Add image arg to up command (#4385)

Using this argument, you can get more customization since you can do
`langgraph build` or directly `docker build` your image and then re-use
the `langgraph up --image my-image` and have it also spin up redis &
postgres for you.

Easier then writing your own compose file

.github/workflows/_integration_test.yml

@@ -4,7 +4,7 @@ on:
   workflow_call:
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "2.1.2"
 
 jobs:
   build:
@@ -71,4 +71,3 @@ jobs:
         working-directory: libs/cli/js-examples
         run: |
           langgraph build -t langgraph-test-e
-  

.github/workflows/_lint.yml

@@ -9,7 +9,7 @@ on:
         description: "From which folder this pipeline executes"
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "2.1.2"
 
   # This env var allows us to get inline annotations when ruff has complaints.
   RUFF_OUTPUT_FORMAT: github
@@ -50,12 +50,6 @@ jobs:
         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

.github/workflows/_test.yml

@@ -9,7 +9,7 @@ on:
         description: "From which folder this pipeline executes"
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "2.1.2"
 
 jobs:
   build:

.github/workflows/_test_langgraph.yml

@@ -4,7 +4,7 @@ on:
   workflow_call:
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "2.1.2"
 
 jobs:
   build:

.github/workflows/_test_release.yml

@@ -9,7 +9,7 @@ on:
         description: "From which folder this pipeline executes"
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "2.1.2"
   PYTHON_VERSION: "3.10"
 
 jobs:

.github/workflows/_test_scheduler_kafka.yml

@@ -4,7 +4,7 @@ on:
   workflow_call:
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "2.1.2"
 
 jobs:
   build:

.github/workflows/baseline.yml

@@ -8,7 +8,7 @@ on:
       - "libs/**"
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "2.1.2"
 
 jobs:
   benchmark:

.github/workflows/bench.yml

@@ -6,7 +6,7 @@ on:
       - "libs/**"
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "2.1.2"
 
 jobs:
   benchmark:
@@ -43,7 +43,7 @@ jobs:
         run: |
           {
             echo 'OUTPUT<<EOF'
-            make -s benchmark
+            make -s benchmark-fast
             echo EOF
           } >> "$GITHUB_OUTPUT"
       - name: Compare benchmarks

.github/workflows/ci.yml

@@ -17,10 +17,34 @@ concurrency:
   cancel-in-progress: true
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "2.1.2"
 
 jobs:
+  changes:
+    runs-on: ubuntu-latest
+    outputs:
+      python: ${{ steps.filter.outputs.python }}
+      sdk-js: ${{ steps.filter.outputs.sdk-js }}
+    steps:
+      - uses: actions/checkout@v4
+      - uses: dorny/paths-filter@v3
+        id: filter
+        with:
+          filters: |
+            python:
+              - 'libs/langgraph/**'
+              - 'libs/sdk-py/**'
+              - 'libs/cli/**'
+              - 'libs/checkpoint/**'
+              - 'libs/checkpoint-sqlite/**'
+              - 'libs/checkpoint-postgres/**'
+              - 'libs/scheduler-kafka/**'
+              - 'libs/prebuilt/**'
+            sdk-js:
+              - 'libs/sdk-js/**'
+
   lint:
+    needs: changes
     name: cd ${{ matrix.working-directory }}
     strategy:
       matrix:
@@ -33,13 +57,16 @@ jobs:
             "libs/checkpoint-sqlite",
             "libs/checkpoint-postgres",
             "libs/scheduler-kafka",
+            "libs/prebuilt",
           ]
+    if: needs.changes.outputs.python == 'true'
     uses: ./.github/workflows/_lint.yml
     with:
       working-directory: ${{ matrix.working-directory }}
     secrets: inherit
 
   test:
+    needs: changes
     name: cd ${{ matrix.working-directory }}
     strategy:
       matrix:
@@ -49,7 +76,9 @@ jobs:
             "libs/checkpoint",
             "libs/checkpoint-sqlite",
             "libs/checkpoint-postgres",
+            "libs/prebuilt",
           ]
+    if: needs.changes.outputs.python == 'true'
     uses: ./.github/workflows/_test.yml
     with:
       working-directory: ${{ matrix.working-directory }}
@@ -57,17 +86,23 @@ jobs:
 
   # NOTE: we're testing langgraph separately because it requires a different matrix
   test-langgraph:
+    needs: changes
+    if: needs.changes.outputs.python == 'true'
     name: "cd libs/langgraph"
     uses: ./.github/workflows/_test_langgraph.yml
     secrets: inherit
 
   # NOTE: we're testing scheduler-kafka separately because it requires a different matrix
   test-scheduler-kafka:
+    needs: changes
+    if: needs.changes.outputs.python == 'true'
     name: "cd libs/scheduler-kafka"
     uses: ./.github/workflows/_test_scheduler_kafka.yml
     secrets: inherit
 
   check-sdk-methods:
+    needs: changes
+    if: needs.changes.outputs.python == 'true'
     name: "Check SDK methods matching"
     runs-on: ubuntu-latest
     steps:
@@ -79,12 +114,52 @@ jobs:
       - name: Run check_sdk_methods script
         run: python .github/scripts/check_sdk_methods.py
 
+  check-schema:
+    needs: changes
+    if: needs.changes.outputs.python == 'true'
+    name: "Check CLI schema hasn't changed #${{ matrix.python-version }}"
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version:
+          - "3.11"
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: "3.11"
+          poetry-version: ${{ env.POETRY_VERSION }}
+          cache-key: schema-check-cli
+      - name: Install CLI dependencies
+        run: |
+          cd libs/cli
+          poetry install
+      - name: Generate schema and check for changes
+        run: |
+          cd libs/cli
+          # Create a temporary copy of the current schema
+          cp schemas/schema.json schemas/schema.current.json
+          # Generate new schema
+          poetry run python generate_schema.py
+          # Compare the new schema with the original
+          if ! diff -q schemas/schema.json schemas/schema.current.json > /dev/null; then
+            echo "Error: Langgraph.json configuration schema has changed. Please run 'poetry run python generate_schema.py' in the libs/cli directory and commit the changes."
+            diff schemas/schema.json schemas/schema.current.json
+            exit 1
+          fi
+          echo "Schema check passed - no changes detected"
+
   integration-test:
+    needs: changes
+    if: needs.changes.outputs.python == 'true'
     name: CLI integration test
     uses: ./.github/workflows/_integration_test.yml
     secrets: inherit
 
   lint-js:
+    needs: changes
+    if: needs.changes.outputs.sdk-js == 'true'
     runs-on: ubuntu-latest
     strategy:
       matrix:
@@ -109,6 +184,8 @@ jobs:
         run: yarn build
 
   test-js:
+    needs: changes
+    if: needs.changes.outputs.sdk-js == 'true'
     runs-on: ubuntu-latest
     strategy:
       matrix:
@@ -139,6 +216,8 @@ jobs:
         test,
         test-langgraph,
         test-scheduler-kafka,
+        check-sdk-methods,
+        check-schema,
         integration-test,
         test-js,
       ]

.github/workflows/deploy_docs.yml

@@ -10,7 +10,7 @@ on:
   workflow_dispatch:
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "2.1.2"
 
 permissions:
   contents: read
@@ -63,30 +63,19 @@ jobs:
           poetry-version: ${{ env.POETRY_VERSION }}
           cache-key: docs
 
-      - name: Use Node.js
-        uses: actions/setup-node@v3
-        with:
-          node-version: "22"
-          cache: "yarn"
-          cache-dependency-path: docs/yarn.lock
-
       - name: Install dependencies
         run: |
           yarn
           poetry install --with test --with docs --no-root
-          poetry run pip install -U \
-            pytest \
-            pytest-check-links \
-            GitPython \
-            "git+https://${GITHUB_TOKEN}@github.com/langchain-ai/mkdocs-material-insiders.git" \
-            "git+https://github.com/benjamincburns/markdown-exec.git@cc0d39d737e5ffd4b83d23cd8729d7ea16e363c8"
-
-          poetry run jupyter kernelspec list
-          poetry run python3 -m ipykernel install --user --name=python3
-          npm install -g tslab
-          poetry run tslab install --python=python3
-          poetry run jupyter kernelspec list
+          # we run this installation only for internal PRs
+          # as GITHUB_TOKEN is not available for PRs from outside contributors
+          if [ -n "${GITHUB_TOKEN}" ]; then
+            poetry run pip install "git+https://${GITHUB_TOKEN}@github.com/langchain-ai/mkdocs-material-insiders.git"
+          fi
 
+      - name: Run unit tests
+        # Run unit tests on the docs build pipeline
+        run: make tests
       - name: Lint Docs
         # This step lints the docs using the existing linting set up.
         # It should be very fast and should not require any external services.
@@ -94,7 +83,14 @@ jobs:
       - name: Build llms-text
         run: make llms-text
       - name: Build site
-        run: make build-docs
+        run: |
+          # If this is main branch, then we want to download stats. we do this 
+          # with the env variable DOWNLOAD_STATS=true
+          if [ "${{ github.ref }}" == "refs/heads/main" ]; then
+            DOWNLOAD_STATS=true make build-docs
+          else
+            make build-docs
+          fi
         env:
           MKDOCS_GIT_COMMITTERS_APIKEY: ${{ secrets.MKDOCS_GIT_COMMITTERS_APIKEY }}
           OPENAI_API_KEY: sf-proj-1234567890 # fake placeholder, shouldn't actually be used
@@ -103,12 +99,13 @@ jobs:
         env:
           LANGCHAIN_API_KEY: test
         run: |
-          if [ "${{ github.event_name }}" == "schedule" ] || [ "${{ github.event_name }}" == "workflow_dispatch" ] || ([ "${{ github.event_name }}" == "push" ] && [ "${{ github.ref }}" == "refs/heads/main" ]); then
+          if [ "${{ github.event_name }}" == "schedule" ]; then
             echo "Running link check on all HTML files matching notebooks in docs directory..."
             poetry run pytest -v \
               --check-links-ignore "https://(api|web|docs)\.smith\.langchain\.com/.*" \
               --check-links-ignore "https://academy\.langchain\.com/.*" \
               --check-links-ignore "https://x.com/.*" \
+              --check-links-ignore "https://twitter.com/.*" \
               --check-links-ignore "https://github\.com/.*" \
               --check-links-ignore "http://localhost:8123/.*" \
               --check-links-ignore "http://localhost:2024.*" \
@@ -118,6 +115,7 @@ jobs:
               --check-links-ignore "https://openai\.com/.*" \
               --check-links-ignore "https://www\.uber\.com/.*" \
               --check-links-ignore "https://pepy\.tech/.*" \
+              --check-links-ignore "docs/docs/static/wordmark_*" \
               --check-links $(find site -name "index.html" | grep -v 'storm/index.html')
               
           else
@@ -135,8 +133,10 @@ jobs:
                 --check-links-ignore "http://localhost:2024.*" \
                 --check-links-ignore "http://127.0.0.1:.*" \
                 --check-links-ignore "https://x.com/.*" \
+                --check-links-ignore "https://twitter.com/.*" \
                 --check-links-ignore "https://github\.com/.*" \
                 --check-links-ignore "/.*\.(ipynb|html)$" \
+                --check-links-ignore "docs/docs/static/wordmark_*" \
                 --check-links ${CHANGED_FILES} \
                 || ([ $? = 5 ] && exit 0 || exit $?)
             else

.github/workflows/link_check.yml

@@ -12,7 +12,7 @@ on:
   workflow_dispatch:
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "2.1.2"
 
 jobs:
   markdown-link-check:
@@ -42,8 +42,8 @@ jobs:
 
       - 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
+          if ! diff -q README.md libs/langgraph/README.md >/dev/null; then
+          echo "README.md is out of sync with libs/langgraph/README.md"
+          diff -C 3 README.md libs/langgraph/README.md
+          exit 1
+          fi

.github/workflows/release.yml

@@ -10,7 +10,7 @@ on:
 
 env:
   PYTHON_VERSION: "3.11"
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "2.1.2"
 
 jobs:
   build:
@@ -195,7 +195,11 @@ jobs:
               "$PKG_NAME==$VERSION" \
           )
 
-          if [[ "$PKG_NAME" == *checkpoint* ]]; then
+          if [[ "$PKG_NAME" == *prebuilt* ]]; then
+            poetry run pip install langgraph
+          fi
+
+          if [[ "$PKG_NAME" == *checkpoint* || "$PKG_NAME" == *prebuilt* ]]; 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)"

.github/workflows/run_notebooks.yml

@@ -9,7 +9,7 @@ on:
         type: string
         description: "JSON string of changed files"
   schedule:
-    - cron: '0 13 * * *'
+    - cron: "0 13 * * *"
 
 defaults:
   run:
@@ -30,12 +30,12 @@ jobs:
         uses: "./.github/actions/poetry_setup"
         with:
           python-version: 3.11
-          poetry-version: 1.7.1
+          poetry-version: 2.1.2
           cache-key: test-langgraph-notebooks
 
       - name: Install dependencies
         run: |
-          poetry install --with test
+          poetry install --with test --no-root
           poetry run pip install jupyter
 
       - name: Start services
@@ -57,13 +57,13 @@ jobs:
         env:
           # these won't actually be used because of the VCR cassettes
           # but need to set them to avoid triggering getpass()
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-          TAVILY_API_KEY: ${{ secrets.TAVILY_API_KEY }}
-          LANGSMITH_API_KEY: ${{ secrets.LANGSMITH_API_KEY }}
-          NOMIC_API_KEY: ${{ secrets.NOMIC_API_KEY }}
-          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
-          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
+          OPENAI_API_KEY: "very-secret-key"
+          ANTHROPIC_API_KEY: "very-secret-key"
+          TAVILY_API_KEY: "very-secret-key"
+          LANGSMITH_API_KEY: "very-secret-key"
+          NOMIC_API_KEY: "very-secret-key"
+          COHERE_API_KEY: "very-secret-key"
+          FIREWORKS_API_KEY: "very-secret-key"
         run: |
           if [ "${{ github.event_name }}" = "workflow_dispatch" ] || [ "${{ github.event_name }}" = "schedule" ]; then
             echo "Running all notebooks"

.github/workflows/size.yml

@@ -1,29 +0,0 @@
-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
-        # TODO: roll back the web voyager hack
-        run: |
-          large_added_files=$(find ${{ steps.changed-files.outputs.added_files }} -maxdepth 0 -size +1M | grep -v "web_voyager" || true)
-          if [ -n "$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

README.md

@@ -1,339 +1,90 @@
-# 🦜🕸️LangGraph
+<picture class="github-only">
+  <source media="(prefers-color-scheme: light)" srcset="https://langchain-ai.github.io/langgraph/static/wordmark_dark.svg">
+  <source media="(prefers-color-scheme: dark)" srcset="https://langchain-ai.github.io/langgraph/static/wordmark_light.svg">
+  <img alt="LangGraph Logo" src="https://langchain-ai.github.io/langgraph/static/wordmark_dark.svg" width="80%">
+</picture>
 
-![Version](https://img.shields.io/pypi/v/langgraph)
+<div>
+<br>
+</div>
+
+[![Version](https://img.shields.io/pypi/v/langgraph.svg)](https://pypi.org/project/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)
 [![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? See the [JS repo](https://github.com/langchain-ai/langgraphjs) and the [JS docs](https://langchain-ai.github.io/langgraphjs/).
 
-## Overview
+LangGraph — used by Replit, Uber, LinkedIn, GitLab and more — is a low-level orchestration framework for building controllable agents. While langchain provides integrations and composable components to streamline LLM application development, the LangGraph library enables agent orchestration — offering customizable architectures, long-term memory, and human-in-the-loop to reliably handle complex tasks.
 
-[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. Check out an introductory tutorial [here](https://langchain-ai.github.io/langgraph/tutorials/introduction/).
-
-
-LangGraph is inspired by [Pregel](https://research.google/pubs/pub37252/) and [Apache Beam](https://beam.apache.org/). The public interface draws inspiration from [NetworkX](https://networkx.org/documentation/latest/). LangGraph is built by LangChain Inc, the creators of LangChain, but can be used without LangChain.
-
-### Why use LangGraph?
-
-LangGraph powers [production-grade agents](https://www.langchain.com/built-with-langgraph), trusted by Linkedin, Uber, Klarna, GitLab, and many more. LangGraph provides fine-grained control over both the flow and state of your agent applications. It implements a central [persistence layer](https://langchain-ai.github.io/langgraph/concepts/persistence/), enabling features that are common to most agent architectures:
-
-- **Memory**: LangGraph persists arbitrary aspects of your application's state,
-supporting memory of conversations and other updates within and across user
-interactions;
-- **Human-in-the-loop**: Because state is checkpointed, execution can be interrupted
-and resumed, allowing for decisions, validation, and corrections at key stages via
-human input.
-
-Standardizing these components allows individuals and teams to focus on the behavior
-of their agent, instead of its supporting infrastructure.
-
-Through [LangGraph Platform](#langgraph-platform), LangGraph also provides tooling for
-the development, deployment, debugging, and monitoring of your applications.
-
-LangGraph integrates seamlessly with
-[LangChain](https://python.langchain.com/docs/introduction/) and
-[LangSmith](https://docs.smith.langchain.com/) (but does not require them).
-
-To learn more about LangGraph, check out our first LangChain Academy
-course, *Introduction to LangGraph*, available for free
-[here](https://academy.langchain.com/courses/intro-to-langgraph).
-
-### LangGraph Platform
-
-[LangGraph Platform](https://langchain-ai.github.io/langgraph/concepts/langgraph_platform) is infrastructure for deploying LangGraph agents. It is a commercial solution for deploying agentic applications to production, built on the open-source LangGraph framework. The LangGraph Platform consists of several components that work together to support the development, deployment, debugging, and monitoring of LangGraph applications: [LangGraph Server](https://langchain-ai.github.io/langgraph/concepts/langgraph_server) (APIs), [LangGraph SDKs](https://langchain-ai.github.io/langgraph/concepts/sdk) (clients for the APIs), [LangGraph CLI](https://langchain-ai.github.io/langgraph/concepts/langgraph_cli) (command line tool for building the server), and [LangGraph Studio](https://langchain-ai.github.io/langgraph/concepts/langgraph_studio) (UI/debugger).
-
-See deployment options [here](https://langchain-ai.github.io/langgraph/concepts/deployment_options/)
-(includes a free tier).
-
-Here are some common issues that arise in complex deployments, which LangGraph Platform addresses:
-
-- **Streaming support**: LangGraph Server provides [multiple streaming modes](https://langchain-ai.github.io/langgraph/concepts/streaming) optimized for various application needs
-- **Background runs**: Runs agents asynchronously in the background
-- **Support for long running agents**: Infrastructure that can handle long running processes
-- **[Double texting](https://langchain-ai.github.io/langgraph/concepts/double_texting)**: Handle the case where you get two messages from the user before the agent can respond
-- **Handle burstiness**: Task queue for ensuring requests are handled consistently without loss, even under heavy loads
-
-## Installation
-
-```shell
+```bash
 pip install -U langgraph
 ```
 
-## Example
-
-Let's build a tool-calling [ReAct-style](https://langchain-ai.github.io/langgraph/concepts/agentic_concepts/#react-implementation) agent that uses a search tool!
-
-```shell
-pip install langchain-anthropic
-```
-
-```shell
-export ANTHROPIC_API_KEY=sk-...
-```
-
-Optionally, we can set up [LangSmith](https://docs.smith.langchain.com/) for best-in-class observability.
-
-```shell
-export LANGSMITH_TRACING=true
-export LANGSMITH_API_KEY=lsv2_sk_...
-```
-
-The simplest way to create a tool-calling agent in LangGraph is to use `create_react_agent`:
-
-<details open>
-  <summary>High-level implementation</summary>
+To learn more about how to use LangGraph, check out [the docs](https://langchain-ai.github.io/langgraph/). We show a simple example below of how to create a ReAct agent.
 
 ```python
+# This code depends on pip install langchain[anthropic]
 from langgraph.prebuilt import create_react_agent
-from langgraph.checkpoint.memory import MemorySaver
-from langchain_anthropic import ChatAnthropic
-from langchain_core.tools import tool
 
-# Define the tools for the agent to use
-@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]
-model = ChatAnthropic(model="claude-3-5-sonnet-latest", temperature=0)
-
-# Initialize memory to persist state between graph runs
-checkpointer = MemorySaver()
-
-app = create_react_agent(model, tools, checkpointer=checkpointer)
-
-# Use the agent
-final_state = app.invoke(
-    {"messages": [{"role": "user", "content": "what is the weather in sf"}]},
-    config={"configurable": {"thread_id": 42}}
+agent = create_react_agent("anthropic:claude-3-7-sonnet-latest", tools=[search])
+agent.invoke(
+    {"messages": [{"role": "user", "content": "what is the weather in sf"}]}
 )
-final_state["messages"][-1].content
 ```
-```
-"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 <code>"thread_id"</code>, the conversation context is retained via the saved state (i.e. stored list of messages)
-
-```python
-final_state = app.invoke(
-    {"messages": [{"role": "user", "content": "what about ny"}]},
-    config={"configurable": {"thread_id": 42}}
-)
-final_state["messages"][-1].content
-```
-
-```
-"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?"
-```
-</details>
 
 > [!TIP]
-> LangGraph is a **low-level** framework that allows you to implement any custom agent
-architectures. Click on the low-level implementation below to see how to implement a
-tool-calling agent from scratch.
+> Check out [this guide](https://langchain-ai.github.io/langgraph/tutorials/workflows/) that walks through implementing common patterns (workflows and agents) in LangGraph. 
 
-<details>
-<summary>Low-level implementation</summary>
+## Why use LangGraph?
 
-```python
-from typing import Literal
+LangGraph is built for developers who want to build powerful, adaptable AI agents. Developers choose LangGraph for:
 
-from langchain_anthropic import ChatAnthropic
-from langchain_core.tools import tool
-from langgraph.checkpoint.memory import MemorySaver
-from langgraph.graph import END, START, StateGraph, MessagesState
-from langgraph.prebuilt import ToolNode
+- **Reliability and controllability.** Steer agent actions with moderation checks and human-in-the-loop approvals. LangGraph persists context for long-running workflows, keeping your agents on course.
+- **Low-level and extensible.** Build custom agents with fully descriptive, low-level primitives – free from rigid abstractions that limit customization. Design scalable multi-agent systems, with each agent serving a specific role tailored to your use case.
+- **First-class streaming support.** With token-by-token streaming and streaming of intermediate steps, LangGraph gives users clear visibility into agent reasoning and actions as they unfold in real time.
 
+LangGraph is trusted in production and powering agents for companies like:
 
-# Define the tools for the agent to use
-@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."
+- [Klarna](https://blog.langchain.dev/customers-klarna/): Customer support bot for 85 million active users
+- [Elastic](https://www.elastic.co/blog/elastic-security-generative-ai-features): Security AI assistant for threat detection
+- [Uber](https://dpe.org/sessions/ty-smith-adam-huda/this-year-in-ubers-ai-driven-developer-productivity-revolution/): Automated unit test generation
+- [Replit](https://www.langchain.com/breakoutagents/replit): Code generation
+- And many more ([see list here](https://www.langchain.com/built-with-langgraph))
 
+## LangGraph’s ecosystem
 
-tools = [search]
+While LangGraph can be used standalone, it also integrates seamlessly with any LangChain product, giving developers a full suite of tools for building agents. To improve your LLM application development, pair LangGraph with:
 
-tool_node = ToolNode(tools)
+- [LangSmith](http://www.langchain.com/langsmith) — Helpful for agent evals and observability. Debug poor-performing LLM app runs, evaluate agent trajectories, gain visibility in production, and improve performance over time.
+- [LangGraph Platform](https://langchain-ai.github.io/langgraph/concepts/#langgraph-platform) — Deploy and scale agents effortlessly with a purpose-built deployment platform for long running, stateful workflows. Discover, reuse, configure, and share agents across teams — and iterate quickly with visual prototyping in [LangGraph Studio](https://langchain-ai.github.io/langgraph/concepts/langgraph_studio/).
 
-model = ChatAnthropic(model="claude-3-5-sonnet-latest", temperature=0).bind_tools(tools)
+## Pairing with LangGraph Platform
 
-# Define the function that determines whether to continue or not
-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
-    if last_message.tool_calls:
-        return "tools"
-    # Otherwise, we stop (reply to the user)
-    return END
+While LangGraph is our open-source agent orchestration framework, enterprises that need scalable agent deployment can benefit from [LangGraph Platform](https://langchain-ai.github.io/langgraph/concepts/langgraph_platform/).
 
+LangGraph Platform can help engineering teams:
 
-# Define the function that calls the model
-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
-    return {"messages": [response]}
+- **Accelerate agent development**: Quickly create agent UXs with configurable templates and [LangGraph Studio](https://langchain-ai.github.io/langgraph/concepts/langgraph_studio/) for visualizing and debugging agent interactions.
+- **Deploy seamlessly**: We handle the complexity of deploying your agent. LangGraph Platform includes robust APIs for memory, threads, and cron jobs plus auto-scaling task queues & servers.
+- **Centralize agent management & reusability**: Discover, reuse, and manage agents across the organization. Business users can also modify agents without coding.
 
+## Additional resources
 
-# Define a new graph
-workflow = StateGraph(MessagesState)
+- [LangChain Academy](https://academy.langchain.com/courses/intro-to-langgraph): Learn the basics of LangGraph in our free, structured course.
+- [Tutorials](https://langchain-ai.github.io/langgraph/tutorials/): Simple walkthroughs with guided examples on getting started with LangGraph.
+- [Templates](https://langchain-ai.github.io/langgraph/concepts/template_applications/): Pre-built reference apps for common agentic workflows (e.g. ReAct agent, memory, retrieval etc.) that can be cloned and adapted.
+- [How-to Guides](https://langchain-ai.github.io/langgraph/how-tos/): Quick, actionable code snippets for topics such as streaming, adding memory & persistence, and design patterns (e.g. branching, subgraphs, etc.).
+- [API Reference](https://langchain-ai.github.io/langgraph/reference/graphs/): Detailed reference on core classes, methods, how to use the graph and checkpointing APIs, and higher-level prebuilt components.
+- [Built with LangGraph](https://www.langchain.com/built-with-langgraph): Hear how industry leaders use LangGraph to ship powerful, production-ready AI applications.
 
-# Define the two nodes we will cycle between
-workflow.add_node("agent", call_model)
-workflow.add_node("tools", tool_node)
+## Acknowledgements
 
-# Set the entrypoint as `agent`
-# This means that this node is the first one called
-workflow.add_edge(START, "agent")
-
-# We now add a conditional edge
-workflow.add_conditional_edges(
-    # First, we define the start node. We use `agent`.
-    # This means these are the edges taken after the `agent` node is called.
-    "agent",
-    # Next, we pass in the function that will determine which node is called next.
-    should_continue,
-)
-
-# We now add a normal edge from `tools` to `agent`.
-# This means that after `tools` is called, `agent` node is called next.
-workflow.add_edge("tools", 'agent')
-
-# Initialize memory to persist state between graph runs
-checkpointer = MemorySaver()
-
-# Finally, we compile it!
-# This compiles it into a LangChain Runnable,
-# meaning you can use it as you would any other runnable.
-# Note that we're (optionally) passing the memory when compiling the graph
-app = workflow.compile(checkpointer=checkpointer)
-
-# Use the agent
-final_state = app.invoke(
-    {"messages": [{"role": "user", "content": "what is the weather in sf"}]},
-    config={"configurable": {"thread_id": 42}}
-)
-final_state["messages"][-1].content
-```
-
-<b>Step-by-step Breakdown</b>:
-
-<details>
-<summary>Initialize the model and tools.</summary>
-<ul>
-  <li>
-    We use <code>ChatAnthropic</code> as our LLM. <strong>NOTE:</strong> we need to 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 <code>.bind_tools()</code> method.
-  </li>
-  <li>
-    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 <a href="https://python.langchain.com/docs/how_to/custom_tools/">here</a>.
-  </li>
-</ul>
-</details>
-
-<details>
-<summary>Initialize graph with state.</summary>
-
-<ul>
-    <li>We initialize graph (<code>StateGraph</code>) by passing state schema (in our case <code>MessagesState</code>)</li>
-    <li><code>MessagesState</code> is a prebuilt state schema that has one attribute -- a list of LangChain <code>Message</code> objects, as well as logic for merging the updates from each node into the state.</li>
-</ul>
-</details>
-
-<details>
-<summary>Define graph nodes.</summary>
-
-There are two main nodes we need:
-
-<ul>
-    <li>The <code>agent</code> node: responsible for deciding what (if any) actions to take.</li>
-    <li>The <code>tools</code> node that invokes tools: if the agent decides to take an action, this node will then execute that action.</li>
-</ul>
-</details>
-
-<details>
-<summary>Define entry point and graph edges.</summary>
-
-First, we need to set the entry point for graph execution - <code>agent</code> node.
-
-Then we define one normal and one conditional edge. Conditional edge means that the destination depends on the contents of the graph's state (<code>MessagesState</code>). In our case, the destination is not known until the agent (LLM) decides.
-
-<ul>
-  <li>Conditional edge: after the agent is called, we should either:
-    <ul>
-      <li>a. Run tools if the agent said to take an action, OR</li>
-      <li>b. Finish (respond to the user) if the agent did not ask to run tools</li>
-    </ul>
-  </li>
-  <li>Normal edge: after the tools are invoked, the graph should always return to the agent to decide what to do next</li>
-</ul>
-</details>
-
-<details>
-<summary>Compile the graph.</summary>
-
-<ul>
-  <li>
-    When we compile the graph, we turn it into a LangChain 
-    <a href="https://python.langchain.com/docs/concepts/runnables/">Runnable</a>, 
-    which automatically enables calling <code>.invoke()</code>, <code>.stream()</code> and <code>.batch()</code> 
-    with your inputs
-  </li>
-  <li>
-    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 <code>MemorySaver</code> - 
-    a simple in-memory checkpointer
-  </li>
-</ul>
-</details>
-
-<details>
-<summary>Execute the graph.</summary>
-
-<ol>
-  <li>LangGraph adds the input message to the internal state, then passes the state to the entrypoint node, <code>"agent"</code>.</li>
-  <li>The <code>"agent"</code> node executes, invoking the chat model.</li>
-  <li>The chat model returns an <code>AIMessage</code>. LangGraph adds this to the state.</li>
-  <li>Graph cycles the following steps until there are no more <code>tool_calls</code> on <code>AIMessage</code>:
-    <ul>
-      <li>If <code>AIMessage</code> has <code>tool_calls</code>, <code>"tools"</code> node executes</li>
-      <li>The <code>"agent"</code> node executes again and returns <code>AIMessage</code></li>
-    </ul>
-  </li>
-  <li>Execution progresses to the special <code>END</code> value and outputs the final state. And as a result, we get a list of all our chat messages as output.</li>
-</ol>
-</details>
-
-</details>
-
-## Documentation
-
-* [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/high_level/): 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.
-* [LangGraph Platform](https://langchain-ai.github.io/langgraph/concepts/#langgraph-platform): LangGraph Platform is a commercial solution for deploying agentic applications in production, built on the open-source LangGraph framework.
-
-## Resources
-
-* [Built with LangGraph](https://www.langchain.com/built-with-langgraph): Hear how industry leaders use LangGraph to ship powerful, production-ready AI applications.
-
-## Contributing
-
-For more information on how to contribute, see [here](https://github.com/langchain-ai/langgraph/blob/main/CONTRIBUTING.md).
+LangGraph is inspired by [Pregel](https://research.google/pubs/pub37252/) and [Apache Beam](https://beam.apache.org/). The public interface draws inspiration from [NetworkX](https://networkx.org/documentation/latest/). LangGraph is built by LangChain Inc, the creators of LangChain, but can be used without LangChain.

docs/Makefile

@@ -1,4 +1,4 @@
-.PHONY: lint-docs format-docs build-docs serve-docs serve-clean-docs clean-docs codespell build-typedoc llms-text build-prebuilt
+.PHONY: lint-docs format-docs build-docs serve-docs serve-clean-docs clean-docs codespell build-typedoc llms-text build-prebuilt tests
 
 build-typedoc:
 	cd ../libs/sdk-js && yarn install --include-dev && yarn typedoc
@@ -10,14 +10,22 @@ build-prebuilt:
 	# Use to create an update to date prebuilt page.
 	# Looks up download stats for each of the prebuilt packages and
 	# generates the final prebuilt page.
-	poetry run python -m _scripts.third_party_page.get_download_stats stats.yml
-	poetry run python -m _scripts.third_party_page.create_third_party_page stats.yml docs/prebuilt.md --language python
+	@if [ "$(DOWNLOAD_STATS)" = "true" ]; then \
+		set -x; \
+		poetry run python -m _scripts.third_party_page.get_download_stats stats.yml; \
+		set +x; \
+	else \
+		set -x; \
+		poetry run python -m _scripts.third_party_page.get_download_stats --fake stats.yml; \
+		set +x; \
+	fi
+	poetry run python -m _scripts.third_party_page.create_third_party_page stats.yml docs/agents/prebuilt.md --language python
 
 build-docs: build-typedoc build-prebuilt
 	poetry run python -m mkdocs build --clean -f mkdocs.yml --strict
 
 llms-text:
-	poetry run python _scripts/generate_llms_text.py docs/llms-full.txt
+	poetry run python -m _scripts.generate_llms_text docs/llms-full.txt
 
 install-vercel-deps:
 	dnf install -y python3.11
@@ -26,11 +34,10 @@ install-vercel-deps:
 	# don't use vercel's python - it wasn't compiled with sqlite support, and it fails when installing ipython's kernel
 	poetry env use /usr/bin/python3.11
 	poetry install --with docs --with test --no-root
-	poetry run pip install "git+https://github.com/benjamincburns/markdown-exec.git@cc0d39d737e5ffd4b83d23cd8729d7ea16e363c8"
-	poetry run python3 -m ipykernel install --name=python3
-	npm install -g tslab
-	poetry run tslab install --python=python3
-	poetry run jupyter kernelspec list
+
+tests:
+	# Run unit tests
+	poetry run pytest tests/unit_tests
 
 
 vercel-build-docs: install-vercel-deps

docs/README.md

@@ -14,6 +14,8 @@ To run the documentation server locally you can run:
 make serve-docs
 ```
 
+This will start the documentation server on [http://127.0.0.1:8000/langgraph/](http://127.0.0.1:8000/langgraph/).
+
 ## Execute notebooks
 
 If you would like to automatically execute all of the notebooks, to mimic the "Run notebooks" GHA, you can run:

docs/_scripts/assets/nock_setup_preamble.ts

@@ -1,75 +0,0 @@
-import nock, { Definition } from "nock";
-import msgpack from "msgpack-lite";
-import zlib from "node:zlib";
-import fs from "node:fs/promises";
-import { Buffer } from "node:buffer";
-
-// deno style imports here because we're running this in the deno jupyter kernel
-
-interface NockCassetteData {
-  hash: string;
-  entries: Definition[];
-}
-
-// Utility functions for compression & serialization
-function compressData(data: NockCassetteData, compressionLevel = 9): string {
-  const packed = msgpack.encode(data);
-  const compressed = zlib.deflateSync(packed, { level: compressionLevel });
-  return compressed.toString("base64");
-}
-
-function decompressData(compressedString: string): NockCassetteData {
-  const decoded = Buffer.from(compressedString, "base64");
-  const decompressed = zlib.inflateSync(decoded);
-  return msgpack.decode(decompressed) as NockCassetteData;
-}
-
-// deno-lint-ignore no-unused-vars
-class HashedCassette {
-  private recording = true;
-
-  constructor(
-    private readonly cassettePath: string,
-    private readonly hash: string
-  ) {}
-
-  async enter() {
-    try {
-      const rawCassette = await fs.readFile(this.cassettePath, "utf-8");
-      const data = decompressData(rawCassette);
-      if (data.hash === this.hash) {
-        this.recording = false;
-        nock.disableNetConnect();
-        nock.define(data.entries);
-        return;
-      }
-    } catch (error) {
-      if (error instanceof Error && error.message.includes("ENOENT")) {
-        this.recording = true;
-      } else {
-        throw error;
-      }
-    }
-
-    nock.recorder.rec({
-      dont_print: true,
-      output_objects: true,
-    });
-  }
-
-  async exit() {
-    if (this.recording) {
-      const entries = nock.recorder.play() as Definition[];
-      const data = {
-        hash: this.hash,
-        entries,
-      };
-      const compressed = compressData(data);
-      await fs.writeFile(this.cassettePath, compressed);
-    } else {
-      nock.enableNetConnect();
-      nock.restore();
-      nock.cleanAll();
-    }
-  }
-}

docs/_scripts/assets/vcr_setup_preamble.py

@@ -1,107 +0,0 @@
-import base64
-import os
-import zlib
-from types import TracebackType
-from typing import Optional, Any, Type
-
-import msgpack
-import vcr
-
-os.environ.pop("LANGCHAIN_TRACING_V2", None)
-custom_vcr = vcr.VCR()
-
-
-def compress_data(data: Any, compression_level: int = 9) -> str:
-    packed = msgpack.packb(data, use_bin_type=True)
-    compressed = zlib.compress(packed, level=compression_level)
-    return base64.b64encode(compressed).decode("utf-8")
-
-
-def decompress_data(compressed_string: str) -> Any:
-    decoded = base64.b64decode(compressed_string)
-    decompressed = zlib.decompress(decoded)
-    return msgpack.unpackb(decompressed, raw=False)
-
-
-class AdvancedCompressedSerializer:
-    def serialize(self, cassette_dict: Any) -> str:
-        return compress_data(cassette_dict)
-
-    def deserialize(self, cassette_string: str) -> Any:
-        return decompress_data(cassette_string)
-
-
-custom_vcr.register_serializer("advanced_compressed", AdvancedCompressedSerializer())
-custom_vcr.serializer = "advanced_compressed"
-
-
-class HashedCassette:
-    def __init__(self, cassette_path: str, hash_value: str) -> None:
-        """A context manager for using VCR cassettes with an embedded hash value.
-
-        Args:
-            cassette_path (str): The file path of the cassette (independent of hash).
-            hash_value (str): The expected hash value (e.g. a uuid string).
-
-        This class provides a context manager for using VCR cassettes with an embedded hash value.
-        The hash value is used to ensure that the cassette matches the expected state, and if not,
-        the cassette is removed or updated with the new hash value.
-        """
-        self.cassette_path: str = cassette_path
-        self.hash_value: str = hash_value
-        self.vcr: vcr.VCR = custom_vcr
-        self.cassette_context: Optional[Any] = None
-        self.exited: bool = False
-
-    def __enter__(self) -> Any:
-        self.exited: bool = False
-        # Get the serializer instance from the VCR instance.
-        serializer = self.vcr.serializers[self.vcr.serializer]
-        # If the cassette file exists, check its embedded hash.
-        if os.path.exists(self.cassette_path):
-            with open(self.cassette_path, "r") as f:
-                content = f.read()
-            try:
-                cassette_data = serializer.deserialize(content)
-            except Exception as e:
-                os.remove(self.cassette_path)
-            else:
-                existing_hash = cassette_data.get("cassette_hash")
-                if existing_hash != self.hash_value:
-                    os.remove(self.cassette_path)
-        # Now enter the VCR cassette context.
-        self.cassette_context = custom_vcr.use_cassette(
-            self.cassette_path,
-            filter_headers=["x-api-key", "authorization"],
-            record_mode="once",
-            serializer="advanced_compressed",
-        )
-        return self.cassette_context.__enter__()
-
-    def __exit__(
-        self,
-        exc_type: Optional[Type[BaseException]] = None,
-        exc_val: Optional[BaseException] = None,
-        exc_tb: Optional[TracebackType] = None,
-    ) -> Optional[bool]:
-        if self.exited:
-            return
-        self.exited = True
-        # Exit the VCR cassette context.
-        result = self.cassette_context.__exit__(exc_type, exc_val, exc_tb)
-        serializer = self.vcr.serializers[self.vcr.serializer]
-        # If a cassette was recorded (or updated), open and update its hash.
-        if os.path.exists(self.cassette_path):
-            with open(self.cassette_path, "r") as f:
-                content = f.read()
-            try:
-                cassette_data = serializer.deserialize(content)
-            except Exception as e:
-                return result
-            # Update the cassette data with the expected hash.
-            if cassette_data.get("cassette_hash") != self.hash_value:
-                cassette_data["cassette_hash"] = self.hash_value
-                serialized_data = serializer.serialize(cassette_data)
-                with open(self.cassette_path, "w") as f:
-                    f.write(serialized_data)
-        return result

docs/_scripts/generate_api_reference_links.py

@@ -1,9 +1,9 @@
+import ast
 import importlib
-import inspect
 import logging
 import re
 from functools import lru_cache
-from typing import List, Literal, Optional
+from typing import List, Optional
 
 from typing_extensions import TypedDict
 
@@ -39,22 +39,26 @@ MANUAL_API_REFERENCES_LANGGRAPH = [
     (["langgraph.graph"], "langgraph.graph.message", "add_messages", "graphs"),
     (["langgraph.graph"], "langgraph.graph.state", "StateGraph", "graphs"),
     (["langgraph.graph"], "langgraph.graph.state", "CompiledStateGraph", "graphs"),
-    ([], "langgraph.types", "StreamMode", "types"),
     (["langgraph.graph"], "langgraph.constants", "START", "constants"),
     (["langgraph.graph"], "langgraph.constants", "END", "constants"),
     (["langgraph.constants"], "langgraph.types", "Send", "types"),
     (["langgraph.constants"], "langgraph.types", "Interrupt", "types"),
     (["langgraph.constants"], "langgraph.types", "interrupt", "types"),
     (["langgraph.constants"], "langgraph.types", "Command", "types"),
+    (["langgraph.config"], "langgraph.config", "get_stream_writer", "config"),
+    (["langgraph.config"], "langgraph.config", "get_store", "config"),
     (["langgraph.func"], "langgraph.func", "entrypoint", "func"),
     (["langgraph.func"], "langgraph.func", "task", "func"),
-    ([], "langgraph.types", "RetryPolicy", "types"),
+    (["langgraph.types"], "langgraph.types", "RetryPolicy", "types"),
+    (["langgraph.types"], "langgraph.types", "StreamMode", "types"),
+    (["langgraph.types"], "langgraph.types", "StreamWriter", "types"),
     ([], "langgraph.checkpoint.base", "Checkpoint", "checkpoints"),
     ([], "langgraph.checkpoint.base", "CheckpointMetadata", "checkpoints"),
     ([], "langgraph.checkpoint.base", "BaseCheckpointSaver", "checkpoints"),
     ([], "langgraph.checkpoint.base", "SerializerProtocol", "checkpoints"),
     ([], "langgraph.checkpoint.serde.jsonplus", "JsonPlusSerializer", "checkpoints"),
     ([], "langgraph.checkpoint.memory", "MemorySaver", "checkpoints"),
+    ([], "langgraph.checkpoint.memory", "InMemorySaver", "checkpoints"),
     ([], "langgraph.checkpoint.sqlite.aio", "AsyncSqliteSaver", "checkpoints"),
     ([], "langgraph.checkpoint.sqlite", "SqliteSaver", "checkpoints"),
     ([], "langgraph.checkpoint.postgres.aio", "AsyncPostgresSaver", "checkpoints"),
@@ -68,34 +72,19 @@ WELL_KNOWN_LANGGRAPH_OBJECTS = {
 }
 
 
-def _make_regular_expression(pkg_prefix: str) -> re.Pattern:
-    if not pkg_prefix.isidentifier():
-        raise ValueError(f"Invalid package prefix: {pkg_prefix}")
-    return re.compile(
-        r"from\s+(" + pkg_prefix + "(?:_\w+)?(?:\.\w+)*?)\s+import\s+"
-        r"((?:\w+(?:,\s*)?)*"  # Match zero or more words separated by a comma+optional ws
-        r"(?:\s*\(.*?\))?)",  # Match optional parentheses block
-        re.DOTALL,  # Match newlines as well
-    )
-
-
-# Regular expression to match langchain import lines
-_IMPORT_LANGCHAIN_RE = _make_regular_expression("langchain")
-_IMPORT_LANGGRAPH_RE = _make_regular_expression("langgraph")
-
-
 @lru_cache(maxsize=10_000)
 def _get_full_module_name(module_path: str, class_name: str) -> Optional[str]:
     """Get full module name using inspect, with LRU cache to memoize results."""
     try:
         module = importlib.import_module(module_path)
-        class_ = getattr(module, class_name)
-        module = inspect.getmodule(class_)
-        if module is None:
-            # For constants, inspect.getmodule() might return None
-            # In this case, we'll return the original module_path
+        symbol = getattr(module, class_name)
+        # First check the __module__ attribute on the symbol.
+        mod_name = getattr(symbol, "__module__", None)
+        # If __module__ is not set or comes from typing,
+        # assume the definition is in module_path.
+        if mod_name is None or mod_name.startswith("typing"):
             return module_path
-        return module.__name__
+        return mod_name
     except AttributeError as e:
         logger.warning(f"API Reference: Could not find module for {class_name}, {e}")
         return None
@@ -104,142 +93,131 @@ def _get_full_module_name(module_path: str, class_name: str) -> Optional[str]:
         return None
 
 
-def _get_doc_title(data: str, file_name: str) -> str:
-    try:
-        return re.findall(r"^#\s*(.*)", data, re.MULTILINE)[0]
-    except IndexError:
-        pass
-    # Parse the rst-style titles
-    try:
-        return re.findall(r"^(.*)\n=+\n", data, re.MULTILINE)[0]
-    except IndexError:
-        return file_name
-
-
 class ImportInformation(TypedDict):
     imported: str  # The name of the class that was imported.
     source: str  # The full module path from which the class was imported.
     docs: str  # The URL pointing to the class's documentation.
-    title: str  # The title of the document where the import is used.
+    path: str  # The path of the file where the markdown content originated.
 
 
-def _get_imports(
-    code: str, doc_title: str, package_ecosystem: Literal["langchain", "langgraph"]
-) -> List[ImportInformation]:
-    """Get imports from the given code block.
-
-    Args:
-        code: Python code block from which to extract imports
-        doc_title: Title of the document
-        package_ecosystem: "langchain" or "langgraph". The two live in different
-            repositories and have separate documentation sites.
-
-    Returns:
-        List of import information for the given code block
-    """
-    imports = []
-
-    if package_ecosystem == "langchain":
-        pattern = _IMPORT_LANGCHAIN_RE
-    elif package_ecosystem == "langgraph":
-        pattern = _IMPORT_LANGGRAPH_RE
-    else:
-        raise ValueError(f"Invalid package ecosystem: {package_ecosystem}")
-
-    for import_match in pattern.finditer(code):
-        module = import_match.group(1)
-        if "pydantic_v1" in module:
-            continue
-        imports_str = (
-            import_match.group(2).replace("(\n", "").replace("\n)", "")
-        )  # Handle newlines within parentheses
-        # remove any newline and spaces, then split by comma
-        imported_classes = [
-            imp.strip()
-            for imp in re.split(r",\s*", imports_str.replace("\n", ""))
-            if imp.strip()
-        ]
-        for class_name in imported_classes:
-            module_path = _get_full_module_name(module, class_name)
-            if not module_path:
-                continue
-            if len(module_path.split(".")) < 2:
-                continue
-
-            if package_ecosystem == "langchain":
-                pkg = module_path.split(".")[0].replace("langchain_", "")
-                top_level_mod = module_path.split(".")[1]
-
-                url = (
-                    _LANGCHAIN_API_REFERENCE
-                    + pkg
-                    + "/"
-                    + top_level_mod
-                    + "/"
-                    + module_path
-                    + "."
-                    + class_name
-                    + ".html"
-                )
-            elif package_ecosystem == "langgraph":
-                if (module, class_name) not in WELL_KNOWN_LANGGRAPH_OBJECTS:
-                    # Likely not documented yet
-                    continue
-
-                source_module, namespace = WELL_KNOWN_LANGGRAPH_OBJECTS[
-                    (module, class_name)
-                ]
-                url = (
-                    _LANGGRAPH_API_REFERENCE
-                    + namespace
-                    + "/#"
-                    + source_module
-                    + "."
-                    + class_name
-                )
-            else:
-                raise ValueError(f"Invalid package ecosystem: {package_ecosystem}")
-
-            # Add the import information to our list
-            imports.append(
-                {
-                    "imported": class_name,
-                    "source": module,
-                    "docs": url,
-                    "title": doc_title,
-                }
-            )
-
-    return imports
-
-
-def get_imports(code: str, doc_title: str) -> List[ImportInformation]:
+def get_imports(code: str, path: str) -> List[ImportInformation]:
     """Retrieve all import references from the given code for specified ecosystems.
 
     Args:
         code: The source code from which to extract import references.
-        doc_title: The documentation title associated with the code.
+        path: The path of the file where the markdown content originated.
 
     Returns:
         A list of import information for each import found.
     """
-    ecosystems = ["langchain", "langgraph"]
-    all_imports = []
-    for package_ecosystem in ecosystems:
-        all_imports.extend(_get_imports(code, doc_title, package_ecosystem))
-    return all_imports
+    # Parse the code into an AST.
+    try:
+        tree = ast.parse(code)
+    except SyntaxError:
+        return []
+
+    found_imports = []
+
+    # Walk through the AST and process ImportFrom nodes.
+    for node in ast.walk(tree):
+        if isinstance(node, ast.ImportFrom):
+            # node.module is the source module.
+            if node.module is None:
+                continue
+            for alias in node.names:
+                if not (
+                    node.module.startswith("langchain")
+                    or node.module.startswith("langgraph")
+                ):
+                    continue
+
+                found_imports.append(
+                    {
+                        "source": node.module,
+                        # alias.name is the original name even if an alias exists.
+                        "imported": alias.name,
+                    }
+                )
+
+    imports: list[ImportInformation] = []
+
+    for found_import in found_imports:
+        module = found_import["source"]
+
+        if module.startswith("langchain"):
+            # Handles things like `langchain` or `langchain_anthropic`
+            package_ecosystem = "langchain"
+        elif module.startswith("langgraph"):
+            package_ecosystem = "langgraph"
+        else:
+            continue
+
+        class_name = found_import["imported"]
+        module_path = _get_full_module_name(module, class_name)
+        if not module_path:
+            continue
+        if len(module_path.split(".")) < 2:
+            continue
+
+        if package_ecosystem == "langchain":
+            pkg = module_path.split(".")[0].replace("langchain_", "")
+            top_level_mod = module_path.split(".")[1]
+
+            url = (
+                _LANGCHAIN_API_REFERENCE
+                + pkg
+                + "/"
+                + top_level_mod
+                + "/"
+                + module_path
+                + "."
+                + class_name
+                + ".html"
+            )
+        elif package_ecosystem == "langgraph":
+            if (module, class_name) not in WELL_KNOWN_LANGGRAPH_OBJECTS:
+                # Likely not documented yet
+                continue
+
+            source_module, namespace = WELL_KNOWN_LANGGRAPH_OBJECTS[
+                (module, class_name)
+            ]
+            url = (
+                _LANGGRAPH_API_REFERENCE
+                + namespace
+                + "/#"
+                + source_module
+                + "."
+                + class_name
+            )
+        else:
+            raise ValueError(f"Invalid package ecosystem: {package_ecosystem}")
+
+        # Add the import information to our list
+        imports.append(
+            {
+                "imported": class_name,
+                "source": module,
+                "docs": url,
+                "path": path,
+            }
+        )
+
+    return imports
 
 
-def update_markdown_with_imports(markdown: str) -> str:
+def update_markdown_with_imports(markdown: str, path: str) -> str:
     """Update markdown to include API reference links for imports in Python code blocks.
 
-    This function scans the markdown content for Python code blocks, extracts any imports, and appends links to their API documentation.
+    This function scans the markdown content for Python code blocks, extracts any
+    imports, and appends links to their API documentation.
 
     Args:
         markdown: The markdown content to process.
+        path: The path of the file where the markdown content originated.
 
     Returns:
-        Updated markdown with API reference links appended to Python code blocks.
+        Updated markdown with API reference links prepended to Python code blocks.
 
     Example:
         Given a markdown with a Python code block:
@@ -247,10 +225,12 @@ def update_markdown_with_imports(markdown: str) -> str:
         ```python
         from langchain.nlp import TextGenerator
         ```
-        This function will append an API reference link to the `TextGenerator` class from the `langchain.nlp` module if it's recognized.
+        This function will append an API reference link to the `TextGenerator` class
+        from the `langchain.nlp` module if it's recognized.
     """
     code_block_pattern = re.compile(
-        r'(?P<indent>[ \t]*)```(?P<language>python|py)\n(?P<code>.*?)\n(?P=indent)```', re.DOTALL
+        r"(?P<indent>[ \t]*)```(?P<language>python|py)\n(?P<code>.*?)\n(?P=indent)```",
+        re.DOTALL,
     )
 
     def replace_code_block(match: re.Match) -> str:
@@ -260,11 +240,10 @@ def update_markdown_with_imports(markdown: str) -> str:
             match (re.Match): The regex match object containing the code block.
 
         Returns:
-            str: The modified code block with API reference links appended if applicable.
+            str: The modified code block with API reference links prepended if applicable.
         """
-        indent = match.group('indent')
-        code_block = match.group('code')
-        language = match.group('language')  # Preserve the language from the regex match
+        indent = match.group("indent")
+        code_block = match.group("code")
         # Retrieve import information from the code block
         imports = get_imports(code_block, "__unused__")
 
@@ -274,11 +253,11 @@ def update_markdown_with_imports(markdown: str) -> str:
             return original_code_block
 
         # Generate API reference links for each import
-        api_links = ' | '.join(
+        api_links = " | ".join(
             f'<a href="{imp["docs"]}">{imp["imported"]}</a>' for imp in imports
         )
-        # Return the code block with appended API reference links
-        return f'{original_code_block}\n\n{indent}API Reference: {api_links}'
+        # Return the code block with prepended API reference links
+        return f"{indent}API Reference: {api_links}\n\n{original_code_block}"
 
     # Apply the replace_code_block function to all matches in the markdown
     updated_markdown = code_block_pattern.sub(replace_code_block, markdown)

docs/_scripts/generate_llms_text.py

@@ -2,12 +2,11 @@
 
 import glob
 import os
-import pathlib
 
 from mkdocs.structure.files import File
 from mkdocs.structure.pages import Page
 
-from notebook_hooks import _on_page_markdown_with_config
+from _scripts.notebook_hooks import _on_page_markdown_with_config
 
 HERE = os.path.dirname(os.path.abspath(__file__))
 # Get source directory (parent of HERE / docs)

docs/_scripts/notebook_convert.py

@@ -1,36 +1,238 @@
-import argparse
+import ast
 import os
 import re
 from pathlib import Path
-from typing import Literal, Optional
+from typing import Literal
 
 import nbformat
 from nbconvert.exporters import MarkdownExporter
 from nbconvert.preprocessors import Preprocessor
 
 
+def _uses_input(source: str) -> bool:
+    """Parse the source code to determine if it uses the input() function."""
+    try:
+        tree = ast.parse(source)
+    except SyntaxError:
+        # If there's a syntax error, assume input() might be present to be safe.
+        return False
+
+    for node in ast.walk(tree):
+        if isinstance(node, ast.Call):
+            # Check if the function called is named 'input'
+            if isinstance(node.func, ast.Name) and node.func.id == "input":
+                return True
+    return False
+
+
+def _rewrite_cell_magic(code: str) -> str:
+    """Process a code block that uses cell magic.:w
+
+    - Lines starting with "%%capture" are ignored.
+    - Lines starting with "%pip" are rewritten by removing the leading "%" character.
+    - Any other non-empty line causes a NotImplementedError.
+
+    Args:
+        code (str): The original code block.
+
+    Returns:
+        str: The transformed code block.
+
+    Raises:
+        NotImplementedError: If a line doesn't start with either "%%capture" or "%pip".
+    """
+    rewritten_lines = []
+
+    for line in code.splitlines():
+        stripped = line.strip()
+        # Skip empty lines
+        if not stripped:
+            continue
+        # Ignore %%capture lines
+        if stripped.startswith("%%capture"):
+            continue
+        # Rewrite %pip lines by dropping the '%'
+        elif stripped.startswith("%pip"):
+            # Drop the leading '%' character
+            rewritten_lines.append(stripped[1:])
+        # Anything else is not supported
+        else:
+            raise NotImplementedError(f"Unhandled line: {line}")
+
+    return "\n".join(rewritten_lines)
+
+
+class PrintCallVisitor(ast.NodeVisitor):
+    """
+    This visitor sets self.has_print to True if it encounters a call
+    to a print within the global scope.
+
+    This should catch calls to print(), print_stream(), etc. (Prefixed with "print").
+
+    May have some false positives, but it's not meant to be perfect.
+
+    Temporary code for notebook conversion.
+    """
+
+    def __init__(self):
+        self.has_print = False
+        self.scope_level = 0  # counter to track whether we're inside a def/lambda
+
+    def visit_FunctionDef(self, node):
+        self.scope_level += 1
+        self.generic_visit(node)
+        self.scope_level -= 1
+
+    def visit_AsyncFunctionDef(self, node):
+        self.scope_level += 1
+        self.generic_visit(node)
+        self.scope_level -= 1
+
+    def visit_Lambda(self, node):
+        self.scope_level += 1
+        self.generic_visit(node)
+        self.scope_level -= 1
+
+    def visit_ClassDef(self, node):
+        self.scope_level += 1
+        self.generic_visit(node)
+        self.scope_level -= 1
+
+    def visit_Call(self, node):
+        # Only consider calls when not inside a function definition.
+        if self.scope_level == 0:
+            if isinstance(node.func, ast.Name) and node.func.id.startswith("print"):
+                self.has_print = True
+        self.generic_visit(node)
+
+
+def _has_output(source: str) -> bool:
+    """Determine if the code block is expected to produce output.
+
+    Args:
+        source (str): The source code of the code block.
+
+    Returns:
+        True if the code block is expected to produce output, False otherwise.
+
+        Must meet the following conditions:
+
+        1. There is a call to a printing function (name starts with "print")
+           that is not inside a function definition.
+        2. The last top-level statement is an expression that is valid if:
+         - It is any expression (including calls) AND
+         - It is NOT a call to `display(...)`.
+
+        `display` isn't handled currently by markdown-exec
+    """
+    try:
+        tree = ast.parse(source)
+    except SyntaxError:
+        return False
+
+    # Condition (1): Check for a global print-like call.
+    visitor = PrintCallVisitor()
+    visitor.visit(tree)
+    condition_a = visitor.has_print
+
+    # Condition (2): Check the last top-level statement.
+    condition_b = False
+    if tree.body:
+        last_stmt = tree.body[-1]
+        if isinstance(last_stmt, ast.Expr):
+            # If the expression is a call, ensure it's not a call to "display"
+            if isinstance(last_stmt.value, ast.Call):
+                if (
+                    isinstance(last_stmt.value.func, ast.Name)
+                    and last_stmt.value.func.id == "display"
+                ):
+                    condition_b = False  # exclude display-wrapped expressions
+                else:
+                    condition_b = True
+            else:
+                # Any other expression qualifies.
+                condition_b = True
+
+    return condition_a or condition_b
+
+
+def _convert_links_in_markdown(markdown: str) -> str:
+    """Convert links present in notebook markdown cells to standardized format.
+
+    We want to update markdown links code cells by linking to markdown
+    files rather than assuming that the link is to the finalized HTML.
+
+    This code is needed temporarily since the markdown links that are present
+    in ipython notebooks do not follow the same conventions as regular markdown
+    files in mkdocs (which should link to a .md file).
+    """
+
+    # Define the regex pattern in parts for clarity:
+    pattern = (
+        r"(?<!!)"  # Negative lookbehind: ensure the link is not an image (i.e., doesn't start with "!")
+        r"\["  # Literal '[' indicating the start of the link text.
+        r"(?P<text>[^\]]*)"  # Named group 'text': match any characters except ']', representing the link text.
+        r"\]"  # Literal ']' indicating the end of the link text.
+        r"\("  # Literal '(' indicating the start of the URL.
+        r"(?![^\)]*//)"  # Negative lookahead: ensure that the URL does not contain '//' (skip absolute URLs).
+        r"(?P<url>[^)]*)"  # Named group 'url': match any characters except ')', representing the URL.
+        r"\)"  # Literal ')' indicating the end of the URL.
+    )
+
+    def custom_replacement(match):
+        """logic will correct the link format used in ipython notebooks
+
+        Ipython notebooks were being converted directly into HTML links
+        instead of markdown links that retain the markdown extension.
+
+        It needs to handle the following cases:
+        - optional fragments (e.g., `#section`)
+            e.g., `[text](url/#section)` -> `[text](url.md#section)`
+            e.g., `[text](url#section)` -> `[text](url.md#section)`
+        - relative paths (e.g., `../path/to/file`) need to be denested by 1 level
+        """
+        text = match.group("text")
+        url = match.group("url")
+
+        if url.startswith("../"):
+            # we strip the "../" from the start of the URL
+            # We only need to denest one level.
+            url = url[3:]
+
+        url = url.rstrip("/")  # Strip `/` from the end of the URL
+
+        # if url has a fragment
+        if "#" in url:
+            url, fragment = url.split("#")
+            url = url.rstrip("/")
+            # Strip `/` from the end of the URL
+            return f"[{text}]({url}.md#{fragment})"
+        # Otherwise add the .md extension
+        return f"[{text}]({url}.md)"
+
+    return re.sub(
+        pattern,
+        custom_replacement,
+        markdown,
+    )
+
+
 class EscapePreprocessor(Preprocessor):
-    def __init__(self, rewrite_links: bool = True, **kwargs) -> None:
+    def __init__(self, markdown_exec_migration: bool = False, **kwargs) -> None:
         super().__init__(**kwargs)
-        self.rewrite_links = rewrite_links
+        self.markdown_exec_migration = markdown_exec_migration
 
     def preprocess_cell(self, cell, resources, cell_index):
         if cell.cell_type == "markdown":
-            if self.rewrite_links:
-                # We'll need to adjust the logic for this to keep markdown format
-                # but link to markdown files rather than ipynb files.
+            if not self.markdown_exec_migration:
+                # Old logic is to convert ipynb links to HTML links
                 cell.source = re.sub(
                     r"(?<!!)\[([^\]]*)\]\((?![^\)]*//)([^)]*)(?:\.ipynb)?\)",
                     r'<a href="\2">\1</a>',
                     cell.source,
                 )
             else:
-                # Keep format but replace the .ipynb extension with .md
-                cell.source = re.sub(
-                    r"(?<!!)\[([^\]]*)\]\((?![^\)]*//)([^)]*)(?:\.ipynb)?\)",
-                    r"[\1](\2.md)",
-                    cell.source,
-                )
+                cell.source = _convert_links_in_markdown(cell.source)
 
             # Fix image paths in <img> tags
             cell.source = re.sub(
@@ -39,9 +241,19 @@ class EscapePreprocessor(Preprocessor):
 
         elif cell.cell_type == "code":
             # Determine if the cell has bash or cell magic
-            if cell.source.startswith("%") or cell.source.startswith("!"):
-                # update metadata to denote that it's not a python cell
-                cell.metadata["language_info"] = {"name": "unknown"}
+            source = cell.source
+            is_exec = not (
+                source.startswith("%") or source.startswith("!") or _uses_input(source)
+            )
+            cell.metadata["exec"] = is_exec
+
+            if self.markdown_exec_migration:
+                # For markdown exec migration we'll re-write cell magic as bash commands
+                if source.startswith("%%"):
+                    cell.source = _rewrite_cell_magic(source)
+                    cell.metadata["language"] = "shell"
+
+                cell.metadata["has_output"] = _has_output(source)
 
             # Remove noqa comments
             cell.source = re.sub(r"#\s*noqa.*$", "", cell.source, flags=re.MULTILINE)
@@ -138,17 +350,6 @@ exporter = MarkdownExporter(
     ],
 )
 
-md_executable = MarkdownExporter(
-    preprocessors=[
-        ExtractAttachmentsPreprocessor,
-        EscapePreprocessor(rewrite_links=False),
-    ],
-    template_name="md_executable",
-    extra_template_basedirs=[
-        os.path.join(os.path.dirname(__file__), "notebook_convert_templates")
-    ],
-)
-
 
 def convert_notebook(
     notebook_path: Path,
@@ -158,91 +359,5 @@ def convert_notebook(
         nb = nbformat.read(f, as_version=4)
 
     nb.metadata.mode = mode
-    if mode == "markdown":
-        body, _ = exporter.from_notebook_node(nb)
-    else:
-        body, _ = md_executable.from_notebook_node(nb)
+    body, _ = exporter.from_notebook_node(nb)
     return body
-
-
-HERE = Path(__file__).parent
-DOCS = HERE.parent / "docs"
-
-
-# Convert notebooks to markdown
-def _convert_notebooks(
-    *,
-    output_dir: Optional[Path] = None,
-    replace: bool = False,
-    pattern: str = "*.ipynb",
-) -> None:
-    """Converting notebooks."""
-    if not output_dir and not replace:
-        raise ValueError("Either --output_dir or --replace must be specified")
-
-    output_dir_path = DOCS if replace else Path(output_dir)
-    notebooks = list(DOCS.rglob(pattern))
-
-    file_names = [notebook.name for notebook in notebooks]
-
-    for notebook in notebooks:
-        markdown = convert_notebook(notebook, mode="exec")
-        markdown_path = output_dir_path / notebook.relative_to(DOCS).with_suffix(".md")
-        markdown_path.parent.mkdir(parents=True, exist_ok=True)
-        with open(markdown_path, "w") as f:
-            f.write(markdown)
-        if replace:
-            notebook.unlink(missing_ok=False)
-
-    if replace:
-        # The regex will match markdown links that point to *.ipynb files.
-        # It captures:
-        #   group(1): the link text (inside the square brackets)
-        #   group(2): the file path (without the trailing .ipynb)
-        link_pattern = r"(?<!!)\[([^\]]+)\]\((?![^)]*//)([^)]+)\.ipynb\)"
-
-        def replace_link(match: re.Match) -> str:
-            link_text = match.group(1)
-            link_target = match.group(2)
-            # Reconstruct the file name with the .ipynb extension.
-            # For example, if link_target is "foo/bar", then linked_file becomes "bar.ipynb".
-            linked_file = Path(link_target).name + ".ipynb"
-            # Only update if the notebook was among those converted.
-            if linked_file in file_names:
-                # Change the extension from .ipynb to .md
-                return f"[{link_text}]({link_target}.md)"
-            # Otherwise, leave the original link intact.
-            return match.group(0)
-
-        # Process all markdown files in the output directory.
-        for path in output_dir_path.rglob("*.md"):
-            with open(path, "r", encoding="utf-8") as f:
-                content = f.read()
-            new_content = re.sub(link_pattern, replace_link, content)
-            with open(path, "w", encoding="utf-8") as f:
-                f.write(new_content)
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser(description="Convert notebooks to markdown")
-    parser.add_argument(
-        "--output_dir",
-        default=None,
-        help="Directory to output markdown files",
-    )
-    parser.add_argument(
-        "--replace",
-        action="store_true",
-        help="Replace original notebooks with markdown files",
-    )
-    parser.add_argument(
-        "--pattern",
-        default="*.ipynb",
-        help="Glob pattern to match notebooks to convert",
-    )
-    args = parser.parse_args()
-    _convert_notebooks(
-        replace=args.replace,
-        output_dir=args.output_dir,
-        pattern=args.pattern,
-    )

docs/_scripts/notebook_convert_templates/md_executable/conf.json

@@ -1,5 +0,0 @@
-{
-  "mimetypes": {
-    "text/markdown": true
-  }
-}

docs/_scripts/notebook_convert_templates/md_executable/index.md.j2

@@ -1,36 +0,0 @@
-{#https://github.com/rdbisme/nbconvert/blob/master/share/jupyter/nbconvert/templates/markdown/index.md.j2#}
-{% extends 'markdown/index.md.j2' %}
-
-{% block input %}
-```
-{%- if 'magics_language' in cell.metadata  -%}
-    {{ cell.metadata.magics_language}}
-{%- elif 'name' in nb.metadata.get('language_info', {}) -%}
-    {{ nb.metadata.language_info.name }} exec="on" source="above" session="1"
-{%- endif %}
-{{ cell.source}}
-```
-{% endblock input %}
-
-{%- block traceback_line -%}
-{%- endblock traceback_line -%}
-
-{%- block stream -%}
-{%- endblock stream -%}
-
-{%- block data_text scoped -%}
-{%- endblock data_text -%}
-
-{%- block data_html scoped -%}
-```html
-{{ output.data['text/html'] | safe }} 
-```
-{%- endblock data_html -%}
-
-{%- block data_jpg scoped -%}
-![](data:image/jpg;base64,{{ output.data['image/jpeg'] }})
-{%- endblock data_jpg -%}
-
-{%- block data_png scoped -%}
-![](data:image/png;base64,{{ output.data['image/png'] }})
-{%- endblock data_png -%}

docs/_scripts/notebook_hooks.py

@@ -1,21 +1,14 @@
 import logging
 import os
+import posixpath
 import re
-import traceback
-from typing import Any, Callable, Dict
+from typing import Any, Dict
 
-from markdown import Markdown
-from pymdownx.superfences import SuperFencesException
 from mkdocs.structure.files import Files, File
 from mkdocs.structure.pages import Page
-import posixpath
-
-from markdown_exec.hooks import SessionHistoryEntry
-
-from generate_api_reference_links import update_markdown_with_imports
-from notebook_convert import convert_notebook
-from setup_vcr import load_postamble, load_preamble, _hash_string
 
+from _scripts.generate_api_reference_links import update_markdown_with_imports
+from _scripts.notebook_convert import convert_notebook
 
 logger = logging.getLogger(__name__)
 logging.basicConfig()
@@ -38,6 +31,8 @@ REDIRECT_MAP = {
     "cloud/concepts/api.md": "concepts/langgraph_server.md",
     "cloud/concepts/cloud.md": "concepts/langgraph_cloud.md",
     "cloud/faq/studio.md": "concepts/langgraph_studio.md#studio-faqs",
+    # misc
+    "prebuilt.md": "agents/prebuilt.md"
 }
 
 
@@ -101,7 +96,7 @@ def _highlight_code_blocks(markdown: str) -> str:
     # existing hl_lines for Python and JavaScript
     # Pattern to find code blocks with highlight comments, handling optional indentation
     code_block_pattern = re.compile(
-        r"(?P<indent>[ \t]*)```(?P<language>py|python|js|javascript)(?!\s+hl_lines=)\n"
+        r"(?P<indent>[ \t]*)```(?P<language>\w+)[ ]*(?P<attributes>[^\n]*)\n"
         r"(?P<code>((?:.*\n)*?))"  # Capture the code inside the block using named group
         r"(?P=indent)```"  # Match closing backticks with the same indentation
     )
@@ -110,6 +105,13 @@ def _highlight_code_blocks(markdown: str) -> str:
         indent = match.group("indent")
         language = match.group("language")
         code_block = match.group("code")
+        attributes = match.group("attributes").rstrip()
+
+        # Account for a case where hl_lines is manually specified
+        if "hl_lines" in attributes:
+            # Return original code block
+            return match.group(0)
+
         lines = code_block.split("\n")
         highlighted_lines = []
 
@@ -135,128 +137,29 @@ def _highlight_code_blocks(markdown: str) -> str:
         # Reconstruct the new code block
         new_code_block = "\n".join(lines_to_keep)
 
+        # Construct the full code block that also includes
+        # the fenced code block syntax.
+        opening_fence = f"```{language}"
+
+        if attributes:
+            opening_fence += f" {attributes}"
+
         if highlighted_lines:
-            return (
-                f'{indent}```{language} hl_lines="{" ".join(highlighted_lines)}"\n'
-                # The indent and terminating \n is already included in the code block
-                f"{new_code_block}"
-                f"{indent}```"
-            )
-        else:
-            return (
-                f"{indent}```{language}\n"
-                # The indent and terminating \n is already included in the code block
-                f"{new_code_block}"
-                f"{indent}```"
-            )
+            opening_fence += f" hl_lines=\"{' '.join(highlighted_lines)}\""
+
+        return (
+            # The indent and opening fence
+            f"{indent}{opening_fence}\n"
+            # The indent and terminating \n is already included in the code block
+            f"{new_code_block}"
+            f"{indent}```"
+        )
 
     # Replace all code blocks in the markdown
     markdown = code_block_pattern.sub(replace_highlight_comments, markdown)
     return markdown
 
 
-def handle_vcr_setup(
-    *,
-    formatter: Callable,
-    language: str,
-    code: str,
-    session: str,
-    id: str,
-    md: Markdown,
-    **kwargs: Dict[str, Any],
-) -> Dict[str, Any]:
-    """Handle VCR setup in markdown content if necessary."""
-    try:
-        if kwargs.get("extra", None) is None:
-            raise SuperFencesException(
-                f"error while processing {language} block: extra dict is required"
-            )
-
-        if kwargs["extra"].get("path", None) is None:
-            raise SuperFencesException(
-                f"error while processing {language} block: path is required"
-            )
-
-        document_filename = kwargs["extra"]["path"]
-
-        if session is None or session == "" and id is None or id == "":
-            id = _hash_string(code)
-
-        if session is not None and session != "":
-            logger.info(f"new session {session} on page {document_filename}")
-
-        cassette_prefix = document_filename.replace(".md", "").replace(os.path.sep, "_")
-
-        cassette_dir = os.path.abspath(
-            os.path.join(os.path.dirname(os.path.dirname(__file__)), "cassettes")
-        )
-        os.makedirs(cassette_dir, exist_ok=True)
-
-        # Build a unique cassette name.
-        cassette_name = os.path.join(
-            cassette_dir,
-            f"{cassette_prefix}_{session if session else id}_{language}.msgpack.zlib",
-        )
-
-        # Add context manager at start with explicit __enter__ and __exit__ calls
-
-        wrapped_lines = [
-            load_preamble(language, code, cassette_name),
-            code,
-        ]
-
-        if session is None or session == "":
-            logger.info(
-                f"no session, adding postamble for {language} in {document_filename}"
-            )
-            wrapped_lines.append(load_postamble(language))
-
-        transformed_source = "\n".join(wrapped_lines)
-        return dict(
-            transform_source=lambda code: (transformed_source, code),
-            id=id,
-            extra={},
-        )
-    except Exception as e:
-        raise SuperFencesException(traceback.format_exc()) from e
-
-
-def handle_vcr_teardown(
-    *,
-    formatter: Callable,
-    language: str,
-    session: str,
-    history: list[SessionHistoryEntry],
-):
-    last_inputs = dict(history[-1].inputs)
-    code = load_postamble(language)
-    md = last_inputs["md"]
-    html = False
-    update_toc = False
-
-    document_filename = last_inputs.get("extra", {}).get("path", None)
-
-    if document_filename is None:
-        logger.warning(f"no document filename found while tearing down {session}!")
-    else:
-        logger.info(f"tearing down {session} on {document_filename}")
-        logger.info(traceback.format_stack())
-
-    kwargs = dict(
-        code=code,
-        session=session,
-        id=f"{id}_vcr_end",
-        md=md,
-        html=html,
-        update_toc=update_toc,
-        extra={},
-    )
-
-    # This doesn't actually render anything, we just call the formatter so it
-    # executes in the same context as the session of which we're disposing.
-    formatter(**kwargs)
-
-
 def _on_page_markdown_with_config(
     markdown: str,
     page: Page,
@@ -274,7 +177,7 @@ def _on_page_markdown_with_config(
 
     # Append API reference links to code blocks
     if add_api_references:
-        markdown = update_markdown_with_imports(markdown)
+        markdown = update_markdown_with_imports(markdown, page.file.abs_src_path)
     # Apply highlight comments to code blocks
     markdown = _highlight_code_blocks(markdown)
 
@@ -285,7 +188,7 @@ def _on_page_markdown_with_config(
 
     if remove_base64_images:
         # Remove base64 encoded images from markdown
-        markdown = re.sub(r"!\[.*?\]\(data:image/+;base64,[^\)]+\)", "", markdown)
+        markdown = re.sub(r"!\[.*?\]\(data:image/[^;]+;base64,[^)]+\)", "", markdown)
 
     return markdown
 

docs/_scripts/prepare_notebooks_for_ci.py

@@ -20,7 +20,6 @@ BLOCKLIST_COMMANDS = (
 
 NOTEBOOKS_NO_CASSETTES = (
     "docs/how-tos/visualization.ipynb",
-    "docs/how-tos/many-tools.ipynb"
 )
 
 NOTEBOOKS_NO_EXECUTION = [
@@ -49,7 +48,10 @@ NOTEBOOKS_NO_EXECUTION = [
     "docs/how-tos/map-reduce.ipynb",  # flakiness from structured output, only when running with VCR
     "docs/tutorials/tot/tot.ipynb",
     "docs/how-tos/visualization.ipynb",
-    "docs/tutorials/llm-compiler/LLMCompiler.ipynb"
+    "docs/how-tos/streaming-specific-nodes.ipynb",
+    "docs/tutorials/llm-compiler/LLMCompiler.ipynb",
+    "docs/tutorials/customer-support/customer-support.ipynb",  # relies on openai embeddings, doesn't play well w/ VCR
+    "docs/how-tos/many-tools.ipynb",  # relies on openai embeddings, doesn't play well w/ VCR
 ]
 
 
@@ -86,6 +88,12 @@ def has_blocklisted_command(code: str, metadata: dict) -> bool:
             return True
     return False
 
+def add_mermaid_retries(code: str) -> str:
+    return code.replace(
+        "draw_mermaid_png()",
+        "draw_mermaid_png(max_retries=10, retry_delay=2.0)"
+    )
+
 
 def add_vcr_to_notebook(
     notebook: nbformat.NotebookNode, cassette_prefix: str
@@ -180,6 +188,15 @@ def add_vcr_to_notebook(
     return notebook
 
 
+def add_mermaid_retries_to_notebook(notebook: nbformat.NotebookNode) -> nbformat.NotebookNode:
+    for cell in notebook.cells:
+        if cell.cell_type != "code":
+            continue
+
+        cell.source = add_mermaid_retries(cell.source)
+    return notebook
+
+
 def process_notebooks(should_comment_install_cells: bool) -> None:
     for directory in NOTEBOOK_DIRS:
         for root, _, files in os.walk(directory):
@@ -201,6 +218,8 @@ def process_notebooks(should_comment_install_cells: bool) -> None:
                             notebook, cassette_prefix=cassette_prefix
                         )
 
+                    notebook = add_mermaid_retries_to_notebook(notebook)
+
                     if notebook_path in NOTEBOOKS_NO_EXECUTION:
                         # Add a cell at the beginning to indicate that this notebook should not be executed
                         warning_cell = nbformat.v4.new_markdown_cell(

docs/_scripts/setup_vcr.py

@@ -1,77 +0,0 @@
-# A list of patterns that, if found in a code block, will cause us to leave that block unchanged.
-import hashlib
-import os
-from textwrap import dedent
-
-preambles = {
-    "python": "vcr_setup_preamble.py",
-    "typescript": "nock_setup_preamble.ts",
-}
-
-
-def _get_python_cassette_init(cassette_name: str, hash_: str) -> str:
-    return dedent(
-        f"""
-        _cassette = HashedCassette('{cassette_name}', '{hash_}')
-        _cassette.__enter__()
-        """
-    )
-
-
-def _get_typescript_cassette_init(cassette_name: str, hash_: str) -> str:
-    return dedent(
-        f"""
-        const _cassette = new HashedCassette("{cassette_name}", "{hash_}");
-        await _cassette.enter();
-        """
-    )
-
-
-def _get_python_cassette_cleanup() -> str:
-    return "_cassette.__exit__()"
-
-
-def _get_typescript_cassette_cleanup() -> str:
-    return "await _cassette.exit();"
-
-
-preamble_inits = {
-    "python": _get_python_cassette_init,
-    "py": _get_python_cassette_init,
-    "typescript": _get_typescript_cassette_init,
-    "ts": _get_typescript_cassette_init,
-}
-
-preamble_cleanups = {
-    "python": _get_python_cassette_cleanup,
-    "py": _get_python_cassette_cleanup,
-    "typescript": _get_typescript_cassette_cleanup,
-    "ts": _get_typescript_cassette_cleanup,
-}
-
-
-def load_preamble(language: str, code: str, cassette_name: str) -> str:
-    """Load the source code for the preamble for a given language."""
-    _assets_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "assets")
-
-    preamble_path = os.path.join(_assets_dir, preambles[language])
-    with open(preamble_path, "r") as f:
-        lines = f.readlines()
-        hash_ = _hash_string(code)
-        lines.append(preamble_inits[language](cassette_name, hash_))
-        return "\n".join(lines).strip()
-
-
-def load_postamble(language: str) -> str:
-    """Load the source code for the postamble for a given language."""
-
-    return preamble_cleanups[language]()
-
-
-def _hash_string(input_string: str) -> str:
-    # Encode the input string to bytes
-    encoded_string = input_string.encode("utf-8")
-    # Create a SHA-256 hash object
-    sha256_hash = hashlib.sha256(encoded_string)
-    # Get the hexadecimal digest of the hash
-    return sha256_hash.hexdigest()

docs/_scripts/third_party_page/create_third_party_page.py

@@ -9,10 +9,7 @@ import yaml
 
 MARKDOWN = """\
 [//]: # (This file is automatically generated using a script in docs/_scripts. Do not edit this file directly!)
-# 🚀 Prebuilt Agents
-
-LangGraph includes a prebuilt React agent. For more information on how to use it, 
-check out our [how-to guides](https://langchain-ai.github.io/langgraph/how-tos/#prebuilt-react-agent).
+# Community Agents
 
 If you’re looking for other prebuilt libraries, explore the community-built options 
 below. These libraries can extend LangGraph's functionality in various ways.
@@ -83,14 +80,18 @@ def generate_markdown(resolved_packages: List[ResolvedPackage], language: str) -
         resolved_packages, key=lambda p: p["weekly_downloads"] or 0, reverse=True
     )
     rows = [
-        "| Name | GitHub URL | Description | Weekly Downloads |",
-        "| --- | --- | --- | --- |",
+        "| Name | GitHub URL | Description | Weekly Downloads | Stars |",
+        "| --- | --- | --- | --- | --- |",
     ]
     for package in sorted_packages:
         name = f"**{package['name']}**"
         repo_url = f"[{package['repo']}](https://github.com/{package['repo']})"
-        downloads = package["weekly_downloads"] or 0
-        row = f"| {name} | {repo_url} | {package['description']} | {downloads} |"
+        stars_badge = (
+            f"https://img.shields.io/github/stars/{package['repo']}?style=social"
+        )
+        stars = f"![GitHub stars]({stars_badge})"
+        downloads = package["weekly_downloads"] or "-"
+        row = f"| {name} | {repo_url} | {package['description']} | {downloads} | {stars}"
         rows.append(row)
     markdown_content = MARKDOWN.format(
         library_list="\n".join(rows), langgraph_url=langgraph_url

docs/_scripts/third_party_page/get_download_stats.py

@@ -30,25 +30,63 @@ PACKAGES_FILE = HERE / "packages.yml"
 PACKAGES = yaml.safe_load(PACKAGES_FILE.read_text())['packages']
 
 
-def _get_weekly_downloads(packages: list[Package]) -> list[ResolvedPackage]:
+def _get_weekly_downloads(packages: list[Package], fake: bool) -> list[ResolvedPackage]:
     """Retrieve the monthly download count for a list of packages from PyPIStats."""
     resolved_packages: list[ResolvedPackage] = []
 
+    if fake:
+        # To avoid making network requests during testing, return fake download counts
+        for package in packages:
+            resolved_packages.append(
+                {
+                    "name": package["name"],
+                    "repo": package["repo"],
+                    "weekly_downloads": -12345,
+                    "description": package["description"],
+                }
+            )
+        return resolved_packages
+
     for package in packages:
-        url = f"https://pypistats.org/api/packages/{package['name']}/overall"
+        # First check if package exists on PyPI
+        pypi_url = f"https://pypi.org/pypi/{package['name']}/json"
+        try:
+            pypi_response = requests.get(pypi_url)
+            pypi_response.raise_for_status()
+        except requests.exceptions.HTTPError:
+            raise AssertionError(f"Package {package['name']} does not exist on PyPI")
 
-        response = requests.get(url)
-        response.raise_for_status()
-        data = response.json()
+        # Get first release date
+        pypi_data = pypi_response.json()
+        releases = pypi_data["releases"]
+        first_release_date = None
+        for version_releases in releases.values():
+            if version_releases:  # Some versions may be empty lists
+                upload_time = datetime.fromisoformat(version_releases[0]["upload_time"])
+                if first_release_date is None or upload_time < first_release_date:
+                    first_release_date = upload_time
 
-        sorted_data = sorted(
-            data["data"],
-            key=lambda x: datetime.strptime(x["date"], "%Y-%m-%d"),
-            reverse=True,
-        )
+        if first_release_date is None:
+            raise AssertionError(f"Package {package['name']} has no releases yet")
 
-        # Sum the last 7 days of downloads
-        num_downloads = sum(entry["downloads"] for entry in sorted_data[:7])
+        # If package was published in last 48 hours, skip download stats
+        if (datetime.now() - first_release_date).total_seconds() >= 48 * 3600:
+            url = f"https://pypistats.org/api/packages/{package['name']}/overall"
+
+            response = requests.get(url)
+            response.raise_for_status()
+            data = response.json()
+
+            sorted_data = sorted(
+                data["data"],
+                key=lambda x: datetime.strptime(x["date"], "%Y-%m-%d"),
+                reverse=True,
+            )
+
+            # Sum the last 7 days of downloads
+            num_downloads = sum(entry["downloads"] for entry in sorted_data[:7])
+        else:
+            num_downloads = None
 
         resolved_packages.append(
             {
@@ -63,13 +101,13 @@ def _get_weekly_downloads(packages: list[Package]) -> list[ResolvedPackage]:
 
 
 
-def main(output_file: str) -> None:
+def main(output_file: str, fake: bool) -> None:
     """Main function to generate package download information.
 
     Args:
         output_file: Path to the output YAML file.
     """
-    resolved_packages: list[ResolvedPackage] = _get_weekly_downloads(PACKAGES)
+    resolved_packages: list[ResolvedPackage] = _get_weekly_downloads(PACKAGES, fake)
 
     if not output_file.endswith(".yml"):
         raise ValueError("Output file must have a .yml extension")
@@ -90,6 +128,15 @@ if __name__ == "__main__":
             "downloads.yml"
         ),
     )
+    parser.add_argument(
+        "--fake",
+        default=False,
+        action="store_true",
+        help=(
+            "Generate fake download counts for testing purposes. "
+            "This option will not make any network requests."
+        ),
+    )
     args = parser.parse_args()
 
-    main(args.output_file)
+    main(args.output_file, args.fake)

docs/_scripts/third_party_page/packages.yml

@@ -2,10 +2,40 @@
 packages:
   - name: "trustcall"
     repo: "hinthornw/trustcall"
-    description: "Tenacious tool calling built on LangGraph"
+    description: "Tenacious tool calling built on LangGraph."
   - name: "breeze-agent"
     repo: "andrestorres123/breeze-agent"
-    description: "A streamlined research system built inspired on STORM and built on LangGraph"
+    description: "A streamlined research system built inspired on STORM and built on LangGraph."
   - name: "langgraph-supervisor"
-    repo: "langchain-ai/langgraph-supervisor"
-    description: "Build supervisor multi-agent systems with LangGraph"
+    repo: "langchain-ai/langgraph-supervisor-py"
+    description: "Build supervisor multi-agent systems with LangGraph."
+  - name: "langmem"
+    repo: "langchain-ai/langmem"
+    description: "Build agents that learn and adapt from interactions over time."
+  - name: "langchain-mcp-adapters"
+    repo: "langchain-ai/langchain-mcp-adapters"
+    description: "Make Anthropic Model Context Protocol (MCP) tools compatible with LangGraph agents."
+  - name: "open-deep-research"
+    repo: "langchain-ai/open_deep_research"
+    description: "Open source assistant for iterative web research and report writing."
+  - name: "langgraph-swarm"
+    repo: "langchain-ai/langgraph-swarm-py"
+    description: "Build swarm-style multi-agent systems using LangGraph."
+  - name: "delve-taxonomy-generator"
+    repo: "andrestorres123/delve"
+    description: "A taxonomy generator for unstructured data"
+  - name: "nodeology"
+    repo: "xyin-anl/Nodeology"
+    description: "Enable researcher to build scientific workflows easily with simplified interface."
+  - name: "langgraph-bigtool"
+    repo: "langchain-ai/langgraph-bigtool"
+    description: "Build LangGraph agents with large numbers of tools."
+  - name: "ai-data-science-team"
+    repo: "business-science/ai-data-science-team"
+    description: "An AI-powered data science team of agents to help you perform common data science tasks 10X faster."
+  - name: "langgraph-reflection"
+    repo: "langchain-ai/langgraph-reflection"
+    description: "LangGraph agent that runs a reflection step."
+  - name: "langgraph-codeact"
+    repo: "langchain-ai/langgraph-codeact"
+    description: "LangGraph implementation of CodeAct agent that generates and executes code instead of tool calling."

docs/cassettes/create-react-agent-manage-message-history_26c53429-90ba-4d0b-abb9-423d9120ad26.msgpack.zlib

@@ -0,0 +1 @@
+eNptV3tcVHUWB3zAbr7yo1mmdZt8JM4dZphhGEAyXibKADI8xCD3zr2/YS5zX9wHMBiZtNaapo2htqW1IY9E8rGwaiVpa1k+UjNw1Tay1NxtSU1LS9d1z29meGX3j/nM3HPO97y+5/x+U9NUjmSFFYXQFlZQkUzRKvxQfDVNMirTkKL+sZFHqltk6rOzHLkbNZk9FelWVUmJj4qiJNYgSkigWAMt8lHlpijaTalR8F3ikB+m3iky3tND0xbpeKQoVAlSdPFPLNLRIrgSVF28rgAMpioEqxIeQawQCJcoz9TpdbLIIZBqCpJ11fr+BpmogigUZQ+RwqpeglX67AiKKKdkFsFr0UWwYMLSBEcJDE/JHkVP0BqnajLFEaygqKyq+QPUE6BAlLNOmRJUQkBsidspym5RZBQD4RB5hLFUNyJ4UQG5qFJODhEuRAEUgrgFmtMYFF8kFAkmAxEZ6VBB4jfKYJ1IVr2RkfFEEqF4eafI4dcuGSFG5P1uGcSLNFTcqyc4kaZUxBCi0GNIpCs4eEOREI2Bc1moIOEo0ygZYcy5vWmzqkI4ZQhcJTj8CTklyyLFVFBeHDnAysE0nZqicqxQQlAqpCO5kYwA3ozhU6C6uDbZUKtAyBwllyBC0pwclFGC1xC9C8l+c0KgAqWUkSqDB6hDoEgsA1UKVoyGBgG8BcOn8RIrIwJXBxHJGssxgOP3I/R0SvF4FSiGhOQ+RxIliDLFg7ScRRXKr5BjMHJPqhhsFsWLmtJblApR5hiS5ihF6SkEIckiowUoDghWjFBAcRxEBn1RMUguOHCxAiXQLCTo1pw9XvMEFnfInwM2jsXGdqCoxivYMN3PBRw21rZDZURJ5FiVEoiAFgZKklV9v592kUGygN8Sj9hFe9K0QKMwQBIPNaAHGGcGqz6bVVRRxiWw4RhSWTzCiEjRWIUVUKB9POJUfwlFf0MC5AcGycjFIRonAj3DVWKC1i7gPKHQSMCciPNzomdgAg7YHjJDWG5ChU4pquwdAI5jh2UB7WRVFuGZg7mVWafmD0UV/Q57ho2S1YBF72D2eDcZsftZlOKGPvWRnQJ1ooQTnaDqCggJGnaQSnF6wg3ziZ2gcmCyApPgQUTvrghCEQUIeQx4VqHJkDKMElEKMwGwLlB1w/QEJggnVQGbieApD6Q1cOdQhCawsBoDI+wV/PyUOIpGhr7NBZyDJkGav1pfFXjoCNxWFrMs0GonVJJwwnbk7th9xXodDxzh4EWJpJIWERQUPHO8Lt5FcQrS61TEw9D4F5Iu3mgwwhtR5AKLVvVKGMulCX7Og3Hv1/hFOggdS0uQurACxgNCAwUGwRiyUkBHlwdlUt2wZqF5oEcE9YA8MGU8hbVw1rAfAAtvGowLQwYRYQbgX/7VFvQYjAcygF7pqqshWzhlYDUwEG6fJmQd1BSdpcBW0Kwurm6CGYZxUbpCRtXjdvu2DDyAtlI0jaBISKBFPIe+1pIqVtLDmnVxMLN6okpRmWbohYD8JfA1exCSSIoDejcGbH3bKEmChecPI6pUEYWWYO9IHNCd4mbcJhJaJ6i+tiwIJSk9KtsL56VAmAxWk8G0rZIEHrACB+cfCQu9xNco+eXv9RdIFO0BEDJ4FvsaA8Zb+uuIiq/BTtFZjgGQlEy7fQ2UzFstrf3fy5qgwpHha0rJvtNdUNjnzmwwmQxx2wcAK16B9jX4SbZzgDFsNi9Ji4Dhe9PYSIuih0W+06HhCxfSroVOPhF5vIUZGcnuea4CQXE71NlpqRWSwxltijGUVEbH5NtjMwvtVZ6qMoNImmItZmtcdLTJQpoMRgPkTKZVpMzKzWBSCyjbLDlZMxjVGHfWbFMZnSVl5EkyW2bNnpM52wrEWZiLshz21LLHo/lcj1ZitzgdhpxsG+91zFYEj6kqlVroTqtikc0cOze7yhqX5S5bkF8xl9ZMOV5kTeMtCQSErJWzTOKCOUnZjmw7w+ZHxzoK57vS5glqXqrCV6LZBelahn1hrGzJUKPz7LGWfjGbjWbSGAzbarTYjPjZ0sMYDgklqttXb7IaY96C9SjBoYOebVTwFUGpqQeSosOfNAUvRnVZc/v4fU99KhDW157r1vSE0UwkSTIRbYyOIUyW+JjYeGMs8bg9tyUl6Cf3N5m5PRe2rAIHKZnWMw9NtFsTPIhpTvnNGWjHMwAN9i9tkSNRpSQqiAxG5WuZT+YEroRkemprYOxIUS6hBLbK79a3CfMbroCs0BYUwybAkOCc5BVfvcUaY94SFPVwrxkSM5ImI2k0vVtJwh5DHMuzUD3/Z/ASCtSPwbXddaeGKnoQ3Fc3mfwK8LzfX0dGPISD/fchWeLg2f3bWr1ofiVr3MCYoImoX0wbTbyy6055EKPOqLRU9iiTLOM7NQlz1khZY6xWmwXog8wus8tkNTEMhWKNCFmQzci8g5cjDSi4fZIoq6SCaLh2q17fKT1PVeJlk2g2xZitkGtCzw3UoTlTRZyEkgB3HMTBpWgr7SJpinYjMsA4X1NqYWaSPT1lx3yyP3XILClw5W8SREVgXa5GB5KhO75mmhM1BnanjBpTZpE5SYW+trhoKs5K2azIxthiUCxDphXkbOtB6yVaPV68TRQHsZfTvla3OVEXb7GYdQlwoCbarBaj0f/HYElj4CD4aNCxB5dHhPifQSvyvlh5f+yw6usFo66+9PxSvrvq0s219elW8nSj/cqojiVJHtvDCM2bLncPqxly4/5b7U+nP3Sq64drYT9+RA9rSLly+fLhnXc/dv6774ZG0vM+jbxxYPlOsevI5SPXftgodn986WZF09yr/1u3v/2DL6I6bV+dOT8u+t09MTG7X3i9o+zkc3Zd7sG3pq4raRr3j9ZTXH7Y9C0HLnj4jgP3Zbk+bm098EPnuZ+dFZ/91Typc/h/rWEhP+c/rSx7s3Fr5/AJq66L+ZNqyLzYVc+HNH/46J5N2R8ucx4rnTF4eHhDdvPT3yd/n3xX6e++7VydemGsfvvkkYa9WW1LstZfPNPw+QPDhs4fPbugqtwzftDvbUOE2rCOMdM6wiYQOaNH/CtpXi0xpfSRecZJjl3nh7897cWkK4NuGV6bvzLslYhXU69PHPJTYssjjGHTkWW1D3PTt0478OmMw/sOjFm58sllGdIV3cYJE7/cO3JJbOj4zDO5e+lSdtj+441fuUbvzR709/2dgz0ZK9vChcecuhYUP7J1xQ3P1LCjZxK6F2yunZSyZ//Yiit/qg658Mt/7u2IDy2x2RynQ5eHza0Liai7N3Fs5sx2fcTuxsERz9WUb3rjyD42c9HN7nvmTJ/8tWJ8NOvY3vyR9K5FxzdMaSl2Rdw62zKlrr2puOxzr+3Qtpnl06jbFy4t/iT0xlF7Svq13IhfZuSN+POKZ0/U0uqba0zc+gWPuU+q6OD1iTdalj/VnD7J+tK5FRfizl5t2HapdsSV9rMnvRmrOukm68iT3czqshFDj1cWKQefGXff5UFbv9lwV9ilS+/pXw69/u8PDx18J2bNzM0zvKNPPzv8byMGF7t+rBm6s5s9tOjlVQkNYZvXLv0D7W06N+Po2Ko38ooco+Y80caeOBf+2tV05suDhcOac+rGd0y5uODQhrWaOfOmKSLlaPGpt/ePpXa8s4QKNz9cqC0p8qxbr1dIR+XS/a61bfXLHxiefnfRt8TVz4ZUfHU315l92jCmdkUmdX7BZu+G2PUdNY2PfhGSnHJ/dteJ48q654q7HNGJbatT7VNf2aBXux4cbBycf7gqcso17zhvZRt5lM/YXbun+O3x49afTNONGXGqLjUuf/INY9jPRd3bF31TmZex+4V3s9/fuPqiuqP141LjuYfiE/acTFsz9tYo255/hr8eYijNUZ8cMWFHtFvfua/zg5XbN098cPCscP526/rF+7p2XEy+ufjM88+Yxqz5Li0jN+Fq2/mv59dxXbe1bt+3OdLk2hNHjiVPbJjxwqvju/977Ymc9Kg5m9POJs+dNmXnrb9Yysq06qWu8mqvXPziA7MWh4aE3L49KOSpnxa3F4aHhPwftFJrYA==

docs/docs/adopters.md

@@ -1,4 +1,4 @@
-# 🦜🕸️ LangGraph Adopters
+# 🦜🕸️ Companies using LangGraph
 
 This list of companies using LangGraph and their success stories is compiled from public sources. If your company uses LangGraph, we'd love for you to share your story and add it to the list. You’re also welcome to contribute updates based on publicly available information from other companies, such as blog posts or press releases.
 
@@ -9,17 +9,23 @@ This list of companies using LangGraph and their success stories is compiled fro
 | [AppFolio](https://www.appfolio.com/) | Real Estate | Copilot for domain-specific task | [Case study, 2024](https://blog.langchain.dev/customers-appfolio/) |
 | [Athena Intelligence](https://www.athenaintel.com/) | Software & Technology (GenAI Native) | Research & summarization | [Case study, 2024](https://blog.langchain.dev/customers-athena-intelligence/) |
 | [Captide](https://www.captide.co/) | Software & Technology (GenAI Native) | Data extraction | [Case study, 2025](https://blog.langchain.dev/how-captide-is-redefining-equity-research-with-agentic-workflows-built-on-langgraph-and-langsmith/) |
+| [Cisco Outshift](https://outshift.cisco.com/) | Software & Technology | DevOps | [Blog post, 2025](https://outshift.cisco.com/blog/build-react-agent-application-for-devops-tasks-using-rest-apis) |
+| [C.H. Robinson](https://www.chrobinson.com/en-us/) | Logistics | Automation | [Case study, 2025](https://blog.langchain.dev/customers-chrobinson/) |
 | [Elastic](https://www.elastic.co/) | Software & Technology | Copilot for domain-specific task | [Blog post, 2025](https://www.elastic.co/blog/elastic-security-generative-ai-features) |
 | [GitLab](https://about.gitlab.com/) | Software & Technology | Code generation | [Duo workflow docs](https://handbook.gitlab.com/handbook/engineering/architecture/design-documents/duo_workflow/) |
+| [Inconvo](https://inconvo.ai/?ref=blog.langchain.dev) | Software & Technology | Code generation | [Case study, 2025](https://blog.langchain.dev/customers-inconvo/) |
 | [Infor](https://infor.com/) | Software & Technology | GenAI embedded product experiences; customer support; copilot | [Case study, 2025](https://blog.langchain.dev/customers-infor/) |
+| [Klarna](https://www.klarna.com/) | Fintech | Copilot for domain-specific task | [Case study, 2025](https://blog.langchain.dev/customers-klarna/) |
 | [Komodo Health](https://www.komodohealth.com/) | Healthcare | Copilot for domain-specific task | [Blog post](https://www.komodohealth.com/perspectives/new-gen-ai-assistant-empowers-the-enterprise/) |
 | [LinkedIn](https://www.linkedin.com/) | Social Media | Code generation; Search & discovery | [Blog post, 2025](https://www.linkedin.com/blog/engineering/ai/practical-text-to-sql-for-data-analytics); [Blog post, 2024](https://www.linkedin.com/blog/engineering/generative-ai/behind-the-platform-the-journey-to-create-the-linkedin-genai-application-tech-stack) |
 | [Minimal](https://gominimal.ai/) | E-commerce | Customer support | [Case study, 2025](https://blog.langchain.dev/how-minimal-built-a-multi-agent-customer-support-system-with-langgraph-langsmith/) |
 | [OpenRecovery](https://www.openrecovery.com/) | Healthcare | Copilot for domain-specific task | [Case study, 2024](https://blog.langchain.dev/customers-openrecovery/) |
+| [Qodo](https://www.qodo.ai/) | Software & Technology (GenAI Native) | Code generation | [Blog post, 2025](https://www.qodo.ai/blog/why-we-chose-langgraph-to-build-our-coding-agent/) |
 | [Rakuten](https://www.rakuten.com/) | E-commerce / Fintech | Copilot for domain-specific task | [Blog post, 2025](https://rakuten.today/blog/from-ai-hype-to-real-world-tools-rakuten-teams-up-with-langchain.html) |
 | [Replit](https://replit.com/) | Software & Technology | Code generation | [Blog post, 2024](https://blog.langchain.dev/customers-replit/); [Breakout agent story, 2024](https://www.langchain.com/breakoutagents/replit); [Fireside chat video, 2024](https://www.youtube.com/watch?v=ViykMqljjxU) |
 | [Rexera](https://www.rexera.com/) | Real Estate (GenAI Native) | Copilot for domain-specific task | [Case study, 2024](https://blog.langchain.dev/customers-rexera/) |
 | [Tradestack](https://www.tradestack.uk/) | Software & Technology (GenAI Native) | Copilot for domain-specific task | [Case study, 2024](https://blog.langchain.dev/customers-tradestack/) |
 | [Uber](https://www.uber.com/) | Transportation | Developer productivity; Code generation | [Presentation, 2024](https://dpe.org/sessions/ty-smith-adam-huda/this-year-in-ubers-ai-driven-developer-productivity-revolution/); [Video, 2024](https://www.youtube.com/watch?v=8rkA5vWUE4Y) |
 | [Unify](https://www.unifygtm.com/) | Software & Technology (GenAI Native) | Copilot for domain-specific task | [Blog post, 2024](https://blog.langchain.dev/unify-launches-agents-for-account-qualification-using-langgraph-and-langsmith/) |
-| [Vizient](https://www.vizientinc.com/) | Healthcare | Copilot for domain-specific task | [Case study, 2025](https://blog.langchain.dev/p/3d2cd58c-13a5-4df9-bd84-7d54ed0ed82c/) |
+| [Vizient](https://www.vizientinc.com/) | Healthcare | Copilot for domain-specific task | [Case study, 2025](https://blog.langchain.dev/p/3d2cd58c-13a5-4df9-bd84-7d54ed0ed82c/) |
+| [Vodafone](https://www.vodafone.com/) | Telecommunications | Code generation; internal search | [Case study, 2025](https://blog.langchain.dev/customers-vodafone/) |

docs/docs/agents/agents.md

@@ -0,0 +1,209 @@
+# Agents
+
+## What is an agent?
+
+An *agent* consists of three components: a **large language model (LLM)**, a set of **tools** it can use, and a **prompt** that provides instructions.
+
+The LLM operates in a loop. In each iteration, it selects a tool to invoke, provides input, receives the result (an observation), and uses that observation to inform the next action. The loop continues until a stopping condition is met — typically when the agent has gathered enough information to respond to the user.
+
+<figure markdown="1">
+![image](./assets/agent.png){: style="max-height:400px"}
+<figcaption>Agent loop: the LLM selects tools and uses their outputs to fulfill a user request.</figcaption>
+</figure>
+
+## Basic configuration
+
+Use [`create_react_agent`](https://python.langchain.com/docs/api_reference/langgraph.prebuilt.chat_agent_executor/#create-react-agent) to instantiate an agent:
+
+```python
+from langgraph.prebuilt import create_react_agent
+
+def get_weather(city: str) -> str:  # (1)!
+    """Get weather for a given city."""
+    return f"It's always sunny in {city}!"
+
+agent = create_react_agent(
+    model="anthropic:claude-3-7-sonnet-latest",  # (2)!
+    tools=[get_weather],  # (3)!
+    prompt="You are a helpful assistant"  # (4)!
+)
+
+# Run the agent
+agent.invoke(
+    {"messages": [{"role": "user", "content": "what is the weather in sf"}]}
+)
+```
+
+1. Define a tool for the agent to use. Tools can be defined as vanilla Python functions. For more advanced tool usage and customization, check the [tools](./tools.md) page.
+2. Provide a language model for the agent to use. To learn more about configuring language models for the agents, check the [models](./models.md) page.
+3. Provide a list of tools for the model to use.
+4. Provide a system prompt (instructions) to the language model used by the agent.
+
+## LLM configuration
+
+Use [init_chat_model](https://python.langchain.com/api_reference/langchain/chat_models/langchain.chat_models.base.init_chat_model.html) to configure an LLM with specific parameters,
+such as temperature:
+
+```python
+from langchain.chat_models import init_chat_model
+from langgraph.prebuilt import create_react_agent
+
+# highlight-next-line
+model = init_chat_model(
+    "anthropic:claude-3-7-sonnet-latest",
+    # highlight-next-line
+    temperature=0
+)
+
+agent = create_react_agent(
+    # highlight-next-line
+    model=model,
+    tools=[get_weather],
+)
+```
+
+See the [models](./models.md) page for more information on how to configure LLMs.
+
+## Custom Prompts
+
+Prompts instruct the LLM how to behave. They can be:
+
+* **Static**: A string is interpreted as a **system message**
+* **Dynamic**: a list of messages generated at **runtime** based on input or configuration
+
+### Static prompts
+
+Define a fixed prompt string or list of messages.
+
+```python
+from langgraph.prebuilt import create_react_agent
+
+agent = create_react_agent(
+    model="anthropic:claude-3-7-sonnet-latest",
+    tools=[get_weather],
+    # A static prompt that never changes
+    # highlight-next-line
+    prompt="Never answer questions about the weather."
+)
+
+agent.invoke(
+    {"messages": [{"role": "user", "content": "what is the weather in sf"}]}
+)
+```
+
+### Dynamic prompts
+
+Define a function that returns a message list based on the agent's state and configuration:
+
+```python
+from langchain_core.messages import AnyMessage
+from langchain_core.runnables import RunnableConfig
+from langgraph.prebuilt.chat_agent_executor import AgentState
+from langgraph.prebuilt import create_react_agent
+
+# highlight-next-line
+def prompt(state: AgentState, config: RunnableConfig) -> list[AnyMessage]:  # (1)!
+    user_name = config.get("configurable", {}).get("user_name")
+    system_msg = f"You are a helpful assistant. Address the user as {user_name}."
+    return [{"role": "system", "content": system_msg}] + state["messages"]
+
+agent = create_react_agent(
+    model="anthropic:claude-3-7-sonnet-latest",
+    tools=[get_weather],
+    # highlight-next-line
+    prompt=prompt
+)
+
+agent.invoke(
+    {"messages": [{"role": "user", "content": "what is the weather in sf"}]},
+    # highlight-next-line
+    config={"configurable": {"user_name": "John Smith"}}
+)
+```
+
+1. Dynamic prompts allow including non-message [context](./context.md) when constructing an input to the LLM, such as:
+
+    - Information passed at runtime, like a `user_id` or API credentials (using `config`).
+    - Internal agent state updated during a multi-step reasoning process (using `state`).
+
+    Dynamic prompts can be defined as functions that take `state` and `config` and return a list of messages to send to the LLM.
+
+See the [context](./context.md) page for more information.
+
+## Memory
+
+To allow multi-turn conversations with an agent, you need to enable [persistence](../concepts/persistence.md) by providing a `checkpointer` when creating an agent. At runtime you need to provide a config containing `thread_id` — a unique identifier for the conversation (session):
+
+```python
+from langgraph.prebuilt import create_react_agent
+from langgraph.checkpoint.memory import InMemorySaver
+
+# highlight-next-line
+checkpointer = InMemorySaver()
+
+agent = create_react_agent(
+    model="anthropic:claude-3-7-sonnet-latest",
+    tools=[get_weather],
+    # highlight-next-line
+    checkpointer=checkpointer  # (1)!
+)
+
+# Run the agent
+# highlight-next-line
+config = {"configurable": {"thread_id": "1"}}
+sf_response = agent.invoke(
+    {"messages": [{"role": "user", "content": "what is the weather in sf"}]},
+    # highlight-next-line
+    config  # (2)!
+)
+ny_response = agent.invoke(
+    {"messages": [{"role": "user", "content": "what about new york?"}]},
+    # highlight-next-line
+    config
+)
+```
+
+1. `checkpointer` allows the agent to store its state at every step in the tool calling loop. This enables [short-term memory](./memory.md#short-term-memory) and [human-in-the-loop](./human-in-the-loop.md) capabilities.
+2. Pass configuration with `thread_id` to be able to resume the same conversation on future agent invocations.
+
+When you enable the checkpointer, it stores agent state at every step in the provided checkpointer database (or in memory, if using `InMemorySaver`).
+
+Note that in the above example, when the agent is invoked the second time with the same `thread_id`, the original message history from the first conversation is automatically included, together with the new user input.
+
+Please see the [memory guide](./memory.md) for more details on how to work with memory.
+
+
+## Structured output
+
+To produce structured responses conforming to a schema, use the `response_format` parameter. The schema can be defined with a `Pydantic` model or `TypedDict`. The result will be accessible via the `structured_response` field.
+
+```python
+from pydantic import BaseModel
+from langgraph.prebuilt import create_react_agent
+
+class WeatherResponse(BaseModel):
+    conditions: str
+
+agent = create_react_agent(
+    model="anthropic:claude-3-7-sonnet-latest",
+    tools=[get_weather],
+    # highlight-next-line
+    response_format=WeatherResponse  # (1)!
+)
+
+response = agent.invoke(
+    {"messages": [{"role": "user", "content": "what is the weather in sf"}]}
+)
+
+# highlight-next-line
+response["structured_response"]
+```
+
+1. When `response_format` is provided, a separate step is added at the end of the agent loop: agent message history is passed to an LLM with structured output to generate a structured response.
+
+    To provide a system prompt to this LLM, use a tuple `(prompt, schema)`, e.g., `response_format=(prompt, WeatherResponse)`.
+
+!!! Note "LLM post-processing"
+
+    Structured output requires an additional call to the LLM to format the response according to the schema.
+

docs/docs/agents/context.md

@@ -0,0 +1,287 @@
+# Context
+
+Agents often require more than a list of messages to function effectively. They need **context**.
+
+Context includes *any* data outside the message list that can shape agent behavior or tool execution. This can be:
+
+- Information passed at runtime, like a `user_id` or API credentials.
+- Internal state updated during a multi-step reasoning process.
+- Persistent memory or facts from previous interactions.
+
+LangGraph provides **three** primary ways to supply context:
+
+| Type                                                                         | Description                                   | Mutable? | Lifetime                |
+|------------------------------------------------------------------------------|-----------------------------------------------|----------|-------------------------|
+| [**Config**](#config-static-context)                                         | data passed at the start of a run             | ❌        | per run                 |
+| [**State**](#state-mutable-context)                                          | dynamic data that can change during execution | ✅        | per run or conversation |
+| [**Long-term Memory (Store)**](#long-term-memory-cross-conversation-context) | data that can be shared between conversations | ✅        | across conversations    |
+
+You can use context to:
+
+- Adjust the system prompt the model sees
+- Feed tools with necessary inputs
+- Track facts during an ongoing conversation
+
+## Providing Runtime Context
+
+Use this when you need to inject data into an agent at runtime.
+
+### Config (static context)
+
+Config is for immutable data like user metadata or API keys. Use
+when you have values that don't change mid-run.
+
+Specify configuration using a key called **"configurable"** which is reserved
+for this purpose:
+
+```python
+agent.invoke(
+    {"messages": [{"role": "user", "content": "hi!"}]},
+    # highlight-next-line
+    config={"configurable": {"user_id": "user_123"}}
+)
+```
+
+### State (mutable context)
+
+State acts as short-term memory during a run. It holds dynamic data that can evolve during execution, such as values derived from tools or LLM outputs.
+
+```python
+class CustomState(AgentState):
+    # highlight-next-line
+    user_name: str
+
+agent = create_react_agent(
+    # Other agent parameters...
+    # highlight-next-line
+    state_schema=CustomState,
+)
+
+agent.invoke({
+    "messages": "hi!",
+    "user_name": "Jane"
+})
+```
+
+!!! tip "Turning on memory"
+
+    Please see the [memory guide](./memory.md) for more details on how to enable memory. This is a powerful feature that allows you to persist the agent's state across multiple invocations.
+    Otherwise, the state is scoped only to a single agent run.
+
+
+
+### Long-Term Memory (cross-conversation context)
+
+For context that spans *across* conversations or sessions, LangGraph allows access to **long-term memory** via a `store`. This can be used to read or update persistent facts (e.g., user profiles, preferences, prior interactions). For more, see the [Memory guide](./memory.md).
+
+## Customizing Prompts with Context
+
+Prompts define how the agent behaves. To incorporate runtime context, you can dynamically generate prompts based on the agent's state or config.
+
+Common use cases:
+
+- Personalization
+- Role or goal customization
+- Conditional behavior (e.g., user is admin)
+
+=== "Using config"
+
+    ```python
+    from langchain_core.messages import AnyMessage
+    from langchain_core.runnables import RunnableConfig
+    from langgraph.prebuilt import create_react_agent
+    from langgraph.prebuilt.chat_agent_executor import AgentState
+
+    def prompt(
+        state: AgentState,
+        # highlight-next-line
+        config: RunnableConfig,
+    ) -> list[AnyMessage]:
+        # highlight-next-line
+        user_name = config.get("configurable", {}).get("user_name")
+        system_msg = f"You are a helpful assistant. User's name is {user_name}"
+        return [{"role": "system", "content": system_msg}] + state["messages"]
+
+    agent = create_react_agent(
+        model="anthropic:claude-3-7-sonnet-latest",
+        tools=[get_weather],
+        # highlight-next-line
+        prompt=prompt
+    )
+
+    agent.invoke(
+        ...,
+        # highlight-next-line
+        config={"configurable": {"user_name": "John Smith"}}
+    )
+    ```
+
+=== "Using state"
+
+    ```python
+    from langchain_core.messages import AnyMessage
+    from langchain_core.runnables import RunnableConfig
+    from langgraph.prebuilt import create_react_agent
+    from langgraph.prebuilt.chat_agent_executor import AgentState
+
+    class CustomState(AgentState):
+        # highlight-next-line
+        user_name: str
+
+    def prompt(
+        # highlight-next-line
+        state: CustomState
+    ) -> list[AnyMessage]:
+        # highlight-next-line
+        user_name = state["user_name"]
+        system_msg = f"You are a helpful assistant. User's name is {user_name}"
+        return [{"role": "system", "content": system_msg}] + state["messages"]
+
+    agent = create_react_agent(
+        model="anthropic:claude-3-7-sonnet-latest",
+        tools=[...],
+        # highlight-next-line
+        state_schema=CustomState,
+        # highlight-next-line
+        prompt=prompt
+    )
+
+    agent.invoke({
+        "messages": "hi!",
+        # highlight-next-line
+        "user_name": "John Smith"
+    })
+    ```
+
+## Tools
+
+Tools can access context through special parameter **annotations**.
+
+* Use `RunnableConfig` for config access
+* Use `Annotated[StateSchema, InjectedState]` for agent state
+
+
+!!! tip 
+
+    These annotations prevent LLMs from attempting to fill in the values. These parameters will be **hidden** from the LLM.
+
+=== "Using config"
+
+    ```python
+    def get_user_info(
+        # highlight-next-line
+        config: RunnableConfig,
+    ) -> str:
+        """Look up user info."""
+        # highlight-next-line
+        user_id = config.get("configurable", {}).get("user_id")
+        return "User is John Smith" if user_id == "user_123" else "Unknown user"
+
+    agent = create_react_agent(
+        model="anthropic:claude-3-7-sonnet-latest",
+        tools=[get_user_info],
+    )
+
+    agent.invoke(
+        {"messages": [{"role": "user", "content": "look up user information"}]},
+        # highlight-next-line
+        config={"configurable": {"user_id": "user_123"}}
+    )
+    ```
+
+=== "Using State"
+
+    ```python
+    from typing import Annotated
+    from langgraph.prebuilt import InjectedState
+
+    class CustomState(AgentState):
+        # highlight-next-line
+        user_id: str
+
+    def get_user_info(
+        # highlight-next-line
+        state: Annotated[CustomState, InjectedState]
+    ) -> str:
+        """Look up user info."""
+        # highlight-next-line
+        user_id = state["user_id"]
+        return "User is John Smith" if user_id == "user_123" else "Unknown user"
+
+    agent = create_react_agent(
+        model="anthropic:claude-3-7-sonnet-latest",
+        tools=[get_user_info],
+        # highlight-next-line
+        state_schema=CustomState,
+    )
+
+    agent.invoke({
+        "messages": "look up user information",
+        # highlight-next-line
+        "user_id": "user_123"
+    })
+    ```
+
+
+## Update context from tools
+
+Tools can modify the agent's state during execution. This is useful for persisting intermediate results or making information accessible to subsequent tools or prompts.
+
+```python
+from typing import Annotated
+from langchain_core.tools import InjectedToolCallId
+from langchain_core.messages import ToolMessage
+from langgraph.prebuilt import InjectedState
+from langgraph.types import Command
+
+class CustomState(AgentState):
+    # highlight-next-line
+    user_name: str
+
+def get_user_info(
+    # highlight-next-line
+    tool_call_id: Annotated[str, InjectedToolCallId],
+    # highlight-next-line
+    config: RunnableConfig
+) -> Command:
+    """Look up user info."""
+    # highlight-next-line
+    user_id = config.get("configurable", {}).get("user_id")
+    name = "John Smith" if user_id == "user_123" else "Unknown user"
+    return Command(update={
+        # highlight-next-line
+        "user_name": name,
+        # update the message history
+        # highlight-next-line
+        "messages": [
+            ToolMessage(
+                "Successfully looked up user information",
+                # highlight-next-line
+                tool_call_id=tool_call_id
+            )
+        ]
+    })
+
+def greet(
+    # highlight-next-line
+    state: Annotated[CustomState, InjectedState]
+) -> str:
+    """Use this to greet the user once you found their info."""
+    user_name = state["user_name"]
+    return f"Hello {user_name}!"
+
+agent = create_react_agent(
+    model="anthropic:claude-3-7-sonnet-latest",
+    tools=[get_user_info, greet],
+    # highlight-next-line
+    state_schema=CustomState
+)
+
+agent.invoke(
+    {"messages": [{"role": "user", "content": "greet the user"}]},
+    # highlight-next-line
+    config={"configurable": {"user_id": "user_123"}}
+)
+```
+
+For more details, see [how to update state from tools](../how-tos/update-state-from-tools.ipynb).

docs/docs/agents/deployment.md

@@ -0,0 +1,83 @@
+# Deployment
+
+To deploy your LangGraph agent, create and configure a LangGraph app. This setup supports both local development and production deployments.
+
+Features: 
+
+* 🖥️ Local server for development
+* 🧩 Studio Web UI for visual debugging
+* ☁️ Cloud and 🔧 self-hosted deployment options
+* 📊 LangSmith integration for tracing and observability
+
+!!! info "Requirements" 
+
+    - ✅ You **must** have a [LangSmith account](https://www.langchain.com/langsmith). You can sign up for **free** and get started with the free tier.
+
+## Create a LangGraph app
+
+```bash
+pip install -U "langgraph-cli[inmem]"
+langgraph new path/to/your/app --template new-langgraph-project-python
+```
+
+This will create an empty LangGraph project. You can modify it by replacing the code in `src/agent/graph.py` with your agent code. For example:
+
+```python
+from langgraph.prebuilt import create_react_agent
+
+def get_weather(city: str) -> str:
+    """Get weather for a given city."""
+    return f"It's always sunny in {city}!"
+
+graph = create_react_agent(
+    model="anthropic:claude-3-7-sonnet-latest",
+    tools=[get_weather],
+    prompt="You are a helpful assistant"
+)
+```
+
+### Install dependencies
+
+In the root of your new LangGraph app, install the dependencies in `edit` mode so your local changes are used by the server:
+
+```shell
+pip install -e .
+```
+
+### Create an `.env` file
+
+You will find a `.env.example` in the root of your new LangGraph app. Create
+a `.env` file in the root of your new LangGraph app and copy the contents of the `.env.example` file into it, filling in the necessary API keys:
+
+```bash
+LANGSMITH_API_KEY=lsv2...
+ANTHROPIC_API_KEY=sk-
+```
+
+## Launch LangGraph server locally
+
+```shell
+langgraph dev
+```
+
+This will start up the LangGraph API server locally. If this runs successfully, you should see something like:
+
+>    Ready!
+> 
+>    - API: [http://localhost:2024](http://localhost:2024/)
+>     
+>    - Docs: http://localhost:2024/docs
+>     
+>    - LangGraph Studio Web UI: https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024
+
+See this [tutorial](https://langchain-ai.github.io/langgraph/tutorials/langgraph-platform/local-server/) to learn more about running LangGraph app locally.
+
+## LangGraph Studio Web UI
+
+LangGraph Studio Web is a specialized UI that you can connect to LangGraph API server to enable visualization, interaction, and debugging of your application locally. Test your graph in the LangGraph Studio Web UI by visiting the URL provided in the output of the `langgraph dev` command.
+
+>    - LangGraph Studio Web UI: https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024
+
+## Deployment
+
+Once your LangGraph app is running locally, you can deploy it using LangGraph Cloud or self-hosted options. Refer to the [deployment options guide](../tutorials/deployment.md) for detailed instructions on all supported deployment models.

docs/docs/agents/evals.md

@@ -0,0 +1,119 @@
+# Evals
+
+To evaluate your agent's performance you can use `LangSmith` [evaluations](https://docs.smith.langchain.com/evaluation). You would need to first define an evaluator function to judge the results from an agent, such as final outputs or trajectory. Depending on your evaluation technique, this may or may not involve a reference output:
+
+```python
+def evaluator(*, outputs: dict, reference_outputs: dict):
+    # compare agent outputs against reference outputs
+    output_messages = outputs["messages"]
+    reference_messages = reference["messages"]
+    score = compare_messages(output_messages, reference_messages)
+    return {"key": "evaluator_score", "score": score}
+```
+
+To get started, you can use prebuilt evaluators from `AgentEvals` package:
+
+```bash
+pip install -U agentevals
+```
+
+## Create evaluator
+
+A common way to evaluate agent performance is by comparing its trajectory (the order in which it calls its tools) against a reference trajectory:
+
+```python
+import json
+# highlight-next-line
+from agentevals.trajectory.match import create_trajectory_match_evaluator
+
+outputs = [
+    {
+        "role": "assistant",
+        "tool_calls": [
+            {
+                "function": {
+                    "name": "get_weather",
+                    "arguments": json.dumps({"city": "san francisco"}),
+                }
+            },
+            {
+                "function": {
+                    "name": "get_directions",
+                    "arguments": json.dumps({"destination": "presidio"}),
+                }
+            }
+        ],
+    }
+]
+reference_outputs = [
+    {
+        "role": "assistant",
+        "tool_calls": [
+            {
+                "function": {
+                    "name": "get_weather",
+                    "arguments": json.dumps({"city": "san francisco"}),
+                }
+            },
+        ],
+    }
+]
+
+# Create the evaluator
+evaluator = create_trajectory_match_evaluator(
+    # highlight-next-line
+    trajectory_match_mode="superset",  # (1)!
+)
+
+# Run the evaluator
+result = evaluator(
+    outputs=outputs, reference_outputs=reference_outputs
+)
+```
+
+1. Specify how the trajectories will be compared. `superset` will accept output trajectory as valid if it's a superset of the reference one. Other options include: [strict](https://github.com/langchain-ai/agentevals?tab=readme-ov-file#strict-match), [unordered](https://github.com/langchain-ai/agentevals?tab=readme-ov-file#unordered-match) and [subset](https://github.com/langchain-ai/agentevals?tab=readme-ov-file#subset-and-superset-match)
+
+
+As a next step, learn more about how to [customize trajectory match evaluator](https://github.com/langchain-ai/agentevals?tab=readme-ov-file#agent-trajectory-match).
+
+### LLM-as-a-judge
+
+You can use LLM-as-a-judge evaluator that uses an LLM to compare the trajectory against the reference outputs and output a score:
+
+```python
+import json
+from agentevals.trajectory.llm import (
+    # highlight-next-line
+    create_trajectory_llm_as_judge,
+    TRAJECTORY_ACCURACY_PROMPT_WITH_REFERENCE
+)
+
+evaluator = create_trajectory_llm_as_judge(
+    prompt=TRAJECTORY_ACCURACY_PROMPT_WITH_REFERENCE,
+    model="openai:o3-mini"
+)
+```
+
+## Run evaluator
+
+To run an evaluator, you will first need to create a [LangSmith dataset](https://docs.smith.langchain.com/evaluation/concepts#datasets). To use the prebuilt AgentEvals evaluators, you will need a dataset with the following schema:
+
+- **input**: `{"messages": [...]}` input messages to call the agent with.
+- **output**: `{"messages": [...]}` expected message history in the agent output. For trajectory evaluation, you can choose to keep only assistant messages.
+
+```python
+from langsmith import Client
+from langgraph.prebuilt import create_react_agent
+from agentevals.trajectory.match import create_trajectory_match_evaluator
+
+client = Client()
+agent = create_react_agent(...)
+evaluator = create_trajectory_match_evaluator(...)
+
+experiment_results = client.evaluate(
+    lambda inputs: agent.invoke(inputs),
+    # replace with your dataset name
+    data="<Name of your dataset>",
+    evaluators=[evaluator]
+)
+```

docs/docs/agents/human-in-the-loop.md

@@ -0,0 +1,227 @@
+# Human-in-the-loop
+
+To review, edit and approve tool calls in an agent you can use LangGraph's built-in [human-in-the-loop](../concepts/human_in_the_loop.md) features, specifically the [`interrupt()`][langgraph.types.interrupt] primitive.
+
+LangGraph allows you to pause execution **indefinitely** — for minutes, hours, or even days—until human input is received.
+
+This is possible because the agent state is **checkpointed into a database**, which allows the system to persist execution context and later resume the workflow, continuing from where it left off.
+
+For a deeper dive into the **human-in-the-loop** concept, see the [concept guide](../concepts/human_in_the_loop.md).
+
+<figure markdown="1">
+![image](../concepts/img/human_in_the_loop/tool-call-review.png){: style="max-height:400px"}
+<figcaption>
+A human can review and edit the output from the agent before proceeding. This is particularly critical in applications where the tool calls requested may be sensitive or require human oversight.
+</figcaption>
+</figure>
+
+
+## Review tool calls
+
+To add a human approval step to a tool:
+
+1. Use `interrupt()` in the tool to pause execution.
+2. Resume with a `Command(resume=...)` to continue based on human input.
+
+```python
+from langgraph.checkpoint.memory import InMemorySaver
+from langgraph.types import interrupt
+from langgraph.prebuilt import create_react_agent
+
+# An example of a sensitive tool that requires human review / approval
+def book_hotel(hotel_name: str):
+    """Book a hotel"""
+    # highlight-next-line
+    response = interrupt(  # (1)!
+        f"Trying to call `book_hotel` with args {{'hotel_name': {hotel_name}}}. "
+        "Please approve or suggest edits."
+    )
+    if response["type"] == "accept":
+        pass
+    elif response["type"] == "edit":
+        hotel_name = response["args"]["hotel_name"]
+    else:
+        raise ValueError(f"Unknown response type: {response['type']}")
+    return f"Successfully booked a stay at {hotel_name}."
+
+# highlight-next-line
+checkpointer = InMemorySaver() # (2)!
+
+agent = create_react_agent(
+    model="anthropic:claude-3-5-sonnet-latest",
+    tools=[book_hotel],
+    # highlight-next-line
+    checkpointer=checkpointer, # (3)!
+)
+```
+
+1. The [`interrupt` function][langgraph.types.interrupt] pauses the agent graph at a specific node. In this case, we call `interrupt()` at the beginning of the tool function, which pauses the graph at the node that executes the tool. The information inside `interrupt()` (e.g., tool calls) can be presented to a human, and the graph can be resumed with the user input (tool call approval, edit or feedback).
+2. The `InMemorySaver` is used to store the agent state at every step in the tool calling loop. This enables [short-term memory](./memory.md#short-term-memory) and [human-in-the-loop](./human-in-the-loop.md) capabilities. In this example, we use `InMemorySaver` to store the agent state in memory. In a production application, the agent state will be stored in a database.
+3. Initialize the agent with the `checkpointer`.
+
+Run the agent with the `stream()` method, passing the `config` object to specify the thread ID. This allows the agent to resume the same conversation on future invocations.
+
+```python
+config = {
+   "configurable": {
+      # highlight-next-line
+      "thread_id": "1"
+   }
+}
+
+for chunk in agent.stream(
+    {"messages": [{"role": "user", "content": "book a stay at McKittrick hotel"}]},
+    # highlight-next-line
+    config
+):
+    print(chunk)
+    print("\n")
+```
+
+> You should see that the agent runs until it reaches the `interrupt()` call, at which point it pauses and waits for human input.
+
+Resume the agent with a `Command(resume=...)` to continue based on human input.
+
+```python
+from langgraph.types import Command
+
+for chunk in agent.stream(
+    # highlight-next-line
+    Command(resume={"type": "accept"}),  # (1)!
+    # Command(resume={"type": "edit", "args": {"hotel_name": "McKittrick Hotel"}}),
+    config
+):
+    print(chunk)
+    print("\n")
+```
+
+1. The [`interrupt` function][langgraph.types.interrupt] is used in conjunction with the [`Command`](../reference/types.md#langgraph.types.Command) object to resume the graph with a value provided by the human.
+
+## Using with Agent Inbox
+
+You can create a wrapper to add interrupts to *any* tool. 
+
+The example below provides a reference implementation compatible with [Agent Inbox UI](https://github.com/langchain-ai/agent-inbox) and [Agent Chat UI](https://github.com/langchain-ai/agent-chat-ui).
+
+```python title="Wrapper that adds human-in-the-loop to any tool"
+from typing import Callable
+from langchain_core.tools import BaseTool, tool as create_tool
+from langchain_core.runnables import RunnableConfig
+from langgraph.types import interrupt 
+from langgraph.prebuilt.interrupt import HumanInterruptConfig, HumanInterrupt
+
+def add_human_in_the_loop(
+    tool: Callable | BaseTool,
+    *,
+    interrupt_config: HumanInterruptConfig = None,
+) -> BaseTool:
+   """Wrap a tool to support human-in-the-loop review.""" 
+    if not isinstance(tool, BaseTool):
+        tool = create_tool(tool)
+
+    if interrupt_config is None:
+        interrupt_config = {
+            "allow_accept": True,
+            "allow_edit": True,
+            "allow_respond": True,
+        }
+
+    @create_tool(  # (1)!
+        tool.name,
+        description=tool.description,
+        args_schema=tool.args_schema
+    )
+    def call_tool_with_interrupt(config: RunnableConfig, **tool_input):
+        request: HumanInterrupt = {
+            "action_request": {
+                "action": tool.name,
+                "args": tool_input
+            },
+            "config": interrupt_config,
+            "description": "Please review the tool call"
+        }
+        # highlight-next-line
+        response = interrupt([request])[0]  # (2)!
+        # approve the tool call
+        if response["type"] == "accept":
+            tool_response = tool.invoke(tool_input, config)
+        # update tool call args
+        elif response["type"] == "edit":
+            tool_input = response["args"]["args"]
+            tool_response = tool.invoke(tool_input, config)
+        # respond to the LLM with user feedback
+        elif response["type"] == "response":
+            user_feedback = response["args"]
+            tool_response = user_feedback
+        else:
+            raise ValueError(f"Unsupported interrupt response type: {response['type']}")
+
+        return tool_response
+
+    return call_tool_with_interrupt
+```
+
+1. This wrapper creates a new tool that calls `interrupt()` **before** executing the wrapped tool.
+2. `interrupt()` is using special input and output format that's expected by [Agent Inbox UI](https://github.com/langchain-ai/agent-inbox):
+    - a list of [`HumanInterrupt`][langgraph.prebuilt.interrupt.HumanInterrupt] objects is sent to `AgentInbox` render interrupt information to the end user
+    - resume value is provided by `AgentInbox` as a list (i.e., `Command(resume=[...])`)
+
+You can use the `add_human_in_the_loop` wrapper to add `interrupt()` to any tool without having to add it *inside* the tool:
+
+```python
+from langgraph.checkpoint.memory import InMemorySaver
+from langgraph.prebuilt import create_react_agent
+
+# highlight-next-line
+checkpointer = InMemorySaver()
+
+def book_hotel(hotel_name: str):
+   """Book a hotel"""
+   return f"Successfully booked a stay at {hotel_name}."
+
+
+agent = create_react_agent(
+    model="anthropic:claude-3-5-sonnet-latest",
+    tools=[
+        # highlight-next-line
+        add_human_in_the_loop(book_hotel), # (1)!
+    ],
+    # highlight-next-line
+    checkpointer=checkpointer,
+)
+
+config = {"configurable": {"thread_id": "1"}}
+
+# Run the agent
+for chunk in agent.stream(
+    {"messages": [{"role": "user", "content": "book a stay at McKittrick hotel"}]},
+    # highlight-next-line
+    config
+):
+    print(chunk)
+    print("\n")
+```
+
+1. The `add_human_in_the_loop` wrapper is used to add `interrupt()` to the tool. This allows the agent to pause execution and wait for human input before proceeding with the tool call.
+
+> You should see that the agent runs until it reaches the `interrupt()` call, 
+>  at which point it pauses and waits for human input.
+
+Resume the agent with a `Command(resume=...)`  to continue based on human input.
+
+```python
+from langgraph.types import Command 
+
+for chunk in agent.stream(
+    # highlight-next-line
+    Command(resume=[{"type": "accept"}]),
+    # Command(resume=[{"type": "edit", "args": {"args": {"hotel_name": "McKittrick Hotel"}}}]),
+    config
+):
+    print(chunk)
+    print("\n")
+```
+
+## Additional resources
+
+* [Human-in-the-loop in LangGraph](../concepts/human_in_the_loop.md)

docs/docs/agents/mcp.md

@@ -0,0 +1,98 @@
+# MCP Integration
+
+[Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction) is an open protocol that standardizes how applications provide tools and context to language models. LangGraph agents can use tools defined on MCP servers through the `langchain-mcp-adapters` library.
+
+![MCP](./assets/mcp.png)
+
+Install the `langchain-mcp-adapters` library to use MCP tools in LangGraph:
+
+```bash
+pip install langchain-mcp-adapters
+```
+
+## Use MCP tools
+
+The `langchain-mcp-adapters` package enables agents to use tools defined across one or more MCP servers.
+
+```python title="Agent using tools defined on MCP servers"
+# highlight-next-line
+from langchain_mcp_adapters.client import MultiServerMCPClient
+from langgraph.prebuilt import create_react_agent
+
+# highlight-next-line
+async with MultiServerMCPClient(
+    {
+        "math": {
+            "command": "python",
+            # Replace with absolute path to your math_server.py file
+            "args": ["/path/to/math_server.py"],
+            "transport": "stdio",
+        },
+        "weather": {
+            # Ensure your start your weather server on port 8000
+            "url": "http://localhost:8000/sse",
+            "transport": "sse",
+        }
+    }
+) as client:
+    agent = create_react_agent(
+        "anthropic:claude-3-7-sonnet-latest",
+        # highlight-next-line
+        client.get_tools()
+    )
+    math_response = await agent.ainvoke(
+        {"messages": [{"role": "user", "content": "what's (3 + 5) x 12?"}]}
+    )
+    weather_response = await agent.ainvoke(
+        {"messages": [{"role": "user", "content": "what is the weather in nyc?"}]}
+    )
+```
+
+## Custom MCP servers
+
+To create your own MCP servers, you can use the `mcp` library. This library provides a simple way to define tools and run them as servers.
+
+Install the MCP library:
+
+```bash
+pip install mcp
+```
+Use the following reference implementations to test your agent with MCP tool servers.
+
+```python title="Example Math Server (stdio transport)"
+from mcp.server.fastmcp import FastMCP
+
+mcp = FastMCP("Math")
+
+@mcp.tool()
+def add(a: int, b: int) -> int:
+    """Add two numbers"""
+    return a + b
+
+@mcp.tool()
+def multiply(a: int, b: int) -> int:
+    """Multiply two numbers"""
+    return a * b
+
+if __name__ == "__main__":
+    mcp.run(transport="stdio")
+```
+
+```python title="Example Weather Server (SSE transport)"
+from mcp.server.fastmcp import FastMCP
+
+mcp = FastMCP("Weather")
+
+@mcp.tool()
+async def get_weather(location: str) -> str:
+    """Get weather for location."""
+    return "It's always sunny in New York"
+
+if __name__ == "__main__":
+    mcp.run(transport="sse")
+```
+
+## Additional resources
+
+- [MCP documentation](https://modelcontextprotocol.io/introduction)
+- [MCP Transport documentation](https://modelcontextprotocol.io/docs/concepts/transports)

docs/docs/agents/memory.md

@@ -0,0 +1,262 @@
+# Memory
+
+LangGraph supports two types of memory essential for building conversational agents:
+
+- **[Short-term memory](#short-term-memory)**: Tracks the ongoing conversation by maintaining message history within a session.
+- **[Long-term memory](#long-term-memory)**: Stores user-specific or application-level data across sessions.
+
+This guide demonstrates how to use both memory types with agents in LangGraph. For a deeper
+understanding of memory concepts, refer to the [LangGraph memory documentation](../concepts/memory.md).
+
+<figure markdown="1">
+![image](./assets/memory.png){: style="max-height:400px"}
+<figcaption>Both <strong>short-term</strong> and <strong>long-term</strong> memory require persistent storage to maintain continuity across LLM interactions. In production environments, this data is typically stored in a database.</figcaption>
+</figure>
+
+!!! note "Terminology"
+
+    In LangGraph:
+
+    - *Short-term memory* is also referred to as **thread-level memory**.
+    - *Long-term memory* is also called **cross-thread memory**.
+
+    A [thread](../concepts/persistence.md#threads) represents a sequence of related runs
+    grouped by the same `thread_id`.
+
+## Short-term memory
+
+Short-term memory enables agents to track multi-turn conversations. To use it, you must:
+
+1. Provide a `checkpointer` when creating the agent. The `checkpointer` enables [persistence](../concepts/persistence.md) of the agent's state.
+2. Supply a `thread_id` in the config when running the agent. The `thread_id` is a unique identifier for the conversation session.
+
+```python
+from langgraph.prebuilt import create_react_agent
+from langgraph.checkpoint.memory import InMemorySaver
+
+# highlight-next-line
+checkpointer = InMemorySaver() # (1)!
+
+
+def get_weather(city: str) -> str:
+    """Get weather for a given city."""
+    return f"It's always sunny in {city}!"
+
+
+agent = create_react_agent(
+    model="anthropic:claude-3-7-sonnet-latest",
+    tools=[get_weather],
+    # highlight-next-line
+    checkpointer=checkpointer # (2)!
+)
+
+# Run the agent
+config = {
+    "configurable": {
+        # highlight-next-line
+        "thread_id": "1"  # (3)!
+    }
+}
+
+sf_response = agent.invoke(
+    {"messages": [{"role": "user", "content": "what is the weather in sf"}]},
+    # highlight-next-line
+    config
+)
+
+# Continue the conversation using the same thread_id
+ny_response = agent.invoke(
+    {"messages": [{"role": "user", "content": "what about new york?"}]},
+    # highlight-next-line
+    config # (4)!
+)
+```
+
+1. The `InMemorySaver` is a checkpointer that stores the agent's state in memory. In a production setting, you would typically use a database or other persistent storage. Please review the [checkpointer documentation](../reference/checkpoints.md) for more options. If you're deploying with **LangGraph Platform**, the platform will provide a production-ready checkpointer for you.
+2. The `checkpointer` is passed to the agent. This enables the agent to persist its state across invocations. Please note that 
+3. A unique `thread_id` is provided in the config. This ID is used to identify the conversation session. The value is controlled by the user and can be any string.
+4. The agent will continue the conversation using the same `thread_id`. This will allow the agent to infer that the user is asking specifically about the **weather** in New York. 
+
+When the agent is invoked the second time with the same `thread_id`, the original message history from the first conversation is automatically included, allowing the agent to infer that the user is asking specifically about the **weather** in New York.
+
+!!! Note "LangGraph Platform providers a production-ready checkpointer"
+
+    If you're using [LangGraph Platform](./deployment.md), during deployment your checkpointer will be automatically configured to use a production-ready database.
+
+### Message history summarization 
+
+<figure markdown="1">
+![image](./assets/summary.png){: style="max-height:400px"}
+<figcaption>Message history can grow quickly and exceed the LLM's context window. A common solution is to maintain a running summary of the conversation. This allows the agent to keep track of the conversation without exceeding the LLM's context window.
+</figcaption>
+</figure>
+
+Long conversations can exceed the LLM's context window. To handle this, you can summarize older messages by specifying a [`pre_model_hook`][langgraph.prebuilt.chat_agent_executor.create_react_agent], such as the prebuilt [`SummarizationNode`](https://langchain-ai.github.io/langmem/reference/short_term/#langmem.short_term.SummarizationNode):
+
+```python
+from langchain_anthropic import ChatAnthropic
+from langmem.short_term import SummarizationNode
+from langchain_core.messages.utils import count_tokens_approximately
+from langgraph.prebuilt import create_react_agent
+from langgraph.prebuilt.chat_agent_executor import AgentState
+from langgraph.checkpoint.memory import InMemorySaver
+from typing import Any
+
+model = ChatAnthropic(model="claude-3-7-sonnet-latest")
+
+summarization_node = SummarizationNode( # (1)!
+    token_counter=count_tokens_approximately,
+    model=model,
+    max_tokens=384,
+    max_summary_tokens=128,
+    output_messages_key="llm_input_messages",
+)
+
+class State(AgentState):
+    # NOTE: we're adding this key to keep track of previous summary information
+    # to make sure we're not summarizing on every LLM call
+    # highlight-next-line
+    context: dict[str, Any]  # (2)!
+
+
+checkpointer = InMemorySaver() # (3)!
+
+agent = create_react_agent(
+    model=model,
+    tools=tools,
+    # highlight-next-line
+    pre_model_hook=summarization_node, # (4)!
+    # highlight-next-line
+    state_schema=State, # (5)!
+    checkpointer=checkpointer,
+)
+```
+
+1. The `InMemorySaver` is a checkpointer that stores the agent's state in memory. In a production setting, you would typically use a database or other persistent storage. Please review the [checkpointer documentation](../reference/checkpoints.md) for more options. If you're deploying with **LangGraph Platform**, the platform will provide a production-ready checkpointer for you.
+2. The `context` key is added to the agent's state. The key contains book-keeping information for the summarization node. It is used to keep track of the last summary information and ensure that the agent doesn't summarize on every LLM call, which can be inefficient.
+3. The `checkpointer` is passed to the agent. This enables the agent to persist its state across invocations.
+4. The `pre_model_hook` is set to the `SummarizationNode`. This node will summarize the message history before sending it to the LLM. The summarization node will automatically handle the summarization process and update the agent's state with the new summary. You can replace this with a custom implementation if you prefer. Please see the [create_react_agent][langgraph.prebuilt.chat_agent_executor.create_react_agent] API reference for more details.
+5. The `state_schema` is set to the `State` class, which is the custom state that contains an extra `context` key.
+
+To learn more about using `pre_model_hook` for managing message history, see this [how-to guide](../how-tos/create-react-agent-manage-message-history.ipynb)
+
+## Long-term memory
+
+Use long-term memory to store user-specific or application-specific data across conversations. This is useful for applications like chatbots, where you want to remember user preferences or other information.
+
+To use long-term memory, you need to:
+
+1. [Configure a store](../how-tos/cross-thread-persistence.ipynb) to persist data across invocations.
+2. Use the [`get_store`][langgraph.config.get_store] function to access the store from within tools or prompts.
+
+### Reading
+
+```python title="A tool the agent can use to look up user information"
+from langgraph.config import get_store
+from langgraph.prebuilt import create_react_agent
+from langgraph.store.memory import InMemoryStore
+
+# highlight-next-line
+store = InMemoryStore() # (1)!
+
+# highlight-next-line
+store.put(  # (2)!
+    ("users",),  # (3)!
+    "user_123",  # (4)!
+    {
+        "name": "John Smith",
+        "language": "English",
+    } # (5)!
+)
+
+def get_user_info(config: RunnableConfig) -> str:
+    """Look up user info."""
+    # Same as that provided to `create_react_agent`
+    # highlight-next-line
+    store = get_store() # (6)!
+    user_id = config.get("configurable", {}).get("user_id")
+    # highlight-next-line
+    user_info = store.get(("users",), user_id) # (7)!
+    return str(user_info.value) if user_info else "Unknown user"
+
+agent = create_react_agent(
+    model="anthropic:claude-3-7-sonnet-latest",
+    tools=[get_user_info],
+    # highlight-next-line
+    store=store # (8)!
+)
+
+# Run the agent
+agent.invoke(
+    {"messages": [{"role": "user", "content": "look up user information"}]},
+    # highlight-next-line
+    config={"configurable": {"user_id": "user_123"}}
+)
+```
+
+1. The `InMemoryStore` is a store that stores data in memory. In a production setting, you would typically use a database or other persistent storage. Please review the [store documentation](../reference/stores.md) for more options. If you're deploying with **LangGraph Platform**, the platform will provide a production-ready store for you.
+2. For this example, we write some sample data to the store using the `put` method. Please see the [BaseStore.put][langgraph.store.base.BaseStore.put] API reference for more details.
+3. The first argument is the namespace. This is used to group related data together. In this case, we are using the `users` namespace to group user data.
+4. A key within the namespace. This example uses a user ID for the key.
+5. The data that we want to store for the given user.
+6. The `get_store` function is used to access the store. You can call it from anywhere in your code, including tools and prompts. This function returns the store that was passed to the agent when it was created.
+7. The `get` method is used to retrieve data from the store. The first argument is the namespace, and the second argument is the key. This will return a `StoreValue` object, which contains the value and metadata about the value.
+8. The `store` is passed to the agent. This enables the agent to access the store when running tools. You can also use the `get_store` function to access the store from anywhere in your code.
+
+### Writing
+
+```python title="Example of a tool that updates user information"
+from typing_extensions import TypedDict
+
+from langgraph.config import get_store
+from langgraph.prebuilt import create_react_agent
+from langgraph.store.memory import InMemoryStore
+
+store = InMemoryStore() # (1)!
+
+class UserInfo(TypedDict): # (2)!
+    name: str
+
+def save_user_info(user_info: UserInfo, config: RunnableConfig) -> str: # (3)!
+    """Save user info."""
+    # Same as that provided to `create_react_agent`
+    # highlight-next-line
+    store = get_store() # (4)!
+    user_id = config.get("configurable", {}).get("user_id")
+    # highlight-next-line
+    store.put(("users",), user_id, user_info) # (5)!
+    return "Successfully saved user info."
+
+agent = create_react_agent(
+    model="anthropic:claude-3-7-sonnet-latest",
+    tools=[save_user_info],
+    # highlight-next-line
+    store=store
+)
+
+# Run the agent
+agent.invoke(
+    {"messages": [{"role": "user", "content": "My name is John Smith"}]},
+    # highlight-next-line
+    config={"configurable": {"user_id": "user_123"}} # (6)!
+)
+
+# You can access the store directly to get the value
+store.get(("users",), "user_123").value
+```
+
+1. The `InMemoryStore` is a store that stores data in memory. In a production setting, you would typically use a database or other persistent storage. Please review the [store documentation](../reference/stores.md) for more options. If you're deploying with **LangGraph Platform**, the platform will provide a production-ready store for you.
+2. The `UserInfo` class is a `TypedDict` that defines the structure of the user information. The LLM will use this to format the response according to the schema.
+3. The `save_user_info` function is a tool that allows an agent to update user information. This could be useful for a chat application where the user wants to update their profile information.
+4. The `get_store` function is used to access the store. You can call it from anywhere in your code, including tools and prompts. This function returns the store that was passed to the agent when it was created.
+5. The `put` method is used to store data in the store. The first argument is the namespace, and the second argument is the key. This will store the user information in the store.
+6. The `user_id` is passed in the config. This is used to identify the user whose information is being updated.
+
+### Prebuilt memory tools
+
+**LangMem** is a LangChain-maintained library that offers tools for managing long-term memories in your agent. See the [LangMem documentation](https://langchain-ai.github.io/langmem/) for usage examples.
+
+
+## Additional resources
+
+* [Memory in LangGraph](../concepts/memory.md)

docs/docs/agents/models.md

@@ -0,0 +1,69 @@
+# Models
+
+This page describes how to configure the chat model used by an agent.
+
+## Tool calling support
+
+To enable tool-calling agents, the underlying LLM must support [tool calling](https://python.langchain.com/docs/concepts/tool_calling/).
+
+Compatible models can be found in the [LangChain integrations directory](https://python.langchain.com/docs/integrations/chat/).
+
+## Specifying a model by name
+
+You can configure an agent with a model name string:
+
+```python
+from langgraph.prebuilt import create_react_agent
+
+agent = create_react_agent(
+    # highlight-next-line
+    model="anthropic:claude-3-7-sonnet-latest",
+    # other parameters
+)
+```
+
+## Using `init_chat_model`
+
+The [`init_chat_model`](https://python.langchain.com/docs/how_to/chat_models_universal_init/) utility simplifies model initialization with configurable parameters:
+
+```python
+from langchain.chat_models import init_chat_model
+
+model = init_chat_model(
+    "anthropic:claude-3-7-sonnet-latest",
+    temperature=0,
+    max_tokens=2048
+)
+```
+
+Refer to the [API reference](https://python.langchain.com/api_reference/langchain/chat_models/langchain.chat_models.base.init_chat_model.html) for advanced options.
+
+## Using provider-specific LLMs 
+
+If a model provider is not available via `init_chat_model`, you can instantiate the provider's model class directly. The model must implement the [BaseChatModel interface](https://python.langchain.com/api_reference/core/language_models/langchain_core.language_models.chat_models.BaseChatModel.html) and support tool calling:
+
+```python
+from langchain_anthropic import ChatAnthropic
+from langgraph.prebuilt import create_react_agent
+
+model = ChatAnthropic(
+    model="claude-3-7-sonnet-latest",
+    temperature=0,
+    max_tokens=2048
+)
+
+agent = create_react_agent(
+    # highlight-next-line
+    model=model,
+    # other parameters
+)
+```
+
+!!! note "Illustrative example" 
+
+    The example above uses `ChatAnthropic`, which is already supported by `init_chat_model`. This pattern is shown to illustrate how to manually instantiate a model not available through init_chat_model.
+
+## Additional resources
+
+- [Model integration directory](https://python.langchain.com/docs/integrations/chat/)
+- [Universal initialization with `init_chat_model`](https://python.langchain.com/docs/how_to/chat_models_universal_init/)

docs/docs/agents/multi-agent.md

@@ -0,0 +1,299 @@
+# Multi-agent
+
+A single agent might struggle if it needs to specialize in multiple domains or manage many tools. To tackle this, you can break your agent into smaller, independent agents and composing them into a [multi-agent system](../concepts/multi_agent.md).
+
+In multi-agent systems, agents need to communicate between each other. They do so via [handoffs](#handoffs) — a primitive that describes which agent to hand control to and the payload to send to that agent.
+
+Two of the most popular multi-agent architectures are:
+
+- [supervisor](#supervisor) — individual agents are coordinated by a central supervisor agent. The supervisor controls all communication flow and task delegation, making decisions about which agent to invoke based on the current context and task requirements.
+- [swarm](#swarm) — agents dynamically hand off control to one another based on their specializations. The system remembers which agent was last active, ensuring that on subsequent interactions, the conversation resumes with that agent.
+
+## Supervisor
+
+![Supervisor](./assets/supervisor.png)
+
+Use [`langgraph-supervisor`](https://github.com/langchain-ai/langgraph-supervisor-py) library to create a supervisor multi-agent system:
+
+```bash
+pip install langgraph-supervisor
+```
+
+```python
+from langchain_openai import ChatOpenAI
+from langgraph.prebuilt import create_react_agent
+# highlight-next-line
+from langgraph_supervisor import create_supervisor
+
+def book_hotel(hotel_name: str):
+    """Book a hotel"""
+    return f"Successfully booked a stay at {hotel_name}."
+
+def book_flight(from_airport: str, to_airport: str):
+    """Book a flight"""
+    return f"Successfully booked a flight from {from_airport} to {to_airport}."
+
+flight_assistant = create_react_agent(
+    model="openai:gpt-4o",
+    tools=[book_flight],
+    prompt="You are a flight booking assistant",
+    # highlight-next-line
+    name="flight_assistant"
+)
+
+hotel_assistant = create_react_agent(
+    model="openai:gpt-4o",
+    tools=[book_hotel],
+    prompt="You are a hotel booking assistant",
+    # highlight-next-line
+    name="hotel_assistant"
+)
+
+# highlight-next-line
+supervisor = create_supervisor(
+    agents=[flight_assistant, hotel_assistant],
+    model=ChatOpenAI(model="gpt-4o"),
+    prompt=(
+        "You manage a hotel booking assistant and a"
+        "flight booking assistant. Assign work to them."
+    )
+).compile()
+
+for chunk in supervisor.stream(
+    {
+        "messages": [
+            {
+                "role": "user",
+                "content": "book a flight from BOS to JFK and a stay at McKittrick Hotel"
+            }
+        ]
+    }
+):
+    print(chunk)
+    print("\n")
+```
+
+## Swarm
+
+![Swarm](./assets/swarm.png)
+
+Use [`langgraph-swarm`](https://github.com/langchain-ai/langgraph-swarm-py) library to create a swarm multi-agent system:
+
+```bash
+pip install langgraph-swarm
+```
+
+```python
+from langgraph.prebuilt import create_react_agent
+# highlight-next-line
+from langgraph_swarm import create_swarm, create_handoff_tool
+
+transfer_to_hotel_assistant = create_handoff_tool(
+    agent_name="hotel_assistant",
+    description="Transfer user to the hotel-booking assistant.",
+)
+transfer_to_flight_assistant = create_handoff_tool(
+    agent_name="flight_assistant",
+    description="Transfer user to the flight-booking assistant.",
+)
+
+flight_assistant = create_react_agent(
+    model="anthropic:claude-3-5-sonnet-latest",
+    # highlight-next-line
+    tools=[book_flight, transfer_to_hotel_assistant],
+    prompt="You are a flight booking assistant",
+    # highlight-next-line
+    name="flight_assistant"
+)
+hotel_assistant = create_react_agent(
+    model="anthropic:claude-3-5-sonnet-latest",
+    # highlight-next-line
+    tools=[book_hotel, transfer_to_flight_assistant],
+    prompt="You are a hotel booking assistant",
+    # highlight-next-line
+    name="hotel_assistant"
+)
+
+# highlight-next-line
+swarm = create_swarm(
+    agents=[flight_assistant, hotel_assistant],
+    default_active_agent="flight_assistant"
+).compile()
+
+for chunk in swarm.stream(
+    {
+        "messages": [
+            {
+                "role": "user",
+                "content": "book a flight from BOS to JFK and a stay at McKittrick Hotel"
+            }
+        ]
+    }
+):
+    print(chunk)
+    print("\n")
+```
+
+## Handoffs
+
+A common pattern in multi-agent interactions is **handoffs**, where one agent *hands off* control to another. Handoffs allow you to specify:
+
+- **destination**: target agent to navigate to
+- **payload**: information to pass to that agent
+
+This is used both by `langgraph-supervisor` (supervisor hands off to individual agents) and `langgraph-swarm` (an individual agent can hand off to other agents).
+
+To implement handoffs with `create_react_agent`, you need to:
+
+1. Create a special tool that can transfer control to a different agent
+
+    ```python
+    def transfer_to_bob():
+        """Transfer to bob."""
+        return Command(
+            # name of the agent (node) to go to
+            # highlight-next-line
+            goto="bob",
+            # data to send to the agent
+            # highlight-next-line
+            update={"messages": [...]},
+            # indicate to LangGraph that we need to navigate to
+            # agent node in a parent graph
+            # highlight-next-line
+            graph=Command.PARENT,
+        )
+    ```
+
+1. Create individual agents that have access to handoff tools:
+
+    ```python
+    flight_assistant = create_react_agent(
+        ..., tools=[book_flight, transfer_to_hotel_assistant]
+    )
+    hotel_assistant = create_react_agent(
+        ..., tools=[book_hotel, transfer_to_flight_assistant]
+    )
+    ```
+
+1. Define a parent graph that contains individual agents as nodes:
+
+    ```python
+    from langgraph.graph import StateGraph, MessagesState
+    multi_agent_graph = (
+        StateGraph(MessagesState)
+        .add_node(flight_assistant)
+        .add_node(hotel_assistant)
+        ...
+    )
+    ```
+
+Putting this together, here is how you can implement a simple multi-agent system with two agents — a flight booking assistant and a hotel booking assistant:
+
+```python
+from typing import Annotated
+from langchain_core.tools import tool, InjectedToolCallId
+from langgraph.prebuilt import create_react_agent, InjectedState
+from langgraph.graph import StateGraph, START, MessagesState
+from langgraph.types import Command
+
+def create_handoff_tool(*, agent_name: str, description: str | None = None):
+    name = f"transfer_to_{agent_name}"
+    description = description or f"Transfer to {agent_name}"
+
+    @tool(name, description=description)
+    def handoff_tool(
+        # highlight-next-line
+        state: Annotated[MessagesState, InjectedState], # (1)!
+        # highlight-next-line
+        tool_call_id: Annotated[str, InjectedToolCallId],
+    ) -> Command:
+        tool_message = {
+            "role": "tool",
+            "content": f"Successfully transferred to {agent_name}",
+            "name": name,
+            "tool_call_id": tool_call_id,
+        }
+        return Command(  # (2)!
+            # highlight-next-line
+            goto=agent_name,  # (3)!
+            # highlight-next-line
+            update={"messages": state["messages"] + [tool_message]},  # (4)!
+            # highlight-next-line
+            graph=Command.PARENT,  # (5)!
+        )
+    return handoff_tool
+
+# Handoffs
+transfer_to_hotel_assistant = create_handoff_tool(
+    agent_name="hotel_assistant",
+    description="Transfer user to the hotel-booking assistant.",
+)
+transfer_to_flight_assistant = create_handoff_tool(
+    agent_name="flight_assistant",
+    description="Transfer user to the flight-booking assistant.",
+)
+
+# Simple agent tools
+def book_hotel(hotel_name: str):
+    """Book a hotel"""
+    return f"Successfully booked a stay at {hotel_name}."
+
+def book_flight(from_airport: str, to_airport: str):
+    """Book a flight"""
+    return f"Successfully booked a flight from {from_airport} to {to_airport}."
+
+# Define agents
+flight_assistant = create_react_agent(
+    model="anthropic:claude-3-5-sonnet-latest",
+    # highlight-next-line
+    tools=[book_flight, transfer_to_hotel_assistant],
+    prompt="You are a flight booking assistant",
+    # highlight-next-line
+    name="flight_assistant"
+)
+hotel_assistant = create_react_agent(
+    model="anthropic:claude-3-5-sonnet-latest",
+    # highlight-next-line
+    tools=[book_hotel, transfer_to_flight_assistant],
+    prompt="You are a hotel booking assistant",
+    # highlight-next-line
+    name="hotel_assistant"
+)
+
+# Define multi-agent graph
+multi_agent_graph = (
+    StateGraph(MessagesState)
+    .add_node(flight_assistant)
+    .add_node(hotel_assistant)
+    .add_edge(START, "flight_assistant")
+    .compile()
+)
+
+# Run the multi-agent graph
+for chunk in multi_agent_graph.stream(
+    {
+        "messages": [
+            {
+                "role": "user",
+                "content": "book a flight from BOS to JFK and a stay at McKittrick Hotel"
+            }
+        ]
+    }
+):
+    print(chunk)
+    print("\n")
+```
+
+1. Access agent's state
+2. The `Command` primitive allows specifying a state update and a node transition as a single operation, making it useful for implementing handoffs.
+3. Name of the agent or node to hand off to.
+4. Take the agent's messages and **add** them to the parent's **state** as part of the handoff. The next agent will see the parent state.
+5. Indicate to LangGraph that we need to navigate to agent node in a **parent** multi-agent graph.
+
+!!! Note
+    This handoff implementation assumes that:
+
+    - each agent receives overall message history (across all agents) in the multi-agent system as its input
+    - each agent outputs its internal messages history to the overall message history of the multi-agent system
+
+    Check out LangGraph [supervisor](https://github.com/langchain-ai/langgraph-supervisor-py#customizing-handoff-tools) and [swarm](https://github.com/langchain-ai/langgraph-swarm-py#customizing-handoff-tools) documentation to learn how to customize handoffs.

docs/docs/agents/overview.md

@@ -0,0 +1,38 @@
+---
+title: Overview
+---
+
+# Agent development with LangGraph
+
+**LangGraph** provides both low-level primitives and high-level prebuilt components for building agent-based applications. This section focuses on the **prebuilt**, **reusable** components designed to help you construct agentic systems quickly and reliably—without the need to implement orchestration, memory, or human feedback handling from scratch.
+
+## Key features
+
+LangGraph includes several capabilities essential for building robust, production-ready agentic systems:
+
+- [**Memory integration**](./memory.md): Native support for *short-term* (session-based) and *long-term* (persistent across sessions) memory, enabling stateful behaviors in chatbots and assistants.
+- [**Human-in-the-loop control**](./human-in-the-loop.md): Execution can pause *indefinitely* to await human feedback—unlike websocket-based solutions limited to real-time interaction. This enables asynchronous approval, correction, or intervention at any point in the workflow.
+- [**Streaming support**](./streaming.md): Real-time streaming of agent state, model tokens, tool outputs, or combined streams.
+- [**Deployment tooling**](./deployment.md): Includes infrastructure-free deployment tools. [**LangGraph Platform**](https://langchain-ai.github.io/langgraph/concepts/langgraph_platform/) supports testing, debugging, and deployment.
+    - **[Studio](https://langchain-ai.github.io/langgraph/concepts/langgraph_studio/)**: A visual IDE for inspecting and debugging workflows.
+    - Supports multiple [**deployment options**](https://langchain-ai.github.io/langgraph/tutorials/deployment/) for production.
+
+## High-level building blocks
+
+LangGraph comes with a set of prebuilt components that implement common agent behaviors and workflows. These abstractions are built on top of the LangGraph framework, offering a faster path to production while remaining flexible for advanced customization.
+
+Using LangGraph for agent development allows you to focus on your application's logic and behavior, instead of building and maintaining the supporting infrastructure for state, memory, and human feedback.
+
+## Package ecosystem
+
+The high-level components are organized into several packages, each with a specific focus.
+
+| Package                                    | Description                                                                 | Installation                            |
+|--------------------------------------------|-----------------------------------------------------------------------------|-----------------------------------------|
+| `langgraph-prebuilt` (part of `langgraph`) | Prebuilt components to [**create agents**](./agents.md)                     | `pip install -U langgraph langchain`    |
+| `langgraph-supervisor`                     | Tools for building [**supervisor**](./multi-agent.md#supervisor) agents     | `pip install -U langgraph-supervisor`   |
+| `langgraph-swarm`                          | Tools for building a [**swarm**](./multi-agent.md#swarm) multi-agent system | `pip install -U langgraph-swarm`        |
+| `langchain-mcp-adapters`                   | Interfaces to [**MCP servers**](./mcp.md) for tool and resource integration | `pip install -U langchain-mcp-adapters` |
+| `langmem`                                  | Agent memory management: [**short-term and long-term**](./memory.md)        | `pip install -U langmem`                |
+| `agentevals`                               | Utilities to [**evaluate agent performance**](./evals.md)                   | `pip install -U agentevals`             |
+

docs/docs/agents/prebuilt.md

@@ -0,0 +1,7 @@
+# Community Agents
+
+To share your project, simply open a Pull Request adding an entry for your package in our [packages.yml](https://github.com/langchain-ai/langgraph/blob/main/docs/_scripts/third_party_page/packages.yml) file.
+
+[//]: # (This file is stub. Do not edit this file directly!)
+[//]: # (1. Update the `packages.yml` file in the `docs/_scripts/third_party_page` directory.)
+[//]: # (2. From the /docs directory, run `make build-prebuilt` to generate an updated version of this file for testing locally.)

docs/docs/agents/run_agents.md

@@ -0,0 +1,159 @@
+# Running agents
+
+
+Agents support both synchronous and asynchronous execution using either `.invoke()` / `await .invoke()` for full responses, or `.stream()` / `.astream()` for **incremental** [streaming](#streaming) output. This section explains how to provide input, interpret output, enable streaming, and control execution limits.
+
+
+## Basic usage
+
+Agents can be executed in two primary modes:
+
+- **Synchronous** using `.invoke()` or `.stream()`
+- **Asynchronous** using `await .invoke()` or `async for` with `.astream()`
+
+=== "Sync invocation"
+    ```python
+    from langgraph.prebuilt import create_react_agent
+
+    agent = create_react_agent(...)
+
+    # highlight-next-line
+    response = agent.invoke({"messages": [{"role": "user", "content": "what is the weather in sf"}]})
+    ```
+
+=== "Async invocation"
+    ```python
+    from langgraph.prebuilt import create_react_agent
+
+    agent = create_react_agent(...)
+    # highlight-next-line
+    response = await agent.ainvoke({"messages": [{"role": "user", "content": "what is the weather in sf"}]})
+    ```
+
+## Inputs and outputs
+
+Agents use a language model that expects a list of `messages` as an input. Therefore, agent inputs and outputs are stored as a list of `messages` under the `messages` key in the agent [state](../concepts/low_level.md#working-with-messages-in-graph-state).
+
+## Input format
+
+Agent input must be a dictionary with a `messages` key. Supported formats are:
+
+| Format             | Example                                                                                                                       |
+|--------------------|-------------------------------------------------------------------------------------------------------------------------------|
+| String             | `{"messages": "Hello"}`  — Interpreted as a [HumanMessage](https://python.langchain.com/docs/concepts/messages/#humanmessage) |
+| Message dictionary | `{"messages": {"role": "user", "content": "Hello"}}`                                                                          |
+| List of messages   | `{"messages": [{"role": "user", "content": "Hello"}]}`                                                                        |
+| With custom state  | `{"messages": [{"role": "user", "content": "Hello"}], "user_name": "Alice"}` — If using a custom `state_schema`               |
+
+Messages are automatically converted into LangChain's internal message format. You can read
+more about [LangChain messages](https://python.langchain.com/docs/concepts/messages/#langchain-messages) in the LangChain documentation.
+
+!!! tip "Using custom agent state"
+
+    You can provide additional fields defined in your agent’s state schema directly in the input dictionary. This allows dynamic behavior based on runtime data or prior tool outputs.  
+    See the [context guide](./context.md) for full details.
+
+!!! note
+
+    A string input for `messages` is converted to a [HumanMessage](https://python.langchain.com/docs/concepts/messages/#humanmessage). This behavior differs from the `prompt` parameter in `create_react_agent`, which is interpreted as a [SystemMessage](https://python.langchain.com/docs/concepts/messages/#systemmessage) when passed as a string.
+
+
+## Output format
+
+Agent output is a dictionary containing:
+
+- `messages`: A list of all messages exchanged during execution (user input, assistant replies, tool invocations).
+- Optionally, `structured_response` if [structured output](./agents.md#structured-output) is configured.
+- If using a custom `state_schema`, additional keys corresponding to your defined fields may also be present in the output. These can hold updated state values from tool execution or prompt logic.
+
+See the [context guide](./context.md) for more details on working with custom state schemas and accessing context.
+
+## Streaming output
+
+Agents support streaming responses for more responsive applications. This includes:
+
+- **Progress updates** after each step
+- **LLM tokens** as they're generated
+- **Custom tool messages** during execution
+
+Streaming is available in both sync and async modes:
+
+=== "Sync streaming"
+
+    ```python
+    for chunk in agent.stream(
+        {"messages": [{"role": "user", "content": "what is the weather in sf"}]},
+        stream_mode="updates"
+    ):
+        print(chunk)
+    ```
+
+=== "Async streaming"
+
+    ```python
+    async for chunk in agent.astream(
+        {"messages": [{"role": "user", "content": "what is the weather in sf"}]},
+        stream_mode="updates"
+    ):
+        print(chunk)
+    ```
+
+!!! tip
+
+    For full details, see the [streaming guide](./streaming.md).
+
+## Max iterations
+
+To control agent execution and avoid infinite loops, set a recursion limit. This defines the maximum number of steps the agent can take before raising a `GraphRecursionError`. You can configure `recursion_limit` at runtime or when defining agent via `.with_config()`:
+
+=== "Runtime"
+
+    ```python
+    from langgraph.errors import GraphRecursionError
+    from langgraph.prebuilt import create_react_agent
+
+    max_iterations = 3
+    # highlight-next-line
+    recursion_limit = 2 * max_iterations + 1
+    agent = create_react_agent(
+        model="anthropic:claude-3-5-haiku-latest",
+        tools=[get_weather]
+    )
+
+    try:
+        response = agent.invoke(
+            {"messages": [{"role": "user", "content": "what's the weather in sf"}]},
+            # highlight-next-line
+            {"recursion_limit": recursion_limit},
+        )
+    except GraphRecursionError:
+        print("Agent stopped due to max iterations.")
+    ```
+
+=== "`.with_config()`"
+
+    ```python
+    from langgraph.errors import GraphRecursionError
+    from langgraph.prebuilt import create_react_agent
+
+    max_iterations = 3
+    # highlight-next-line
+    recursion_limit = 2 * max_iterations + 1
+    agent = create_react_agent(
+        model="anthropic:claude-3-5-haiku-latest",
+        tools=[get_weather]
+    )
+    # highlight-next-line
+    agent_with_recursion_limit = agent.with_config(recursion_limit=recursion_limit)
+
+    try:
+        response = agent_with_recursion_limit.invoke(
+            {"messages": [{"role": "user", "content": "what's the weather in sf"}]},
+        )
+    except GraphRecursionError:
+        print("Agent stopped due to max iterations.")
+    ```
+
+## Additional Resources
+
+* [Async programming in LangChain](https://python.langchain.com/docs/concepts/async)

docs/docs/agents/streaming.md

@@ -0,0 +1,208 @@
+# Streaming
+
+Streaming is key to building responsive applications. There are a few types of data you’ll want to stream:
+
+1. [**Agent progress**](#agent-progress) — get updates after each node in the agent graph is executed.
+2. [**LLM tokens**](#llm-tokens) — stream tokens as they are generated by the language model.
+3. [**Custom updates**](#tool-updates) — emit custom data from tools during execution (e.g., "Fetched 10/100 records")
+
+You can stream [more than one type of data](#stream-multiple-modes) at a time. 
+
+
+<figure markdown="1">
+![image](./assets/fast_parrot.png){: style="max-height:300px"}
+<figcaption>
+Waiting is for pigeons.
+</figcaption>
+</figure>
+
+## Agent progress
+
+To stream agent progress, use the [`stream()`][langgraph.graph.state.CompiledStateGraph.stream] or [`astream()`][langgraph.graph.state.CompiledStateGraph.astream] methods with [`stream_mode="updates"`](https://langchain-ai.github.io/langgraph/how-tos/streaming/#updates). This emits an event after every agent step.
+
+For example, if you have an agent that calls a tool once, you should see the following updates:
+
+* **LLM node**: AI message with tool call requests
+* **Tool node**: Tool message with execution result
+* **LLM node**: Final AI response
+
+=== "Sync"
+
+    ```python
+    agent = create_react_agent(
+        model="anthropic:claude-3-7-sonnet-latest",
+        tools=[get_weather],
+    )
+    # highlight-next-line
+    for chunk in agent.stream(
+        {"messages": [{"role": "user", "content": "what is the weather in sf"}]},
+        # highlight-next-line
+        stream_mode="updates"
+    ):
+        print(chunk)
+        print("\n")
+    ```
+
+=== "Async"
+
+    ```python
+    agent = create_react_agent(
+        model="anthropic:claude-3-7-sonnet-latest",
+        tools=[get_weather],
+    )
+    # highlight-next-line
+    async for chunk in agent.astream(
+        {"messages": [{"role": "user", "content": "what is the weather in sf"}]},
+        # highlight-next-line
+        stream_mode="updates"
+    ):
+        print(chunk)
+        print("\n")
+    ```
+
+## LLM tokens
+
+To stream tokens as they are produced by the LLM, use `stream_mode="messages"`:
+
+=== "Sync"
+
+    ```python
+    agent = create_react_agent(
+        model="anthropic:claude-3-7-sonnet-latest",
+        tools=[get_weather],
+    )
+    # highlight-next-line
+    for token, metadata in agent.stream(
+        {"messages": [{"role": "user", "content": "what is the weather in sf"}]},
+        # highlight-next-line
+        stream_mode="messages"
+    ):
+        print("Token", token)
+        print("Metadata", metadata)
+        print("\n")
+    ```
+
+=== "Async"
+
+    ```python
+    agent = create_react_agent(
+        model="anthropic:claude-3-7-sonnet-latest",
+        tools=[get_weather],
+    )
+    # highlight-next-line
+    async for token, metadata in agent.astream(
+        {"messages": [{"role": "user", "content": "what is the weather in sf"}]},
+        # highlight-next-line
+        stream_mode="messages"
+    ):
+        print("Token", token)
+        print("Metadata", metadata)
+        print("\n")
+    ```
+
+## Tool updates
+
+To stream updates from tools as they are executed, you can use [get_stream_writer][langgraph.config.get_stream_writer].
+
+=== "Sync"
+
+    ```python
+    # highlight-next-line
+    from langgraph.config import get_stream_writer
+
+    def get_weather(city: str) -> str:
+        """Get weather for a given city."""
+        # highlight-next-line
+        writer = get_stream_writer()
+        # stream any arbitrary data
+        # highlight-next-line
+        writer(f"Looking up data for city: {city}")
+        return f"It's always sunny in {city}!"
+
+    agent = create_react_agent(
+        model="anthropic:claude-3-7-sonnet-latest",
+        tools=[get_weather],
+    )
+
+    for chunk in agent.stream(
+        {"messages": [{"role": "user", "content": "what is the weather in sf"}]},
+        # highlight-next-line
+        stream_mode="custom"
+    ):
+        print(chunk)
+        print("\n")
+    ```
+
+=== "Async"
+
+    ```python
+    # highlight-next-line
+    from langgraph.config import get_stream_writer
+
+    def get_weather(city: str) -> str:
+        """Get weather for a given city."""
+        # highlight-next-line
+        writer = get_stream_writer()
+        # stream any arbitrary data
+        # highlight-next-line
+        writer(f"Looking up data for city: {city}")
+        return f"It's always sunny in {city}!"
+
+    agent = create_react_agent(
+        model="anthropic:claude-3-7-sonnet-latest",
+        tools=[get_weather],
+    )
+
+    async for chunk in agent.astream(
+        {"messages": [{"role": "user", "content": "what is the weather in sf"}]},
+        # highlight-next-line
+        stream_mode="custom"
+    ):
+        print(chunk)
+        print("\n")
+    ```
+
+!!! Note
+    If you add `get_stream_writer` inside your tool, you won't be able to invoke the tool outside of a LangGraph execution context. 
+
+## Stream multiple modes
+
+You can specify multiple streaming modes by passing stream mode as a list: `stream_mode=["updates", "messages", "custom"]`:
+
+=== "Sync"
+
+    ```python
+    agent = create_react_agent(
+        model="anthropic:claude-3-7-sonnet-latest",
+        tools=[get_weather],
+    )
+
+    for stream_mode, chunk in agent.stream(
+        {"messages": [{"role": "user", "content": "what is the weather in sf"}]},
+        # highlight-next-line
+        stream_mode=["updates", "messages", "custom"]
+    ):
+        print(chunk)
+        print("\n")
+    ```
+
+=== "Async"
+
+    ```python
+    agent = create_react_agent(
+        model="anthropic:claude-3-7-sonnet-latest",
+        tools=[get_weather],
+    )
+
+    async for stream_mode, chunk in agent.astream(
+        {"messages": [{"role": "user", "content": "what is the weather in sf"}]},
+        # highlight-next-line
+        stream_mode=["updates", "messages", "custom"]
+    ):
+        print(chunk)
+        print("\n")
+    ```
+
+## Additional resources
+
+* [Streaming in LangGraph](https://langchain-ai.github.io/langgraph/how-tos/streaming)

docs/docs/agents/tools.md

@@ -0,0 +1,280 @@
+# Tools
+
+[Tools](https://python.langchain.com/docs/concepts/tools/) are a way to encapsulate a function and its input schema in a way that can be passed to a chat model that supports tool calling. This allows the model to request the execution of this function with specific inputs.
+
+You can either [define your own tools](#define-simple-tools) or use [prebuilt integrations](#prebuilt-tools) that LangChain provides.
+
+## Define simple tools
+
+You can pass a vanilla function to `create_react_agent` to use as a tool:
+
+```python
+from langgraph.prebuilt import create_react_agent
+
+def multiply(a: int, b: int) -> int:
+    """Multiply two numbers."""
+    return a * b
+
+create_react_agent(
+    model="anthropic:claude-3-7-sonnet",
+    tools=[multiply]
+)
+```
+
+`create_react_agent` automatically converts vanilla functions to [LangChain tools](https://python.langchain.com/docs/concepts/tools/#tool-interface).
+
+## Customize tools
+
+For more control over tool behavior, use the `@tool` decorator:
+
+```python
+# highlight-next-line
+from langchain_core.tools import tool
+
+# highlight-next-line
+@tool("multiply_tool", parse_docstring=True)
+def multiply(a: int, b: int) -> int:
+    """Multiply two numbers.
+
+    Args:
+        a: First operand
+        b: Second operand
+    """
+    return a * b
+```
+
+You can also define a custom input schema using Pydantic:
+
+```python
+from pydantic import BaseModel, Field
+
+class MultiplyInputSchema(BaseModel):
+    """Multiply two numbers"""
+    a: int = Field(description="First operand")
+    b: int = Field(description="Second operand")
+
+# highlight-next-line
+@tool("multiply_tool", args_schema=MultiplyInputSchema)
+def multiply(a: int, b: int) -> int:
+   return a * b
+```
+
+For additional customization, refer to the [custom tools guide](https://python.langchain.com/docs/how_to/custom_tools/).
+
+## Hide arguments from the model
+
+Some tools require runtime-only arguments (e.g., user ID or session context) that should not be controllable by the model.
+
+You can put these arguments in the `state` or `config` of the agent, and access
+this information inside the tool:
+
+```python
+from langgraph.prebuilt import InjectedState
+from langgraph.prebuilt.chat_agent_executor import AgentState
+from langchain_core.runnables import RunnableConfig
+
+def my_tool(
+    # This will be populated by an LLM
+    tool_arg: str,
+    # access information that's dynamically updated inside the agent
+    # highlight-next-line
+    state: Annotated[AgentState, InjectedState],
+    # access static data that is passed at agent invocation
+    # highlight-next-line
+    config: RunnableConfig,
+) -> str:
+    """My tool."""
+    do_something_with_state(state["messages"])
+    do_something_with_config(config)
+    ...
+```
+
+## Disable parallel tool calling
+
+Some model providers support executing multiple tools in parallel, but
+allow users to disable this feature.
+
+For supported providers, you can disable parallel tool calling by setting `parallel_tool_calls=False` via the `model.bind_tools()` method:
+
+```python
+from langchain.chat_models import init_chat_model
+
+def add(a: int, b: int) -> int:
+    """Add two numbers"""
+    return a + b
+
+def multiply(a: int, b: int) -> int:
+    """Multiply two numbers."""
+    return a * b
+
+model = init_chat_model("anthropic:claude-3-5-sonnet-latest", temperature=0)
+tools = [add, multiply]
+agent = create_react_agent(
+    # disable parallel tool calls
+    # highlight-next-line
+    model=model.bind_tools(tools, parallel_tool_calls=False),
+    tools=tools
+)
+
+agent.invoke(
+    {"messages": [{"role": "user", "content": "what's 3 + 5 and 4 * 7?"}]}
+)
+```
+
+## Return tool results directly
+
+Use `return_direct=True` to return tool results immediately and stop the agent loop:
+
+```python
+from langchain_core.tools import tool
+
+# highlight-next-line
+@tool(return_direct=True)
+def add(a: int, b: int) -> int:
+    """Add two numbers"""
+    return a + b
+
+agent = create_react_agent(
+    model="anthropic:claude-3-7-sonnet-latest",
+    tools=[add]
+)
+
+agent.invoke(
+    {"messages": [{"role": "user", "content": "what's 3 + 5?"}]}
+)
+```
+
+## Force tool use
+
+To force the agent to use specific tools, you can set the `tool_choice` option in `model.bind_tools()`:
+
+```python
+from langchain_core.tools import tool
+
+# highlight-next-line
+@tool(return_direct=True)
+def greet(user_name: str) -> int:
+    """Greet user."""
+    return f"Hello {user_name}!"
+
+tools = [greet]
+
+agent = create_react_agent(
+    # highlight-next-line
+    model=model.bind_tools(tools, tool_choice={"type": "tool", "name": "greet"}),
+    tools=tools
+)
+
+agent.invoke(
+    {"messages": [{"role": "user", "content": "Hi, I am Bob"}]}
+)
+```
+
+!!! Warning "Avoid infinite loops"
+
+    Forcing tool usage without stopping conditions can create infinite loops. Use one of the following safeguards:
+
+    - Mark the tool with [`return_direct=True`](#return-tool-results-directly) to end the loop after execution.
+    - Set [`recursion_limit`](../concepts/low_level.md#recursion-limit) to restrict the number of execution steps.
+
+## Handle tool errors
+
+By default, the agent will catch all exceptions raised during tool calls and will pass those as tool messages to the LLM. To control how the errors are handled, you can use the prebuilt [`ToolNode`][langgraph.prebuilt.tool_node.ToolNode] — the node that executes tools inside `create_react_agent` — via its `handle_tool_errors` parameter:
+
+=== "Enable error handling (default)"
+
+    ```python
+    from langgraph.prebuilt import create_react_agent
+
+    def multiply(a: int, b: int) -> int:
+        """Multiply two numbers."""
+        if a == 42:
+            raise ValueError("The ultimate error")
+        return a * b
+
+    # Run with error handling (default)
+    agent = create_react_agent(
+        model="anthropic:claude-3-7-sonnet-latest",
+        tools=[multiply]
+    )
+    agent.invoke(
+        {"messages": [{"role": "user", "content": "what's 42 x 7?"}]}
+    )
+    ```
+
+=== "Disable error handling"
+
+    ```python
+    from langgraph.prebuilt import create_react_agent, ToolNode
+
+    def multiply(a: int, b: int) -> int:
+        """Multiply two numbers."""
+        if a == 42:
+            raise ValueError("The ultimate error")
+        return a * b
+
+    # highlight-next-line
+    tool_node = ToolNode(
+        [multiply],
+        # highlight-next-line
+        handle_tool_errors=False  # (1)!
+    )
+    agent_no_error_handling = create_react_agent(
+        model="anthropic:claude-3-7-sonnet-latest",
+        tools=tool_node
+    )
+    agent_no_error_handling.invoke(
+        {"messages": [{"role": "user", "content": "what's 42 x 7?"}]}
+    )
+    ```
+
+    1. This disables error handling (enabled by default). See all available strategies in the [API reference][langgraph.prebuilt.tool_node.ToolNode].
+
+=== "Custom error handling"
+
+    ```python
+    from langgraph.prebuilt import create_react_agent, ToolNode
+
+    def multiply(a: int, b: int) -> int:
+        """Multiply two numbers."""
+        if a == 42:
+            raise ValueError("The ultimate error")
+        return a * b
+
+    # highlight-next-line
+    tool_node = ToolNode(
+        [multiply],
+        # highlight-next-line
+        handle_tool_errors=(
+            "Can't use 42 as a first operand, you must switch operands!"  # (1)!
+        )
+    )
+    agent_custom_error_handling = create_react_agent(
+        model="anthropic:claude-3-7-sonnet-latest",
+        tools=tool_node
+    )
+    agent_custom_error_handling.invoke(
+        {"messages": [{"role": "user", "content": "what's 42 x 7?"}]}
+    )
+    ```
+
+    1. This provides a custom message to send to the LLM in case of an exception. See all available strategies in the [API reference][langgraph.prebuilt.tool_node.ToolNode].
+
+See [API reference][langgraph.prebuilt.tool_node.ToolNode] for more information on different tool error handling options.
+
+## Prebuilt tools
+
+LangChain supports a wide range of prebuilt tool integrations for interacting with APIs, databases, file systems, web data, and more. These tools extend the functionality of agents and enable rapid development.
+
+You can browse the full list of available integrations in the [LangChain integrations directory](https://python.langchain.com/docs/integrations/tools/).
+
+Some commonly used tool categories include:
+
+- **Search**: Bing, SerpAPI, Tavily
+- **Code interpreters**: Python REPL, Node.js REPL
+- **Databases**: SQL, MongoDB, Redis
+- **Web data**: Web scraping and browsing
+- **APIs**: OpenWeatherMap, NewsAPI, and others
+
+These integrations can be configured and added to your agents using the same `tools` parameter shown in the examples above.
+

docs/docs/agents/ui.md

@@ -0,0 +1,31 @@
+# UI
+
+You can use a prebuilt chat UI for interacting with any LangGraph agent through the [Agent Chat UI](https://github.com/langchain-ai/agent-chat-ui). Using the [deployed version](https://agentchat.vercel.app) is the quickest way to get started, and allows you to interact with both local and deployed graphs.
+
+## Run agent in UI
+
+First, set up LangGraph API server [locally](./deployment.md#launch-langgraph-server-locally) or deploy your agent on [LangGraph Cloud](https://langchain-ai.github.io/langgraph/cloud/quick_start/).
+
+Then, navigate to [Agent Chat UI](https://agentchat.vercel.app), or clone the repository and [run the dev server locally](https://github.com/langchain-ai/agent-chat-ui?tab=readme-ov-file#setup):
+
+<video controls src="../assets/base-chat-ui.mp4" type="video/mp4"></video>
+
+!!! Tip
+
+    UI has out-of-box support for rendering tool calls, and tool result messages. To customize what messages are shown, see the [Hiding Messages in the Chat](https://github.com/langchain-ai/agent-chat-ui?tab=readme-ov-file#hiding-messages-in-the-chat) section in the Agent Chat UI documentation.
+
+## Add human-in-the-loop
+
+Agent Chat UI has full support for [human-in-the-loop](../concepts/human_in_the_loop.md) workflows. To try it out, replace the agent code in `src/agent/graph.py` (from the [deployment](./deployment.md) guide) with this [agent implementation](./human-in-the-loop.md#using-with-agent-inbox):
+
+<video controls src="../assets/interrupt-chat-ui.mp4" type="video/mp4"></video>
+
+!!! Important
+
+    Agent Chat UI works best if your LangGraph agent interrupts using the [`HumanInterrupt` schema][langgraph.prebuilt.interrupt.HumanInterrupt]. If you do not use that schema, the Agent Chat UI will be able to render the input passed to the `interrupt` function, but it will not have full support for resuming your graph.
+
+## Generative UI
+
+You can also use generative UI in the Agent Chat UI.
+
+Generative UI allows you to define [React](https://react.dev/) components, and push them to the UI from the LangGraph server. For more documentation on building generative UI LangGraph agents, read [these docs](https://langchain-ai.github.io/langgraph/cloud/how-tos/generative_ui_react/).

docs/docs/cloud/deployment/cloud.md

@@ -1,6 +1,6 @@
-# How to Deploy to LangGraph Cloud
+# How to Deploy to Cloud SaaS (Beta)
 
-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>.
+Before deploying, review the [conceptual guide for the Cloud SaaS](../../concepts/langgraph_cloud.md) deployment option.
 
 ## Prerequisites
 
@@ -92,3 +92,28 @@ Starting from the `LangGraph Platform` view...
 1. Check/uncheck checkbox to `Automatically update deployment on push to branch`.
     1. Branch creation/deletion and tag creation/deletion events will not trigger an update. Only pushes to an existing branch will trigger an update.
     1. Pushes in quick succession to a branch will not trigger subsequent updates. In the future, this functionality may be changed/improved.
+
+## Add or Remove GitHub Repositories
+
+After installing and authorizing LangChain's `hosted-langserve` GitHub app, repository access for the app can be modified to add new repositories or remove existing repositories. If a new repository is created, it may need to be added explicitly.
+
+1. From the GitHub profile, navigate to `Settings` > `Applications` > `hosted-langserve` > click `Configure`.
+1. Under `Repository access`, select `All repositories` or `Only select repositories`. If `Only select repositories` is selected, new repositories must be explicitly added.
+1. Click `Save`.
+1. When creating a new deployment, the list of GitHub repositories in the dropdown menu will be updated to reflect the repository access changes.
+
+## Whitelisting IP Addresses
+
+All traffic from `LangGraph Platform` deployments created after January 6th 2025 will come through a NAT gateway.
+This NAT gateway will have several static ip addresses depending on the region you are deploying in. Refer to the table below for the list of IP addresses to whitelist:
+
+| US             | EU             |
+|----------------|----------------|
+| 35.197.29.146  | 34.13.192.67   |
+| 34.145.102.123 | 34.147.105.64  |
+| 34.169.45.153  | 34.90.22.166   |
+| 34.82.222.17   | 34.147.36.213  |
+| 35.227.171.135 | 34.32.137.113  | 
+| 34.169.88.30   | 34.91.238.184  |
+| 34.19.93.202   | 35.204.101.241 |
+| 34.19.34.50    | 35.204.48.32   |

docs/docs/cloud/deployment/self_hosted_control_plane.md

@@ -0,0 +1,56 @@
+# How to Deploy Self-Hosted Control Plane (Beta)
+
+Before deploying, review the [conceptual guide for the Self-Hosted Control Plane](../../concepts/langgraph_self_hosted_control_plane.md) deployment option.
+
+## Prerequisites
+
+1. You are using Kubernetes.
+1. You have self-hosted LangSmith deployed.
+1. Use the [LangGraph CLI](../../concepts/langgraph_cli.md) to [test your application locally](./test_locally.md).
+1. Use the [LangGraph CLI](../../concepts/langgraph_cli.md) to build a Docker image (i.e. `langgraph build`) and push it to a registry your Kubernetes cluster has access to.
+1. `KEDA` is installed on your cluster.
+
+         helm repo add kedacore https://kedacore.github.io/charts 
+         helm install keda kedacore/keda --namespace keda --create-namespace
+
+1. Ingress Configuration (recommended)
+    1. Install `Ingress Nginx` to serve as a reverse proxy for your deployment.
+
+            helm repo add ingress-nginx https://kubernetes.github.io/ingress-nginx
+            helm repo update
+            helm install ingress-nginx ingress-nginx/ingress-nginx
+
+    1. Provision a root domain that will suffix all domains for your workloads (e.g. `us.langgraph.app`).
+    1. Provision wildcard certificates to terminate TLS for your deployments.
+    1. Note: If this step is skipped, you will need to provision domains/certs for each of your deployments.
+
+1. You have slack space in your cluster for multiple deployments. `Cluster-Autoscaler` is recommended to automatically provision new nodes.
+
+## Setup
+
+1. As part of configuring your Self-Hosted LangSmith instance, you enable the `langgraphPlatform` option. This will provision a few key resources.
+    1. `listener`: This is a service that listens to the [control plane](../../concepts/langgraph_control_plane.md) for changes to your deployments and creates/updates downstream CRDs.
+    1. `LangGraphPlatform CRD`: A CRD for LangGraph Platform deployments. This contains the spec for managing an instance of a LangGraph platform deployment.
+    1. `operator`: This operator handles changes to your LangGraph Platform CRDs.
+    1. `host-backend`: This is the [control plane](../../concepts/langgraph_control_plane.md).
+1. Two additional images will be used by the chart.
+
+        hostBackendImage:
+          repository: "docker.io/langchain/hosted-langserve-backend"
+          pullPolicy: IfNotPresent
+          tag: "0.9.80"
+        operatorImage:
+          repository: "docker.io/langchain/langgraph-operator"
+          pullPolicy: IfNotPresent
+          tag: "aa9dff4"
+
+1. In your `values.yaml` file, enable the `langgraphPlatform` option.
+
+        config:
+          langgraphPlatform:
+            enabled: true
+            langgraphPlatformLicenseKey: "YOUR_LANGGRAPH_PLATFORM_LICENSE_KEY"
+            rootDomain: "YOUR_ROOT_DOMAIN"
+
+1. You can also configure base templates for your agents by overriding the base templates [here](https://github.com/langchain-ai/helm/blob/main/charts/langsmith/values.yaml#L898).
+1. You create a deployment from the [Control Plane UI](../../concepts/langgraph_control_plane.md#control-plane-ui).

docs/docs/cloud/deployment/self_hosted_data_plane.md

@@ -0,0 +1,53 @@
+# How to Deploy Self-Hosted Data Plane (Beta)
+
+Before deploying, review the [conceptual guide for the Self-Hosted Data Plane](../../concepts/langgraph_self_hosted_data_plane.md) deployment option.
+
+## Prerequisites
+
+1. Use the [LangGraph CLI](../../concepts/langgraph_cli.md) to [test your application locally](./test_locally.md).
+1. Use the [LangGraph CLI](../../concepts/langgraph_cli.md) to build a Docker image (i.e. `langgraph build`) and push it to a registry your Kubernetes cluster or Amazon ECS cluster has access to.
+
+## Kubernetes
+
+### Prerequisites
+1. `KEDA` is installed on your cluster.
+
+        helm repo add kedacore https://kedacore.github.io/charts 
+        helm install keda kedacore/keda --namespace keda --create-namespace
+
+1. A valid `Ingress` controller is install on your cluster.
+1. You have slack space in your cluster for multiple deployments. `Cluster-Autoscaler` is recommended to automatically provision new nodes.
+
+### Setup
+
+1. You give us your LangSmith organization ID. We will enable the Self-Hosted Data Plane for your organization.
+1. We provide you a [Helm chart](https://github.com/langchain-ai/helm/tree/main/charts/langgraph-dataplane) which you run to setup your Kubernetes cluster. This chart contains a few important components.
+    1. `langgraph-listener`: This is a service that listens to LangChain's [control plane](../../concepts/langgraph_control_plane.md) for changes to your deployments and creates/updates downstream CRDs.
+    1. `LangGraphPlatform CRD`: A CRD for LangGraph Platform deployments. This contains the spec for managing an instance of a LangGraph Platform deployment.
+    1. `langgraph-platform-operator`: This operator handles changes to your LangGraph Platform CRDs.
+1. Configure your `langgraph-dataplane-values.yaml` file.
+
+        config:
+          langgraphPlatformLicenseKey: "" # Your LangGraph Platform license key
+          langsmithApiKey: "" # API Key of your Workspace
+          langsmithWorkspaceId: "" # Workspace ID
+          hostBackendUrl: "https://api.host.langchain.com" # Only override this if on EU
+          smithBackendUrl: "https://api.smith.langchain.com" # Only override this if on EU
+
+1. Deploy `langgraph-dataplane` Helm chart.
+
+        helm repo add langchain https://langchain-ai.github.io/helm/
+        helm repo update
+        helm upgrade -i langgraph-dataplane langchain/langgraph-dataplane --values langgraph-dataplane-values.yaml
+
+1. If successful, you will see two services start up in your namespace.
+
+        NAME                                          READY   STATUS              RESTARTS   AGE
+        langgraph-dataplane-listener-7fccd788-wn2dx   0/1     Running             0          9s
+        langgraph-dataplane-redis-0                   0/1     ContainerCreating   0          9s
+
+1. You create a deployment from the [Control Plane UI](../../concepts/langgraph_control_plane.md#control-plane-ui).
+
+## Amazon ECS
+
+Coming soon!

docs/docs/cloud/deployment/semantic_search.md

@@ -17,7 +17,7 @@ This guide explains how to add semantic search to your LangGraph deployment's cr
     ...
     "store": {
         "index": {
-            "embed": "openai:text-embeddings-3-small",
+            "embed": "openai:text-embedding-3-small",
             "dims": 1536,
             "fields": ["$"]
         }
@@ -27,7 +27,7 @@ This guide explains how to add semantic search to your LangGraph deployment's cr
 
 This configuration:
 
-- Uses OpenAI's text-embeddings-3-small model for generating embeddings
+- Uses OpenAI's text-embedding-3-small model for generating embeddings
 - Sets the embedding dimension to 1536 (matching the model's output)
 - Indexes all fields in your stored data (`["$"]` means index everything, or specify specific fields like `["text", "metadata.title"]`)
 

docs/docs/cloud/deployment/setup.md

@@ -36,21 +36,20 @@ Dependencies can optionally be specified in one of the following files: `pyproje
 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>=0.2.56,<0.3.0
-langgraph-checkpoint>=2.0.5,<3.0
+langgraph>=0.2.56,<0.4.0
+langgraph-sdk>=0.1.53
+langgraph-checkpoint>=2.0.15,<3.0
 langchain-core>=0.2.38,<0.4.0
 langsmith>=0.1.63
 orjson>=3.9.7
 httpx>=0.25.0
 tenacity>=8.0.0
 uvicorn>=0.26.0
-sse-starlette>=2.1.0
+sse-starlette>=2.1.0,<2.2.0
 uvloop>=0.18.0
 httptools>=0.5.0
-jsonschema-rs>=0.16.3
-croniter>=1.0.1
+jsonschema-rs>=0.20.0
 structlog>=23.1.0
-redis>=5.0.0,<6.0.0
 ```
 
 Example `requirements.txt` file:

docs/docs/cloud/deployment/setup_pyproject.md

@@ -36,21 +36,20 @@ Dependencies can optionally be specified in one of the following files: `pyproje
 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>=0.2.56,<0.3.0
-langgraph-checkpoint>=2.0.5,<3.0
+langgraph>=0.2.56,<0.4.0
+langgraph-sdk>=0.1.53
+langgraph-checkpoint>=2.0.15,<3.0
 langchain-core>=0.2.38,<0.4.0
 langsmith>=0.1.63
 orjson>=3.9.7
 httpx>=0.25.0
 tenacity>=8.0.0
 uvicorn>=0.26.0
-sse-starlette>=2.1.0
+sse-starlette>=2.1.0,<2.2.0
 uvloop>=0.18.0
 httptools>=0.5.0
-jsonschema-rs>=0.16.3
-croniter>=1.0.1
+jsonschema-rs>=0.20.0
 structlog>=23.1.0
-redis>=5.0.0,<6.0.0
 ```
 
 Example `pyproject.toml` file:
@@ -65,7 +64,7 @@ license = "MIT"
 readme = "README.md"
 
 [tool.poetry.dependencies]
-python = ">=3.9.0,<3.13"
+python = ">=3.9"
 langgraph = "^0.2.0"
 langchain-fireworks = "^0.1.3"
 

docs/docs/cloud/deployment/standalone_container.md

@@ -0,0 +1,110 @@
+# How to Deploy a Standalone Container
+
+Before deploying, review the [conceptual guide for the Standalone Container](../../concepts/langgraph_standalone_container.md) deployment option.
+
+## Prerequisites
+
+1. Use the [LangGraph CLI](../../concepts/langgraph_cli.md) to [test your application locally](./test_locally.md).
+1. Use the [LangGraph CLI](../../concepts/langgraph_cli.md) to build a Docker image (i.e. `langgraph build`).
+1. The following environment variables are needed for a standalone container deployment.
+    1. `REDIS_URI`: Connection details to a Redis instance. Redis will be used as a pub-sub broker to enable streaming real time output from background runs. The value of `REDIS_URI` must be a valid [Redis connection URI](https://redis-py.readthedocs.io/en/stable/connections.html#redis.Redis.from_url).
+
+        !!! Note "Shared Redis Instance"
+            Multiple self-hosted deployments can share the same Redis instance. For example, for `Deployment A`, `REDIS_URI` can be set to `redis://<hostname_1>:<port>/1` and for `Deployment B`, `REDIS_URI` can be set to `redis://<hostname_1>:<port>/2`.
+
+            `1` and `2` are different database numbers within the same instance, but `<hostname_1>` is shared. **The same database number cannot be used for separate deployments**.
+
+    1. `DATABASE_URI`: Postgres connection details. Postgres will be used to store assistants, threads, runs, persist thread state and long term memory, and to manage the state of the background task queue with 'exactly once' semantics. The value of `DATABASE_URI` must be a valid [Postgres connection URI](https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNSTRING-URIS).
+
+        !!! Note "Shared Postgres Instance"
+            Multiple self-hosted deployments can share the same Postgres instance. For example, for `Deployment A`, `DATABASE_URI` can be set to `postgres://<user>:<password>@/<database_name_1>?host=<hostname_1>` and for `Deployment B`, `DATABASE_URI` can be set to `postgres://<user>:<password>@/<database_name_2>?host=<hostname_1>`.
+
+            `<database_name_1>` and `database_name_2` are different databases within the same instance, but `<hostname_1>` is shared. **The same database cannot be used for separate deployments**.
+
+    1. `LANGSMITH_API_KEY`: (if using [Lite](../../concepts/langgraph_data_plane.md#lite-vs-enterprise)) LangSmith API key. This will be used to authenticate ONCE at server start up.
+    1. `LANGGRAPH_CLOUD_LICENSE_KEY`: (if using [Enterprise](../../concepts/langgraph_data_plane.md#lite-vs-enterprise)) LangGraph Platform license key. This will be used to authenticate ONCE at server start up.
+    1. `LANGSMITH_ENDPOINT`: To send traces to a [self-hosted LangSmith](https://docs.smith.langchain.com/self_hosting) instance, set `LANGSMITH_ENDPOINT` to the hostname of the self-hosted LangSmith instance.
+
+## Kubernetes (Helm)
+
+Use this [Helm chart](https://github.com/langchain-ai/helm/blob/main/charts/langgraph-cloud/README.md) to deploy a LangGraph Server to a Kubernetes cluster.
+
+## Docker
+
+Run the following `docker` command:
+```shell
+docker run \
+    --env-file .env \
+    -p 8123:8000 \
+    -e REDIS_URI="foo" \
+    -e DATABASE_URI="bar" \
+    -e LANGSMITH_API_KEY="baz" \
+    my-image
+```
+
+!!! note
+
+    * You need to replace `my-image` with the name of the image you built in the prerequisite steps (from `langgraph build`)
+    and you should provide appropriate values for `REDIS_URI`, `DATABASE_URI`, and `LANGSMITH_API_KEY`.
+    * If your application requires additional environment variables, you can pass them in a similar way.
+
+## Docker Compose
+
+Docker Compose YAML file:
+```yml
+volumes:
+    langgraph-data:
+        driver: local
+services:
+    langgraph-redis:
+        image: redis:6
+        healthcheck:
+            test: redis-cli ping
+            interval: 5s
+            timeout: 1s
+            retries: 5
+    langgraph-postgres:
+        image: postgres:16
+        ports:
+            - "5433:5432"
+        environment:
+            POSTGRES_DB: postgres
+            POSTGRES_USER: postgres
+            POSTGRES_PASSWORD: postgres
+        volumes:
+            - langgraph-data:/var/lib/postgresql/data
+        healthcheck:
+            test: pg_isready -U postgres
+            start_period: 10s
+            timeout: 1s
+            retries: 5
+            interval: 5s
+    langgraph-api:
+        image: ${IMAGE_NAME}
+        ports:
+            - "8123:8000"
+        depends_on:
+            langgraph-redis:
+                condition: service_healthy
+            langgraph-postgres:
+                condition: service_healthy
+        env_file:
+            - .env
+        environment:
+            REDIS_URI: redis://langgraph-redis:6379
+            LANGSMITH_API_KEY: ${LANGSMITH_API_KEY}
+            POSTGRES_URI: postgres://postgres:postgres@langgraph-postgres:5432/postgres?sslmode=disable
+```
+
+You can run the command `docker compose up` with this Docker Compose file in the same folder.
+
+This will launch a LangGraph Server on port `8123` (if you want to change this, you can change this by changing the ports in the `langgraph-api` volume). You can test if the application is healthy by running:
+
+```shell
+curl --request GET --url 0.0.0.0:8123/ok
+```
+Assuming everything is running correctly, you should see a response like:
+
+```shell
+{"ok":true}
+```

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

@@ -0,0 +1,31 @@
+# Testing local agents with remote traces
+
+## Overview
+
+A common workflow when debugging production-deployed agents is to test the same thread against a local version of the same agent, which may have modifications.
+
+To support this, LangGraph Studio, in combination with LangSmith, allows you to clone remote threads traced in LangSmith into your locally running agent. This cloned thread can then be used to re-run specific nodes within Studio.
+
+## Requirements
+
+!!! info "Prerequisites"
+
+    - langgraph>=0.3.18
+    - langgraph-api>=0.0.32
+
+- A thread traced in LangSmith.
+- A locally running agent. See [here](../../how-tos/local-studio.md) for setup instructions.
+  - Note that your local agent must be using the above specified `langgraph` and `langgraph-api` versions.
+  - The nodes present in the remote trace must exist in at least one of the graphs in your local agent.
+
+## Cloning Thread
+
+First navigate to the LangSmith trace. Here you should see a button to "Run in Studio".
+
+![Run in Studio](../img/run_in_studio.png){width=1200}
+
+This will prompt you to enter the url that your locally running agent is accessible at. Once provided, select "Clone thread locally". If you have multiple graphs in your agent, you will also be prompted to select a graph to clone this thread under.
+
+Once selected, a will a new thread in your local agent will be created and the thread history will be reconstruced to reflect the original trace.
+
+Alternatively, if your trace originates from an agent deployed on LangGraph Platform, you can "View original thread" to open Studio with the actual deployed thread.

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

@@ -0,0 +1,366 @@
+# How to implement Generative User Interfaces with LangGraph
+
+!!! info "Prerequisites"
+
+    - [LangGraph Platform](../../concepts/langgraph_platform.md)
+    - [LangGraph Server](../../concepts/langgraph_server.md)
+    - [`useStream()` React Hook](./use_stream_react.md)
+
+Generative user interfaces (Generative UI) allows agents to go beyond text and generate rich user interfaces. This enables creating more interactive and context-aware applications where the UI adapts based on the conversation flow and AI responses.
+
+![Generative UI Sample](./img/generative_ui_sample.jpg)
+
+LangGraph Platform supports colocating your React components with your graph code. This allows you to focus on building specific UI components for your graph while easily plugging into existing chat interfaces such as [Agent Chat](https://agentchat.vercel.app) and loading the code only when actually needed.
+
+## Tutorial
+
+### 1. Define and configure UI components
+
+First, create your first UI component. For each component you need to provide an unique identifier that will be used to reference the component in your graph code.
+
+```tsx title="src/agent/ui.tsx"
+const WeatherComponent = (props: { city: string }) => {
+  return <div>Weather for {props.city}</div>;
+};
+
+export default {
+  weather: WeatherComponent,
+};
+```
+
+Next, define your UI components in your `langgraph.json` configuration:
+
+```json
+{
+  "node_version": "20",
+  "graphs": {
+    "agent": "./src/agent/index.ts:graph"
+  },
+  "ui": {
+    "agent": "./src/agent/ui.tsx"
+  }
+}
+```
+
+The `ui` section points to the UI components that will be used by graphs. By default, we recommend using the same key as the graph name, but you can split out the components however you like, see [Customise the namespace of UI components](#customise-the-namespace-of-ui-components) for more details.
+
+LangGraph Platform will automatically bundle your UI components code and styles and serve them as external assets that can be loaded by the `LoadExternalComponent` component. Some dependencies such as `react` and `react-dom` will be automatically excluded from the bundle.
+
+CSS and Tailwind 4.x is also supported out of the box, so you can freely use Tailwind classes as well as `shadcn/ui` in your UI components.
+
+=== "`src/agent/ui.tsx`"
+
+    ```tsx
+    import "./styles.css";
+
+    const WeatherComponent = (props: { city: string }) => {
+      return <div className="bg-red-500">Weather for {props.city}</div>;
+    };
+
+    export default {
+      weather: WeatherComponent,
+    };
+    ```
+
+=== "`src/agent/styles.css`"
+
+    ```css
+    @import "tailwindcss";
+    ```
+
+### 2. Send the UI components in your graph
+
+=== "Python"
+
+    ```python title="src/agent.py"
+    import uuid
+    from typing import Annotated, Sequence, TypedDict
+
+    from langchain_core.messages import AIMessage, BaseMessage
+    from langchain_openai import ChatOpenAI
+    from langgraph.graph import StateGraph
+    from langgraph.graph.message import add_messages
+    from langgraph.graph.ui import AnyUIMessage, ui_message_reducer, push_ui_message
+
+
+    class AgentState(TypedDict):  # noqa: D101
+        messages: Annotated[Sequence[BaseMessage], add_messages]
+        ui: Annotated[Sequence[AnyUIMessage], ui_message_reducer]
+
+
+    async def weather(state: AgentState):
+        class WeatherOutput(TypedDict):
+            city: str
+
+        weather: WeatherOutput = (
+            await ChatOpenAI(model="gpt-4o-mini")
+            .with_structured_output(WeatherOutput)
+            .with_config({"tags": ["nostream"]})
+            .ainvoke(state["messages"])
+        )
+
+        message = AIMessage(
+            id=str(uuid.uuid4()),
+            content=f"Here's the weather for {weather['city']}",
+        )
+
+        # Emit UI elements associated with the message
+        push_ui_message("weather", weather, message=message)
+        return {"messages": [message]}
+
+
+    workflow = StateGraph(AgentState)
+    workflow.add_node(weather)
+    workflow.add_edge("__start__", "weather")
+    graph = workflow.compile()
+    ```
+
+=== "JS"
+
+    Use the `typedUi` utility to emit UI elements from your agent nodes:
+
+    ```typescript title="src/agent/index.ts"
+    import {
+      typedUi,
+      uiMessageReducer,
+    } from "@langchain/langgraph-sdk/react-ui/server";
+
+    import { ChatOpenAI } from "@langchain/openai";
+    import { v4 as uuidv4 } from "uuid";
+    import { z } from "zod";
+
+    import type ComponentMap from "./ui.js";
+
+    import {
+      Annotation,
+      MessagesAnnotation,
+      StateGraph,
+      type LangGraphRunnableConfig,
+    } from "@langchain/langgraph";
+
+    const AgentState = Annotation.Root({
+      ...MessagesAnnotation.spec,
+      ui: Annotation({ reducer: uiMessageReducer, default: () => [] }),
+    });
+
+    export const graph = new StateGraph(AgentState)
+      .addNode("weather", async (state, config) => {
+        // Provide the type of the component map to ensure
+        // type safety of `ui.push()` calls as well as
+        // pushing the messages to the `ui` and sending a custom event as well.
+        const ui = typedUi<typeof ComponentMap>(config);
+
+        const weather = await new ChatOpenAI({ model: "gpt-4o-mini" })
+          .withStructuredOutput(z.object({ city: z.string() }))
+          .withConfig({ tags: ["nostream"] })
+          .invoke(state.messages);
+
+        const response = {
+          id: uuidv4(),
+          type: "ai",
+          content: `Here's the weather for ${weather.city}`,
+        };
+
+        // Emit UI elements associated with the AI message
+        ui.push({ name: "weather", props: weather }, { message: response });
+
+        return { messages: [response] };
+      })
+      .addEdge("__start__", "weather")
+      .compile();
+    ```
+
+### 3. Handle UI elements in your React application
+
+On the client side, you can use `useStream()` and `LoadExternalComponent` to display the UI elements.
+
+```tsx title="src/app/page.tsx"
+"use client";
+
+import { useStream } from "@langchain/langgraph-sdk/react";
+import { LoadExternalComponent } from "@langchain/langgraph-sdk/react-ui";
+
+export default function Page() {
+  const { thread, values } = useStream({
+    apiUrl: "http://localhost:2024",
+    assistantId: "agent",
+  });
+
+  return (
+    <div>
+      {thread.messages.map((message) => (
+        <div key={message.id}>
+          {message.content}
+          {values.ui
+            ?.filter((ui) => ui.metadata?.message_id === message.id)
+            .map((ui) => (
+              <LoadExternalComponent key={ui.id} stream={thread} message={ui} />
+            ))}
+        </div>
+      ))}
+    </div>
+  );
+}
+```
+
+Behind the scenes, `LoadExternalComponent` will fetch the JS and CSS for the UI components from LangGraph Platform and render them in a shadow DOM, thus ensuring style isolation from the rest of your application.
+
+## How-to guides
+
+### Show loading UI when components are loading
+
+You can provide a fallback UI to be rendered when the components are loading.
+
+```tsx
+<LoadExternalComponent
+  stream={thread}
+  message={ui}
+  fallback={<div>Loading...</div>}
+/>
+```
+
+### Provide custom components on the client side
+
+If you already have the components loaded in your client application, you can provide a map of such components to be rendered directly without fetching the UI code from LangGraph Platform.
+
+```tsx
+const clientComponents = {
+  weather: WeatherComponent,
+};
+
+<LoadExternalComponent
+  stream={thread}
+  message={ui}
+  components={clientComponents}
+/>;
+```
+
+### Customise the namespace of UI components.
+
+By default `LoadExternalComponent` will use the `assistantId` from `useStream()` hook to fetch the code for UI components. You can customise this by providing a `namespace` prop to the `LoadExternalComponent` component.
+
+=== "`src/app/page.tsx`"
+
+    ```tsx
+    <LoadExternalComponent
+      stream={thread}
+      message={ui}
+      namespace="custom-namespace"
+    />
+    ```
+
+=== "`langgraph.json`"
+
+    ```json
+    {
+      "ui": {
+        "custom-namespace": "./src/agent/ui.tsx"
+      }
+    }
+    ```
+
+### Access and interact with the thread state from the UI component
+
+You can access the thread state inside the UI component by using the `useStreamContext` hook.
+
+```tsx
+import { useStreamContext } from "@langchain/langgraph-sdk/react-ui";
+
+const WeatherComponent = (props: { city: string }) => {
+  const { thread, submit } = useStreamContext();
+  return (
+    <>
+      <div>Weather for {props.city}</div>
+
+      <button
+        onClick={() => {
+          const newMessage = {
+            type: "human",
+            content: `What's the weather in ${props.city}?`,
+          };
+
+          submit({ messages: [newMessage] });
+        }}
+      >
+        Retry
+      </button>
+    </>
+  );
+};
+```
+
+### Pass additional context to the client components
+
+You can pass additional context to the client components by providing a `meta` prop to the `LoadExternalComponent` component.
+
+```tsx
+<LoadExternalComponent stream={thread} message={ui} meta={{ userId: "123" }} />
+```
+
+Then, you can access the `meta` prop in the UI component by using the `useStreamContext` hook.
+
+```tsx
+import { useStreamContext } from "@langchain/langgraph-sdk/react-ui";
+
+const WeatherComponent = (props: { city: string }) => {
+  const { meta } = useStreamContext<
+    { city: string },
+    { MetaType: { userId?: string } }
+  >();
+
+  return (
+    <div>
+      Weather for {props.city} (user: {meta?.userId})
+    </div>
+  );
+};
+```
+
+### Streaming UI updates before the node execution is finished
+
+You can stream UI updates before the node execution is finished by using the `onCustomEvent` callback of the `useStream()` hook.
+
+```tsx
+import { uiMessageReducer } from "@langchain/langgraph-sdk/react-ui";
+
+const { thread, submit } = useStream({
+  apiUrl: "http://localhost:2024",
+  assistantId: "agent",
+  onCustomEvent: (event, options) => {
+    options.mutate((prev) => {
+      const ui = uiMessageReducer(prev.ui ?? [], event);
+      return { ...prev, ui };
+    });
+  },
+});
+```
+
+### Remove UI messages from state
+
+Similar to how messages can be removed from the state by appending a RemoveMessage you can remove an UI message from the state by calling `remove_ui_message` / `ui.delete` with the ID of the UI message.
+
+=== "Python"
+
+    ```python
+    from langgraph.graph.ui import push_ui_message, delete_ui_message
+
+    # push message
+    message = push_ui_message("weather", {"city": "London"})
+
+    # remove said message
+    delete_ui_message(message["id"])
+    ```
+
+=== "JS"
+
+    ```tsx
+    // push message
+    const message = ui.push({ name: "weather", props: { city: "London" } });
+
+    // remove said message
+    ui.delete(message.id);
+    ```
+
+## Learn more
+
+- [JS/TS SDK Reference](../reference/sdk/js_ts_sdk_ref.md)

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

@@ -63,7 +63,7 @@ Now, let's invoke our graph by interrupting before `ask_human` node:
         "messages": [
             {
                 "role": "user",
-                "content": "Use the search tool to ask the user where they are, then look up the weather there",
+                "content": "Ask the user where they are, then look up the weather there",
             }
         ]
     }
@@ -85,8 +85,7 @@ Now, let's invoke our graph by interrupting before `ask_human` node:
       messages: [
         {
           role: "human",
-          content: "Use the search tool to ask the user where they are, then look up the weather there"
-        }
+          content: "Ask the user where they are, then look up the weather there" }
       ]
     };
 
@@ -115,7 +114,7 @@ Now, let's invoke our graph by interrupting before `ask_human` node:
      --header 'Content-Type: application/json' \
      --data "{
        \"assistant_id\": \"agent\",
-       \"input\": {\"messages\": [{\"role\": \"human\", \"content\": \"Use the search tool to ask the user where they are, then look up the weather there\"}]},
+       \"input\": {\"messages\": [{\"role\": \"human\", \"content\": \"Ask the user where they are, then look up the weather there\"}]},
        \"interrupt_before\": [\"ask_human\"],
        \"stream_mode\": [
          \"updates\"

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

@@ -0,0 +1,140 @@
+# Prompt Engineering in LangGraph Studio
+
+## Overview
+
+A central aspect of agent development is prompt engineering. LangGraph Studio makes it easy to iterate on the prompts used within your graph directly within the UI.
+
+## Setup
+
+The first step is to define your [configuration](https://langchain-ai.github.io/langgraph/how-tos/configuration/) such that LangGraph Studio is aware of the prompts you want to iterate on and which nodes they are associated with.
+
+### Reference
+
+When defining your configuration, you can use special metadata keys to instruct LangGraph Studio how to handle different fields. Here's a reference for the available configuration options:
+
+#### `langgraph_nodes`
+
+- **Description**: Specifies which graph nodes a configuration field is associated with.
+- **Value Type**: Array of strings, where each string is the name of a node in your graph.
+- **Usage Context**: Include in the `json_schema_extra` dictionary for Pydantic models or the `metadata["json_schema_extra"]` dictionary for dataclasses.
+- **Required**: No, but necessary if you want a field to be editable for specific nodes in the UI.
+- **Example**:
+  ```python
+  system_prompt: str = Field(
+      default="You are a helpful AI assistant.",
+      json_schema_extra={"langgraph_nodes": ["call_model", "other_node"]},
+  )
+  ```
+
+#### `langgraph_type`
+
+- **Description**: Specifies the type of configuration field, which determines how it's handled in the UI.
+- **Value Type**: String
+- **Supported Values**:
+  - `"prompt"`: Indicates the field contains prompt text that should be treated specially in the UI.
+- **Usage Context**: Include in the `json_schema_extra` dictionary for Pydantic models or the `metadata["json_schema_extra"]` dictionary for dataclasses.
+- **Required**: No, but helpful for prompt fields to enable special handling.
+- **Example**:
+  ```python
+  system_prompt: str = Field(
+      default="You are a helpful AI assistant.",
+      json_schema_extra={
+          "langgraph_nodes": ["call_model"],
+          "langgraph_type": "prompt",
+      },
+  )
+  ```
+
+### Example
+
+For example, if you have a node called `call_model` whose system prompt you want to iterate on, you can define a configuration like the following.
+
+```python
+## Using Pydantic
+from pydantic import BaseModel, Field
+from typing import Annotated, Literal
+
+class Configuration(BaseModel):
+    """The configuration for the agent."""
+
+    system_prompt: str = Field(
+        default="You are a helpful AI assistant.",
+        description="The system prompt to use for the agent's interactions. "
+        "This prompt sets the context and behavior for the agent.",
+        json_schema_extra={
+            "langgraph_nodes": ["call_model"],
+            "langgraph_type": "prompt",
+        },
+    )
+
+    model: Annotated[
+        Literal[
+            "anthropic/claude-3-7-sonnet-latest",
+            "anthropic/claude-3-5-haiku-latest",
+            "openai/o1",
+            "openai/gpt-4o-mini",
+            "openai/o1-mini",
+            "openai/o3-mini",
+        ],
+        {"__template_metadata__": {"kind": "llm"}},
+    ] = Field(
+        default="openai/gpt-4o-mini",
+        description="The name of the language model to use for the agent's main interactions. "
+        "Should be in the form: provider/model-name.",
+        json_schema_extra={"langgraph_nodes": ["call_model"]},
+    )
+
+## Using Dataclasses
+from dataclasses import dataclass, field
+
+@dataclass(kw_only=True)
+class Configuration:
+    """The configuration for the agent."""
+
+    system_prompt: str = field(
+        default="You are a helpful AI assistant.",
+        metadata={
+            "description": "The system prompt to use for the agent's interactions. "
+            "This prompt sets the context and behavior for the agent.",
+            "json_schema_extra": {"langgraph_nodes": ["call_model"]},
+        },
+    )
+
+    model: Annotated[str, {"__template_metadata__": {"kind": "llm"}}] = field(
+        default="anthropic/claude-3-5-sonnet-20240620",
+        metadata={
+            "description": "The name of the language model to use for the agent's main interactions. "
+            "Should be in the form: provider/model-name.",
+            "json_schema_extra": {"langgraph_nodes": ["call_model"]},
+        },
+    )
+
+```
+
+## Iterating on prompts
+
+### Node Configuration
+
+With this set up, running your graph and viewing in LangGraph Studio will result in the graph rendering like such.
+
+**Note the configuration icon in the top right corner of the `call_model` node**:
+
+![Graph in Studio](../img/studio_graph_with_configuration.png){width=1200}
+
+Clicking this icon will open a modal where you can edit the configuration for all of the fields associated with the `call_model` node. From here, you can save your changes and apply them to the graph. Note that these values reflect the currently active assistant, and saving will update the assistant with the new values.
+
+![Configuration modal](../img/studio_node_configuration.png){width=1200}
+
+### Playground
+
+LangGraph Studio also supports prompt engineering through an integration with the LangSmith Playground. To do so:
+
+1. Open an existing thread or create a new one.
+2. Within the thread log, any nodes that have made an LLM call will have a "View LLM Runs" button. Clicking this will open a popover with the LLM runs for that node.
+3. Select the LLM run you want to edit. This will open the LangSmith Playground with the selected LLM run.
+
+![Playground in Studio](../img/studio_playground.png){width=1200}
+
+From here you can edit the prompt, test different model configurations and re-run just this LLM call without having to re-run the entire graph. When you are happy with your changes, you can copy the updated prompt back into your graph.
+
+For more information on how to use the LangSmith Playground, see the [LangSmith Playground documentation](https://docs.smith.langchain.com/prompt_engineering/how_to_guides#playground).

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

@@ -99,7 +99,7 @@ We can stream the results of a stateless run in an almost identical fashion to h
 
     ```bash
     curl --request POST \
-        --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/stream \
+        --url <DEPLOYMENT_URL>/runs/stream \
         --header 'Content-Type: application/json' \
         --data "{
             \"assistant_id\": \"agent\",
@@ -144,7 +144,7 @@ In addition to streaming, you can also wait for a stateless result by using the
 
     ```bash
     curl --request POST \
-        --url <DEPLOYMENT_URL>/runs/runs/wait \
+        --url <DEPLOYMENT_URL>/runs/wait \
         --header 'Content-Type: application/json' \
         --data '{
             "assistant_id": <ASSISTANT_IDD>,

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

@@ -1,10 +1,10 @@
-# Test Cloud Deployment
+# Test LangGraph Platform Deployment
 
-The LangGraph Studio UI connects directly to LangGraph Cloud deployments.
+The LangGraph Studio UI connects directly to LangGraph Platform deployments.
 
 Starting from the <a href="https://smith.langchain.com/" target="_blank">LangSmith UI</a>...
 
-1. In the left-hand navigation panel, select `LangGraph Cloud`. The `LangGraph Cloud` view contains a list of existing LangGraph Cloud deployments.
+1. In the left-hand navigation panel, select `LangGraph Platform`. The `LangGraph Platform` view contains a list of existing LangGraph Platform 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).

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

@@ -1,7 +1,7 @@
 # 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.
+    Safari blocks `localhost` connections to Studio. To work around this, start the server with `--tunnel` and you’ll be able to access Studio from Safari via a secure tunnel.
 
 ## Setup
 

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

@@ -0,0 +1,484 @@
+# How to integrate LangGraph into your React application
+
+!!! info "Prerequisites" 
+
+    - [LangGraph Platform](../../concepts/langgraph_platform.md) 
+    - [LangGraph Server](../../concepts/langgraph_server.md)
+
+The `useStream()` React hook provides a seamless way to integrate LangGraph into your React applications. It handles all the complexities of streaming, state management, and branching logic, letting you focus on building great chat experiences.
+
+Key features:
+
+- Messages streaming: Handle a stream of message chunks to form a complete message
+- Automatic state management for messages, interrupts, loading states, and errors
+- Conversation branching: Create alternate conversation paths from any point in the chat history
+- UI-agnostic design: bring your own components and styling
+
+Let's explore how to use `useStream()` in your React application.
+
+The `useStream()` provides a solid foundation for creating bespoke chat experiences. For pre-built chat components and interfaces, we also recommend checking out [CopilotKit](https://docs.copilotkit.ai/coagents/quickstart/langgraph) and [assistant-ui](https://www.assistant-ui.com/docs/runtimes/langgraph).
+
+## Installation
+
+```bash
+npm install @langchain/langgraph-sdk @langchain/core
+```
+
+## Example
+
+```tsx
+"use client";
+
+import { useStream } from "@langchain/langgraph-sdk/react";
+import type { Message } from "@langchain/langgraph-sdk";
+
+export default function App() {
+  const thread = useStream<{ messages: Message[] }>({
+    apiUrl: "http://localhost:2024",
+    assistantId: "agent",
+    messagesKey: "messages",
+  });
+
+  return (
+    <div>
+      <div>
+        {thread.messages.map((message) => (
+          <div key={message.id}>{message.content as string}</div>
+        ))}
+      </div>
+
+      <form
+        onSubmit={(e) => {
+          e.preventDefault();
+
+          const form = e.target as HTMLFormElement;
+          const message = new FormData(form).get("message") as string;
+
+          form.reset();
+          thread.submit({ messages: [{ type: "human", content: message }] });
+        }}
+      >
+        <input type="text" name="message" />
+
+        {thread.isLoading ? (
+          <button key="stop" type="button" onClick={() => thread.stop()}>
+            Stop
+          </button>
+        ) : (
+          <button keytype="submit">Send</button>
+        )}
+      </form>
+    </div>
+  );
+}
+```
+
+## Customizing Your UI
+
+The `useStream()` hook takes care of all the complex state management behind the scenes, providing you with simple interfaces to build your UI. Here's what you get out of the box:
+
+- Thread state management
+- Loading and error states
+- Interrupts
+- Message handling and updates
+- Branching support
+
+Here are some examples on how to use these features effectively:
+
+### Loading States
+
+The `isLoading` property tells you when a stream is active, enabling you to:
+
+- Show a loading indicator
+- Disable input fields during processing
+- Display a cancel button
+
+```tsx
+export default function App() {
+  const { isLoading, stop } = useStream<{ messages: Message[] }>({
+    apiUrl: "http://localhost:2024",
+    assistantId: "agent",
+    messagesKey: "messages",
+  });
+
+  return (
+    <form>
+      {isLoading && (
+        <button key="stop" type="button" onClick={() => stop()}>
+          Stop
+        </button>
+      )}
+    </form>
+  );
+}
+```
+
+### Thread Management
+
+Keep track of conversations with built-in thread management. You can access the current thread ID and get notified when new threads are created:
+
+```tsx
+const [threadId, setThreadId] = useState<string | null>(null);
+
+const thread = useStream<{ messages: Message[] }>({
+  apiUrl: "http://localhost:2024",
+  assistantId: "agent",
+
+  threadId: threadId,
+  onThreadId: setThreadId,
+});
+```
+
+We recommend storing the `threadId` in your URL's query parameters to let users resume conversations after page refreshes.
+
+### Messages Handling
+
+The `useStream()` hook will keep track of the message chunks received from the server and concatenate them together to form a complete message. The completed message chunks can be retrieved via the `messages` property.
+
+By default, the `messagesKey` is set to `messages`, where it will append the new messages chunks to `values["messages"]`. If you store messages in a different key, you can change the value of `messagesKey`.
+
+```tsx
+import type { Message } from "@langchain/langgraph-sdk";
+import { useStream } from "@langchain/langgraph-sdk/react";
+
+export default function HomePage() {
+  const thread = useStream<{ messages: Message[] }>({
+    apiUrl: "http://localhost:2024",
+    assistantId: "agent",
+    messagesKey: "messages",
+  });
+
+  return (
+    <div>
+      {thread.messages.map((message) => (
+        <div key={message.id}>{message.content as string}</div>
+      ))}
+    </div>
+  );
+}
+```
+
+Under the hood, the `useStream()` hook will use the `streamMode: "messages-tuple"` to receive a stream of messages (i.e. individual LLM tokens) from any LangChain chat model invocations inside your graph nodes. Learn more about messages streaming in the [How to stream messages from your graph](./stream_messages.md) guide.
+
+### Interrupts
+
+The `useStream()` hook exposes the `interrupt` property, which will be filled with the last interrupt from the thread. You can use interrupts to:
+
+- Render a confirmation UI before executing a node
+- Wait for human input, allowing agent to ask the user with clarifying questions
+
+Learn more about interrupts in the [How to handle interrupts](../../how-tos/human_in_the_loop/wait-user-input.ipynb) guide.
+
+```tsx
+const thread = useStream<{ messages: Message[] }, { InterruptType: string }>({
+  apiUrl: "http://localhost:2024",
+  assistantId: "agent",
+  messagesKey: "messages",
+});
+
+if (thread.interrupt) {
+  return (
+    <div>
+      Interrupted! {thread.interrupt.value}
+      <button
+        type="button"
+        onClick={() => {
+          // `resume` can be any value that the agent accepts
+          thread.submit(undefined, { command: { resume: true } });
+        }}
+      >
+        Resume
+      </button>
+    </div>
+  );
+}
+```
+
+### Branching
+
+For each message, you can use `getMessagesMetadata()` to get the first checkpoint from which the message has been first seen. You can then create a new run from the checkpoint preceding the first seen checkpoint to create a new branch in a thread.
+
+A branch can be created in following ways:
+
+1. Edit a previous user message.
+2. Request a regeneration of a previous assistant message.
+
+```tsx
+"use client";
+
+import type { Message } from "@langchain/langgraph-sdk";
+import { useStream } from "@langchain/langgraph-sdk/react";
+import { useState } from "react";
+
+function BranchSwitcher({
+  branch,
+  branchOptions,
+  onSelect,
+}: {
+  branch: string | undefined;
+  branchOptions: string[] | undefined;
+  onSelect: (branch: string) => void;
+}) {
+  if (!branchOptions || !branch) return null;
+  const index = branchOptions.indexOf(branch);
+
+  return (
+    <div className="flex items-center gap-2">
+      <button
+        type="button"
+        onClick={() => {
+          const prevBranch = branchOptions[index - 1];
+          if (!prevBranch) return;
+          onSelect(prevBranch);
+        }}
+      >
+        Prev
+      </button>
+      <span>
+        {index + 1} / {branchOptions.length}
+      </span>
+      <button
+        type="button"
+        onClick={() => {
+          const nextBranch = branchOptions[index + 1];
+          if (!nextBranch) return;
+          onSelect(nextBranch);
+        }}
+      >
+        Next
+      </button>
+    </div>
+  );
+}
+
+function EditMessage({
+  message,
+  onEdit,
+}: {
+  message: Message;
+  onEdit: (message: Message) => void;
+}) {
+  const [editing, setEditing] = useState(false);
+
+  if (!editing) {
+    return (
+      <button type="button" onClick={() => setEditing(true)}>
+        Edit
+      </button>
+    );
+  }
+
+  return (
+    <form
+      onSubmit={(e) => {
+        e.preventDefault();
+        const form = e.target as HTMLFormElement;
+        const content = new FormData(form).get("content") as string;
+
+        form.reset();
+        onEdit({ type: "human", content });
+        setEditing(false);
+      }}
+    >
+      <input name="content" defaultValue={message.content as string} />
+      <button type="submit">Save</button>
+    </form>
+  );
+}
+
+export default function App() {
+  const thread = useStream({
+    apiUrl: "http://localhost:2024",
+    assistantId: "agent",
+    messagesKey: "messages",
+  });
+
+  return (
+    <div>
+      <div>
+        {thread.messages.map((message) => {
+          const meta = thread.getMessagesMetadata(message);
+          const parentCheckpoint = meta?.firstSeenState?.parent_checkpoint;
+
+          return (
+            <div key={message.id}>
+              <div>{message.content as string}</div>
+
+              {message.type === "human" && (
+                <EditMessage
+                  message={message}
+                  onEdit={(message) =>
+                    thread.submit(
+                      { messages: [message] },
+                      { checkpoint: parentCheckpoint }
+                    )
+                  }
+                />
+              )}
+
+              {message.type === "ai" && (
+                <button
+                  type="button"
+                  onClick={() =>
+                    thread.submit(undefined, { checkpoint: parentCheckpoint })
+                  }
+                >
+                  <span>Regenerate</span>
+                </button>
+              )}
+
+              <BranchSwitcher
+                branch={meta?.branch}
+                branchOptions={meta?.branchOptions}
+                onSelect={(branch) => thread.setBranch(branch)}
+              />
+            </div>
+          );
+        })}
+      </div>
+
+      <form
+        onSubmit={(e) => {
+          e.preventDefault();
+
+          const form = e.target as HTMLFormElement;
+          const message = new FormData(form).get("message") as string;
+
+          form.reset();
+          thread.submit({ messages: [message] });
+        }}
+      >
+        <input type="text" name="message" />
+
+        {thread.isLoading ? (
+          <button key="stop" type="button" onClick={() => thread.stop()}>
+            Stop
+          </button>
+        ) : (
+          <button key="submit" type="submit">
+            Send
+          </button>
+        )}
+      </form>
+    </div>
+  );
+}
+```
+
+For advanced use cases you can use the `experimental_branchTree` property to get the tree representation of the thread, which can be used to render branching controls for non-message based graphs.
+
+### Optimistic Updates
+
+You can optimistically update the client state before performing a network request to the agent, allowing you to provide immediate feedback to the user, such as showing the user message immediately before the agent has seen the request.
+
+```tsx
+const stream = useStream({
+  apiUrl: "http://localhost:2024",
+  assistantId: "agent",
+  messagesKey: "messages",
+});
+
+const handleSubmit = (text: string) => {
+  const newMessage = { type: "human" as const, content: text };
+
+  stream.submit(
+    { messages: [newMessage] },
+    {
+      optimisticValues(prev) {
+        const prevMessages = prev.messages ?? [];
+        const newMessages = [...prevMessages, newMessage];
+        return { ...prev, messages: newMessages };
+      },
+    }
+  );
+};
+```
+
+### TypeScript
+
+The `useStream()` hook is friendly for apps written in TypeScript and you can specify types for the state to get better type safety and IDE support.
+
+```tsx
+// Define your types
+type State = {
+  messages: Message[];
+  context?: Record<string, unknown>;
+};
+
+// Use them with the hook
+const thread = useStream<State>({
+  apiUrl: "http://localhost:2024",
+  assistantId: "agent",
+  messagesKey: "messages",
+});
+```
+
+You can also optionally specify types for different scenarios, such as:
+
+- `ConfigurableType`: Type for the `config.configurable` property (default: `Record<string, unknown>`)
+- `InterruptType`: Type for the interrupt value - i.e. contents of `interrupt(...)` function (default: `unknown`)
+- `CustomEventType`: Type for the custom events (default: `unknown`)
+- `UpdateType`: Type for the submit function (default: `Partial<State>`)
+
+```tsx
+const thread = useStream<
+  State,
+  {
+    UpdateType: {
+      messages: Message[] | Message;
+      context?: Record<string, unknown>;
+    };
+    InterruptType: string;
+    CustomEventType: {
+      type: "progress" | "debug";
+      payload: unknown;
+    };
+    ConfigurableType: {
+      model: string;
+    };
+  }
+>({
+  apiUrl: "http://localhost:2024",
+  assistantId: "agent",
+  messagesKey: "messages",
+});
+```
+
+If you're using LangGraph.js, you can also reuse your graph's annotation types. However, make sure to only import the types of the annotation schema in order to avoid importing the entire LangGraph.js runtime (i.e. via `import type { ... }` directive).
+
+```tsx
+import {
+  Annotation,
+  MessagesAnnotation,
+  type StateType,
+  type UpdateType,
+} from "@langchain/langgraph/web";
+
+const AgentState = Annotation.Root({
+  ...MessagesAnnotation.spec,
+  context: Annotation<string>(),
+});
+
+const thread = useStream<
+  StateType<typeof AgentState.spec>,
+  { UpdateType: UpdateType<typeof AgentState.spec> }
+>({
+  apiUrl: "http://localhost:2024",
+  assistantId: "agent",
+  messagesKey: "messages",
+});
+```
+
+## Event Handling
+
+The `useStream()` hook provides several callback options to help you respond to different events:
+
+- `onError`: Called when an error occurs.
+- `onFinish`: Called when the stream is finished.
+- `onUpdateEvent`: Called when an update event is received.
+- `onCustomEvent`: Called when a custom event is received. See [Custom events](../../concepts/streaming.md#custom) to learn how to stream custom events.
+- `onMetadataEvent`: Called when a metadata event is received, which contains the Run ID and Thread ID.
+
+## Learn More
+
+- [JS/TS SDK Reference](../reference/sdk/js_ts_sdk_ref.md)

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

@@ -1,142 +1,147 @@
-# Use Webhooks
+# Using Webhooks
 
-You may wish to use webhooks in your client, especially when using async streams in case you want to update something in your service once the API call to LangGraph Cloud has finished running. To do so, you will need to expose an endpoint that can accept POST requests, and then pass it to your API request in the "webhook" parameter.
+When working with LangGraph Cloud, you may want to use webhooks to receive updates after an API call completes. Webhooks are useful for triggering actions in your service once a run has finished processing. To implement this, you need to expose an endpoint that can accept `POST` requests and pass this endpoint as a `webhook` parameter in your API request.
 
-Currently, the SDK has not exposed this endpoint but you can access it through curl commands as follows.
+Currently, the SDK does not provide built-in support for defining webhook endpoints, but you can specify them manually using API requests.
 
-The following endpoints accept `webhook` as a parameter: 
+## Supported Endpoints
 
-- Create Run -> POST /thread/{thread_id}/runs
-- Create Thread Cron -> POST /thread/{thread_id}/runs/crons
-- Stream Run -> POST /thread/{thread_id}/runs/stream
-- Wait Run -> POST /thread/{thread_id}/runs/wait
-- Create Cron -> POST /runs/crons
-- Stream Run Stateless -> POST /runs/stream
-- Wait Run Stateless -> POST /runs/wait
+The following API endpoints accept a `webhook` parameter:
 
-In this example, we will show calling a webhook after streaming a run. 
+| Operation | HTTP Method | Endpoint |
+|-----------|------------|----------|
+| Create Run | `POST` | `/thread/{thread_id}/runs` |
+| Create Thread Cron | `POST` | `/thread/{thread_id}/runs/crons` |
+| Stream Run | `POST` | `/thread/{thread_id}/runs/stream` |
+| Wait Run | `POST` | `/thread/{thread_id}/runs/wait` |
+| Create Cron | `POST` | `/runs/crons` |
+| Stream Run Stateless | `POST` | `/runs/stream` |
+| Wait Run Stateless | `POST` | `/runs/wait` |
 
-## Setup
+In this guide, we’ll show how to trigger a webhook after streaming a run.
 
-First, let's setup our assistant and thread:
+## Setting Up Your Assistant and Thread
+
+Before making API calls, set up your assistant and thread.
 
 === "Python"
+```python
+from langgraph_sdk import get_client
 
-    ```python
-    from langgraph_sdk import get_client
+client = get_client(url=<DEPLOYMENT_URL>)
+assistant_id = "agent"
+thread = await client.threads.create()
+print(thread)
+```
 
-    client = get_client(url=<DEPLOYMENT_URL>)
-    # Using the graph deployed with the name "agent"
-    assistant_id = "agent"
-    # create thread
-    thread = await client.threads.create()
-    print(thread)
-    ```
+=== "JavaScript"
+```js
+import { Client } from "@langchain/langgraph-sdk";
 
-=== "Javascript"
-
-    ```js
-    import { Client } from "@langchain/langgraph-sdk";
-
-    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
-    // Using the graph deployed with the name "agent"
-    const assistantID = "agent";
-    // create thread
-    const thread = await client.threads.create();
-    console.log(thread);
-    ```
+const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
+const assistantID = "agent";
+const thread = await client.threads.create();
+console.log(thread);
+```
 
 === "CURL"
+```bash
+curl --request POST \
+    --url <DEPLOYMENT_URL>/assistants/search \
+    --header 'Content-Type: application/json' \
+    --data '{ "limit": 10, "offset": 0 }' | jq -c 'map(select(.config == null or .config == {})) | .[0]' && \
+curl --request POST \
+    --url <DEPLOYMENT_URL>/threads \
+    --header 'Content-Type: application/json' \
+    --data '{}'
+```
 
-    ```bash
-    curl --request POST \
-        --url <DEPLOYMENT_URL>/assistants/search \
-        --header 'Content-Type: application/json' \
-        --data '{
-            "limit": 10,
-            "offset": 0
-        }' | jq -c 'map(select(.config == null or .config == {})) | .[0]' && \
-    curl --request POST \
-        --url <DEPLOYMENT_URL>/threads \
-        --header 'Content-Type: application/json' \
-        --data '{}'
-    ```
+### Example Response
+```json
+{
+    "thread_id": "9dde5490-2b67-47c8-aa14-4bfec88af217",
+    "created_at": "2024-08-30T23:07:38.242730+00:00",
+    "updated_at": "2024-08-30T23:07:38.242730+00:00",
+    "metadata": {},
+    "status": "idle",
+    "config": {},
+    "values": null
+}
+```
 
-Output:
+## Using a Webhook with a Graph Run
 
-    {
-        'thread_id': '9dde5490-2b67-47c8-aa14-4bfec88af217', 
-        'created_at': '2024-08-30T23:07:38.242730+00:00', 
-        'updated_at': '2024-08-30T23:07:38.242730+00:00', 
-        'metadata': {}, 
-        'status': 'idle', 
-        'config': {}, 
-        'values': None
-    }
+To use a webhook, specify the `webhook` parameter in your API request. When the run completes, LangGraph Cloud sends a `POST` request to the specified webhook URL.
 
-## Use graph with a webhook
-
-To invoke a run with a webhook, we specify the `webhook` parameter with the desired endpoint when creating a run. Webhook requests are triggered by the end of a run.
-
-For example, if we can receive requests at `https://my-server.app/my-webhook-endpoint`, we can pass this to `stream`:
+For example, if your server listens for webhook events at `https://my-server.app/my-webhook-endpoint`, include this in your request:
 
 === "Python"
+```python
+input = { "messages": [{ "role": "user", "content": "Hello!" }] }
 
-    ```python
-    # create input
-    input = { "messages": [{ "role": "user", "content": "Hello!" }] }
+async for chunk in client.runs.stream(
+    thread_id=thread["thread_id"],
+    assistant_id=assistant_id,
+    input=input,
+    stream_mode="events",
+    webhook="https://my-server.app/my-webhook-endpoint"
+):
+    pass
+```
 
-    async for chunk in client.runs.stream(
-        thread_id=thread["thread_id"],
-        assistant_id=assistant_id,
-        input=input,
-        stream_mode="events",
-        webhook="https://my-server.app/my-webhook-endpoint"
-    ):
-        # Do something with the stream output
-        pass
-    ```
+=== "JavaScript"
+```js
+const input = { messages: [{ role: "human", content: "Hello!" }] };
 
-=== "Javascript"
+const streamResponse = client.runs.stream(
+  thread["thread_id"],
+  assistantID,
+  {
+    input: input,
+    webhook: "https://my-server.app/my-webhook-endpoint"
+  }
+);
 
-    ```js
-    // create input
-    const input = { messages: [{ role: "human", content: "Hello!" }] };
-
-    // stream events
-    const streamResponse = client.runs.stream(
-      thread["thread_id"],
-      assistantID,
-      {
-        input: input,
-        webhook: "https://my-server.app/my-webhook-endpoint"
-      }
-    );
-    for await (const chunk of streamResponse) {
-      // Do something with the stream output
-    }
-    ```
+for await (const chunk of streamResponse) {
+  // Handle stream output
+}
+```
 
 === "CURL"
-
-    ```bash
-    curl --request POST \
-        --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/stream \
-        --header 'Content-Type: application/json' \
-        --data '{
-            "assistant_id": <ASSISTANT_ID>,
-            "input" : {"messages":[{"role": "user", "content": "Hello!"}]},
-            "webhook": "https://my-server.app/my-webhook-endpoint"
-        }'
-    ```
-
-The schema for the payload sent to `my-webhook-endpoint` is that of a [run](../../concepts/langgraph_server.md/#runs). See [API Reference](https://langchain-ai.github.io/langgraph/cloud/reference/api/api_ref.html#model/run) for more detail. Note that the run input, configuration, etc. are included in the `kwargs` field.
-
-### Signing webhook requests
-
-To sign the webhook requests, we can specify a token parameter in the webhook URL, e.g.,
-```
-https://my-server.app/my-webhook-endpoint?token=...
+```bash
+curl --request POST \
+    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/stream \
+    --header 'Content-Type: application/json' \
+    --data '{
+        "assistant_id": <ASSISTANT_ID>,
+        "input": {"messages": [{"role": "user", "content": "Hello!"}]},
+        "webhook": "https://my-server.app/my-webhook-endpoint"
+    }'
 ```
 
-The server should then extract the token from the request's parameters and validate it before processing the payload.
+## Webhook Payload
+
+LangGraph Cloud sends webhook notifications in the format of a [Run](../../concepts/langgraph_server.md/#runs). See the [API Reference](https://langchain-ai.github.io/langgraph/cloud/reference/api/api_ref.html#model/run) for details. The request payload includes run input, configuration, and other metadata in the `kwargs` field.
+
+## Securing Webhooks
+
+To ensure only authorized requests hit your webhook endpoint, consider adding a security token as a query parameter:
+
+```
+https://my-server.app/my-webhook-endpoint?token=YOUR_SECRET_TOKEN
+```
+
+Your server should extract and validate this token before processing requests.
+
+## Testing Webhooks
+
+You can test your webhook using online services like:
+
+- **[Beeceptor](https://beeceptor.com/)** – Quickly create a test endpoint and inspect incoming webhook payloads.
+- **[Webhook.site](https://webhook.site/)** – View, debug, and log incoming webhook requests in real time.
+
+These tools help you verify that LangGraph Cloud is correctly triggering and sending webhooks to your service.
+
+---
+
+By following these steps, you can integrate webhooks into your LangGraph Cloud workflow, automating actions based on completed runs.

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

@@ -22,7 +22,7 @@
       "description": "A run is an invocation of a graph / assistant, with no state or memory persistence."
     },
     {
-      "name": "Crons (Enterprise-only)",
+      "name": "Crons (Plus tier)",
       "description": "A cron is a periodic run that recurs on a given schedule. The repeats can be isolated, or share state in a thread"
     },
     {
@@ -805,6 +805,58 @@
         }
       }
     },
+    "/threads/state/bulk": {
+      "post": {
+        "tags": [
+          "Threads"
+        ],
+        "summary": "Bulk Update Thread State",
+        "description": "Create a new thread from a batch of state updates.",
+        "operationId": "bulk_update_thread_state_post",
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ThreadStateBulkUpdate"
+              }
+            }
+          },
+          "required": true
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Thread"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "Conflict",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            }
+          },
+          "422": {
+            "description": "Validation Error",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
     "/threads/{thread_id}/state": {
       "get": {
         "tags": [
@@ -1342,6 +1394,21 @@
             },
             "name": "offset",
             "in": "query"
+          },
+          {
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "pending",
+                "error",
+                "success",
+                "timeout",
+                "interrupted"
+              ]
+            },
+            "name": "status",
+            "in": "query"
           }
         ],
         "responses": {
@@ -1458,7 +1525,7 @@
     "/threads/{thread_id}/runs/crons": {
       "post": {
         "tags": [
-          "Crons (Enterprise-only)"
+          "Crons (Plus tier)"
         ],
         "summary": "Create Thread Cron",
         "description": "Create a cron to schedule runs on a thread.",
@@ -1836,6 +1903,17 @@
             },
             "name": "run_id",
             "in": "path"
+          },
+          {
+            "required": false,
+            "schema": {
+              "type": "boolean",
+              "title": "Cancel on Disconnect",
+              "description": "If true, the run will be cancelled if the client disconnects.",
+              "default": false
+            },
+            "name": "cancel_on_disconnect",
+            "in": "query"
           }
         ],
         "responses": {
@@ -2032,7 +2110,7 @@
     "/runs/crons": {
       "post": {
         "tags": [
-          "Crons (Enterprise-only)"
+          "Crons (Plus tier)"
         ],
         "summary": "Create Cron",
         "description": "Create a cron to schedule runs on new threads.",
@@ -2084,7 +2162,7 @@
     "/runs/crons/search": {
       "post": {
         "tags": [
-          "Crons (Enterprise-only)"
+          "Crons (Plus tier)"
         ],
         "summary": "Search Crons",
         "description": "Search all active crons",
@@ -2190,6 +2268,68 @@
         }
       }
     },
+    "/runs/cancel": {
+      "post": {
+        "tags": [
+          "Thread Runs"
+        ],
+        "summary": "Cancel Runs",
+        "description": "Cancel one or more runs. Can cancel runs by thread ID and run IDs, or by status filter.",
+        "operationId": "cancel_runs_post",
+        "parameters": [
+          {
+            "description": "Action to take when cancelling the run. Possible values are `interrupt` or `rollback`. `interrupt` will simply cancel the run. `rollback` will cancel the run and delete the run and associated checkpoints afterwards.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "interrupt",
+                "rollback"
+              ],
+              "title": "Action",
+              "default": "interrupt"
+            },
+            "name": "action",
+            "in": "query"
+          }
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/RunsCancel"
+              }
+            }
+          },
+          "required": true
+        },
+        "responses": {
+          "204": {
+            "description": "Success - Runs cancelled"
+          },
+          "404": {
+            "description": "Not Found",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            }
+          },
+          "422": {
+            "description": "Validation Error",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
     "/runs/wait": {
       "post": {
         "tags": [
@@ -2373,7 +2513,7 @@
     "/runs/crons/{cron_id}": {
       "delete": {
         "tags": [
-          "Crons (Enterprise-only)"
+          "Crons (Plus tier)"
         ],
         "summary": "Delete Cron",
         "description": "Delete a cron by ID.",
@@ -2936,7 +3076,7 @@
             "type": "string",
             "maxLength": 65536,
             "minLength": 1,
-            "format": "uri",
+            "format": "uri-reference",
             "title": "Webhook",
             "description": "Webhook to call after LangGraph API call is done."
           },
@@ -3216,7 +3356,11 @@
         "description": "The command to run.",
         "properties": {
           "update": {
-            "type": "object",
+            "type": [
+              "object",
+              "array",
+              "null"
+            ],
             "title": "Update",
             "description": "An update to the state."
           },
@@ -3226,12 +3370,13 @@
               "array",
               "number",
               "string",
+              "boolean",
               "null"
             ],
             "title": "Resume",
             "description": "A value to pass to an interrupted node."
           },
-          "send": {
+          "goto": {
             "anyOf": [
               {
                 "$ref": "#/components/schemas/Send"
@@ -3242,10 +3387,21 @@
                   "$ref": "#/components/schemas/Send"
                 }
               },
+              {
+                "type": "string"
+              },
+              {
+                "type": "array",
+                "items": {
+                  "type": "string"
+                }
+              },
               {
                 "type": "null"
               }
-            ]
+            ],
+            "title": "Goto",
+            "description": "Name of the node(s) to navigate to next or node(s) to be executed with a provided input."
           }
         }
       },
@@ -3276,6 +3432,18 @@
               {
                 "type": "object"
               },
+              {
+                "type": "array"
+              },
+              {
+                "type": "string"
+              },
+              {
+                "type": "number"
+              },
+              {
+                "type": "boolean"
+              },
               {
                 "type": "null"
               }
@@ -3326,7 +3494,7 @@
             "type": "string",
             "maxLength": 65536,
             "minLength": 1,
-            "format": "uri",
+            "format": "uri-reference",
             "title": "Webhook",
             "description": "Webhook to call after LangGraph API call is done."
           },
@@ -3491,6 +3659,18 @@
               {
                 "type": "object"
               },
+              {
+                "type": "array"
+              },
+              {
+                "type": "string"
+              },
+              {
+                "type": "number"
+              },
+              {
+                "type": "boolean"
+              },
               {
                 "type": "null"
               }
@@ -3541,7 +3721,7 @@
             "type": "string",
             "maxLength": 65536,
             "minLength": 1,
-            "format": "uri",
+            "format": "uri-reference",
             "title": "Webhook",
             "description": "Webhook to call after LangGraph API call is done."
           },
@@ -3840,6 +4020,36 @@
             "title": "If Exists",
             "description": "How to handle duplicate creation. Must be either 'raise' (raise error if duplicate), or 'do_nothing' (return existing thread).",
             "default": "raise"
+          },
+          "ttl": {
+            "type": "object",
+            "title": "TTL",
+            "description": "The time-to-live for the thread.",
+            "properties": {
+              "strategy": {
+                "type": "string",
+                "enum": ["delete"],
+                "description": "The TTL strategy. 'delete' removes the entire thread.",
+                "default": "delete"
+              },
+              "ttl": {
+                "type": "number",
+                "description": "The time-to-live in minutes from now until thread should be swept."
+              }
+            }
+          },
+          "supersteps": {
+            "type": "array",
+            "items": {
+              "type": "object",
+              "properties": {
+                "updates": {
+                  "type": "array",
+                  "items": { "$ref": "#/components/schemas/ThreadSuperstepUpdate" }
+                }
+              },
+              "required": ["updates"]
+            }
           }
         },
         "type": "object",
@@ -4028,6 +4238,43 @@
         "title": "ThreadStateUpdate",
         "description": "Payload for updating the state of a thread."
       },
+      "ThreadSuperstepUpdate": {
+        "properties": {
+          "values": {
+            "anyOf": [
+              {
+                "type": "array",
+                "items": {
+                  "type": "object"
+                }
+              },
+              {
+                "type": "object"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "command": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Command"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The command associated with the update."
+          },
+          "as_node": {
+            "type": "string",
+            "description": "Update the state as if this node had just executed."
+          }
+        },
+        "required": ["as_node"],
+        "type": "object"
+      },
       "ThreadStateUpdateResponse": {
         "properties": {
           "checkpoint": {
@@ -4230,6 +4477,42 @@
         },
         "description": "Represents a single document or data entry in the graph's Store. Items are used to store cross-thread memories."
       },
+      "RunsCancel": {
+        "type": "object",
+        "title": "RunsCancel",
+        "description": "Payload for cancelling runs.",
+        "properties": {
+          "status": {
+            "type": "string",
+            "enum": ["pending", "running", "all"],
+            "title": "Status",
+            "description": "Filter runs by status to cancel. Must be one of 'pending', 'running', or 'all'."
+          },
+          "thread_id": {
+            "type": "string",
+            "format": "uuid",
+            "title": "Thread Id",
+            "description": "The ID of the thread containing runs to cancel."
+          },
+          "run_ids": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "format": "uuid"
+            },
+            "title": "Run Ids",
+            "description": "List of run IDs to cancel."
+          }
+        },
+        "oneOf": [
+          {
+            "required": ["status"]
+          },
+          {
+            "required": ["thread_id", "run_ids"]
+          }
+        ]
+      },
       "SearchItemsResponse": {
         "type": "object",
         "required": [

docs/docs/cloud/reference/cli.md

@@ -1,6 +1,6 @@
 # LangGraph CLI
 
-The LangGraph command line interface includes commands to build and run a LangGraph Cloud API server locally in [Docker](https://www.docker.com/). For development and testing, you can use the CLI to deploy a local API server as an alternative to the [Studio desktop app](../../concepts/langgraph_studio.md).
+The LangGraph command line interface includes commands to build and run a LangGraph Cloud API server locally in [Docker](https://www.docker.com/). For development and testing, you can use the CLI to deploy a local API server.
 
 ## Installation
 
@@ -10,9 +10,6 @@ The LangGraph command line interface includes commands to build and run a LangGr
     === "Python"
         ```bash
         pip install langgraph-cli
-
-        # Install via Homebrew
-        brew install langgraph-cli
         ```
 
     === "JS"
@@ -29,7 +26,7 @@ The LangGraph command line interface includes commands to build and run a LangGr
 
 ## Configuration File {#configuration-file}
 
-The LangGraph CLI requires a JSON configuration file with the following keys:
+The LangGraph CLI requires a JSON configuration file that follows this [schema](https://raw.githubusercontent.com/langchain-ai/langgraph/refs/heads/main/libs/cli/schemas/schema.json). It contains the following properties:
 
 <div class="admonition tip">
     <p class="admonition-title">Note</p>
@@ -42,15 +39,17 @@ The LangGraph CLI requires a JSON configuration file with the following keys:
 
     | Key                                                          | Description                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
     | ------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-    | <span style="white-space: nowrap;">`dependencies`</span>     | **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.                                                                                                                                                                                                                                                                                     |
+    | <span style="white-space: nowrap;">`dependencies`</span>     | **Required**. Array of dependencies for LangGraph Cloud API server. Dependencies can be one of the following: <ul><li>A single period (`"."`), which will look for local Python packages.</li><li>The directory path where `pyproject.toml`, `setup.py` or `requirements.txt` is located.</br></br>For example, if `requirements.txt` is located in the root of the project directory, specify `"./"`. If it's located in a subdirectory called `local_package`, specify `"./local_package"`. Do not specify the string `"requirements.txt"` itself.</li><li>A Python package name.</li></ul> |
     | <span style="white-space: nowrap;">`graphs`</span>           | **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>                                    |
     | <span style="white-space: nowrap;">`auth`</span>             | _(Added in v0.0.11)_ Auth configuration containing the path to your authentication handler. Example: `./your_package/auth.py:auth`, where `auth` is an instance of `langgraph_sdk.Auth`. See [authentication guide](../../concepts/auth.md) for details.                                                                                                                                                                                                                                                                                                                        |
     | <span style="white-space: nowrap;">`env`</span>              | Path to `.env` file or a mapping from environment variable to its value.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
-    | <span style="white-space: nowrap;">`store`</span>            | Configuration for adding semantic search to the BaseStore. Contains the following fields: <ul><li>`index`: Configuration for semantic search indexing with fields:<ul><li>`embed`: Embedding provider (e.g., "openai:text-embedding-3-small") or path to custom embedding function</li><li>`dims`: Dimension size of the embedding model. Used to initialize the vector table.</li><li>`fields` (optional): List of fields to index. Defaults to `["$"]`, which means to index entire documents. Can be specific fields like `["text", "summary", "some.value"]`</li></ul></li></ul> |
-    | <span style="white-space: nowrap;">`python_version`</span>   | `3.11` or `3.12`. Defaults to `3.11`.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
+    | <span style="white-space: nowrap;">`store`</span>            | Configuration for adding semantic search and/or time-to-live (TTL) to the BaseStore. Contains the following fields: <ul><li>`index` (optional): Configuration for semantic search indexing with fields `embed`, `dims`, and optional `fields`.</li><li>`ttl` (optional): Configuration for item expiration. An object with optional fields: `refresh_on_read` (boolean, defaults to `true`), `default_ttl` (float, lifespan in **minutes**, defaults to no expiration), and `sweep_interval_minutes` (integer, how often to check for expired items, defaults to no sweeping).</li></ul> |
+    | <span style="white-space: nowrap;">`python_version`</span>   | `3.11`, `3.12`, or `3.13`. Defaults to `3.11`.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
     | <span style="white-space: nowrap;">`node_version`</span>     | Specify `node_version: 20` to use LangGraph.js.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
     | <span style="white-space: nowrap;">`pip_config_file`</span>  | Path to `pip` config file.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
     | <span style="white-space: nowrap;">`dockerfile_lines`</span> | Array of additional lines to add to Dockerfile following the import from parent image.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+    | <span style="white-space: nowrap;">`checkpointer`</span>   | Configuration for the checkpointer. Contains a `ttl` field which is an object with the following keys: <ul><li>`strategy`: How to handle expired checkpoints (e.g., `"delete"`).</li><li>`sweep_interval_minutes`: How often to check for expired checkpoints (integer).</li><li>`default_ttl`: Default time-to-live for checkpoints in **minutes** (integer). Defines how long checkpoints are kept before the specified strategy is applied.</li></ul> |
+    | <span style="white-space: nowrap;">`http`</span>            | HTTP server configuration with the following fields: <ul><li>`app`: Path to custom Starlette/FastAPI app (e.g., `"./src/agent/webapp.py:app"`). See [custom routes guide](../../how-tos/http/custom_routes.md).</li><li>`disable_assistants`: Disable `/assistants` routes</li><li>`disable_threads`: Disable `/threads` routes</li><li>`disable_runs`: Disable `/runs` routes</li><li>`disable_store`: Disable `/store` routes</li><li>`disable_meta`: Disable `/ok`, `/info`, `/metrics`, and `/docs` routes</li><li>`cors`: CORS configuration with fields for `allow_origins`, `allow_methods`, `allow_headers`, etc.</li></ul> |
 
 === "JS"
 
@@ -58,9 +57,10 @@ The LangGraph CLI requires a JSON configuration file with the following keys:
     | ------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
     | <span style="white-space: nowrap;">`graphs`</span>           | **Required**. Mapping from graph ID to path where the compiled graph or a function that makes a graph is defined. Example: <ul><li>`./src/graph.ts:variable`, where `variable` is an instance of `CompiledStateGraph`</li><li>`./src/graph.ts:makeGraph`, where `makeGraph` is a function that takes a config dictionary (`LangGraphRunnableConfig`) and creates an instance of `StateGraph` / `CompiledStateGraph`.</li></ul>                                    |
     | <span style="white-space: nowrap;">`env`</span>              | Path to `.env` file or a mapping from environment variable to its value.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
-    | <span style="white-space: nowrap;">`store`</span>            | Configuration for adding semantic search to the BaseStore. Contains the following fields: <ul><li>`index`: Configuration for semantic search indexing with fields:<ul><li>`embed`: Embedding provider (e.g., "openai:text-embedding-3-small") or path to custom embedding function</li><li>`dims`: Dimension size of the embedding model. Used to initialize the vector table.</li><li>`fields` (optional): List of fields to index. Defaults to `["$"]`, which means to index entire documents. Can be specific fields like `["text", "summary", "some.value"]`</li></ul></li></ul> |
+    | <span style="white-space: nowrap;">`store`</span>            | Configuration for adding semantic search and/or time-to-live (TTL) to the BaseStore. Contains the following fields: <ul><li>`index` (optional): Configuration for semantic search indexing with fields `embed`, `dims`, and optional `fields`.</li><li>`ttl` (optional): Configuration for item expiration. An object with optional fields: `refresh_on_read` (boolean, defaults to `true`), `default_ttl` (float, lifespan in **minutes**, defaults to no expiration), and `sweep_interval_minutes` (integer, how often to check for expired items, defaults to no sweeping).</li></ul> |
     | <span style="white-space: nowrap;">`node_version`</span>     | Specify `node_version: 20` to use LangGraph.js.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
     | <span style="white-space: nowrap;">`dockerfile_lines`</span> | Array of additional lines to add to Dockerfile following the import from parent image.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+    | <span style="white-space: nowrap;">`checkpointer`</span>   | Configuration for the checkpointer. Contains a `ttl` field which is an object with the following keys: <ul><li>`strategy`: How to handle expired checkpoints (e.g., `"delete"`).</li><li>`sweep_interval_minutes`: How often to check for expired checkpoints (integer).</li><li>`default_ttl`: Default time-to-live for checkpoints in **minutes** (integer). Defines how long checkpoints are kept before the specified strategy is applied.</li></ul> |
 
 ### Examples
 
@@ -81,7 +81,7 @@ The LangGraph CLI requires a JSON configuration file with the following keys:
 
     All deployments come with a DB-backed BaseStore. Adding an "index" configuration to your `langgraph.json` will enable [semantic search](../deployment/semantic_search.md) within the BaseStore of your deployment.
 
-    The `fields` configuration determines which parts of your documents to embed:
+    The `index.fields` configuration determines which parts of your documents to embed:
 
     - If omitted or set to `["$"]`, the entire document will be embedded
     - To embed specific fields, use JSON path notation: `["metadata.title", "content.text"]`
@@ -170,6 +170,62 @@ The LangGraph CLI requires a JSON configuration file with the following keys:
 
     See the [authentication conceptual guide](../../concepts/auth.md) for details, and the [setting up custom authentication](../../tutorials/auth/getting_started.md) guide for a practical walk through of the process.
 
+    #### Configuring Store Item Time-to-Live (TTL)
+
+    You can configure default data expiration for items/memories in the BaseStore using the `store.ttl` key. This determines how long items are retained after they are last accessed (with reads potentially refreshing the timer based on `refresh_on_read`). Note that these defaults can be overwritten on a per-call basis by modifying the corresponding arguments in `get`, `search`, etc.
+    
+    The `ttl` configuration is an object containing optional fields:
+
+    - `refresh_on_read`: If `true` (the default), accessing an item via `get` or `search` resets its expiration timer. Set to `false` to only refresh TTL on writes (`put`).
+    - `default_ttl`: The default lifespan of an item in **minutes**. If not set, items do not expire by default.
+    - `sweep_interval_minutes`: How frequently (in minutes) the system should run a background process to delete expired items. If not set, sweeping does not occur automatically.
+
+    Here is an example enabling a 7-day TTL (10080 minutes), refreshing on reads, and sweeping every hour:
+
+    ```json
+    {
+      "dependencies": ["."],
+      "graphs": {
+        "memory_agent": "./agent/graph.py:graph"
+      },
+      "store": {
+        "ttl": {
+          "refresh_on_read": true,
+          "sweep_interval_minutes": 60,
+          "default_ttl": 10080 
+        }
+      }
+    }
+    ```
+
+    #### Configuring Checkpoint Time-to-Live (TTL)
+
+    You can configure the time-to-live (TTL) for checkpoints using the `checkpointer` key. This determines how long checkpoint data is retained before being automatically handled according to the specified strategy (e.g., deletion). The `ttl` configuration is an object containing:
+
+    - `strategy`: The action to take on expired checkpoints (currently `"delete"` is the only accepted option).
+    - `sweep_interval_minutes`: How frequently (in minutes) the system checks for expired checkpoints.
+    - `default_ttl`: The default lifespan of a checkpoint in **minutes**.
+
+    Here's an example setting a default TTL of 30 days (43200 minutes):
+
+    ```json
+    {
+      "dependencies": ["."],
+      "graphs": {
+        "chat": "./chat/graph.py:graph"
+      },
+      "checkpointer": {
+        "ttl": {
+          "strategy": "delete",
+          "sweep_interval_minutes": 10,
+          "default_ttl": 43200
+        }
+      }
+    }
+    ```
+
+    In this example, checkpoints older than 30 days will be deleted, and the check runs every 10 minutes.
+
 
 === "JS"
     
@@ -239,6 +295,11 @@ The LangGraph CLI requires a JSON configuration file with the following keys:
     | `--no-reload`                 |                  | Disable auto-reload                                                                 |
     | `--n-jobs-per-worker INTEGER` |                  | Number of jobs per worker. Default is 10                                            |
     | `--debug-port INTEGER`        |                  | Port for debugger to listen on                                                      |
+    | `--wait-for-client`           | `False`          | Wait for a debugger client to connect to the debug port before starting the server   |
+    | `--no-browser`                |                  | Skip automatically opening the browser when the server starts                       |
+    | `--studio-url TEXT`           |                  | URL of the LangGraph Studio instance to connect to. Defaults to https://smith.langchain.com |
+    | `--allow-blocking`            | `False`          | Do not raise errors for synchronous I/O blocking operations in your code (added in `0.2.6`)           |
+    | `--tunnel`                    | `False`          | Expose the local server via a public tunnel (Cloudflare) for remote frontend access. This avoids issues with browsers like Safari or networks blocking localhost connections        |
     | `--help`                      |                  | Display command documentation                                                       |
 
 
@@ -262,6 +323,11 @@ The LangGraph CLI requires a JSON configuration file with the following keys:
     | `--no-reload`                 |                  | Disable auto-reload                                                                 |
     | `--n-jobs-per-worker INTEGER` |                  | Number of jobs per worker. Default is 10                                            |
     | `--debug-port INTEGER`        |                  | Port for debugger to listen on                                                      |
+    | `--wait-for-client`           | `False`          | Wait for a debugger client to connect to the debug port before starting the server   |
+    | `--no-browser`                |                  | Skip automatically opening the browser when the server starts                       |
+    | `--studio-url TEXT`           |                  | URL of the LangGraph Studio instance to connect to. Defaults to https://smith.langchain.com |
+    | `--allow-blocking`            | `False`          | Do not raise errors for synchronous I/O blocking operations in your code            |
+    | `--tunnel`                    | `False`          | Expose the local server via a public tunnel (Cloudflare) for remote frontend access. This avoids issues with browsers or networks blocking localhost connections        |
     | `--help`                      |                  | Display command documentation                                                       |
 
 ### `build`

docs/docs/cloud/reference/env_var.md

@@ -1,6 +1,28 @@
 # Environment Variables
 
-The LangGraph Cloud Server supports specific environment variables for configuring a deployment.
+The LangGraph Server supports specific environment variables for configuring a deployment.
+
+## `BG_JOB_ISOLATED_LOOPS`
+
+Set `BG_JOB_ISOLATED_LOOPS` to `True` to execute background runs in an isolated event loop separate from the serving API event loop.
+
+This environment variable should be set to `True` if the implementation of a graph/node contains synchronous code. In this situation, the synchronous code will block the serving API event loop, which may cause the API to be unavailable. A symptom of an unavailable API is continuous application restarts due to failing health checks.
+
+Defaults to `False`.
+
+## `BG_JOB_TIMEOUT_SECS`
+
+The timeout of a background run can be increased. However, the infrastructure for a Cloud SaaS deployment enforces a 1 hour timeout limit for API requests. This means the connection between client and server will timeout after 1 hour. This is not configurable.
+
+A background run can execute for longer than 1 hour, but a client must reconnect to the server (e.g. join stream via `POST /threads/{thread_id}/runs/{run_id}/stream`) to retrieve output from the run if the run is taking longer than 1 hour.
+
+Defaults to `3600`.
+
+## `DD_API_KEY`
+
+Specify `DD_API_KEY` (your [Datadog API Key](https://docs.datadoghq.com/account_management/api-app-keys/)) to automatically enable Datadog tracing for the deployment. Specify other [`DD_*` environment variables](https://ddtrace.readthedocs.io/en/stable/configuration.html) to configure the tracing instrumentation.
+
+If `DD_API_KEY` is specified, the application process is wrapped in the [`ddtrace-run` command](https://ddtrace.readthedocs.io/en/stable/installation_quickstart.html). Other `DD_*` environment variables (e.g. `DD_SITE`, `DD_ENV`, `DD_SERVICE`, `DD_TRACE_ENABLED`) are typically needed to properly configure the tracing instrumentation. See [`DD_*` environment variables](https://ddtrace.readthedocs.io/en/stable/configuration.html) for more details.
 
 ## `LANGCHAIN_TRACING_SAMPLING_RATE`
 
@@ -10,7 +32,7 @@ See <a href="https://docs.smith.langchain.com/how_to_guides/tracing/sample_trace
 
 ## `LANGGRAPH_AUTH_TYPE`
 
-Type of authentication for the LangGraph Cloud Server deployment. Valid values: `langsmith`, `noop`.
+Type of authentication for the LangGraph Server 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`.
 
@@ -22,15 +44,35 @@ Set this environment variable to have a BYOC deployment send traces to a self-ho
 
 `SELF_HOSTED_LANGSMITH_HOSTNAME` is the hostname of the self-hosted LangSmith instance. It must be accessible to the BYOC deployment. `LANGSMITH_API_KEY` is a LangSmith API generated from the self-hosted LangSmith instance.
 
+## `LANGSMITH_TRACING`
+
+!!! info "Only for Self-Hosted Data Plane, Self-Hosted Control Plane, and Standalone Container"
+    Disabling LangSmith tracing is only available for [Self-Hosted Data Plane](../../concepts/langgraph_self_hosted_data_plane.md), [Self-Hosted Control Plane](../../concepts/langgraph_self_hosted_control_plane.md), and [Standalone Container](../../concepts/langgraph_standalone_container.md) deployments.
+
+Set `LANGSMITH_TRACING` to `false` to disable tracing to LangSmith.
+
+## `LOG_LEVEL`
+
+Configure [log level](https://docs.python.org/3/library/logging.html#logging-levels). Defaults to `INFO`.
+
+## `LOG_JSON`
+
+Set `LOG_JSON` to `true` to render all log messages as JSON objects using the configured `JSONRenderer`. This produces structured logs that can be easily parsed or ingested by log management systems. Defaults to `false`.
+
+## `LOG_COLOR`
+
+This is mainly relevant in the context of using the dev server via the `langgraph dev` command. Set `LOG_COLOR` to `true` to enable ANSI-colored console output when using the default console renderer. Disabling color output by setting this variable to `false` produces monochrome logs. Defaults to `true`.
+
 ## `N_JOBS_PER_WORKER`
 
-Number of jobs per worker for the LangGraph Cloud task queue. Defaults to `10`.
+Number of jobs per worker for the LangGraph Server task queue. Defaults to `10`.
 
 ## `POSTGRES_URI_CUSTOM`
 
-For [Bring Your Own Cloud (BYOC)](../../concepts/bring_your_own_cloud.md) deployments only.
+!!! info "Only for Self-Hosted Data Plane and Self-Hosted Control Plane"
+    Custom Postgres instances are only available for [Self-Hosted Data Plane](../../concepts/langgraph_self_hosted_data_plane.md) and [Self-Hosted Control Plane](../../concepts/langgraph_self_hosted_control_plane.md) deployments.
 
-Specify `POSTGRES_URI_CUSTOM` to use an externally managed Postgres instance. The value of `POSTGRES_URI_CUSTOM` must be a valid [Postgres connection URI](https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNSTRING-URIS).
+Specify `POSTGRES_URI_CUSTOM` to use a custom Postgres instance. The value of `POSTGRES_URI_CUSTOM` must be a valid [Postgres connection URI](https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNSTRING-URIS).
 
 Postgres:
 
@@ -47,5 +89,11 @@ Control Plane Functionality:
 
 Database Connectivity:
 
-- The externally managed Postgres instance must be accessible by the LangGraph Server service in the ECS cluster. The BYOC user is responsible for ensuring connectivity.
-- For example, if an AWS RDS Postgres instance is provisioned, it can be provisioned in the same VPC (`langgraph-cloud-vpc`) as the ECS cluster with the `langgraph-cloud-service-sg` security group to ensure connectivity.
+- The custom Postgres instance must be accessible by the LangGraph Server. The user is responsible for ensuring connectivity.
+
+## `REDIS_URI_CUSTOM`
+
+!!! info "Only for Self-Hosted Data Plane and Self-Hosted Control Plane"
+    Custom Redis instances are only available for [Self-Hosted Data Plane](../../concepts/langgraph_self_hosted_data_plane.md) and [Self-Hosted Control Plane](../../concepts/langgraph_self_hosted_control_plane.md) deployments.
+
+Specify `REDIS_URI_CUSTOM` to use a custom Redis instance. The value of `REDIS_URI_CUSTOM` must be a valid [Redis connection URI](https://redis-py.readthedocs.io/en/stable/connections.html#redis.Redis.from_url).

docs/docs/concepts/agentic_concepts.md

@@ -14,7 +14,7 @@ As a result, there are many different types of [agent architectures](https://blo
 
 ## Router
 
-A router allows an LLM to select a single step from a specified set of options. This is an agent architecture that exhibits a relatively limited level of control because the LLM usually focuses on making a single decision and produces a specific output from limited set of pre-defined options. Routers typically employ a few different concepts to achieve this.
+A router allows an LLM to select a single step from a specified set of options. This is an agent architecture that exhibits a relatively limited level of control because the LLM usually focuses on making a single decision and produces a specific output from a limited set of pre-defined options. Routers typically employ a few different concepts to achieve this.
 
 ### Structured Output
 

docs/docs/concepts/auth.md

@@ -2,10 +2,6 @@
 
 LangGraph Platform provides a flexible authentication and authorization system that can integrate with most authentication schemes.
 
-!!! note "Python only"
-
-    We currently only support custom authentication and authorization in Python deployments with `langgraph-api>=0.0.11`. Support for LangGraph.JS will be added soon.
-
 ## Core Concepts
 
 ### Authentication vs Authorization
@@ -27,12 +23,19 @@ LangGraph Platform provides different security defaults:
 - Requires valid API key in `x-api-key` header
 - Can be customized with your auth handler
 
+!!! note "Custom auth"
+    Custom auth **is supported** for all plans in LangGraph Cloud.
+
 ### Self-Hosted
 
 - No default authentication
 - Complete flexibility to implement your security model
 - You control all aspects of authentication and authorization
 
+!!! note "Custom auth"
+    Custom auth is supported for **Enterprise** self-hosted plans.
+    Self-hosted lite plans do not support custom auth natively.
+
 ## System Architecture
 
 A typical authentication setup involves three main components:
@@ -139,7 +142,7 @@ The returned user information is available:
 
 After authentication, LangGraph calls your [`@auth.on`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.Auth.on) handlers to control access to specific resources (e.g., threads, assistants, crons). These handlers can:
 
-1. Add metadata to be saved during resource creation by mutating the `value["metadata"]` dictionary directly. See the [supported actions table](##supported-actions) for the list of types the value can take for each action.
+1. Add metadata to be saved during resource creation by mutating the `value["metadata"]` dictionary directly. See the [supported actions table](#supported-actions) for the list of types the value can take for each action.
 2. Filter resources by metadata during search/list or read operations by returning a [filter dictionary](#filter-operations).
 3. Raise an HTTP exception if access is denied.
 
@@ -282,7 +285,7 @@ async def on_assistant_create(
         )
 ```
 
-Notice that we are mixing global and resource-specific handlers in the above example. Since each request is handled by the most specific handler, a request to create a `thread` would match the `on_thread_create` handler but NOT the `reject_unhandled_requests` handler. A request to `update` a thread, however would be handled by the global handler, since we don't have a more specific handler for that resource and action. Requests to create, update, 
+Notice that we are mixing global and resource-specific handlers in the above example. Since each request is handled by the most specific handler, a request to create a `thread` would match the `on_thread_create` handler but NOT the `reject_unhandled_requests` handler. A request to `update` a thread, however would be handled by the global handler, since we don't have a more specific handler for that resource and action.
 
 ### Filter Operations {#filter-operations}
 
@@ -416,6 +419,7 @@ Here are all the supported action handlers:
 | | `@auth.on.crons.search` | Listing cron jobs | [`CronsSearch`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.types.CronsSearch) |
 
 ???+ note "About Runs"
+
     Runs are scoped to their parent thread for access control. This means permissions are typically inherited from the thread, reflecting the conversational nature of the data model. All run operations (reading, listing) except creation are controlled by the thread's handlers.
     There is a specific `create_run` handler for creating new runs because it had more arguments that you can view in the handler.
 

docs/docs/concepts/breakpoints.md

@@ -83,12 +83,12 @@ node at a time or if you want to pause the graph execution at specific nodes.
 
 ### `NodeInterrupt` exception
 
-We recommend that you [**use the `interrupt` function instead**](#the-interrupt-function) of the `NodeInterrupt` exception if you're trying to implement
+We recommend that you [**use the `interrupt` function instead**][langgraph.types.interrupt] of the `NodeInterrupt` exception if you're trying to implement
 [human-in-the-loop](./human_in_the_loop.md) workflows. The `interrupt` function is easier to use and more flexible.
 
 ??? node "`NodeInterrupt` exception"
 
-    The developer can define some *condition* that must be met for a breakpoint to be triggered. This concept of [dynamic breakpoints](./low_level.md#dynamic-breakpoints) is useful when the developer wants to halt the graph under *a particular condition*. This uses a `NodeInterrupt`, which is a special type of exception that can be raised from within a node based upon some condition. As an example, we can define a dynamic breakpoint that triggers when the `input` is longer than 5 characters.
+    The developer can define some *condition* that must be met for a breakpoint to be triggered. This concept of _dynamic breakpoints_ is useful when the developer wants to halt the graph under *a particular condition*. This uses a `NodeInterrupt`, which is a special type of exception that can be raised from within a node based upon some condition. As an example, we can define a dynamic breakpoint that triggers when the `input` is longer than 5 characters.
 
     ```python
     def my_node(state: State) -> State:

docs/docs/concepts/deployment_options.md

@@ -10,90 +10,65 @@
 
 There are 4 main options for deploying with the LangGraph Platform:
 
-1. **[Self-Hosted Lite](#self-hosted-lite)**: Available for all plans.
+1. **<a href="#cloud-saas">Cloud SaaS<sup>(Beta)</sup></a>**: Available for **Plus** and **Enterprise** plans.
 
-2. **[Self-Hosted Enterprise](#self-hosted-enterprise)**: Available for the **Enterprise** plan.
+1. **<a href="#self-hosted-data-plane">Self-Hosted Data Plane<sup>(Beta)</sup></a>**: Available for the **Enterprise** plan.
 
-3. **[Cloud SaaS](#cloud-saas)**: Available for **Plus** and **Enterprise** plans.
+1. **<a href="#self-hosted-control-plane">Self-Hosted Control Plane<sup>(Beta)</sup></a>**: Available for the **Enterprise** plan.
 
-4. **[Bring Your Own Cloud](#bring-your-own-cloud)**: Available only for **Enterprise** plans and **only on AWS**.
+1. **[Standalone Container](#standalone-container)**: Available for all plans.
 
 Please see the [LangGraph Platform Plans](./plans.md) for more information on the different plans.
 
 The guide below will explain the differences between the deployment options.
 
-## Self-Hosted Enterprise
-
-!!! important
-
-    The Self-Hosted Enterprise version is only available for the **Enterprise** plan.
-
-!!! warning "Note"
-
-    The LangGraph Platform Deployments view (within LangSmith SaaS and self-hosted LangSmith) is not available for Self-Hosted Enterprise LangGraph deployments. Self-hosted LangGraph deployments are managed externally from LangSmith (e.g. there is no UI to manage these deployments).
-
-With a Self-Hosted Enterprise deployment, you are responsible for managing the infrastructure, including setting up and maintaining required databases and Redis instances.
-
-You’ll build a Docker image using the [LangGraph CLI](./langgraph_cli.md), which can then be deployed on your own infrastructure.
-
-For more information, please see:
-
-* [Self-Hosted conceptual guide](./self_hosted.md)
-* [Self-Hosted Deployment how-to guide](../how-tos/deploy-self-hosted.md)
-
-## Self-Hosted Lite
-
-!!! important
-
-    The Self-Hosted Lite version is available for all plans.
-
-!!! warning "Note"
-
-    The LangGraph Platform Deployments view (within LangSmith SaaS and self-hosted LangSmith) is not available for Self-Hosted Lite LangGraph deployments. Self-hosted LangGraph deployments are managed externally from LangSmith (e.g. there is no UI to manage these deployments).
-
-The Self-Hosted Lite deployment option is a free (up to 1 million nodes executed per year), limited version of LangGraph Platform that you can run locally or in a self-hosted manner.
-
-With a Self-Hosted Lite deployment, you are responsible for managing the infrastructure, including setting up and maintaining required databases and Redis instances.
-
-You’ll build a Docker image using the [LangGraph CLI](./langgraph_cli.md), which can then be deployed on your own infrastructure.
-
-[Cron jobs](../cloud/how-tos/cron_jobs.md) are not available for Self-Hosted Lite deployments.
-
-For more information, please see:
-
-* [Self-Hosted conceptual guide](./self_hosted.md)
-* [Self-Hosted deployment how-to guide](../how-tos/deploy-self-hosted.md)
-
 ## Cloud SaaS
 
-!!! important
+The [Cloud SaaS](./langgraph_cloud.md) deployment option is a fully managed model for deployment where we manage the [control plane](./langgraph_control_plane.md) and [data plane](./langgraph_data_plane.md) in our cloud. This option provides a simple way to deploy and manage your LangGraph Servers.
 
-    The Cloud SaaS version of LangGraph Platform is only available for **Plus** and **Enterprise** plans.
-
-The [Cloud SaaS](./langgraph_cloud.md) version of LangGraph Platform is hosted as part of [LangSmith](https://smith.langchain.com/).
-
-The Cloud SaaS version of LangGraph Platform provides a simple way to deploy and manage your LangGraph applications.
-
-This deployment option provides access to the LangGraph Platform UI (within LangSmith) and an integration with GitHub, allowing you to deploy code from any of your repositories on GitHub.
+Connect your GitHub repositories to the platform and deploy your LangGraph Servers from the [Control Plane UI](./langgraph_control_plane.md#control-plane-ui). The build process (i.e. CI/CD) is managed internally by the platform.
 
 For more information, please see:
 
 * [Cloud SaaS Conceptual Guide](./langgraph_cloud.md)
 * [How to deploy to Cloud SaaS](../cloud/deployment/cloud.md)
 
+## Self-Hosted Data Plane
 
-## Bring Your Own Cloud
+The [Self-Hosted Data Plane](./langgraph_self_hosted_data_plane.md) deployment option is a "hybrid" model for deployemnt where we manage the [control plane](./langgraph_control_plane.md) in our cloud and you manage the [data plane](./langgraph_data_plane.md) in your cloud. This option provides a way to securely manage your data plane infrastructure, while offloading control plane management to us.
 
-!!! important
+Build a Docker image using the [LangGraph CLI](./langgraph_cli.md) and deploy your LangGraph Server from the [Control Plane UI](./langgraph_control_plane.md#control-plane-ui).
 
-    The Bring Your Own Cloud version of LangGraph Platform is only available for **Enterprise** plans.
+Supported Compute Platforms: [Kubernetes](https://kubernetes.io/), [Amazon ECS](https://aws.amazon.com/ecs/) (coming soon!)
 
+For more information, please see:
 
-This combines the best of both worlds for Cloud and Self-Hosted. Create your deployments through the LangGraph Platform UI (within LangSmith) and we manage the infrastructure so you don't have to. The infrastructure all runs within your cloud. This is currently only available on AWS.
+* [Self-Hosted Data Plane Conceptual Guide](./langgraph_self_hosted_data_plane.md)
+* [How to deploy the Self-Hosted Data Plane](../cloud/deployment/self_hosted_data_plane.md)
 
-For more information please see:
+## Self-Hosted Control Plane
 
-* [Bring Your Own Cloud Conceptual Guide](./bring_your_own_cloud.md)
+The [Self-Hosted Control Plane](./langgraph_self_hosted_control_plane.md) deployment option is a fully self-hosted model for deployment where you manage the [control plane](./langgraph_control_plane.md) and [data plane](./langgraph_data_plane.md) in your cloud. This option give you full control and responsibility of the control plane and data plane infrastructure.
+
+Build a Docker image using the [LangGraph CLI](./langgraph_cli.md) and deploy your LangGraph Server from the [Control Plane UI](./langgraph_control_plane.md#control-plane-ui).
+
+Supported Compute Platforms: [Kubernetes](https://kubernetes.io/)
+
+For more information, please see:
+
+* [Self-Hosted Control Plane Conceptual Guide](./langgraph_self_hosted_control_plane.md)
+* [How to deploy the Self-Hosted Control Plane](../cloud/deployment/self_hosted_control_plane.md)
+
+## Standalone Container
+
+The [Standalone Container](./langgraph_standalone_container.md) deployment option is the least restrictive model for deployment. Deploy standalone instances of a LangGraph Server in your cloud.
+
+Build a Docker image using the [LangGraph CLI](./langgraph_cli.md) and deploy your LangGraph Server using the container deployment tooling of your choice. Images can be deployed to any compute platform.
+
+For more information, please see:
+
+* [Sandalone Container Conceptual Guide](./langgraph_standalone_container.md)
+* [How to deploy a Standalone Container](../cloud/deployment/standalone_container.md)
 
 ## Related
 

docs/docs/concepts/durable_execution.md

@@ -0,0 +1,152 @@
+# Durable Execution
+
+**Durable execution** is a technique in which a process or workflow saves its progress at key points, allowing it to pause and later resume exactly where it left off. This is particularly useful in scenarios that require [human-in-the-loop](./human_in_the_loop.md), where users can inspect, validate, or modify the process before continuing, and in long-running tasks that might encounter interruptions or errors (e.g., calls to an LLM timing out). By preserving completed work, durable execution enables a process to resume without reprocessing previous steps -- even after a significant delay (e.g., a week later). 
+
+LangGraph's built-in [persistence](./persistence.md) layer provides durable execution for workflows, ensuring that the state of each execution step is saved to a durable store. This capability guarantees that if a workflow is interrupted -- whether by a system failure or for [human-in-the-loop](./human_in_the_loop.md) interactions -- it can be resumed from its last recorded state.
+
+!!! tip
+
+    If you are using LangGraph with a checkpointer, you already have durable execution enabled. You can pause and resume workflows at any point, even after interruptions or failures.
+    To make the most of durable execution, ensure that your workflow is designed to be [deterministic](#determinism-and-consistent-replay) and [idempotent](#determinism-and-consistent-replay) and wrap any side effects or non-deterministic operations inside [tasks](./functional_api.md#task). You can use [tasks](./functional_api.md#task) from both the [StateGraph (Graph API)](./low_level.md) and the [Functional API](./functional_api.md).
+
+## Requirements
+
+To leverage durable execution in LangGraph, you need to:
+
+1. Enable [persistence](./persistence.md) in your workflow by specifying a [checkpointer](./persistence.md#checkpointer-libraries) that will save workflow progress.
+2. Specify a [thread identifier](./persistence.md#threads) when executing a workflow. This will track the execution history for a particular instance of the workflow.
+3. Wrap any non-deterministic operations (e.g., random number generation) or operations with side effects (e.g., file writes, API calls) inside [tasks][langgraph.func.task] to ensure that when a workflow is resumed, these operations are not repeated for the particular run, and instead their results are retrieved from the persistence layer. For more information, see [Determinism and Consistent Replay](#determinism-and-consistent-replay).
+
+## Determinism and Consistent Replay
+
+When you resume a workflow run, the code does **NOT** resume from the **same line of code** where execution stopped; instead, it will identify an appropriate [starting point](#starting-points-for-resuming-workflows) from which to pick up where it left off. This means that the workflow will replay all steps from the [starting point](#starting-points-for-resuming-workflows) until it reaches the point where it was stopped.
+
+As a result, when you are writing a workflow for durable execution, you must wrap any non-deterministic operations (e.g., random number generation) and any operations with side effects (e.g., file writes, API calls) inside [tasks](./functional_api.md#task) or [nodes](./low_level.md#nodes).
+
+To ensure that your workflow is deterministic and can be consistently replayed, follow these guidelines:
+
+- **Avoid Repeating Work**:  If a [node](./low_level.md#nodes) contains multiple operations with side effects (e.g., logging, file writes, or network calls), wrap each operation in a separate **task**. This ensures that when the workflow is resumed, the operations are not repeated, and their results are retrieved from the persistence layer.
+- **Encapsulate Non-Deterministic Operations:**  Wrap any code that might yield non-deterministic results (e.g., random number generation) inside **tasks** or **nodes**. This ensures that, upon resumption, the workflow follows the exact recorded sequence of steps with the same outcomes.
+- **Use Idempotent Operations**: When possible ensure that side effects (e.g., API calls, file writes) are idempotent. This means that if an operation is retried after a failure in the workflow, it will have the same effect as the first time it was executed. This is particularly important for operations that result in data writes. In the event that a **task** starts but fails to complete successfully, the workflow's resumption will re-run the **task**, relying on recorded outcomes to maintain consistency. Use idempotency keys or verify existing results to avoid unintended duplication, ensuring a smooth and predictable workflow execution.
+
+For some examples of pitfalls to avoid, see the [Common Pitfalls](./functional_api.md#common-pitfalls) section in the functional API, which shows
+how to structure your code using **tasks** to avoid these issues. The same principles apply to the [StateGraph (Graph API)][langgraph.graph.state.StateGraph].
+
+## Using tasks in nodes
+
+If a [node](./low_level.md#nodes) contains multiple operations, you may find it easier to convert each operation into a **task** rather than refactor the operations into individual nodes.
+
+=== "Original"
+
+    ```python
+    from typing import NotRequired
+    from typing_extensions import TypedDict
+    import uuid
+
+    from langgraph.checkpoint.memory import MemorySaver
+    from langgraph.graph import StateGraph, START, END
+    import requests
+
+    # Define a TypedDict to represent the state
+    class State(TypedDict):
+        url: str
+        result: NotRequired[str]
+
+    def call_api(state: State):
+        """Example node that makes an API request."""
+        # highlight-next-line
+        result = requests.get(state['url']).text[:100]  # Side-effect
+        return {
+            "result": result
+        }
+
+    # Create a StateGraph builder and add a node for the call_api function
+    builder = StateGraph(State)
+    builder.add_node("call_api", call_api)
+
+    # Connect the start and end nodes to the call_api node
+    builder.add_edge(START, "call_api")
+    builder.add_edge("call_api", END)
+
+    # Specify a checkpointer
+    checkpointer = MemorySaver()
+
+    # Compile the graph with the checkpointer
+    graph = builder.compile(checkpointer=checkpointer)
+
+    # Define a config with a thread ID.
+    thread_id = uuid.uuid4()
+    config = {"configurable": {"thread_id": thread_id}}
+
+    # Invoke the graph
+    graph.invoke({"url": "https://www.example.com"}, config)
+    ```
+
+=== "With task"
+
+    ```python
+    from typing import NotRequired
+    from typing_extensions import TypedDict
+    import uuid
+
+    from langgraph.checkpoint.memory import MemorySaver
+    from langgraph.func import task
+    from langgraph.graph import StateGraph, START, END
+    import requests
+
+    # Define a TypedDict to represent the state
+    class State(TypedDict):
+        urls: list[str]
+        result: NotRequired[list[str]]
+
+
+    @task
+    def _make_request(url: str):
+        """Make a request."""
+        # highlight-next-line
+        return requests.get(url).text[:100]
+
+    def call_api(state: State):
+        """Example node that makes an API request."""
+        # highlight-next-line
+        requests = [_make_request(url) for url in state['urls']]
+        results = [request.result() for request in requests]
+        return {
+            "results": results
+        }
+
+    # Create a StateGraph builder and add a node for the call_api function
+    builder = StateGraph(State)
+    builder.add_node("call_api", call_api)
+
+    # Connect the start and end nodes to the call_api node
+    builder.add_edge(START, "call_api")
+    builder.add_edge("call_api", END)
+
+    # Specify a checkpointer
+    checkpointer = MemorySaver()
+
+    # Compile the graph with the checkpointer
+    graph = builder.compile(checkpointer=checkpointer)
+
+    # Define a config with a thread ID.
+    thread_id = uuid.uuid4()
+    config = {"configurable": {"thread_id": thread_id}}
+
+    # Invoke the graph
+    graph.invoke({"urls": ["https://www.example.com"]}, config)
+    ```
+
+## Resuming Workflows
+
+Once you have enabled durable execution in your workflow, you can resume execution for the following scenarios:
+
+- **Pausing and Resuming Workflows:** Use the [interrupt][langgraph.types.interrupt] function to pause a workflow at specific points and the [Command][langgraph.types.Command] primitive to resume it with updated state. See [**Human-in-the-Loop**](./human_in_the_loop.md) for more details.
+- **Recovering from Failures:** Automatically resume workflows from the last successful checkpoint after an exception (e.g., LLM provider outage). This involves executing the workflow with the same thread identifier by providing it with a `None` as the input value (see this [example](./functional_api.md#resuming-after-an-error) with the functional API).
+
+## Starting Points for Resuming Workflows
+
+* If you're using a [StateGraph (Graph API)][langgraph.graph.state.StateGraph], the starting point is the beginning of the [**node**](./low_level.md#nodes) where execution stopped. 
+* If you're making a subgraph call inside a node, the starting point will be the **parent** node that called the subgraph that was halted.
+Inside the subgraph, the starting point will be the specific [**node**](./low_level.md#nodes) where execution stopped.
+* If you're using the Functional API, the starting point is the beginning of the [**entrypoint**](./functional_api.md#entrypoint) where execution stopped.

docs/docs/concepts/faq.md

@@ -36,7 +36,7 @@ LangGraph is a stateful, orchestration framework that brings added control to ag
 | Concurrency Control | Simple threading                                          | Supports double-texting                                                                                |
 | Scheduling          | None                                                      | Cron scheduling                                                                                        |
 | Monitoring          | None                                                      | Integrated with LangSmith for observability                                                            |
-| IDE integration     | LangGraph Studio for Desktop                              | LangGraph Studio for Desktop & Cloud                                                                   |
+| IDE integration     | LangGraph Studio                                          | LangGraph Studio                                                                                       |
 
 ## What are my deployment options for LangGraph Platform?
 
@@ -62,3 +62,9 @@ Yes! You can use LangGraph with any LLMs. The main reason we use LLMs that suppo
 ## 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.
+
+## Can I use LangGraph Studio without logging to LangSmith
+
+Yes! You can use the [development version of LangGraph Server](../tutorials/langgraph-platform/local-server.md) to run the backend locally.
+This will connect to the studio frontend hosted as part of LangSmith.
+If you set an environment variable of `LANGSMITH_TRACING=false` then no traces will be sent to LangSmith.

docs/docs/concepts/functional_api.md

@@ -1,8 +1,5 @@
 # Functional API
 
-!!! warning "Beta"
-    The Functional API is currently in **beta** and is subject to change. Please [report any issues](https://github.com/langchain-ai/langgraph/issues) or feedback to the LangGraph team.
-
 ## Overview
 
 The **Functional API** allows you to add LangGraph's key features -- [persistence](./persistence.md), [memory](./memory.md), [human-in-the-loop](./human_in_the_loop.md), and [streaming](./streaming.md) — to your applications with minimal changes to your existing code.
@@ -26,9 +23,11 @@ This provides a minimal abstraction for building workflows with state management
 Below we demonstrate a simple application that writes an essay and [interrupts](human_in_the_loop.md) to request human review.
 
 ```python
+from langgraph.checkpoint.memory import MemorySaver
 from langgraph.func import entrypoint, task
 from langgraph.types import interrupt
 
+
 @task
 def write_essay(topic: str) -> str:
     """Write an essay about the given topic."""
@@ -832,7 +831,8 @@ from langgraph.checkpoint.memory import MemorySaver
 from langgraph.func import entrypoint, task
 from langgraph.types import StreamWriter
 
-# Global variable to track the number of attempts
+# This variable is just used for demonstration purposes to simulate a network failure.
+# It's not something you will have in your actual code.
 attempts = 0
 
 @task()

docs/docs/concepts/high_level.md

@@ -2,7 +2,7 @@
 
 ## LLM applications
 
-LLMs make it possible to embed intelligence into a new class of applications. There are many patterns for building applications that use LLMs. [Workflows](https://www.anthropic.com/research/building-effective-agents) have scaffolding of predefined code paths around LLM calls. LLMs can direct the control flow through these predefined code paths, which some consider to be an "[agentic system](https://www.anthropic.com/research/building-effective-agents)". In other cases, it's possible to remove this scaffolding, creating autonomous agents that can [plan](https://huyenchip.com/2025/01/07/agents.html), take actions via [tool calls](https://python.langchain.com/docs/concepts/tool_calling/), and directly respond [to the feedback from their own actions](https://research.google/blog/react-synergizing-reasoning-and-acting-in-language-models/) with further actions.
+LLMs make it possible to embed intelligence into a new class of applications. There are many patterns for building applications that use LLMs. Workflows have scaffolding of predefined code paths around LLM calls. LLMs can direct the control flow through these predefined code paths, which some consider to be an "agentic system". In other cases, it's possible to remove this scaffolding, creating autonomous agents that can [plan](https://huyenchip.com/2025/01/07/agents.html), take actions via [tool calls](https://python.langchain.com/docs/concepts/tool_calling/), and directly respond [to the feedback from their own actions](https://research.google/blog/react-synergizing-reasoning-and-acting-in-language-models/) with further actions.
 
 ![Agent Workflow](img/agent_workflow.png)
 

docs/docs/concepts/human_in_the_loop.md

@@ -647,19 +647,15 @@ def node_in_parent_graph(state: State):
       This will print out
 
       ```pycon
-      --- First invocation ---
-      In parent node: {'foo': 'bar'}
       Entered `parent_node` a total of 1 times
       Entered `node_in_subgraph` a total of 1 times
       Entered human_node in sub-graph a total of 1 times
-      {'__interrupt__': (Interrupt(value='what is your name?', resumable=True, ns=['parent_node:0b23d72f-aaba-0329-1a59-ca4f3c8bad3b', 'human_node:25df717c-cb80-57b0-7410-44e20aac8f3c'], when='during'),)}
-
+      {'__interrupt__': (Interrupt(value='what is your name?', resumable=True, ns=['parent_node:4c3a0248-21f0-1287-eacf-3002bc304db4', 'human_node:2fe86d52-6f70-2a3f-6b2f-b1eededd6348'], when='during'),)}
       --- Resuming ---
-      In parent node: {'foo': 'bar'}
       Entered `parent_node` a total of 2 times
       Entered human_node in sub-graph a total of 2 times
       Got an answer of 35
-      {'parent_node': None} 
+      {'parent_node': {'state_counter': 1}}
       ```
 
 

docs/docs/concepts/index.md

@@ -7,7 +7,7 @@ description: Conceptual Guide for LangGraph
 
 This guide provides explanations of the key concepts behind the LangGraph framework and AI applications more broadly.
 
-We recommend that you go through at least the [Quick Start](../tutorials/introduction.ipynb) before diving into the conceptual guide. This will provide practical context that will make it easier to understand the concepts discussed here.
+We recommend that you go through at least the [Quickstart](../tutorials/introduction.ipynb) before diving into the conceptual guide. This will provide practical context that will make it easier to understand the concepts discussed here.
 
 The conceptual guide does not cover step-by-step instructions or specific implementation examples — those are found in the [Tutorials](../tutorials/index.md) and [How-to guides](../how-tos/index.md). For detailed reference material, please see the [API reference](../reference/index.md).
 
@@ -26,9 +26,11 @@ The conceptual guide does not cover step-by-step instructions or specific implem
 - [Human-in-the-Loop](human_in_the_loop.md): Explains different ways of integrating human feedback into a LangGraph application.
 - [Time Travel](time-travel.md): Time travel allows you to replay past actions in your LangGraph application to explore alternative paths and debug issues.
 - [Persistence](persistence.md): LangGraph has a built-in persistence layer, implemented through checkpointers. This persistence layer helps to support powerful capabilities like human-in-the-loop, memory, time travel, and fault-tolerance.
-- [Memory](memory.md): Memory in AI applications refers to the ability to process, store, and effectively recall information from past interactions. With memory, your agents can learn from feedback and adapt to users' preferences.  
-- [Streaming](streaming.md): Streaming is crucial for enhancing the responsiveness of applications built on LLMs. By displaying output progressively, even before a complete response is ready, streaming significantly improves user experience (UX), particularly when dealing with the latency of LLMs. 
-- [Functional API (beta)](functional_api.md): An alternative to [Graph API (StateGraph)](low_level.md#stategraph) for development in LangGraph.
+- [Memory](memory.md): Memory in AI applications refers to the ability to process, store, and effectively recall information from past interactions. With memory, your agents can learn from feedback and adapt to users' preferences.
+- [Streaming](streaming.md): Streaming is crucial for enhancing the responsiveness of applications built on LLMs. By displaying output progressively, even before a complete response is ready, streaming significantly improves user experience (UX), particularly when dealing with the latency of LLMs.
+- [Functional API](functional_api.md): `@entrypoint` and `@task` decorators that allow you to add LangGraph functionality to an existing codebase.
+- [Durable Execution](durable_execution.md): LangGraph's built-in [persistence](./persistence.md) layer provides durable execution for workflows, ensuring that the state of each execution step is saved to a durable store. 
+- [Pregel](pregel.md): Pregel is LangGraph's runtime, which is responsible for managing the execution of LangGraph applications.
 - [FAQ](faq.md): Frequently asked questions about LangGraph.
 
 ## LangGraph Platform
@@ -37,7 +39,6 @@ LangGraph Platform is a commercial solution for deploying agentic applications i
 
 The LangGraph Platform offers a few different deployment options described in the [deployment options guide](./deployment_options.md).
 
-
 !!! tip
 
     * LangGraph is an MIT-licensed open-source library, which we are committed to maintaining and growing for the community.
@@ -46,7 +47,9 @@ The LangGraph Platform offers a few different deployment options described in th
 ### High Level
 
 - [Why LangGraph Platform?](./langgraph_platform.md): The LangGraph platform is an opinionated way to deploy and manage LangGraph applications. This guide provides an overview of the key features and concepts behind LangGraph Platform.
-- [Deployment Options](./deployment_options.md): LangGraph Platform offers four deployment options: [Self-Hosted Lite](./self_hosted.md#self-hosted-lite), [Self-Hosted Enterprise](./self_hosted.md#self-hosted-enterprise), [bring your own cloud (BYOC)](./bring_your_own_cloud.md), and [Cloud SaaS](./langgraph_cloud.md). This guide explains the differences between these options, and which Plans they are available on.
+- [Platform Architecture](./platform_architecture.md): A high-level overview of the architecture of the LangGraph Platform.
+- [Scalability and Resilience](./scalability_and_resilience.md): LangGraph Platform is designed to be scalable and resilient. This document explains how the platform achieves this.
+- [Deployment Options](./deployment_options.md): LangGraph Platform offers four deployment options: [Cloud SaaS](./langgraph_cloud.md), [Self-Hosted Data Plane](./langgraph_self_hosted_data_plane.md), [Self-Hosted Control Plane](./langgraph_self_hosted_control_plane.md), and [Standalone Container](./langgraph_standalone_container.md). This guide explains the differences between these options, and which Plans they are available on.
 - [Plans](./plans.md): LangGraph Platforms offer three different plans: Developer, Plus, Enterprise. This guide explains the differences between these options, what deployment options are available for each, and how to sign up for each one.
 - [Template Applications](./template_applications.md): Reference applications designed to help you get started quickly when building with LangGraph.
 
@@ -54,11 +57,13 @@ The LangGraph Platform offers a few different deployment options described in th
 
 The LangGraph Platform comprises several components that work together to support the deployment and management of LangGraph applications:
 
-- [LangGraph Server](./langgraph_server.md): The LangGraph Server is designed to support a wide range of agentic application use cases, from background processing to real-time interactions. 
+- [LangGraph Server](./langgraph_server.md): The LangGraph Server is designed to support a wide range of agentic application use cases, from background processing to real-time interactions.
 - [LangGraph Studio](./langgraph_studio.md): LangGraph Studio is a specialized IDE that can connect to a LangGraph Server to enable visualization, interaction, and debugging of the application locally.
 - [LangGraph CLI](./langgraph_cli.md): LangGraph CLI is a command-line interface that helps to interact with a local LangGraph
 - [Python/JS SDK](./sdk.md): The Python/JS SDK provides a programmatic way to interact with deployed LangGraph Applications.
 - [Remote Graph](../how-tos/use-remote-graph.md): A RemoteGraph allows you to interact with any deployed LangGraph application as though it were running locally.
+- [LangGraph Control Plane](./langgraph_control_plane.md): The LangGraph Control Plane refers to the Control Plane UI where users create and update LangGraph Servers and the Control Plane APIs that support the UI experience.
+- [LangGraph Data Plane](./langgraph_data_plane.md): The LangGraph Data Plane refers to LangGraph Servers, the corresponding infrastructure for each server, and the "listener" application that continuously polls for updates from the LangGraph Control Plane.
 
 ### LangGraph Server
 
@@ -71,8 +76,7 @@ The LangGraph Platform comprises several components that work together to suppor
 
 ### Deployment Options
 
-
-- [Self-Hosted Lite](./self_hosted.md): A free (up to 1 million nodes executed per year), limited version of LangGraph Platform that you can run locally or in a self-hosted manner
-- [Cloud SaaS](./langgraph_cloud.md): Hosted as part of LangSmith.
-- [Bring Your Own Cloud](./bring_your_own_cloud.md): We manage the infrastructure, so you don't have to, but the infrastructure all runs within your cloud.
-- [Self-Hosted Enterprise](./self_hosted.md): Completely managed by you.
+- <a href="./langgraph_cloud/">Cloud SaaS<sup>(Beta)</sup></a>: Connect to your GitHub repositories and deploy LangGraph Servers to LangChain's cloud. We manage everything.
+- <a href="./langgraph_self_hosted_data_plane/">Self-Hosted Data Plane<sup>(Beta)</sup></a>: Create deployments from the [Control Plane UI](../concepts/langgraph_control_plane.md#control-plane-ui) and deploy LangGraph Servers to your cloud. We manage the [control plane](../concepts/langgraph_control_plane.md), you manage the deployments.
+- <a href="./langgraph_self_hosted_control_plane/">Self-Hosted Control Plane<sup>(Beta)</sup></a>: Create deployments from a self-hosted [Control Plane UI](../concepts/langgraph_control_plane.md#control-plane-ui) and deploy LangGraph Servers to your cloud. You manage everything.
+- [Standalone Container](../concepts/langgraph_standalone_container.md): Deploy LangGraph Server Docker images however you like.

docs/docs/concepts/langgraph_cli.md

@@ -4,7 +4,7 @@
     - [LangGraph Platform](./langgraph_platform.md)
     - [LangGraph Server](./langgraph_server.md)
 
-The LangGraph CLI is a multi-platform command-line tool for building and running the [LangGraph API server](./langgraph_server.md) locally. This offers an alternative to the [LangGraph Studio desktop app](./langgraph_studio.md) for developing and testing agents across all major operating systems (Linux, Windows, MacOS). The resulting server includes all API endpoints for your graph's runs, threads, assistants, etc. as well as the other services required to run your agent, including a managed database for checkpointing and storage.
+The LangGraph CLI is a multi-platform command-line tool for building and running the [LangGraph API server](./langgraph_server.md) locally. The resulting server includes all API endpoints for your graph's runs, threads, assistants, etc. as well as the other services required to run your agent, including a managed database for checkpointing and storage.
 
 ## Installation
 
@@ -54,7 +54,7 @@ pip install -U "langgraph-cli[inmem]"
 
 ### `up`
 
-The `langgraph up` command starts an instance of the [LangGraph API server](./langgraph_server.md) locally in a docker container. This requires thedocker server to be running locally. It also requires a LangSmith API key for local development or a license key for production use.
+The `langgraph up` command starts an instance of the [LangGraph API server](./langgraph_server.md) locally in a docker container. This requires the docker server to be running locally. It also requires a LangSmith API key for local development or a license key for production use.
 
 The server includes all API endpoints for your graph's runs, threads, assistants, etc. as well as the other services required to run your agent, including a managed database for checkpointing and storage.
 

docs/docs/concepts/langgraph_cloud.md

@@ -1,85 +1,17 @@
-# Cloud SaaS
+# Cloud SaaS (Beta)
 
-!!! info "Prerequisites" 
-    - [LangGraph Platform](./langgraph_platform.md) 
-    - [LangGraph Server](./langgraph_server.md)
+To deploy a [LangGraph Server](../concepts/langgraph_server.md), follow the how-to guide for [how to deploy to Cloud SaaS](../cloud/deployment/cloud.md).
 
 ## Overview
 
-LangGraph's Cloud SaaS is a managed service for deploying LangGraph Servers, regardless of its definition or dependencies. The service offers managed implementations of checkpointers and stores, allowing you to focus on building the right cognitive architecture for your use case. By handling scalable & secure infrastructure, LangGraph Cloud SaaS offers the fastest path to getting your LangGraph Server deployed to production.
+The Cloud SaaS deployment option is a fully managed model for deployment where we manage the [control plane](./langgraph_control_plane.md) and [data plane](./langgraph_data_plane.md) in our cloud.
 
-## Deployment
-
-A **deployment** is an instance of a LangGraph Server. A single deployment can have many [revisions](#revision). When a deployment is created, all the necessary infrastructure (e.g. database, containers, secrets store) are automatically provisioned. See the [architecture diagram](#architecture) below for more details.
-
-Resource Allocation:
-
-| **Deployment Type** | **CPU** | **Memory** | **Scaling**         |
-|---------------------|---------|------------|---------------------|
-| Development         | 1 CPU   | 1 GB       | Up to 1 container   |
-| Production          | 2 CPU   | 2 GB       | Up to 10 containers |
-
-See the [how-to guide](../cloud/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](../cloud/deployment/cloud.md#create-new-revision) for creating a new revision.
-
-## Persistence
-
-A dedicated database is automatically created for each deployment. The database serves as the [persistence layer](../concepts/persistence.md) for the deployment.
-
-When defining a graph to be deployed to LangGraph Cloud SaaS, a [checkpointer](../concepts/persistence.md#checkpointer-libraries) should not be configured by the user. Instead, a checkpointer is automatically configured for the graph.
-
-There is no direct access to the database. All access to the database occurs through the LangGraph Server APIs.
-
-## Autoscaling
-`Production` type deployments automatically scale up to 10 containers. Scaling is based on the current request load for a single container. Specifically, the autoscaling implementation scales the deployment so that each container is processing about 10 concurrent requests. For example... 
-
-- If the deployment is processing 20 concurrent requests, the deployment will scale up from 1 container to 2 containers (20 requests / 2 containers = 10 requests per container).
-- If a deployment of 2 containers is processing 10 requests, the deployment will scale down from 2 containers to 1 container (10 requests / 1 container = 10 requests per container).
-
-10 concurrent requests per container is the target threshold. However, 10 concurrent requests per container is not a hard limit. The number of concurrent requests can exceed 10 if there is a sudden burst of requests.
-
-Scale down actions are delayed for 30 minutes before any action is taken. In other words, if the autoscaling implementation decides to scale down a deployment, it will first wait for 30 minutes before scaling down. After 30 minutes, the concurrency metric is recomputed and the deployment will scale down if the concurrency metric has met the target threshold. Otherwise, the deployment remains scaled up. This "cool down" period ensures that deployments do not scale up and down too frequently.
-
-In the future, the autoscaling implementation may evolve to accommodate other metrics such as background run queue size.
-
-## 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.
-
-- When a new deployment is created, a new database is created for the deployment. Database creation is a one-time step. This step contributes to a longer deployment time for the initial revision of the deployment.
-- When a subsequent revision is created for a deployment, there is no database creation step. The deployment time for a subsequent revision is significantly faster compared to the deployment time of the initial revision.
-- The deployment process for each revision contains a build step, which can take up to a few minutes.
-
-## LangSmith Integration
-
-A [LangSmith](https://docs.smith.langchain.com/) tracing project is automatically created for each deployemnt. The tracing project has the same name as the deployment. When creating a deployment, the `LANGCHAIN_TRACING_V2` and `LANGCHAIN_API_KEY` environment variables do not need to be specified; they are set internally, automatically. Traces are created for each run and are emitted to the tracing project automatically.
-
-When a deployment is deleted, the traces and the tracing project are not deleted.
-
-## Automatic Deletion
-
-Deployments are automatically deleted after 28 consecutive days of non-use (it is in an unused state). A deployment is in an unused state if there are no traces emitted to LangSmith from the deployment after 28 consecutive days. On any given day, if a deployment emits a trace to LangSmith, the counter for consecutive days of non-use is reset.
-
-- An email notification is sent after 7 consecutive days of non-use.
-- A deployment is deleted after 28 consecutive days of non-use.
-
-!!! danger "Data Cannot Be Recovered"
-    After a deployment is deleted, the data (i.e. [persistence](#persistence)) from the deployment cannot be recovered.
+|                   | [Control Plane](../concepts/langgraph_control_plane.md) | [Data Plane](../concepts/langgraph_data_plane.md) |
+|-------------------|-------------------|------------|
+| **What is it?** | <ul><li>Control Plane UI for creating deployments and revisions</li><li>Control Plane APIs for creating deployments and revisions</li></ul> | <ul><li>Data plane "listener" for reconciling deployments with control plane state</li><li>LangGraph Servers</li><li>Postgres, Redis, etc</li></ul> |
+| **Where is it hosted?** | LangChain's cloud | LangChain's cloud |
+| **Who provisions and manages it?** | LangChain | LangChain |
 
 ## Architecture
 
-!!! warning "Subject to Change"
-    The Cloud SaaS deployment architecture may change in the future.
-
-A high-level diagram of a Cloud SaaS deployment.
-
-![diagram](img/langgraph_cloud_architecture.png)
-
-## Related
-
-- [Deployment Options](./deployment_options.md)
+![Cloud SaaS](./img/self_hosted_control_plane_architecture.png)

docs/docs/concepts/langgraph_control_plane.md

@@ -0,0 +1,98 @@
+# LangGraph Control Plane
+
+The term "control plane" is used broadly to refer to the Control Plane UI where users create and update [LangGraph Servers](./langgraph_server.md) (deployments) and the Control Plane APIs that support the UI experience.
+
+When a user makes an update through the Control Plane UI, the update is stored in the control plane state. The [LangGraph Data Plane](./langgraph_data_plane.md) "listener" application polls for these updates by calling the Control Plane APIs.
+
+## Control Plane UI
+
+From the Control Plane UI, you can:
+
+- View a list of outstanding deployments.
+- View details of an individual deployment.
+- Create a new deployment.
+- Update a deployment.
+- Update environment variables for a deployment.
+- View build and server logs of a deployment.
+- Delete a deployment.
+
+The Control Plane UI is embedded in [LangSmith](https://docs.smith.langchain.com/langgraph_cloud).
+
+## Control Plane API
+
+This section describes data model of the LangGraph Control Plane API. Control Plane API is used to create, update, and delete deployments. However, they are not publicly accessible.
+
+### Deployment
+
+A deployment is an instance of a LangGraph Server. A single deployment can have many revisions.
+
+### Revision
+
+A revision is an iteration of a deployment. When a new deployment is created, an initial revision is automatically created. To deploy code changes or update environment variables for a deployment, a new revision must be created.
+
+### Environment Variable
+
+Environment variables are set for a deployment. All environment variables are stored as secrets (i.e. saved in a secrets store).
+
+## Control Plane Features
+
+This section describes various features of the control plane.
+
+### Deployment Types
+
+For simplicity, the control plane offers two deployment types with different resource allocations: `Development` and `Production`.
+
+| **Deployment Type** | **CPU** | **Memory** | **Scaling**         |
+|---------------------|---------|------------|---------------------|
+| Development         | 1 CPU   | 1 GB       | Up to 1 container   |
+| Production          | 2 CPU   | 2 GB       | Up to 10 containers |
+
+CPU and memory resources are per container.
+
+!!! info "For [Cloud SaaS](../concepts/langgraph_cloud.md)"
+    For `Production` type deployments, resources can be manually increased on a case-by-case basis depending on use case and capacity constraints. Contact support@langchain.dev to request an increase in resources.
+
+!!! info "For [Self-Hosted Data Plane](../concepts/langgraph_self_hosted_data_plane.md) and [Self-Hosted Control Plane](../concepts/langgraph_self_hosted_control_plane.md)"
+    Resources for [Self-Hosted Data Plane](../concepts/langgraph_data_plane.md) and [Self-Hosted Control Plane](../concepts/langgraph_control_plane.md) deployments can be fully customized.
+
+### Database Provisioning
+
+The control plane and [LangGraph Data Plane](./langgraph_data_plane.md) "listener" application coordinate to automatically create a Postgres database for each deployment. The database serves as the [persistence layer](../concepts/persistence.md) for the deployment.
+
+When implementing a LangGraph application, a [checkpointer](../concepts/persistence.md#checkpointer-libraries) does not need to be configured by the developer. Instead, a checkpointer is automatically configured for the graph. Any checkpointer configured for a graph will be replaced by the one that is automatically configured.
+
+There is no direct access to the database. All access to the database occurs through the [LangGraph Server](../concepts/langgraph_server.md).
+
+The database is never deleted until the deployment itself is deleted. See [Automatic Deletion](#automatic-deletion) for additional details.
+
+!!! info "For [Self-Hosted Data Plane](../concepts/langgraph_self_hosted_data_plane.md) and [Self-Hosted Control Plane](../concepts/langgraph_self_hosted_control_plane.md)"
+    A custom Postgres instance can be configured for [Self-Hosted Data Plane](../concepts/langgraph_data_plane.md) and [Self-Hosted Control Plane](../concepts/langgraph_control_plane.md) deployments.
+
+### Asynchronous Deployment
+
+Infrastructure for deployments and revisions are provisioned and deployed asynchronously. They are not deployed immediately after submission. Currently, deployment can take up to several minutes.
+
+- When a new deployment is created, a new database is created for the deployment. Database creation is a one-time step. This step contributes to a longer deployment time for the initial revision of the deployment.
+- When a subsequent revision is created for a deployment, there is no database creation step. The deployment time for a subsequent revision is significantly faster compared to the deployment time of the initial revision.
+- The deployment process for each revision contains a build step, which can take up to a few minutes.
+
+The control plane and [LangGraph Data Plane](./langgraph_data_plane.md) "listener" application coordinate to achieve asynchronous deployments.
+
+### Automatic Deletion
+
+!!! info "Only for [Cloud SaaS](../concepts/langgraph_cloud.md)"
+    Automatic deletion of deployments is only available for [Cloud SaaS](../concepts/langgraph_cloud.md).
+
+The control plane automatically deletes deployments after 28 consecutive days of non-use (it is in an unused state). A deployment is in an unused state if there are no traces emitted to LangSmith from the deployment after 28 consecutive days. On any given day, if a deployment emits a trace to LangSmith, the counter for consecutive days of non-use is reset.
+
+- An email notification is sent after 7 consecutive days of non-use.
+- A deployment is deleted after 28 consecutive days of non-use.
+
+!!! danger "Data Cannot Be Recovered"
+    After a deployment is deleted, the data (e.g. Postgres) from the deployment cannot be recovered.
+
+### LangSmith Integration
+
+A [LangSmith](https://docs.smith.langchain.com/) tracing project is automatically created for each deployment. The tracing project has the same name as the deployment. When creating a deployment, the `LANGCHAIN_TRACING` and `LANGSMITH_API_KEY`/`LANGCHAIN_API_KEY` environment variables do not need to be specified; they are set automatically by the control plane.
+
+When a deployment is deleted, the traces and the tracing project are not deleted.