no function call, then we finish\n",
-    "    if not last_message.tool_calls:\n",
-    "        return \"end\"\n",
-    "    # Otherwise if there is, we continue\n",
-    "    else:\n",
-    "        return \"continue\"\n",
-    "\n",
-    "\n",
-    "# Define the function that calls the model\n",
-    "def call_model(state: AgentState):\n",
-    "    messages = state[\"messages\"]\n",
-    "    response = model.invoke(messages)\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [response]}\n",
-    "\n",
-    "\n",
-    "# Define the function to execute tools\n",
-    "# We recommend you use ToolNode\n",
-    "# for this, but we are showing the\n",
-    "# manual way here for clarity\n",
-    "def call_tool(state: AgentState):\n",
-    "    messages = state[\"messages\"]\n",
-    "    # Based on the continue condition\n",
-    "    # we know the last message involves a function call\n",
-    "    last_message = messages[-1]\n",
-    "    # We construct an ToolInvocation for each tool call\n",
-    "    tool_invocations = []\n",
-    "    for tool_call in last_message.tool_calls:\n",
-    "        action = ToolInvocation(\n",
-    "            tool=tool_call[\"name\"],\n",
-    "            tool_input=tool_call[\"args\"],\n",
-    "        )\n",
-    "        tool_invocations.append(action)\n",
-    "\n",
-    "    action = ToolInvocation(\n",
-    "        tool=tool_call[\"name\"],\n",
-    "        tool_input=tool_call[\"args\"],\n",
-    "    )\n",
-    "    # We call the tool_executor and get back a response\n",
-    "    responses = tool_executor.batch(tool_invocations, return_exceptions=True)\n",
-    "    # We use the response to create tool messages\n",
-    "    tool_messages = [\n",
-    "        ToolMessage(\n",
-    "            content=str(response),\n",
-    "            name=tc[\"name\"],\n",
-    "            tool_call_id=tc[\"id\"],\n",
-    "        )\n",
-    "        for tc, response in zip(last_message.tool_calls, responses)\n",
-    "    ]\n",
-    "\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": tool_messages}"
-   ]
+   "source": ["from langchain_core.messages import ToolMessage\n\nfrom langgraph.prebuilt import ToolInvocation\n\n\n# Define the function that determines whether to continue or not\ndef should_continue(state: AgentState):\n    messages = state[\"messages\"]\n    last_message = messages[-1]\n    # If there is no function call, then we finish\n    if not last_message.tool_calls:\n        return \"end\"\n    # Otherwise if there is, we continue\n    else:\n        return \"continue\"\n\n\n# Define the function that calls the model\ndef call_model(state: AgentState):\n    messages = state[\"messages\"]\n    response = model.invoke(messages)\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [response]}\n\n\n# Define the function to execute tools\n# We recommend you use ToolNode\n# for this, but we are showing the\n# manual way here for clarity\ndef call_tool(state: AgentState):\n    messages = state[\"messages\"]\n    # Based on the continue condition\n    # we know the last message involves a function call\n    last_message = messages[-1]\n    # We construct an ToolInvocation for each tool call\n    tool_invocations = []\n    for tool_call in last_message.tool_calls:\n        action = ToolInvocation(\n            tool=tool_call[\"name\"],\n            tool_input=tool_call[\"args\"],\n        )\n        tool_invocations.append(action)\n\n    action = ToolInvocation(\n        tool=tool_call[\"name\"],\n        tool_input=tool_call[\"args\"],\n    )\n    # We call the tool_executor and get back a response\n    responses = tool_executor.batch(tool_invocations, return_exceptions=True)\n    # We use the response to create tool messages\n    tool_messages = [\n        ToolMessage(\n            content=str(response),\n            name=tc[\"name\"],\n            tool_call_id=tc[\"id\"],\n        )\n        for tc, response in zip(last_message.tool_calls, responses)\n    ]\n\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": tool_messages}"]
   },
   {
    "cell_type": "markdown",
@@ -331,30 +221,7 @@
    "id": "1bfd2b22-292a-4f4d-91a0-46bb704f5e38",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# This is the new first - the first call of the model we want to explicitly hard-code some action\n",
-    "from langchain_core.messages import AIMessage\n",
-    "\n",
-    "\n",
-    "def first_model(state: AgentState):\n",
-    "    human_input = state[\"messages\"][-1].content\n",
-    "    return {\n",
-    "        \"messages\": [\n",
-    "            AIMessage(\n",
-    "                content=\"\",\n",
-    "                tool_calls=[\n",
-    "                    {\n",
-    "                        \"name\": \"tavily_search_results_json\",\n",
-    "                        \"args\": {\n",
-    "                            \"query\": human_input,\n",
-    "                        },\n",
-    "                        \"id\": \"tool_abcd123\",\n",
-    "                    }\n",
-    "                ],\n",
-    "            )\n",
-    "        ]\n",
-    "    }"
-   ]
+   "source": ["# This is the new first - the first call of the model we want to explicitly hard-code some action\nfrom langchain_core.messages import AIMessage\n\n\ndef first_model(state: AgentState):\n    human_input = state[\"messages\"][-1].content\n    return {\n        \"messages\": [\n            AIMessage(\n                content=\"\",\n                tool_calls=[\n                    {\n                        \"name\": \"tavily_search_results_json\",\n                        \"args\": {\n                            \"query\": human_input,\n                        },\n                        \"id\": \"tool_abcd123\",\n                    }\n                ],\n            )\n        ]\n    }"]
   },
   {
    "cell_type": "markdown",
@@ -376,56 +243,7 @@
    "id": "813ae66c-3b58-4283-a02a-36da72a2ab90",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the new entrypoint\n",
-    "workflow.add_node(\"first_agent\", first_model)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "workflow.add_node(\"action\", call_tool)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"first_agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# After we call the first agent, we know we want to go to action\n",
-    "workflow.add_edge(\"first_agent\", \"action\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the new entrypoint\nworkflow.add_node(\"first_agent\", first_model)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", call_model)\nworkflow.add_node(\"action\", call_tool)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"first_agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# After we call the first agent, we know we want to go to action\nworkflow.add_edge(\"first_agent\", \"action\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -444,11 +262,7 @@
      "output_type": "display_data"
     }
    ],
-   "source": [
-    "from IPython.display import Image, display\n",
-    "\n",
-    "display(Image(app.get_graph(xray=True).draw_mermaid_png()))"
-   ]
+   "source": ["from IPython.display import Image, display\n\ndisplay(Image(app.get_graph(xray=True).draw_mermaid_png()))"]
   },
   {
    "cell_type": "markdown",
@@ -670,17 +484,7 @@
      ]
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "for output in app.stream(inputs, stream_mode=\"values\"):\n",
-    "    # stream() yields dictionaries with output keyed by node name\n",
-    "    messages = output[\"messages\"]\n",
-    "    for message in messages:\n",
-    "        message.pretty_print()\n",
-    "    print(\"\\n---\\n\")"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\ninputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\nfor output in app.stream(inputs, stream_mode=\"values\"):\n    # stream() yields dictionaries with output keyed by node name\n    messages = output[\"messages\"]\n    for message in messages:\n        message.pretty_print()\n    print(\"\\n---\\n\")"]
   },
   {
    "cell_type": "code",
@@ -688,7 +492,7 @@
    "id": "08ae8246-11d5-40e1-8567-361e5bef8917",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/chat_agent_executor_with_function_calling/human-in-the-loop.ipynb

@@ -30,10 +30,7 @@
    "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain_community langchain_openai tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain_community langchain_openai tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -58,13 +55,7 @@
      ]
     }
    ],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nos.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\nos.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -88,10 +79,7 @@
      ]
     }
    ],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -111,11 +99,7 @@
    "id": "d7ef57dd-5d6e-4ad3-9377-a92201c1310e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "\n",
-    "tools = [TavilySearchResults(max_results=1)]"
-   ]
+   "source": ["from langchain_community.tools.tavily_search import TavilySearchResults\n\ntools = [TavilySearchResults(max_results=1)]"]
   },
   {
    "cell_type": "markdown",
@@ -133,11 +117,7 @@
    "id": "5cf3331e-ccb3-41c8-aeb9-a840a94d41e7",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolExecutor\n",
-    "\n",
-    "tool_executor = ToolExecutor(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolExecutor\n\ntool_executor = ToolExecutor(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -161,13 +141,7 @@
    "id": "892b54b9-75f0-4804-9ed0-88b5e5532989",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "# We will set streaming=True so that we can stream tokens\n",
-    "# See the streaming section for more information on this.\n",
-    "model = ChatOpenAI(temperature=0, streaming=True)"
-   ]
+   "source": ["from langchain_openai import ChatOpenAI\n\n# We will set streaming=True so that we can stream tokens\n# See the streaming section for more information on this.\nmodel = ChatOpenAI(temperature=0, streaming=True)"]
   },
   {
    "cell_type": "markdown",
@@ -185,9 +159,7 @@
    "id": "cd3cbae5-d92c-4559-a4aa-44721b80d107",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "model = model.bind_tools(tools)"
-   ]
+   "source": ["model = model.bind_tools(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -213,16 +185,7 @@
    "id": "ea793afa-2eab-4901-910d-6eed90cd6564",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, Sequence, TypedDict\n",
-    "\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    messages: Annotated[Sequence[BaseMessage], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, Sequence, TypedDict\n\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    messages: Annotated[Sequence[BaseMessage], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -257,31 +220,7 @@
    "id": "b547109f-f9e8-4e77-a7e7-ed2bae7a72ab",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.messages import ToolMessage\n",
-    "\n",
-    "from langgraph.prebuilt import ToolInvocation\n",
-    "\n",
-    "\n",
-    "# Define the function that determines whether to continue or not\n",
-    "def should_continue(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    last_message = messages[-1]\n",
-    "    # If there is no function call, then we finish\n",
-    "    if not last_message.tool_calls:\n",
-    "        return \"end\"\n",
-    "    # Otherwise if there is, we continue\n",
-    "    else:\n",
-    "        return \"continue\"\n",
-    "\n",
-    "\n",
-    "# Define the function that calls the model\n",
-    "def call_model(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    response = model.invoke(messages)\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [response]}"
-   ]
+   "source": ["from langchain_core.messages import ToolMessage\n\nfrom langgraph.prebuilt import ToolInvocation\n\n\n# Define the function that determines whether to continue or not\ndef should_continue(state):\n    messages = state[\"messages\"]\n    last_message = messages[-1]\n    # If there is no function call, then we finish\n    if not last_message.tool_calls:\n        return \"end\"\n    # Otherwise if there is, we continue\n    else:\n        return \"continue\"\n\n\n# Define the function that calls the model\ndef call_model(state):\n    messages = state[\"messages\"]\n    response = model.invoke(messages)\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [response]}"]
   },
   {
    "cell_type": "code",
@@ -289,41 +228,7 @@
    "id": "73fd6432-42e8-472a-89ca-bb5ddbbcc35a",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Define the function to execute tools\n",
-    "def call_tool(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    # Based on the continue condition\n",
-    "    # we know the last message involves a function call\n",
-    "    last_message = messages[-1]\n",
-    "    # We construct an ToolInvocation for each tool call\n",
-    "    tool_invocations = []\n",
-    "    for tool_call in last_message.tool_calls:\n",
-    "        action = ToolInvocation(\n",
-    "            tool=tool_call[\"name\"],\n",
-    "            tool_input=tool_call[\"args\"],\n",
-    "        )\n",
-    "        tool_invocations.append(action)\n",
-    "\n",
-    "    action = ToolInvocation(\n",
-    "        tool=tool_call[\"name\"],\n",
-    "        tool_input=tool_call[\"args\"],\n",
-    "    )\n",
-    "    # We call the tool_executor and get back a response\n",
-    "    responses = tool_executor.batch(tool_invocations, return_exceptions=True)\n",
-    "    # We use the response to create tool messages\n",
-    "    tool_messages = [\n",
-    "        ToolMessage(\n",
-    "            content=str(response),\n",
-    "            name=tc[\"name\"],\n",
-    "            tool_call_id=tc[\"id\"],\n",
-    "        )\n",
-    "        for tc, response in zip(last_message.tool_calls, responses)\n",
-    "    ]\n",
-    "\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": tool_messages}"
-   ]
+   "source": ["# Define the function to execute tools\ndef call_tool(state):\n    messages = state[\"messages\"]\n    # Based on the continue condition\n    # we know the last message involves a function call\n    last_message = messages[-1]\n    # We construct an ToolInvocation for each tool call\n    tool_invocations = []\n    for tool_call in last_message.tool_calls:\n        action = ToolInvocation(\n            tool=tool_call[\"name\"],\n            tool_input=tool_call[\"args\"],\n        )\n        tool_invocations.append(action)\n\n    action = ToolInvocation(\n        tool=tool_call[\"name\"],\n        tool_input=tool_call[\"args\"],\n    )\n    # We call the tool_executor and get back a response\n    responses = tool_executor.batch(tool_invocations, return_exceptions=True)\n    # We use the response to create tool messages\n    tool_messages = [\n        ToolMessage(\n            content=str(response),\n            name=tc[\"name\"],\n            tool_call_id=tc[\"id\"],\n        )\n        for tc, response in zip(last_message.tool_calls, responses)\n    ]\n\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": tool_messages}"]
   },
   {
    "cell_type": "markdown",
@@ -345,51 +250,7 @@
    "id": "813ae66c-3b58-4283-a02a-36da72a2ab90",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.checkpoint.memory import MemorySaver\n",
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "workflow.add_node(\"action\", call_tool)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile(checkpointer=MemorySaver(), interrupt_before=[\"action\"])"
-   ]
+   "source": ["from langgraph.checkpoint.memory import MemorySaver\nfrom langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", call_model)\nworkflow.add_node(\"action\", call_tool)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile(checkpointer=MemorySaver(), interrupt_before=[\"action\"])"]
   },
   {
    "cell_type": "code",
@@ -408,15 +269,7 @@
      "output_type": "display_data"
     }
    ],
-   "source": [
-    "from IPython.display import Image, display\n",
-    "\n",
-    "try:\n",
-    "    display(Image(app.get_graph(xray=True).draw_mermaid_png()))\n",
-    "except Exception:\n",
-    "    # This requires some extra dependencies and is optional\n",
-    "    pass"
-   ]
+   "source": ["from IPython.display import Image, display\n\ntry:\n    display(Image(app.get_graph(xray=True).draw_mermaid_png()))\nexcept Exception:\n    # This requires some extra dependencies and is optional\n    pass"]
   },
   {
    "cell_type": "markdown",
@@ -460,30 +313,7 @@
      ]
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "config = {\"configurable\": {\"thread_id\": \"thread-1\"}}\n",
-    "while True:\n",
-    "    for output in app.stream(inputs, config):\n",
-    "        # stream() yields dictionaries with output keyed by node name\n",
-    "        for key, value in output.items():\n",
-    "            print(f\"Output from node '{key}':\")\n",
-    "            print(\"---\")\n",
-    "            print(value)\n",
-    "        print(\"\\n---\\n\")\n",
-    "    snapshot = app.get_state(config)\n",
-    "    # If \"next\" is present, it means we've interrupted mid-execution\n",
-    "    if not snapshot.next:\n",
-    "        break\n",
-    "    inputs = None\n",
-    "    response = input(\n",
-    "        \"Do you approve the next step? Type y if you do, anything else to stop: \"\n",
-    "    )\n",
-    "    if response != \"y\":\n",
-    "        break"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\ninputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\nconfig = {\"configurable\": {\"thread_id\": \"thread-1\"}}\nwhile True:\n    for output in app.stream(inputs, config):\n        # stream() yields dictionaries with output keyed by node name\n        for key, value in output.items():\n            print(f\"Output from node '{key}':\")\n            print(\"---\")\n            print(value)\n        print(\"\\n---\\n\")\n    snapshot = app.get_state(config)\n    # If \"next\" is present, it means we've interrupted mid-execution\n    if not snapshot.next:\n        break\n    inputs = None\n    response = input(\n        \"Do you approve the next step? Type y if you do, anything else to stop: \"\n    )\n    if response != \"y\":\n        break"]
   }
  ],
  "metadata": {

examples/chat_agent_executor_with_function_calling/managing-agent-steps.ipynb

@@ -30,10 +30,7 @@
    "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain langchain_openai tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain langchain_openai tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -49,13 +46,7 @@
    "id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nos.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\nos.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -71,10 +62,7 @@
    "id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -94,11 +82,7 @@
    "id": "d7ef57dd-5d6e-4ad3-9377-a92201c1310e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "\n",
-    "tools = [TavilySearchResults(max_results=1)]"
-   ]
+   "source": ["from langchain_community.tools.tavily_search import TavilySearchResults\n\ntools = [TavilySearchResults(max_results=1)]"]
   },
   {
    "cell_type": "markdown",
@@ -116,11 +100,7 @@
    "id": "5cf3331e-ccb3-41c8-aeb9-a840a94d41e7",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolExecutor\n",
-    "\n",
-    "tool_executor = ToolExecutor(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolExecutor\n\ntool_executor = ToolExecutor(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -144,13 +124,7 @@
    "id": "892b54b9-75f0-4804-9ed0-88b5e5532989",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "# We will set streaming=True so that we can stream tokens\n",
-    "# See the streaming section for more information on this.\n",
-    "model = ChatOpenAI(temperature=0, streaming=True)"
-   ]
+   "source": ["from langchain_openai import ChatOpenAI\n\n# We will set streaming=True so that we can stream tokens\n# See the streaming section for more information on this.\nmodel = ChatOpenAI(temperature=0, streaming=True)"]
   },
   {
    "cell_type": "markdown",
@@ -168,9 +142,7 @@
    "id": "cd3cbae5-d92c-4559-a4aa-44721b80d107",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "model = model.bind_tools(tools)"
-   ]
+   "source": ["model = model.bind_tools(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -196,16 +168,7 @@
    "id": "ea793afa-2eab-4901-910d-6eed90cd6564",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, Sequence, TypedDict\n",
-    "\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    messages: Annotated[Sequence[BaseMessage], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, Sequence, TypedDict\n\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    messages: Annotated[Sequence[BaseMessage], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -240,23 +203,7 @@
    "id": "e718a9c5-6596-457f-ac25-a25d8cb8c259",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.messages import ToolMessage\n",
-    "\n",
-    "from langgraph.prebuilt import ToolInvocation\n",
-    "\n",
-    "\n",
-    "# Define the function that determines whether to continue or not\n",
-    "def should_continue(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    last_message = messages[-1]\n",
-    "    # If there is no function call, then we finish\n",
-    "    if not last_message.tool_calls:\n",
-    "        return \"end\"\n",
-    "    # Otherwise if there is, we continue\n",
-    "    else:\n",
-    "        return \"continue\""
-   ]
+   "source": ["from langchain_core.messages import ToolMessage\n\nfrom langgraph.prebuilt import ToolInvocation\n\n\n# Define the function that determines whether to continue or not\ndef should_continue(state):\n    messages = state[\"messages\"]\n    last_message = messages[-1]\n    # If there is no function call, then we finish\n    if not last_message.tool_calls:\n        return \"end\"\n    # Otherwise if there is, we continue\n    else:\n        return \"continue\""]
   },
   {
    "cell_type": "markdown",
@@ -274,14 +221,7 @@
    "id": "714e4135-7cb5-4f17-b2ae-46f7e98bde61",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Define the function that calls the model\n",
-    "def call_model(state):\n",
-    "    messages = state[\"messages\"][-5:]\n",
-    "    response = model.invoke(messages)\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [response]}"
-   ]
+   "source": ["# Define the function that calls the model\ndef call_model(state):\n    messages = state[\"messages\"][-5:]\n    response = model.invoke(messages)\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [response]}"]
   },
   {
    "cell_type": "code",
@@ -289,41 +229,7 @@
    "id": "b3ca9564-63cc-4309-b158-5e8d3e907164",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Define the function to execute tools\n",
-    "def call_tool(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    # Based on the continue condition\n",
-    "    # we know the last message involves a function call\n",
-    "    last_message = messages[-1]\n",
-    "    # We construct an ToolInvocation for each tool call\n",
-    "    tool_invocations = []\n",
-    "    for tool_call in last_message.tool_calls:\n",
-    "        action = ToolInvocation(\n",
-    "            tool=tool_call[\"name\"],\n",
-    "            tool_input=tool_call[\"args\"],\n",
-    "        )\n",
-    "        tool_invocations.append(action)\n",
-    "\n",
-    "    action = ToolInvocation(\n",
-    "        tool=tool_call[\"name\"],\n",
-    "        tool_input=tool_call[\"args\"],\n",
-    "    )\n",
-    "    # We call the tool_executor and get back a response\n",
-    "    responses = tool_executor.batch(tool_invocations, return_exceptions=True)\n",
-    "    # We use the response to create tool messages\n",
-    "    tool_messages = [\n",
-    "        ToolMessage(\n",
-    "            content=str(response),\n",
-    "            name=tc[\"name\"],\n",
-    "            tool_call_id=tc[\"id\"],\n",
-    "        )\n",
-    "        for tc, response in zip(last_message.tool_calls, responses)\n",
-    "    ]\n",
-    "\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": tool_messages}"
-   ]
+   "source": ["# Define the function to execute tools\ndef call_tool(state):\n    messages = state[\"messages\"]\n    # Based on the continue condition\n    # we know the last message involves a function call\n    last_message = messages[-1]\n    # We construct an ToolInvocation for each tool call\n    tool_invocations = []\n    for tool_call in last_message.tool_calls:\n        action = ToolInvocation(\n            tool=tool_call[\"name\"],\n            tool_input=tool_call[\"args\"],\n        )\n        tool_invocations.append(action)\n\n    action = ToolInvocation(\n        tool=tool_call[\"name\"],\n        tool_input=tool_call[\"args\"],\n    )\n    # We call the tool_executor and get back a response\n    responses = tool_executor.batch(tool_invocations, return_exceptions=True)\n    # We use the response to create tool messages\n    tool_messages = [\n        ToolMessage(\n            content=str(response),\n            name=tc[\"name\"],\n            tool_call_id=tc[\"id\"],\n        )\n        for tc, response in zip(last_message.tool_calls, responses)\n    ]\n\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": tool_messages}"]
   },
   {
    "cell_type": "markdown",
@@ -341,50 +247,7 @@
    "id": "813ae66c-3b58-4283-a02a-36da72a2ab90",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "workflow.add_node(\"action\", call_tool)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", call_model)\nworkflow.add_node(\"action\", call_tool)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -403,15 +266,7 @@
      "output_type": "display_data"
     }
    ],
-   "source": [
-    "from IPython.display import Image, display\n",
-    "\n",
-    "try:\n",
-    "    display(Image(app.get_graph(xray=True).draw_mermaid_png()))\n",
-    "except Exception:\n",
-    "    # This requires some extra dependencies and is optional\n",
-    "    pass"
-   ]
+   "source": ["from IPython.display import Image, display\n\ntry:\n    display(Image(app.get_graph(xray=True).draw_mermaid_png()))\nexcept Exception:\n    # This requires some extra dependencies and is optional\n    pass"]
   },
   {
    "cell_type": "markdown",
@@ -455,18 +310,7 @@
      ]
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "for output in app.stream(inputs):\n",
-    "    # stream() yields dictionaries with output keyed by node name\n",
-    "    for key, value in output.items():\n",
-    "        print(f\"Output from node '{key}':\")\n",
-    "        print(\"---\")\n",
-    "        print(value)\n",
-    "    print(\"\\n---\\n\")"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\ninputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\nfor output in app.stream(inputs):\n    # stream() yields dictionaries with output keyed by node name\n    for key, value in output.items():\n        print(f\"Output from node '{key}':\")\n        print(\"---\")\n        print(value)\n    print(\"\\n---\\n\")"]
   },
   {
    "cell_type": "code",
@@ -474,7 +318,7 @@
    "id": "08ae8246-11d5-40e1-8567-361e5bef8917",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/chat_agent_executor_with_function_calling/prebuilt-tool-node.ipynb

@@ -27,10 +27,7 @@
    "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain langchain_openai tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain langchain_openai tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -46,13 +43,7 @@
    "id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nos.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\nos.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -68,10 +59,7 @@
    "id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -95,11 +83,7 @@
    "id": "d7ef57dd-5d6e-4ad3-9377-a92201c1310e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "\n",
-    "tools = [TavilySearchResults(max_results=1)]"
-   ]
+   "source": ["from langchain_community.tools.tavily_search import TavilySearchResults\n\ntools = [TavilySearchResults(max_results=1)]"]
   },
   {
    "cell_type": "markdown",
@@ -123,11 +107,7 @@
    "id": "892b54b9-75f0-4804-9ed0-88b5e5532989",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "model = ChatOpenAI(temperature=0)"
-   ]
+   "source": ["from langchain_openai import ChatOpenAI\n\nmodel = ChatOpenAI(temperature=0)"]
   },
   {
    "cell_type": "markdown",
@@ -145,9 +125,7 @@
    "id": "cd3cbae5-d92c-4559-a4aa-44721b80d107",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "model = model.bind_tools(tools)"
-   ]
+   "source": ["model = model.bind_tools(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -173,16 +151,7 @@
    "id": "ea793afa-2eab-4901-910d-6eed90cd6564",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, Sequence, TypedDict\n",
-    "\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    messages: Annotated[Sequence[BaseMessage], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, Sequence, TypedDict\n\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    messages: Annotated[Sequence[BaseMessage], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -217,33 +186,7 @@
    "id": "3b541bb9-900c-40d0-964d-7b5dfee30667",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolNode\n",
-    "\n",
-    "\n",
-    "# Define the function that determines whether to continue or not\n",
-    "def should_continue(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    last_message = messages[-1]\n",
-    "    # If there are no tool calls, then we finish\n",
-    "    if not last_message.tool_calls:\n",
-    "        return \"end\"\n",
-    "    # Otherwise if there is, we continue\n",
-    "    else:\n",
-    "        return \"continue\"\n",
-    "\n",
-    "\n",
-    "# Define the function that calls the model\n",
-    "def call_model(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    response = model.invoke(messages)\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [response]}\n",
-    "\n",
-    "\n",
-    "# Define the function to execute tools\n",
-    "tool_node = ToolNode(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolNode\n\n\n# Define the function that determines whether to continue or not\ndef should_continue(state):\n    messages = state[\"messages\"]\n    last_message = messages[-1]\n    # If there are no tool calls, then we finish\n    if not last_message.tool_calls:\n        return \"end\"\n    # Otherwise if there is, we continue\n    else:\n        return \"continue\"\n\n\n# Define the function that calls the model\ndef call_model(state):\n    messages = state[\"messages\"]\n    response = model.invoke(messages)\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [response]}\n\n\n# Define the function to execute tools\ntool_node = ToolNode(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -261,50 +204,7 @@
    "id": "813ae66c-3b58-4283-a02a-36da72a2ab90",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "workflow.add_node(\"action\", tool_node)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", call_model)\nworkflow.add_node(\"action\", tool_node)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "markdown",
@@ -337,12 +237,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "app.invoke(inputs)"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\ninputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\napp.invoke(inputs)"]
   },
   {
    "cell_type": "markdown",
@@ -392,16 +287,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "for output in app.stream(inputs):\n",
-    "    # stream() yields dictionaries with output keyed by node name\n",
-    "    for key, value in output.items():\n",
-    "        print(f\"Output from node '{key}':\")\n",
-    "        print(\"---\")\n",
-    "        print(value)\n",
-    "    print(\"\\n---\\n\")"
-   ]
+   "source": ["inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\nfor output in app.stream(inputs):\n    # stream() yields dictionaries with output keyed by node name\n    for key, value in output.items():\n        print(f\"Output from node '{key}':\")\n        print(\"---\")\n        print(value)\n    print(\"\\n---\\n\")"]
   },
   {
    "cell_type": "markdown",
@@ -496,21 +382,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf?\")]}\n",
-    "\n",
-    "async for output in app.astream_log(inputs, include_types=[\"llm\"]):\n",
-    "    # astream_log() yields the requested logs (here LLMs) in JSONPatch format\n",
-    "    for op in output.ops:\n",
-    "        if op[\"path\"] == \"/streamed_output/-\":\n",
-    "            # this is the output from .stream()\n",
-    "            ...\n",
-    "        elif op[\"path\"].startswith(\"/logs/\") and op[\"path\"].endswith(\n",
-    "            \"/streamed_output/-\"\n",
-    "        ):\n",
-    "            # because we chose to only include LLMs, these are LLM tokens\n",
-    "            print(op[\"value\"])"
-   ]
+   "source": ["inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf?\")]}\n\nasync for output in app.astream_log(inputs, include_types=[\"llm\"]):\n    # astream_log() yields the requested logs (here LLMs) in JSONPatch format\n    for op in output.ops:\n        if op[\"path\"] == \"/streamed_output/-\":\n            # this is the output from .stream()\n            ...\n        elif op[\"path\"].startswith(\"/logs/\") and op[\"path\"].endswith(\n            \"/streamed_output/-\"\n        ):\n            # because we chose to only include LLMs, these are LLM tokens\n            print(op[\"value\"])"]
   },
   {
    "cell_type": "code",
@@ -518,7 +390,7 @@
    "id": "08ae8246-11d5-40e1-8567-361e5bef8917",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/chat_agent_executor_with_function_calling/respond-in-format.ipynb

@@ -38,22 +38,7 @@
    "id": "de1db3c1",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from typing import Annotated\n",
-    "\n",
-    "from typing_extensions import TypedDict\n",
-    "\n",
-    "from langgraph.graph.message import add_messages\n",
-    "\n",
-    "# Add messages essentially does this with more\n",
-    "# robust handling\n",
-    "# def add_messages(left: list, right: list):\n",
-    "#     return left + right\n",
-    "\n",
-    "\n",
-    "class State(TypedDict):\n",
-    "    messages: Annotated[list, add_messages]"
-   ]
+   "source": ["from typing import Annotated\n\nfrom typing_extensions import TypedDict\n\nfrom langgraph.graph.message import add_messages\n\n# Add messages essentially does this with more\n# robust handling\n# def add_messages(left: list, right: list):\n#     return left + right\n\n\nclass State(TypedDict):\n    messages: Annotated[list, add_messages]"]
   },
   {
    "cell_type": "markdown",
@@ -73,19 +58,7 @@
    "id": "23a2ca43",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.tools import tool\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "def search(query: str):\n",
-    "    \"\"\"Call to surf the web.\"\"\"\n",
-    "    # This is a placeholder, but don't tell the LLM that...\n",
-    "    return [\"The answer to your question lies within.\"]\n",
-    "\n",
-    "\n",
-    "tools = [search]"
-   ]
+   "source": ["from langchain_core.tools import tool\n\n\n@tool\ndef search(query: str):\n    \"\"\"Call to surf the web.\"\"\"\n    # This is a placeholder, but don't tell the LLM that...\n    return [\"The answer to your question lies within.\"]\n\n\ntools = [search]"]
   },
   {
    "cell_type": "markdown",
@@ -102,11 +75,7 @@
    "id": "979512e4",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolNode\n",
-    "\n",
-    "tool_node = ToolNode(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolNode\n\ntool_node = ToolNode(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -130,11 +99,7 @@
    "id": "1c8132c5",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_anthropic import ChatAnthropic\n",
-    "\n",
-    "model = ChatAnthropic(model=\"claude-3-haiku-20240307\")"
-   ]
+   "source": ["from langchain_anthropic import ChatAnthropic\n\nmodel = ChatAnthropic(model=\"claude-3-haiku-20240307\")"]
   },
   {
    "cell_type": "markdown",
@@ -152,9 +117,7 @@
    "id": "055d84bf",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "model = model.bind_tools(tools)"
-   ]
+   "source": ["model = model.bind_tools(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -172,10 +135,7 @@
    "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain langchain_openai tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain langchain_openai tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -191,13 +151,7 @@
    "id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nos.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\nos.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -213,10 +167,7 @@
    "id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -236,11 +187,7 @@
    "id": "d7ef57dd-5d6e-4ad3-9377-a92201c1310e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "\n",
-    "tools = [TavilySearchResults(max_results=1)]"
-   ]
+   "source": ["from langchain_community.tools.tavily_search import TavilySearchResults\n\ntools = [TavilySearchResults(max_results=1)]"]
   },
   {
    "cell_type": "markdown",
@@ -258,11 +205,7 @@
    "id": "5cf3331e-ccb3-41c8-aeb9-a840a94d41e7",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolExecutor\n",
-    "\n",
-    "tool_executor = ToolExecutor(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolExecutor\n\ntool_executor = ToolExecutor(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -286,13 +229,7 @@
    "id": "892b54b9-75f0-4804-9ed0-88b5e5532989",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "# We will set streaming=True so that we can stream tokens\n",
-    "# See the streaming section for more information on this.\n",
-    "model = ChatOpenAI(temperature=0, streaming=True)"
-   ]
+   "source": ["from langchain_openai import ChatOpenAI\n\n# We will set streaming=True so that we can stream tokens\n# See the streaming section for more information on this.\nmodel = ChatOpenAI(temperature=0, streaming=True)"]
   },
   {
    "cell_type": "markdown",
@@ -315,19 +252,7 @@
    "id": "cd3cbae5-d92c-4559-a4aa-44721b80d107",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
-    "\n",
-    "\n",
-    "class Response(BaseModel):\n",
-    "    \"\"\"Final response to the user\"\"\"\n",
-    "\n",
-    "    temperature: float = Field(description=\"the temperature\")\n",
-    "    other_notes: str = Field(description=\"any other notes about the weather\")\n",
-    "\n",
-    "\n",
-    "model = model.bind_tools(tools + [Response])"
-   ]
+   "source": ["from langchain_core.pydantic_v1 import BaseModel, Field\n\n\nclass Response(BaseModel):\n    \"\"\"Final response to the user\"\"\"\n\n    temperature: float = Field(description=\"the temperature\")\n    other_notes: str = Field(description=\"any other notes about the weather\")\n\n\nmodel = model.bind_tools(tools + [Response])"]
   },
   {
    "cell_type": "markdown",
@@ -353,16 +278,7 @@
    "id": "ea793afa-2eab-4901-910d-6eed90cd6564",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, Sequence, TypedDict\n",
-    "\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    messages: Annotated[Sequence[BaseMessage], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, Sequence, TypedDict\n\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    messages: Annotated[Sequence[BaseMessage], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -401,70 +317,7 @@
    "id": "3b541bb9-900c-40d0-964d-7b5dfee30667",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from typing import Literal\n",
-    "\n",
-    "from langchain_core.messages import ToolMessage\n",
-    "\n",
-    "from langgraph.prebuilt import ToolInvocation\n",
-    "\n",
-    "\n",
-    "# Define the function that determines whether to continue or not\n",
-    "def should_continue(state) -> Literal[\"continue\", \"end\"]:\n",
-    "    messages = state[\"messages\"]\n",
-    "    last_message = messages[-1]\n",
-    "    # If there is no function call, then we finish\n",
-    "    if not last_message.tool_calls:\n",
-    "        return \"end\"\n",
-    "    # Otherwise if there is, we need to check what type of function call it is\n",
-    "    if last_message.tool_calls[0][\"name\"] == \"Response\":\n",
-    "        return \"end\"\n",
-    "    # Otherwise we continue\n",
-    "    return \"continue\"\n",
-    "\n",
-    "\n",
-    "# Define the function that calls the model\n",
-    "def call_model(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    response = model.invoke(messages)\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [response]}\n",
-    "\n",
-    "\n",
-    "# Define the function to execute tools\n",
-    "def call_tool(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    # Based on the continue condition\n",
-    "    # we know the last message involves a function call\n",
-    "    last_message = messages[-1]\n",
-    "    # We construct an ToolInvocation for each tool call\n",
-    "    tool_invocations = []\n",
-    "    for tool_call in last_message.tool_calls:\n",
-    "        action = ToolInvocation(\n",
-    "            tool=tool_call[\"name\"],\n",
-    "            tool_input=tool_call[\"args\"],\n",
-    "        )\n",
-    "        tool_invocations.append(action)\n",
-    "\n",
-    "    action = ToolInvocation(\n",
-    "        tool=tool_call[\"name\"],\n",
-    "        tool_input=tool_call[\"args\"],\n",
-    "    )\n",
-    "    # We call the tool_executor and get back a response\n",
-    "    responses = tool_executor.batch(tool_invocations, return_exceptions=True)\n",
-    "    # We use the response to create tool messages\n",
-    "    tool_messages = [\n",
-    "        ToolMessage(\n",
-    "            content=str(response),\n",
-    "            name=tc[\"name\"],\n",
-    "            tool_call_id=tc[\"id\"],\n",
-    "        )\n",
-    "        for tc, response in zip(last_message.tool_calls, responses)\n",
-    "    ]\n",
-    "\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": tool_messages}"
-   ]
+   "source": ["from typing import Literal\n\nfrom langchain_core.messages import ToolMessage\n\nfrom langgraph.prebuilt import ToolInvocation\n\n\n# Define the function that determines whether to continue or not\ndef should_continue(state) -> Literal[\"continue\", \"end\"]:\n    messages = state[\"messages\"]\n    last_message = messages[-1]\n    # If there is no function call, then we finish\n    if not last_message.tool_calls:\n        return \"end\"\n    # Otherwise if there is, we need to check what type of function call it is\n    if last_message.tool_calls[0][\"name\"] == \"Response\":\n        return \"end\"\n    # Otherwise we continue\n    return \"continue\"\n\n\n# Define the function that calls the model\ndef call_model(state):\n    messages = state[\"messages\"]\n    response = model.invoke(messages)\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [response]}\n\n\n# Define the function to execute tools\ndef call_tool(state):\n    messages = state[\"messages\"]\n    # Based on the continue condition\n    # we know the last message involves a function call\n    last_message = messages[-1]\n    # We construct an ToolInvocation for each tool call\n    tool_invocations = []\n    for tool_call in last_message.tool_calls:\n        action = ToolInvocation(\n            tool=tool_call[\"name\"],\n            tool_input=tool_call[\"args\"],\n        )\n        tool_invocations.append(action)\n\n    action = ToolInvocation(\n        tool=tool_call[\"name\"],\n        tool_input=tool_call[\"args\"],\n    )\n    # We call the tool_executor and get back a response\n    responses = tool_executor.batch(tool_invocations, return_exceptions=True)\n    # We use the response to create tool messages\n    tool_messages = [\n        ToolMessage(\n            content=str(response),\n            name=tc[\"name\"],\n            tool_call_id=tc[\"id\"],\n        )\n        for tc, response in zip(last_message.tool_calls, responses)\n    ]\n\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": tool_messages}"]
   },
   {
    "cell_type": "markdown",
@@ -482,50 +335,7 @@
    "id": "813ae66c-3b58-4283-a02a-36da72a2ab90",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "workflow.add_node(\"action\", call_tool)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", call_model)\nworkflow.add_node(\"action\", call_tool)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -544,15 +354,7 @@
      "output_type": "display_data"
     }
    ],
-   "source": [
-    "from IPython.display import Image, display\n",
-    "\n",
-    "try:\n",
-    "    display(Image(app.get_graph(xray=True).draw_mermaid_png()))\n",
-    "except Exception:\n",
-    "    # This requires some extra dependencies and is optional\n",
-    "    pass"
-   ]
+   "source": ["from IPython.display import Image, display\n\ntry:\n    display(Image(app.get_graph(xray=True).draw_mermaid_png()))\nexcept Exception:\n    # This requires some extra dependencies and is optional\n    pass"]
   },
   {
    "cell_type": "markdown",
@@ -596,18 +398,7 @@
      ]
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "for output in app.stream(inputs):\n",
-    "    # stream() yields dictionaries with output keyed by node name\n",
-    "    for key, value in output.items():\n",
-    "        print(f\"Output from node '{key}':\")\n",
-    "        print(\"---\")\n",
-    "        print(value[\"messages\"][-1])\n",
-    "    print(\"\\n---\\n\")"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\ninputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\nfor output in app.stream(inputs):\n    # stream() yields dictionaries with output keyed by node name\n    for key, value in output.items():\n        print(f\"Output from node '{key}':\")\n        print(\"---\")\n        print(value[\"messages\"][-1])\n    print(\"\\n---\\n\")"]
   },
   {
    "cell_type": "code",
@@ -615,7 +406,7 @@
    "id": "eed4360d-2cdf-497b-b03f-8bc51062f780",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/chatbot-simulation-evaluation/agent-simulation-evaluation.ipynb

@@ -26,10 +26,7 @@
    "id": "0d30b6f7-3bec-4d9f-af50-43dfdc81ae6c",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# %%capture --no-stderr\n",
-    "# %pip install -U langgraph langchain langchain_openai"
-   ]
+   "source": ["# %%capture --no-stderr\n# %pip install -U langgraph langchain langchain_openai"]
   },
   {
    "cell_type": "code",
@@ -37,24 +34,7 @@
    "id": "30c2f3de-c730-4aec-85a6-af2c2f058803",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "\n",
-    "def _set_if_undefined(var: str):\n",
-    "    if not os.environ.get(var):\n",
-    "        os.environ[var] = getpass.getpass(f\"Please provide your {var}\")\n",
-    "\n",
-    "\n",
-    "_set_if_undefined(\"OPENAI_API_KEY\")\n",
-    "_set_if_undefined(\"LANGCHAIN_API_KEY\")\n",
-    "\n",
-    "# Optional, add tracing in LangSmith.\n",
-    "# This will help you visualize and debug the control flow\n",
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_PROJECT\"] = \"Agent Simulation Evaluation\""
-   ]
+   "source": ["import getpass\nimport os\n\n\ndef _set_if_undefined(var: str):\n    if not os.environ.get(var):\n        os.environ[var] = getpass.getpass(f\"Please provide your {var}\")\n\n\n_set_if_undefined(\"OPENAI_API_KEY\")\n_set_if_undefined(\"LANGCHAIN_API_KEY\")\n\n# Optional, add tracing in LangSmith.\n# This will help you visualize and debug the control flow\nos.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_PROJECT\"] = \"Agent Simulation Evaluation\""]
   },
   {
    "cell_type": "markdown",
@@ -75,24 +55,7 @@
    "id": "828479af-cf9c-4888-a365-599643a96b55",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from typing import List\n",
-    "\n",
-    "import openai\n",
-    "\n",
-    "\n",
-    "# This is flexible, but you can define your agent here, or call your agent API here.\n",
-    "def my_chat_bot(messages: List[dict]) -> dict:\n",
-    "    system_message = {\n",
-    "        \"role\": \"system\",\n",
-    "        \"content\": \"You are a customer support agent for an airline.\",\n",
-    "    }\n",
-    "    messages = [system_message] + messages\n",
-    "    completion = openai.chat.completions.create(\n",
-    "        messages=messages, model=\"gpt-3.5-turbo\"\n",
-    "    )\n",
-    "    return completion.choices[0].message.model_dump()"
-   ]
+   "source": ["from typing import List\n\nimport openai\n\n\n# This is flexible, but you can define your agent here, or call your agent API here.\ndef my_chat_bot(messages: List[dict]) -> dict:\n    system_message = {\n        \"role\": \"system\",\n        \"content\": \"You are a customer support agent for an airline.\",\n    }\n    messages = [system_message] + messages\n    completion = openai.chat.completions.create(\n        messages=messages, model=\"gpt-3.5-turbo\"\n    )\n    return completion.choices[0].message.model_dump()"]
   },
   {
    "cell_type": "code",
@@ -114,9 +77,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "my_chat_bot([{\"role\": \"user\", \"content\": \"hi!\"}])"
-   ]
+   "source": ["my_chat_bot([{\"role\": \"user\", \"content\": \"hi!\"}])"]
   },
   {
    "cell_type": "markdown",
@@ -135,33 +96,7 @@
    "id": "32c147df-7f90-4b0d-9a6b-671677020353",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "system_prompt_template = \"\"\"You are a customer of an airline company. \\\n",
-    "You are interacting with a user who is a customer support person. \\\n",
-    "\n",
-    "{instructions}\n",
-    "\n",
-    "When you are finished with the conversation, respond with a single word 'FINISHED'\"\"\"\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", system_prompt_template),\n",
-    "        MessagesPlaceholder(variable_name=\"messages\"),\n",
-    "    ]\n",
-    ")\n",
-    "instructions = \"\"\"Your name is Harrison. You are trying to get a refund for the trip you took to Alaska. \\\n",
-    "You want them to give you ALL the money back. \\\n",
-    "This trip happened 5 years ago.\"\"\"\n",
-    "\n",
-    "prompt = prompt.partial(name=\"Harrison\", instructions=instructions)\n",
-    "\n",
-    "model = ChatOpenAI()\n",
-    "\n",
-    "simulated_user = prompt | model"
-   ]
+   "source": ["from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\nfrom langchain_openai import ChatOpenAI\n\nsystem_prompt_template = \"\"\"You are a customer of an airline company. \\\nYou are interacting with a user who is a customer support person. \\\n\n{instructions}\n\nWhen you are finished with the conversation, respond with a single word 'FINISHED'\"\"\"\n\nprompt = ChatPromptTemplate.from_messages(\n    [\n        (\"system\", system_prompt_template),\n        MessagesPlaceholder(variable_name=\"messages\"),\n    ]\n)\ninstructions = \"\"\"Your name is Harrison. You are trying to get a refund for the trip you took to Alaska. \\\nYou want them to give you ALL the money back. \\\nThis trip happened 5 years ago.\"\"\"\n\nprompt = prompt.partial(name=\"Harrison\", instructions=instructions)\n\nmodel = ChatOpenAI()\n\nsimulated_user = prompt | model"]
   },
   {
    "cell_type": "code",
@@ -180,12 +115,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "messages = [HumanMessage(content=\"Hi! How can I help you?\")]\n",
-    "simulated_user.invoke({\"messages\": messages})"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\nmessages = [HumanMessage(content=\"Hi! How can I help you?\")]\nsimulated_user.invoke({\"messages\": messages})"]
   },
   {
    "cell_type": "markdown",
@@ -223,19 +153,7 @@
    "id": "69e2a3a3-40f3-4223-9136-113738440be9",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_community.adapters.openai import convert_message_to_dict\n",
-    "from langchain_core.messages import AIMessage\n",
-    "\n",
-    "\n",
-    "def chat_bot_node(messages):\n",
-    "    # Convert from LangChain format to the OpenAI format, which our chatbot function expects.\n",
-    "    messages = [convert_message_to_dict(m) for m in messages]\n",
-    "    # Call the chat bot\n",
-    "    chat_bot_response = my_chat_bot(messages)\n",
-    "    # Respond with an AI Message\n",
-    "    return AIMessage(content=chat_bot_response[\"content\"])"
-   ]
+   "source": ["from langchain_community.adapters.openai import convert_message_to_dict\nfrom langchain_core.messages import AIMessage\n\n\ndef chat_bot_node(messages):\n    # Convert from LangChain format to the OpenAI format, which our chatbot function expects.\n    messages = [convert_message_to_dict(m) for m in messages]\n    # Call the chat bot\n    chat_bot_response = my_chat_bot(messages)\n    # Respond with an AI Message\n    return AIMessage(content=chat_bot_response[\"content\"])"]
   },
   {
    "cell_type": "markdown",
@@ -251,25 +169,7 @@
    "id": "7cad7527-ffa5-4c30-8585-b54a7a18bd98",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "def _swap_roles(messages):\n",
-    "    new_messages = []\n",
-    "    for m in messages:\n",
-    "        if isinstance(m, AIMessage):\n",
-    "            new_messages.append(HumanMessage(content=m.content))\n",
-    "        else:\n",
-    "            new_messages.append(AIMessage(content=m.content))\n",
-    "    return new_messages\n",
-    "\n",
-    "\n",
-    "def simulated_user_node(messages):\n",
-    "    # Swap roles of messages\n",
-    "    new_messages = _swap_roles(messages)\n",
-    "    # Call the simulated user\n",
-    "    response = simulated_user.invoke({\"messages\": new_messages})\n",
-    "    # This response is an AI message - we need to flip this to be a human message\n",
-    "    return HumanMessage(content=response.content)"
-   ]
+   "source": ["def _swap_roles(messages):\n    new_messages = []\n    for m in messages:\n        if isinstance(m, AIMessage):\n            new_messages.append(HumanMessage(content=m.content))\n        else:\n            new_messages.append(AIMessage(content=m.content))\n    return new_messages\n\n\ndef simulated_user_node(messages):\n    # Swap roles of messages\n    new_messages = _swap_roles(messages)\n    # Call the simulated user\n    response = simulated_user.invoke({\"messages\": new_messages})\n    # This response is an AI message - we need to flip this to be a human message\n    return HumanMessage(content=response.content)"]
   },
   {
    "cell_type": "markdown",
@@ -292,15 +192,7 @@
    "id": "28004fbf-a2f3-46b7-bde7-46c7adaf97fb",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "def should_continue(messages):\n",
-    "    if len(messages) > 6:\n",
-    "        return \"end\"\n",
-    "    elif messages[-1].content == \"FINISHED\":\n",
-    "        return \"end\"\n",
-    "    else:\n",
-    "        return \"continue\""
-   ]
+   "source": ["def should_continue(messages):\n    if len(messages) > 6:\n        return \"end\"\n    elif messages[-1].content == \"FINISHED\":\n        return \"end\"\n    else:\n        return \"continue\""]
   },
   {
    "cell_type": "markdown",
@@ -318,29 +210,7 @@
    "id": "0b597e4b-4cbb-4bbc-82e5-f7e31275964c",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, MessageGraph\n",
-    "\n",
-    "graph_builder = MessageGraph()\n",
-    "graph_builder.add_node(\"user\", simulated_user_node)\n",
-    "graph_builder.add_node(\"chat_bot\", chat_bot_node)\n",
-    "# Every response from  your chat bot will automatically go to the\n",
-    "# simulated user\n",
-    "graph_builder.add_edge(\"chat_bot\", \"user\")\n",
-    "graph_builder.add_conditional_edges(\n",
-    "    \"user\",\n",
-    "    should_continue,\n",
-    "    # If the finish criteria are met, we will stop the simulation,\n",
-    "    # otherwise, the virtual user's message will be sent to your chat bot\n",
-    "    {\n",
-    "        \"end\": END,\n",
-    "        \"continue\": \"chat_bot\",\n",
-    "    },\n",
-    ")\n",
-    "# The input will first go to your chat bot\n",
-    "graph_builder.set_entry_point(\"chat_bot\")\n",
-    "simulation = graph_builder.compile()"
-   ]
+   "source": ["from langgraph.graph import END, MessageGraph, START\n\ngraph_builder = MessageGraph()\ngraph_builder.add_node(\"user\", simulated_user_node)\ngraph_builder.add_node(\"chat_bot\", chat_bot_node)\n# Every response from  your chat bot will automatically go to the\n# simulated user\ngraph_builder.add_edge(\"chat_bot\", \"user\")\ngraph_builder.add_conditional_edges(\n    \"user\",\n    should_continue,\n    # If the finish criteria are met, we will stop the simulation,\n    # otherwise, the virtual user's message will be sent to your chat bot\n    {\n        \"end\": END,\n        \"continue\": \"chat_bot\",\n    },\n)\n# The input will first go to your chat bot\ngraph_builder.add_edge(START, \"chat_bot\")\nsimulation = graph_builder.compile()"]
   },
   {
    "cell_type": "markdown",
@@ -381,13 +251,7 @@
      ]
     }
    ],
-   "source": [
-    "for chunk in simulation.stream([]):\n",
-    "    # Print out all events aside from the final end chunk\n",
-    "    if END not in chunk:\n",
-    "        print(chunk)\n",
-    "        print(\"----\")"
-   ]
+   "source": ["for chunk in simulation.stream([]):\n    # Print out all events aside from the final end chunk\n    if END not in chunk:\n        print(chunk)\n        print(\"----\")"]
   },
   {
    "cell_type": "code",
@@ -395,7 +259,7 @@
    "id": "dde4f2b5-cfe8-4ff0-99ea-fe2c5fed70c0",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/chatbot-simulation-evaluation/simulation_utils.py

@@ -9,7 +9,7 @@ from langchain_core.runnables import chain as as_runnable
 from langchain_openai import ChatOpenAI
 from typing_extensions import TypedDict
 
-from langgraph.graph import END, StateGraph
+from langgraph.graph import END, StateGraph, START
 
 
 def langchain_to_openai_messages(messages: List[BaseMessage]):
@@ -116,7 +116,7 @@ def create_chat_simulator(
         should_continue or functools.partial(_should_continue, max_turns=max_turns),
     )
     # If your dataset has a 'leading question/input', then we route first to the assistant, otherwise, we let the user take the lead.
-    graph_builder.set_entry_point("assistant" if input_key is not None else "user")
+    graph_builder.add_edge(START, "assistant" if input_key is not None else "user")
 
     return (
         RunnableLambda(_prepare_example).bind(input_key=input_key)

examples/chatbots/customer-support.ipynb

@@ -2,10 +2,739 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "4c37bb65-6e2c-42e4-bfa7-9df10e2652a0",
+   "id": "d9d1a28b-c2a1-4246-b1c2-c58d6938f798",
    "metadata": {},
    "source": [
-    "This example has moved! Check out the [Customer Support Tutorial](../customer-support/customer-support.ipynb) for more information."
+    "# Customer Support\n",
+    "\n",
+    "Here, we show an example of building a customer support chatbot.\n",
+    "\n",
+    "This customer support chatbot interacts with SQL database to answer questions.\n",
+    "We will use a mock SQL database to get started: the [Chinook](https://www.sqlitetutorial.net/sqlite-sample-database/) database.\n",
+    "This database is about sales from a music store: what songs and album exists, customer orders, things like that.\n",
+    "\n",
+    "This chatbot has two different states: \n",
+    "1. Music: the user can inquire about different songs and albums present in the store\n",
+    "2. Account: the user can ask questions about their account\n",
+    "\n",
+    "Under the hood, this is handled by two separate agents. \n",
+    "Each has a specific prompt and tools related to their objective. \n",
+    "There is also a generic agent who is responsible for routing between these two agents as needed.\n",
+    "\n",
+    "Note: This is a very simple example! For a more complete tutorial on building a customer support bot, check out the [Customer Support Tutorial](../customer-support/customer-support.ipynb) for more information."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "35abc013-2613-4a49-a806-939dcf13ccf3",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "%%capture --no-stderr\n",
+    "%pip install -U langgraph langchain-community langchain-openai scikit-learn"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9431e7f1-07fa-49d9-ac45-29613703dcc1",
+   "metadata": {},
+   "source": [
+    "## Load the data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "3d1ef253-6b0c-4481-868c-e1fe84f2c8ff",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import requests\n",
+    "\n",
+    "url = \"https://storage.googleapis.com/benchmarks-artifacts/chinook/Chinook.db\"\n",
+    "response = requests.get(url)\n",
+    "\n",
+    "with open(\"Chinook.db\", \"wb\") as file:\n",
+    "    file.write(response.content)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "61f7ef9c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['Album',\n",
+       " 'Artist',\n",
+       " 'Customer',\n",
+       " 'Employee',\n",
+       " 'Genre',\n",
+       " 'Invoice',\n",
+       " 'InvoiceLine',\n",
+       " 'MediaType',\n",
+       " 'Playlist',\n",
+       " 'PlaylistTrack',\n",
+       " 'Track']"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_community.utilities import SQLDatabase\n",
+    "\n",
+    "db = SQLDatabase.from_uri(\"sqlite:///Chinook.db\")\n",
+    "db.get_usable_table_names()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1cf668e4-8cb4-4de1-bc5e-c90284bf74bc",
+   "metadata": {},
+   "source": [
+    "## Load an LLM\n",
+    "\n",
+    "We will load a language model to use.\n",
+    "For this demo we will use OpenAI."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "d9ea4e80-30e6-4d46-b480-35f0be2fb055",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "model = ChatOpenAI(temperature=0, streaming=True, model=\"gpt-4o\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "73907422-7e05-431e-b06d-256c9ec1f6f6",
+   "metadata": {},
+   "source": [
+    "## Load Other Modules\n",
+    "\n",
+    "Load other modules we will use.\n",
+    "\n",
+    "All of the tools our agents will use will be custom tools. As such, we will use the `@tool` decorator to create custom tools.\n",
+    "\n",
+    "We will pass in messages to the agent, so we load `HumanMessage` and `SystemMessage`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "ea958e9f-ab1f-49b5-bd85-16332055297c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.messages import HumanMessage, SystemMessage"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "35271d4d-2a1c-41be-9359-a3a7c3fed3d9",
+   "metadata": {},
+   "source": [
+    "## Define the Customer Agent\n",
+    "\n",
+    "This agent is responsible for looking up customer information.\n",
+    "It will have a specific prompt as well a specific tool to look up information about that customer (after asking for their user id)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "975b039a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# This tool is given to the agent to look up information about a customer\n",
+    "def get_customer_info(customer_id: int):\n",
+    "    \"\"\"Look up customer info given their ID. ALWAYS make sure you have the customer ID before invoking this.\"\"\"\n",
+    "    return db.run(f\"SELECT * FROM Customer WHERE CustomerID = {customer_id};\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "1d5fa446",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "customer_prompt = \"\"\"Your job is to help a user update their profile.\n",
+    "\n",
+    "You only have certain tools you can use. These tools require specific input. If you don't know the required input, then ask the user for it.\n",
+    "\n",
+    "If you are unable to help the user, you can \"\"\"\n",
+    "\n",
+    "\n",
+    "def get_customer_messages(messages):\n",
+    "    return [SystemMessage(content=customer_prompt)] + messages\n",
+    "\n",
+    "\n",
+    "customer_chain = get_customer_messages | model.bind_tools([get_customer_info])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "904a9485-3857-458e-8b9d-33bc33842bc9",
+   "metadata": {},
+   "source": [
+    "## Define the Music Agent\n",
+    "\n",
+    "This agent is responsible for figuring out information about music. To do that, we will create a prompt and various tools for looking up information about music\n",
+    "\n",
+    "First, we will create indexes for looking up artists and track names.\n",
+    "This will allow us to look up artists and tracks without having to spell their names exactly right."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "a8604a3b-b484-4b2b-a914-4236cb98c524",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.vectorstores import SKLearnVectorStore\n",
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "\n",
+    "artists = db._execute(\"select * from Artist\")\n",
+    "songs = db._execute(\"select * from Track\")\n",
+    "artist_retriever = SKLearnVectorStore.from_texts(\n",
+    "    [a[\"Name\"] for a in artists], OpenAIEmbeddings(), metadatas=artists\n",
+    ").as_retriever()\n",
+    "song_retriever = SKLearnVectorStore.from_texts(\n",
+    "    [a[\"Name\"] for a in songs], OpenAIEmbeddings(), metadatas=songs\n",
+    ").as_retriever()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ac7eb264-c572-4925-ad55-a1d52a18b1c0",
+   "metadata": {},
+   "source": [
+    "First, let's create a tool for getting albums by artist."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "0a2a2b74",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_albums_by_artist(artist):\n",
+    "    \"\"\"Get albums by an artist (or similar artists).\"\"\"\n",
+    "    docs = artist_retriever.get_relevant_documents(artist)\n",
+    "    artist_ids = \", \".join([str(d.metadata[\"ArtistId\"]) for d in docs])\n",
+    "    return db.run(\n",
+    "        f\"SELECT Title, Name FROM Album LEFT JOIN Artist ON Album.ArtistId = Artist.ArtistId WHERE Album.ArtistId in ({artist_ids});\",\n",
+    "        include_columns=True,\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "45e85066-f2fc-490e-992d-cd66c9cd6486",
+   "metadata": {},
+   "source": [
+    "Next, lets create a tool for getting tracks by an artist"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "da533f50",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_tracks_by_artist(artist):\n",
+    "    \"\"\"Get songs by an artist (or similar artists).\"\"\"\n",
+    "    docs = artist_retriever.invoke(artist)\n",
+    "    artist_ids = \", \".join([str(d.metadata[\"ArtistId\"]) for d in docs])\n",
+    "    return db.run(\n",
+    "        f\"SELECT Track.Name as SongName, Artist.Name as ArtistName FROM Album LEFT JOIN Artist ON Album.ArtistId = Artist.ArtistId LEFT JOIN Track ON Track.AlbumId = Album.AlbumId WHERE Album.ArtistId in ({artist_ids});\",\n",
+    "        include_columns=True,\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bb0e50ab-b059-427c-924b-f8072d8db23c",
+   "metadata": {},
+   "source": [
+    "Finally, let's create a tool for looking up songs by their name."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "b3c07010",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def check_for_songs(song_title):\n",
+    "    \"\"\"Check if a song exists by its name.\"\"\"\n",
+    "    return song_retriever.invoke(song_title)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "88388ff8-38b5-4e4e-a24d-de8c3670bd2b",
+   "metadata": {},
+   "source": [
+    "Create the chain to call the relevant tools"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "72a14d5c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "song_system_message = \"\"\"Your job is to help a customer find any songs they are looking for. \n",
+    "\n",
+    "You only have certain tools you can use. If a customer asks you to look something up that you don't know how, politely tell them what you can help with.\n",
+    "\n",
+    "When looking up artists and songs, sometimes the artist/song will not be found. In that case, the tools will return information \\\n",
+    "on similar songs and artists. This is intentional, it is not the tool messing up.\"\"\"\n",
+    "\n",
+    "\n",
+    "def get_song_messages(messages):\n",
+    "    return [SystemMessage(content=song_system_message)] + messages\n",
+    "\n",
+    "\n",
+    "song_recc_chain = get_song_messages | model.bind_tools(\n",
+    "    [get_albums_by_artist, get_tracks_by_artist, check_for_songs]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "cff15eb0-62c7-451d-a5f9-4576b24c879e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_aXa9rSRXvTCJabrMY6AqkSV8', 'function': {'arguments': '{\"artist\":\"Amy Winehouse\"}', 'name': 'get_tracks_by_artist'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_ce0793330f'}, id='run-60633269-fd02-43e8-b434-28e3b8b69fb1-0', tool_calls=[{'name': 'get_tracks_by_artist', 'args': {'artist': 'Amy Winehouse'}, 'id': 'call_aXa9rSRXvTCJabrMY6AqkSV8'}])"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "msgs = [HumanMessage(content=\"hi! can you help me find songs by amy whinehouse?\")]\n",
+    "song_recc_chain.invoke(msgs)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0a42c293-0816-4f3c-b4a3-5b9f3a0665d1",
+   "metadata": {},
+   "source": [
+    "## Define the Generic Agent\n",
+    "\n",
+    "We now define a generic agent that is responsible for handling initial inquiries and routing to the right sub agent."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "73e74268",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.messages import AIMessage, HumanMessage, SystemMessage\n",
+    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
+    "\n",
+    "\n",
+    "class Router(BaseModel):\n",
+    "    \"\"\"Call this if you are able to route the user to the appropriate representative.\"\"\"\n",
+    "\n",
+    "    choice: str = Field(description=\"should be one of: music, customer\")\n",
+    "\n",
+    "\n",
+    "system_message = \"\"\"Your job is to help as a customer service representative for a music store.\n",
+    "\n",
+    "You should interact politely with customers to try to figure out how you can help. You can help in a few ways:\n",
+    "\n",
+    "- Updating user information: if a customer wants to update the information in the user database. Call the router with `customer`\n",
+    "- Recommending music: if a customer wants to find some music or information about music. Call the router with `music`\n",
+    "\n",
+    "If the user is asking or wants to ask about updating or accessing their information, send them to that route.\n",
+    "If the user is asking or wants to ask about music, send them to that route.\n",
+    "Otherwise, respond.\"\"\"\n",
+    "\n",
+    "\n",
+    "def get_messages(messages):\n",
+    "    return [SystemMessage(content=system_message)] + messages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "ddf27314",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = get_messages | model.bind_tools([Router])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "3c896f34",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_0aaFPPCWDiAoPyXQX2PS8TcJ', 'function': {'arguments': '{\"choice\":\"music\"}', 'name': 'Router'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_ce0793330f'}, id='run-73d51d75-b7c5-49fe-b558-105ede7c75d1-0', tool_calls=[{'name': 'Router', 'args': {'choice': 'music'}, 'id': 'call_0aaFPPCWDiAoPyXQX2PS8TcJ'}])"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "msgs = [HumanMessage(content=\"hi! can you help me find a good song?\")]\n",
+    "chain.invoke(msgs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "40d86f59",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_Okla9DfMHIPs5TslS6KPaoBA', 'function': {'arguments': '{\"choice\":\"customer\"}', 'name': 'Router'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4008e3b719'}, id='run-0d82d4f8-f4eb-4b16-add8-3e7fdffd6332-0', tool_calls=[{'name': 'Router', 'args': {'choice': 'customer'}, 'id': 'call_Okla9DfMHIPs5TslS6KPaoBA'}])"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "msgs = [HumanMessage(content=\"hi! what's the email you have for me?\")]\n",
+    "chain.invoke(msgs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "bd6ddd8b-7500-46a7-811d-3bcb937bda51",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.messages import AIMessage\n",
+    "\n",
+    "\n",
+    "def add_name(message, name):\n",
+    "    _dict = message.dict()\n",
+    "    _dict[\"name\"] = name\n",
+    "    return AIMessage(**_dict)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "27494de5-8345-4c23-bc0e-81e0dd5d47d8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "\n",
+    "from langgraph.graph import END\n",
+    "\n",
+    "\n",
+    "def _get_last_ai_message(messages):\n",
+    "    for m in messages[::-1]:\n",
+    "        if isinstance(m, AIMessage):\n",
+    "            return m\n",
+    "    return None\n",
+    "\n",
+    "\n",
+    "def _is_tool_call(msg):\n",
+    "    return hasattr(msg, \"additional_kwargs\") and \"tool_calls\" in msg.additional_kwargs\n",
+    "\n",
+    "\n",
+    "def _route(messages):\n",
+    "    last_message = messages[-1]\n",
+    "    if isinstance(last_message, AIMessage):\n",
+    "        if not last_message.tool_calls:\n",
+    "            return END\n",
+    "        else:\n",
+    "            if last_message.name == \"general\":\n",
+    "                if len(last_message.tool_calls) > 1:\n",
+    "                    raise ValueError(\"Too many tools\")\n",
+    "                return last_message.tool_calls[0][\"args\"][\"choice\"]\n",
+    "            else:\n",
+    "                return \"tools\"\n",
+    "    last_m = _get_last_ai_message(messages)\n",
+    "    if last_m is None:\n",
+    "        return \"general\"\n",
+    "    if last_m.name == \"music\":\n",
+    "        return \"music\"\n",
+    "    elif last_m.name == \"customer\":\n",
+    "        return \"customer\"\n",
+    "    else:\n",
+    "        return \"general\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "8aec704a-46fe-4fb3-bdee-11c3bbffc370",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langgraph.prebuilt import ToolNode\n",
+    "\n",
+    "tools = [get_albums_by_artist, get_tracks_by_artist, check_for_songs, get_customer_info]\n",
+    "tool_node = ToolNode(tools)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "4d5b75c6-73e0-4922-a765-a15be63f869e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def _filter_out_routes(messages):\n",
+    "    ms = []\n",
+    "    for m in messages:\n",
+    "        if _is_tool_call(m):\n",
+    "            if m.name == \"general\":\n",
+    "                continue\n",
+    "        ms.append(m)\n",
+    "    return ms"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "fd4dbf98-dbb3-411a-bad6-2bb334072aaf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from functools import partial\n",
+    "\n",
+    "general_node = _filter_out_routes | chain | partial(add_name, name=\"general\")\n",
+    "music_node = _filter_out_routes | song_recc_chain | partial(add_name, name=\"music\")\n",
+    "customer_node = _filter_out_routes | customer_chain | partial(add_name, name=\"customer\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "dcade924",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
+    "\n",
+    "from langgraph.graph import MessageGraph\n",
+    "\n",
+    "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
+    "graph = MessageGraph()\n",
+    "nodes = {\n",
+    "    \"general\": \"general\",\n",
+    "    \"music\": \"music\",\n",
+    "    END: END,\n",
+    "    \"tools\": \"tools\",\n",
+    "    \"customer\": \"customer\",\n",
+    "}\n",
+    "# Define a new graph\n",
+    "workflow = MessageGraph()\n",
+    "workflow.add_node(\"general\", general_node)\n",
+    "workflow.add_node(\"music\", music_node)\n",
+    "workflow.add_node(\"customer\", customer_node)\n",
+    "workflow.add_node(\"tools\", tool_node)\n",
+    "workflow.add_conditional_edges(\"general\", _route, nodes)\n",
+    "workflow.add_conditional_edges(\"tools\", _route, nodes)\n",
+    "workflow.add_conditional_edges(\"music\", _route, nodes)\n",
+    "workflow.add_conditional_edges(\"customer\", _route, nodes)\n",
+    "workflow.set_conditional_entry_point(_route, nodes)\n",
+    "graph = workflow.compile()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "ac65d6d2",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "User (q/Q to quit):  what music do you have?\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Output from node 'general':\n",
+      "---\n",
+      "content='' additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_iste6NuKvZou8O9QudOectOU', 'function': {'arguments': '{\"choice\":\"music\"}', 'name': 'Router'}, 'type': 'function'}]} response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4008e3b719'} name='general' id='run-9eb940ff-6592-43ae-aa34-22c3d630ac65-0' tool_calls=[{'name': 'Router', 'args': {'choice': 'music'}, 'id': 'call_iste6NuKvZou8O9QudOectOU'}]\n",
+      "\n",
+      "---\n",
+      "\n",
+      "Output from node 'music':\n",
+      "---\n",
+      "content=\"I can help you find songs and albums by specific artists, or check if a particular song exists. Just let me know the name of the artist or song you're interested in!\" response_metadata={'finish_reason': 'stop', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4008e3b719'} name='music' id='run-91f560e7-ffa5-437f-afda-27490cbd1efe-0'\n",
+      "\n",
+      "---\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "User (q/Q to quit):  how about shakira?\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Output from node 'general':\n",
+      "---\n",
+      "content='' additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_fH4oKyA3U9aQy3p31MYXv2VP', 'function': {'arguments': '{\"choice\":\"music\"}', 'name': 'Router'}, 'type': 'function'}]} response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_d576307f90'} name='general' id='run-6f2eee09-9e3e-4011-a045-196cc5baa1ee-0' tool_calls=[{'name': 'Router', 'args': {'choice': 'music'}, 'id': 'call_fH4oKyA3U9aQy3p31MYXv2VP'}]\n",
+      "\n",
+      "---\n",
+      "\n",
+      "Output from node 'music':\n",
+      "---\n",
+      "content='' additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_qivZqsI8zQAqSDP2jsvHyR7T', 'function': {'arguments': '{\"artist\": \"Shakira\"}', 'name': 'get_albums_by_artist'}, 'type': 'function'}, {'index': 1, 'id': 'call_GER0B3vlAjxcvYOYq1NGlV4r', 'function': {'arguments': '{\"artist\": \"Shakira\"}', 'name': 'get_tracks_by_artist'}, 'type': 'function'}]} response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_ce0793330f'} name='music' id='run-38e2eca8-771c-48a2-83be-023fd17fc6f6-0' tool_calls=[{'name': 'get_albums_by_artist', 'args': {'artist': 'Shakira'}, 'id': 'call_qivZqsI8zQAqSDP2jsvHyR7T'}, {'name': 'get_tracks_by_artist', 'args': {'artist': 'Shakira'}, 'id': 'call_GER0B3vlAjxcvYOYq1NGlV4r'}]\n",
+      "\n",
+      "---\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/wfh/code/lc/langchain/libs/core/langchain_core/_api/deprecation.py:139: LangChainDeprecationWarning: The method `BaseRetriever.get_relevant_documents` was deprecated in langchain-core 0.1.46 and will be removed in 0.3.0. Use invoke instead.\n",
+      "  warn_deprecated(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Output from node 'tools':\n",
+      "---\n",
+      "[ToolMessage(content=\"[{'Title': 'Supernatural', 'Name': 'Santana'}, {'Title': 'Santana - As Years Go By', 'Name': 'Santana'}, {'Title': 'Santana Live', 'Name': 'Santana'}, {'Title': 'Lulu Santos - RCA 100 Anos De Música - Álbum 01', 'Name': 'Lulu Santos'}, {'Title': 'Lulu Santos - RCA 100 Anos De Música - Álbum 02', 'Name': 'Lulu Santos'}]\", name='get_albums_by_artist', id='14ad12f3-afa1-4375-a89d-e878babf2d95', tool_call_id='call_qivZqsI8zQAqSDP2jsvHyR7T'), ToolMessage(content='[{\\'SongName\\': \\'(Da Le) Yaleo\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Love Of My Life\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Put Your Lights On\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Africa Bamba\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Smooth\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Do You Like The Way\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Maria Maria\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Migra\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Corazon Espinado\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Wishing It Was\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'El Farol\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Primavera\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'The Calling\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Jingo\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'El Corazon Manda\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'La Puesta Del Sol\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Persuasion\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'As The Years Go by\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Soul Sacrifice\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Fried Neckbones And Home Fries\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Santana Jam\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Evil Ways\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \"We\\'ve Got To Get Together/Jingo\", \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Rock Me\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \"Just Ain\\'t Good Enough\", \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Funky Piano\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'The Way You Do To Mer\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Assim Caminha A Humanidade\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Um Pro Outro\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Casa\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Condição\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Satisfação\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Brumário\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Sábado À Noite\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'A Cura\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Atrás Do Trio Elétrico\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Tudo Bem\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Toda Forma De Amor\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Sereia\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Se Você Pensa\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Lá Vem O Sol (Here Comes The Sun)\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Honolulu\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Dancin´Days\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Aviso Aos Navegantes\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Hyperconectividade\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'O Descobridor Dos Sete Mares\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Um Certo Alguém\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Fullgás\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Aquilo\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Senta A Pua\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Ro-Que-Se-Da-Ne\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Tudo Igual\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Fogo De Palha\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Assaltaram A Gramática\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'O Último Romântico (Ao Vivo)\\', \\'ArtistName\\': \\'Lulu Santos\\'}]', name='get_tracks_by_artist', id='4ddcebc3-8e4e-42d4-8ae4-3ce3a62b548c', tool_call_id='call_GER0B3vlAjxcvYOYq1NGlV4r')]\n",
+      "\n",
+      "---\n",
+      "\n",
+      "Output from node 'music':\n",
+      "---\n",
+      "content=\"It seems I couldn't find specific albums or songs by Shakira, but I did find some related artists and their works. Here are some albums and songs by Santana and Lulu Santos:\\n\\n### Albums:\\n- **Santana:**\\n  - Supernatural\\n  - Santana - As Years Go By\\n  - Santana Live\\n\\n- **Lulu Santos:**\\n  - Lulu Santos - RCA 100 Anos De Música - Álbum 01\\n  - Lulu Santos - RCA 100 Anos De Música - Álbum 02\\n\\n### Songs:\\n- **Santana:**\\n  - (Da Le) Yaleo\\n  - Love Of My Life\\n  - Put Your Lights On\\n  - Africa Bamba\\n  - Smooth\\n  - Maria Maria\\n  - Corazon Espinado\\n  - Jingo\\n  - Evil Ways\\n\\n- **Lulu Santos:**\\n  - Assim Caminha A Humanidade\\n  - Um Pro Outro\\n  - Casa\\n  - Condição\\n  - Satisfação\\n  - A Cura\\n  - Atrás Do Trio Elétrico\\n  - Toda Forma De Amor\\n  - Sereia\\n  - Se Você Pensa\\n\\nIf you have any other specific artists or songs in mind, feel free to let me know!\" response_metadata={'finish_reason': 'stop', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_d576307f90'} name='music' id='run-3d90d7cc-e7f7-48dc-bffd-00765c3f5d13-0'\n",
+      "\n",
+      "---\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "User (q/Q to quit):  hm cool\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Output from node 'general':\n",
+      "---\n",
+      "content='' additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_Nc5d0TWNbpnVJFeYJdQFuFGd', 'function': {'arguments': '{\"choice\":\"music\"}', 'name': 'Router'}, 'type': 'function'}]} response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4008e3b719'} name='general' id='run-19a3588e-f04c-48db-a54f-95d6b930ee3e-0' tool_calls=[{'name': 'Router', 'args': {'choice': 'music'}, 'id': 'call_Nc5d0TWNbpnVJFeYJdQFuFGd'}]\n",
+      "\n",
+      "---\n",
+      "\n",
+      "Output from node 'music':\n",
+      "---\n",
+      "content='' additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_weMHkgu3GYaMwXZM6hnCZd0z', 'function': {'arguments': '{\"artist\": \"Shakira\"}', 'name': 'get_albums_by_artist'}, 'type': 'function'}, {'index': 1, 'id': 'call_rXlVbPiEHbt10CNDUJ5GA2ZQ', 'function': {'arguments': '{\"artist\": \"Shakira\"}', 'name': 'get_tracks_by_artist'}, 'type': 'function'}]} response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_ce0793330f'} name='music' id='run-71bf8550-b5a8-423f-b463-83d9ff51391b-0' tool_calls=[{'name': 'get_albums_by_artist', 'args': {'artist': 'Shakira'}, 'id': 'call_weMHkgu3GYaMwXZM6hnCZd0z'}, {'name': 'get_tracks_by_artist', 'args': {'artist': 'Shakira'}, 'id': 'call_rXlVbPiEHbt10CNDUJ5GA2ZQ'}]\n",
+      "\n",
+      "---\n",
+      "\n",
+      "Output from node 'tools':\n",
+      "---\n",
+      "[ToolMessage(content=\"[{'Title': 'Supernatural', 'Name': 'Santana'}, {'Title': 'Santana - As Years Go By', 'Name': 'Santana'}, {'Title': 'Santana Live', 'Name': 'Santana'}, {'Title': 'Lulu Santos - RCA 100 Anos De Música - Álbum 01', 'Name': 'Lulu Santos'}, {'Title': 'Lulu Santos - RCA 100 Anos De Música - Álbum 02', 'Name': 'Lulu Santos'}]\", name='get_albums_by_artist', id='52ada997-83f6-4500-b0a7-1104d4d38eb9', tool_call_id='call_weMHkgu3GYaMwXZM6hnCZd0z'), ToolMessage(content='[{\\'SongName\\': \\'(Da Le) Yaleo\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Love Of My Life\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Put Your Lights On\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Africa Bamba\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Smooth\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Do You Like The Way\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Maria Maria\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Migra\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Corazon Espinado\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Wishing It Was\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'El Farol\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Primavera\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'The Calling\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Jingo\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'El Corazon Manda\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'La Puesta Del Sol\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Persuasion\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'As The Years Go by\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Soul Sacrifice\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Fried Neckbones And Home Fries\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Santana Jam\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Evil Ways\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \"We\\'ve Got To Get Together/Jingo\", \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Rock Me\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \"Just Ain\\'t Good Enough\", \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Funky Piano\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'The Way You Do To Mer\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Assim Caminha A Humanidade\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Um Pro Outro\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Casa\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Condição\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Satisfação\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Brumário\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Sábado À Noite\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'A Cura\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Atrás Do Trio Elétrico\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Tudo Bem\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Toda Forma De Amor\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Sereia\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Se Você Pensa\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Lá Vem O Sol (Here Comes The Sun)\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Honolulu\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Dancin´Days\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Aviso Aos Navegantes\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Hyperconectividade\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'O Descobridor Dos Sete Mares\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Um Certo Alguém\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Fullgás\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Aquilo\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Senta A Pua\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Ro-Que-Se-Da-Ne\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Tudo Igual\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Fogo De Palha\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Assaltaram A Gramática\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'O Último Romântico (Ao Vivo)\\', \\'ArtistName\\': \\'Lulu Santos\\'}]', name='get_tracks_by_artist', id='7583e077-2fb4-44bf-bb00-b89d599ae84d', tool_call_id='call_rXlVbPiEHbt10CNDUJ5GA2ZQ')]\n",
+      "\n",
+      "---\n",
+      "\n",
+      "Output from node 'music':\n",
+      "---\n",
+      "content=\"It seems like I couldn't find specific albums or songs by Shakira. However, I did find some related artists and their works. Here are some albums and songs by Santana and Lulu Santos:\\n\\n### Albums:\\n1. **Santana**\\n   - Supernatural\\n   - Santana - As Years Go By\\n   - Santana Live\\n\\n2. **Lulu Santos**\\n   - RCA 100 Anos De Música - Álbum 01\\n   - RCA 100 Anos De Música - Álbum 02\\n\\n### Songs:\\n1. **Santana**\\n   - (Da Le) Yaleo\\n   - Love Of My Life\\n   - Put Your Lights On\\n   - Africa Bamba\\n   - Smooth\\n   - Maria Maria\\n   - Corazon Espinado\\n   - Jingo\\n   - Evil Ways\\n\\n2. **Lulu Santos**\\n   - Assim Caminha A Humanidade\\n   - Um Pro Outro\\n   - Casa\\n   - Condição\\n   - Satisfação\\n   - A Cura\\n   - Atrás Do Trio Elétrico\\n   - Toda Forma De Amor\\n   - Sereia\\n\\nIf you have any other artists or songs in mind, feel free to let me know!\" response_metadata={'finish_reason': 'stop', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_d576307f90'} name='music' id='run-2418b45b-2762-49ca-b166-a0fee309ed9e-0'\n",
+      "\n",
+      "---\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "User (q/Q to quit):  q\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "AI: Byebye\n"
+     ]
+    }
+   ],
+   "source": [
+    "import uuid\n",
+    "\n",
+    "from langchain_core.messages import HumanMessage\n",
+    "\n",
+    "from langgraph.graph.graph import START\n",
+    "\n",
+    "history = []\n",
+    "while True:\n",
+    "    user = input(\"User (q/Q to quit): \")\n",
+    "    if user in {\"q\", \"Q\"}:\n",
+    "        print(\"AI: Byebye\")\n",
+    "        break\n",
+    "    history.append(HumanMessage(content=user))\n",
+    "    async for output in graph.astream(history):\n",
+    "        for key, value in output.items():\n",
+    "            print(f\"Output from node '{key}':\")\n",
+    "            print(\"---\")\n",
+    "            print(value)\n",
+    "        print(\"\\n---\\n\")"
    ]
   }
  ],

examples/cloud_examples/cron_jobs.ipynb

@@ -20,9 +20,10 @@
    "outputs": [],
    "source": [
     "from langgraph_sdk import get_client\n",
+    "\n",
     "client = get_client()\n",
     "assistants = await client.assistants.search()\n",
-    "assistants = [a for a in assistants if not a['config']]\n",
+    "assistants = [a for a in assistants if not a[\"config\"]]\n",
     "assistant = assistants[0]\n",
     "thread = await client.threads.create()"
    ]
@@ -43,7 +44,12 @@
    "outputs": [],
    "source": [
     "# This schedules a job to run at 15:27 (3:27PM) every day\n",
-    "cron_1 = await client.crons.create_for_thread(thread['thread_id'],assistant['assistant_id'],schedule=\"27 15 * * *\",input={'messages':[{\"role\":\"user\",\"content\":\"What time is it?\"}]})"
+    "cron_1 = await client.crons.create_for_thread(\n",
+    "    thread[\"thread_id\"],\n",
+    "    assistant[\"assistant_id\"],\n",
+    "    schedule=\"27 15 * * *\",\n",
+    "    input={\"messages\": [{\"role\": \"user\", \"content\": \"What time is it?\"}]},\n",
+    ")"
    ]
   },
   {
@@ -59,16 +65,16 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "await client.crons.delete(cron_1['cron_id'])"
+    "await client.crons.delete(cron_1[\"cron_id\"])"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Cron job threadless\n",
+    "## Cron job stateless\n",
     "\n",
-    "You can also create threadless cron jobs by using the following code:"
+    "You can also create stateless cron jobs by using the following code:"
    ]
   },
   {
@@ -78,7 +84,11 @@
    "outputs": [],
    "source": [
     "# This schedules a job to run at 15:27 (3:27PM) every day\n",
-    "cron_2 = await client.crons.create(assistant['assistant_id'],schedule=\"27 15 * * *\",input={'messages':[{\"role\":\"user\",\"content\":\"What time is it?\"}]})"
+    "cron_2 = await client.crons.create(\n",
+    "    assistant[\"assistant_id\"],\n",
+    "    schedule=\"27 15 * * *\",\n",
+    "    input={\"messages\": [{\"role\": \"user\", \"content\": \"What time is it?\"}]},\n",
+    ")"
    ]
   },
   {
@@ -94,7 +104,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "await client.crons.delete(cron_2['cron_id'])"
+    "await client.crons.delete(cron_2[\"cron_id\"])"
    ]
   }
  ],

examples/cloud_examples/enqueue_concurrent.ipynb

@@ -1,190 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Enqueue\n",
-    "\n",
-    "This notebook assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide](https://langchain-ai.github.io/langgraph/cloud/concepts/#double-texting).\n",
-    "\n",
-    "The guide covers the `enqueue` option for double texting, which adds the interruptions to a queue and executes them in the order they are received by the client. Below is a quick example of using the `enqueue` option.\n",
-    "\n",
-    "First, let's import our required packages and instantiate our client, assistant, and thread."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.messages import convert_to_messages\n",
-    "from langgraph_sdk import get_client"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "client = get_client()\n",
-    "assistant_id = \"agent\"\n",
-    "thread = await client.threads.create()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# this run will be interrupted\n",
-    "first_run = await client.runs.create(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant_id,\n",
-    "    input={\"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in sf?\"}]},\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "second_run = await client.runs.create(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant_id,\n",
-    "    input={\"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in nyc?\"}]},\n",
-    "    multitask_strategy=\"enqueue\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Verify that the thread has data from both runs"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# wait until the second run completes\n",
-    "await client.runs.join(thread[\"thread_id\"], second_run[\"run_id\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "state = await client.threads.get_state(thread[\"thread_id\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "what's the weather in sf?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "[{'id': 'toolu_01Dez1sJre4oA2Y7NsKJV6VT', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]\n",
-      "Tool Calls:\n",
-      "  tavily_search_results_json (toolu_01Dez1sJre4oA2Y7NsKJV6VT)\n",
-      " Call ID: toolu_01Dez1sJre4oA2Y7NsKJV6VT\n",
-      "  Args:\n",
-      "    query: weather in san francisco\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: tavily_search_results_json\n",
-      "\n",
-      "[{\"url\": \"https://www.accuweather.com/en/us/san-francisco/94103/weather-forecast/347629\", \"content\": \"Get the current and future weather conditions for San Francisco, CA, including temperature, precipitation, wind, air quality and more. See the hourly and 10-day outlook, radar maps, alerts and allergy information.\"}]\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "According to AccuWeather, the current weather conditions in San Francisco are:\n",
-      "\n",
-      "Temperature: 57°F (14°C)\n",
-      "Conditions: Mostly Sunny\n",
-      "Wind: WSW 10 mph\n",
-      "Humidity: 72%\n",
-      "\n",
-      "The forecast for the next few days shows partly sunny skies with highs in the upper 50s to mid 60s F (14-18°C) and lows in the upper 40s to low 50s F (9-11°C). Typical mild, dry weather for San Francisco this time of year.\n",
-      "\n",
-      "Some key details from the AccuWeather forecast:\n",
-      "\n",
-      "Today: Mostly sunny, high of 62°F (17°C)\n",
-      "Tonight: Partly cloudy, low of 49°F (9°C) \n",
-      "Tomorrow: Partly sunny, high of 59°F (15°C)\n",
-      "Saturday: Mostly sunny, high of 64°F (18°C)\n",
-      "Sunday: Partly sunny, high of 61°F (16°C)\n",
-      "\n",
-      "So in summary, expect seasonable spring weather in San Francisco over the next several days, with a mix of sun and clouds and temperatures ranging from the upper 40s at night to the low 60s during the days. Typical dry conditions with no rain in the forecast.\n",
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "what's the weather in nyc?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "[{'text': 'Here are the current weather conditions and forecast for New York City:', 'type': 'text'}, {'id': 'toolu_01FFft5Sx9oS6AdVJuRWWcGp', 'input': {'query': 'weather in new york city'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]\n",
-      "Tool Calls:\n",
-      "  tavily_search_results_json (toolu_01FFft5Sx9oS6AdVJuRWWcGp)\n",
-      " Call ID: toolu_01FFft5Sx9oS6AdVJuRWWcGp\n",
-      "  Args:\n",
-      "    query: weather in new york city\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: tavily_search_results_json\n",
-      "\n",
-      "[{\"url\": \"https://www.weatherapi.com/\", \"content\": \"{'location': {'name': 'New York', 'region': 'New York', 'country': 'United States of America', 'lat': 40.71, 'lon': -74.01, 'tz_id': 'America/New_York', 'localtime_epoch': 1718734479, 'localtime': '2024-06-18 14:14'}, 'current': {'last_updated_epoch': 1718733600, 'last_updated': '2024-06-18 14:00', 'temp_c': 29.4, 'temp_f': 84.9, 'is_day': 1, 'condition': {'text': 'Sunny', 'icon': '//cdn.weatherapi.com/weather/64x64/day/113.png', 'code': 1000}, 'wind_mph': 2.2, 'wind_kph': 3.6, 'wind_degree': 158, 'wind_dir': 'SSE', 'pressure_mb': 1025.0, 'pressure_in': 30.26, 'precip_mm': 0.0, 'precip_in': 0.0, 'humidity': 63, 'cloud': 0, 'feelslike_c': 31.3, 'feelslike_f': 88.3, 'windchill_c': 28.3, 'windchill_f': 82.9, 'heatindex_c': 29.6, 'heatindex_f': 85.3, 'dewpoint_c': 18.4, 'dewpoint_f': 65.2, 'vis_km': 16.0, 'vis_miles': 9.0, 'uv': 7.0, 'gust_mph': 16.5, 'gust_kph': 26.5}}\"}]\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "According to the weather data from WeatherAPI:\n",
-      "\n",
-      "Current Conditions in New York City (as of 2:00 PM local time):\n",
-      "- Temperature: 85°F (29°C)\n",
-      "- Conditions: Sunny\n",
-      "- Wind: 2 mph (4 km/h) from the SSE\n",
-      "- Humidity: 63%\n",
-      "- Heat Index: 85°F (30°C)\n",
-      "\n",
-      "The forecast shows sunny and warm conditions persisting over the next few days:\n",
-      "\n",
-      "Today: Sunny, high of 85°F (29°C)\n",
-      "Tonight: Clear, low of 68°F (20°C)\n",
-      "Tomorrow: Sunny, high of 88°F (31°C) \n",
-      "Thursday: Mostly sunny, high of 90°F (32°C)\n",
-      "Friday: Partly cloudy, high of 87°F (31°C)\n",
-      "\n",
-      "So New York City is experiencing beautiful sunny weather with seasonably warm temperatures in the mid-to-upper 80s Fahrenheit (around 30°C). Humidity is moderate in the 60% range. Overall, ideal late spring/early summer conditions for being outdoors in the city over the next several days.\n"
-     ]
-    }
-   ],
-   "source": [
-    "for m in convert_to_messages(state[\"values\"][\"messages\"]):\n",
-    "    m.pretty_print()"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "",
-   "name": ""
-  },
-  "language_info": {
-   "name": "python"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

examples/cloud_examples/human_in_the_loop_breakpoint.ipynb

@@ -1,116 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# How to Add Breakpoints\n",
-    "\n",
-    "When creating LangGraph agents, it is often nice to add a human-in-the-loop component.\n",
-    "This can be helpful when giving them access to tools.\n",
-    "Often in these situations you may want to manually approve an action before taking.\n",
-    "\n",
-    "This can be in several ways, but the primary supported way is to add an \"interrupt\" before a node is executed.\n",
-    "This interrupts execution at that node.\n",
-    "You can then resume from that spot to continue.  "
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup\n",
-    "\n",
-    "### Code for your graph\n",
-    "\n",
-    "In this how-to we use a simple ReAct style hosted graph (you can see the full code for defining it [here](https://langchain-ai.github.io/langgraph/how-tos/human_in_the_loop/breakpoints/)). The important thing is that there are two nodes (one named `agent` that calls the LLM, and one named `action` that calls the tool), and a routing function from `agent` that determines whether to call `action` next or just end the graph run (the `action` node always calls the `agent` node after execution).\n",
-    "\n",
-    "### SDK Initialization"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph_sdk import get_client\n",
-    "client = get_client()\n",
-    "assistants = await client.assistants.search()\n",
-    "assistants = [a for a in assistants if not a['config']]\n",
-    "assistant = assistants[0]\n",
-    "assistant_id = assistant['assistant_id']\n",
-    "thread = await client.threads.create()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Adding a breakpoint\n",
-    "\n",
-    "We now want to add a breakpoint in our graph run, which we will do before a tool is called.\n",
-    "We can do this by adding `interrupt_before=[\"action\"]`, which tells us to interrupt before calling the action node.\n",
-    "We can do this either when compiling the graph or when kicking off a run.\n",
-    "Here we will do it when kicking of a run, if you would like to to do it at compile time you need to edit the python file where your graph is defined and add the `interrupt_before` parameter when you call `.compile`.\n",
-    "\n",
-    "First let's access our hosted Langgraph instance through the SDK:"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "And, now let's compile it with a breakpoint before the tool node:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Receiving new event of type: metadata...\n",
-      "{'run_id': '3b77ef83-687a-4840-8858-0371f91a92c3'}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: data...\n",
-      "{'agent': {'messages': [{'content': [{'id': 'toolu_01HwZqM1ptX6E15A5LAmyZTB', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-e5d17791-4d37-4ad2-815f-a0c4cba62585', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in san francisco'}, 'id': 'toolu_01HwZqM1ptX6E15A5LAmyZTB'}], 'invalid_tool_calls': []}]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: end...\n",
-      "None\n",
-      "\n",
-      "\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "input = {\"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in sf\"}]}\n",
-    "async for chunk in client.runs.stream(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant_id,\n",
-    "    input=input,\n",
-    "    stream_mode=\"updates\",\n",
-    "    interrupt_before=[\"action\"],\n",
-    "):\n",
-    "    print(f\"Receiving new event of type: {chunk.event}...\")\n",
-    "    print(chunk.data)\n",
-    "    print(\"\\n\\n\")"
-   ]
-  }
- ],
- "metadata": {
-  "language_info": {
-   "name": "python"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

examples/cloud_examples/human_in_the_loop_edit_state.ipynb

@@ -1,173 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# How to Edit State of a Deployed Graph\n",
-    "\n",
-    "When creating LangGraph agents, it is often nice to add a human-in-the-loop component. This can be helpful when giving them access to tools. Often in these situations you may want to edit the graph state before continuing (for example, to edit what tool is being called, or how it is being called).\n",
-    "\n",
-    "This can be in several ways, but the primary supported way is to add an \"interrupt\" before a node is executed. This interrupts execution at that node. You can then use update_state to update the state, and then resume from that spot to continue.\n",
-    "\n",
-    "## Setup\n",
-    "\n",
-    "We are not going to show the full code for the graph we are hosting, but you can see it [here](https://langchain-ai.github.io/langgraph/how-tos/human_in_the_loop/edit-graph-state/#build-the-agent) if you want to. Once this graph is hosted, we are ready to invoke it and wait for user input. \n",
-    "\n",
-    "### SDK initialization\n",
-    "\n",
-    "First, we need to setup our client so that we can communicate with our hosted graph:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 37,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph_sdk import get_client\n",
-    "client = get_client()\n",
-    "assistants = await client.assistants.search()\n",
-    "assistants = [a for a in assistants if not a['config']]\n",
-    "assistant = assistants[0]\n",
-    "thread = await client.threads.create()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Editing state\n",
-    "\n",
-    "### Initial invocation\n",
-    "\n",
-    "Now let's invoke our graph, making sure to interrupt before the `action` node."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 38,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'agent': {'messages': [{'content': [{'text': \"Certainly! I'll search for the current weather in San Francisco for you using the search function. Here's how I'll do that:\", 'type': 'text'}, {'id': 'toolu_01KEJMBFozSiZoS4mAcPZeqQ', 'input': {'query': 'current weather in San Francisco'}, 'name': 'search', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-6dbb0167-f8f6-4e2a-ab68-229b2d1fbb64', 'example': False, 'tool_calls': [{'name': 'search', 'args': {'query': 'current weather in San Francisco'}, 'id': 'toolu_01KEJMBFozSiZoS4mAcPZeqQ'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}\n"
-     ]
-    }
-   ],
-   "source": [
-    "input = {'messages':[{\"role\":\"user\",\"content\":\"search for weather in SF\"}]}\n",
-    "\n",
-    "async for chunk in client.runs.stream(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant[\"assistant_id\"], # graph_id\n",
-    "    input=input,\n",
-    "    stream_mode=\"updates\",\n",
-    "    interrupt_before=[\"action\"],\n",
-    "):\n",
-    "    if chunk.data and \"run_id\" not in chunk.data:\n",
-    "        print(chunk.data)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Edit the state\n",
-    "\n",
-    "Now, let's assume we actually meant to search for the weather in Sidi Frej (another city with the initials SF). We can edit the state to properly reflect that:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 39,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'configurable': {'thread_id': '88d58d3f-4151-47a9-a8e0-e42fdd3527b8',\n",
-       "  'thread_ts': '1ef3274b-a809-6913-8002-91536ce6554d'}}"
-      ]
-     },
-     "execution_count": 39,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# First, lets get the current state\n",
-    "current_state = await client.threads.get_state(thread['thread_id'])\n",
-    "\n",
-    "# Let's now get the last message in the state\n",
-    "# This is the one with the tool calls that we want to update\n",
-    "last_message = current_state['values']['messages'][-1]\n",
-    "\n",
-    "# Let's now update the args for that tool call\n",
-    "last_message['tool_calls'][0]['args'] = {'query': 'current weather in Sidi Frej'}\n",
-    "\n",
-    "# Let's now call `update_state` to pass in this message in the `messages` key\n",
-    "# This will get treated as any other update to the state\n",
-    "# It will get passed to the reducer function for the `messages` key\n",
-    "# That reducer function will use the ID of the message to update it\n",
-    "# It's important that it has the right ID! Otherwise it would get appended\n",
-    "# as a new message\n",
-    "await client.threads.update_state(thread['thread_id'], {\"messages\": last_message})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Resume invocation\n",
-    "\n",
-    "Now we can resume our graph run but with the updated state:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 40,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'action': {'messages': [{'content': '[\"I looked up: current weather in Sidi Frej. Result: It\\'s sunny in San Francisco, but you better look out if you\\'re a Gemini 😈.\"]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '1161b8d1-bee4-4188-9be8-698aecb69f10', 'tool_call_id': 'toolu_01KEJMBFozSiZoS4mAcPZeqQ'}]}}\n",
-      "{'agent': {'messages': [{'content': [{'text': 'I apologize for the confusion in my search query. It seems the search function interpreted \"SF\" as \"Sidi Frej\" instead of \"San Francisco\" as we intended. Let me search again with the full city name to get the correct information:', 'type': 'text'}, {'id': 'toolu_0111rrwgfAcmurHZn55qjqTR', 'input': {'query': 'current weather in San Francisco'}, 'name': 'search', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-b8c25779-cfb4-46fc-a421-48553551242f', 'example': False, 'tool_calls': [{'name': 'search', 'args': {'query': 'current weather in San Francisco'}, 'id': 'toolu_0111rrwgfAcmurHZn55qjqTR'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}\n",
-      "{'action': {'messages': [{'content': '[\"I looked up: current weather in San Francisco. Result: It\\'s sunny in San Francisco, but you better look out if you\\'re a Gemini 😈.\"]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '6bc632ae-5ee6-4d01-9532-79c524a2d443', 'tool_call_id': 'toolu_0111rrwgfAcmurHZn55qjqTR'}]}}\n",
-      "{'agent': {'messages': [{'content': \"Now, based on the search results, I can provide you with information about the current weather in San Francisco:\\n\\nThe weather in San Francisco is currently sunny. \\n\\nIt's worth noting that the search result included an unusual comment about Gemini, which doesn't seem directly related to the weather. This might be due to the search engine including some astrological information or a joke in its results. However, for the purpose of weather information, we can focus on the fact that it's sunny in San Francisco right now.\\n\\nIs there anything else you'd like to know about the weather in San Francisco or any other location?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-227a042b-dd97-476e-af32-76a3703af5d8', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}\n"
-     ]
-    }
-   ],
-   "source": [
-    "async for chunk in client.runs.stream(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant[\"assistant_id\"], # graph_id\n",
-    "    input=None,\n",
-    "    stream_mode=\"updates\",\n",
-    "):\n",
-    "    if chunk.data and \"run_id\" not in chunk.data:\n",
-    "        print(chunk.data)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "As you can see it now looks up the current weather in Sidi Frej (although our dummy search node still returns results for SF because we don't actually do a search in this example, we just return the same \"It's sunny in San Francisco ...\" result every time)."
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

examples/cloud_examples/human_in_the_loop_time_travel.ipynb

@@ -1,235 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# How to Replay and Branch from Prior States\n",
-    "\n",
-    "With Langgraph Cloud you have the ability to return to any of your prior states and either re-run the graph to reproduce issues noticed during testing, or branch out in a different way from what was originally done in the prior states. In this guide we will show a quick example of how to rerun past states and how to branch off from previous states as well.\n",
-    "\n",
-    "## Setup\n",
-    "\n",
-    "We are not going to show the full code for the graph we are hosting, but you can see it [here](https://langchain-ai.github.io/langgraph/how-tos/human_in_the_loop/time-travel/#build-the-agent) if you want to. Once this graph is hosted, we are ready to invoke it and wait for user input. \n",
-    "\n",
-    "### SDK initialization\n",
-    "\n",
-    "First, we need to setup our client so that we can communicate with our hosted graph:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 99,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph_sdk import get_client\n",
-    "client = get_client()\n",
-    "assistants = await client.assistants.search()\n",
-    "assistants = [a for a in assistants if not a['config']]\n",
-    "assistant = assistants[0]\n",
-    "thread = await client.threads.create()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Replay a state\n",
-    "\n",
-    "### Initial invocation\n",
-    "\n",
-    "Before replaying a state - we need to create states to replay from! In order to do this, let's invoke our graph with a simple message:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 100,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'agent': {'messages': [{'content': [{'text': \"Certainly! I'll use the search function to look up the current weather in San Francisco for you. Let me do that now.\", 'type': 'text'}, {'id': 'toolu_011vroKUtWU7SBdrngpgpFMn', 'input': {'query': 'current weather in San Francisco'}, 'name': 'search', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ee639877-d97d-40f8-96dc-d0d1ae22d203', 'example': False, 'tool_calls': [{'name': 'search', 'args': {'query': 'current weather in San Francisco'}, 'id': 'toolu_011vroKUtWU7SBdrngpgpFMn'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}\n",
-      "{'action': {'messages': [{'content': '[\"I looked up: current weather in San Francisco. Result: It\\'s sunny in San Francisco, but you better look out if you\\'re a Gemini 😈.\"]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '7bad0e72-5ebe-4b08-9b8a-b99b0fe22fb7', 'tool_call_id': 'toolu_011vroKUtWU7SBdrngpgpFMn'}]}}\n",
-      "{'agent': {'messages': [{'content': \"Based on the search results, I can provide you with information about the current weather in San Francisco:\\n\\nThe weather in San Francisco is currently sunny. This is great news for outdoor activities and enjoying the city's beautiful sights.\\n\\nIt's worth noting that the search result included an unusual comment about Geminis, which isn't typically part of a weather report. This might be due to the search engine including some astrological information or a joke in its results. However, for the purpose of answering your question about the weather, we can focus on the fact that it's sunny in San Francisco.\\n\\nIf you need any more specific information about the weather in San Francisco, such as temperature, wind speed, or forecast for the coming days, please let me know, and I'd be happy to search for that information for you.\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-dbac539a-33c8-4f0c-9e20-91f318371e7c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}\n"
-     ]
-    }
-   ],
-   "source": [
-    "input = {'messages':[{\"role\":\"user\",\"content\":\"Please search the weather in SF\"}]}\n",
-    "\n",
-    "async for chunk in client.runs.stream(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant[\"assistant_id\"], # graph_id\n",
-    "    input=input,\n",
-    "    stream_mode=\"updates\",\n",
-    "):\n",
-    "    if chunk.data and \"run_id\" not in chunk.data:\n",
-    "        print(chunk.data)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Now let's get our list of states, and invoke from the third state (right before the tool get called):"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 101,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "states = await client.threads.get_history(thread['thread_id'])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 102,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "['action']"
-      ]
-     },
-     "execution_count": 102,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# We can confirm that this state is correct by checking the 'next' attribute and seeing that it is the tool call node\n",
-    "state_to_replay = states[2]\n",
-    "state_to_replay['next']"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "To rerun from a state, we need to pass in the `checkpoint_id` into the config of the run like follows:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 103,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'action': {'messages': [{'content': '[\"I looked up: current weather in San Francisco. Result: It\\'s sunny in San Francisco, but you better look out if you\\'re a Gemini 😈.\"]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': 'eba650e5-400e-4938-8508-f878dcbcc532', 'tool_call_id': 'toolu_011vroKUtWU7SBdrngpgpFMn'}]}}\n",
-      "{'agent': {'messages': [{'content': \"Based on the search results, I can provide you with information about the current weather in San Francisco:\\n\\nThe weather in San Francisco is currently sunny. This is great news if you're planning any outdoor activities or simply want to enjoy a pleasant day in the city.\\n\\nIt's worth noting that the search result included an unusual comment about Geminis, which doesn't seem directly related to the weather. This appears to be a playful or humorous addition to the weather report, possibly from the source where this information was obtained.\\n\\nIs there anything else you'd like to know about the weather in San Francisco or any other information you need?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-bc6dca3f-a1e2-4f59-a69b-fe0515a348bb', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}\n"
-     ]
-    }
-   ],
-   "source": [
-    "async for chunk in client.runs.stream(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant[\"assistant_id\"], # graph_id\n",
-    "    input=None,\n",
-    "    stream_mode=\"updates\",\n",
-    "    config={\"configurable\":{\"thread_ts\":state_to_replay['checkpoint_id']}}\n",
-    "):\n",
-    "    if chunk.data and \"run_id\" not in chunk.data:\n",
-    "        print(chunk.data)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "As we can see, the graph restarted from the tool node with the same input as our original graph run.\n",
-    "\n",
-    "## Branch off from previous state\n",
-    "\n",
-    "Using LangGraph's checkpointing, you can do more than just replay past states. You can branch off previous locations to let the agent explore alternate trajectories or to let a user \"version control\" changes in a workflow.\n",
-    "\n",
-    "Let's show how to do this to edit the state at a particular point in time. Let's update the state to change the input to the tool"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 104,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Let's now get the last message in the state\n",
-    "# This is the one with the tool calls that we want to update\n",
-    "last_message = state_to_replay['values']['messages'][-1]\n",
-    "\n",
-    "# Let's now update the args for that tool call\n",
-    "last_message['tool_calls'][0]['args'] = {'query': 'current weather in SF'}\n",
-    "\n",
-    "new_state = await client.threads.update_state(thread['thread_id'],{\"messages\":[last_message]},checkpoint_id=state_to_replay['checkpoint_id'])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Now we can rerun our graph with this new config, starting from the `new_state`, which is a branch of our `state_to_replay`:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 105,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'action': {'messages': [{'content': '[\"I looked up: current weather in SF. Result: It\\'s sunny in San Francisco, but you better look out if you\\'re a Gemini 😈.\"]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '2baf9941-4fda-4081-9f87-d76795d289f1', 'tool_call_id': 'toolu_011vroKUtWU7SBdrngpgpFMn'}]}}\n",
-      "{'agent': {'messages': [{'content': \"Based on the search results, I can provide you with information about the current weather in San Francisco (SF):\\n\\nThe weather in San Francisco is currently sunny. This means it's a clear day with plenty of sunshine. \\n\\nIt's worth noting that the specific temperature wasn't provided in the search result, but sunny weather in San Francisco typically means comfortable temperatures. San Francisco is known for its mild climate, so even on sunny days, it's often not too hot.\\n\\nThe search result also included a playful reference to astrological signs, mentioning Gemini. However, this is likely just a joke or part of the search engine's presentation and not related to the actual weather conditions.\\n\\nIs there any specific information about the weather in San Francisco you'd like to know more about? I'd be happy to perform another search if you need details on temperature, wind conditions, or the forecast for the coming days.\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-a83de52d-ed18-4402-9384-75c462485743', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}\n"
-     ]
-    }
-   ],
-   "source": [
-    "async for chunk in client.runs.stream(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant[\"assistant_id\"], # graph_id\n",
-    "    input=None,\n",
-    "    stream_mode=\"updates\",\n",
-    "    config={\"configurable\":{\"thread_ts\":new_state['configurable']['thread_ts']}}\n",
-    "):\n",
-    "    if chunk.data and \"run_id\" not in chunk.data:\n",
-    "        print(chunk.data)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "As we can see, the search query changed from San Francisco to SF, just as we had hoped!"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

examples/cloud_examples/human_in_the_loop_user_input.ipynb

@@ -1,175 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# How to Wait for User Input\n",
-    "\n",
-    "One of the main human-in-the-loop interaction patterns is waiting for human input. A key use case involves asking the user clarifying questions. One way to accomplish this is simply go to the END node and exit the graph. Then, any user response comes back in as fresh invocation of the graph. This is basically just creating a chatbot architecture.\n",
-    "\n",
-    "The issue with this is it is tough to resume back in a particular point in the graph. Often times the agent is halfway through some process, and just needs a bit of a user input. Although it is possible to design your graph in such a way where you have a `conditional_entry_point` to route user messages back to the right place, that is not super scalable (as it essentially involves having a routing function that can end up almost anywhere).\n",
-    "\n",
-    "A separate way to do this is to have a node explicitly for getting user input. This is easy to implement in a notebook setting - you just put an `input()` call in the node. But that isn't exactly production ready.\n",
-    "\n",
-    "Luckily, LangGraph makes it possible to do similar things in a production way. The basic idea is:\n",
-    "\n",
-    "- Set up a node that represents human input. This can have specific incoming/outgoing edges (as you desire). There shouldn't actually be any logic inside this node.\n",
-    "- Add a breakpoint before the node. This will stop the graph before this node executes (which is good, because there's no real logic in it anyways)\n",
-    "- Use `.update_state` to update the state of the graph. Pass in whatever human response you get. The key here is to use the `as_node` parameter to apply this update **as if you were that node**. This will have the effect of making it so that when you resume execution next it resumes as if that node just acted, and not from the beginning."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup\n",
-    "\n",
-    "We are not going to show the full code for the graph we are hosting, but you can see it [here](https://langchain-ai.github.io/langgraph/how-tos/human_in_the_loop/wait-user-input/#build-the-agent) if you want to. Once this graph is hosted, we are ready to invoke it and wait for user input. "
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### SDK initialization\n",
-    "\n",
-    "First, we need to setup our client so that we can communicate with our hosted graph:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph_sdk import get_client\n",
-    "client = get_client()\n",
-    "assistants = await client.assistants.search()\n",
-    "assistants = [a for a in assistants if not a['config']]\n",
-    "assistant = assistants[0]\n",
-    "thread = await client.threads.create()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Waiting for user input\n",
-    "\n",
-    "### Initial invocation\n",
-    "\n",
-    "Now, let's invoke our graph by interrupting before `ask_human` node:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'agent': {'messages': [{'content': [{'text': \"Certainly! I'll use the AskHuman function to ask the user about their location, and then I'll use the search function to look up the weather for that location. Let's start by asking the user where they are.\", 'type': 'text'}, {'id': 'toolu_01RFahzYPvnPWTb2USk2RdKR', 'input': {'question': 'Where are you currently located?'}, 'name': 'AskHuman', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-a8422215-71d3-4093-afb4-9db141c94ddb', 'example': False, 'tool_calls': [{'name': 'AskHuman', 'args': {'question': 'Where are you currently located?'}, 'id': 'toolu_01RFahzYPvnPWTb2USk2RdKR'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}\n"
-     ]
-    }
-   ],
-   "source": [
-    "input = {'messages':[{\"role\":\"user\",\"content\":\"Use the search tool to ask the user where they are, then look up the weather there\"}]}\n",
-    "\n",
-    "async for chunk in client.runs.stream(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant[\"assistant_id\"], # graph_id\n",
-    "    input=input,\n",
-    "    stream_mode=\"updates\",\n",
-    "    interrupt_before=[\"ask_human\"],\n",
-    "):\n",
-    "    if chunk.data and \"run_id\" not in chunk.data:\n",
-    "        print(chunk.data)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Adding user input to state\n",
-    "\n",
-    "We now want to update this thread with a response from the user. We then can kick off another run.\n",
-    "\n",
-    "Because we are treating this as a tool call, we will need to update the state as if it is a response from a tool call. In order to do this, we will need to check the state to get the ID of the tool call."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'configurable': {'thread_id': '10d0ee61-db47-48fc-a58c-109a1e68cd73',\n",
-       "  'thread_ts': '1ef32729-3cc3-6647-8002-14dcb621b46e'}}"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "state = await client.threads.get_state(thread['thread_id'])\n",
-    "tool_call_id = state['values']['messages'][-1]['tool_calls'][0]['id']\n",
-    "\n",
-    "# We now create the tool call with the id and the response we want\n",
-    "tool_message = [{\"tool_call_id\": tool_call_id, \"type\": \"tool\", \"content\": \"san francisco\"}]\n",
-    "\n",
-    "await client.threads.update_state(thread['thread_id'], {\"messages\": tool_message}, as_node=\"ask_human\")\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Invoking after receiving human input\n",
-    "\n",
-    "We can now tell the agent to continue. We can just pass in None as the input to the graph, since no additional input is needed:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'agent': {'messages': [{'content': [{'text': \"Thank you for letting me know that you're in San Francisco. Now, I'll use the search function to look up the weather in San Francisco.\", 'type': 'text'}, {'id': 'toolu_01K57ofmgG2wyJ8tYJjbq5k7', 'input': {'query': 'current weather in San Francisco'}, 'name': 'search', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-241baed7-db5e-44ce-ac3c-56431705c22b', 'example': False, 'tool_calls': [{'name': 'search', 'args': {'query': 'current weather in San Francisco'}, 'id': 'toolu_01K57ofmgG2wyJ8tYJjbq5k7'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}\n",
-      "{'action': {'messages': [{'content': '[\"I looked up: current weather in San Francisco. Result: It\\'s sunny in San Francisco, but you better look out if you\\'re a Gemini 😈.\"]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '8b699b95-8546-4557-8e66-14ea71a15ed8', 'tool_call_id': 'toolu_01K57ofmgG2wyJ8tYJjbq5k7'}]}}\n",
-      "{'agent': {'messages': [{'content': \"Based on the search results, I can provide you with information about the current weather in San Francisco:\\n\\nThe weather in San Francisco is currently sunny. It's a beautiful day in the city! \\n\\nHowever, I should note that the search result included an unusual comment about Gemini zodiac signs. This appears to be either a joke or potentially irrelevant information added by the search engine. For accurate and detailed weather information, you might want to check a reliable weather service or app for San Francisco.\\n\\nIs there anything else you'd like to know about the weather or San Francisco?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-b4d7309f-f849-46aa-b6ef-475bcabd2be9', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}\n"
-     ]
-    }
-   ],
-   "source": [
-    "async for chunk in client.runs.stream(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant[\"assistant_id\"], # graph_id\n",
-    "    input=None,\n",
-    "    stream_mode=\"updates\",\n",
-    "):\n",
-    "    if chunk.data and \"run_id\" not in chunk.data:\n",
-    "        print(chunk.data)"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

examples/cloud_examples/interrupt_concurrent.ipynb

@@ -1,181 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Interrupt\n",
-    "\n",
-    "This notebook assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide](https://langchain-ai.github.io/langgraph/cloud/concepts/#double-texting).\n",
-    "\n",
-    "The guide covers the `interrupt` option for double texting, which interrupts the prior run of the graph and starts a new one with the double-text. This option does not delete the first run, but rather keeps it in the database but sets its status to `interrupted`. Below is a quick example of using the `interrupt` option.\n",
-    "\n",
-    "First, let's import our required packages and instantiate our client, assistant, and thread."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import asyncio\n",
-    "\n",
-    "from langchain_core.messages import convert_to_messages\n",
-    "from langgraph_sdk import get_client"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "client = get_client()\n",
-    "assistant_id = \"agent\"\n",
-    "thread = await client.threads.create()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# the first run will be interrupted\n",
-    "interrupted_run = await client.runs.create(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant_id,\n",
-    "    input={\"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in sf?\"}]},\n",
-    ")\n",
-    "await asyncio.sleep(2)\n",
-    "run = await client.runs.create(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant_id,\n",
-    "    input={\"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in nyc?\"}]},\n",
-    "    multitask_strategy=\"interrupt\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# wait until the second run completes\n",
-    "await client.runs.join(thread[\"thread_id\"], run[\"run_id\"])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "We can see that the thread has partial data from the first run + data from the second run"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "state = await client.threads.get_state(thread[\"thread_id\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "what's the weather in sf?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "[{'id': 'toolu_01MjNtVJwEcpujRGrf3x6Pih', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]\n",
-      "Tool Calls:\n",
-      "  tavily_search_results_json (toolu_01MjNtVJwEcpujRGrf3x6Pih)\n",
-      " Call ID: toolu_01MjNtVJwEcpujRGrf3x6Pih\n",
-      "  Args:\n",
-      "    query: weather in san francisco\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: tavily_search_results_json\n",
-      "\n",
-      "[{\"url\": \"https://www.wunderground.com/hourly/us/ca/san-francisco/KCASANFR2002/date/2024-6-18\", \"content\": \"High 64F. Winds W at 10 to 20 mph. A few clouds from time to time. Low 49F. Winds W at 10 to 20 mph. Temp. San Francisco Weather Forecasts. Weather Underground provides local & long-range weather ...\"}]\n",
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "what's the weather in nyc?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "[{'id': 'toolu_01KtE1m1ifPLQAx4fQLyZL9Q', 'input': {'query': 'weather in new york city'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]\n",
-      "Tool Calls:\n",
-      "  tavily_search_results_json (toolu_01KtE1m1ifPLQAx4fQLyZL9Q)\n",
-      " Call ID: toolu_01KtE1m1ifPLQAx4fQLyZL9Q\n",
-      "  Args:\n",
-      "    query: weather in new york city\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: tavily_search_results_json\n",
-      "\n",
-      "[{\"url\": \"https://www.accuweather.com/en/us/new-york/10021/june-weather/349727\", \"content\": \"Get the monthly weather forecast for New York, NY, including daily high/low, historical averages, to help you plan ahead.\"}]\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "The search results provide weather forecasts and information for New York City. Based on the top result from AccuWeather, here are some key details about the weather in NYC:\n",
-      "\n",
-      "- This is a monthly weather forecast for New York City for the month of June.\n",
-      "- It includes daily high and low temperatures to help plan ahead.\n",
-      "- Historical averages for June in NYC are also provided as a reference point.\n",
-      "- More detailed daily or hourly forecasts with precipitation chances, humidity, wind, etc. can be found by visiting the AccuWeather page.\n",
-      "\n",
-      "So in summary, the search provides a convenient overview of the expected weather conditions in New York City over the next month to give you an idea of what to prepare for if traveling or making plans there. Let me know if you need any other details!\n"
-     ]
-    }
-   ],
-   "source": [
-    "for m in convert_to_messages(state[\"values\"][\"messages\"]):\n",
-    "    m.pretty_print()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Verify that the original, interrupted run was interrupted"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'interrupted'"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "(await client.runs.get(thread[\"thread_id\"], interrupted_run[\"run_id\"]))[\"status\"]"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "",
-   "name": ""
-  },
-  "language_info": {
-   "name": "python"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

examples/cloud_examples/langgraph_to_langgraph_cloud.ipynb

@@ -119,6 +119,7 @@
    "outputs": [],
    "source": [
     "from langgraph_sdk import get_client\n",
+    "\n",
     "client = get_client()"
    ]
   },
@@ -354,7 +355,9 @@
    ],
    "source": [
     "inputs = {\"messages\": [(\"human\", \"what's the weather in sf\")]}\n",
-    "async for chunk in client.runs.stream(None, \"agent\", input=inputs, stream_mode=\"values\"):\n",
+    "async for chunk in client.runs.stream(\n",
+    "    None, \"agent\", input=inputs, stream_mode=\"values\"\n",
+    "):\n",
     "    if chunk.event == \"values\":\n",
     "        messages = convert_to_messages(chunk.data[\"messages\"])\n",
     "        messages[-1].pretty_print()"
@@ -423,7 +426,9 @@
    ],
    "source": [
     "inputs = {\"messages\": [(\"human\", \"what's the weather in nyc\")]}\n",
-    "invoke_output = await graph_with_memory.ainvoke(inputs, config={\"configurable\": {\"thread_id\": \"1\"}})\n",
+    "invoke_output = await graph_with_memory.ainvoke(\n",
+    "    inputs, config={\"configurable\": {\"thread_id\": \"1\"}}\n",
+    ")\n",
     "invoke_output[\"messages\"][-1].pretty_print()"
    ]
   },
@@ -458,7 +463,9 @@
    ],
    "source": [
     "inputs = {\"messages\": [(\"human\", \"what's it known for?\")]}\n",
-    "invoke_output = await graph_with_memory.ainvoke(inputs, config={\"configurable\": {\"thread_id\": \"1\"}})\n",
+    "invoke_output = await graph_with_memory.ainvoke(\n",
+    "    inputs, config={\"configurable\": {\"thread_id\": \"1\"}}\n",
+    ")\n",
     "invoke_output[\"messages\"][-1].pretty_print()"
    ]
   },
@@ -480,7 +487,9 @@
    ],
    "source": [
     "inputs = {\"messages\": [(\"human\", \"what's it known for?\")]}\n",
-    "invoke_output = await graph_with_memory.ainvoke(inputs, config={\"configurable\": {\"thread_id\": \"2\"}})\n",
+    "invoke_output = await graph_with_memory.ainvoke(\n",
+    "    inputs, config={\"configurable\": {\"thread_id\": \"2\"}}\n",
+    ")\n",
     "invoke_output[\"messages\"][-1].pretty_print()"
    ]
   },
@@ -724,7 +733,12 @@
    ],
    "source": [
     "inputs = {\"messages\": [(\"human\", \"what's the weather in sf\")]}\n",
-    "async for chunk in graph_with_memory.astream(inputs, stream_mode=\"values\", interrupt_before=[\"tools\"], config={\"configurable\": {\"thread_id\": \"3\"}}):\n",
+    "async for chunk in graph_with_memory.astream(\n",
+    "    inputs,\n",
+    "    stream_mode=\"values\",\n",
+    "    interrupt_before=[\"tools\"],\n",
+    "    config={\"configurable\": {\"thread_id\": \"3\"}},\n",
+    "):\n",
     "    chunk[\"messages\"][-1].pretty_print()"
    ]
   },
@@ -749,7 +763,12 @@
     }
    ],
    "source": [
-    "async for chunk in graph_with_memory.astream(None, stream_mode=\"values\", interrupt_before=[\"tools\"], config={\"configurable\": {\"thread_id\": \"3\"}}):\n",
+    "async for chunk in graph_with_memory.astream(\n",
+    "    None,\n",
+    "    stream_mode=\"values\",\n",
+    "    interrupt_before=[\"tools\"],\n",
+    "    config={\"configurable\": {\"thread_id\": \"3\"}},\n",
+    "):\n",
     "    chunk[\"messages\"][-1].pretty_print()"
    ]
   },
@@ -794,7 +813,13 @@
    "source": [
     "thread = await client.threads.create()\n",
     "\n",
-    "async for chunk in client.runs.stream(thread[\"thread_id\"], \"agent\", input=inputs, stream_mode=\"values\", interrupt_before=[\"tools\"]):\n",
+    "async for chunk in client.runs.stream(\n",
+    "    thread[\"thread_id\"],\n",
+    "    \"agent\",\n",
+    "    input=inputs,\n",
+    "    stream_mode=\"values\",\n",
+    "    interrupt_before=[\"tools\"],\n",
+    "):\n",
     "    if chunk.event == \"values\":\n",
     "        messages = convert_to_messages(chunk.data[\"messages\"])\n",
     "        messages[-1].pretty_print()"
@@ -821,7 +846,13 @@
     }
    ],
    "source": [
-    "async for chunk in client.runs.stream(thread[\"thread_id\"], \"agent\", input=None, stream_mode=\"values\", interrupt_before=[\"tools\"]):\n",
+    "async for chunk in client.runs.stream(\n",
+    "    thread[\"thread_id\"],\n",
+    "    \"agent\",\n",
+    "    input=None,\n",
+    "    stream_mode=\"values\",\n",
+    "    interrupt_before=[\"tools\"],\n",
+    "):\n",
     "    if chunk.event == \"values\":\n",
     "        messages = convert_to_messages(chunk.data[\"messages\"])\n",
     "        messages[-1].pretty_print()"
@@ -1000,7 +1031,9 @@
    ],
    "source": [
     "inputs = {\"messages\": [(\"human\", \"what's the weather in sf\")]}\n",
-    "async for chunk in client.runs.stream(None, \"agent\", input=inputs, stream_mode=\"events\"):\n",
+    "async for chunk in client.runs.stream(\n",
+    "    None, \"agent\", input=inputs, stream_mode=\"events\"\n",
+    "):\n",
     "    if chunk.event == \"events\" and chunk.data[\"event\"] == \"on_chat_model_stream\":\n",
     "        print(chunk.data[\"data\"][\"chunk\"])"
    ]

examples/cloud_examples/reject_concurrent.ipynb

@@ -1,164 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Reject\n",
-    "\n",
-    "This notebook assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide](https://langchain-ai.github.io/langgraph/cloud/concepts/#double-texting).\n",
-    "\n",
-    "The guide covers the `reject` option for double texting, which rejects the new run of the graph by throwing an error and continues with the original run until completion. Below is a quick example of using the `reject` option.\n",
-    "\n",
-    "First, let's import our required packages and instantiate our client, assistant, and thread."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import httpx\n",
-    "from langchain_core.messages import convert_to_messages\n",
-    "from langgraph_sdk import get_client"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "client = get_client()\n",
-    "assistant_id = \"agent\"\n",
-    "thread = await client.threads.create()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "run = await client.runs.create(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant_id,\n",
-    "    input={\"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in sf?\"}]},\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Failed to start concurrent run Client error '409 Conflict' for url 'http://localhost:8123/threads/f9e7088b-8028-4e5c-88d2-9cc9a2870e50/runs'\n",
-      "For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/409\n"
-     ]
-    }
-   ],
-   "source": [
-    "try:\n",
-    "    await client.runs.create(\n",
-    "        thread[\"thread_id\"],\n",
-    "        assistant_id,\n",
-    "        input={\n",
-    "            \"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in nyc?\"}]\n",
-    "        },\n",
-    "        multitask_strategy=\"reject\",\n",
-    "    )\n",
-    "except httpx.HTTPStatusError as e:\n",
-    "    print(\"Failed to start concurrent run\", e)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "We can verify that the original thread finished executing:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# wait until the original run completes\n",
-    "await client.runs.join(thread[\"thread_id\"], run[\"run_id\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "state = await client.threads.get_state(thread[\"thread_id\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "what's the weather in sf?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "[{'id': 'toolu_01CyewEifV2Kmi7EFKHbMDr1', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]\n",
-      "Tool Calls:\n",
-      "  tavily_search_results_json (toolu_01CyewEifV2Kmi7EFKHbMDr1)\n",
-      " Call ID: toolu_01CyewEifV2Kmi7EFKHbMDr1\n",
-      "  Args:\n",
-      "    query: weather in san francisco\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: tavily_search_results_json\n",
-      "\n",
-      "[{\"url\": \"https://www.accuweather.com/en/us/san-francisco/94103/june-weather/347629\", \"content\": \"Get the monthly weather forecast for San Francisco, CA, including daily high/low, historical averages, to help you plan ahead.\"}]\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "According to the search results from Tavily, the current weather in San Francisco is:\n",
-      "\n",
-      "The average high temperature in San Francisco in June is around 65°F (18°C), with average lows around 54°F (12°C). June tends to be one of the cooler and foggier months in San Francisco due to the marine layer of fog that often blankets the city during the summer months.\n",
-      "\n",
-      "Some key points about the typical June weather in San Francisco:\n",
-      "\n",
-      "- Mild temperatures with highs in the 60s F and lows in the 50s F\n",
-      "- Foggy mornings that often burn off to sunny afternoons\n",
-      "- Little to no rainfall, as June falls in the dry season\n",
-      "- Breezy conditions, with winds off the Pacific Ocean\n",
-      "- Layers are recommended for changing weather conditions\n",
-      "\n",
-      "So in summary, you can expect mild, foggy mornings giving way to sunny but cool afternoons in San Francisco this time of year. The marine layer keeps temperatures moderate compared to other parts of California in June.\n"
-     ]
-    }
-   ],
-   "source": [
-    "for m in convert_to_messages(state[\"values\"][\"messages\"]):\n",
-    "    m.pretty_print()"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "",
-   "name": ""
-  },
-  "language_info": {
-   "name": "python"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

examples/cloud_examples/rollback_concurrent.ipynb

@@ -1,161 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Rollback\n",
-    "\n",
-    "This notebook assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide](https://langchain-ai.github.io/langgraph/cloud/concepts/#double-texting).\n",
-    "\n",
-    "The guide covers the `rollback` option for double texting, which interrupts the prior run of the graph and starts a new one with the double-text. This option is very similar to the `interrupt` option, but in this case the first run is completely deleted from the database and cannot be restarted. Below is a quick example of using the `rollback` option.\n",
-    "\n",
-    "First, let's import our required packages and instantiate our client, assistant, and thread."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import asyncio\n",
-    "\n",
-    "import httpx\n",
-    "from langchain_core.messages import convert_to_messages\n",
-    "from langgraph_sdk import get_client"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "client = get_client()\n",
-    "assistant_id = \"agent\"\n",
-    "thread = await client.threads.create()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# the first run will be interrupted\n",
-    "rolled_back_run = await client.runs.create(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant_id,\n",
-    "    input={\"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in sf?\"}]},\n",
-    ")\n",
-    "await asyncio.sleep(2)\n",
-    "run = await client.runs.create(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant_id,\n",
-    "    input={\"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in nyc?\"}]},\n",
-    "    multitask_strategy=\"rollback\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# wait until the second run completes\n",
-    "await client.runs.join(thread[\"thread_id\"], run[\"run_id\"])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "We can see that the thread has data only from the second run"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "state = await client.threads.get_state(thread[\"thread_id\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "what's the weather in nyc?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "[{'id': 'toolu_01JzPqefao1gxwajHQ3Yh3JD', 'input': {'query': 'weather in nyc'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]\n",
-      "Tool Calls:\n",
-      "  tavily_search_results_json (toolu_01JzPqefao1gxwajHQ3Yh3JD)\n",
-      " Call ID: toolu_01JzPqefao1gxwajHQ3Yh3JD\n",
-      "  Args:\n",
-      "    query: weather in nyc\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: tavily_search_results_json\n",
-      "\n",
-      "[{\"url\": \"https://www.weatherapi.com/\", \"content\": \"{'location': {'name': 'New York', 'region': 'New York', 'country': 'United States of America', 'lat': 40.71, 'lon': -74.01, 'tz_id': 'America/New_York', 'localtime_epoch': 1718734479, 'localtime': '2024-06-18 14:14'}, 'current': {'last_updated_epoch': 1718733600, 'last_updated': '2024-06-18 14:00', 'temp_c': 29.4, 'temp_f': 84.9, 'is_day': 1, 'condition': {'text': 'Sunny', 'icon': '//cdn.weatherapi.com/weather/64x64/day/113.png', 'code': 1000}, 'wind_mph': 2.2, 'wind_kph': 3.6, 'wind_degree': 158, 'wind_dir': 'SSE', 'pressure_mb': 1025.0, 'pressure_in': 30.26, 'precip_mm': 0.0, 'precip_in': 0.0, 'humidity': 63, 'cloud': 0, 'feelslike_c': 31.3, 'feelslike_f': 88.3, 'windchill_c': 28.3, 'windchill_f': 82.9, 'heatindex_c': 29.6, 'heatindex_f': 85.3, 'dewpoint_c': 18.4, 'dewpoint_f': 65.2, 'vis_km': 16.0, 'vis_miles': 9.0, 'uv': 7.0, 'gust_mph': 16.5, 'gust_kph': 26.5}}\"}]\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "The weather API results show that the current weather in New York City is sunny with a temperature of around 85°F (29°C). The wind is light at around 2-3 mph from the south-southeast. Overall it looks like a nice sunny summer day in NYC.\n"
-     ]
-    }
-   ],
-   "source": [
-    "for m in convert_to_messages(state[\"values\"][\"messages\"]):\n",
-    "    m.pretty_print()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Verify that the original, rolled back run was deleted"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Original run was correctly deleted\n"
-     ]
-    }
-   ],
-   "source": [
-    "try:\n",
-    "    await client.runs.get(thread[\"thread_id\"], rolled_back_run[\"run_id\"])\n",
-    "except httpx.HTTPStatusError as _:\n",
-    "    print(\"Original run was correctly deleted\")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "",
-   "name": ""
-  },
-  "language_info": {
-   "name": "python"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

examples/cloud_examples/same-thread.ipynb

@@ -7,9 +7,13 @@
    "source": [
     "# How to run multiple agents on the same thread\n",
     "\n",
-    "In LangGraph API, a thread is not explicitly associated with a particular agent.\n",
-    "This means that you can run multiple agents on the same thread.\n",
-    "In this example, we will create two agents and then call them both on the same thread."
+    "In LangGraph Cloud, a thread is not explicitly associated with a particular agent.\n",
+    "This means that you can run multiple agents on the same thread, which allows a different\n",
+    "agent to continue from an initial agent's progress.\n",
+    "\n",
+    "In this example, we will create two agents and then call them both on the same thread.\n",
+    "You'll see that the second agent will respond using information from the [checkpoint](https://langchain-ai.github.io/langgraph/concepts/low_level/#checkpointer-state) generated in the thread\n",
+    "by the first agent as context."
    ]
   },
   {
@@ -37,7 +41,7 @@
    "id": "4f10d346-69e6-44f4-8ff0-ef539ba938df",
    "metadata": {},
    "source": [
-    "We can see that these agents are different"
+    "We can see that these agents are different:"
    ]
   },
   {
@@ -97,7 +101,7 @@
    "id": "5e655e61-c2ee-488a-90f6-6189c84841da",
    "metadata": {},
    "source": [
-    "We can now run it on the OpenAI assistant first."
+    "We can now run the OpenAI assistant on the thread first."
    ]
   },
   {
@@ -133,7 +137,7 @@
    "id": "c53709e9-ddb2-4429-9042-456eb6c91244",
    "metadata": {},
    "source": [
-    "Now, we can run it on a different Anthropic-based assistant."
+    "Now, we can run it on a second Anthropic-based assistant and see that this second assistant is aware of the initial question, and can answer the question, `and you?`:"
    ]
   },
   {

examples/cloud_examples/stateless_runs.ipynb

@@ -20,9 +20,10 @@
    "outputs": [],
    "source": [
     "from langgraph_sdk import get_client\n",
+    "\n",
     "client = get_client()\n",
     "assistants = await client.assistants.search()\n",
-    "assistants = [a for a in assistants if not a['config']]\n",
+    "assistants = [a for a in assistants if not a[\"config\"]]\n",
     "assistant = assistants[0]\n",
     "thread = await client.threads.create()"
    ]
@@ -50,13 +51,17 @@
     }
    ],
    "source": [
-    "input = {\"messages\":[{\"role\": \"user\", \"content\": \"Hello! My name is Bagatur and I am 26 years old.\"}]}\n",
+    "input = {\n",
+    "    \"messages\": [\n",
+    "        {\"role\": \"user\", \"content\": \"Hello! My name is Bagatur and I am 26 years old.\"}\n",
+    "    ]\n",
+    "}\n",
     "\n",
     "\n",
     "async for chunk in client.runs.stream(\n",
     "    # Don't pass in a thread_id and the stream will be stateless\n",
     "    None,\n",
-    "    assistant[\"assistant_id\"], # graph_id\n",
+    "    assistant[\"assistant_id\"],  # graph_id\n",
     "    input=input,\n",
     "    stream_mode=\"updates\",\n",
     "):\n",
@@ -81,7 +86,7 @@
    "source": [
     "stateless_run_result = await client.runs.wait(\n",
     "    None,\n",
-    "    assistant[\"assistant_id\"], # graph_id\n",
+    "    assistant[\"assistant_id\"],  # graph_id\n",
     "    input=input,\n",
     ")"
    ]

examples/cloud_examples/stream_debug.ipynb

@@ -1,176 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# How to stream debug events\n",
-    "This guide covers how to stream debug events from your graph (`stream_mode=\"debug\"`)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph_sdk import get_client\n",
-    "\n",
-    "client = get_client()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3',\n",
-       " 'created_at': '2024-06-21T22:10:27.696862+00:00',\n",
-       " 'updated_at': '2024-06-21T22:10:27.696862+00:00',\n",
-       " 'metadata': {}}"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# create thread\n",
-    "thread = await client.threads.create()\n",
-    "thread"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Streaming debug events produces responses containing `type` and `timestamp` keys. Debug events correspond to different steps in the graph's execution (e.g. `task`, `task_result`, `checkpoint`)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Receiving new event of type: metadata...\n",
-      "{'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.256850+00:00', 'step': -1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a2e-6bb6-bfff-8423bcf47561', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'messages': []}, 'metadata': {'source': 'input', 'step': -1, 'writes': {'messages': [{'role': 'human', 'content': \"What's the weather in SF?\"}]}}}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.259723+00:00', 'step': 0, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a35-6c86-8000-f4a85315dbeb', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}]}, 'metadata': {'source': 'loop', 'step': 0, 'writes': None}}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task', 'timestamp': '2024-06-21T22:11:09.260021+00:00', 'step': 1, 'payload': {'id': '12ab1026-a551-5f96-9ad3-43424f094774', 'name': 'agent', 'input': {'some_bytes': None, 'some_byte_array': None, 'dict_with_bytes': None, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}], 'sleep': None}, 'triggers': ['start:agent']}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task_result', 'timestamp': '2024-06-21T22:11:09.267632+00:00', 'step': 1, 'payload': {'id': '12ab1026-a551-5f96-9ad3-43424f094774', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.268469+00:00', 'step': 1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a4b-60ae-8001-dd378f965bf7', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 1, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task', 'timestamp': '2024-06-21T22:11:09.268659+00:00', 'step': 2, 'payload': {'id': '494ad427-fe8d-5654-91e6-50495a2699f5', 'name': 'tool', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}, 'triggers': ['branch:agent:should_continue:tool']}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task_result', 'timestamp': '2024-06-21T22:11:09.272916+00:00', 'step': 2, 'payload': {'id': '494ad427-fe8d-5654-91e6-50495a2699f5', 'name': 'tool', 'result': [['messages', [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}]]]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.273113+00:00', 'step': 2, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a56-6832-8002-8ab17e662980', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}]}, 'metadata': {'source': 'loop', 'step': 2, 'writes': {'tool': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}]}}}}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task', 'timestamp': '2024-06-21T22:11:09.273192+00:00', 'step': 3, 'payload': {'id': '677de327-99b7-5d97-9bbd-0092abb62d46', 'name': 'agent', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}], 'sleep': None}, 'triggers': ['tool']}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task_result', 'timestamp': '2024-06-21T22:11:09.277262+00:00', 'step': 3, 'payload': {'id': '677de327-99b7-5d97-9bbd-0092abb62d46', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-006e1758-b1ca-4c90-9ff3-d2e75b9ca9a7', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.277519+00:00', 'step': 3, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a61-6462-8003-1316d9875b7f', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-006e1758-b1ca-4c90-9ff3-d2e75b9ca9a7', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 3, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-006e1758-b1ca-4c90-9ff3-d2e75b9ca9a7', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: end...\n",
-      "None\n",
-      "\n",
-      "\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "# create input\n",
-    "input = {\n",
-    "    \"messages\": [\n",
-    "        {\n",
-    "            \"role\": \"human\",\n",
-    "            \"content\": \"What's the weather in SF?\",\n",
-    "        }\n",
-    "    ]\n",
-    "}\n",
-    "\n",
-    "# stream events\n",
-    "async for chunk in client.runs.stream(\n",
-    "    thread_id=thread[\"thread_id\"],\n",
-    "    assistant_id=\"agent\",\n",
-    "    input=input,\n",
-    "    stream_mode=\"debug\",\n",
-    "):\n",
-    "    print(f\"Receiving new event of type: {chunk.event}...\")\n",
-    "    print(chunk.data)\n",
-    "    print(\"\\n\\n\")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "env",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

examples/cloud_examples/stream_events.ipynb

@@ -1,313 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# How to stream events\n",
-    "This guide covers how to stream events from your graph (`stream_mode=\"events\"`). Depending on the use case and user experience of your LangGraph application, your application may process event types differently."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph_sdk import get_client\n",
-    "\n",
-    "client = get_client()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 27,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'thread_id': '3f4c64e0-f792-4a5e-aa07-a4404e06e0bd',\n",
-       " 'created_at': '2024-06-24T22:16:29.301522+00:00',\n",
-       " 'updated_at': '2024-06-24T22:16:29.301522+00:00',\n",
-       " 'metadata': {}}"
-      ]
-     },
-     "execution_count": 27,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# create thread\n",
-    "thread = await client.threads.create()\n",
-    "thread"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Streaming events produces responses containing an `event` key (in addition to other keys such as `data`). See the LangChain [`Runnable.astream_events()` reference](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable.astream_events) for all event types."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Receiving new event of type: metadata...\n",
-      "{'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8'}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_start', 'data': {'input': {'messages': [{'role': 'human', 'content': \"What's the weather in SF?\"}]}}, 'name': 'LangGraph', 'tags': [], 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_start', 'data': {}, 'name': 'agent', 'tags': ['graph:step:6'], 'run_id': '7bb08493-d507-4e28-b9e6-4a5eda9d04f0', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_start', 'data': {'input': {'messages': [[{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}]]}}, 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'b', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'g', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'i', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'n', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_end', 'data': {'output': {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, 'input': {'messages': [[{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}]]}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_start', 'data': {'input': {'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'name': 'should_continue', 'tags': ['seq:step:3'], 'run_id': 'c7fe4d2d-3fb8-4e53-946d-03de13527853', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_end', 'data': {'output': 'tool', 'input': {'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'run_id': 'c7fe4d2d-3fb8-4e53-946d-03de13527853', 'name': 'should_continue', 'tags': ['seq:step:3'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '7bb08493-d507-4e28-b9e6-4a5eda9d04f0', 'name': 'agent', 'tags': ['graph:step:6'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}], 'sleep': None}}, 'run_id': '7bb08493-d507-4e28-b9e6-4a5eda9d04f0', 'name': 'agent', 'tags': ['graph:step:6'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_start', 'data': {}, 'name': 'tool', 'tags': ['graph:step:7'], 'run_id': 'f044fd3d-7271-488f-b8aa-e01572ff9112', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 7, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': 'f044fd3d-7271-488f-b8aa-e01572ff9112', 'name': 'tool', 'tags': ['graph:step:7'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 7, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': None, 'tool_call_id': 'tool_call_id'}]}}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}]}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}}, 'run_id': 'f044fd3d-7271-488f-b8aa-e01572ff9112', 'name': 'tool', 'tags': ['graph:step:7'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 7, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_start', 'data': {}, 'name': 'agent', 'tags': ['graph:step:8'], 'run_id': '1f4f95d0-0ce1-4061-85d4-946446bbd3e5', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_start', 'data': {'input': {'messages': [[{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}]]}}, 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'n', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'd', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_end', 'data': {'output': {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, 'input': {'messages': [[{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}]]}}, 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_start', 'data': {'input': {'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'name': 'should_continue', 'tags': ['seq:step:3'], 'run_id': 'f2b2dfaf-475d-422b-8bf5-02a31bcc7d1a', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_end', 'data': {'output': '__end__', 'input': {'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'run_id': 'f2b2dfaf-475d-422b-8bf5-02a31bcc7d1a', 'name': 'should_continue', 'tags': ['seq:step:3'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1f4f95d0-0ce1-4061-85d4-946446bbd3e5', 'name': 'agent', 'tags': ['graph:step:8'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}], 'sleep': None}}, 'run_id': '1f4f95d0-0ce1-4061-85d4-946446bbd3e5', 'name': 'agent', 'tags': ['graph:step:8'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_end', 'data': {'output': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}, 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'name': 'LangGraph', 'tags': [], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: end...\n",
-      "None\n",
-      "\n",
-      "\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "# create input\n",
-    "input = {\n",
-    "    \"messages\": [\n",
-    "        {\n",
-    "            \"role\": \"human\",\n",
-    "            \"content\": \"What's the weather in SF?\",\n",
-    "        }\n",
-    "    ]\n",
-    "}\n",
-    "\n",
-    "# stream events\n",
-    "async for chunk in client.runs.stream(\n",
-    "    thread_id=thread[\"thread_id\"],\n",
-    "    assistant_id=\"agent\",\n",
-    "    input=input,\n",
-    "    stream_mode=\"events\",\n",
-    "):\n",
-    "    print(f\"Receiving new event of type: {chunk.event}...\")\n",
-    "    print(chunk.data)\n",
-    "    print(\"\\n\\n\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Token-by-Token Streaming\n",
-    "\n",
-    "Token-by-token streaming can be implemented with the `events` streaming mode. The `on_chat_model_stream` event type should be processed to stream LLM responses token-by-token."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 28,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "b\n",
-      "be\n",
-      "beg\n",
-      "begi\n",
-      "begin\n",
-      "begine\n",
-      "beginen\n",
-      "beginend\n"
-     ]
-    }
-   ],
-   "source": [
-    "# create input\n",
-    "input = {\n",
-    "    \"messages\": [\n",
-    "        {\n",
-    "            \"role\": \"human\",\n",
-    "            \"content\": \"What's the weather in SF?\",\n",
-    "        }\n",
-    "    ]\n",
-    "}\n",
-    "\n",
-    "llm_response = \"\"\n",
-    "\n",
-    "# stream token-by-token\n",
-    "async for chunk in client.runs.stream(\n",
-    "    thread_id=thread[\"thread_id\"],\n",
-    "    assistant_id=\"agent\",\n",
-    "    input=input,\n",
-    "    stream_mode=\"events\",\n",
-    "):\n",
-    "    if (\n",
-    "        chunk.event == \"events\" and\n",
-    "        chunk.data[\"event\"] == \"on_chat_model_stream\"\n",
-    "    ):\n",
-    "        llm_response += chunk.data[\"data\"][\"chunk\"][\"content\"]\n",
-    "        print(llm_response)"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "env",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

examples/cloud_examples/stream_messages.ipynb

@@ -1,397 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "51466c8d-8ce4-4b3d-be4e-18fdbeda5f53",
-   "metadata": {},
-   "source": [
-    "# How to stream messages from your graph\n",
-    "\n",
-    "LangGraph Cloud supports multiple streaming modes. The main ones are:\n",
-    "\n",
-    "- `values`: This streaming mode streams back values of the graph. This is the **full state of the graph** after each node is called.\n",
-    "- `updates`: This streaming mode streams back updates to the graph. This is the **update to the state of the graph** after each node is called.\n",
-    "- `messages`: This streaming mode streams back messages - both complete messages (at the end of a node) as well as **tokens** for any messages generated inside a node. This mode is primarily meant for powering chat applications.\n",
-    "\n",
-    "\n",
-    "This guide covers `stream_mode=\"messages\"`.\n",
-    "\n",
-    "In order to use this mode, the state of the graph you are interacting with MUST have a messages key that is a list of messages.\n",
-    "Eg, the state should look something like:\n",
-    "\n",
-    "```python\n",
-    "from typing import TypedDict, Annotated\n",
-    "from langgraph.graph import add_messages\n",
-    "from langchain_core.messages import AnyMessage\n",
-    "\n",
-    "class State(TypedDict):\n",
-    "    messages: Annotated[list[AnyMessage], add_messages]\n",
-    "```\n",
-    "\n",
-    "OR it should be an instance or subclass of `from langgraph.graph import MessageState` (`MessageState` is just a helper type hint equivalent to the above).\n",
-    "\n",
-    "With `stream_mode=\"messages\"` two things will be streamed back:\n",
-    "\n",
-    "- It outputs messages produced by any chat model called inside (unless tagged in a special way)\n",
-    "- It outputs messages returned from nodes (to allow for nodes to return `ToolMessages` and the like"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "521d975b-e94b-4c37-bfa1-82d969e2a4dc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph_sdk import get_client"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "27a1392b-86c3-464e-99a8-90ffc965f3ec",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "client = get_client()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "714e9f92-86b4-4cd8-9d68-cfc45d56ed2c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "assistant_id = \"agent\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "56aa5159-5583-4134-9210-709b969bda6f",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'thread_id': 'e1431c95-e241-4d1d-a252-27eceb1e5c86',\n",
-       " 'created_at': '2024-06-21T15:48:59.808924+00:00',\n",
-       " 'updated_at': '2024-06-21T15:48:59.808924+00:00',\n",
-       " 'metadata': {}}"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "thread = await client.threads.create()\n",
-    "thread"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "147c3f98-f889-4f05-a090-6b31f2a0b291",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[]"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "runs = await client.runs.list(thread[\"thread_id\"])\n",
-    "runs"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "040795c6-5d9f-4729-9132-f3b0f94d9e94",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Helper function for formatting messages\n",
-    "\n",
-    "\n",
-    "def format_tool_calls(tool_calls):\n",
-    "    if tool_calls:\n",
-    "        formatted_calls = []\n",
-    "        for call in tool_calls:\n",
-    "            formatted_calls.append(\n",
-    "                f\"Tool Call ID: {call['id']}, Function: {call['name']}, Arguments: {call['args']}\"\n",
-    "            )\n",
-    "        return \"\\n\".join(formatted_calls)\n",
-    "    return \"No tool calls\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "7da70e20-1a4e-4df2-b996-1927f474c835",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Metadata: Run ID - 1ef2fe5c-6a1d-6575-bc09-d7832711c17e\n",
-      "--------------------------------------------------\n",
-      "Invalid Tool Calls:\n",
-      "Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: \n",
-      "--------------------------------------------------\n",
-      "Tool Calls:\n",
-      "Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {}\n",
-      "--------------------------------------------------\n",
-      "Tool Calls:\n",
-      "Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {}\n",
-      "--------------------------------------------------\n",
-      "Tool Calls:\n",
-      "Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': ''}\n",
-      "--------------------------------------------------\n",
-      "Tool Calls:\n",
-      "Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current'}\n",
-      "--------------------------------------------------\n",
-      "Tool Calls:\n",
-      "Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather'}\n",
-      "--------------------------------------------------\n",
-      "Tool Calls:\n",
-      "Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in'}\n",
-      "--------------------------------------------------\n",
-      "Tool Calls:\n",
-      "Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in San'}\n",
-      "--------------------------------------------------\n",
-      "Tool Calls:\n",
-      "Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in San Francisco'}\n",
-      "--------------------------------------------------\n",
-      "Tool Calls:\n",
-      "Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in San Francisco'}\n",
-      "--------------------------------------------------\n",
-      "Tool Calls:\n",
-      "Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in San Francisco'}\n",
-      "Response Metadata: Finish Reason - tool_calls\n",
-      "--------------------------------------------------\n",
-      "--------------------------------------------------\n",
-      "AI: The\n",
-      "--------------------------------------------------\n",
-      "AI: The current\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is over\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of \n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F).\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-s\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-south\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at \n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 k\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph).\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at \n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%,\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is \n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles).\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is \n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is 3\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is 3.\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is 3.\n",
-      "Response Metadata: Finish Reason - stop\n",
-      "--------------------------------------------------\n"
-     ]
-    }
-   ],
-   "source": [
-    "input = {\"messages\": [{\"role\": \"user\", \"content\": \"what's the weather in sf\"}]}\n",
-    "config = {\"configurable\": {\"model_name\": \"openai\"}}\n",
-    "\n",
-    "async for event in client.runs.stream(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant_id,\n",
-    "    input=input,\n",
-    "    config=config,\n",
-    "    stream_mode=\"messages\",\n",
-    "):\n",
-    "    if event.event == \"metadata\":\n",
-    "        print(f\"Metadata: Run ID - {event.data['run_id']}\")\n",
-    "        print(\"-\" * 50)\n",
-    "    elif event.event == \"messages/partial\":\n",
-    "        for data_item in event.data:\n",
-    "            if \"role\" in data_item and data_item[\"role\"] == \"user\":\n",
-    "                print(f\"Human: {data_item['content']}\")\n",
-    "            else:\n",
-    "                tool_calls = data_item.get(\"tool_calls\", [])\n",
-    "                invalid_tool_calls = data_item.get(\"invalid_tool_calls\", [])\n",
-    "                content = data_item.get(\"content\", \"\")\n",
-    "                response_metadata = data_item.get(\"response_metadata\", {})\n",
-    "\n",
-    "                if content:\n",
-    "                    print(f\"AI: {content}\")\n",
-    "\n",
-    "                if tool_calls:\n",
-    "                    print(\"Tool Calls:\")\n",
-    "                    print(format_tool_calls(tool_calls))\n",
-    "\n",
-    "                if invalid_tool_calls:\n",
-    "                    print(\"Invalid Tool Calls:\")\n",
-    "                    print(format_tool_calls(invalid_tool_calls))\n",
-    "\n",
-    "                if response_metadata:\n",
-    "                    finish_reason = response_metadata.get(\"finish_reason\", \"N/A\")\n",
-    "                    print(f\"Response Metadata: Finish Reason - {finish_reason}\")\n",
-    "        print(\"-\" * 50)"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "langgraph-example-dev",
-   "language": "python",
-   "name": "langgraph-example-dev"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

examples/cloud_examples/stream_multiple.ipynb

@@ -1,457 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# How to configure multiple streaming modes at the same time\n",
-    "\n",
-    "This guide covers how to configure multiple streaming modes at the same time."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph_sdk import get_client\n",
-    "\n",
-    "client = get_client()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4',\n",
-       " 'created_at': '2024-06-24T21:30:07.980789+00:00',\n",
-       " 'updated_at': '2024-06-24T21:30:07.980789+00:00',\n",
-       " 'metadata': {}}"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# create thread\n",
-    "thread = await client.threads.create()\n",
-    "thread"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "When configuring multiple streaming modes for a run, responses for each respective mode will be produced. In the following example, note that a `list` of modes (`messages`, `events`, `debug`) is passed to the `stream_mode` parameter and the response contains `events`, `debug`, `messages/complete`, `messages/metadata`, and `messages/partial` event types."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Receiving new event of type: metadata...\n",
-      "{'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_start', 'data': {'input': {'messages': [{'role': 'human', 'content': \"What's the weather in SF?\"}]}}, 'name': 'LangGraph', 'tags': [], 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.116009+00:00', 'step': -1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc7c-6daa-bfff-6b9027c1a50e', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'messages': []}, 'metadata': {'source': 'input', 'step': -1, 'writes': {'messages': [{'role': 'human', 'content': \"What's the weather in SF?\"}]}}}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.116009+00:00', 'step': -1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc7c-6daa-bfff-6b9027c1a50e', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'messages': []}, 'metadata': {'source': 'input', 'step': -1, 'writes': {'messages': [{'role': 'human', 'content': \"What's the weather in SF?\"}]}}}}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['values', {'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/complete...\n",
-      "[{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.117924+00:00', 'step': 0, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc81-68c8-8000-4e18ae7d67a5', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]}, 'metadata': {'source': 'loop', 'step': 0, 'writes': None}}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.117924+00:00', 'step': 0, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc81-68c8-8000-4e18ae7d67a5', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]}, 'metadata': {'source': 'loop', 'step': 0, 'writes': None}}}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task', 'timestamp': '2024-06-24T21:34:06.118042+00:00', 'step': 1, 'payload': {'id': '212ed9c2-a454-50c5-a202-12066bbbe7b8', 'name': 'agent', 'input': {'some_bytes': None, 'some_byte_array': None, 'dict_with_bytes': None, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}], 'sleep': None}, 'triggers': ['start:agent']}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task', 'timestamp': '2024-06-24T21:34:06.118042+00:00', 'step': 1, 'payload': {'id': '212ed9c2-a454-50c5-a202-12066bbbe7b8', 'name': 'agent', 'input': {'some_bytes': None, 'some_byte_array': None, 'dict_with_bytes': None, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}], 'sleep': None}, 'triggers': ['start:agent']}}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_start', 'data': {}, 'name': 'agent', 'tags': ['graph:step:1'], 'run_id': '72b74d24-5792-48da-a887-102100d6e2c0', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_start', 'data': {'input': {'messages': [[{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]]}}, 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'b', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/metadata...\n",
-      "{'run-2424dd6d-5cf5-4244-8d98-357640ce6e12': {'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/partial...\n",
-      "[{'content': 'b', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/partial...\n",
-      "[{'content': 'be', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'g', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/partial...\n",
-      "[{'content': 'beg', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'i', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/partial...\n",
-      "[{'content': 'begi', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'n', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/partial...\n",
-      "[{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_end', 'data': {'output': {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, 'input': {'messages': [[{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]]}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_start', 'data': {'input': {'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'name': 'should_continue', 'tags': ['seq:step:3'], 'run_id': '227afb0f-f909-4d54-a042-556ca6d98a69', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_end', 'data': {'output': 'tool', 'input': {'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'run_id': '227afb0f-f909-4d54-a042-556ca6d98a69', 'name': 'should_continue', 'tags': ['seq:step:3'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '72b74d24-5792-48da-a887-102100d6e2c0', 'name': 'agent', 'tags': ['graph:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}, 'input': {'some_bytes': None, 'some_byte_array': None, 'dict_with_bytes': None, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}], 'sleep': None}}, 'run_id': '72b74d24-5792-48da-a887-102100d6e2c0', 'name': 'agent', 'tags': ['graph:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.124350+00:00', 'step': 1, 'payload': {'id': '212ed9c2-a454-50c5-a202-12066bbbe7b8', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.124350+00:00', 'step': 1, 'payload': {'id': '212ed9c2-a454-50c5-a202-12066bbbe7b8', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['values', {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/complete...\n",
-      "[{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.124510+00:00', 'step': 1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc91-6a34-8001-26353c117c25', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 1, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.124510+00:00', 'step': 1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc91-6a34-8001-26353c117c25', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 1, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task', 'timestamp': '2024-06-24T21:34:06.124572+00:00', 'step': 2, 'payload': {'id': '44139125-a1be-57c2-9cb2-19eb62bbaf2f', 'name': 'tool', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}, 'triggers': ['branch:agent:should_continue:tool']}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task', 'timestamp': '2024-06-24T21:34:06.124572+00:00', 'step': 2, 'payload': {'id': '44139125-a1be-57c2-9cb2-19eb62bbaf2f', 'name': 'tool', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}, 'triggers': ['branch:agent:should_continue:tool']}}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_start', 'data': {}, 'name': 'tool', 'tags': ['graph:step:2'], 'run_id': '91575720-886e-485e-ae2d-d6817e5346bf', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 2, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '91575720-886e-485e-ae2d-d6817e5346bf', 'name': 'tool', 'tags': ['graph:step:2'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 2, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': None, 'tool_call_id': 'tool_call_id'}]}}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}}, 'run_id': '91575720-886e-485e-ae2d-d6817e5346bf', 'name': 'tool', 'tags': ['graph:step:2'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 2, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.126828+00:00', 'step': 2, 'payload': {'id': '44139125-a1be-57c2-9cb2-19eb62bbaf2f', 'name': 'tool', 'result': [['messages', [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]]]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.126828+00:00', 'step': 2, 'payload': {'id': '44139125-a1be-57c2-9cb2-19eb62bbaf2f', 'name': 'tool', 'result': [['messages', [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]]]}}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['values', {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/complete...\n",
-      "[{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.126966+00:00', 'step': 2, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc97-6a06-8002-8e9ffc1ea75a', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}, 'metadata': {'source': 'loop', 'step': 2, 'writes': {'tool': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}}}}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.126966+00:00', 'step': 2, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc97-6a06-8002-8e9ffc1ea75a', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}, 'metadata': {'source': 'loop', 'step': 2, 'writes': {'tool': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}}}}}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task', 'timestamp': '2024-06-24T21:34:06.127034+00:00', 'step': 3, 'payload': {'id': 'f1ccf371-63b3-5268-a837-7f360a93c4ec', 'name': 'agent', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}], 'sleep': None}, 'triggers': ['tool']}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task', 'timestamp': '2024-06-24T21:34:06.127034+00:00', 'step': 3, 'payload': {'id': 'f1ccf371-63b3-5268-a837-7f360a93c4ec', 'name': 'agent', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}], 'sleep': None}, 'triggers': ['tool']}}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_start', 'data': {}, 'name': 'agent', 'tags': ['graph:step:3'], 'run_id': 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_start', 'data': {'input': {'messages': [[{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]]}}, 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/metadata...\n",
-      "{'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575': {'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/partial...\n",
-      "[{'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'n', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/partial...\n",
-      "[{'content': 'en', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'd', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/partial...\n",
-      "[{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_end', 'data': {'output': {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, 'input': {'messages': [[{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]]}}, 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_start', 'data': {'input': {'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'name': 'should_continue', 'tags': ['seq:step:3'], 'run_id': '8af814e9-8136-4aab-acbc-dffc5bcafdfd', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_end', 'data': {'output': '__end__', 'input': {'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'run_id': '8af814e9-8136-4aab-acbc-dffc5bcafdfd', 'name': 'should_continue', 'tags': ['seq:step:3'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e', 'name': 'agent', 'tags': ['graph:step:3'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}], 'sleep': None}}, 'run_id': 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e', 'name': 'agent', 'tags': ['graph:step:3'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.133991+00:00', 'step': 3, 'payload': {'id': 'f1ccf371-63b3-5268-a837-7f360a93c4ec', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.133991+00:00', 'step': 3, 'payload': {'id': 'f1ccf371-63b3-5268-a837-7f360a93c4ec', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['values', {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/complete...\n",
-      "[{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.134190+00:00', 'step': 3, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bca9-6418-8003-8d0d0b06845c', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 3, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.134190+00:00', 'step': 3, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bca9-6418-8003-8d0d0b06845c', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 3, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_end', 'data': {'output': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: end...\n",
-      "None\n",
-      "\n",
-      "\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "# create input\n",
-    "input = {\n",
-    "    \"messages\": [\n",
-    "        {\n",
-    "            \"role\": \"human\",\n",
-    "            \"content\": \"What's the weather in SF?\",\n",
-    "        }\n",
-    "    ]\n",
-    "}\n",
-    "\n",
-    "# stream events with multiple streaming modes\n",
-    "async for chunk in client.runs.stream(\n",
-    "    thread_id=thread[\"thread_id\"],\n",
-    "    assistant_id=\"agent\",\n",
-    "    input=input,\n",
-    "    stream_mode=[\"messages\", \"events\", \"debug\"],\n",
-    "):\n",
-    "    print(f\"Receiving new event of type: {chunk.event}...\")\n",
-    "    print(chunk.data)\n",
-    "    print(\"\\n\\n\")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "env",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

examples/cloud_examples/stream_updates.ipynb

@@ -1,178 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "51466c8d-8ce4-4b3d-be4e-18fdbeda5f53",
-   "metadata": {},
-   "source": [
-    "# How to stream state updates of your graph\n",
-    "\n",
-    "LangGraph Cloud supports multiple streaming modes. The main ones are:\n",
-    "\n",
-    "- `values`: This streaming mode streams back values of the graph. This is the **full state of the graph** after each node is called.\n",
-    "- `updates`: This streaming mode streams back updates to the graph. This is the **update to the state of the graph** after each node is called.\n",
-    "- `messages`: This streaming mode streams back messages - both complete messages (at the end of a node) as well as **tokens** for any messages generated inside a node. This mode is primarily meant for powering chat applications.\n",
-    "\n",
-    "\n",
-    "This guide covers `stream_mode=\"updates\"`."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "521d975b-e94b-4c37-bfa1-82d969e2a4dc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph_sdk import get_client"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "27a1392b-86c3-464e-99a8-90ffc965f3ec",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "client = get_client()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "230c0464-a6e5-420f-9e38-ca514e5634ce",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "assistant_id = \"agent\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "56aa5159-5583-4134-9210-709b969bda6f",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'thread_id': '979e3c89-a702-4882-87c2-7a59a250ce16',\n",
-       " 'created_at': '2024-06-21T15:22:07.453100+00:00',\n",
-       " 'updated_at': '2024-06-21T15:22:07.453100+00:00',\n",
-       " 'metadata': {}}"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "thread = await client.threads.create()\n",
-    "thread"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "147c3f98-f889-4f05-a090-6b31f2a0b291",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[]"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "runs = await client.runs.list(thread[\"thread_id\"])\n",
-    "runs"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "7da70e20-1a4e-4df2-b996-1927f474c835",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Receiving new event of type: metadata...\n",
-      "{'run_id': 'cfc96c16-ed9a-44bd-b5bb-c30e3c0725f0'}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: data...\n",
-      "{'agent': {'messages': [{'content': [{'id': 'toolu_0148tMmDK51iLQfG1yaNwRHM', 'input': {'query': 'weather in los angeles'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-1a9d32b0-7007-4a36-abde-8df812a0ed94', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in los angeles'}, 'id': 'toolu_0148tMmDK51iLQfG1yaNwRHM'}], 'invalid_tool_calls': []}]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: data...\n",
-      "{'action': {'messages': [{'content': '[{\"url\": \"https://www.weatherapi.com/\", \"content\": \"{\\'location\\': {\\'name\\': \\'Los Angeles\\', \\'region\\': \\'California\\', \\'country\\': \\'United States of America\\', \\'lat\\': 34.05, \\'lon\\': -118.24, \\'tz_id\\': \\'America/Los_Angeles\\', \\'localtime_epoch\\': 1716062239, \\'localtime\\': \\'2024-05-18 12:57\\'}, \\'current\\': {\\'last_updated_epoch\\': 1716061500, \\'last_updated\\': \\'2024-05-18 12:45\\', \\'temp_c\\': 18.9, \\'temp_f\\': 66.0, \\'is_day\\': 1, \\'condition\\': {\\'text\\': \\'Overcast\\', \\'icon\\': \\'//cdn.weatherapi.com/weather/64x64/day/122.png\\', \\'code\\': 1009}, \\'wind_mph\\': 2.2, \\'wind_kph\\': 3.6, \\'wind_degree\\': 10, \\'wind_dir\\': \\'N\\', \\'pressure_mb\\': 1017.0, \\'pressure_in\\': 30.02, \\'precip_mm\\': 0.0, \\'precip_in\\': 0.0, \\'humidity\\': 65, \\'cloud\\': 100, \\'feelslike_c\\': 18.9, \\'feelslike_f\\': 66.0, \\'vis_km\\': 16.0, \\'vis_miles\\': 9.0, \\'uv\\': 6.0, \\'gust_mph\\': 7.5, \\'gust_kph\\': 12.0}}\"}]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'tavily_search_results_json', 'id': 'a36e8cd1-0e96-4417-9c15-f10a945d2b42', 'tool_call_id': 'toolu_0148tMmDK51iLQfG1yaNwRHM'}]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: data...\n",
-      "{'agent': {'messages': [{'content': 'The weather in Los Angeles is currently overcast with a temperature of around 66°F (18.9°C). There are light winds from the north at around 2-3 mph. The humidity is 65% and visibility is good at 9 miles. Overall, mild spring weather conditions in LA.', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-d5c1c2f0-b12d-41ce-990b-f36570e7483d', 'example': False, 'tool_calls': [], 'invalid_tool_calls': []}]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: end...\n",
-      "None\n",
-      "\n",
-      "\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "input = {\"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in la\"}]}\n",
-    "async for chunk in client.runs.stream(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant_id,\n",
-    "    input=input,\n",
-    "    stream_mode=\"updates\",\n",
-    "):\n",
-    "    print(f\"Receiving new event of type: {chunk.event}...\")\n",
-    "    print(chunk.data)\n",
-    "    print(\"\\n\\n\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "53800469-354a-4739-8e77-b88044c772d5",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.12.3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

examples/cloud_examples/stream_values.ipynb

@@ -1,212 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "51466c8d-8ce4-4b3d-be4e-18fdbeda5f53",
-   "metadata": {},
-   "source": [
-    "# How to stream full state of your graph\n",
-    "\n",
-    "LangGraph Cloud supports multiple streaming modes. The main ones are:\n",
-    "\n",
-    "- `values`: This streaming mode streams back values of the graph. This is the **full state of the graph** after each node is called.\n",
-    "- `updates`: This streaming mode streams back updates to the graph. This is the **update to the state of the graph** after each node is called.\n",
-    "- `messages`: This streaming mode streams back messages - both complete messages (at the end of a node) as well as **tokens** for any messages generated inside a node. This mode is primarily meant for powering chat applications.\n",
-    "\n",
-    "\n",
-    "This guide covers `stream_mode=\"values\"`."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "521d975b-e94b-4c37-bfa1-82d969e2a4dc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph_sdk import get_client"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "27a1392b-86c3-464e-99a8-90ffc965f3ec",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "client = get_client()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "230c0464-a6e5-420f-9e38-ca514e5634ce",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "assistant_id = \"agent\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "7da70e20-1a4e-4df2-b996-1927f474c835",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Receiving new event of type: metadata...\n",
-      "{'run_id': 'f08791ce-0a3d-44e0-836c-ff62cd2e2786'}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: values...\n",
-      "{'messages': [{'role': 'human', 'content': 'what's the weather in la'}]}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: values...\n",
-      "{'messages': [{'content': 'what's the weather in la', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'faa15565-8823-4aa1-87af-e21b40526fae', 'example': False}, {'content': [{'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g', 'input': {'query': 'weather in los angeles'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-3fe1db7a-6b8d-4d83-ba07-8657190ad811', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in los angeles'}, 'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}], 'invalid_tool_calls': []}]}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: values...\n",
-      "{'messages': [{'content': 'what's the weather in la', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'faa15565-8823-4aa1-87af-e21b40526fae', 'example': False}, {'content': [{'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g', 'input': {'query': 'weather in los angeles'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-3fe1db7a-6b8d-4d83-ba07-8657190ad811', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in los angeles'}, 'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}], 'invalid_tool_calls': []}, {'content': '[{\"url\": \"https://www.weatherapi.com/\", \"content\": \"{\\'location\\': {\\'name\\': \\'Los Angeles\\', \\'region\\': \\'California\\', \\'country\\': \\'United States of America\\', \\'lat\\': 34.05, \\'lon\\': -118.24, \\'tz_id\\': \\'America/Los_Angeles\\', \\'localtime_epoch\\': 1716310320, \\'localtime\\': \\'2024-05-21 9:52\\'}, \\'current\\': {\\'last_updated_epoch\\': 1716309900, \\'last_updated\\': \\'2024-05-21 09:45\\', \\'temp_c\\': 16.7, \\'temp_f\\': 62.1, \\'is_day\\': 1, \\'condition\\': {\\'text\\': \\'Overcast\\', \\'icon\\': \\'//cdn.weatherapi.com/weather/64x64/day/122.png\\', \\'code\\': 1009}, \\'wind_mph\\': 8.1, \\'wind_kph\\': 13.0, \\'wind_degree\\': 250, \\'wind_dir\\': \\'WSW\\', \\'pressure_mb\\': 1015.0, \\'pressure_in\\': 29.97, \\'precip_mm\\': 0.0, \\'precip_in\\': 0.0, \\'humidity\\': 65, \\'cloud\\': 100, \\'feelslike_c\\': 16.7, \\'feelslike_f\\': 62.1, \\'vis_km\\': 16.0, \\'vis_miles\\': 9.0, \\'uv\\': 5.0, \\'gust_mph\\': 12.5, \\'gust_kph\\': 20.2}}\"}]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'tavily_search_results_json', 'id': '0d5dab31-5ff8-4ae2-a560-bc4bcba7c9d7', 'tool_call_id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}]}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: values...\n",
-      "{'messages': [{'content': 'what's the weather in la', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'faa15565-8823-4aa1-87af-e21b40526fae', 'example': False}, {'content': [{'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g', 'input': {'query': 'weather in los angeles'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-3fe1db7a-6b8d-4d83-ba07-8657190ad811', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in los angeles'}, 'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}], 'invalid_tool_calls': []}, {'content': '[{\"url\": \"https://www.weatherapi.com/\", \"content\": \"{\\'location\\': {\\'name\\': \\'Los Angeles\\', \\'region\\': \\'California\\', \\'country\\': \\'United States of America\\', \\'lat\\': 34.05, \\'lon\\': -118.24, \\'tz_id\\': \\'America/Los_Angeles\\', \\'localtime_epoch\\': 1716310320, \\'localtime\\': \\'2024-05-21 9:52\\'}, \\'current\\': {\\'last_updated_epoch\\': 1716309900, \\'last_updated\\': \\'2024-05-21 09:45\\', \\'temp_c\\': 16.7, \\'temp_f\\': 62.1, \\'is_day\\': 1, \\'condition\\': {\\'text\\': \\'Overcast\\', \\'icon\\': \\'//cdn.weatherapi.com/weather/64x64/day/122.png\\', \\'code\\': 1009}, \\'wind_mph\\': 8.1, \\'wind_kph\\': 13.0, \\'wind_degree\\': 250, \\'wind_dir\\': \\'WSW\\', \\'pressure_mb\\': 1015.0, \\'pressure_in\\': 29.97, \\'precip_mm\\': 0.0, \\'precip_in\\': 0.0, \\'humidity\\': 65, \\'cloud\\': 100, \\'feelslike_c\\': 16.7, \\'feelslike_f\\': 62.1, \\'vis_km\\': 16.0, \\'vis_miles\\': 9.0, \\'uv\\': 5.0, \\'gust_mph\\': 12.5, \\'gust_kph\\': 20.2}}\"}]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'tavily_search_results_json', 'id': '0d5dab31-5ff8-4ae2-a560-bc4bcba7c9d7', 'tool_call_id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}, {'content': 'Based on the weather API results, the current weather in Los Angeles is overcast with a temperature of around 62°F (17°C). There are light winds from the west-southwest around 8-13 mph. The humidity is 65% and visibility is good at 9 miles. Overall, mild spring weather conditions in LA.', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-4d6d4c23-5aad-4042-b0d9-19407a9e08e3', 'example': False, 'tool_calls': [], 'invalid_tool_calls': []}]}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: end...\n",
-      "None\n",
-      "\n",
-      "\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "input = {\"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in la\"}]}\n",
-    "thread = await client.threads.create()\n",
-    "async for chunk in client.runs.stream(thread[\"thread_id\"], assistant_id, input=input):\n",
-    "    print(f\"Receiving new event of type: {chunk.event}...\")\n",
-    "    print(chunk.data)\n",
-    "    print(\"\\n\\n\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "43e4432d-e96c-4ae4-8085-866fb57bbcb3",
-   "metadata": {},
-   "source": [
-    "If we want to just get the final result, we can use this endpoint and just keep track of the last value we received"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "d2560481-d161-4d4f-b385-4977696c4aa1",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "input = {\"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in la\"}]}\n",
-    "thread = await client.threads.create()\n",
-    "final_answer = None\n",
-    "async for chunk in client.runs.stream(thread[\"thread_id\"], assistant_id, input=input):\n",
-    "    if chunk.event == \"values\":\n",
-    "        final_answer = chunk.data"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "9c2d60ea-450f-45cd-b867-0cbb162528f6",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'messages': [{'content': 'what's the weather in la',\n",
-       "   'additional_kwargs': {},\n",
-       "   'response_metadata': {},\n",
-       "   'type': 'human',\n",
-       "   'name': None,\n",
-       "   'id': 'e78c2f94-d810-42fc-a399-11f6bb1b1092',\n",
-       "   'example': False},\n",
-       "  {'content': [{'id': 'toolu_01SBMoAGr4U9x3ibztm2UUom',\n",
-       "     'input': {'query': 'weather in los angeles'},\n",
-       "     'name': 'tavily_search_results_json',\n",
-       "     'type': 'tool_use'}],\n",
-       "   'additional_kwargs': {},\n",
-       "   'response_metadata': {},\n",
-       "   'type': 'ai',\n",
-       "   'name': None,\n",
-       "   'id': 'run-80767ab8-09fc-40ec-9e45-657ddef5e0b1',\n",
-       "   'example': False,\n",
-       "   'tool_calls': [{'name': 'tavily_search_results_json',\n",
-       "     'args': {'query': 'weather in los angeles'},\n",
-       "     'id': 'toolu_01SBMoAGr4U9x3ibztm2UUom'}],\n",
-       "   'invalid_tool_calls': []},\n",
-       "  {'content': '[{\"url\": \"https://www.weatherapi.com/\", \"content\": \"{\\'location\\': {\\'name\\': \\'Los Angeles\\', \\'region\\': \\'California\\', \\'country\\': \\'United States of America\\', \\'lat\\': 34.05, \\'lon\\': -118.24, \\'tz_id\\': \\'America/Los_Angeles\\', \\'localtime_epoch\\': 1716310320, \\'localtime\\': \\'2024-05-21 9:52\\'}, \\'current\\': {\\'last_updated_epoch\\': 1716309900, \\'last_updated\\': \\'2024-05-21 09:45\\', \\'temp_c\\': 16.7, \\'temp_f\\': 62.1, \\'is_day\\': 1, \\'condition\\': {\\'text\\': \\'Overcast\\', \\'icon\\': \\'//cdn.weatherapi.com/weather/64x64/day/122.png\\', \\'code\\': 1009}, \\'wind_mph\\': 8.1, \\'wind_kph\\': 13.0, \\'wind_degree\\': 250, \\'wind_dir\\': \\'WSW\\', \\'pressure_mb\\': 1015.0, \\'pressure_in\\': 29.97, \\'precip_mm\\': 0.0, \\'precip_in\\': 0.0, \\'humidity\\': 65, \\'cloud\\': 100, \\'feelslike_c\\': 16.7, \\'feelslike_f\\': 62.1, \\'vis_km\\': 16.0, \\'vis_miles\\': 9.0, \\'uv\\': 5.0, \\'gust_mph\\': 12.5, \\'gust_kph\\': 20.2}}\"}]',\n",
-       "   'additional_kwargs': {},\n",
-       "   'response_metadata': {},\n",
-       "   'type': 'tool',\n",
-       "   'name': 'tavily_search_results_json',\n",
-       "   'id': 'af25e94a-c119-48c3-bbd3-096e42f472ac',\n",
-       "   'tool_call_id': 'toolu_01SBMoAGr4U9x3ibztm2UUom'},\n",
-       "  {'content': 'Based on the weather API results, the current weather in Los Angeles is overcast with a temperature of around 62°F (17°C). There are light winds from the west-southwest around 8-13 mph. The humidity is 65% and visibility is good at 9 miles. Overall, mild spring weather conditions in LA.',\n",
-       "   'additional_kwargs': {},\n",
-       "   'response_metadata': {},\n",
-       "   'type': 'ai',\n",
-       "   'name': None,\n",
-       "   'id': 'run-b90f0037-e56a-4f3b-ad92-00d10d079a9e',\n",
-       "   'example': False,\n",
-       "   'tool_calls': [],\n",
-       "   'invalid_tool_calls': []}]}"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "final_answer"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "39cedbff-0a7f-4a3e-bfc1-595797358769",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.12.3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

examples/cloud_examples/webhooks.ipynb

@@ -0,0 +1,72 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Use Webhooks\n",
+    "\n",
+    "You may wish to use webhooks in your client, especially when using async streams in case you want to update something in your service once the API call to LangGraph Cloud has finished running. To do so, you will need to expose an endpoint that can accept POST requests, and then pass it to your API request in the \"webhook\" parameter.\n",
+    "\n",
+    "Currently, the SDK has not exposed this endpoint but you can access it through curl commands as follows.\n",
+    "\n",
+    "The following endpoints accept `webhook` as a parameter: \n",
+    "\n",
+    "- Create Run -> POST /thread/{thread_id}/runs\n",
+    "- Create Thread Cron -> POST /thread/{thread_id}/runs/crons\n",
+    "- Stream Run -> POST /thread/{thread_id}/runs/stream\n",
+    "- Wait Run -> POST /thread/{thread_id}/runs/wait\n",
+    "- Create Cron -> POST /runs/crons\n",
+    "- Stream Run Stateless -> POST /runs/stream\n",
+    "- Wait Run Stateless -> POST /runs/wait\n",
+    "\n",
+    "The following example uses a url from a public website that allows users to create free webhooks, but you should pass in the webhook that you wish to use. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "curl --request POST \\\n",
+    "  --url http://localhost:8123/threads/b76d1e94-f251-40e3-8933-796d775cdb4c/runs/stream \\\n",
+    "  --header 'Content-Type: application/json' \\\n",
+    "  --data '{\n",
+    "  \"assistant_id\": \"fe096781-5601-53d2-b2f6-0d3403f7e9ca\",\n",
+    "  \"input\" : {\"messages\":[{\"role\": \"user\", \"content\": \"Hello! My name is Bagatur and I am 26 years old.\"}]},\n",
+    "  \"metadata\": {},\n",
+    "  \"config\": {\n",
+    "    \"configurable\": {}\n",
+    "  },\n",
+    "  \"multitask_strategy\": \"reject\",\n",
+    "  \"stream_mode\": [\n",
+    "    \"values\"\n",
+    "  ],\n",
+    " \"webhook\": \"https://webhook.site/6ca33471-dd65-4103-a851-0a252dae0f2a\"\n",
+    "}'"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To check that this worked as intended, we can go to the website where our webhook was created and confirm that it received a POST request:"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "![Webhook response](./img/webhook_results.png)"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}