checkpoint-postgres: release 1.0.0 (#1245 )

checkpoint-sqlite: release 1.0.0 (#1244 )
checkpoint: release 1.0.1 (#1243 )
2026-08-18 05:35:43 +02:00 · 2024-08-06 22:53:29 -04:00 · 2024-08-06 22:43:35 -04:00 · 2024-08-06 22:38:13 -04:00 · 2024-08-06 22:37:06 -04:00 · 2024-08-06 17:15:19 -07:00
360 changed files with 50320 additions and 25795 deletions
@@ -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
        
@@ -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
@@ -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]

@@ -12,6 +12,7 @@ jobs:
    strategy:
      matrix:
        python-version:
+          - "3.10"
          - "3.11"
    name: "CLI integration test"
    defaults:
@@ -19,51 +20,41 @@ jobs:
        working-directory: libs/cli
    steps:
      - uses: actions/checkout@v4
-
+      - name: Get changed files
+        id: changed-files
+        uses: Ana06/get-changed-files@v2.2.0
+        with:
+          filter: "libs/cli/**"
      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        if: steps.changed-files.outputs.all
        uses: "./.github/actions/poetry_setup"
        with:
          python-version: ${{ matrix.python-version }}
          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: libs/cli
          cache-key: integration-test-cli
-
      - name: Setup env
+        if: steps.changed-files.outputs.all
        working-directory: libs/cli/examples
        run: cat .env.example > .env
      - name: Install cli globally
+        if: steps.changed-files.outputs.all
        run: pip install -e .
      - name: Start service A
+        if: steps.changed-files.outputs.all
        run: |
-          langgraph up -c examples/langgraph.json --wait --verbose
-      - name: Stop service A
-        run: |
-          langgraph down -c examples/langgraph.json
-          sudo rm -rf .langgraph-data
+          timeout 60 langgraph test -c examples/langgraph.json --verbose || (exit "$(($? == 124 ? 0 : $?))")
      - name: Start service B
+        if: steps.changed-files.outputs.all
        working-directory: libs/cli/examples/graphs
        run: |
-          langgraph up --wait --verbose
-      - name: Stop service B
-        working-directory: libs/cli/examples/graphs
-        run: |
-          langgraph down
-          sudo rm -rf .langgraph-data
+          timeout 60 langgraph test --verbose || (exit "$(($? == 124 ? 0 : $?))")
      - name: Start service C
+        if: steps.changed-files.outputs.all
        working-directory: libs/cli/examples/graphs_reqs_a
        run: |
-          langgraph up --wait -d compose.yml --verbose
-      - name: Stop service C
-        working-directory: libs/cli/examples/graphs_reqs_a
-        run: |
-          langgraph down
-          sudo rm -rf .langgraph-data
+          timeout 60 langgraph test --verbose || (exit "$(($? == 124 ? 0 : $?))")
      - name: Start service D
+        if: steps.changed-files.outputs.all
        working-directory: libs/cli/examples/graphs_reqs_b
        run: |
-          langgraph up --wait -d compose.yml --verbose
-      - name: Stop service D
-        working-directory: libs/cli/examples/graphs_reqs_b
-        run: |
-          langgraph down
-          sudo rm -rf .langgraph-data
+          timeout 60 langgraph test --verbose || (exit "$(($? == 124 ? 0 : $?))")
@@ -32,8 +32,13 @@ jobs:
    name: "lint #${{ matrix.python-version }}"
    steps:
      - uses: actions/checkout@v4
-
+      - name: Get changed files
+        id: changed-files
+        uses: Ana06/get-changed-files@v2.2.0
+        with:
+          filter: "${{ inputs.working-directory }}/**"
      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        if: steps.changed-files.outputs.all
        uses: "./.github/actions/poetry_setup"
        with:
          python-version: ${{ matrix.python-version }}
@@ -42,16 +47,19 @@ jobs:
          cache-key: lint-with-extras

      - name: Check Poetry File
+        if: steps.changed-files.outputs.all
        shell: bash
        working-directory: ${{ inputs.working-directory }}
        run: poetry check

      - name: Check lock file
+        if: steps.changed-files.outputs.all
        shell: bash
        working-directory: ${{ inputs.working-directory }}
        run: poetry lock --check

      - name: Install dependencies
+        if: steps.changed-files.outputs.all
        # Also installs dev/lint/test/typing dependencies, to ensure we have
        # type hints for as many of our libraries as possible.
        # This helps catch errors that require dependencies to be spotted, for example:
@@ -64,6 +72,7 @@ jobs:
        run: poetry install --with dev

      - name: Get .mypy_cache to speed up mypy
+        if: steps.changed-files.outputs.all
        uses: actions/cache@v3
        env:
          SEGMENT_DOWNLOAD_TIMEOUT_MIN: "2"
@@ -73,6 +82,7 @@ jobs:
          key: mypy-lint-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}

      - name: Analysing package code with our lint
+        if: steps.changed-files.outputs.all
        working-directory: ${{ inputs.working-directory }}
        run: |
          if make lint_package > /dev/null 2>&1; then
@@ -83,6 +93,7 @@ jobs:
          fi

      - name: Install test dependencies
+        if: steps.changed-files.outputs.all
        # Also installs dev/lint/test/typing dependencies, to ensure we have
        # type hints for as many of our libraries as possible.
        # This helps catch errors that require dependencies to be spotted, for example:
@@ -96,6 +107,7 @@ jobs:
          poetry install --with dev

      - name: Get .mypy_cache_test to speed up mypy
+        if: steps.changed-files.outputs.all
        uses: actions/cache@v3
        env:
          SEGMENT_DOWNLOAD_TIMEOUT_MIN: "2"
@@ -105,6 +117,7 @@ jobs:
          key: mypy-test-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}

      - name: Analysing tests with our lint
+        if: steps.changed-files.outputs.all
        working-directory: ${{ inputs.working-directory }}
        run: |
          if make lint_tests > /dev/null 2>&1; then
@@ -24,8 +24,13 @@ jobs:
    name: "test #${{ matrix.python-version }}"
    steps:
      - uses: actions/checkout@v4
-
+      - name: Get changed files
+        id: changed-files
+        uses: Ana06/get-changed-files@v2.2.0
+        with:
+          filter: "${{ inputs.working-directory }}/**"
      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        if: steps.changed-files.outputs.all
        uses: "./.github/actions/poetry_setup"
        with:
          python-version: ${{ matrix.python-version }}
@@ -34,17 +39,20 @@ jobs:
          cache-key: core

      - name: Install dependencies
+        if: steps.changed-files.outputs.all
        shell: bash
        working-directory: ${{ inputs.working-directory }}
        run: poetry install --with dev

      - name: Run core tests
+        if: steps.changed-files.outputs.all
        shell: bash
        working-directory: ${{ inputs.working-directory }}
        run: |
          make test

      - name: Ensure the tests did not create any additional files
+        if: steps.changed-files.outputs.all
        shell: bash
        working-directory: ${{ inputs.working-directory }}
        run: |
@@ -36,7 +36,10 @@
            working-directory: [
                "libs/langgraph",
                "libs/sdk-py",
-                "libs/cli"
+                "libs/cli",
+                "libs/checkpoint",
+                "libs/checkpoint-sqlite",
+                "libs/checkpoint-postgres"
            ]
        uses: ./.github/workflows/_lint.yml
        with:
@@ -50,7 +53,10 @@
          matrix:
            working-directory: [
                "libs/langgraph",
-                "libs/cli"
+                "libs/cli",
+                "libs/checkpoint",
+                "libs/checkpoint-sqlite",
+                "libs/checkpoint-postgres"
            ]
        uses: ./.github/workflows/_test.yml
        with:
@@ -36,5 +36,4 @@
              ignore_words_list: ${{ steps.extract_ignore_words.outputs.ignore_words_list }}
          # We do this to avoid spellchecking cell outputs
          - name: Codespell Notebooks
-            run: |
-              find . -name "*.ipynb" | head -n 1 | xargs cat $1 | jupytext --from ipynb --to py:percent | codespell -
+            run: make codespell
@@ -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
@@ -6,7 +6,7 @@ on:
      working-directory:
        required: true
        type: string
-        default: 'libs/langgraph'
+        default: "libs/langgraph"

 env:
  PYTHON_VERSION: "3.11"
@@ -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 "")
+          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"
@@ -129,8 +136,8 @@ jobs:
    needs:
      - build
      - release-notes
-    uses:
-      ./.github/workflows/_test_release.yml
+    permissions: write-all
+    uses: ./.github/workflows/_test_release.yml
    with:
      working-directory: ${{ inputs.working-directory }}
    secrets: inherit
@@ -190,9 +197,15 @@ jobs:
              "$PKG_NAME==$VERSION" \
          )

-          # Replace all dashes in the package name with underscores,
-          # since that's how Python imports packages with dashes in the name.
-          IMPORT_NAME="$(echo "$PKG_NAME" | sed s/-/_/g)"
+          if [[ "$PKG_NAME" == *checkpoint* ]]; then
+            # since checkpoint packages are namespace packages, import them with . convention
+            # i.e. import langgraph.checkpoint or langgraph.checkpoint.sqlite
+            IMPORT_NAME="$(echo "$PKG_NAME" | sed s/-/./g)"
+          else
+            # Replace all dashes in the package name with underscores,
+            # since that's how Python imports packages with dashes in the name.
+            IMPORT_NAME="$(echo "$PKG_NAME" | sed s/-/_/g)"
+          fi

          poetry run python -c "import $IMPORT_NAME; print(dir($IMPORT_NAME))"

@@ -0,0 +1,28 @@
+name: Check File Size
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+  workflow_dispatch:
+
+jobs:
+  file-size-check:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Get changed files
+        id: changed-files
+        uses: tj-actions/changed-files@v44
+      - name: Filter by size
+        run: |
+          large_added_files=$(find ${{ steps.changed-files.outputs.added_files }} -maxdepth 0 -size +1M)
+          if [ -n "$large_added_files" ]; then
+            echo "Large files added: $large_added_files"
+            echo "# Large files added:" >> $GITHUB_STEP_SUMMARY
+            echo "$large_added_files" >> $GITHUB_STEP_SUMMARY
+            exit 1
+          fi
@@ -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
+```
@@ -1,6 +1,14 @@
-.PHONY: build-docs serve-docs serve-clean-docs clean-docs
+.PHONY: build-docs serve-docs serve-clean-docs clean-docs codespell build-typedoc

-build-docs:
+build-typedoc:
+	cd libs/sdk-js && yarn install --include-dev && yarn typedoc
+	cd libs/sdk-js && yarn --silent concat-md --decrease-title-levels --ignore=js_ts_sdk_ref.md --start-title-level-at 2 docs > ../../docs/docs/cloud/reference/sdk/js_ts_sdk_ref.md 2>/dev/null
+	#  Add links to the monorepo
+	sed -e '1,10s|@langchain/langgraph-sdk|[@langchain/langgraph-sdk](https://github.com/langchain-ai/langgraph/tree/main/libs/sdk-js)|g' docs/docs/cloud/reference/sdk/js_ts_sdk_ref.md > temp_file && mv temp_file docs/docs/cloud/reference/sdk/js_ts_sdk_ref.md
+
+
+
+build-docs: build-typedoc
 	poetry run python docs/_scripts/copy_notebooks.py
 	poetry run python -m mkdocs build --clean -f docs/mkdocs.yml --strict

@@ -8,10 +16,13 @@ serve-clean-docs: clean-docs
 	poetry run python docs/_scripts/copy_notebooks.py
 	poetry run python -m mkdocs serve -c -f docs/mkdocs.yml --strict -w ./libs/langgraph

-serve-docs:
+serve-docs: build-typedoc
 	poetry run python docs/_scripts/copy_notebooks.py
 	poetry run python -m mkdocs serve -f docs/mkdocs.yml -w ./libs/langgraph --dirty

 clean-docs:
 	find ./docs/docs -name "*.ipynb" -type f -delete
-	rm -rf docs/site
+	rm -rf docs/site
+
+codespell:
+	./docs/codespell_notebooks.sh .
@@ -3,11 +3,13 @@
 ![Version](https://img.shields.io/pypi/v/langgraph)
 [![Downloads](https://static.pepy.tech/badge/langgraph/month)](https://pepy.tech/project/langgraph)
 [![Open Issues](https://img.shields.io/github/issues-raw/langchain-ai/langgraph)](https://github.com/langchain-ai/langgraph/issues)
-[![](https://dcbadge.vercel.app/api/server/6adMQxSpJS?compact=true&style=flat)](https://discord.com/channels/1038097195422978059/1170024642245832774)
 [![Docs](https://img.shields.io/badge/docs-latest-blue)](https://langchain-ai.github.io/langgraph/)

 ⚡ Building language agents as graphs ⚡

+> [!NOTE]
+> Looking for the JS version? Click [here](https://github.com/langchain-ai/langgraphjs) ([JS docs](https://langchain-ai.github.io/langgraphjs/)).
+
 ## 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.
@@ -33,43 +35,52 @@ 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 langgraph.checkpoint import MemorySaver
+from langchain_anthropic import ChatAnthropic
+from langchain_core.tools import tool
+from langgraph.checkpoint.memory 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
@@ -80,7 +91,7 @@ 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
@@ -129,7 +140,7 @@ 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)
@@ -143,30 +154,34 @@ 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:
+### Step-by-step Breakdown

 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>
    <summary>Initialize graph with state.</summary>

    - we initialize graph (`StateGraph`) by passing state schema (in our case `MessagesState`)
    - `MessagesState` is a prebuilt state schema that has one attribute -- a list of LangChain `Message` objects, as well as logic for merging the updates from each node into the state
   </details>
+
 3. <details>
    <summary>Define graph nodes.</summary>

    There are two main nodes we need:
+
      - The `agent` node: responsible for deciding what (if any) actions to take.
      - The `tools` node that invokes tools: if the agent decides to take an action, this node will then execute that action.
   </details>
+
 4. <details>
    <summary>Define entry point and graph edges.</summary>

@@ -179,12 +194,14 @@ final_state["messages"][-1].content
        - b. Finish (respond to the user) if the agent did not ask to run tools
      - Normal edge: after the tools are invoked, the graph should always return to the agent to decide what to do next
   </details>
+
 5. <details>
    <summary>Compile the graph.</summary>

    - When we compile the graph, we turn it into a LangChain [Runnable](https://python.langchain.com/v0.2/docs/concepts/#runnable-interface), which automatically enables calling `.invoke()`, `.stream()` and `.batch()` with your inputs
    - We can also optionally pass checkpointer object for persisting state between graph runs, and enabling memory, human-in-the-loop workflows, time travel and more. In our case we use `MemorySaver` - a simple in-memory checkpointer
    </details>
+
 6. <details>
   <summary>Execute the graph.</summary>

@@ -192,8 +209,10 @@ final_state["messages"][-1].content
    2. The `"agent"` node executes, invoking the chat model.
    3. The chat model returns an `AIMessage`. LangGraph adds this to the state.
    4. Graph cycles the following steps until there are no more `tool_calls` on `AIMessage`:
-      - If `AIMessage` has `tool_calls`, `"tools"` node executes
-      - The `"agent"` node executes again and returns `AIMessage`
+
+        - If `AIMessage` has `tool_calls`, `"tools"` node executes
+        - The `"agent"` node executes again and returns `AIMessage`
+
    5. Execution progresses to the special `END` value and outputs the final state.
    And as a result, we get a list of all our chat messages as output.
   </details>
@@ -204,4 +223,9 @@ final_state["messages"][-1].content
 * [Tutorials](https://langchain-ai.github.io/langgraph/tutorials/): Learn to build with LangGraph through guided examples.
 * [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.
+* [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 (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).
@@ -1,2 +1,4 @@
 *.ipynb
 site/
+docs/tutorials/**/*.png
+docs/cloud/reference/sdk/js_ts_sdk_ref.md
@@ -1,4 +1,6 @@
+import json
 import os
+import re
 import shutil
 from pathlib import Path

@@ -8,19 +10,40 @@ examples_dir = root_dir / "examples"
 docs_dir = root_dir / "docs/docs"
 how_tos_dir = docs_dir / "how-tos"
 tutorials_dir = docs_dir / "tutorials"
+cloud_how_tos_dir = docs_dir / "cloud/how-tos"
+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",
-        "human-in-the-loop.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",
-        "time-travel.ipynb",
+        "input_output_schema.ipynb",
+        "pass_private_state.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",
+        "pass-config-to-tools.ipynb",
+        "many-tools.ipynb",
        "dynamic-returning-direct.ipynb",
        "managing-agent-steps.ipynb",
        "respond-in-format.ipynb",
@@ -28,25 +51,28 @@ _MANUAL = {
        "dynamically-returning-directly.ipynb",
        "configuration.ipynb",
        "map-reduce.ipynb",
-        "extraction/retries.ipynb",
        "create-react-agent.ipynb",
+        "create-react-agent-system-prompt.ipynb",
+        "create-react-agent-memory.ipynb",
+        "create-react-agent-hitl.ipynb",
+        "human_in_the_loop/breakpoints.ipynb",
+        "human_in_the_loop/time-travel.ipynb",
+        "human_in_the_loop/edit-graph-state.ipynb",
+        "human_in_the_loop/wait-user-input.ipynb",
+        "node-retries.ipynb",
    ],
    "tutorials": [
        "introduction.ipynb",
        "customer-support/customer-support.ipynb",
        "tutorials/tnt-llm/tnt-llm.ipynb",
-        "tutorials/sql-agent.ipynb"
+        "tutorials/sql-agent.ipynb",
    ],
 }
 _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",
@@ -66,6 +92,19 @@ _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",
+        "tutorials/rag-agent-testing-local.ipynb",
+        "tutorials/tool-calling-agent-local.ipynb",
+        "time-travel.ipynb",
+        "code_assistant/langgraph_code_assistant_mistral.ipynb",
    ]
 )

@@ -87,6 +126,44 @@ 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):
@@ -96,13 +173,15 @@ def copy_notebooks():
            continue
        if any(path in _HOW_TOS for path in root.split(os.sep)):
            dst_dir = how_tos_dir
+        elif "sdk" in root.split(os.sep):
+            dst_dir = cloud_sdk_dir
+        elif "cloud_examples" in root.split(os.sep):
+            dst_dir = cloud_how_tos_dir
        else:
            dst_dir = tutorials_dir
        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)
@@ -118,7 +197,6 @@ def copy_notebooks():
                        )
                        print(f"Overriding: {src_path} to {dst_path}")
                        break
-
                # Avoid double nesting.
                dst_path = dst_path.replace("tutorials/tutorials", "tutorials").replace(
                    "how-tos/how-tos", "how-tos"
@@ -134,15 +212,8 @@ 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__":
@@ -0,0 +1,13 @@
+ERROR_FOUND=0
+for file in $(find $1 -name "*.ipynb"); do
+    OUTPUT=$(cat "$file" | jupytext --from ipynb --to py:percent | codespell -)
+    if [ -n "$OUTPUT" ]; then
+        echo "Errors found in $file"
+        echo "$OUTPUT"
+        ERROR_FOUND=1
+    fi
+done
+
+if [ "$ERROR_FOUND" -ne 0 ]; then
+    exit 1
+fi
@@ -0,0 +1,111 @@
+# 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`][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.
+
+#### Configuring Assistants
+
+You can save custom assistants from the same graph to set different default prompts, models, and other configurations without changing a line of code in your graph. This allows you the ability to quickly test out different configurations without having to rewrite your graph every time, and also give users the flexibility to select different configurations when using your LangGraph application. See <a href="https://langchain-ai.github.io/langgraph/cloud/how-tos/cloud_examples/configuration_cloud/">this</a> how-to for information on how to configure a deployed graph. 
+
+### Threads
+
+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.
+
+### Cron Jobs
+
+It's often useful to run graphs on some schedule. LangGraph Cloud supports cron jobs, which run on a user defined schedule. The user specifies a schedule, an assistant, and some input. After than, on the specified schedule LangGraph cloud will:
+
+- 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.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/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/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/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
+
+All runs use the built-in checkpointer to store checkpoints for runs. However, it can often be useful to just kick off a run without worrying about explicitly creating a thread and without wanting to keep those checkpointers around. Stateless runs allow you to do this by exposing an endpoint that:
+
+- Takes in user input
+- Under the hood, creates a thread
+- Runs the agent but skips all checkpointing steps
+- Cleans up the thread afterwards
+
+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.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
+
+The LangGraph Cloud offers several features to support secure and robost deployments.
+
+### 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.
@@ -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)
@@ -0,0 +1,78 @@
+# How to Deploy to LangGraph Cloud
+
+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>.
+
+## Prerequisites
+
+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
+
+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. In the top-right corner, select `+ New Deployment` to create a new deployment.
+1. In the `Create New Deployment` panel, fill out the required fields.
+    1. `Deployment details`
+        1. Select `Import from GitHub` and follow the GitHub OAuth workflow to install and authorize LangChain's `hosted-langserve` GitHub app to  access the selected repositories. After installation is complete, return to the `Create New Deployment` panel and select the GitHub repository to deploy from the dropdown menu.
+        1. Specify a name for the deployment.
+        1. Specify the full path to the [LangGraph API config file](../reference/cli.md#configuration-file) including the file name. For example, if the file `langgraph.json` is in the root of the repository, simply specify `langgraph.json`.
+        1. Specify the desired `git` reference (e.g. branch name). For example, different branches of the repository can be deployed.
+    1. Select the desired `Deployment Type`.
+        1. `Development` deployments are meant for non-production use cases and are provisioned with minimal resources.
+        1. `Production` deployments can serve up to 500 requests/second and are provisioned with highly available storage with automatic backups.
+    1. Specify `Environment Variables` and secrets. See the [Environment Variables reference](../reference/env_var.md) to configure additional variables for the deployment.
+        1. Sensitive values such as API keys (e.g. `OPENAI_API_KEY`) should be specified as secrets.
+        1. Additional non-secret environment variables can be specified as well.
+    1. A new LangSmith `Tracing Project` is automatically created with the same name as the deployment.
+1. In the top-right corner, select `Submit`. After a few seconds, the `Deployment` view appears and the new deployment will be queued for provisioning.
+
+## Create New Revision
+
+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>...
+
+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 create a new revision for.
+1. In the `Deployment` view, in the top-right corner, select `+ New Revision`.
+1. In the `New Revision` modal, fill out the required fields.
+    1. Specify the full path to the [LangGraph API config file](../reference/cli.md#configuration-file) including the file name. For example, if the file `langgraph.json` is in the root of the repository, simply specify `langgraph.json`.
+    1. Specify the desired `git` reference (e.g. branch name). For example, different branches of the repository can be deployed.
+    1. Specify `Environment Variables` and secrets. Existing secrets and environment variables are prepopulated. See the [Environment Variables reference](../reference/env_var.md) to configure additional variables for the revision.
+        1. Add new secrets or environment variables.
+        1. Remove existing secrets or environment variables.
+        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.
+
+## View Build and Deployment Logs
+
+Build and deployment logs are available for each revision.
+
+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`.
@@ -0,0 +1,146 @@
+# Rebuild Graph at Runtime
+
+You might need to rebuild your graph with a different configuration for a new run. For example, you might need to use a different graph state or graph structure depending on the config. This guide shows how you can do this.
+
+!!! note "Note"
+    In most cases, customizing behavior based on the config should be handled by a single graph where each node can read a config and change its behavior based on it
+
+## Prerequisites
+
+Make sure to check out [this how-to guide](./setup.md) on setting up your app for deployment first.
+
+## Define graphs
+
+Let's say you have an app with a simple graph that calls an LLM and returns the response to the user. The app file directory looks like the following:
+
+```
+my-app/
+|-- requirements.txt
+|-- .env
+|-- openai_agent.py     # code for your graph
+```
+
+where the graph is defined in `openai_agent.py`. 
+
+### No rebuild
+
+In the standard LangGraph API configuration, the server uses the compiled graph instance that's defined at the top level of `openai_agent.py`, which looks like the following:
+
+```python
+from langchain_openai import ChatOpenAI
+from langgraph.graph import END, MessageGraph
+
+model = ChatOpenAI(temperature=0)
+
+graph_workflow = MessageGraph()
+
+graph_workflow.add_node("agent", model)
+graph_workflow.add_edge("agent", END)
+graph_workflow.set_entry_point("agent")
+
+agent = graph_workflow.compile()
+```
+
+To make the server aware of your graph, you need to specify a path to the variable that contains the `CompiledStateGraph` instance in your LangGraph API configuration (`langgraph.json`), e.g.:
+
+```
+{
+    "dependencies": ["."],
+    "graphs": {
+        "openai_agent": "./openai_agent.py:agent",
+    },
+    "env": "./.env"
+}
+```
+
+### Rebuild
+
+To make your graph rebuild on each new run with custom configuration, you need to rewrite `openai_agent.py` to instead provide a _function_ that takes a config and returns a graph (or compiled graph) instance. Let's say we want to return our existing graph for user ID '1', and a tool-calling agent for other users. We can modify `openai_agent.py` as follows:
+
+```python
+from typing import Annotated, TypedDict
+from langchain_openai import ChatOpenAI
+from langgraph.graph import END, MessageGraph
+from langgraph.graph.state import StateGraph
+from langgraph.graph.message import add_messages
+from langgraph.prebuilt import ToolNode
+from langchain_core.tools import tool
+from langchain_core.messages import BaseMessage
+from langchain_core.runnables import RunnableConfig
+
+
+class State(TypedDict):
+    messages: Annotated[list[BaseMessage], add_messages]
+
+
+model = ChatOpenAI(temperature=0)
+
+def make_default_graph():
+    """Make a simple LLM agent"""
+    graph_workflow = StateGraph(State)
+    def call_model(state):
+        return {"messages": [model.invoke(state["messages"])]}
+
+    graph_workflow.add_node("agent", call_model)
+    graph_workflow.add_edge("agent", END)
+    graph_workflow.set_entry_point("agent")
+
+    agent = graph_workflow.compile()
+    return agent
+
+
+def make_alternative_graph():
+    """Make a tool-calling agent"""
+
+    @tool
+    def add(a: float, b: float):
+        """Adds two numbers."""
+        return a + b
+
+    tool_node = ToolNode([add])
+    model_with_tools = model.bind_tools([add])
+    def call_model(state):
+        return {"messages": [model_with_tools.invoke(state["messages"])]}
+
+    def should_continue(state: State):
+        if state["messages"][-1].tool_calls:
+            return "tools"
+        else:
+            return END
+
+    graph_workflow = StateGraph(State)
+
+    graph_workflow.add_node("agent", call_model)
+    graph_workflow.add_node("tools", tool_node)
+    graph_workflow.add_edge("tools", "agent")
+    graph_workflow.set_entry_point("agent")
+    graph_workflow.add_conditional_edges("agent", should_continue)
+
+    agent = graph_workflow.compile()
+    return agent
+
+
+# this is the graph making function that will decide which graph to
+# build based on the provided config
+def make_graph(config: RunnableConfig):
+    user_id = config.get("configurable", {}).get("user_id")
+    # route to different graph state / structure based on the user ID
+    if user_id == "1":
+        return make_default_graph()
+    else:
+        return make_alternative_graph()
+```
+
+Finally, you need to specify the path to your graph-making function (`make_graph`) in `langgraph.json`:
+
+```
+{
+    "dependencies": ["."],
+    "graphs": {
+        "openai_agent": "./openai_agent.py:make_graph",
+    },
+    "env": "./.env"
+}
+```
+
+See more info on LangGraph API configuration file [here](../reference/cli.md#configuration-file)
@@ -0,0 +1,35 @@
+# How to Self-Host LangGraph Cloud API
+
+!!! 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).
@@ -0,0 +1,139 @@
+# 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 `requirements.txt` to specify project dependencies. 
+
+!!! tip "Setup with pyproject.toml"
+    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 none of these files is created, then dependencies can be specified later in the [LangGraph API configuration file](#create-langgraph-api-config).
+
+The dependencies below will be included in the image, you can also use them in your code, as long as with a compatible version range:
+```
+langgraph>=0.1.19,<0.2.0
+langchain-core>=0.2.8,<0.3.0
+langsmith>=0.1.63
+orjson>=3.10.1
+httpx>=0.27.0
+tenacity>=8.3.0
+uvicorn>=0.29.0
+sse-starlette>=2.1.0
+uvloop>=0.19.0
+httptools>=0.6.1
+jsonschema-rs>=0.18.0
+croniter>=1.0.1
+```
+
+Example `requirements.txt` file:
+```
+langgraph
+langchain_openai
+```
+
+Example file directory:
+```
+my-app/
+|-- requirements.txt    # 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
+OPENAI_API_KEY=key
+```
+
+Example file directory:
+```
+my-app/
+|-- requirements.txt
+|-- .env                # file with environment variables
+```
+
+## 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 `openai_agent.py` file:
+```python
+from langchain_openai import ChatOpenAI
+from langgraph.graph import END, MessageGraph
+
+model = ChatOpenAI(temperature=0)
+
+graph_workflow = MessageGraph()
+
+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 (alternatively, you can provide [a function that creates a graph](./graph_rebuild.md)).
+
+Example file directory:
+```
+my-app/
+|-- requirements.txt
+|-- .env
+|-- openai_agent.py     # code for your graph
+|-- anthropic_agent.py  # code for your graph
+```
+
+## 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": {
+        "openai_agent": "./openai_agent.py:agent",
+        "anthropic_agent": "./anthropic_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/
+|-- requirements.txt
+|-- .env
+|-- openai_agent.py
+|-- anthropic_agent.py
+|-- langgraph.json      # configuration file for LangGraph
+```
+
+## Next
+
+After you setup your project and place it in a github repo, it's time to [deploy your app](./cloud.md).
@@ -0,0 +1,169 @@
+# 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).
+
+The dependencies below will be included in the image, you can also use them in your code, as long as with a compatible version range:
+```
+langgraph>=0.1.19,<0.2.0
+langchain-core>=0.2.8,<0.3.0
+langsmith>=0.1.63
+orjson>=3.10.1
+httpx>=0.27.0
+tenacity>=8.3.0
+uvicorn>=0.29.0
+sse-starlette>=2.1.0
+uvloop>=0.19.0
+httptools>=0.6.1
+jsonschema-rs>=0.18.0
+croniter>=1.0.1
+```
+
+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 = "^0.1.7"
+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
+```
+
+## Next
+
+After you setup your project and place it in a github repo, it's time to [deploy your app](./cloud.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: ${chunk.event}...`);
+      console.log(chunk.data);
+      console.log("\n\n");
+    }
+    ```
+
+If your graph works correctly, you should see your graph output displayed in the console. Of course, there are many more ways you might need to test your graph, for a full list of commands you can send with the SDK, see the [Python](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/python_sdk_ref/) and [JS/TS](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/) references.
@@ -0,0 +1,183 @@
+## Enqueue
+
+This guide assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide](../concepts/api.md#double-texting).
+
+The guide covers the `enqueue` option for double texting, which adds the interruptions to a queue and executes them in the order they are received by the client. Below is a quick example of using the `enqueue` option.
+
+
+First, we will define a quick helper function for printing out JS model outputs (you can skip this if using Python):
+
+```js
+function prettyPrint(m) {
+  const padded = " " + m['type'] + " ";
+  const sepLen = Math.floor((80 - padded.length) / 2);
+  const sep = "=".repeat(sepLen);
+  const secondSep = sep + (padded.length % 2 ? "=" : "");
+  
+  console.log(`${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:
+
+    ================================[1m Human Message [0m=================================
+    
+    what's the weather in sf?
+    ==================================[1m Ai Message [0m==================================
+    
+    [{'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
+    =================================[1m Tool Message [0m=================================
+    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."}]
+    ==================================[1m Ai Message [0m==================================
+    
+    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.
+    ================================[1m Human Message [0m=================================
+    
+    what's the weather in nyc?
+    ==================================[1m Ai Message [0m==================================
+    
+    [{'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
+    =================================[1m Tool Message [0m=================================
+    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}}"}]
+    ==================================[1m Ai Message [0m==================================
+    
+    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.
+
@@ -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
+    
+    
+    
+
@@ -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).
@@ -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!
@@ -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}]}}
+
@@ -0,0 +1,74 @@
+---
+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 enter LangGraph Studio for local deployment](./test_local_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)
@@ -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:
+
+    ================================[1m Human Message [0m=================================
+    
+    what's the weather in sf?
+    ==================================[1m Ai Message [0m==================================
+    
+    [{'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
+    =================================[1m Tool Message [0m=================================
+    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 ..."}]
+    ================================[1m Human Message [0m=================================
+    
+    what's the weather in nyc?
+    ==================================[1m Ai Message [0m==================================
+    
+    [{'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
+    =================================[1m Tool Message [0m=================================
+    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."}]
+    ==================================[1m Ai Message [0m==================================
+    
+    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'
+
@@ -0,0 +1,15 @@
+# Invoke Assistant
+
+The LangGraph Studio lets you test different configurations and inputs to your graph. It also provides a nice visualization of your graph during execution so it is easy to see which nodes are being run and what the outputs of each individual node are.
+
+1. The LangGraph Studio UI displays a visualization of the selected assistant.
+    1. In the top-left 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 video shows these exact steps being carried out:
+
+<video controls allowfullscreen="true" poster="../img/studio_input_poster.png">
+    <source src="../img/studio_input.mp4" type="video/mp4">
+</video>
@@ -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:
+
+    ================================[1m Human Message [0m=================================
+    
+    what's the weather in sf?
+    ==================================[1m Ai Message [0m==================================
+    
+    [{'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
+    =================================[1m Tool Message [0m=================================
+    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."}]
+    ==================================[1m Ai Message [0m==================================
+    
+    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.
+
@@ -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:
+
+    ================================[1m Human Message [0m=================================
+    
+    what's the weather in nyc?
+    ==================================[1m Ai Message [0m==================================
+    
+    [{'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
+    =================================[1m Tool Message [0m=================================
+    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}}"}]
+    ==================================[1m Ai Message [0m==================================
+    
+    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
+
@@ -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
+    
+    
+    
+
@@ -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
+
@@ -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
+    --------------------------------------------------
+
@@ -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
+    
+    
+    
+
@@ -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
@@ -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': []}]}
@@ -0,0 +1,16 @@
+# 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 video shows these exact steps being carried out:
+
+<video controls allowfullscreen="true" poster="../img/studio_usage_poster.png">
+    <source src="../img/studio_usage.mp4" type="video/mp4">
+</video>
@@ -0,0 +1,28 @@
+# LangGraph Studio With Local Deployment
+
+!!! warning "Browser Compatibility"
+    Viewing the studio page of a local LangGraph deployment does not work in Safari. Use Chrome instead.
+
+## Setup
+
+Make sure you have setup your app correctly, by creating a compiled graph, a `.env` file with any environment variables, and a `langgraph.json` config file that points to your environment file and compiled graph. See [here](https://langchain-ai.github.io/langgraph/cloud/deployment/setup/) for more detailed instructions.
+
+After you have your app setup, head into the directory with your `langgraph.json` file and call `langgraph up -c langgraph.json --watch` to start the API server in watch mode which means it will restart on code changes, which is ideal for local testing. If the API server start correctly you should see logs that look something like this:
+
+    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
+
+Read this [reference](https://langchain-ai.github.io/langgraph/cloud/reference/cli/#up) to learn about all the options for starting the API server.
+
+## Access Studio
+
+Once you have successfully started the API server, you can access the studio by going to the following URL: `https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:8123` (see warning above if using Safari).
+
+If everything is working correctly you should see the studio show up looking something like this (with your graph diagram on the left hand side):
+
+![LangGraph Studio](./img/studio_screenshot.png)
+
+## Use the Studio for Testing
+
+To learn about how to use the studio for testing, read the [LangGraph Studio how-tos](https://langchain-ai.github.io/langgraph/cloud/how-tos/#langgraph-studio).
@@ -0,0 +1,23 @@
+# 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 video shows these exact steps being carried out:
+
+<video controls="true" allowfullscreen="true" poster="../img/studio_threads_poster.png">
+    <source src="../img/studio_threads.mp4" type="video/mp4">
+</video>
+
+## 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 video shows how to edit a thread in the studio:
+
+<video controls allowfullscreen="true" poster="../img/studio_forks_poster.png">
+    <source src="../img/studio_forks.mp4" type="video/mp4">
+</video>
@@ -0,0 +1,42 @@
+# LangGraph Cloud (beta)
+
+!!! tip
+    - LangGraph is an MIT-licensed open-source library, which we are committed to maintaining and growing for the community.
+    - LangGraph Cloud is an optional managed hosting service for LangGraph, which provides additional features geared towards production deployments.
+    - We are actively contributing improvements back to LangGraph informed by our work on LangGraph Cloud.
+    - You can always deploy LangGraph applications on your own infrastructure using the open-source LangGraph project.
+
+!!! warning "Under Construction"
+    LangGraph Cloud documentation is under construction. Contents may change until general availability.
+
+
+<video controls preload="auto" allowfullscreen="true" poster="how-tos/img/studio_forks_poster.png">
+    <source src="how-tos/img/studio_forks.mp4" type="video/mp4">
+</video>
+
+
+## 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 horizontally scalable and deployed with durable storage.
+
+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.
+
+## Key Features
+
+The LangGraph Cloud API supports key LangGraph features in addition to new functionality for enabling complex, agentic workflows.
+
+- **Assistants and Threads**: Assistants abstract the cognitive architecture of graphs and threads track the state/history of graphs.
+- **Streaming**: API support for [LangGraph streaming modes](../concepts/low_level.md#streaming) including setting multiple streaming modes at the same time.
+- **Human-in-the-Loop**: API support for [LangGraph human-in-the-loop features](../concepts/agentic_concepts.md#human-in-the-loop).
+- **Double Texting**: Configure how assistants respond when new input is received while processing a previous input. Interrupt, rollback, reject, or enqueue.
+- **Background Runs/Cron Jobs**: A built-in task queue enables background runs and scheduled cron jobs.
+- **Stateless Runs**: For simpler use cases, invoke an assistant without needing to create a thread.
+
+## Documentation
+
+- [Tutorials](./quick_start.md): Learn to build and deploy applications for LangGraph Cloud.
+- [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.
@@ -0,0 +1,252 @@
+# Quick Start
+
+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:
+
+        <my-app>/
+        |-- agent.py            # code for your LangGraph agent
+        |-- requirements.txt    # Python packages required for your graph
+        |-- 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 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_anthropic import ChatAnthropic
+    from langchain_community.tools.tavily_search import TavilySearchResults
+    from langgraph.prebuilt import create_react_agent
+
+    model = ChatAnthropic(model="claude-3-5-sonnet-20240620")
+
+    tools = [TavilySearchResults(max_results=2)]
+
+    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 four packages for our graph to run:
+
+        langgraph
+        langchain_anthropic
+        tavily-python
+        langchain_community
+
+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"
+    }
+    ```
+
+    Learn more about the LangGraph CLI configuration file [here](./reference/cli.md#configuration-file).
+
+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:
+
+    ```shell
+    ANTHROPIC_API_KEY=...
+    TAVILY_API_KEY=...
+    ```
+
+Now that we have set everything up on our local file system, we are ready to host our graph.
+
+## Test the graph build 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.
+
+In order to do this we can first install the LangGraph CLI
+
+```shell
+pip install langgraph-cli
+```
+
+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.
+
+```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
+```
+
+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:
+
+```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"
+    ]
+}'
+```
+
+If you get back a valid response, then all is functioning properly!
+
+## Deploy to Cloud
+
+### Push your code to GitHub
+
+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. Then click the `+ New Deployment` button.
+
+![Langsmith Workflow](./img/cloud_deployment.png)
+
+**_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.
+
+**_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 (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:
+
+![Deployment filled out](./deployment/img/deploy_filled_out.png)
+
+Hit `Submit` and your application will start deploying!
+
+## Inspect Traces + Monitor Service
+
+### Deployments View
+
+After your deployment is complete, your deployments page should look as follows:
+
+![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 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.
+
+### Access the Docs
+
+You can access the docs by clicking on the API docs link, which should send you to a page that looks like this:
+
+![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, 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
+
+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:
+
+![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. 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.
@@ -0,0 +1,19 @@
+<!doctype html>
+<html>
+  <head>
+    <title>LangGraph Cloud API Reference</title>
+    <meta charset="utf-8" />
+    <meta
+      name="viewport"
+      content="width=device-width, initial-scale=1" />
+  </head>
+  <body>
+    <script id="api-reference" data-url="./openapi.json"></script>
+    <script>
+      var configuration = {}
+      document.getElementById('api-reference').dataset.configuration =
+        JSON.stringify(configuration)
+    </script>
+    <script src="https://cdn.jsdelivr.net/npm/@scalar/api-reference"></script>
+  </body>
+</html>
@@ -0,0 +1,5 @@
+# API Reference
+
+The LangGraph Cloud API reference is available with each deployment at the `/docs` URL path (e.g. `http://localhost:8124/docs`).
+
+Click <a href="/langgraph/cloud/reference/api/api_ref.html" target="_blank">here</a> to view the API reference.
@@ -0,0 +1,127 @@
+# LangGraph CLI
+The LangGraph CLI includes commands to build and run a LangGraph Cloud API server locally in [Docker](https://www.docker.com/). For development and testing, use the CLI to deploy a local API server.
+
+## Installation
+1. Ensure that Docker is installed (e.g. `docker --version`).
+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:
+
+| Key | Description |
+| --- | ----------- |
+| `dependencies` | **Required**. Array of dependencies for LangGraph Cloud API server. Dependencies can be one of the following: (1) `"."`, which will look for local Python packages, (2) `pyproject.toml`, `setup.py` or `requirements.txt` in the app directory `"./local_package"`, or (3) a package name. |
+| `graphs` | **Required**. Mapping from graph ID to path where the compiled graph or a function that makes a graph is defined. Example: <ul><li>`./your_package/your_file.py:variable`, where `variable` is an instance of `langgraph.graph.state.CompiledStateGraph`</li><li>`./your_package/your_file.py:make_graph`, where `make_graph` is a function that takes a config dictionary (`langchain_core.runnables.RunnableConfig`) and creates an instance of `langgraph.graph.state.StateGraph` / `langgraph.graph.state.CompiledStateGraph`.</li></ul> |
+| `env` | Path to `.env` file or a mapping from environment variable to its value. |
+| `python_version` | `3.11` or `3.12`. Defaults to `3.11`. |
+| `pip_config_file`| Path to `pip` config file. |
+| `dockerfile_lines` | Array of additional lines to add to Dockerfile following the import from parent image. |
+
+<div class="admonition tip">
+    <p class="admonition-title">Note</p>
+    <p>
+        The LangGraph CLI defaults to using the configuration file <strong>langgraph.json</strong> in the current directory.
+    </p>
+</div>
+
+Example:
+```json
+{
+    "dependencies": [
+        "langchain_openai",
+        "./your_package"
+    ],
+    "graphs": {
+        "my_graph_id": "./your_package/your_file.py:variable"
+    },
+    "env": "./.env"
+}
+```
+
+Example:
+```json
+{
+    "python_version": "3.11",
+    "dependencies": [
+        "langchain_openai",
+        "."
+    ],
+    "graphs": {
+        "my_graph_id": "./your_package/your_file.py:make_graph"
+    },
+    "env": {
+        "OPENAI_API_KEY": "secret-key"
+    }
+}
+```
+
+## Commands
+The base command for the LangGraph CLI is `langgraph`.
+
+**Usage**
+```
+langgraph [OPTIONS] COMMAND [ARGS]
+```
+
+### `build`
+Build LangGraph Cloud API server Docker image.
+
+**Usage**
+```
+langgraph build [OPTIONS]
+```
+
+**Options**
+
+| Option | Default | Description |
+| ------ | ------- | ----------- |
+| `--platform TEXT` | | Target platform(s) to build the Docker image for. Example: `langgraph build --platform linux/amd64,linux/arm64` |
+| `-t, --tag TEXT` | | **Required**. Tag for the Docker image. Example: `langgraph build -t my-image` |
+| `--pull / --no-pull` | `--pull` | Build with latest remote Docker image. Use `--no-pull` for running the LangGraph Cloud API server with locally built images. |
+| `-c, --config FILE` | `langgraph.json` | Path to configuration file declaring dependencies, graphs and environment variables. |
+| `--help` | | Display command documentation. |
+
+### `up`
+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**
+```
+langgraph up [OPTIONS]
+```
+
+**Options**
+
+| Option | Default | Description |
+| ------ | ------- | ----------- |
+| `--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` | | 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. |
@@ -0,0 +1,13 @@
+# Environment Variables
+
+The LangGraph Cloud API supports specific environment variables for configuring a deployment.
+
+## `LANGGRAPH_AUTH_TYPE`
+
+Type of authentication for the LangGraph Cloud API deployment. Valid values: `langsmith`, `noop`.
+
+For deployments to LangGraph Cloud, this environment variable is set automatically. For local development or deployments where authentication is handled externally (e.g. self-hosted), set this environment variable to `noop`.
+
+## `N_JOBS_PER_WORKER`
+
+Number of jobs per worker for the LangGraph Cloud task queue. Defaults to `10`.
@@ -0,0 +1,79 @@
+# Python SDK Reference
+
+The Python SDK provides four underlying clients (`AssistantsClient`, `ThreadsClient`, `RunsClient`, `CronClient`) that correspond to each of the core API models and one top-level client (`LangGraphClient`) to access them.
+
+## get_client()
+
+The `get_client()` function returns the top-level `LangGraphClient` client.
+
+```python
+from langgraph_sdk import get_client
+
+# get top-level LangGraphClient
+client = get_client(url="http://localhost:8123")
+
+# example usage: client.<model>.<method_name>()
+assistants = await client.assistants.get(assistant_id="some_uuid")
+```
+
+::: langgraph_sdk.client.get_client
+    handler: python
+
+## LangGraphClient
+
+`LangGraphClient` is the top-level client for accessing `AssistantsClient`, `ThreadsClient`, `RunsClient`, and `CronClient`.
+
+::: langgraph_sdk.client.LangGraphClient
+    handler: python
+
+## AssistantsClient
+
+Access the `AssistantsClient` via the `LangGraphClient.assistants` attribute.
+```python
+from langgraph_sdk import get_client
+
+client = get_client(url="http://localhost:8123")
+await client.assistants.<method_name>()
+```
+
+::: langgraph_sdk.client.AssistantsClient
+    handler: python
+
+## ThreadsClient
+
+Access the `ThreadsClient` via the `LangGraphClient.threads` attribute.
+```python
+from langgraph_sdk import get_client
+
+client = get_client(url="http://localhost:8123")
+await client.threads.<method_name>()
+```
+
+::: langgraph_sdk.client.ThreadsClient
+    handler: python
+
+## RunsClient
+
+Access the `RunsClient` via the `LangGraphClient.runs` attribute.
+```python
+from langgraph_sdk import get_client
+
+client = get_client(url="http://localhost:8123")
+await client.runs.<method_name>()
+```
+
+::: langgraph_sdk.client.RunsClient
+    handler: python
+
+## CronClient
+
+Access the `CronClient` via the `LangGraphClient.crons` attribute.
+```python
+from langgraph_sdk import get_client
+
+client = get_client(url="http://localhost:8123")
+await client.crons.<method_name>()
+```
+
+::: langgraph_sdk.client.CronClient
+    handler: python
@@ -0,0 +1,99 @@
+# Common Agentic Patterns
+
+## Structured Output
+
+It's pretty common to want LLMs inside nodes to return structured output when building agents. This is because that structured output can often be used to route to the next step (e.g. choose between two different edges) or update specific keys of the state.
+
+Since LangGraph nodes can be arbitrary Python functions, you can do this however you want. If you want to use LangChain, [this how-to guide](https://python.langchain.com/v0.2/docs/how_to/structured_output/) is a starting point.
+
+## Tool calling
+
+It's extremely common to want agents to do tool calling. Tool calling refers to choosing from several available tools, and specifying which ones to call and what the inputs should be. This is extremely common in agents, as you often want to let the LLM decide which tools to call and then call those tools.
+
+Since LangGraph nodes can be arbitrary Python functions, you can do this however you want. If you want to use LangChain, [this how-to guide](https://python.langchain.com/v0.2/docs/how_to/tool_calling/) is a starting point.
+
+## Memory
+
+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`](./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](./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](./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
+
+A similar one is to have the agent wait for human input. This can be done by:
+
+1. Create a node specifically for human input
+2. Add a breakpoint before the node
+3. Get user input
+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](./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](./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](../how-tos/map-reduce.ipynb)
+
+## Multi-agent
+
+A term you may have heard is "multi-agent" architectures. What exactly does this mean?
+
+Given that it is hard to even define an "agent", it's almost impossible to exactly define a "multi-agent" architecture. When most people talk about a multi-agent architecture, they typically mean a system where there are multiple different LLM-based systems. These LLM-based systems can be as simple as a prompt and an LLM call, or as complex as a [ReAct agent](#react-agent).
+
+The big question in multi-agent systems is how they communicate. This involves both the schema of how they communicate, as well as the sequence in which they communicate. LangGraph is perfect for orchestrating these types of systems. It allows you to define multiple agents (each one is a node) an arbitrary state (to encapsulate the schema of how they communicate) as well as the edges (to control the sequence in which they communicate).
+
+## Planning
+
+One of the big things that agentic systems struggle with is long term planning. A common technique to overcome this is to have an explicit planning this. This generally involves calling an LLM to come up with a series of steps to execute. From there, the system then tries to execute the series of tasks (this could use a sub-agent to do so). Optionally, you can revisit the plan after each step and update it if needed.
+
+## Reflection
+
+Agents often struggle to produce reliable results. Therefore, it can be helpful to check whether the agent has completed a task correctly or not. If it has - then you can finish. If it hasn't - then you can take the feedback on why it's not correct and pass it back into another iteration of the agent.
+
+This "reflection" step often uses an LLM, but doesn't have to. A good example of where using an LLM may not be necessary is in coding, when you can try to compile the generated code and use any errors as the feedback.
+
+## ReAct Agent
+
+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`](../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:
+
+- First, we use [tool-calling](#tool-calling) to have LLMs call tools, whereas the paper used prompting + parsing of raw output. This is because tool calling did not exist when the paper was written, but is generally better and more reliable.
+- Second, we use messages to prompt the LLM, whereas the paper used string formatting. This is because at the time of writing, LLMs didn't even expose a message-based interface, whereas now that's the only interface they expose.
+- 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.
@@ -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.
@@ -0,0 +1,55 @@
+# LangGraph for Agentic Applications
+
+## What does it mean to be agentic?
+
+Other people may talk about a system being an "agent" - we prefer to talk about systems being "agentic". But what does this actually mean?
+
+When we talk about systems being "agentic", we are talking about systems that use an LLM to decide the control flow of an application. There are different levels that an LLM can be used to decide the control flow, and this spectrum of "agentic" makes more sense to us than defining an arbitrary cutoff for what is or isn't an agent.
+
+Examples of using an LLM to decide the control of an application:
+
+- Using an LLM to route between two potential paths
+- Using an LLM to decide which of many tools to call
+- Using an LLM to decide whether the generated answer is sufficient or more work is need
+
+The more times these types of decisions are made inside an application, the more agentic it is.
+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](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](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](../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**
+
+LangGraph is extremely low level. This gives you a high degree of control over what the system you are building actually does. We believe this is important because it is still hard to get agentic systems to work reliably, and we've seen that the more control you exercise over them, the more likely it is that they will "work".
+
+**Human-in-the-Loop**
+
+LangGraph comes with a built-in persistence layer as a first-class concept. This enables several different human-in-the-loop interaction patterns. We believe that "Human-Agent Interaction" patterns will be the new "Human-Computer Interaction", and have built LangGraph with built in persistence to enable 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](../how-tos/stream-updates.ipynb)) as well as of [tokens that an LLM may emit](../how-tos/streaming-tokens.ipynb).
+
+## Deployment
+
+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](../cloud/index.md) or rolling your own solution.
+
+[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.
@@ -1,427 +1,57 @@
 # Conceptual Guides

-Welcome to LangGraph, a Python library for building complex, scalable AI agents using graph-based state machines. In this guide, we'll explore the core concepts behind LangGraph and why it's uniquely suited for creating reliable, fault-tolerant agent systems. We assume you have already learned the basic covered in the [introduction tutorial](https://langchain-ai.github.io/langgraph/tutorials/introduction/#requirements) and want to deepen your understanding of LangGraph's underlying design and inner workings.
-
-First off, why graphs?
-
-## Background: Agents & AI Workflows as Graphs
-
-While everyone has a slightly different definition of what constitutes an "AI Agent", we will take "agent" to mean any system that tasks a language model with controlling a looping workflow and takes actions. The prototypical LLM agent uses a ~["reasoning and action" (ReAct)](https://arxiv.org/abs/2210.03629)-style design, applying an LLM to power a basic loop with the following steps:
-
- reason and plan actions to take
- take actions using tools (regular software functions)
- observe the effects of the tools and re-plan or react as appropriate
-
-While LLM agents are surprisingly effective at this, the naive agent loop doesn't deliver the [reliability users expect at scale](https://en.wikipedia.org/wiki/High_availability). They're beautifully stochastic. Well-designed systems take advantage of that randomness and apply it sensibly within a well-designed composite system and make that system **tolerant** to mistakes in the LLM's outputs, because mistakes **will** occur.
-
-We think agents are exciting and new, but AI design patterns should apply applicable good engineering practices from Software 2.0. Some similarities include:
-
- AI applications must balance autonomous operations with user control.
- Agent applications resemble distributed systems in their need for error tolerance and correction.
- Multi-agent systems resemble multi-player web apps in their need for parallelism + conflict resolution.
- Everyone loves an undo button and version control.
-
-LangGraph's primary [StateGraph](https://langchain-ai.github.io/langgraph/reference/graphs/#langgraph.graph.StateGraph) abstraction is designed to support these and other needs, providing an API that is lower level than other agent frameworks such as LangChain's [AgentExecutor](https://python.langchain.com/v0.1/docs/modules/agents/) to give you full control of where and how to apply "AI."
-
-It extends Google's [Pregel](https://research.google/pubs/pregel-a-system-for-large-scale-graph-processing/) graph processing framework to provide fault tolerance and recovery when running long or error-prone workloads. When developing, you can focus on a local action or task-specific agent, and the system composes these actions to form a more capable and scalable application.
-
-Its parallelism and `State` reduction functionality let you control what happens if, for example, multiple agents return conflicting information.
-
-And finally, its persistent, versioned checkpointing system lets you roll back the agent's state, explore other paths, and maintain full control of what is going on.
-
-The following sections go into greater detail about how and why all of this works.
-
-## Core Design
-
-At its core, LangGraph models agent workflows as state machines. 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`.
-
-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`.
-
-3. `Edges`: Control flow rules 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`.
-
-Or 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.
-
-We will go through a full execution of a StateGraph later, but first, lets explore these concepts in more detail.
-
-## Nodes
-
-In StateGraph, nodes are typically python functions (sync or `async`) where the **first** positional argument is the [state](#state-management), 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:
-
-```python
-from langchain_core.runnables import RunnableConfig
-from langgraph.graph import END, START, StateGraph
-
-builder = StateGraph(dict)
-
-
-def my_node(state: dict, config: RunnableConfig):
-    print("In node: ", config["configurable"]["user_id"])
-    return {"results": f"Hello, {state['input']}!"}
-
-
-# The second argument is optional
-def my_other_node(state: dict):
-    return state
-
-
-builder.add_node("my_node", my_node)
-builder.add_node("other_node", my_other_node)
-builder.add_edge(START, "my_node")
-builder.add_edge("my_node", "other_node")
-builder.add_edge("other_node", END)
-graph = builder.compile()
-graph.invoke({"input": "Will"}, {"configurable": {"user_id": "abcd-123"}})
-# In node:  abcd-123
-# {'results': 'Hello, Will!'}
-```
-
-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.
-
-## Edges
-
-Edges define how the logic is routed and how the graph decides to stop. Similar to nodes, they accept the current `state` of the graph and return a value.
-
-By default, the value is the name of the node or nodes to send the state to next. All those nodes will be run in parallel as a part of the next superstep.
-
-If you want to reuse an edge, you can optionally provide a dictionary that maps the edge's output to the name of the next node.
-
-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 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.
-
-If a node has multiple out-going edges, **all** of those destination nodes will be executed in parallel as a part of the next superstep.
-
-## State Management
-
-LangGraph introduces two key ideas to state management: state schemas and reducers.
-
-The state schema defines the type of the object that is given to each of the graph's `Node`.
-
-Reducers define how to apply `Node` outputs to the current `State`. For example, you might use a reducer to merge a new dialogue response into a conversation history, or average together outputs from multiple agent nodes. By annotating your `State` fields with reducer functions, you can precisely control how data flows through your application.
-
-We'll illustrate how reducers work with an example. Compare the following two `State`. Can you guess the output in both case?
-
-```python
-from typing import Annotated
-
-from typing_extensions import TypedDict
-
-from langgraph.graph import END, START, StateGraph
-
-
-class StateA(TypedDict):
-    value: int
-
-
-builder = StateGraph(StateA)
-builder.add_node("my_node", lambda state: {"value": 1})
-builder.add_edge(START, "my_node")
-builder.add_edge("my_node", END)
-graph = builder.compile()
-graph.invoke({"value": 5})
-```
-
-And `StateB`:
-
-```python
-from typing import Annotated
-
-from typing_extensions import TypedDict
-
-from langgraph.graph import END, START, StateGraph
-
-
-
-def add(existing: int, new: int):
-    return existing + new
-
-
-class StateB(TypedDict):
-    # highlight-next-line
-    value: Annotated[int, add]
-
-
-builder = StateGraph(StateB)
-builder.add_node("my_node", lambda state: {"value": 1})
-builder.add_edge(START, "my_node")
-builder.add_edge("my_node", END)
-graph = builder.compile()
-graph.invoke({"value": 5})
-```
-
-If you guesed "1" and "6", then you're correct!
-
-In the first case (`StateA`), the result is "1", since the default **reducer** for your state is a direct overwrite.
-In the second case (`StateB`), the result is "6" since we have have created the `add` function as the **reducer**. This function takes the existing state (for that field) and the state update (if provided) and returns the updated value for that state.
-
-In general, **reducers** provided as annotations tell the graph **how to process updates for this field**.
-
-While we typically use `TypedDict` as the graph's `state_schema` (i.e., `State`), it can be almost any [type](https://docs.python.org/3/library/stdtypes.html#type-objects), meaning the following graph is also completely valid:
-
-```python
-# Analogous to StateA above
-builder = StateGraph(int)
-builder.add_node("my_node", lambda state: 1)
-builder.add_edge(START, "my_node")
-builder.add_edge("my_node", END)
-builder.compile().invoke(5)
-
-# Analogous to StateB
-def add(left, right):
-    return left + right
-
-
-builder = StateGraph(Annotated[int, add])
-builder.add_node("my_node", lambda state: 1)
-builder.add_edge(START, "my_node")
-builder.add_edge("my_node", END)
-graph = builder.compile()
-graph.invoke(5)
-```
-
-This also means you can [use 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.
-
-When building simple chatbots like ChatGPT, the state can be as simple as a list of chat messages. This is the state used by [MessageGraph](https://langchain-ai.github.io/langgraph/reference/graphs/?h=message+graph#langgraph.graph.MessageGraph) (a light wrapper of `StateGraph`), which is only slightly more involved than the following:
-
-```python
-builder = StateGraph(Annotated[list, add])
-```
-
-Using a shared state within a graph comes with some design tradeoffs. For instance, you may think it feels like using dreaded global variables (though this can be addressed by namespacing arguments). However, sharing a typed state provides a number of benefits relevant to building AI workflows, including:
-
-1. The data flow is fully inspectable before and after each "superstep".
-2. The state is mutable, making it easy to let users or other software write to the same state between supersteps to control an agent's direction (using [update_state](https://langchain-ai.github.io/langgraph/reference/graphs/#langgraph.graph.graph.CompiledGraph.update_state)).
-3. It is well-defined when checkpointing, making it easy to save and resume or even fully version control the execution of your entire workflows in whatever storage backend you wish.
-
-We will talk about checkpointing more in the next section.
-
-## Persistence
-
-Any "intelligent" system needs memory to function. AI agents are no different, requiring memory across one or more timeframes:
-
- they _always_ need to remember the steps already taken **within this task** (to avoid repeating itself when answering a given query).
- they _typically_ need to remember the previous turns within a multi-turn conversation with a user (for coreference resolution and additional context).
- they _ideally_ need to "remember" context from previous interactions with the user and from actions in a given "environment" (such as an application context) to be more personalized and efficient in its behavior.
-
-That last form of memory covers a lot (personalization, optimization, continual learning, etc.) and is beyond the scope of this conversation, although it can be easily integrated in any LangGraph workflow, and we are actively exploring the best way to expose this functionality natively.
-
-The first two forms of memory are natively supported by the [StateGraph](https://langchain-ai.github.io/langgraph/reference/graphs/#langgraph.graph.StateGraph) API via [checkpointers](https://langchain-ai.github.io/langgraph/reference/checkpoints/#basecheckpointsaver).
-
-#### Checkpoints
-
-A checkpoint represents the state of a `thread` within a (potentially) multi-turn interaction between your application and a user (or users or other systems). Checkpoints that are made _within_ a single run will have a set of `next` nodes that will be executed when starting from this state. Checkpoints that are made at the end of a given run are identical, except there are no `next` nodes to transition to (the graph is awaiting user input).
-
-Checkpointing supports chat memory and much more, letting you tag and persist every state your system has taken, regardless of whether it is within a single run or across many turns. Let's explore a bit why that is useful.
-
-#### Single-turn Memory
-
-**Within** a given run, each step of the agent is checkpointed. This means you could ask your agent to go create world peace. In the likely scenario that it runs into an error as it fails to do so, you can resume its quest at any time by resuming from one of its saved checkpoints.
-
-This also lets you build **human-in-the-loop** workflows, common in use cases like [customer support bots](https://langchain-ai.github.io/langgraph/tutorials/customer-support/customer-support/), [programming assistants](https://langchain-ai.github.io/langgraph/tutorials/usaco/usaco/), and other applications. Before or after executing a given node, you can `interrupt` the graph's execution and "escalate" control to a user or support person. That person may respond immediately. Or they could respond a month from now. Either way, your workflow can resume at any time as if no time had passed at all.
-
-#### Multi-turn Memory
-
-Checkpoints are saved under a "thread_id" to support multi-turn interactions between users and your system. To the developer, there is absolutely no difference in how you configure your graph to add multi-turn memory support, since the checkpointing works the same throughout.
-
-If you have some portion of state that you want to retain across turns and some state that you want to treat as "ephemeral", you can always clear the relevant state in the graph's final node.
-
-Using checkpointing is as easy as calling `compile(checkpointer=my_checkpointer)` and then invoking it with a `thread_id` within its `configurable` parameters. You can see more in the following sections!
-
-## Threads
-
-Threads in LangGraph represent separate **sessions** of a graph. They organize state checkpoints within discrete sessions to facilitate multi-conversation and multi-user support in an application.
-
-A typical chat bot application would have multiple threads for each user. Each thread represents a single conversation, with its own persistent chat history and other state. Checkpoints within a thread can be rewound and branched as needed.
-
-Threads in LangGraph are distinct from [operating system threads](https://docs.python.org/3/library/threading.html), which are units of execution managed by the OS. They are more akin to a [conversational thread](<https://en.wikipedia.org/wiki/Thread_(online_communication)>) in email, twitter, and other messaging apps.
-
-When a `StateGraph` is compiled with a checkpointer, each invocation of the graph requires a `thread_id` to be provided via [configuration (see below)](#configuration).
-
-## Configuration
-
-For any given graph deployment, you'll likely want some amount of configurable values that you can control at runtime. These differ from the graph **inputs** in that they aren't meant to be treated as state variables. They are more akin to "[out-of-band](https://en.wikipedia.org/wiki/Out-of-band)" communication.
-
-A common example is a conversational `thread_id`, a `user_id`, a choice of which LLM to use, how many documents to return in a retriever, etc. While you **could** pass this within the state, it is nicer to separate out from the regular data flow. Configurable values are also automatically added to LangSmith traces as [metadata](https://docs.smith.langchain.com/concepts/tracing#metadata).
-
-#### Example
-
-Let's review another example to see how our multi-turn memory works! Can you guess what `result` and `result2` look like if you run this graph?
-
-```python
-from typing import Annotated
-
-from typing_extensions import TypedDict
-
-from langgraph.checkpoint.memory import MemorySaver
-from langgraph.graph import END, START, StateGraph
-
-
-def add(left, right):
-    return left + right
-
-
-class State(TypedDict):
-    total: Annotated[int, add]
-    turn: str
-
-
-builder = StateGraph(State)
-builder.add_node("add_one", lambda x: {"total": 1})
-builder.add_edge(START, "add_one")
-builder.add_edge("add_one", END)
-
-memory = MemorySaver()
-graph = builder.compile(checkpointer=memory)
-thread_id = "some-thread"
-config = {"configurable": {"thread_id": thread_id}}
-result = graph.invoke({"total": 1, "turn": "First Turn"}, config)
-result2 = graph.invoke({"turn": "Next Turn"}, config)
-result3 = graph.invoke({"total": 5}, config)
-result4 = graph.invoke({"total": 5}, {"configurable": {"thread_id": "new-thread-id"}})
-```
-
-If you guessed the following, you're correct!
-
-```python
->>> result
-{'total': 2, 'turn': 'First Turn'}
->>> result2
-{'total': 3, 'turn': 'Next Turn'}
->>> result3
-{'total': 9, 'turn': 'Next Turn'}
->>> result4
-{'total': 6}
-
-```
-
-For the first run, no checkpoint existed, so the graph ran on the raw input. The "total" value is incremented from 1 to 2, and the "turn" is set to "First Turn".
-
-For the second run, the user provides an update to "turn" but no total! Since we are loading from the state, the previous result is incremented by one (in our "add_one" node), and the "turn" is overwritten by the user.
-
-For the third run, the "turn" remains the same, since it is loaded from the checkpoint but not overwritten by the user. The "total" is incremented by the value provided by the user, since this is **reduced** (i.e., used to update the existing value) by the `add` function.
-
-For the fourth run, we are using a **new thread id** for which no checkpoint is found, so the result is just the user's provided **total** incremented by one.
-
-You probably noticed that this user-facing behavior is equivalent to running the following **without a checkpointer**.
-
-```python
-graph = builder.compile()
-result = graph.invoke({"total": 1, "turn": "First Turn"})
-result2 = graph.invoke({**result, "turn": "Next Turn"})
-result3 = graph.invoke({**result2, "total": result2["total"] + 5})
-result4 = graph.invoke({"total": 5})
-```
-
-Run this for yourself to confirm equivalence. User inputs and checkpoint loading is treated more or less the same as any other **state update**.
-
-Now that we've introduced the core concepts behind LangGraph, it may be instructive to walk through an end-to-end example to see how all the pieces fit together.
-
-## Data flow of a single execution of a StateGraph
-
-As engineers, we are never really satisfied until we know what's going on "under the hood". In the previous sections, we explained some of the LangGraph's core concepts. Now it's time to really show how they fit together.
-
-Let's extend our toy example above with a conditional edge and then walk through two consecutive invocations.
-
-```python
-from typing import Annotated, Literal
-
-from typing_extensions import TypedDict
-
-from langgraph.checkpoint.memory import MemorySaver
-from langgraph.graph import END, START, StateGraph
-
-
-
-def add(left, right):
-    return left + right
-
-
-class State(TypedDict):
-    total: Annotated[int, add]
-
-
-builder = StateGraph(State)
-builder.add_node("add_one", lambda x: {"total": 1})
-builder.add_node("double", lambda x: {"total": x["total"]})
-builder.add_edge(START, "add_one")
-
-
-def route(state: State) -> Literal["double", "__end__"]:
-    if state["total"] < 6:
-        return "double"
-    return "__end__" # This is what END is
-
-
-builder.add_conditional_edges("add_one", route)
-builder.add_edge("double", "add_one")
-
-memory = MemorySaver()
-graph = builder.compile(checkpointer=memory)
-```
-
-...
-
-And then call it for the first time:
-
-```python
-thread_id = "some-thread"
-config = {"configurable": {"thread_id": thread_id}}
-for step in graph.stream({"total": 1}, config, stream_mode="debug"):
-    print(step["step"], step["type"], step["payload"].get("values"))
-# 0 checkpoint {'total': 1}
-# 1 task None
-# 1 task_result None
-# 1 checkpoint {'total': 2}
-# 2 task None
-# 2 task_result None
-# 2 checkpoint {'total': 4}
-# 3 task None
-# 3 task_result None
-# 3 checkpoint {'total': 5}
-# 4 task None
-# 4 task_result None
-# 4 checkpoint {'total': 10}
-# 5 task None
-# 5 task_result None
-# 5 checkpoint {'total': 11}
-```
-
-To inspect the trace of this run, check out the [LangSmith link here](https://smith.langchain.com/public/0c543370-d459-4b8d-9962-058f67bdc9ce/r). We'll walk through the execution below:
-
-1. First, the graph looks for a checkpoint. None is found, so the state is thus initialized with a total of 0.
-2. Next, the graph applies the user's input as an update to the state. The reducer adds the input (1) to the existing value (0). At the end of this superstep, the total is (1).
-3. After that, the "add_one" node is called, returning 1.
-4. Next, the reducer adds this update to the existing total (1). The state is now 2.
-5. Then, the conditional edge "`route`" is called. Since the value is less than 6, we continue to the 'double' node.
-6. Double takes the existing state (2), and returns it. The reducer is then called and adds it to the existing state. The state is now 4.
-7. The graph then loops back through add_one (5), checks the conditional edge and proceeds to since it's < 6. After doubling, the total is (10).
-8. The fixed edge loops back to add_one (11), checks the conditional edge, and since it is greater than 6, the program terminates.
-
-For our second run, we will use the same configuration:
-
-```python
-for step in graph.stream(
-    {"total": -2, "turn": "First Turn"}, config, stream_mode="debug"
-):
-    print(step["step"], step["type"], step["payload"].get("values"))
-# 7 checkpoint {'total': 9}
-# 8 task None
-# 8 task_result None
-# 8 checkpoint {'total': 10}
-```
-
-To inspect the trace of this run, check out the [LangSmith link here](https://smith.langchain.com/public/494f1817-46f5-4051-b41c-2dc416ce8b4d/r). We'll walk through the execution below:
-
-1. First, it applies the update from the user's input. The `add` **reducer** updates the total from 0 to -2.
-2. Next, the graph looks for the checkpoint. It loads it to memory as the initial state. Total is (9) now ((-2) + 11).
-3. After that, the 'add_one' node is called with this state. It returns 10.
-4. That update is applied using the reducer, raising the value to 10.
-5. Next, the "route" conditional edge is triggered. Since the value is greater than 6, we terminate the program, ending where we started at (11).
+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](../how-tos/index.md)
+
+
+LangGraph for Agentic Applications
+
+- [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.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#working-with-messages-in-graph-state)
+- [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.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)
@@ -0,0 +1,428 @@
+# Low Level Conceptual Guide
+
+## Graphs
+
+At its core, LangGraph models agent workflows as graphs. You define the behavior of your agents using three key components:
+
+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`](#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`](#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 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
+
+The `StateGraph` class is the main graph class to uses. This is parameterized by a user defined `State` object.
+
+### MessageGraph
+
+The `MessageGraph` class is a special type of graph. The `State` of a `MessageGraph` is ONLY a list of messages. This class is rarely used except for chatbots, as most applications require the `State` to be more complex than a list of messages.
+
+### Compiling your graph
+
+To build your graph, you first define the [state](#state), you then add [nodes](#nodes) and [edges](#edges), and then you compile it. What exactly is compiling your graph and why is it needed?
+
+Compiling is a pretty simple step. It provides a few basic checks on the structure of your graph (no orphaned nodes, etc). It is also where you can specify runtime args like [checkpointers](#checkpointer) and [breakpoints](#breakpoints). You compile your graph by just calling the `.compile` method:
+
+```python
+graph = graph_builder.compile(...)
+```
+
+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 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](../how-tos/state-model.ipynb) as your graph state to add **default values** and additional data validation.
+
+By default, the graph will have the same input and output schemas. If you want to change this, you can also specify explicit input and output schemas directly. This is useful when you have a lot of keys, and some are explicitly for input and others for output. See the [notebook here](../how-tos/input_output_schema.ipynb) for how to use.
+
+By default, all nodes in the graph will share the same state. This means that they will read and write to the same state channels. It is possible to have nodes write to private state channels inside the graph for internal node communication - see [this notebook](../how-tos/pass_private_state.ipynb) for how to do that.
+
+### Reducers
+
+Reducers are key to understanding how updates from nodes are applied to the `State`. Each key in the `State` has its own independent reducer function. If no reducer function is explicitly specified then it is assumed that all updates to that key should override it. Let's take a look at a few examples to understand them better.
+
+**Example A:**
+
+```python
+from typing import TypedDict
+
+class State(TypedDict):
+    foo: int
+    bar: list[str]
+```
+
+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
+from typing import TypedDict, Annotated
+from operator import add
+
+class State(TypedDict):
+    foo: int
+    bar: Annotated[list[str], add]
+```
+
+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.
+
+### Working with Messages in Graph State
+
+#### Why use messages?
+
+Most modern LLM providers have a chat model interface that accepts a list of messages as input. LangChain's [`ChatModel`](https://python.langchain.com/v0.2/docs/concepts/#chat-models) in particular accepts a list of `Message` objects as inputs. These messages come in a variety of forms such as `HumanMessage` (user input) or `AIMessage` (LLM response). To read more about what message objects are, please refer to [this](https://python.langchain.com/v0.2/docs/concepts/#messages) conceptual guide.
+
+#### Using Messages in your Graph
+
+In many cases, it is helpful to store prior conversation history as a list of messages in your graph state. To do so, we can add a key (channel) to the graph state that stores a list of `Message` objects and annotate it with a reducer function (see `messages` key in the example below). The reducer function is vital to telling the graph how to update the list of `Message` objects in the state with each state update (for example, when a node sends an update). If you don't specify a reducer, every state update will overwrite the list of messages with the most recently provided value. If you wanted to simply append messages to the existing list, you could use `operator.add` as a reducer.
+
+However, you might also want to manually update messages in your graph state (e.g. human-in-the-loop). If you were to use `operator.add`, the manual state updates you send to the graph would be appended to the existing list of messages, instead of updating existing messages. To avoid that, you need a reducer that can keep track of message IDs and overwrite existing messages, if updated. To achieve this, you can use the prebuilt `add_messages` function. For brand new messages, it will simply append to existing list, but it will also handle the updates for existing messages correctly.
+
+#### Serialization
+
+In addition to keeping track of message IDs, the `add_messages` function will also try to deserialize messages into LangChain `Message` objects whenever a state update is received on the `messages` channel. See more information on LangChain serialization/deserialization [here](https://python.langchain.com/v0.2/docs/how_to/serialization/). This allows sending graph inputs / state updates in the following format:
+
+```python
+# this is supported
+{"messages": [HumanMessage(content="message")]}
+
+# and this is also supported
+{"messages": [{"type": "human", "content": "message"}]}
+```
+
+Since the state updates are always deserialized into LangChain `Messages` when using `add_messages`, you should use dot notation to access message attributes, like `state["messages"][-1].content`. Below is an example of a graph that uses `add_messages` as it's reducer function.
+
+```python
+from langchain_core.messages import AnyMessage
+from langgraph.graph.message import add_messages
+from typing import Annotated, TypedDict
+
+class GraphState(TypedDict):
+    messages: Annotated[list[AnyMessage], add_messages]
+```
+
+#### MessagesState
+
+Since having a list of messages in your state is so common, there exists a prebuilt state called `MessagesState` which makes it easy to use messages. `MessagesState` is defined with a single `messages` key which is a list of `AnyMessage` objects and uses the `add_messages` reducer. Typically, there is more state to track than just messages, so we see people subclass this state and add more fields, like:
+
+```python
+from langgraph.graph import MessagesState
+
+class State(MessagesState):
+    documents: list[str]
+```
+
+## Nodes
+
+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][langgraph.graph.StateGraph.add_node] method:
+
+```python
+from langchain_core.runnables import RunnableConfig
+from langgraph.graph import StateGraph
+
+builder = StateGraph(dict)
+
+
+def my_node(state: dict, config: RunnableConfig):
+    print("In node: ", config["configurable"]["user_id"])
+    return {"results": f"Hello, {state['input']}!"}
+
+
+# The second argument is optional
+def my_other_node(state: dict):
+    return state
+
+
+builder.add_node("my_node", my_node)
+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.
+
+```python
+builder.add_node(my_node)
+# You can then create edges to/from this node by referencing it as `"my_node"`
+```
+
+### `START` Node
+
+The `START` Node is a special node that represents the node sends user input to the graph. The main purpose for referencing this node is to determine which nodes should be called first.
+
+```python
+from langgraph.graph import START
+
+graph.add_edge(START, "node_a")
+```
+
+### `END` Node
+
+The `END` Node is a special node that represents a terminal node. This node is referenced when you want to denote which edges have no actions after they are done.
+
+```
+from langgraph.graph import END
+
+graph.add_edge("node_a", END)
+```
+
+## Edges
+
+Edges define how the logic is routed and how the graph decides to stop. This is a big part of how your agents work and how different nodes communicate with each other. There are a few key types of edges:
+
+- Normal Edges: Go directly from one node to the next.
+- Conditional Edges: Call a function to determine which node(s) to go to next.
+- Entry Point: Which node to call first when user input arrives.
+- Conditional Entry Point: Call a function to determine which node(s) to call first when user input arrives.
+
+A node can have MULTIPLE outgoing edges. If a node has multiple out-going edges, **all** of those destination nodes will be executed in parallel as a part of the next superstep.
+
+### Normal Edges
+
+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")
+```
+
+### Conditional Edges
+
+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_conditional_edges("node_a", routing_function)
+```
+
+Similar to nodes, the `routing_function` accept the current `state` of the graph and return a value.
+
+By default, the return value `routing_function` is used as the name of the node (or a list of nodes) to send the state to next. All those nodes will be run in parallel as a part of the next superstep.
+
+You can optionally provide a dictionary that maps the `routing_function`'s output to the name of the next node.
+
+```python
+graph.add_conditional_edges("node_a", routing_function, {True: "node_b", False: "node_c"})
+```
+
+### Entry Point
+
+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
+
+graph.add_edge(START, "node_a")
+```
+
+### Conditional Entry Point
+
+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
+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.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`](../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):
+    return [Send("generate_joke", {"subject": s}) for s in state['subjects']]
+
+graph.add_conditional_edges("node_a", continue_to_jokes)
+```
+
+## Checkpointer
+
+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:
+
+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.
+
+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.
+
+See [this guide](../how-tos/persistence.ipynb) for how to add a checkpointer to your graph.
+
+## Threads
+
+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
+
+`thread_ts` can optionally be passed. This identifier refers to a specific checkpoint within a thread. This can be used to kick of a run of a graph from some point halfway through a thread.
+
+You must pass these when invoking the graph as part of the configurable part of the config.
+
+```python
+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 interacting with the checkpointer state, you must specify a [thread identifier](#threads).Each checkpoint saved by the checkpointer 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.
+
+### Get state
+
+You can get the state of a checkpointer by calling `graph.get_state(config)`. The config should contain `thread_id`, and the state will be fetched for that thread.
+
+### 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.
+
+### Update state
+
+You can also interact with the state directly and update it. This takes three different components:
+
+- config
+- values
+- `as_node`
+
+**config**
+
+The config should contain `thread_id` specifying which thread to update.
+
+**values**
+
+These are the values that will be used to update the state. Note that this update is treated exactly as any update from a node is treated. This means that these values will be passed to the [reducer](#reducers) functions that are part of the state. So this does NOT automatically overwrite the state. Let's walk through an example.
+
+Let's assume you have defined the state of your graph as:
+
+```python
+from typing import TypedDict, Annotated
+from operator import add
+
+class State(TypedDict):
+    foo: int
+    bar: Annotated[list[str], add]
+```
+
+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"]})
+```
+
+Then the new state of the graph will be:
+
+```
+{"foo": 2, "bar": ["a", "b"]}
+```
+
+The `foo` key is completely changed (because there is no reducer specified for that key, so it overwrites it). However, there is a reducer specified for the `bar` key, and so it appends `"b"` to the state of `bar`.
+
+**`as_node`**
+
+The final thing you specify when calling `update_state` is `as_node`. This update will be applied as if it came from node `as_node`. If `as_node` is not provided, it will be set to the last node that updated the state, if not ambiguous.
+
+The reason this matters is that the next steps in the graph to execute depend on the last node to have given an update, so this can be used to control which node executes next.
+
+## Graph Migrations
+
+LangGraph can easily handle migrations of graph definitions (nodes, edges, and state) even when using a checkpointer to track state.
+
+- For threads at the end of the graph (i.e. not interrupted) you can change the entire topology of the graph (i.e. all nodes and edges, remove, add, rename, etc)
+- For threads currently interrupted, we support all topology changes other than renaming / removing nodes (as that thread could now be about to enter a node that no longer exists) -- if this is a blocker please reach out and we can prioritize a solution.
+- For modifying state, we have full backwards and forwards compatibility for adding and removing keys
+- State keys that are renamed lose their saved state in existing threads
+- State keys whose types change in incompatible ways could currently cause issues in threads with state from before the change -- if this is a blocker please reach out and we can prioritize a solution.
+
+## Configuration
+
+When creating a graph, you can also mark that certain parts of the graph are configurable. This is commonly done to enable easily switching between models or system prompts. This allows you to create a single "cognitive architecture" (the graph) but have multiple different instance of it.
+
+You can optionally specify a `config_schema` when creating a graph.
+
+```python
+class ConfigSchema(TypedDict):
+    llm: str
+
+graph = StateGraph(State, config_schema=ConfigSchema)
+```
+
+You can then pass this configuration into the graph using the `configurable` config field.
+
+```python
+config = {"configurable": {"llm": "anthropic"}}
+
+graph.invoke(inputs, config=config)
+```
+
+You can then access and use this configuration inside a node:
+
+```python
+def node_a(state, config):
+    llm_type = config.get("configurable", {}).get("llm", "openai")
+    llm = get_llm(llm_type)
+    ...
+```
+
+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`.)
+
+You **MUST** use a [checkpoiner](#checkpointer) when using breakpoints. This is because your graph needs to be able to resume execution.
+
+In order to resume execution, you can just invoke your graph with `None` as the input.
+
+```python
+# Initial run of graph
+graph.invoke(inputs, config=config)
+
+# Let's assume it hit a breakpoint somewhere, you can then resume by passing in None
+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](../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"`](../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`](../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).
@@ -1,40 +1,89 @@
+---
+hide:
+  - toc
+---
+
 # How-to guides

 Welcome to the LangGraph how-to guides! These guides provide practical, step-by-step instructions for accomplishing key tasks in LangGraph.

-## Core
+## Controllability

-The core guides show how to address common needs when building out AI workflows, with special focus placed on [ReAct](https://arxiv.org/abs/2210.03629)-style agents with [tool calling](https://python.langchain.com/docs/modules/model_io/chat/function_calling/).
+LangGraph is known for being a highly controllable agent framework.
+These how-to guides show how to achieve that controllability.

- [ReAct agent](create-react-agent.ipynb): How to create a tool-calling agent that **Re**asons and **Act**s to accomplish tasks
- [Persistence](persistence.ipynb): How to give your graph "memory" and resilience by saving and loading state
- [Time travel](time-travel.ipynb): How to navigate and manipulate graph state history once it's persisted
- [Async execution](async.ipynb): How to run nodes asynchronously for improved performance
- [Streaming responses](streaming-tokens.ipynb): How to stream agent responses in real-time
- [Visualization](visualization.ipynb): How to visualize your graphs
- [Configuration](configuration.ipynb): How to indicate that a graph can swap out configurable components
+- [How to create subgraphs](subgraph.ipynb)
+- [How to create branches for parallel execution](branching.ipynb)
+- [How to create map-reduce branches for parallel execution](map-reduce.ipynb)

-### Design patterns

-Recipes showing how to apply common design patterns in your workflows:
+## Persistence

- [Subgraphs](subgraph.ipynb): How to compose subgraphs within a larger graph
- [Branching](branching.ipynb): How to create branching logic in your graphs for parallel node execution
- [Map-reduce](map-reduce.ipynb): How to branch **different views** of the state for parallel node execution (even applying the same node in parallel N times)
- [Human-in-the-loop](human-in-the-loop.ipynb): How to incorporate human feedback and intervention
+LangGraph makes it easy to persist state across graph runs. The guide below shows how to add persistence to your graph.

-The following examples are useful especially if you are used to LangChain's AgentExecutor configurations.
+- [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)

- [Force calling a tool first](force-calling-a-tool-first.ipynb): Define a fixed workflow before ceding control to the ReAct agent
- [Pass run time values to tools](pass-run-time-values-to-tools.ipynb): Pass values that are only known at run time to tools (e.g., the ID of the user who made the request)
- [Dynamic direct return](dynamically-returning-directly.ipynb): Let the LLM decide whether the graph should finish after a tool is run or whether the LLM should be able to review the output and keep going
- [Respond in structured format](respond-in-format.ipynb): Let the LLM use tools or populate schema to provide the user. Useful if your agent should generate structured content
- [Managing agent steps](managing-agent-steps.ipynb): How to format the intermediate steps of your workflow for the agent
+## Human in the Loop

-### Alternative ways to define state
+One of LangGraph's main benefits is that it makes human-in-the-loop workflows easy.
+These guides cover common examples of that.

- [Pydantic state](state-model.ipynb): Use a Pydantic model as your state
+- [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)
+- [How to view and update past graph state](human_in_the_loop/time-travel.ipynb)

-### Structured output
+## Streaming

- [Extraction with re-prompting](./extraction/retries.ipynb): How to generate complex nested schemas using JSONPatch retries, for when function calling is insufficient, and regular reprompting still fails to generate valid results
+LangGraph is built to be streaming first.
+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)
+- [How to pass config to tools](pass-config-to-tools.ipynb)
+- [How to handle large numbers of tools](many-tools.ipynb)
+
+## State Management
+
+- [Use Pydantic model as state](state-model.ipynb)
+- [Use a context object in state](state-context-key.ipynb)
+- [Have a separate input and output schema](input_output_schema.ipynb)
+- [Pass private state between nodes inside the graph](pass_private_state.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)
+- [How to add node retries](node-retries.ipynb)
+
+## Prebuilt ReAct Agent
+
+These guides show how to use the prebuilt ReAct agent.
+Please note that here will we use a **prebuilt agent**. One of the big benefits of LangGraph is that you can easily create your own agent architectures. So while it's fine to start here to build an agent quickly, we would strongly recommend learning how to build your own agent so that you can take full advantage of LangGraph.
+
+- [How to create a ReAct agent](create-react-agent.ipynb)
+- [How to add memory to a ReAct agent](create-react-agent-memory.ipynb)
+- [How to add a custom system prompt to a ReAct agent](create-react-agent-system-prompt.ipynb)
+- [How to add human-in-the-loop processes to a ReAct agent](create-react-agent-hitl.ipynb)
@@ -1,131 +1,7 @@
 ---
 hide_comments: true
+hide:
+  - navigation
 ---
-# 🦜🕸️LangGraph

-![Version](https://img.shields.io/pypi/v/langgraph)
-[![Downloads](https://static.pepy.tech/badge/langgraph/month)](https://pepy.tech/project/langgraph)
-[![Open Issues](https://img.shields.io/github/issues-raw/langchain-ai/langgraph)](https://github.com/langchain-ai/langgraph/issues)
-[![](https://dcbadge.vercel.app/api/server/6adMQxSpJS?compact=true&style=flat)](https://discord.com/channels/1038097195422978059/1170024642245832774)
-
-
-⚡ Build language agents as graphs ⚡
-
-!!! note "Python version :material-language-python:"
-
-    Looking for the JS version? Click [:fontawesome-brands-square-js: here](https://github.com/langchain-ai/langgraphjs) ([:simple-readme: JS docs](https://langchain-ai.github.io/langgraphjs/)).
-
-## Overview
-
-Suppose you're building a customer support assistant. You want your assistant to be able to:
-
-1. Use tools to respond to questions
-2. Connect with a human if needed
-3. Be able to pause the process indefinitely and resume whenever the human responds
-
-LangGraph makes this all easy. First install:
-
-```bash
-pip install -U langgraph
-```
-
-Then define your assistant:
-
-```python
-import json
-
-from langchain_anthropic import ChatAnthropic
-from langchain_community.tools.tavily_search import TavilySearchResults
-
-from langgraph.checkpoint.sqlite import SqliteSaver
-from langgraph.graph import END, MessageGraph
-from langgraph.prebuilt.tool_node import ToolNode
-
-
-# Define the function that determines whether to continue or not
-def should_continue(messages):
-    last_message = messages[-1]
-    # If there is no function call, then we finish
-    if not last_message.tool_calls:
-        return END
-    else:
-        return "action"
-
-
-# Define a new graph
-workflow = MessageGraph()
-
-tools = [TavilySearchResults(max_results=1)]
-model = ChatAnthropic(model="claude-3-haiku-20240307").bind_tools(tools)
-workflow.add_node("agent", model)
-workflow.add_node("action", ToolNode(tools))
-
-workflow.set_entry_point("agent")
-
-# Conditional agent -> action OR agent -> END
-workflow.add_conditional_edges(
-    "agent",
-    should_continue,
-)
-
-# Always transition `action` -> `agent`
-workflow.add_edge("action", "agent")
-
-memory = SqliteSaver.from_conn_string(":memory:") # Here we only save in-memory
-
-# Setting the interrupt means that any time an action is called, the machine will stop
-app = workflow.compile(checkpointer=memory, interrupt_before=["action"])
-```
-
-Now, run the graph:
-
-```python
-# Run the graph
-thread = {"configurable": {"thread_id": "4"}}
-for event in app.stream("what is the weather in sf currently", thread, stream_mode="values"):
-    event[-1].pretty_print()
-
-```
-We configured the graph to **wait** before executing the `action`. The `SqliteSaver` persists the state. Resume at any time.
-
-```python
-for event in app.stream(None, thread, stream_mode="values"):
-    event[-1].pretty_print()
-```
-
-The graph orchestrates everything:
-
- The `MessageGraph` contains the agent's "Memory"
- Conditional edges enable dynamic routing between the chatbot, tools, and the user
- Persistence makes it easy to stop, resume, and even rewind for full control over your application
-
-With LangGraph, you can build complex, stateful agents without getting bogged down in manual state and interrupt management. Just define your nodes, edges, and state schema - and let the graph take care of the rest.
-
-
-## Tutorials
-
-Consult the [Tutorials](tutorials/index.md) to learn more about building with LangGraph, including advanced use cases.
-
-
-## How-To Guides
-
-Check out the [How-To Guides](how-tos/index.md) for instructions on handling common tasks with LangGraph
-
-## Reference
-
-For documentation on the core APIs, check out the [Reference](reference/graphs.md) docs.
-
-## Conceptual Guides
-
-Once you've learned the basics, if you want to further understand LangGraph's core abstractions, check out the [Conceptual Guides](./concepts/index.md).
-
-## Why LangGraph?
-
-LangGraph is framework agnostic (each node is a regular python function). It extends the core Runnable API (shared interface for streaming, async, and batch calls) to make it easy to:
-
- Seamless state management across multiple turns of conversation or tool usage
- The ability to flexibly route between nodes based on dynamic criteria 
- Smooth switching between LLMs and human intervention  
- Persistence for long-running, multi-session applications
-
-If you're building a straightforward DAG, Runnables are a great fit. But for more complex, stateful applications with nonlinear flows, LangGraph is the perfect tool for the job.
+{!README.md!}
@@ -1,25 +1,29 @@
 # 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
 - Resilience for long-running, error-prone agents
 - Time travel retry and branch from a previous checkpoint

+Key checkpointer interfaces and primitives are defined in [`langgraph_checkpoint`](https://github.com/langchain-ai/langgraph/tree/main/libs/checkpoint) library.
+
 ### Checkpoint

-::: langgraph.checkpoint.Checkpoint
+::: langgraph.checkpoint.base.Checkpoint
+
+### CheckpointMetadata
+
+::: langgraph.checkpoint.base.CheckpointMetadata

 ### BaseCheckpointSaver

 ::: langgraph.checkpoint.base.BaseCheckpointSaver
-handler: python

 ### SerializerProtocol

-::: langgraph.checkpoint.SerializerProtocol
-handler: python
+::: langgraph.checkpoint.base.SerializerProtocol

 ## Implementations

@@ -28,12 +32,10 @@ LangGraph also natively provides the following checkpoint implementations.
 ### MemorySaver

 ::: langgraph.checkpoint.memory.MemorySaver
-handler: python

 ### AsyncSqliteSaver

-::: langgraph.checkpoint.aiosqlite.AsyncSqliteSaver
-handler: python
+::: langgraph.checkpoint.sqlite.aio.AsyncSqliteSaver

 ### SqliteSaver

@@ -13,17 +13,19 @@ graph = StateGraph(MyState)
 ```

 ::: langgraph.graph.StateGraph
-    handler: python
+handler: python

 ## MessageGraph

 ::: langgraph.graph.message.MessageGraph

-
 ## CompiledGraph

 ::: langgraph.graph.graph.CompiledGraph
-    handler: python
+
+## StreamMode
+
+::: langgraph.pregel.StreamMode

 ## Constants

@@ -64,4 +66,7 @@ builder.add_conditional_edges("my_node", my_condition)
 ## Send

 ::: langgraph.constants.Send
-    handler: python
+
+## RetryPolicy
+
+::: langgraph.pregel.types.RetryPolicy
@@ -55,4 +55,13 @@ from langgraph.prebuilt import tools_condition
 from langgraph.prebuilt import ValidationNode
 ```

-::: langgraph.prebuilt.ValidationNode
+::: langgraph.prebuilt.ValidationNode
+
+## InjectedState
+
+```python
+from langgraph.prebuilt import InjectedState
+```
+
+::: langgraph.prebuilt.InjectedState
+    handler: python
@@ -1,12 +1,17 @@
+---
+hide:
+  - toc
+---
+
 # Tutorials

 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

@@ -15,55 +20,49 @@ Learn from example implementations of graphs designed for specific scenarios and
 #### Chatbots

 - [Customer Support](customer-support/customer-support.ipynb): Build a customer support chatbot to manage flights, hotel reservations, car rentals, and other tasks
- [Info Gathering](chatbots/information-gather-prompting.ipynb): Build an information gathering chatbot  
- [Code Assistant](code_assistant/langgraph_code_assistant.ipynb): Building a code analysis and generation assistant
-
+- [Prompt Generation from User Requirements](chatbots/information-gather-prompting.ipynb): Build an information gathering chatbot
+- [Code Assistant](code_assistant/langgraph_code_assistant.ipynb): Build a code analysis and generation assistant

 #### Multi-Agent Systems

- [Collaboration](multi_agent/multi-agent-collaboration.ipynb): Enabling two agents to collaborate on a task  
- [Supervision](multi_agent/agent_supervisor.ipynb): Using an LLM to orchestrate and delegate to individual agents
- [Hierarchical Teams](multi_agent/hierarchical_agent_teams.ipynb): Orchestrating nested teams of agents to solve problems
+- [Collaboration](multi_agent/multi-agent-collaboration.ipynb): Enable two agents to collaborate on a task
+- [Supervision](multi_agent/agent_supervisor.ipynb): Use an LLM to orchestrate and delegate to individual agents
+- [Hierarchical Teams](multi_agent/hierarchical_agent_teams.ipynb): Orchestrate nested teams of agents to solve problems

 #### RAG

 - [Adaptive RAG](rag/langgraph_adaptive_rag.ipynb)
-    - [Adaptive RAG using local models](rag/langgraph_adaptive_rag_local.ipynb)
- [Agentic RAG.ipynb](rag/langgraph_agentic_rag.ipynb)
+    - [Adaptive RAG using local LLMs](rag/langgraph_adaptive_rag_local.ipynb)
+- [Agentic RAG](rag/langgraph_agentic_rag.ipynb)
 - [Corrective RAG](rag/langgraph_crag.ipynb)
-    - [Corrective RAG with local models](rag/langgraph_crag_local.ipynb)
+    - [Corrective RAG using local LLMs](rag/langgraph_crag_local.ipynb)
 - [Self-RAG](rag/langgraph_self_rag.ipynb)
-    - [Self-RAG with local models](rag/langgraph_self_rag_local.ipynb)
- [Web Research (STORM)](storm/storm.ipynb): Generating Wikipedia-like articles via research and multi-perspective QA
-
+    - [Self-RAG using local LLMs](rag/langgraph_self_rag_local.ipynb)
+- [SQL Agent](sql-agent.ipynb)

 #### Planning Agents

- [Plan-and-Execute](plan-and-execute/plan-and-execute.ipynb): Implementing a basic planning and execution agent  
- [Reasoning without Observation](rewoo/rewoo.ipynb): Reducing re-planning by saving observations as variables 
- [LLMCompiler](llm-compiler/LLMCompiler.ipynb): Streaming and eagerly executing a DAG of tasks from a planner
+- [Plan-and-Execute](plan-and-execute/plan-and-execute.ipynb): Implement a basic planning and execution agent
+- [Reasoning without Observation](rewoo/rewoo.ipynb): Reduce re-planning by saving observations as variables
+- [LLMCompiler](llm-compiler/LLMCompiler.ipynb): Stream and eagerly execute a DAG of tasks from a planner

 #### Reflection & Critique 

- [Basic Reflection](reflection/reflection.ipynb): Prompting the agent to reflect on and revise its outputs
- [Reflexion](reflexion/reflexion.ipynb): Critiquing missing and superfluous details to guide next steps
- [Language Agent Tree Search](lats/lats.ipynb): Using reflection and rewards to drive a tree search over agents
- [Self-Discovering Agent](self-discover/self-discover.ipynb): Analyzing an agent that learns about its own capabilities
+- [Basic Reflection](reflection/reflection.ipynb): Prompt the agent to reflect on and revise its outputs
+- [Reflexion](reflexion/reflexion.ipynb): Critique missing and superfluous details to guide next steps
+- [Language Agent Tree Search](lats/lats.ipynb): Use reflection and rewards to drive a tree search over agents
+- [Self-Discover Agent](self-discover/self-discover.ipynb): Analyze an agent that learns about its own capabilities

 #### Evaluation

- [Agent-based](chatbot-simulation-evaluation/agent-simulation-evaluation.ipynb): Evaluating chatbots via simulated user interactions
- [Within LangSmith](chatbot-simulation-evaluation/langsmith-agent-simulation-evaluation.ipynb): Evaluating chatbots in LangSmith over a dialog dataset
+- [Agent-based](chatbot-simulation-evaluation/agent-simulation-evaluation.ipynb): Evaluate chatbots via simulated user interactions
+- [In LangSmith](chatbot-simulation-evaluation/langsmith-agent-simulation-evaluation.ipynb): Evaluate chatbots in LangSmith over a dialog dataset

-#### Text Mining
+#### Experimental

- [TNT-LLM](tnt-llm/tnt-llm.ipynb): learn to build rich, interpretable taxonomies of user intentand using the classification system developed by Microsoft for their Bing Copilot application.
-
-#### Competitive Programming
-
- [Can Language Models Solve Olympiad Programming?](usaco/usaco.ipynb): Build an agent with few-shot "episodic memory" and human-in-the-loop collaboration to solve problems from the USA Computing Olympiad; adapted from the [paper of the same name](https://arxiv.org/abs/2404.10952v1) by Shi, Tang, Narasimhan, and Yao.
-
-
-#### Other Experimental Architectures
-
- [Web Navigation](web-navigation/web_voyager.ipynb): Building an agent that can navigate and interact with websites
+- [Web Research (STORM)](storm/storm.ipynb): Generate Wikipedia-like articles via research and multi-perspective QA
+- [TNT-LLM](tnt-llm/tnt-llm.ipynb): Build rich, interpretable taxonomies of user intentand using the classification system developed by Microsoft for their Bing Copilot application.
+- [Web Navigation](web-navigation/web_voyager.ipynb): Build an agent that can navigate and interact with websites
+- [Competitive Programming](usaco/usaco.ipynb): Build an agent with few-shot "episodic memory" and human-in-the-loop collaboration to solve problems from the USA Computing Olympiad; adapted from the ["Can Language Models Solve Olympiad Programming?"](https://arxiv.org/abs/2404.10952v1) paper by Shi, Tang, Narasimhan, and Yao.
+- [Complex data extraction](extraction/retries.ipynb): Build an agent that can use function calling to do complex extraction tasks
+- 
@@ -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
@@ -26,7 +25,6 @@ theme:
    - navigation.instant.prefetch
    - navigation.instant.progress
    - navigation.prune
-    - navigation.sections
    - navigation.tabs
    - navigation.top
    - navigation.tracking
@@ -35,18 +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"
@@ -61,7 +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
@@ -69,9 +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
@@ -81,91 +79,166 @@ 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'
-      - Quick Start: how-tos/docs/quickstart.ipynb
-      - Intro to LangGraph: tutorials/introduction.ipynb
+  - Home:
+      - "index.md"
  - Tutorials:
-      - 'tutorials/index.md'
-      - Introduction: tutorials/introduction.ipynb
-      - Use cases:
-          - Chatbots:
-              - Customer Support: tutorials/customer-support/customer-support.ipynb
-              - Info Gathering: tutorials/chatbots/information-gather-prompting.ipynb
-              - Code Assistant: tutorials/code_assistant/langgraph_code_assistant.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
+          - Code Assistant: tutorials/code_assistant/langgraph_code_assistant.ipynb
+      - RAG:
+          - Adaptive RAG: tutorials/rag/langgraph_adaptive_rag.ipynb
+          - Adaptive RAG using local LLMs: tutorials/rag/langgraph_adaptive_rag_local.ipynb
+          - Agentic RAG: tutorials/rag/langgraph_agentic_rag.ipynb
+          - Corrective RAG (CRAG): tutorials/rag/langgraph_crag.ipynb
+          - Corrective RAG (CRAG) using local LLMs: tutorials/rag/langgraph_crag_local.ipynb
+          - Self-RAG: tutorials/rag/langgraph_self_rag.ipynb
+          - 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
-          - RAG:
-              - tutorials/rag/langgraph_adaptive_rag.ipynb
-              - tutorials/rag/langgraph_adaptive_rag_local.ipynb
-              - tutorials/rag/langgraph_agentic_rag.ipynb
-              - tutorials/rag/langgraph_crag.ipynb
-              - tutorials/rag/langgraph_crag_local.ipynb
-              - tutorials/rag/langgraph_self_rag.ipynb
-              - tutorials/rag/langgraph_self_rag_local.ipynb
-          - Web Research (STORM): tutorials/storm/storm.ipynb
          - Planning Agents:
              - Plan-and-Execute: tutorials/plan-and-execute/plan-and-execute.ipynb
-              - Reasoning w/o Observation: tutorials/rewoo/rewoo.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-Discovering Agent: tutorials/self-discover/self-discover.ipynb
-          - Evaluation & Analysis:
-              - Chatbot Eval via Sim:
-                  - Agent-based: tutorials/chatbot-simulation-evaluation/agent-simulation-evaluation.ipynb
-                  - In LangSmith: tutorials/chatbot-simulation-evaluation/langsmith-agent-simulation-evaluation.ipynb
-          - Text Mining:
-              - TNT-LLM: tutorials/tnt-llm/tnt-llm.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
-          - SQL: tutorials/sql-agent.ipynb
+          - Extract structured output: tutorials/extraction/retries.ipynb

  - "How-to Guides":
-     - 'how-tos/index.md'
-     - Core:
-         - "ReAct Agent": how-tos/create-react-agent.ipynb
-         - "Persistence": how-tos/persistence.ipynb
-         - "Time Travel": how-tos/time-travel.ipynb 
-         - "Async Execution": how-tos/async.ipynb
-         - "Streaming Responses": how-tos/streaming-tokens.ipynb
-         - "Visualization": how-tos/visualization.ipynb
-         - "Configuration": how-tos/configuration.ipynb
-     - Design Patterns:
-         - "Subgraphs": how-tos/subgraph.ipynb
-         - "Branching": how-tos/branching.ipynb
-         - "Map-reduce": how-tos/map-reduce.ipynb
-         - "Human-in-the-Loop": how-tos/human-in-the-loop.ipynb
-         - "Force Calling a Tool First": how-tos/force-calling-a-tool-first.ipynb
-         - "Pass Run-Time Values to Tools": how-tos/pass-run-time-values-to-tools.ipynb
-         - "Dynamic Direct Return": how-tos/dynamically-returning-directly.ipynb
-         - "Respond in Structured Format": how-tos/respond-in-format.ipynb
-         - "Managing Agent Steps": how-tos/managing-agent-steps.ipynb
-     - Alternative State Definitions:  
-         - "Pydantic State": how-tos/state-model.ipynb
-     - Structured Output:
-         - "Extraction with Re-prompting": how-tos/extraction/retries.ipynb
-  - 'Conceptual Guides':
-     - 'concepts/index.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
+          - Pass config to tools: how-tos/pass-config-to-tools.ipynb
+          - Handle many tools: how-tos/many-tools.ipynb
+      - State Management:
+          - Use Pydantic model as state: how-tos/state-model.ipynb
+          - Use a context object in state: how-tos/state-context-key.ipynb
+          - Have a separate input and output schema: how-tos/input_output_schema.ipynb
+          - Pass private state between nodes inside the graph: how-tos/pass_private_state.ipynb
+      - Other:
+          - Run graph asynchronously: how-tos/async.ipynb
+          - Visualize your graph: how-tos/visualization.ipynb
+          - Add runtime configuration: how-tos/configuration.ipynb
+          - Add node retries: how-tos/node-retries.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    
-  
+      - Errors: reference/errors.md
+  - "Cloud (beta)":
+      - "cloud/index.md"
+      - Tutorials:
+          - Quick Start: "cloud/quick_start.md"
+      - How-to Guides: 
+          - "cloud/how-tos/index.md"
+          - Setup:
+              - Setup App: "cloud/deployment/setup.md"
+              - Setup App (pyproject.toml): "cloud/deployment/setup_pyproject.md"
+              - Rebuild Graph at Runtime: "cloud/deployment/graph_rebuild.md"
+              - Test App Locally: "cloud/deployment/test_locally.md"
+          - Deployment:
+              - Deploy to Cloud: "cloud/deployment/cloud.md"
+              - Self-Host: "cloud/deployment/self_hosted.md"
+          - Streaming:
+              - 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"
+              - Test Local Deployment: "cloud/how-tos/test_local_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:
+          - API Concepts: "cloud/concepts/api.md"
+          - Cloud Concepts: "cloud/concepts/cloud.md"
+      - Reference:
+          - 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"

 markdown_extensions:
  - abbr
@@ -175,6 +248,9 @@ markdown_extensions:
  - def_list
  - footnotes
  - md_in_html
+  - pymdownx.superfences
+  - pymdownx.tabbed:
+      alternate_style: true
  - toc:
      permalink: true
  - pymdownx.arithmatex:
@@ -196,7 +272,7 @@ markdown_extensions:
  - pymdownx.magiclink:
      normalize_issue_symbols: true
      repo_url_shorthand: true
-      user: langchain-ai 
+      user: langchain-ai
      repo: langgraph
  - pymdownx.mark
  - pymdownx.smartsymbols
@@ -213,12 +289,15 @@ markdown_extensions:
      combine_header_slug: true
  - pymdownx.tasklist:
      custom_checkbox: true
+  - markdown_include.include:
+      base_path: ./
+  - github-callouts
 extra_css:
  - css/mkdocstrings.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
@@ -238,5 +317,10 @@ 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
@@ -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 %}
@@ -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 %}
@@ -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": {
@@ -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": {
@@ -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": {
@@ -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": {
@@ -5,9 +5,9 @@
   "id": "51466c8d-8ce4-4b3d-be4e-18fdbeda5f53",
   "metadata": {},
   "source": [
-    "# Async\n",
+    "# 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": {
@@ -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": {
@@ -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": {
@@ -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": {
@@ -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": {
--- a/Show More
+++ b/Show More