release(langgraph): 0.3.25 (#4167)

Sample usage:

```python
from typing import Annotated, Sequence, TypedDict

from langchain_core.messages import 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 agent(state: AgentState):  # noqa: D103
    message = await ChatOpenAI(model="gpt-4o-mini", temperature=0).ainvoke(
        state["messages"]
    )

    # Also directly writes the message to `ui`
    push_ui_message("simple", {"hello": "123"}, message=message, state_key="ui")

    return {"messages": [message]}

```

.github/workflows/_lint.yml

@@ -54,7 +54,7 @@ jobs:
         if: steps.changed-files.outputs.all
         shell: bash
         working-directory: ${{ inputs.working-directory }}
-        run: poetry lock --check
+        run: poetry check --lock
 
       - name: Install dependencies
         if: steps.changed-files.outputs.all

.github/workflows/_test.yml

@@ -39,6 +39,12 @@ jobs:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_RO_TOKEN }}
 
+      - name: Check Lock
+        shell: bash
+        working-directory: ${{ inputs.working-directory }}
+        run: |
+          poetry check --lock
+
       - name: Install dependencies
         shell: bash
         working-directory: ${{ inputs.working-directory }}

.github/workflows/bench.yml

@@ -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

@@ -114,6 +114,42 @@ 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'
@@ -180,6 +216,8 @@ jobs:
         test,
         test-langgraph,
         test-scheduler-kafka,
+        check-sdk-methods,
+        check-schema,
         integration-test,
         test-js,
       ]

.github/workflows/deploy_docs.yml

@@ -63,35 +63,16 @@ 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.com/benjamincburns/markdown-exec.git@cc0d39d737e5ffd4b83d23cd8729d7ea16e363c8"
-
           # 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
 
-          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
-
       - name: Run unit tests
         # Run unit tests on the docs build pipeline
         run: make tests
@@ -102,7 +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: ${{ secrets.MKDOCS_GIT_COMMITTERS_APIKEY }}
           OPENAI_API_KEY: sf-proj-1234567890 # fake placeholder, shouldn't actually be used
@@ -111,7 +99,7 @@ jobs:
         env:
           LANGCHAIN_API_KEY: test
         run: |
-          if [ "${{ 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/.*" \
@@ -127,6 +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
@@ -147,6 +136,7 @@ jobs:
                 --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/run_notebooks.yml

@@ -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 +1,87 @@
-# 🦜🕸️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)
+## Why use LangGraph?
 
-```python
-final_state = app.invoke(
-    {"messages": [{"role": "user", "content": "what about ny"}]},
-    config={"configurable": {"thread_id": 42}}
-)
-final_state["messages"][-1].content
-```
+LangGraph is built for developers who want to build powerful, adaptable AI agents. Developers choose LangGraph for:
 
-```
-"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>
+- **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.
 
-> [!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.
+LangGraph is trusted in production and powering agents for companies like:
 
-<details>
-<summary>Low-level implementation</summary>
+- [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))
 
-```python
-from typing import Literal
+## LangGraph’s ecosystem
 
-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
+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:
 
+- [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/).
 
-# 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."
+## Pairing with LangGraph Platform
 
+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/).
 
-tools = [search]
+LangGraph Platform can help engineering teams:
 
-tool_node = ToolNode(tools)
+- **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.
 
-model = ChatAnthropic(model="claude-3-5-sonnet-latest", temperature=0).bind_tools(tools)
+## Additional resources
 
-# 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
+- [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.
 
+## Acknowledgements
 
-# 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]}
-
-
-# Define a new graph
-workflow = StateGraph(MessagesState)
-
-# Define the two nodes we will cycle between
-workflow.add_node("agent", call_model)
-workflow.add_node("tools", tool_node)
-
-# 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

@@ -10,7 +10,15 @@ 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
+	@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/prebuilt.md --language python
 
 build-docs: build-typedoc build-prebuilt

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/notebook_hooks.py

@@ -186,7 +186,7 @@ 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/third_party_page/get_download_stats.py

@@ -30,10 +30,23 @@ 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:
         # First check if package exists on PyPI
         pypi_url = f"https://pypi.org/pypi/{package['name']}/json"
@@ -88,13 +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")
@@ -115,6 +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

@@ -23,4 +23,19 @@ packages:
     description: "Build swarm-style multi-agent systems using LangGraph."
   - name: "delve-taxonomy-generator"
     repo: "andrestorres123/delve"
-    description: "A taxonomy generator for unstructured data"
+    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 @@
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

docs/docs/adopters.md

@@ -10,14 +10,17 @@ This list of companies using LangGraph and their success stories is compiled fro
 | [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/) |
@@ -25,3 +28,4 @@ This list of companies using LangGraph and their success stories is compiled fro
 | [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/) |
+| [Vodafone](https://www.vodafone.com/) | Telecommunications | Code generation; internal search | [Case study, 2025](https://blog.langchain.dev/customers-vodafone/) |

docs/docs/cloud/deployment/cloud.md

@@ -1,6 +1,6 @@
-# How to Deploy to LangGraph Cloud
+# How to Deploy to Cloud SaaS
 
-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
 

docs/docs/cloud/deployment/self_hosted_control_plane.md

@@ -0,0 +1,56 @@
+# How to Deploy Self-Hosted Control Plane
+
+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
+
+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_pyproject.md

@@ -64,7 +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

@@ -1,6 +1,133 @@
 # Prompt Engineering in LangGraph Studio
 
-In LangGraph Studio you can iterate on the prompts used within your graph by utilizing the LangSmith Playground. To do so:
+## 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.
@@ -8,8 +135,6 @@ In LangGraph Studio you can iterate on the prompts used within your graph by uti
 
 ![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/use_stream_react.md

@@ -1,8 +1,6 @@
 # How to integrate LangGraph into your React application
 
-!!! info "Prerequisites"
-    - [LangGraph Platform](../../concepts/langgraph_platform.md)
-    - [LangGraph Server](../../concepts/langgraph_server.md)
+!!! 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.
 
@@ -169,10 +167,7 @@ The `useStream()` hook exposes the `interrupt` property, which will be filled wi
 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 }
->({
+const thread = useStream<{ messages: Message[] }, { InterruptType: string }>({
   apiUrl: "http://localhost:2024",
   assistantId: "agent",
   messagesKey: "messages",
@@ -182,7 +177,6 @@ if (thread.interrupt) {
   return (
     <div>
       Interrupted! {thread.interrupt.value}
-
       <button
         type="button"
         onClick={() => {
@@ -313,7 +307,7 @@ export default function App() {
                   onEdit={(message) =>
                     thread.submit(
                       { messages: [message] },
-                      { checkpoint: parentCheckpoint },
+                      { checkpoint: parentCheckpoint }
                     )
                   }
                 />
@@ -370,6 +364,33 @@ export default function App() {
 
 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.
@@ -397,21 +418,23 @@ You can also optionally specify types for different scenarios, such as:
 - `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;
-  };
-}>({
+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",

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

@@ -29,7 +29,7 @@ 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 +42,16 @@ 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"
@@ -59,9 +60,10 @@ 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
 
@@ -82,7 +84,7 @@ 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"]`
@@ -171,6 +173,62 @@ 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"
     

docs/docs/cloud/reference/env_var.md

@@ -2,6 +2,22 @@
 
 The LangGraph Cloud 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.
@@ -28,6 +44,10 @@ 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.
 
+## `LOG_LEVEL`
+
+Configure [log level](https://docs.python.org/3/library/logging.html#logging-levels). Defaults to `INFO`.
+
 ## `N_JOBS_PER_WORKER`
 
 Number of jobs per worker for the LangGraph Cloud task queue. Defaults to `10`.
@@ -55,3 +75,9 @@ 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.
+
+## `REDIS_URI_CUSTOM`
+
+For [Bring Your Own Cloud (BYOC)](../../concepts/bring_your_own_cloud.md) deployments only.
+
+Specify `REDIS_URI_CUSTOM` to use an externally managed 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/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. **[Cloud SaaS](#cloud-saas)**: Available for **Plus** and **Enterprise** plans.
 
-2. **[Self-Hosted Enterprise](#self-hosted-enterprise)**: Available for the **Enterprise** plan.
+1. **[Self-Hosted Data Plane](#self-hosted-data-plane)**: Available for the **Enterprise** plan.
 
-3. **[Cloud SaaS](#cloud-saas)**: Available for **Plus** and **Enterprise** plans.
+1. **[Self-Hosted Control Plane](#self-hosted-control-plane)**: 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 is optionally available for Self-Hosted Enterprise LangGraph deployments. With one click, self-hosted LangGraph deployments can be deployed in the same Kubernetes cluster where a self-hosted LangSmith instance is deployed.
-
-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 is optionally available for Self-Hosted Lite LangGraph deployments. With one click, self-hosted LangGraph deployments can be deployed in the same Kubernetes cluster where a self-hosted LangSmith instance is deployed.
-
-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/functional_api.md

@@ -23,9 +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."""

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/index.md

@@ -49,7 +49,7 @@ The LangGraph Platform offers a few different deployment options described in th
 - [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.
 - [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: [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.
+- [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.
 
@@ -62,6 +62,8 @@ The LangGraph Platform comprises several components that work together to suppor
 - [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
 
@@ -74,7 +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.
+- [Cloud SaaS](../concepts/langgraph_cloud.md): Connect to your GitHub repositories and deploy LangGraph Servers to LangChain's cloud. We manage everything.
+- [Self-Hosted Data Plane](../concepts/langgraph_self_hosted_data_plane.md): 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.
+- [Self-Hosted Control Plane](../concepts/langgraph_self_hosted_control_plane.md#control-plane-ui): Create deployments from a self-hosted [Control Plane UI](../concepts/langgraph_control_plane.md) 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_cloud.md

@@ -1,101 +1,17 @@
 # Cloud SaaS
 
-!!! 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)
-
-## 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   |
-
-## 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.

docs/docs/concepts/langgraph_data_plane.md

@@ -0,0 +1,74 @@
+# LangGraph Data Plane
+
+The term "data plane" is used broadly to refer to [LangGraph Servers](./langgraph_server.md) (deployments), the corresponding infrastructure for each server, and the "listener" application that continuously polls for updates from the [LangGraph Control Plane](./langgraph_control_plane.md).
+
+## Server Infrastructure
+
+In addition to the [LangGraph Server](./langgraph_server.md) itself, the following infrastructure for each server are also included in the broad definition of "data plane":
+
+- [Postgres](../concepts/platform_architecture.md#how-we-use-postgres)
+- [Redis](../concepts/platform_architecture.md#how-we-use-redis)
+- Secrets store
+- Autoscalers
+
+See [LangGraph Platform Architecture](../concepts/platform_architecture.md) for more details.
+
+## "Listener" Application
+
+The data plane "listener" application periodically calls [Control Plane APIs](../concepts/langgraph_control_plane.md#control-plane-api) to:
+
+- Determine if new deployments should be created.
+- Determine if existing deployments should be updated (i.e. new revisions).
+- Determine if existing deployments should be deleted.
+
+In other words, the data plane "listener" reads the latest state of the control plane (desired state) and takes action to reconcile outstanding deployments (current state) to match the latest state.
+
+## Data Plane Features
+
+This section describes various features of the data plane.
+
+### Lite vs Enterprise
+
+There are two versions of the LangGraph Server: `Lite` and `Enterprise`.
+
+The `Lite` version is a limited version of the LangGraph Server that you can run locally or in a self-hosted manner (up to 1 million nodes executed per year). `Lite` is only available for the [Standalone Container](../concepts/langgraph_standalone_container.md) deployment option.
+
+The `Enterprise` version is the full version of the LangGraph Server. To use the `Enterprise` version, you must acquire a license key that you will need to specify when running the Docker image. To acquire a license key, please email sales@langchain.dev. `Enterprise` is available for [Cloud SaaS](../concepts/langgraph_cloud.md), [Self-Hosted Data Plane](../concepts/langgraph_self_hosted_data_plane.md), and [Self-Hosted Control Plane](../concepts/langgraph_self_hosted_control_plane.md) deployment options.
+
+Feature Differences:
+
+|       | Lite       | Enterprise |
+|-------|------------|------------|
+| [Cron Jobs](../concepts/langgraph_server.md#cron-jobs) |❌|✅|
+| [Custom Authentication](../concepts/auth.md) |❌|✅|
+
+### Autoscaling
+
+[`Production` type](../concepts/langgraph_control_plane.md#deployment-types) 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.
+
+### Static IP Addresses
+
+!!! info "Only for Cloud SaaS"
+    Static IP addresses are only available for [Cloud SaaS](../concepts/langgraph_cloud.md).
+
+All traffic from deployments created after January 6th 2025 will come through a NAT gateway. This NAT gateway will have several static IP addresses depending on the data region. Refer to the table below for the list of static IP addresses:
+
+| 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/concepts/langgraph_platform.md

@@ -1,3 +1,8 @@
+---
+search:
+  boost: 2
+---
+
 # LangGraph Platform
 
 ## Overview
@@ -11,6 +16,8 @@ The LangGraph Platform consists of several components that work together to supp
 - [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.
 
 ![](img/lg_platform.png)
 

docs/docs/concepts/langgraph_self_hosted_control_plane.md

@@ -0,0 +1,23 @@
+# Self-Hosted Control Plane
+
+To deploy a [LangGraph Server](../concepts/langgraph_server.md), follow the how-to guide for [how to deploy the Self-Hosted Control Plane](../cloud/deployment/self_hosted_control_plane.md).
+
+## Overview
+
+The Self-Hosted Control Plane 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 implies that the data plane is self-hosted).
+
+|                   | [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?** | Your cloud | Your cloud |
+| **Who provisions and manages it?** | You | You |
+
+## Architecture
+
+![Self-Hosted Control Plane Architecture](./img/self_hosted_control_plane_architecture.png)
+
+## Compute Platforms
+
+### Kubernetes
+
+The Self-Hosted Control Plane deployment option supports deploying control plane and data plane infrastructure to any Kubernetes cluster.

docs/docs/concepts/langgraph_self_hosted_data_plane.md

@@ -0,0 +1,27 @@
+# Self-Hosted Data Plane
+
+To deploy a [LangGraph Server](../concepts/langgraph_server.md), follow the how-to guide for [how to deploy the Self-Hosted Data Plane](../cloud/deployment/self_hosted_data_plane.md).
+
+## Overview
+
+LangGraph Platform's Self-Hosted Data Plane 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.
+
+|                   | [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 | Your cloud |
+| **Who provisions and manages it?** | LangChain | You |
+
+## Architecture
+
+![Self-Hosted Data Plane Architecture](./img/self_hosted_data_plane_architecture.png)
+
+## Compute Platforms
+
+### Kubernetes
+
+The Self-Hosted Data Plane deployment option supports deploying data plane infrastructure to any Kubernetes cluster.
+
+### Amazon ECS
+
+Coming soon...

docs/docs/concepts/langgraph_standalone_container.md

@@ -0,0 +1,27 @@
+# Standalone Container
+
+To deploy a [LangGraph Server](../concepts/langgraph_server.md), follow the how-to guide for [how to deploy a Standalone Container](../cloud/deployment/standalone_container.md).
+
+## Overview
+
+The Standalone Container deployment option is the least restrictive model for deployment. There is no [control plane](./langgraph_control_plane.md). [Data plane](./langgraph_data_plane.md) infrastructure is managed by you.
+
+|                   | [Control Plane](../concepts/langgraph_control_plane.md) | [Data Plane](../concepts/langgraph_data_plane.md) |
+|-------------------|-------------------|------------|
+| **What is it?** | n/a | <ul><li>LangGraph Servers</li><li>Postgres, Redis, etc</li></ul> |
+| **Where is it hosted?** | n/a | Your cloud |
+| **Who provisions and manages it?** | n/a | You |
+
+## Architecture
+
+![Standalone Container](./img/langgraph_platform_deployment_architecture.png)
+
+## Compute Platforms
+
+### Kubernetes
+
+The Standalone Container deployment option supports deploying data plane infrastructure to a Kubernetes cluster.
+
+### Docker
+
+The Standalone Container deployment option supports deploying data plane infrastructure to any Docker-supported compute platform.

docs/docs/concepts/low_level.md

@@ -360,7 +360,7 @@ Use [conditional edges](#conditional-edges) to route between nodes conditionally
 If you are using [subgraphs](#subgraphs), you might want to navigate from a node within a subgraph to a different subgraph (i.e. a different node in the parent graph). To do so, you can specify `graph=Command.PARENT` in `Command`:
 
 ```python
-def my_node(state: State) -> Command[Literal["my_other_node"]]:
+def my_node(state: State) -> Command[Literal["other_subgraph"]]:
     return Command(
         update={"foo": "bar"},
         goto="other_subgraph",  # where `other_subgraph` is a node in the parent graph

docs/docs/concepts/memory.md

@@ -275,7 +275,7 @@ See this how-to [video](https://www.youtube.com/watch?v=37VaU7e7t5o) for example
 
 [Procedural memory](https://en.wikipedia.org/wiki/Procedural_memory), in both humans and AI agents, involves remembering the rules used to perform tasks. In humans, procedural memory is like the internalized knowledge of how to perform tasks, such as riding a bike via basic motor skills and balance. Episodic memory, on the other hand, involves recalling specific experiences, such as the first time you successfully rode a bike without training wheels or a memorable bike ride through a scenic route. For AI agents, procedural memory is a combination of model weights, agent code, and agent's prompt that collectively determine the agent's functionality. 
 
-In practice, it is fairly uncommon for agents to modify their model weights or rewrite their code. However, it is more common for agents to [modify their own prompts](https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/prompt-generator). 
+In practice, it is fairly uncommon for agents to modify their model weights or rewrite their code. However, it is more common for agents to modify their own prompts. 
 
 One effective approach to refining an agent's instructions is through ["Reflection"](https://blog.langchain.dev/reflection-agents/) or meta-prompting. This involves prompting the agent with its current instructions (e.g., the system prompt) along with recent conversations or explicit user feedback. The agent then refines its own instructions based on this input. This method is particularly useful for tasks where instructions are challenging to specify upfront, as it allows the agent to learn and adapt from its interactions.
 

docs/docs/concepts/multi_agent.md

@@ -50,7 +50,7 @@ def agent(state) -> Command[Literal["agent", "another_agent"]]:
 In a more complex scenario where each agent node is itself a graph (i.e., a [subgraph](./low_level.md#subgraphs)), a node in one of the agent subgraphs might want to navigate to a different agent. For example, if you have two agents, `alice` and `bob` (subgraph nodes in a parent graph), and `alice` needs to navigate to `bob`, you can set `graph=Command.PARENT` in the `Command` object:
 
 ```python
-def some_node_inside_alice(state)
+def some_node_inside_alice(state):
     return Command(
         goto="bob",
         update={"my_state_key": "my_state_value"},
@@ -89,7 +89,7 @@ def transfer_to_bob(state):
     )
 ```
 
-This is a special case of updating the graph state from tools where in addition the state update, the control flow is included as well.
+This is a special case of updating the graph state from tools where, in addition to the state update, the control flow is included as well.
 
 !!! important
 
@@ -235,7 +235,7 @@ supervisor = create_react_agent(model, tools)
 
 ### Hierarchical
 
-As you add more agents to your system, it might become too hard for the supervisor to manage all of them. The supervisor might start making poor decisions about which agent to call next, the context might become too complex for a single supervisor to keep track of. In other words, you end up with the same problems that motivated the multi-agent architecture in the first place.
+As you add more agents to your system, it might become too hard for the supervisor to manage all of them. The supervisor might start making poor decisions about which agent to call next, or the context might become too complex for a single supervisor to keep track of. In other words, you end up with the same problems that motivated the multi-agent architecture in the first place.
 
 To address this, you can design your system _hierarchically_. For example, you can create separate, specialized teams of agents managed by individual supervisors, and a top-level supervisor to manage the teams.
 
@@ -339,9 +339,9 @@ builder.add_edge("agent_1", "agent_2")
 
 ## Communication between agents
 
-The most important thing when building multi-agent systems is figuring out how the agents communicate. There are few different considerations:
+The most important thing when building multi-agent systems is figuring out how the agents communicate. There are a few different considerations:
 
-- Do agents communicate via [**via graph state or via tool calls**](#graph-state-vs-tool-calls)?
+- Do agents communicate [**via graph state or via tool calls**](#graph-state-vs-tool-calls)?
 - What if two agents have [**different state schemas**](#different-state-schemas)?
 - How to communicate over a [**shared message list**](#shared-message-list)?
 

docs/docs/concepts/persistence.md

@@ -32,7 +32,7 @@ from typing_extensions import TypedDict
 from operator import add
 
 class State(TypedDict):
-    foo: int
+    foo: str
     bar: Annotated[list[str], add]
 
 def node_a(state: State):
@@ -232,7 +232,7 @@ from langgraph.store.memory import InMemoryStore
 in_memory_store = InMemoryStore()
 ```
 
-Memories are namespaced by a `tuple`, which in this specific example will be `(<user_id>, "memories")`. The namespace can be any length and represent anything, does not have be user specific.
+Memories are namespaced by a `tuple`, which in this specific example will be `(<user_id>, "memories")`. The namespace can be any length and represent anything, does not have to be user specific.
 
 ```python 
 user_id = "1"
@@ -387,6 +387,9 @@ We can access the memories and use them in our model call.
 def call_model(state: MessagesState, config: RunnableConfig, *, store: BaseStore):
     # Get the user id from the config
     user_id = config["configurable"]["user_id"]
+
+    # Namespace the memory
+    namespace = (user_id, "memories")
     
     # Search based on the most recent message
     memories = store.search(

docs/docs/concepts/pregel.md

@@ -284,7 +284,7 @@ LangGraph provides two high-level APIs for creating a Pregel application: the [S
     {'__start__': <langgraph.pregel.read.PregelNode at 0x7d05e3ba1810>,
      'write_essay': <langgraph.pregel.read.PregelNode at 0x7d05e3ba14d0>,
      'score_essay': <langgraph.pregel.read.PregelNode at 0x7d05e3ba1710>}
-     ```
+    ```
 
     ```python
     print(graph.channels)
@@ -344,4 +344,4 @@ LangGraph provides two high-level APIs for creating a Pregel application: the [S
     {'write_essay': <langgraph.pregel.read.PregelNode object at 0x7d05e2f9aad0>}
     Channels: 
     {'__start__': <langgraph.channels.ephemeral_value.EphemeralValue object at 0x7d05e2c906c0>, '__end__': <langgraph.channels.last_value.LastValue object at 0x7d05e2c90c40>, '__previous__': <langgraph.channels.last_value.LastValue object at 0x7d05e1007280>}
-    ```
+    ```

docs/docs/concepts/v0-human-in-the-loop.md

@@ -1,3 +1,8 @@
+---
+search:
+  exclude: true
+---
+
 # Human-in-the-loop
 
 !!! note "Use the `interrupt` function instead."

docs/docs/how-tos/command.ipynb

@@ -33,7 +33,7 @@
     "    )\n",
     "```\n",
     "\n",
-    "If you are using [subgraphs](#subgraphs), you might want to navigate from a node a subgraph to a different subgraph (i.e. a different node in the parent graph). To do so, you can specify `graph=Command.PARENT` in `Command`:\n",
+    "If you are using [subgraphs](#subgraphs), you might want to navigate from a node within a subgraph to a different subgraph (i.e. a different node in the parent graph). To do so, you can specify `graph=Command.PARENT` in `Command`:\n",
     "\n",
     "```python\n",
     "def my_node(state: State) -> Command[Literal[\"my_other_node\"]]:\n",

docs/docs/how-tos/create-react-agent-memory.ipynb

@@ -122,20 +122,18 @@
     "\n",
     "# For this tutorial we will use custom tool that returns pre-defined values for weather in two cities (NYC & SF)\n",
     "\n",
-    "from typing import Literal\n",
-    "\n",
     "from langchain_core.tools import tool\n",
     "\n",
     "\n",
     "@tool\n",
-    "def get_weather(city: Literal[\"nyc\", \"sf\"]):\n",
+    "def get_weather(location: str) -> str:\n",
     "    \"\"\"Use this to get weather information.\"\"\"\n",
-    "    if city == \"nyc\":\n",
+    "    if any([city in location.lower() for city in [\"nyc\", \"new york city\"]]):\n",
     "        return \"It might be cloudy in nyc\"\n",
-    "    elif city == \"sf\":\n",
+    "    elif any([city in location.lower() for city in [\"sf\", \"san francisco\"]]):\n",
     "        return \"It's always sunny in sf\"\n",
     "    else:\n",
-    "        raise AssertionError(\"Unknown city\")\n",
+    "        return f\"I am not sure what the weather is in {location}\"\n",
     "\n",
     "\n",
     "tools = [get_weather]\n",
@@ -220,7 +218,7 @@
    "id": "838a043f-90ad-4e69-9d1d-6e22db2c346c",
    "metadata": {},
    "source": [
-    "Notice that when we pass the same the same thread ID, the chat history is preserved"
+    "Notice that when we pass the same thread ID, the chat history is preserved."
    ]
   },
   {

docs/docs/how-tos/human_in_the_loop/wait-user-input.ipynb

@@ -397,7 +397,8 @@
     "# We define a fake node to ask the human\n",
     "def ask_human(state):\n",
     "    tool_call_id = state[\"messages\"][-1].tool_calls[0][\"id\"]\n",
-    "    location = interrupt(\"Please provide your location:\")\n",
+    "    ask = AskHuman.model_validate(state[\"messages\"][-1].tool_calls[0][\"args\"])\n",
+    "    location = interrupt(ask.question)\n",
     "    tool_message = [{\"tool_call_id\": tool_call_id, \"type\": \"tool\", \"content\": location}]\n",
     "    return {\"messages\": tool_message}\n",
     "\n",
@@ -491,7 +492,7 @@
     "        \"messages\": [\n",
     "            (\n",
     "                \"user\",\n",
-    "                \"Use the search tool to ask the user where they are, then look up the weather there\",\n",
+    "                \"Ask the user where they are, then look up the weather there\",\n",
     "            )\n",
     "        ]\n",
     "    },\n",

docs/docs/how-tos/index.md

@@ -163,6 +163,7 @@ These guides show how to use the prebuilt ReAct agent:
 - [How to add human-in-the-loop processes to a ReAct agent](create-react-agent-hitl.ipynb)
 - [How to return structured output from a ReAct agent](create-react-agent-structured-output.ipynb)
 - [How to add semantic search for long-term memory to a ReAct agent](memory/semantic-search.ipynb#using-in-create-react-agent)
+- [How to manage message history in a ReAct agent](create-react-agent-manage-message-history.ipynb)
 
 Interested in further customizing the ReAct agent? This guide provides an
 overview of its underlying implementation to help you customize for your own needs:
@@ -198,15 +199,17 @@ Learn how to set up your app for deployment to LangGraph Platform:
 - [How to test locally](../cloud/deployment/test_locally.md)
 - [How to rebuild graph at runtime](../cloud/deployment/graph_rebuild.md)
 - [How to use LangGraph Platform to deploy CrewAI, AutoGen, and other frameworks](autogen-langgraph-platform.ipynb)
-- [How to integrate LangGraph into your React application](../cloud/how-tos/use_stream_react.md)
 
 ### Deployment
 
-LangGraph applications can be deployed using LangGraph Cloud, which provides a range of services to help you deploy, manage, and scale your applications.
+LangGraph applications can be deployed using LangGraph Platform, which provides a range of services to help you deploy, manage, and scale your applications.
 
-- [How to deploy to LangGraph cloud](../cloud/deployment/cloud.md)
-- [How to deploy to a self-hosted environment](./deploy-self-hosted.md)
+- [How to deploy to Cloud SaaS](../cloud/deployment/cloud.md)
+- [How to deploy the Self-Hosted Data Plane](../cloud/deployment/self_hosted_data_plane.md)
+- [How to deploy the Self-Hosted Control Plane](../cloud/deployment/self_hosted_control_plane.md)
+- [How to deploy a Standalone Container](../cloud/deployment/standalone_container.md)
 - [How to interact with the deployment using RemoteGraph](./use-remote-graph.md)
+- [How to add TTLs to your LangGraph application](./ttl/configure_ttl.md)
 
 ### Authentication & Access Control
 
@@ -257,6 +260,13 @@ Streaming the results of your LLM application is vital for ensuring a good user
 - [How to stream in debug mode](../cloud/how-tos/stream_debug.md)
 - [How to stream multiple modes](../cloud/how-tos/stream_multiple.md)
 
+### Frontend and Generative UI
+
+With LangGraph Platform you can integrate LangGraph agents into your React applications and colocate UI components with your agent code. 
+
+- [How to integrate LangGraph into your React application](../cloud/how-tos/use_stream_react.md)
+- [How to implement Generative User Interfaces with LangGraph](../cloud/how-tos/generative_ui_react.md)
+
 ### Human-in-the-loop
 
 When designing complex graphs, relying entirely on the LLM for decision-making can be risky, particularly when it involves tools that interact with files, APIs, or databases. These interactions may lead to unintended data access or modifications, depending on the use case. To mitigate these risks, LangGraph allows you to integrate human-in-the-loop behavior, ensuring your LLM applications operate as intended without undesirable outcomes.
@@ -294,6 +304,7 @@ LangGraph Studio is a built-in UI for visualizing, testing, and debugging your a
 - [How to interact with threads in LangGraph Studio](../cloud/how-tos/threads_studio.md)
 - [How to add nodes as dataset examples in LangGraph Studio](../cloud/how-tos/datasets_studio.md)
 - [How to engineer prompts in LangGraph Studio](../cloud/how-tos/iterate_graph_studio.md)
+- [How to test your agent against remote traces](../cloud/how-tos/clone_traces_studio.md)
 
 ## Troubleshooting
 

docs/docs/how-tos/memory/add-summary-conversation-history.ipynb

@@ -10,6 +10,7 @@
     "One of the most common use cases for persistence is to use it to keep track of conversation history. This is great - it makes it easy to continue conversations. As conversations get longer and longer, however, this conversation history can build up and take up more and more of the context window. This can often be undesirable as it leads to more expensive and longer calls to the LLM, and potentially ones that error. One way to work around that is to create a summary of the conversation to date, and use that with the past N messages. This guide will go through an example of how to do that.\n",
     "\n",
     "This will involve a few steps:\n",
+    "\n",
     "- Check if the conversation is too long (can be done by checking number of messages or length of messages)\n",
     "- If yes, the create summary (will need a prompt for this)\n",
     "- Then remove all except the last N messages\n",
@@ -98,7 +99,7 @@
     "from typing import Literal\n",
     "\n",
     "from langchain_anthropic import ChatAnthropic\n",
-    "from langchain_core.messages import SystemMessage, RemoveMessage\n",
+    "from langchain_core.messages import SystemMessage, RemoveMessage, HumanMessage\n",
     "from langgraph.checkpoint.memory import MemorySaver\n",
     "from langgraph.graph import MessagesState, StateGraph, START, END\n",
     "\n",

docs/docs/how-tos/memory/manage-conversation-history.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# How to manage conversation history\n",
     "\n",
-    "One of the most common use cases for persistence is to use it to keep track of conversation history. This is great - it makes it easy to continue conversations. As conversations get longer and longer, however, this conversation history can build up and take up more and more of the context window. This can often be undesirable as it leads to more expensive and longer calls to the LLM, and potentially ones that error. In order to prevent this from happening, you need to probably manage the conversation history.\n",
+    "One of the most common use cases for persistence is to use it to keep track of conversation history. This is great - it makes it easy to continue conversations. As conversations get longer and longer, however, this conversation history can build up and take up more and more of the context window. This can often be undesirable as it leads to more expensive and longer calls to the LLM, and potentially ones that error. In order to prevent this from happening, you need to properly manage the conversation history.\n",
     "\n",
     "Note: this guide focuses on how to do this in LangGraph, where you can fully customize how this is done. If you want a more off-the-shelf solution, you can look into functionality provided in LangChain:\n",
     "\n",

docs/docs/how-tos/pass-run-time-values-to-tools.ipynb

@@ -38,7 +38,7 @@
     "    </p>\n",
     "</div> \n",
     "\n",
-    "The core technique the examples below is to **annotate** a parameter as \"injected\", meaning it will be injected by your program and should not be seen or populated by the LLM. Let the following codesnippet serve as a tl;dr:\n",
+    "The core technique in the examples below is to **annotate** a parameter as \"injected\", meaning it will be injected by your program and should not be seen or populated by the LLM. Let the following codesnippet serve as a tl;dr:\n",
     "\n",
     "```python\n",
     "from typing import Annotated\n",

docs/docs/how-tos/react-agent-structured-output.ipynb

@@ -65,7 +65,7 @@
     "\n",
     "**Pros and Cons**\n",
     "\n",
-    "The benefit to this format is that you only need one LLM, and can save money and latency because of this. The downside to this option is that it isn't guaranteed that the single LLM will call the correct tool when you want it to. We can help the LLM by setting `tool_choice` to `any` when we use `bind_tools` which forces the LLM to select at least one tool at every turn, but this is far from a fool proof strategy. In addition, another downside is that the agent might call *multiple* tools, so we need to check for this explicitly in our routing function (or if we are using OpenAI we an set `parallell_tool_calling=False` to ensure only one tool is called at a time).\n",
+    "The benefit to this format is that you only need one LLM, and can save money and latency because of this. The downside to this option is that it isn't guaranteed that the single LLM will call the correct tool when you want it to. We can help the LLM by setting `tool_choice` to `any` when we use `bind_tools` which forces the LLM to select at least one tool at every turn, but this is far from a foolproof strategy. In addition, another downside is that the agent might call *multiple* tools, so we need to check for this explicitly in our routing function (or if we are using OpenAI we can set `parallell_tool_calling=False` to ensure only one tool is called at a time).\n",
     "\n",
     "**Option 2**\n",
     "\n",

docs/docs/how-tos/state-model.ipynb

@@ -266,6 +266,235 @@
     "    print(\"An exception was raised because bad_node sets `a` to an integer.\")\n",
     "    print(e)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2270bc3c",
+   "metadata": {},
+   "source": [
+    "## Multiple Nodes\n",
+    "\n",
+    "Run-time validation will also work in a multi-node graph. In the example below `bad_node` updates `a` to an integer. \n",
+    "\n",
+    "Because run-time validation occurs on **inputs**, the validation error will occur when `ok_node` is called (not when `bad_node` returns an update to the state which is inconsistent with the schema)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d832cdcc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langgraph.graph import StateGraph, START, END\n",
+    "from typing_extensions import TypedDict\n",
+    "\n",
+    "from pydantic import BaseModel\n",
+    "\n",
+    "\n",
+    "# The overall state of the graph (this is the public state shared across nodes)\n",
+    "class OverallState(BaseModel):\n",
+    "    a: str\n",
+    "\n",
+    "\n",
+    "def bad_node(state: OverallState):\n",
+    "    return {\n",
+    "        \"a\": 123  # Invalid\n",
+    "    }\n",
+    "\n",
+    "\n",
+    "def ok_node(state: OverallState):\n",
+    "    return {\"a\": \"goodbye\"}\n",
+    "\n",
+    "\n",
+    "# Build the state graph\n",
+    "builder = StateGraph(OverallState)\n",
+    "builder.add_node(bad_node)\n",
+    "builder.add_node(ok_node)\n",
+    "builder.add_edge(START, \"bad_node\")\n",
+    "builder.add_edge(\"bad_node\", \"ok_node\")\n",
+    "builder.add_edge(\"ok_node\", END)\n",
+    "graph = builder.compile()\n",
+    "\n",
+    "# Test the graph with a valid input\n",
+    "try:\n",
+    "    graph.invoke({\"a\": \"hello\"})\n",
+    "except Exception as e:\n",
+    "    print(\"An exception was raised because bad_node sets `a` to an integer.\")\n",
+    "    print(e)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "456b1f77",
+   "metadata": {},
+   "source": [
+    "## Advanced Pydantic Model Usage\n",
+    "\n",
+    "This section covers more advanced topics when using Pydantic models with LangGraph.\n",
+    "\n",
+    "### Serialization Behavior\n",
+    "\n",
+    "When using Pydantic models as state schemas, it's important to understand how serialization works, especially when:\n",
+    "- Passing Pydantic objects as inputs\n",
+    "- Receiving outputs from the graph\n",
+    "- Working with nested Pydantic models\n",
+    "\n",
+    "Let's see these behaviors in action:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0e919cdc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langgraph.graph import StateGraph, START, END\n",
+    "from pydantic import BaseModel\n",
+    "\n",
+    "\n",
+    "class NestedModel(BaseModel):\n",
+    "    value: str\n",
+    "\n",
+    "\n",
+    "class ComplexState(BaseModel):\n",
+    "    text: str\n",
+    "    count: int\n",
+    "    nested: NestedModel\n",
+    "\n",
+    "\n",
+    "def process_node(state: ComplexState):\n",
+    "    # Node receives a validated Pydantic object\n",
+    "    print(f\"Input state type: {type(state)}\")\n",
+    "    print(f\"Nested type: {type(state.nested)}\")\n",
+    "\n",
+    "    # Return a dictionary update\n",
+    "    return {\"text\": state.text + \" processed\", \"count\": state.count + 1}\n",
+    "\n",
+    "\n",
+    "# Build the graph\n",
+    "builder = StateGraph(ComplexState)\n",
+    "builder.add_node(\"process\", process_node)\n",
+    "builder.add_edge(START, \"process\")\n",
+    "builder.add_edge(\"process\", END)\n",
+    "graph = builder.compile()\n",
+    "\n",
+    "# Create a Pydantic instance for input\n",
+    "input_state = ComplexState(text=\"hello\", count=0, nested=NestedModel(value=\"test\"))\n",
+    "print(f\"Input object type: {type(input_state)}\")\n",
+    "\n",
+    "# Invoke graph with a Pydantic instance\n",
+    "result = graph.invoke(input_state)\n",
+    "print(f\"Output type: {type(result)}\")\n",
+    "print(f\"Output content: {result}\")\n",
+    "\n",
+    "# Convert back to Pydantic model if needed\n",
+    "output_model = ComplexState(**result)\n",
+    "print(f\"Converted back to Pydantic: {type(output_model)}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f13f28ce",
+   "metadata": {},
+   "source": [
+    "### Runtime Type Coercion\n",
+    "\n",
+    "Pydantic performs runtime type coercion for certain data types. This can be helpful but also lead to unexpected behavior if you're not aware of it."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "faf59316",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langgraph.graph import StateGraph, START, END\n",
+    "from pydantic import BaseModel\n",
+    "\n",
+    "\n",
+    "class CoercionExample(BaseModel):\n",
+    "    # Pydantic will coerce string numbers to integers\n",
+    "    number: int\n",
+    "    # Pydantic will parse string booleans to bool\n",
+    "    flag: bool\n",
+    "\n",
+    "\n",
+    "def inspect_node(state: CoercionExample):\n",
+    "    print(f\"number: {state.number} (type: {type(state.number)})\")\n",
+    "    print(f\"flag: {state.flag} (type: {type(state.flag)})\")\n",
+    "    return {}\n",
+    "\n",
+    "\n",
+    "builder = StateGraph(CoercionExample)\n",
+    "builder.add_node(\"inspect\", inspect_node)\n",
+    "builder.add_edge(START, \"inspect\")\n",
+    "builder.add_edge(\"inspect\", END)\n",
+    "graph = builder.compile()\n",
+    "\n",
+    "# Demonstrate coercion with string inputs that will be converted\n",
+    "result = graph.invoke({\"number\": \"42\", \"flag\": \"true\"})\n",
+    "\n",
+    "# This would fail with a validation error\n",
+    "try:\n",
+    "    graph.invoke({\"number\": \"not-a-number\", \"flag\": \"true\"})\n",
+    "except Exception as e:\n",
+    "    print(f\"\\nExpected validation error: {e}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2844475b",
+   "metadata": {},
+   "source": [
+    "### Working with Message Models\n",
+    "\n",
+    "When working with LangChain message types in your state schema, there are important considerations for serialization. You should use `AnyMessage` (rather than `BaseMessage`) for proper serialization/deserialization when using message objects over the wire:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bd0734b0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langgraph.graph import StateGraph, START, END\n",
+    "from pydantic import BaseModel\n",
+    "from langchain_core.messages import HumanMessage, AIMessage, AnyMessage\n",
+    "from typing import List\n",
+    "\n",
+    "\n",
+    "class ChatState(BaseModel):\n",
+    "    messages: List[AnyMessage]\n",
+    "    context: str\n",
+    "\n",
+    "\n",
+    "def add_message(state: ChatState):\n",
+    "    return {\"messages\": state.messages + [AIMessage(content=\"Hello there!\")]}\n",
+    "\n",
+    "\n",
+    "builder = StateGraph(ChatState)\n",
+    "builder.add_node(\"add_message\", add_message)\n",
+    "builder.add_edge(START, \"add_message\")\n",
+    "builder.add_edge(\"add_message\", END)\n",
+    "graph = builder.compile()\n",
+    "\n",
+    "# Create input with a message\n",
+    "initial_state = ChatState(\n",
+    "    messages=[HumanMessage(content=\"Hi\")], context=\"Customer support chat\"\n",
+    ")\n",
+    "\n",
+    "result = graph.invoke(initial_state)\n",
+    "print(f\"Output: {result}\")\n",
+    "\n",
+    "# Convert back to Pydantic model to see message types\n",
+    "output_model = ChatState(**result)\n",
+    "for i, msg in enumerate(output_model.messages):\n",
+    "    print(f\"Message {i}: {type(msg).__name__} - {msg.content}\")"
+   ]
   }
  ],
  "metadata": {

docs/docs/how-tos/stream-multiple.ipynb

@@ -1,210 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "3631f2b9-aa79-472e-a9d6-9125a90ee704",
-   "metadata": {},
-   "source": [
-    "# How to configure multiple streaming modes at the same time"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "858c7499-0c92-40a9-bd95-e5a5a5817e92",
-   "metadata": {},
-   "source": [
-    "This guide covers how to configure multiple streaming modes at the same time."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "7c2f84f1-0751-4779-97d4-5cbb286093b7",
-   "metadata": {},
-   "source": [
-    "## Setup\n",
-    "\n",
-    "First, let's install the required packages and set our API keys"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "6b4285e4-7434-4971-bde0-aabceef8ee7e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install -U langgraph langchain-openai langchain-community"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "f7f9f24a-e3d0-422b-8924-47950b2facd6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "\n",
-    "def _set_env(var: str):\n",
-    "    if not os.environ.get(var):\n",
-    "        os.environ[var] = getpass.getpass(f\"{var}: \")\n",
-    "\n",
-    "\n",
-    "_set_env(\"OPENAI_API_KEY\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "4e48aa9e",
-   "metadata": {},
-   "source": [
-    "<div class=\"admonition tip\">\n",
-    "    <p class=\"admonition-title\">Set up <a href=\"https://smith.langchain.com\">LangSmith</a> for LangGraph development</p>\n",
-    "    <p style=\"padding-top: 5px;\">\n",
-    "        Sign up for LangSmith to quickly spot issues and improve the performance of your LangGraph projects. LangSmith lets you use trace data to debug, test, and monitor your LLM apps built with LangGraph — read more about how to get started <a href=\"https://docs.smith.langchain.com\">here</a>. \n",
-    "    </p>\n",
-    "</div>"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "cc82c21f",
-   "metadata": {},
-   "source": [
-    "## Define the graph\n",
-    "\n",
-    "We'll be using a simple ReAct agent for this guide."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "85cf2e23-29f2-40cc-b302-5377b3b49da9",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from typing import Literal\n",
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "from langchain_core.runnables import ConfigurableField\n",
-    "from langchain_core.tools import tool\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "from langgraph.prebuilt import create_react_agent\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "def get_weather(city: Literal[\"nyc\", \"sf\"]):\n",
-    "    \"\"\"Use this to get weather information.\"\"\"\n",
-    "    if city == \"nyc\":\n",
-    "        return \"It might be cloudy in nyc\"\n",
-    "    elif city == \"sf\":\n",
-    "        return \"It's always sunny in sf\"\n",
-    "    else:\n",
-    "        raise AssertionError(\"Unknown city\")\n",
-    "\n",
-    "\n",
-    "tools = [get_weather]\n",
-    "\n",
-    "model = ChatOpenAI(model_name=\"gpt-4o\", temperature=0)\n",
-    "graph = create_react_agent(model, tools)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "48a7751c-3f06-452b-89f4-70267e4dd305",
-   "metadata": {},
-   "source": [
-    "## Stream multiple"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "e9e9ffb0-2cd5-466f-b70b-b6ed51b852d1",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task', 'timestamp': '2024-06-25T16:12:29.144117+00:00', 'step': 1, 'payload': {'id': '8399d8fd-4b28-515a-b0e9-1679557c0953', 'name': 'agent', 'input': {'messages': [HumanMessage(content=\"what's the weather in sf\", id='44ff9154-9485-49c9-b679-791314cc19e3')], 'is_last_step': False}, 'triggers': ['start:agent']}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: updates...\n",
-      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_gZEyPpcgwnzsnee1HH4geKmB', 'function': {'arguments': '{\"city\":\"sf\"}', 'name': 'get_weather'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 57, 'total_tokens': 71}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_3e7d703517', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-37ca191f-f68f-4a70-8924-a40f90c8c0ed-0', tool_calls=[{'name': 'get_weather', 'args': {'city': 'sf'}, 'id': 'call_gZEyPpcgwnzsnee1HH4geKmB'}], usage_metadata={'input_tokens': 57, 'output_tokens': 14, 'total_tokens': 71})]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task_result', 'timestamp': '2024-06-25T16:12:29.802322+00:00', 'step': 1, 'payload': {'id': '8399d8fd-4b28-515a-b0e9-1679557c0953', 'name': 'agent', 'result': [('messages', [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_gZEyPpcgwnzsnee1HH4geKmB', 'function': {'arguments': '{\"city\":\"sf\"}', 'name': 'get_weather'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 57, 'total_tokens': 71}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_3e7d703517', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-37ca191f-f68f-4a70-8924-a40f90c8c0ed-0', tool_calls=[{'name': 'get_weather', 'args': {'city': 'sf'}, 'id': 'call_gZEyPpcgwnzsnee1HH4geKmB'}], usage_metadata={'input_tokens': 57, 'output_tokens': 14, 'total_tokens': 71})])]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task', 'timestamp': '2024-06-25T16:12:29.802738+00:00', 'step': 2, 'payload': {'id': 'f22971bf-6eff-55a2-84ab-fb97f629b133', 'name': 'tools', 'input': {'messages': [HumanMessage(content=\"what's the weather in sf\", id='44ff9154-9485-49c9-b679-791314cc19e3'), AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_gZEyPpcgwnzsnee1HH4geKmB', 'function': {'arguments': '{\"city\":\"sf\"}', 'name': 'get_weather'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 57, 'total_tokens': 71}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_3e7d703517', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-37ca191f-f68f-4a70-8924-a40f90c8c0ed-0', tool_calls=[{'name': 'get_weather', 'args': {'city': 'sf'}, 'id': 'call_gZEyPpcgwnzsnee1HH4geKmB'}], usage_metadata={'input_tokens': 57, 'output_tokens': 14, 'total_tokens': 71})], 'is_last_step': False}, 'triggers': ['branch:agent:should_continue:tools']}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: updates...\n",
-      "{'tools': {'messages': [ToolMessage(content=\"It's always sunny in sf\", name='get_weather', tool_call_id='call_gZEyPpcgwnzsnee1HH4geKmB')]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task_result', 'timestamp': '2024-06-25T16:12:29.806676+00:00', 'step': 2, 'payload': {'id': 'f22971bf-6eff-55a2-84ab-fb97f629b133', 'name': 'tools', 'result': [('messages', [ToolMessage(content=\"It's always sunny in sf\", name='get_weather', tool_call_id='call_gZEyPpcgwnzsnee1HH4geKmB')])]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task', 'timestamp': '2024-06-25T16:12:29.807014+00:00', 'step': 3, 'payload': {'id': '3e1a91b9-b94c-56a7-ace5-6fd8ee73fe8d', 'name': 'agent', 'input': {'messages': [HumanMessage(content=\"what's the weather in sf\", id='44ff9154-9485-49c9-b679-791314cc19e3'), AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_gZEyPpcgwnzsnee1HH4geKmB', 'function': {'arguments': '{\"city\":\"sf\"}', 'name': 'get_weather'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 57, 'total_tokens': 71}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_3e7d703517', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-37ca191f-f68f-4a70-8924-a40f90c8c0ed-0', tool_calls=[{'name': 'get_weather', 'args': {'city': 'sf'}, 'id': 'call_gZEyPpcgwnzsnee1HH4geKmB'}], usage_metadata={'input_tokens': 57, 'output_tokens': 14, 'total_tokens': 71}), ToolMessage(content=\"It's always sunny in sf\", name='get_weather', id='afc3ceaa-6663-4f7a-b874-e77e5515b175', tool_call_id='call_gZEyPpcgwnzsnee1HH4geKmB')], 'is_last_step': False}, 'triggers': ['tools']}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: updates...\n",
-      "{'agent': {'messages': [AIMessage(content='The weather in San Francisco is currently sunny.', response_metadata={'token_usage': {'completion_tokens': 10, 'prompt_tokens': 84, 'total_tokens': 94}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_3e7d703517', 'finish_reason': 'stop', 'logprobs': None}, id='run-575efeca-fdeb-4b4f-80f8-08ff177c34a5-0', usage_metadata={'input_tokens': 84, 'output_tokens': 10, 'total_tokens': 94})]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task_result', 'timestamp': '2024-06-25T16:12:30.355658+00:00', 'step': 3, 'payload': {'id': '3e1a91b9-b94c-56a7-ace5-6fd8ee73fe8d', 'name': 'agent', 'result': [('messages', [AIMessage(content='The weather in San Francisco is currently sunny.', response_metadata={'token_usage': {'completion_tokens': 10, 'prompt_tokens': 84, 'total_tokens': 94}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_3e7d703517', 'finish_reason': 'stop', 'logprobs': None}, id='run-575efeca-fdeb-4b4f-80f8-08ff177c34a5-0', usage_metadata={'input_tokens': 84, 'output_tokens': 10, 'total_tokens': 94})])]}}\n",
-      "\n",
-      "\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "inputs = {\"messages\": [(\"human\", \"what's the weather in sf\")]}\n",
-    "async for event, chunk in graph.astream(inputs, stream_mode=[\"updates\", \"debug\"]):\n",
-    "    print(f\"Receiving new event of type: {event}...\")\n",
-    "    print(chunk)\n",
-    "    print(\"\\n\\n\")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/docs/how-tos/ttl/configure_ttl.md

@@ -0,0 +1,102 @@
+# How to add TTLs to your LangGraph application
+
+!!! tip "Prerequisites"
+
+    This guide assumes familiarity with the [LangGraph Platform](../../concepts/index.md#langgraph-platform), [Persistence](../../concepts/persistence.md), and [Cross-thread persistence](../../concepts/store.md) concepts.
+
+???+ note "LangGraph platform only"
+    
+    TTLs are only supported for LangGraph platform deployments. This guide does not apply to LangGraph OSS.
+
+The LangGraph Platform persists both [checkpoints](../../concepts/persistence.md#checkpoints) (thread state) and [cross-thread memories](../../concepts/persistence.md#memory-store) (store items). Configure Time-to-Live (TTL) policies in `langgraph.json` to automatically manage the lifecycle of this data, preventing indefinite accumulation.
+
+## Configuring Checkpoint TTL
+
+Checkpoints capture the state of conversation threads. Setting a TTL ensures old checkpoints and threads are automatically deleted.
+
+Add a `checkpointer.ttl` configuration to your `langgraph.json` file:
+
+```json
+{
+  "dependencies": ["."],
+  "graphs": {
+    "agent": "./agent.py:graph"
+  },
+  "checkpointer": {
+    "ttl": {
+      "strategy": "delete",
+      "sweep_interval_minutes": 60,
+      "default_ttl": 43200 
+    }
+  }
+}
+```
+
+*   `strategy`: Specifies the action taken on expiration. Currently, only `"delete"` is supported, which deletes all checkpoints in the thread upon expiration.
+*   `sweep_interval_minutes`: Defines how often, in minutes, the system checks for expired checkpoints.
+*   `default_ttl`: Sets the default lifespan of checkpoints in minutes (e.g., 43200 minutes = 30 days).
+
+## Configuring Store Item TTL
+
+Store items allow cross-thread data persistence. Configuring TTL for store items helps manage memory by removing stale data.
+
+Add a `store.ttl` configuration to your `langgraph.json` file:
+
+```json
+{
+  "dependencies": ["."],
+  "graphs": {
+    "agent": "./agent.py:graph"
+  },
+  "store": {
+    "ttl": {
+      "refresh_on_read": true,
+      "sweep_interval_minutes": 120,
+      "default_ttl": 10080
+    }
+  }
+}
+```
+
+*   `refresh_on_read`: (Optional, default `true`) If `true`, accessing an item via `get` or `search` resets its expiration timer. If `false`, TTL only refreshes on `put`.
+*   `sweep_interval_minutes`: (Optional) Defines how often, in minutes, the system checks for expired items. If omitted, no sweeping occurs.
+*   `default_ttl`: (Optional) Sets the default lifespan of store items in minutes (e.g., 10080 minutes = 7 days). If omitted, items do not expire by default.
+
+## Combining TTL Configurations
+
+You can configure TTLs for both checkpoints and store items in the same `langgraph.json` file to set different policies for each data type. Here is an example:
+
+```json
+{
+  "dependencies": ["."],
+  "graphs": {
+    "agent": "./agent.py:graph"
+  },
+  "checkpointer": {
+    "ttl": {
+      "strategy": "delete",
+      "sweep_interval_minutes": 60,
+      "default_ttl": 43200
+    }
+  },
+  "store": {
+    "ttl": {
+      "refresh_on_read": true,
+      "sweep_interval_minutes": 120,
+      "default_ttl": 10080
+    }
+  }
+}
+```
+
+## Runtime Overrides
+
+The default `store.ttl` settings from `langgraph.json` can be overridden at runtime by providing specific TTL values in SDK method calls like `get`, `put`, and `search`.
+
+## Deployment Process
+
+After configuring TTLs in `langgraph.json`, deploy or restart your LangGraph application for the changes to take effect. Use `langgraph dev` for local development or `langgraph up` for Docker deployment.
+
+
+See the [langgraph.json CLI reference][configuration-file] for more details on the other configurable options.
+

docs/docs/how-tos/update-state-from-tools.ipynb

@@ -210,7 +210,7 @@
    "id": "cbb06aea-6654-4245-91f8-af6e8f2b5377",
    "metadata": {},
    "source": [
-    "Let's now add personalization: we'll respond differently to the user based on the state values AFTER the state has been updated from the tool. To achieve this, let's define a function that will dynamically construct the system prompt based on the graph state. It will be called ever time the LLM is called and the function output will be passed to the LLM:"
+    "Let's now add personalization: we'll respond differently to the user based on the state values AFTER the state has been updated from the tool. To achieve this, let's define a function that will dynamically construct the system prompt based on the graph state. It will be called every time the LLM is called and the function output will be passed to the LLM:"
    ]
   },
   {

docs/docs/index.md

@@ -3,4 +3,26 @@ hide_comments: true
 title: Home
 ---
 
+<script>
+  // This script only runs in MkDocs, not on GitHub
+  var hideGitHubVersion = function() {
+    document.querySelectorAll('.github-only').forEach(el => el.style.display = 'none');
+  };
+
+  // Handle both initial load and subsequent navigation
+  document.addEventListener('DOMContentLoaded', hideGitHubVersion);
+  document$.subscribe(hideGitHubVersion);
+</script>
+
+<p class="mkdocs-only">
+  <img class="logo-light" src="static/wordmark_dark.svg" alt="LangGraph Logo" width="80%">
+  <img class="logo-dark" src="static/wordmark_light.svg" alt="LangGraph Logo" width="80%">
+</p>
+
+<style>
+.md-content h1 {
+  display: none;
+}
+</style>
+
 {!../README.md!}

docs/docs/llms-txt-overview.md

@@ -0,0 +1,51 @@
+# LLMs-txt Overview
+
+## Overview
+
+Below you can find a list of documentation files in the [`llms.txt`](https://llmstxt.org/) format, specifically `llms.txt` and `llms-full.txt`. These files allow large language models (LLMs) and agents to access programming documentation and APIs, particularly useful within integrated development environments (IDEs).
+
+| Language Version | llms.txt                                                                                                   | llms-full.txt                                                                                                        |
+|------------------|------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------|
+| LangGraph Python | [https://langchain-ai.github.io/langgraph/llms.txt](https://langchain-ai.github.io/langgraph/llms.txt)     | [https://langchain-ai.github.io/langgraph/llms-full.txt](https://langchain-ai.github.io/langgraph/llms-full.txt)     |
+| LangGraph JS     | [https://langchain-ai.github.io/langgraphjs/llms.txt](https://langchain-ai.github.io/langgraphjs/llms.txt) | [https://langchain-ai.github.io/langgraphjs/llms-full.txt](https://langchain-ai.github.io/langgraphjs/llms-full.txt) |
+| LangChain Python | [https://python.langchain.com/llms.txt](https://python.langchain.com/llms.txt)                             | N/A                                                                                                                  |
+| LangChain JS     | [https://js.langchain.com/llms.txt](https://js.langchain.com/llms.txt)                                     | N/A                                                                                                                  |
+
+!!! info "Review the output"
+
+    Even with access to up-to-date documentation, current state-of-the-art models may not always generate correct code. Treat the generated code as a starting point, and always review it before shipping
+    code to production.
+
+## Differences Between `llms.txt` and `llms-full.txt`
+
+- **`llms.txt`** is an index file containing links with brief descriptions of the content. An LLM or agent must follow these links to access detailed information.
+
+- **`llms-full.txt`** includes all the detailed content directly in a single file, eliminating the need for additional navigation.
+
+A key consideration when using `llms-full.txt` is its size. For extensive documentation, this file may become too large to fit into an LLM's context window.
+
+## Using `llms.txt` via an MCP Server
+
+As of March 9, 2025, IDEs [do not yet have robust native support for `llms.txt`](https://x.com/jeremyphoward/status/1902109312216129905?t=1eHFv2vdNdAckajnug0_Vw&s=19). However, you can still use `llms.txt` effectively through an MCP server.
+
+### 🚀 Use the `mcpdoc` Server
+
+We provide an **MCP server** that was designed to serve documentation for LLMs and IDEs:
+
+👉 **[langchain-ai/mcpdoc GitHub Repository](https://github.com/langchain-ai/mcpdoc)**
+
+This MCP server allows integrating `llms.txt` into tools like **Cursor**, **Windsurf**, **Claude**, and **Claude Code**.
+
+📘 **Setup instructions and usage examples** are available in the repository.
+
+## Using `llms-full.txt`
+
+The LangGraph `llms-full.txt` file typically contains several hundred thousand tokens, exceeding the context window limitations of most LLMs. To effectively use this file:
+
+1. **With IDEs (e.g., Cursor, Windsurf)**:
+    - Add the `llms-full.txt` as custom documentation. The IDE will automatically chunk and index the content, implementing Retrieval-Augmented Generation (RAG).
+
+2. **Without IDE support**:
+    - Use a chat model with a large context window.
+    - Implement a RAG strategy to manage and query the documentation efficiently.
+

docs/docs/llms.txt

@@ -0,0 +1,204 @@
+# LangGraph
+
+## Tutorials
+
+[Learn the basics](https://langchain-ai.github.io/langgraph/tutorials/introduction/): LLM should read this page when needing to build a LangGraph chatbot or when learning about chat agents with memory, human-in-the-loop functionality, and state management. This page provides a comprehensive LangGraph quickstart tutorial covering building a support chatbot with web search capability, conversation memory, human review routing, custom state management, and time travel functionality to explore alternative conversation paths.
+
+[Local Deploy](https://langchain-ai.github.io/langgraph/tutorials/langgraph-platform/local-server/): LLM should read this page when setting up a LangGraph app locally using `langgraph dev` and troubleshooting LangGraph server deployment. This page contains a quickstart guide for launching a LangGraph server locally, including installation steps, app creation from templates, environment setup, API testing with Python/JS SDKs, and links to deployment options and further documentation.
+
+[Workflows and Agents](https://langchain-ai.github.io/langgraph/tutorials/workflows/): LLM should read this page when implementing agent systems, designing workflow architectures, or troubleshooting LLM orchestration strategies. The page covers patterns for LLM system design, comparing workflows (predefined paths) vs agents (dynamic control), with implementations of prompt chaining, parallelization, routing, orchestrator-worker, evaluator-optimizer, and agent patterns using both graph and functional APIs in LangGraph.
+
+## Concepts 
+
+[Concepts](https://langchain-ai.github.io/langgraph/concepts/): LLM should read this page when needing to understand LangGraph's key concepts or when planning to deploy LangGraph applications. Comprehensive guide covering LangGraph fundamentals (graph primitives, agents, multi-agent systems, breakpoints, persistence), features (time travel, memory, streaming), and LangGraph Platform deployment options (self-hosted, cloud, enterprise).
+
+[Agent architectures](https://langchain-ai.github.io/langgraph/concepts/agentic_concepts/): LLM should read this page when designing agent architectures, implementing control flows for LLM applications, or customizing agent behavior patterns. This page covers different LLM agent architectures including routers, tool calling agents (ReAct), structured outputs, memory systems, planning capabilities, and advanced customization options like human-in-the-loop, parallelization, subgraphs, and reflection mechanisms.
+
+[Application Structure](https://langchain-ai.github.io/langgraph/concepts/application_structure/): LLM should read this page when needing to understand LangGraph application structure, preparing to deploy a LangGraph application, or troubleshooting configuration issues. This page details the structure of LangGraph applications, including required components (graphs, langgraph.json config file, dependency files, optional .env), file organization patterns for Python/JavaScript projects, configuration file format with all supported fields, and how to specify dependencies, graphs, and environment variables.
+
+[Assistants](https://langchain-ai.github.io/langgraph/concepts/assistants/): LLM should read this page when looking for information about LangGraph assistants, understanding assistant configuration in LangGraph Platform, or learning about versioning agent configurations. This page explains LangGraph assistants, which allow developers to modify agent configurations (prompts, models, etc.) without changing graph logic, supports versioning for tracking changes, and is available only in LangGraph Platform (not open source).
+
+[Authentication & Access Control](https://langchain-ai.github.io/langgraph/concepts/auth/): LLM should read this page when implementing authentication in LangGraph Platform, designing access control for LangGraph applications, or troubleshooting security issues in LangGraph deployments. This page explains LangGraph's authentication and authorization system, covering the difference between authentication and authorization, system architecture, implementing custom auth handlers, common access patterns, and supported resources/actions for access control.
+
+[Bring Your Own Cloud (BYOC)](https://langchain-ai.github.io/langgraph/concepts/bring_your_own_cloud/): LLM should read this page when learning about LangGraph Platform deployment options, understanding Bring Your Own Cloud architecture, or managing deployments in AWS. This page explains LangGraph's BYOC deployment model, detailing how it separates control plane (managed by LangChain) from data plane (in customer's AWS account), outlines AWS requirements, infrastructure setup via Terraform, required permissions, and explains the deployment workflow.
+
+[Deployment Options](https://langchain-ai.github.io/langgraph/concepts/deployment_options/): LLM should read this page when needing information about LangGraph deployment options, comparing different deployment methods, or understanding LangGraph Platform plans. This page outlines four deployment options for LangGraph Platform: Self-Hosted Lite (available for all plans), Self-Hosted Enterprise (Enterprise plan only), Cloud SaaS (Plus and Enterprise plans), and Bring Your Own Cloud (Enterprise plan only, AWS-only).
+
+[Double Texting](https://langchain-ai.github.io/langgraph/concepts/double_texting/): LLM should read this page when handling concurrent user interactions in LangGraph Platform, implementing double-texting safeguards, or designing stateful conversation systems. This page explains four approaches to handling "double texting" in LangGraph (when users send a second message before the first completes): Reject, Enqueue, Interrupt, and Rollback, noting these features are currently only available in LangGraph Platform.
+
+[Durable Execution](https://langchain-ai.github.io/langgraph/concepts/durable_execution/): LLM should read this page when needing to understand durable execution in LangGraph, implementing workflow persistence, or troubleshooting workflow resumption. This page explains durable execution in LangGraph: how workflows save progress to resume later, requirements (checkpointers and thread IDs), determinism guidelines for consistent replay, using tasks to encapsulate non-deterministic operations, and approaches for pausing/resuming workflows.
+
+[FAQ](https://langchain-ai.github.io/langgraph/concepts/faq/): LLM should read this page when needing to understand differences between LangGraph and LangChain, exploring deployment options for LangGraph Platform, or determining compatibility with various LLMs. FAQ covering LangGraph basics, comparisons with other frameworks, deployment options (free self-hosted, Cloud SaaS, BYOC, Enterprise), compatibility with different LLMs including OSS models, and feature differences between open-source LangGraph and proprietary LangGraph Platform.
+
+[Functional API](https://langchain-ai.github.io/langgraph/concepts/functional_api/): LLM should read this page when implementing workflows with persistent state, adding human-in-the-loop features, or converting existing code to use LangGraph. The page documents LangGraph's Functional API, which allows adding persistence, memory, and human-in-the-loop capabilities with minimal code changes using @entrypoint and @task decorators, handling serialization requirements, state management, and common patterns for parallel execution and error handling.
+
+[Why LangGraph?](https://langchain-ai.github.io/langgraph/concepts/high_level/): LLM should read this page when understanding LangGraph's core capabilities, exploring LLM application infrastructure, or evaluating agent/workflow persistence options. LangGraph provides infrastructure for LLM applications with three key benefits: persistence for memory and human-in-the-loop capabilities, streaming of workflow events and LLM outputs, and tools for debugging and deployment via LangGraph Platform.
+
+[Human-in-the-loop](https://langchain-ai.github.io/langgraph/concepts/human_in_the_loop/): LLM should read this page when implementing human-in-the-loop workflows in LangGraph, designing approval systems with LLMs, or creating interactive multi-turn conversation agents. This page explains human-in-the-loop patterns in LangGraph using the interrupt function, showing how to pause graph execution for human review/input and resume with Command. Includes design patterns for approval workflows, state editing, tool call reviews, and multi-turn conversations, with code examples and warnings about execution flow and common pitfalls.
+
+[LangGraph CLI](https://langchain-ai.github.io/langgraph/concepts/langgraph_cli/): LLM should read this page when looking for information about LangGraph CLI installation or when needing to deploy a LangGraph API server locally. The page covers LangGraph CLI installation methods (Homebrew, pip), key commands (build, dev, up, dockerfile), and features like hot reloading, debugger support, and database management for running LangGraph servers.
+
+[Cloud SaaS](https://langchain-ai.github.io/langgraph/concepts/langgraph_cloud/): LLM should read this page when learning about LangGraph's Cloud SaaS offering, understanding deployment options for LangGraph Servers, or planning autoscaling infrastructure for LangGraph applications. This page describes LangGraph Cloud SaaS, a managed deployment service for LangGraph Servers with details on deployment types (Development/Production), revisions, persistence, autoscaling capabilities (up to 10 containers), LangSmith integration, IP whitelisting, and automatic deletion policies after 28 days of non-use.
+
+[LangGraph Platform](https://langchain-ai.github.io/langgraph/concepts/langgraph_platform/): LLM should read this page when seeking information about LangGraph Platform's components or evaluating production deployment options for agentic applications. The page details the LangGraph Platform, a commercial solution for deploying agentic applications, including its components (Server, Studio, CLI, SDK, Remote Graph) and key benefits like streaming support, background runs, long run handling, burstiness management, and human-in-the-loop capabilities.
+
+[LangGraph Server](https://langchain-ai.github.io/langgraph/concepts/langgraph_server/): LLM should read this page when developing applications with LangGraph Server, deploying agent-based applications, or integrating persistent state management in agent workflows. LangGraph Server provides an API for creating and managing agent applications with key features like streaming endpoints, background runs, task queues, persistence, webhooks, cron jobs, and monitoring capabilities through a structured system of assistants, threads, runs, and stores.
+
+[LangGraph Studio](https://langchain-ai.github.io/langgraph/concepts/langgraph_studio/): LLM should read this page when looking for information about LangGraph Studio features, needing to troubleshoot LangGraph Studio issues, or learning how to connect a LangGraph application to the Studio. LangGraph Studio is a specialized agent IDE for visualizing, interacting with, and debugging LLM applications, offering features such as graph visualization, state editing, assistant management, and integration with LangSmith, with instructions for connecting via deployed applications or local development servers, plus troubleshooting FAQs.
+
+[LangGraph Glossary](https://langchain-ai.github.io/langgraph/concepts/low_level/): LLM should read this page when needing to understand LangGraph terminology, implementing agent workflows as graphs, or developing modular multi-step AI systems. The page covers core LangGraph concepts including StateGraph, nodes, edges, state management, messaging, persistence, configuration, human-in-the-loop features, subgraphs, and visualization capabilities.
+
+[Memory](https://langchain-ai.github.io/langgraph/concepts/memory/): LLM should read this page when implementing memory systems for AI agents, managing conversation context across sessions, or designing systems that require both short-term and long-term information retention. This page explains memory systems in LangGraph, covering short-term (thread-scoped) memory for managing conversation history and long-term memory across threads, with techniques for handling long conversations, summarizing past interactions, and organizing persistent memories in namespaces.
+
+[Multi-agent Systems](https://langchain-ai.github.io/langgraph/concepts/multi_agent/): LLM should read this page when implementing multi-agent systems, troubleshooting complex agent architectures, or designing agent communication patterns. Multi-agent systems organize LLMs into modular architectures (network, supervisor, hierarchical, custom) with different communication patterns, using Command objects for handoffs between agents, and supporting various state management approaches.
+
+[Persistence](https://langchain-ai.github.io/langgraph/concepts/persistence/): LLM should read this page when needing to understand LangGraph persistence mechanisms, implementing stateful workflows, or managing conversation history across interactions. This page covers LangGraph's persistence features including checkpointers, threads, state snapshots, replay functionality, forking state, cross-thread memory via InMemoryStore, and semantic search capabilities for stored memories.
+
+[LangGraph Platform Plans](https://langchain-ai.github.io/langgraph/concepts/plans/): LLM should read this page when determining LangGraph Platform pricing tiers, comparing deployment options, or researching features available across different plans. This page outlines LangGraph Platform plans (Developer, Plus, Enterprise), detailing deployment options, usage limitations, feature availability, and pricing structure for agentic application deployment.
+
+[LangGraph Platform Architecture](https://langchain-ai.github.io/langgraph/concepts/platform_architecture/): LLM should read this page when needing to understand LangGraph Platform's technical architecture or troubleshooting deployment issues. The page details how LangGraph Platform uses Postgres for persistent storage of user/run data and Redis for worker communication (run cancellation, output streaming) and ephemeral metadata storage (retry attempts).
+
+[LangGraph's Runtime (Pregel)](https://langchain-ai.github.io/langgraph/concepts/pregel/): LLM should read this page when learning about LangGraph's runtime, implementing applications with Pregel directly, or understanding how LangGraph executes graph applications. Explains LangGraph's Pregel runtime which manages graph application execution through a three-phase process (Plan, Execution, Update), describes different channel types (LastValue, Topic, Context, BinaryOperatorAggregate), provides direct implementation examples, and contrasts the StateGraph API with the Functional API.
+
+[LangGraph Platform: Scalability & Resilience](https://langchain-ai.github.io/langgraph/concepts/scalability_and_resilience/): LLM should read this page when needing to understand LangGraph Platform's scaling capabilities, designing high-availability LangGraph deployments, or troubleshooting resilience issues. This page details LangGraph Platform's horizontal scaling features including stateless server instances, queue worker scaling, resilience mechanisms for handling crashes, and database failover strategies in Postgres and Redis.
+
+[LangGraph SDK](https://langchain-ai.github.io/langgraph/concepts/sdk/): LLM should read this page when looking for installation instructions for LangGraph SDK, needing to choose between sync and async Python clients, or requiring SDK API references. The page covers LangGraph SDK installation for Python and JS, provides API reference links, explains the difference between synchronous and asynchronous Python clients, and includes code examples for both client types.
+
+[Self-Hosted](https://langchain-ai.github.io/langgraph/concepts/self_hosted/): LLM should read this page when looking for LangGraph deployment options, understanding self-hosted versions, or seeking requirements for self-hosting LangGraph. This page details two self-hosted deployment options for LangGraph Platform: Self-Hosted Lite (limited to 1M nodes/year) and Self-Hosted Enterprise (full version requiring license). Includes requirements, deployment process using Redis/Postgres, Docker, and optional Kubernetes deployment via Helm chart.
+
+[Streaming](https://langchain-ai.github.io/langgraph/concepts/streaming/): LLM should read this page when implementing streaming features in LangGraph applications, understanding different streaming modes, or building responsive LLM applications. This page explains streaming in LangGraph, covering the main types (workflow progress, LLM tokens, custom updates) and streaming modes (values, updates, custom, messages, debug, events), with details on how to use multiple modes simultaneously and differences between LangGraph library and Platform implementations.
+
+[Template Applications](https://langchain-ai.github.io/langgraph/concepts/template_applications/): LLM should read this page when looking for LangGraph template applications, setting up a new LangGraph project, or finding reference implementations for agentic workflows. This page presents LangGraph template applications with installation requirements, available templates (including ReAct Agent, Memory Agent, Retrieval Agent, etc.), instructions for creating new apps using the CLI, deployment options, and links to further learning resources.
+
+[Time Travel ⏱️](https://langchain-ai.github.io/langgraph/concepts/time-travel/): LLM should read this page when debugging LLM-based agent behavior, analyzing decision-making paths, or exploring alternative execution branches in LangGraph. This page explains LangGraph's Time Travel debugging features: Replaying (reproducing past actions up to specific checkpoints) and Forking (creating alternative execution paths from specific points), with code examples for retrieving checkpoints, configuring replay, and creating forked states.
+
+## How Tos
+
+[How-to Guides](https://langchain-ai.github.io/langgraph/how-tos/): LLM should read this page when looking for specific implementation techniques in LangGraph or when trying to deploy LangGraph applications to production environments. This page contains an extensive collection of how-to guides for LangGraph, covering graph fundamentals, persistence, memory management, human-in-the-loop features, tool calling, multi-agent systems, streaming, and deployment options through LangGraph Platform.
+
+[How to implement handoffs between agents](https://langchain-ai.github.io/langgraph/how-tos/agent-handoffs/): LLM should read this page when implementing multi-agent systems that require agent coordination, when building systems with specialized agents that need to work together, or when needing to implement handoffs between agents. This page explains how to implement handoffs between agents in LangGraph using Command objects, both directly from agent nodes and through specialized handoff tools, with code examples for creating multi-agent systems.
+
+[How to run a graph asynchronously](https://langchain-ai.github.io/langgraph/how-tos/async/): LLM should read this page when needing to implement asynchronous graph execution in LangGraph or when optimizing IO-bound LLM applications. This page explains how to convert synchronous graphs to asynchronous in LangGraph, including updating node definitions with async/await, using StateGraph with TypedDict, implementing conditional edges, and streaming results.
+
+[How to integrate LangGraph with AutoGen, CrewAI, and other frameworks](https://langchain-ai.github.io/langgraph/how-tos/autogen-integration/): LLM should read this page when integrating LangGraph with other agent frameworks, building multi-agent systems, or adding persistence features to agents. The page demonstrates how to combine LangGraph with AutoGen by calling AutoGen agents inside LangGraph nodes, showing code examples for setting up the integration with memory and conversation persistence.
+
+[How to integrate LangGraph (functional API) with AutoGen, CrewAI, and other frameworks](https://langchain-ai.github.io/langgraph/how-tos/autogen-integration-functional/): LLM should read this page when integrating LangGraph with other agent frameworks, building multi-agent systems with different frameworks, or adding LangGraph features to existing agent systems. This page demonstrates how to integrate LangGraph's functional API with AutoGen, including code examples for creating a workflow that calls AutoGen agents, leveraging LangGraph's memory and persistence features.
+
+[How to create branches for parallel node execution](https://langchain-ai.github.io/langgraph/how-tos/branching/): LLM should read this page when needing to implement parallel node execution in LangGraph, optimizing graph performance, or handling conditional branching in workflows. This page explains how to create branches for parallel execution in LangGraph using fan-out/fan-in mechanisms, reducer functions for state accumulation, handling exceptions during parallel execution, and implementing conditional branching logic between nodes.
+
+[How to combine control flow and state updates with Command](https://langchain-ai.github.io/langgraph/how-tos/command): LLM should read this page when learning how to combine control flow with state updates in LangGraph, understanding Command objects, or navigating between parent graphs and subgraphs. This page explains how to use Command objects to simultaneously update state and control flow between nodes, demonstrates using Command.PARENT to navigate from subgraphs to parent graphs, and includes examples of implementing reducers for state updates across graph hierarchies.
+
+[How to add runtime configuration to your graph](https://langchain-ai.github.io/langgraph/how-tos/configuration/): LLM should read this page when implementing runtime configuration for LangGraph, adding model selection options to agents, or enabling dynamic system messages. This page demonstrates how to configure LangGraph at runtime, including selecting different LLMs dynamically and adding custom configuration options like system messages through the configurable dictionary.
+
+[How to use the pre-built ReAct agent](https://langchain-ai.github.io/langgraph/how-tos/create-react-agent/): LLM should read this page when implementing a ReAct agent, needing pre-built agent solutions, or learning how to integrate tools with LLM agents. This page covers how to use the pre-built ReAct agent in LangGraph, including setup instructions, creating a weather checking tool, implementing the agent architecture, and examples of running the agent with and without tool calls.
+
+[How to add human-in-the-loop processes to the prebuilt ReAct agent](https://langchain-ai.github.io/langgraph/how-tos/create-react-agent-hitl/): LLM should read this page when implementing human-in-the-loop processes for ReAct agents, debugging tool calls, or learning about interrupts in LangGraph. This guide demonstrates how to add human-in-the-loop functionality to prebuilt ReAct agents using interrupt_before=["tools"], working with MemorySaver checkpoints, and showing how to approve or edit tool calls before they execute.
+
+[How to add thread-level memory to a ReAct Agent](https://langchain-ai.github.io/langgraph/how-tos/create-react-agent-memory/): LLM should read this page when adding memory to ReAct agents, implementing thread-level persistence in LangGraph, or building stateful conversational agents. This guide demonstrates how to add memory to a ReAct agent using LangGraph's checkpointer interface, with code examples showing MemorySaver implementation, thread_id configuration, and persistent chat context across multiple interactions.
+
+[How to return structured output from the prebuilt ReAct agent](https://langchain-ai.github.io/langgraph/how-tos/create-react-agent-structured-output/): LLM should read this page when implementing structured output with ReAct agents, customizing agent response formats, or working with LangGraph agents. This page explains how to return structured output from prebuilt ReAct agents by providing a response_format parameter with a Pydantic schema, including examples with weather data and options for customizing the prompt.
+
+[How to add a custom system prompt to the prebuilt ReAct agent](https://langchain-ai.github.io/langgraph/how-tos/create-react-agent-system-prompt/): LLM should read this page when learning to customize ReAct agents, needing to add system prompts to agents, or working with LangGraph's prebuilt agents. This tutorial demonstrates how to add a custom system prompt to a prebuilt ReAct agent, with code examples showing model setup, tool creation, and using the prompt parameter in the create_react_agent function.
+
+[How to add cross-thread persistence to your graph](https://langchain-ai.github.io/langgraph/how-tos/cross-thread-persistence): LLM should read this page when needing to implement persistence across multiple threads in LangGraph, when storing user data between conversations, or when implementing shared memory in graph-based LLM applications. This page demonstrates how to use LangGraph's Store API to persist data across threads, including creating an InMemoryStore with embedding search capabilities, passing stores to graph nodes, and accessing user-specific memories in different conversation threads.
+
+[How to add cross-thread persistence (functional API)](https://langchain-ai.github.io/langgraph/how-tos/cross-thread-persistence-functional): LLM should read this page when needing to implement cross-thread persistence in LangGraph functional API, storing user data across different conversation threads, or creating shared memory between workflows. This page explains how to add cross-thread persistence to LangGraph using the Store interface, including defining a store, configuring the entrypoint decorator, and implementing a workflow that can store and retrieve user information across different conversation threads.
+
+[How to do a Self-hosted deployment of LangGraph](https://langchain-ai.github.io/langgraph/how-tos/deploy-self-hosted/): LLM should read this page when implementing a self-hosted deployment of LangGraph, configuring required environment variables, or building Docker images for LangGraph applications. This page explains how to deploy LangGraph applications using Docker, covering environment requirements (Redis, Postgres), how to build Docker images with the LangGraph CLI, configuration using environment variables, and deployment options using Docker or Docker Compose.
+
+[How to disable streaming for models that don't support it](https://langchain-ai.github.io/langgraph/how-tos/disable-streaming/): LLM should read this page when handling models that don't support streaming, implementing LangGraph with non-streaming models, or troubleshooting streaming errors with OpenAI's O1 models. This page explains how to use the disable_streaming=True parameter with ChatOpenAI to make non-streaming models work with LangGraph's astream_events API, with code examples showing the error case and proper implementation.
+
+[How to edit graph state](https://langchain-ai.github.io/langgraph/how-tos/human_in_the_loop/edit-graph-state/): LLM should read this page when needing to implement human intervention in LangGraph workflows, wanting to edit graph state during execution, or implementing breakpoints in agent systems. This page explains how to edit graph state in LangGraph using breakpoints, including implementing human-in-the-loop interactions, setting up interruptions before specific nodes, and updating state during agent execution.
+
+[How to Review Tool Calls](https://langchain-ai.github.io/langgraph/how-tos/human_in_the_loop/review-tool-calls/): LLM should read this page when implementing human review of tool calls, creating interactive agent workflows, or building approval systems for AI actions. This page explains how to implement human-in-the-loop review for tool calls in LangGraph, including approving tool calls, modifying tool calls manually, and providing natural language feedback to agents with complete code examples and explanations.
+
+[How to view and update past graph state](https://langchain-ai.github.io/langgraph/how-tos/human_in_the_loop/time-travel/): LLM should read this page when needing to access or modify past states in LangGraph, when debugging agent execution, or when implementing user interventions in agent workflows. This page demonstrates how to view and update past graph states in LangGraph using get_state and update_state methods, with examples of replaying execution from checkpoints and branching workflows.
+
+[How to wait for user input using interrupt](https://langchain-ai.github.io/langgraph/how-tos/human_in_the_loop/wait-user-input/): LLM should read this page when implementing wait-for-user functions in LangGraph, implementing human-in-the-loop interactions, or learning how to use the interrupt() function. This page explains how to pause graph execution to collect user input using LangGraph's interrupt() function, with examples of simple feedback collection and more complex agent interactions that ask clarifying questions.
+
+[How to define input/output schema for your graph](https://langchain-ai.github.io/langgraph/how-tos/input_output_schema/): LLM should read this page when needing to define separate input/output schemas for LangGraph, implementing schema-based data filtering, or understanding schema definitions in StateGraph. This page explains how to define distinct input and output schemas for a StateGraph, showing how input schema validates the provided data structure while output schema filters internal data to return only relevant information, with code examples demonstrating implementation.
+
+[How to handle large numbers of tools](https://langchain-ai.github.io/langgraph/how-tos/many-tools/): LLM should read this page when handling large tool collections, implementing dynamic tool selection, or creating retrieval-based tool management in LangGraph. This page demonstrates how to manage large numbers of tools by using vector search to dynamically select relevant tools based on user queries, implementing tool selection nodes in LangGraph, and handling tool selection errors with retry mechanisms.
+
+[How to create map-reduce branches for parallel execution](https://langchain-ai.github.io/langgraph/how-tos/map-reduce/): LLM should read this page when learning to implement parallel execution in LangGraph, creating map-reduce operations, or handling dynamic task decomposition. This guide explains how to use LangGraph's Send API to create map-reduce workflows, breaking tasks into parallel sub-tasks and recombining results, with examples showing joke generation across multiple subjects.
+
+[How to add summary of the conversation history](https://langchain-ai.github.io/langgraph/how-tos/memory/add-summary-conversation-history/): LLM should read this page when implementing conversation summarization, managing context windows, or building chatbots with memory management. This page demonstrates how to add summary functionality to conversation history using LangGraph, including checking conversation length, creating summaries, and removing old messages while maintaining context.
+
+[How to delete messages](https://langchain-ai.github.io/langgraph/how-tos/memory/delete-messages): LLM should read this page when attempting to manage message history in LangGraph, needing to delete specific messages from conversational state, or implementing memory management in LLM applications. This page explains how to delete messages from a LangGraph application using RemoveMessage modifiers, covering both manual deletion with message IDs and programmatic deletion within graph logic to maintain conversation history limits.
+
+[How to manage conversation history](https://langchain-ai.github.io/langgraph/how-tos/memory/manage-conversation-history/): LLM should read this page when managing conversation history in LangGraph, preventing context window issues, or implementing custom message filtering. This page explains how to manage conversation history in LangGraph to prevent context window overflow by implementing message filtering functions that control which messages are sent to the LLM.
+
+[How to add semantic search to your agent's memory](https://langchain-ai.github.io/langgraph/how-tos/memory/semantic-search/): LLM should read this page when implementing semantic search in agent memory, enabling memory-aware AI assistants, or configuring advanced memory retrieval systems. This page demonstrates how to add semantic search to LangGraph agent memory stores, covering basic setup with embeddings, storing memories, searching by semantic similarity, integrating memory in agents and ReAct agents, and advanced usage like multi-vector indexing and selective memory indexing.
+
+[How to add multi-turn conversation in a multi-agent application](https://langchain-ai.github.io/langgraph/how-tos/multi-agent-multi-turn-convo/): LLM should read this page when implementing multi-turn conversations between agents, creating interactive agent systems with human input, or learning about langgraph interrupts and agent handoffs. This page demonstrates how to build a multi-agent system with multi-turn conversations, including human-in-the-loop interactions, agent handoffs, and state management using LangGraph, Command objects, and interrupts.
+
+[How to add multi-turn conversation in a multi-agent application (functional API)](https://langchain-ai.github.io/langgraph/how-tos/multi-agent-multi-turn-convo-functional/): LLM should read this page when building multi-turn conversational agents, implementing agent-to-agent handoffs, or using interrupts to collect user input in LangGraph. This guide demonstrates how to create a multi-agent system with multi-turn conversations using LangGraph's functional API, featuring agent handoffs, interrupt mechanics for user input, and a complete example of travel and hotel advisor agents that can transfer control between each other.
+
+[How to build a multi-agent network](https://langchain-ai.github.io/langgraph/how-tos/multi-agent-network/): LLM should read this page when implementing multi-agent networks, setting up agent communication via handoffs, or building travel assistance agents. This page explains how to create a fully-connected multi-agent network with LangGraph where agents can communicate with each other via handoffs, including custom agent implementation and using prebuilt ReAct agents with tools.
+
+[How to build a multi-agent network (functional API)](https://langchain-ai.github.io/langgraph/how-tos/multi-agent-network-functional/): LLM should read this page when building multi-agent systems, implementing agent handoffs between specialists, or creating fully-connected agent networks. This guide demonstrates how to create a multi-agent network using LangGraph's functional API, with tasks for individual agents and entrypoint functions to manage agent handoffs based on tool calls.
+
+[How to add node retry policies](https://langchain-ai.github.io/langgraph/how-tos/node-retries/): LLM should read this page when implementing error handling in LangGraph nodes, configuring API retry mechanisms, or troubleshooting node failures in graph workflows. Shows how to add custom retry policies to LangGraph nodes, including specifying which exceptions to retry on, setting max attempts, intervals, backoff factors, and implementing different retry behaviors for different node types.
+
+[How to pass config to tools](https://langchain-ai.github.io/langgraph/how-tos/pass-config-to-tools/): LLM should read this page when implementing secure tool configuration in LangChain, passing user-specific parameters to tools, or configuring tools with runtime values. This page explains how to pass configuration to LangChain tools using RunnableConfig, allowing application-controlled values (like user IDs) to be securely passed to tools without LLM control, with examples of implementing tools that access user-specific data.
+
+[How to pass private state between nodes](https://langchain-ai.github.io/langgraph/how-tos/pass_private_state/): LLM should read this page when implementing data sharing between specific nodes in LangGraph, handling private state in graph workflows, or designing multi-node sequential processes with selective data visibility. This page demonstrates how to pass private data between specific nodes in a LangGraph without making it part of the main schema, using typed dictionaries to define both public and private states, and showing a three-node example where private data flows only between the first two nodes.
+
+[How to add thread-level persistence to your graph](https://langchain-ai.github.io/langgraph/how-tos/persistence/): LLM should read this page when implementing persistence in LangGraph, needing to preserve context across user interactions, or learning about thread-level state management. This page explains how to add thread-level persistence to LangGraph applications using MemorySaver, including code examples for creating stateful conversations where context is maintained across multiple interactions.
+
+[How to add thread-level persistence (functional API)](https://langchain-ai.github.io/langgraph/how-tos/persistence-functional/): LLM should read this page when implementing thread-level persistence in LangGraph, creating conversational agents with memory, or using functional API with state management. This page explains how to add thread-level persistence to LangGraph functional API workflows using checkpointers, including code examples for creating a simple chatbot with memory across conversation turns.
+
+[How to use MongoDB checkpointer for persistence](https://langchain-ai.github.io/langgraph/how-tos/persistence_mongodb/): LLM should read this page when implementing persistence in LangGraph agents, setting up MongoDB for state checkpointing, or working with MongoDB connections in LangGraph applications. This page explains how to use the MongoDB checkpointer for LangGraph persistence, covering connection methods (direct, client-based, async), basic setup requirements, and practical examples of saving and retrieving agent state between interactions.
+
+[How to use Postgres checkpointer for persistence](https://langchain-ai.github.io/langgraph/how-tos/persistence_postgres/): LLM should read this page when setting up persistence for LangGraph agents, implementing PostgreSQL as a checkpoint storage backend, or working with either synchronous or asynchronous database connections. This page details how to use PostgreSQL for persisting LangGraph agent state, covering setup and configuration of PostgresSaver and AsyncPostgresSaver with different connection methods (pool, direct connection, connection string).
+
+[How to create a custom checkpointer using Redis](https://langchain-ai.github.io/langgraph/how-tos/persistence_redis/): LLM should read this page when implementing persistence in LangGraph applications, creating custom checkpoint mechanisms for agents, or working with Redis as a storage backend. This page demonstrates how to create custom checkpointers for LangGraph agents using Redis, including implementations for both synchronous and asynchronous interfaces that save and retrieve agent state.
+
+[How to create a ReAct agent from scratch](https://langchain-ai.github.io/langgraph/how-tos/react-agent-from-scratch/): LLM should read this page when needing to create a custom ReAct agent, wanting more control than prebuilt agents, or implementing ReAct from scratch with LangGraph. This guide shows how to build a custom ReAct agent using LangGraph, covering state definition, model/tool setup, node/edge configuration, graph creation, and testing the implementation with a weather query example.
+
+[How to create a ReAct agent from scratch (Functional API)](https://langchain-ai.github.io/langgraph/how-tos/react-agent-from-scratch-functional): LLM should read this page when creating a ReAct agent using LangGraph's Functional API, implementing tool-calling workflows, or building conversational agents with thread persistence. This page explains how to build a ReAct agent from scratch using LangGraph's Functional API, including model and tool setup, defining tasks for model/tool calling, creating an entrypoint for orchestration, and adding thread-level persistence for conversational experiences.
+
+[How to force tool-calling agent to structure output](https://langchain-ai.github.io/langgraph/how-tos/react-agent-structured-output): LLM should read this page when needing to force tool-calling agents to produce structured output, implementing consistent output formats for downstream software, or choosing between single-LLM vs two-LLM structured output approaches. The page explains two methods for implementing structured output with tool-calling agents: binding output as a tool (single LLM approach) and using two LLMs with structured output conversion, with code examples for both approaches using LangGraph.
+
+[How to create and control loops](https://langchain-ai.github.io/langgraph/how-tos/recursion-limit/): LLM should read this page when building loops in computational graphs, needing to implement termination conditions, or handling recursion limits in LangGraph. The page explains how to create graphs with loops using conditional edges for termination, set recursion limits, handle GraphRecursionError, and implement complex loops with branches.
+
+[How to review tool calls (Functional API)](https://langchain-ai.github.io/langgraph/how-tos/review-tool-calls-functional/): LLM should read this page when implementing human review of tool calls, creating ReAct agents with Functional API, or adding human-in-the-loop workflows. This page demonstrates how to review tool calls before execution in a ReAct agent using LangGraph's Functional API, including accepting, revising, or generating custom tool messages with the interrupt function.
+
+[How to pass custom run ID or set tags and metadata for graph runs in LangSmith](https://langchain-ai.github.io/langgraph/how-tos/run-id-langsmith/): LLM should read this page when needing to customize trace information in LangSmith for LangGraph runs or when debugging graph runs with custom identifiers. The page explains how to pass custom run_id, set tags, add metadata, and customize run names for LangGraph traces in LangSmith using RunnableConfig, with examples showing implementation with a ReAct agent.
+
+[How to create a sequence of steps](https://langchain-ai.github.io/langgraph/how-tos/sequence/): LLM should read this page when implementing sequential workflows in LangGraph, creating multi-step processes in applications, or learning about state management in graph-based systems. This page explains how to create sequences in LangGraph, covering methods for building sequential graphs using .add_node/.add_edge or the shorthand .add_sequence, defining state with TypedDict, creating nodes as functions that update state, and compiling/invoking graphs with examples.
+
+[How to use Pydantic model as graph state](https://langchain-ai.github.io/langgraph/how-tos/state-model): LLM should read this page when implementing Pydantic models for state validation in LangGraph, handling complex state schema definitions, or troubleshooting validation errors in graph nodes. This guide explains how to use Pydantic BaseModel as a state schema in LangGraph for runtime validation, covering basic implementation, limitations, validation behavior across multiple nodes, serialization patterns, type coercion, and working with message models.
+
+[How to update graph state from nodes](https://langchain-ai.github.io/langgraph/how-tos/state-reducers/): LLM should read this page when needing to update state in LangGraph, designing graphs with nodes that modify state, or implementing reducers for state management. This page explains how to define state schemas in LangGraph using TypedDict, how nodes can update state, and how to use reducers to control state updates, with specific examples using message handling.
+
+[How to stream](https://langchain-ai.github.io/langgraph/how-tos/streaming/): LLM should read this page when needing to implement streaming in LangGraph applications, understanding different streaming modes, or troubleshooting LLM response delivery. This page explains how to stream LLM outputs using LangGraph, covering different streaming modes (values, updates, custom, messages, debug), with code examples for each mode and how to combine multiple streaming modes.
+
+[How to stream data from within a tool](https://langchain-ai.github.io/langgraph/how-tos/streaming-events-from-within-tools/): LLM should read this page when implementing streaming functionality in tools, integrating LLM outputs with custom data streams, or developing LangGraph applications with real-time feedback. This page explains how to stream data from within tools using LangGraph, covering custom data streaming with stream_mode="custom", LLM token streaming with stream_mode="messages", and implementation approaches both with and without LangChain.
+
+[How to stream LLM tokens from specific nodes](https://langchain-ai.github.io/langgraph/how-tos/streaming-specific-nodes/): LLM should read this page when needing to filter token streaming from specific nodes in LangGraph, implementing selective streaming in multi-node workflows, or controlling which node outputs are displayed. Guide explains how to stream LLM tokens from specific nodes using stream_mode="messages" and filtering by the langgraph_node metadata field, with complete code examples for implementing this in StateGraph applications.
+
+[How to stream from subgraphs](https://langchain-ai.github.io/langgraph/how-tos/streaming-subgraphs/): LLM should read this page when needing to stream outputs from subgraphs in LangGraph, implementing nested graph streaming, or debugging hierarchical graph execution. This page explains how to stream outputs from subgraphs in LangGraph by using the subgraphs=True parameter in the parent graph's stream() method, with a complete code example showing the difference between regular streaming and subgraph streaming.
+
+[How to stream LLM tokens from your graph](https://langchain-ai.github.io/langgraph/how-tos/streaming-tokens): LLM should read this page when needing to stream LLM tokens from a LangGraph application, implementing custom token streaming, or filtering streamed outputs. This page explains how to stream individual LLM tokens from LangGraph nodes using graph.stream() with different stream_mode options, including examples with and without LangChain, async implementations, and how to filter streamed tokens using metadata.
+
+[How to use subgraphs](https://langchain-ai.github.io/langgraph/how-tos/subgraph/): LLM should read this page when building complex systems with subgraphs, implementing multi-agent systems, or needing to share state between parent graphs and subgraphs. The page explains two methods for using subgraphs: adding compiled subgraphs when schemas share keys, and invoking subgraphs via node functions when schemas differ, with code examples for both approaches.
+
+[How to add thread-level persistence to a subgraph](https://langchain-ai.github.io/langgraph/how-tos/subgraph-persistence/): LLM should read this page when implementing persistence in nested LangGraph architectures, adding thread-level storage to subgraphs, or debugging state propagation in LangGraph applications. This guide demonstrates how to add thread-level persistence to subgraphs by passing a checkpointer only to the parent graph during compilation, accessing persisted states from both parent and child graphs, and retrieving subgraph state using the proper configuration parameters.
+
+[How to transform inputs and outputs of a subgraph](https://langchain-ai.github.io/langgraph/how-tos/subgraph-transform-state/): LLM should read this page when needing to work with nested subgraphs, transforming state between parent and child graphs, or integrating independent state components in LangGraph. This page demonstrates how to transform inputs and outputs between parent graphs and subgraphs with different state structures, showing implementation of three nested graphs (parent, child, grandchild) with separate state dictionaries and transformation functions.
+
+[How to view and update state in subgraphs](https://langchain-ai.github.io/langgraph/how-tos/subgraphs-manage-state/): LLM should read this page when working with state management in nested subgraphs, implementing human-in-the-loop patterns, or debugging complex graph flows. This guide covers viewing and updating state in LangGraph subgraphs, including how to resume execution from breakpoints, modify subgraph state, act as specific nodes, and work with multi-level nested subgraphs.
+
+[How to call tools using ToolNode](https://langchain-ai.github.io/langgraph/how-tos/tool-calling/): LLM should read this page when learning how to implement tool calling with LangGraph, when working with the ToolNode component, or when building ReAct agents. This page covers using LangGraph's ToolNode for tool calling, including setup, manual invocation, working with chat models, building a ReAct agent, handling single and parallel tool calls, and error handling.
+
+[How to handle tool calling errors](https://langchain-ai.github.io/langgraph/how-tos/tool-calling-errors/): LLM should read this page when handling tool call errors, implementing error handling for LLM-tool interactions, or creating fallback strategies for failed tool calls. This page covers strategies for handling tool calling errors in LangGraph, including using the prebuilt ToolNode with built-in error handling, implementing custom error handling patterns, and fallback mechanisms with model upgrades when tools fail.
+
+[How to update graph state from tools](https://langchain-ai.github.io/langgraph/how-tos/update-state-from-tools/): LLM should read this page when needing to update graph state from tools in LangGraph, implementing personalized responses based on tool updates, or using Command objects to modify state. This page details how to update graph state from tools using Command objects, creating personalized agents with state tracking, and implementing dynamic prompt construction based on updated state values.
+
+[How to interact with the deployment using RemoteGraph](https://langchain-ai.github.io/langgraph/how-tos/use-remote-graph/): LLM should read this page when needing to interact with LangGraph Platform deployments remotely, when implementing RemoteGraph interfaces, or when using deployed graphs as subgraphs. This page explains how to use RemoteGraph to interact with LangGraph Platform deployments, covering initialization methods (URL-based or client-based), synchronous/asynchronous invocation, thread-level persistence, and using RemoteGraph as a subgraph in larger applications.
+
+[How to visualize your graph](https://langchain-ai.github.io/langgraph/how-tos/visualization): LLM should read this page when needing to visualize LangGraph graphs, looking for graph visualization methods, or working with graph visualization in Python. Comprehensive guide for visualizing graphs in LangGraph with multiple methods: Mermaid syntax, Mermaid.ink API for PNG rendering, Pyppeteer-based visualization, and Graphviz, with customization options for colors, styles, and layout.
+
+[How to wait for user input (Functional API)](https://langchain-ai.github.io/langgraph/how-tos/wait-user-input-functional/): LLM should read this page when implementing human-in-the-loop workflows, integrating user input into agent systems, or adding interruption capabilities to LangGraph applications. The page explains how to use the `interrupt()` function in LangGraph's Functional API to pause execution for human input, with examples for both simple workflows and ReAct agents, including code implementations with checkpointing.
+

docs/docs/stylesheets/version_admonitions.css

@@ -0,0 +1,38 @@
+:root {
+  --md-admonition-icon--version-added: url('data:image/svg+xml;charset=utf-8,<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 2H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h4l3 3 3-3h4c1.1 0 2-.9 2-2V4c0-1.1-.9-2-2-2m0 16h-4.2l-.8.8-2 2-2-2-.8-.8H5V4h14z"/><path d="M11 15h2v2h-2v-2m0-10h2v8h-2V5"/></svg>');
+  --md-admonition-icon--version-changed: url('data:image/svg+xml;charset=utf-8,<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 2H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h4l3 3 3-3h4c1.1 0 2-.9 2-2V4c0-1.1-.9-2-2-2m0 16h-4.2l-.8.8-2 2-2-2-.8-.8H5V4h14z"/><path d="M15 11h-2V9h-2v2H9v2h2v2h2v-2h2v-2Z"/></svg>');
+}
+
+.md-typeset .admonition.version-added,
+.md-typeset details.version-added {
+  border-color: rgb(0, 191, 165);
+}
+
+.md-typeset .version-added > .admonition-title,
+.md-typeset .version-added > summary {
+  background-color: rgba(0, 191, 165, 0.1);
+}
+
+.md-typeset .version-added > .admonition-title::before,
+.md-typeset .version-added > summary::before {
+  background-color: rgb(0, 191, 165);
+  -webkit-mask-image: var(--md-admonition-icon--version-added);
+          mask-image: var(--md-admonition-icon--version-added);
+}
+
+.md-typeset .admonition.version-changed,
+.md-typeset details.version-changed {
+  border-color: rgb(100, 221, 23);
+}
+
+.md-typeset .version-changed > .admonition-title,
+.md-typeset .version-changed > summary {
+  background-color: rgba(100, 221, 23, 0.1);
+}
+
+.md-typeset .version-changed > .admonition-title::before,
+.md-typeset .version-changed > summary::before {
+  background-color: rgb(100, 221, 23);
+  -webkit-mask-image: var(--md-admonition-icon--version-changed);
+          mask-image: var(--md-admonition-icon--version-changed);
+} 

docs/docs/tutorials/code_assistant/langgraph_code_assistant.ipynb

@@ -125,7 +125,7 @@
     "\n",
     "### Code solution\n",
     "\n",
-    "First, we will try OpenAI and [Claude3](https://docs.anthropic.com/en/docs/about-claude/models) with function calling.\n",
+    "First, we will try OpenAI and [Claude3](https://python.langchain.com/docs/integrations/providers/anthropic/) with function calling.\n",
     "\n",
     "We will create a `code_gen_chain` w/ either OpenAI or Claude and test them here."
    ]

docs/docs/tutorials/deployment.md

@@ -1,3 +1,8 @@
+---
+search:
+  boost: 2
+---
+
 # Deployment
 
 Get started deploying your LangGraph applications locally or on the cloud with
@@ -12,7 +17,18 @@ Get started deploying your LangGraph applications locally or on the cloud with
 
 ## Deployment Options
 
-- [Self-Hosted Lite](../concepts/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](../concepts/langgraph_cloud.md): Hosted as part of LangSmith.
-- [Bring Your Own Cloud](../concepts/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](../concepts/self_hosted.md): Completely managed by you.
+- [Cloud SaaS](../concepts/langgraph_cloud.md): Connect to your GitHub repositories and deploy LangGraph Servers to LangChain's cloud. We manage everything.
+- [Self-Hosted Data Plane](../concepts/langgraph_self_hosted_data_plane.md): 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.
+- [Self-Hosted Control Plane](../concepts/langgraph_self_hosted_control_plane.md#control-plane-ui): Create deployments from a self-hosted [Control Plane UI](../concepts/langgraph_control_plane.md) 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.
+
+A quick comparison...
+
+|                      | **Cloud SaaS** | **Self-Hosted [Data Plane](../concepts/langgraph_data_plane.md)** | **Self-Hosted [Control Plane](../concepts/langgraph_control_plane.md)** | **Standalone Container** |
+|----------------------|----------------|----------------------------|-------------------------------|--------------------------|
+| **[Control Plane UI/API](../concepts/langgraph_control_plane.md)** | Yes | Yes | Yes | No |
+| **CI/CD** | Managed internally by platform | Managed externally by you | Managed externally by you | Managed externally by you |
+| **Data/Compute Residency** | LangChain’s cloud | Your cloud | Your cloud | Your cloud |
+| **Required Permissions** | None | See details [here](). | See details [here](). | None |
+| **LangSmith Compatibility** | Trace to LangSmith SaaS | Trace to LangSmith SaaS | Trace to Self-Hosted LangSmith | Optional tracing |
+| **[Pricing](https://www.langchain.com/pricing-langgraph-platform)** | Plus | Enterprise | Enterprise | Developer |

docs/docs/tutorials/introduction.ipynb

@@ -279,7 +279,6 @@
     "        if user_input.lower() in [\"quit\", \"exit\", \"q\"]:\n",
     "            print(\"Goodbye!\")\n",
     "            break\n",
-    "\n",
     "        stream_graph_updates(user_input)\n",
     "    except:\n",
     "        # fallback if input() is not available\n",

docs/docs/tutorials/storm/storm.ipynb

@@ -153,7 +153,7 @@
     "\n",
     "from langchain_core.prompts import ChatPromptTemplate\n",
     "\n",
-    "from pydantic import BaseModel, Field\n",
+    "from pydantic import BaseModel, Field, field_validator\n",
     "\n",
     "direct_gen_outline_prompt = ChatPromptTemplate.from_messages(\n",
     "    [\n",
@@ -336,6 +336,10 @@
     "        description=\"Description of the editor's focus, concerns, and motives.\",\n",
     "    )\n",
     "\n",
+    "    @field_validator(\"name\", mode=\"before\")\n",
+    "    def sanitize_name(cls, value: str) -> str:\n",
+    "        return value.replace(\" \", \"\").replace(\".\", \"\")\n",
+    "\n",
     "    @property\n",
     "    def persona(self) -> str:\n",
     "        return f\"Name: {self.name}\\nRole: {self.role}\\nAffiliation: {self.affiliation}\\nDescription: {self.description}\\n\"\n",
@@ -362,9 +366,9 @@
     "    ]\n",
     ")\n",
     "\n",
-    "gen_perspectives_chain = gen_perspectives_prompt | ChatOpenAI(\n",
-    "    model=\"gpt-3.5-turbo\"\n",
-    ").with_structured_output(Perspectives)"
+    "gen_perspectives_chain = gen_perspectives_prompt | fast_llm.with_structured_output(\n",
+    "    Perspectives, method=\"function_calling\"\n",
+    ")"
    ]
   },
   {
@@ -451,7 +455,7 @@
     }
    ],
    "source": [
-    "perspectives.dict()"
+    "perspectives.model_dump()"
    ]
   },
   {
@@ -559,7 +563,7 @@
     "    converted = []\n",
     "    for message in state[\"messages\"]:\n",
     "        if isinstance(message, AIMessage) and message.name != name:\n",
-    "            message = HumanMessage(**message.dict(exclude={\"type\"}))\n",
+    "            message = HumanMessage(**message.model_dump(exclude={\"type\"}))\n",
     "        converted.append(message)\n",
     "    return {\"messages\": converted}\n",
     "\n",
@@ -637,9 +641,9 @@
     "        MessagesPlaceholder(variable_name=\"messages\", optional=True),\n",
     "    ]\n",
     ")\n",
-    "gen_queries_chain = gen_queries_prompt | ChatOpenAI(\n",
-    "    model=\"gpt-3.5-turbo\"\n",
-    ").with_structured_output(Queries, include_raw=True)"
+    "gen_queries_chain = gen_queries_prompt | fast_llm.with_structured_output(\n",
+    "    Queries, include_raw=True, method=\"function_calling\"\n",
+    ")"
    ]
   },
   {
@@ -1695,6 +1699,13 @@
     "# We will down-header the sections to create less confusion in this notebook\n",
     "Markdown(article.replace(\"\\n#\", \"\\n##\"))"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {

docs/docs/tutorials/workflows/index.md

@@ -1,6 +1,6 @@
 # Workflows and Agents
 
-This guide reviews common patterns for agentic systems. In describing these systems, it can be useful to make a distinction between "workflows" and "agents". One way to think about this difference is nicely explained [here](https://www.anthropic.com/research/building-effective-agents) by Anthropic:
+This guide reviews common patterns for agentic systems. In describing these systems, it can be useful to make a distinction between "workflows" and "agents". One way to think about this difference is nicely explained in [Anthropic's](https://python.langchain.com/docs/integrations/providers/anthropic/) `Building Effective Agents` blog post:
 
 > Workflows are systems where LLMs and tools are orchestrated through predefined code paths.
 > Agents, on the other hand, are systems where LLMs dynamically direct their own processes and tool usage, maintaining control over how they accomplish tasks.
@@ -9,7 +9,7 @@ Here is a simple way to visualize these differences:
 
 ![Agent Workflow](../../concepts/img/agent_workflow.png)
 
-When building agents and workflows, LangGraph [offers a number of benefits](https://langchain-ai.github.io/langgraph/concepts/high_level/) including persistence, streaming, and support for debugging as well as deployment.
+When building agents and workflows, LangGraph offers a number of benefits including persistence, streaming, and support for debugging as well as deployment.
 
 ## Set up
 
@@ -41,7 +41,7 @@ llm = ChatAnthropic(model="claude-3-5-sonnet-latest")
 
 ## Building Blocks: The Augmented LLM 
 
-LLM have [augmentations](https://www.anthropic.com/research/building-effective-agents) that support building workflows and agents. These include [structured outputs](https://python.langchain.com/docs/concepts/structured_outputs/) and [tool calling](https://python.langchain.com/docs/concepts/tool_calling/), as shown in this image from the Anthropic [blog](https://www.anthropic.com/research/building-effective-agents):
+LLM have augmentations that support building workflows and agents. These include [structured outputs](https://python.langchain.com/docs/concepts/structured_outputs/) and [tool calling](https://python.langchain.com/docs/concepts/tool_calling/), as shown in this image from the Anthropic blog on `Building Effective Agents`:
 
 ![augmented_llm.png](./img/augmented_llm.png)
 
@@ -81,7 +81,7 @@ msg.tool_calls
 
 In prompt chaining, each LLM call processes the output of the previous one. 
 
-As noted in the [Anthropic blog](https://www.anthropic.com/research/building-effective-agents): 
+As noted in the Anthropic blog on `Building Effective Agents`: 
 
 > Prompt chaining decomposes a task into a sequence of steps, where each LLM call processes the output of the previous one. You can add programmatic checks (see "gate” in the diagram below) on any intermediate steps to ensure that the process is still on track.
 
@@ -392,7 +392,7 @@ With parallelization, LLMs work simultaneously on a task:
 
 ## Routing
 
-Routing classifies an input and directs it to a followup task. As noted in the [Anthropic blog](https://www.anthropic.com/research/building-effective-agents): 
+Routing classifies an input and directs it to a followup task. As noted in the Anthropic blog on `Building Effective Agents`: 
 
 > Routing classifies an input and directs it to a specialized followup task. This workflow allows for separation of concerns, and building more specialized prompts. Without this workflow, optimizing for one kind of input can hurt performance on other inputs.
 
@@ -603,7 +603,7 @@ Routing classifies an input and directs it to a followup task. As noted in the [
 
 ## Orchestrator-Worker
 
-With orchestrator-worker, an orchestrator breaks down a task and delegates each sub-task to workers. As noted in the [Anthropic blog](https://www.anthropic.com/research/building-effective-agents): 
+With orchestrator-worker, an orchestrator breaks down a task and delegates each sub-task to workers. As noted in the Anthropic blog on `Building Effective Agents`: 
 
 > In the orchestrator-workers workflow, a central LLM dynamically breaks down tasks, delegates them to worker LLMs, and synthesizes their results.
 
@@ -948,7 +948,7 @@ In the evaluator-optimizer workflow, one LLM call generates a response while ano
 
     **Examples**
 
-    [Here](https://github.com/langchain-ai/research-rabbit) is an assistant that uses evaluator-optimizer to improve a report. See our video [here](https://www.youtube.com/watch?v=XGuTzHoqlj8).
+    [Here](https://github.com/langchain-ai/local-deep-researcher) is an assistant that uses evaluator-optimizer to improve a report. See our video [here](https://www.youtube.com/watch?v=XGuTzHoqlj8).
 
     [Here](https://langchain-ai.github.io/langgraph/tutorials/rag/langgraph_adaptive_rag_local/) is a RAG workflow that grades answers for hallucinations or errors. See our video [here](https://www.youtube.com/watch?v=bq1Plo2RhYI).
 
@@ -1012,7 +1012,7 @@ In the evaluator-optimizer workflow, one LLM call generates a response while ano
 
 ## Agent
 
-Agents are typically implemented as an LLM performing actions (via tool-calling) based on environmental feedback in a loop. As noted in the [Anthropic blog](https://www.anthropic.com/research/building-effective-agents):
+Agents are typically implemented as an LLM performing actions (via tool-calling) based on environmental feedback in a loop. As noted in the Anthropic blog on `Building Effective Agents`:
 
 > Agents can handle sophisticated tasks, but their implementation is often straightforward. They are typically just LLMs using tools based on environmental feedback in a loop. It is therefore crucial to design toolsets and their documentation clearly and thoughtfully.
 

docs/mkdocs.yml

@@ -54,7 +54,7 @@ theme:
     code: "Roboto Mono"
 plugins:
   - search:
-      separator: '[\s\u200b\-_,:!=\[\]()"`/]+|\.(?!\d)|&[lg]t;|(?!\b)(?=[A-Z][a-z])'
+      separator: '[\s\u200b\-,:!=\[\]()"`/]+|\.(?!\d)|&[lg]t;'
   - autorefs
   - mkdocstrings:
       handlers:
@@ -85,7 +85,7 @@ plugins:
 
 nav:
   - Home:
-    - Introduction: index.md
+    - index.md
     - Get started:
       - Learn the basics: tutorials/introduction.ipynb
       - Deployment:
@@ -185,6 +185,7 @@ nav:
               - how-tos/create-react-agent-system-prompt.ipynb
               - how-tos/create-react-agent-hitl.ipynb
               - how-tos/create-react-agent-structured-output.ipynb
+              - how-tos/create-react-agent-manage-message-history.ipynb
               - how-tos/react-agent-from-scratch.ipynb
               - how-tos/react-agent-from-scratch-functional.ipynb
         - LangGraph Platform:
@@ -202,8 +203,14 @@ nav:
             - Deployment:
                 - Deployment: how-tos#deployment
                 - cloud/deployment/cloud.md
+                - cloud/deployment/self_hosted_data_plane.md
+                - cloud/deployment/self_hosted_control_plane.md
+                - cloud/deployment/standalone_container.md
                 - how-tos/deploy-self-hosted.md
                 - how-tos/use-remote-graph.md
+                - how-tos/ttl/configure_ttl.md
+            - Data Management:
+                - how-tos/ttl/configure_ttl.md
             - Authentication & Access Control:
                 - Authentication & Access Control: how-tos#authentication-access-control
                 - cloud/how-tos/auth/custom_auth_new.md
@@ -231,6 +238,7 @@ nav:
                 - cloud/how-tos/stream_debug.md
                 - cloud/how-tos/stream_multiple.md
                 - cloud/how-tos/use_stream_react.md
+                - cloud/how-tos/generative_ui_react.md
             - Human-in-the-loop:
                 - Human-in-the-loop: how-tos#human-in-the-loop_1
                 - cloud/how-tos/human_in_the_loop_breakpoint.md
@@ -255,6 +263,8 @@ nav:
                 - cloud/how-tos/invoke_studio.md
                 - cloud/how-tos/threads_studio.md
                 - cloud/how-tos/datasets_studio.md
+                - cloud/how-tos/iterate_graph_studio.md
+                - cloud/how-tos/clone_traces_studio.md
       - Concepts:
         - concepts/index.md
         - LangGraph:
@@ -282,6 +292,8 @@ nav:
             - concepts/template_applications.md
           - Components:
             - Components: concepts#components
+            - concepts/langgraph_control_plane.md
+            - concepts/langgraph_data_plane.md
             - concepts/langgraph_server.md
             - concepts/langgraph_studio.md
             - concepts/langgraph_cli.md
@@ -295,9 +307,10 @@ nav:
             - concepts/auth.md
           - Deployment Options:
             - Deployment Options: concepts#deployment-options
-            - concepts/self_hosted.md
             - concepts/langgraph_cloud.md
-            - concepts/bring_your_own_cloud.md
+            - concepts/langgraph_self_hosted_data_plane.md
+            - concepts/langgraph_self_hosted_control_plane.md
+            - concepts/langgraph_standalone_container.md
       - Tutorials:
         - tutorials/index.md
         - Quick Start:
@@ -360,6 +373,7 @@ nav:
       # NOTE: prebuilt.md is auto-generated by `make build-prebuilt`
       - Prebuilt Agents: prebuilt.md
       - Companies using LangGraph: adopters.md
+      - LLMS-txt: llms-txt-overview.md
       - FAQ: concepts/faq.md
       - Troubleshooting:
           - Troubleshooting: troubleshooting/errors/index.md
@@ -501,3 +515,5 @@ validation:
   not_found: info
 copyright: >
   Copyright &copy; 2025 LangChain, Inc | <a href="#__consent">Consent Preferences</a>
+extra_css:
+  - stylesheets/version_admonitions.css

docs/overrides/main.html

@@ -1,6 +1,7 @@
 {% extends "base.html" %}
 
 {% block extrahead %}
+  <meta name="algolia-site-verification" content="165B7E7C89E49946" />
   <style>
     @import url("https://fonts.googleapis.com/css2?family=Public+Sans&display=swap");
     :root {

docs/pyproject.toml

@@ -10,6 +10,7 @@ readme = "README.md"
 python = "^3.10"
 aiohappyeyeballs = "2.4.3"
 hub = "^3.0.1"
+xxhash = "^3.5.0"
 
 [tool.poetry.group.docs.dependencies]
 langgraph = { path = "../libs/langgraph/", develop = true }
@@ -49,7 +50,8 @@ langchain-community = "^0.3.0"
 langchain-experimental = "^0.3.2"
 langchain-mistralai = "^0.2.6"
 langgraph-checkpoint-mongodb = "^0.1.0"
-langsmith = "^0.2.0"
+langmem = "^0.0.19"
+langsmith = "^0.3.0"
 chromadb = "^0.5.5"
 gpt4all = "^2.8.2"
 scikit-learn = "^1.5.2"
@@ -63,6 +65,8 @@ grandalf = "^0.8"
 pyppeteer = "^2.0.0"
 networkx = "^3.3"
 autogen = { version = "^0.3.0", python = "<3.13,>=3.8" }
+pytest = "^8.3.5"
+pytest-check-links = "^0.10.1"
 
 [tool.poetry.group.test]
 optional = true

libs/checkpoint-postgres/README.md

@@ -25,7 +25,7 @@ with PostgresSaver.from_conn_string(DB_URI) as checkpointer:
     # call .setup() the first time you're using the checkpointer
     checkpointer.setup()
     checkpoint = {
-        "v": 1,
+        "v": 2,
         "ts": "2024-07-31T20:14:19.804150+00:00",
         "id": "1ef4f797-8335-6428-8001-8a1503f9b875",
         "channel_values": {
@@ -67,7 +67,7 @@ from langgraph.checkpoint.postgres.aio import AsyncPostgresSaver
 
 async with AsyncPostgresSaver.from_conn_string(DB_URI) as checkpointer:
     checkpoint = {
-        "v": 1,
+        "v": 2,
         "ts": "2024-07-31T20:14:19.804150+00:00",
         "id": "1ef4f797-8335-6428-8001-8a1503f9b875",
         "channel_values": {

libs/checkpoint-postgres/langgraph/store/postgres/aio.py

@@ -2,6 +2,7 @@ import asyncio
 import logging
 from collections.abc import AsyncIterator, Iterable, Sequence
 from contextlib import asynccontextmanager
+from types import TracebackType
 from typing import Any, Callable, Optional, Union, cast
 
 import orjson
@@ -20,11 +21,12 @@ from langgraph.store.base import (
 )
 from langgraph.store.base.batch import AsyncBatchedBaseStore
 from langgraph.store.postgres.base import (
-    _PLACEHOLDER,
+    PLACEHOLDER,
     BasePostgresStore,
     PoolConfig,
     PostgresIndexConfig,
     Row,
+    TTLConfig,
     _decode_ns_bytes,
     _ensure_index_config,
     _group_ops,
@@ -76,7 +78,7 @@ class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Con
             await store.aput(("docs",), "doc3", {"text": "Other guide"}, index=False)  # don't index
 
             # Search by similarity
-            results = await store.asearch(("docs",), "programming guides", limit=2)
+            results = await store.asearch(("docs",), query="programming guides", limit=2)
         ```
 
         Using connection pooling for better performance:
@@ -106,6 +108,11 @@ class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Con
         Semantic search is disabled by default. You can enable it by providing an `index` configuration
         when creating the store. Without this configuration, all `index` arguments passed to
         `put` or `aput` will have no effect.
+
+    Note:
+        If you provide a TTL configuration, you must explicitly call `start_ttl_sweeper()` to begin
+        the background task that removes expired items. Call `stop_ttl_sweeper()` to properly
+        clean up resources when you're done with the store.
     """
 
     __slots__ = (
@@ -115,7 +122,11 @@ class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Con
         "supports_pipeline",
         "index_config",
         "embeddings",
+        "ttl_config",
+        "_ttl_sweeper_task",
+        "_ttl_stop_event",
     )
+    supports_ttl: bool = True
 
     def __init__(
         self,
@@ -126,6 +137,7 @@ class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Con
             Callable[[Union[bytes, orjson.Fragment]], dict[str, Any]]
         ] = None,
         index: Optional[PostgresIndexConfig] = None,
+        ttl: Optional[TTLConfig] = None,
     ) -> None:
         if isinstance(conn, AsyncConnectionPool) and pipe is not None:
             raise ValueError(
@@ -141,10 +153,13 @@ class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Con
         self.index_config = index
         if self.index_config:
             self.embeddings, self.index_config = _ensure_index_config(self.index_config)
-
         else:
             self.embeddings = None
 
+        self.ttl_config = ttl
+        self._ttl_sweeper_task: Optional[asyncio.Task[None]] = None
+        self._ttl_stop_event = asyncio.Event()
+
     async def abatch(self, ops: Iterable[Op]) -> list[Result]:
         grouped_ops, num_ops = _group_ops(ops)
         results: list[Result] = [None] * num_ops
@@ -167,6 +182,7 @@ class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Con
         pipeline: bool = False,
         pool_config: Optional[PoolConfig] = None,
         index: Optional[PostgresIndexConfig] = None,
+        ttl: Optional[TTLConfig] = None,
     ) -> AsyncIterator["AsyncPostgresStore"]:
         """Create a new AsyncPostgresStore instance from a connection string.
 
@@ -198,16 +214,16 @@ class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Con
                     **cast(dict, pc),
                 ),
             ) as pool:
-                yield cls(conn=pool, index=index)
+                yield cls(conn=pool, index=index, ttl=ttl)
         else:
             async with await AsyncConnection.connect(
                 conn_string, autocommit=True, prepare_threshold=0, row_factory=dict_row
             ) as conn:
                 if pipeline:
                     async with conn.pipeline() as pipe:
-                        yield cls(conn=conn, pipe=pipe, index=index)
+                        yield cls(conn=conn, pipe=pipe, index=index, ttl=ttl)
                 else:
-                    yield cls(conn=conn, index=index)
+                    yield cls(conn=conn, index=index, ttl=ttl)
 
     async def setup(self) -> None:
         """Set up the store database asynchronously.
@@ -256,6 +272,119 @@ class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Con
                         "INSERT INTO vector_migrations (v) VALUES (%s)", (v,)
                     )
 
+    async def sweep_ttl(self) -> int:
+        """Delete expired store items based on TTL.
+
+        Returns:
+            int: The number of deleted items.
+        """
+        async with self._cursor() as cur:
+            await cur.execute(
+                """
+                DELETE FROM store
+                WHERE expires_at IS NOT NULL AND expires_at < NOW()
+                """
+            )
+            deleted_count = cur.rowcount
+            return deleted_count
+
+    async def start_ttl_sweeper(
+        self, sweep_interval_minutes: Optional[int] = None
+    ) -> asyncio.Task[None]:
+        """Periodically delete expired store items based on TTL.
+
+        Returns:
+            Task that can be awaited or cancelled.
+        """
+        if not self.ttl_config:
+            return asyncio.create_task(asyncio.sleep(0))
+
+        if self._ttl_sweeper_task is not None and not self._ttl_sweeper_task.done():
+            return self._ttl_sweeper_task
+
+        self._ttl_stop_event.clear()
+
+        interval = float(
+            sweep_interval_minutes or self.ttl_config.get("sweep_interval_minutes") or 5
+        )
+        logger.info(f"Starting store TTL sweeper with interval {interval} minutes")
+
+        async def _sweep_loop() -> None:
+            while not self._ttl_stop_event.is_set():
+                try:
+                    try:
+                        await asyncio.wait_for(
+                            self._ttl_stop_event.wait(),
+                            timeout=interval * 60,
+                        )
+                        break
+                    except asyncio.TimeoutError:
+                        pass
+
+                    expired_items = await self.sweep_ttl()
+                    if expired_items > 0:
+                        logger.info(f"Store swept {expired_items} expired items")
+                except asyncio.CancelledError:
+                    break
+                except Exception as exc:
+                    logger.exception("Store TTL sweep iteration failed", exc_info=exc)
+
+        task = asyncio.create_task(_sweep_loop())
+        task.set_name("ttl_sweeper")
+        self._ttl_sweeper_task = task
+        return task
+
+    async def stop_ttl_sweeper(self, timeout: Optional[float] = None) -> bool:
+        """Stop the TTL sweeper task if it's running.
+
+        Args:
+            timeout: Maximum time to wait for the task to stop, in seconds.
+                If None, wait indefinitely.
+
+        Returns:
+            bool: True if the task was successfully stopped or wasn't running,
+                False if the timeout was reached before the task stopped.
+        """
+        if self._ttl_sweeper_task is None or self._ttl_sweeper_task.done():
+            return True
+
+        logger.info("Stopping TTL sweeper task")
+        self._ttl_stop_event.set()
+
+        if timeout is not None:
+            try:
+                await asyncio.wait_for(self._ttl_sweeper_task, timeout=timeout)
+                success = True
+            except asyncio.TimeoutError:
+                success = False
+        else:
+            await self._ttl_sweeper_task
+            success = True
+
+        if success:
+            self._ttl_sweeper_task = None
+            logger.info("TTL sweeper task stopped")
+        else:
+            logger.warning("Timed out waiting for TTL sweeper task to stop")
+
+        return success
+
+    async def __aenter__(self) -> "AsyncPostgresStore":
+        return self
+
+    async def __aexit__(
+        self,
+        exc_type: Optional[type[BaseException]],
+        exc_val: Optional[BaseException],
+        exc_tb: Optional["TracebackType"],
+    ) -> None:
+        # Ensure the TTL sweeper task is stopped when exiting the context
+        if hasattr(self, "_ttl_sweeper_task") and self._ttl_sweeper_task is not None:
+            # Set the event to signal the task to stop
+            self._ttl_stop_event.set()
+            # We don't wait for the task to complete here to avoid blocking
+            # The task will clean up itself gracefully
+
     async def _execute_batch(
         self,
         grouped_ops: dict,
@@ -360,7 +489,7 @@ class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Con
             for (idx, _), vector in zip(embedding_requests, vectors):
                 _paramslist = queries[idx][1]
                 for i in range(len(_paramslist)):
-                    if _paramslist[i] is _PLACEHOLDER:
+                    if _paramslist[i] is PLACEHOLDER:
                         _paramslist[i] = vector
 
         for (idx, _), (query, params) in zip(search_ops, queries):

libs/checkpoint-postgres/langgraph/store/postgres/base.py

@@ -1,4 +1,5 @@
 import asyncio
+import concurrent.futures
 import json
 import logging
 import threading
@@ -39,6 +40,7 @@ from langgraph.store.base import (
     Result,
     SearchItem,
     SearchOp,
+    TTLConfig,
     ensure_embeddings,
     get_text_at_path,
     tokenize_path,
@@ -73,6 +75,17 @@ CREATE TABLE IF NOT EXISTS store (
     """
 -- For faster lookups by prefix
 CREATE INDEX CONCURRENTLY IF NOT EXISTS store_prefix_idx ON store USING btree (prefix text_pattern_ops);
+""",
+    """
+-- Add expires_at column to store table
+ALTER TABLE store
+ADD COLUMN IF NOT EXISTS expires_at TIMESTAMP WITH TIME ZONE,
+ADD COLUMN IF NOT EXISTS ttl_minutes INT;
+""",
+    """
+-- Add indexes for efficient TTL sweeping
+CREATE INDEX IF NOT EXISTS idx_store_expires_at ON store (expires_at)
+WHERE expires_at IS NOT NULL;
 """,
 ]
 
@@ -224,20 +237,55 @@ class BasePostgresStore(Generic[C]):
         self,
         get_ops: Sequence[tuple[int, GetOp]],
     ) -> list[tuple[str, tuple, tuple[str, ...], list]]:
+        """
+        Build queries to fetch (and optionally refresh the TTL of) multiple keys per namespace.
+
+        Each returned element is a tuple of:
+        (sql_query_string, sql_params, namespace, items_for_this_namespace)
+
+        where items_for_this_namespace is the original list of (idx, key, refresh_ttl).
+        """
+
         namespace_groups = defaultdict(list)
+        refresh_ttls = defaultdict(list)
         for idx, op in get_ops:
             namespace_groups[op.namespace].append((idx, op.key))
+            refresh_ttls[op.namespace].append(op.refresh_ttl)
+
         results = []
         for namespace, items in namespace_groups.items():
             _, keys = zip(*items)
-            keys_to_query = ",".join(["%s"] * len(keys))
-            query = f"""
-                SELECT key, value, created_at, updated_at
-                FROM store
-                WHERE prefix = %s AND key IN ({keys_to_query})
+            this_refresh_ttls = refresh_ttls[namespace]
+
+            query = """
+                WITH passed_in AS (
+                    SELECT unnest(%s::text[]) AS key,
+                        unnest(%s::bool[])  AS do_refresh
+                ),
+                updated AS (
+                    UPDATE store s
+                    SET expires_at = NOW() + (s.ttl_minutes || ' minutes')::interval
+                    FROM passed_in p
+                    WHERE s.prefix = %s
+                    AND s.key    = p.key
+                    AND p.do_refresh = TRUE
+                    AND s.ttl_minutes IS NOT NULL
+                    RETURNING s.key
+                )
+                SELECT s.key, s.value, s.created_at, s.updated_at
+                FROM store s
+                JOIN passed_in p ON s.key = p.key
+                WHERE s.prefix = %s
             """
-            params = (_namespace_to_text(namespace), *keys)
+            ns_text = _namespace_to_text(namespace)
+            params = (
+                list(keys),  # -> unnest(%s::text[])
+                list(this_refresh_ttls),  # -> unnest(%s::bool[])
+                ns_text,  # -> prefix = %s (for UPDATE)
+                ns_text,  # -> prefix = %s (for final SELECT)
+            )
             results.append((query, params, namespace, items))
+
         return results
 
     def _prepare_batch_PUT_queries(
@@ -247,7 +295,6 @@ class BasePostgresStore(Generic[C]):
         list[tuple[str, Sequence]],
         Optional[tuple[str, Sequence[tuple[str, str, str, str]]]],
     ]:
-        # Last-write wins
         dedupped_ops: dict[tuple[tuple[str, ...], str], PutOp] = {}
         for _, op in put_ops:
             dedupped_ops[(op.namespace, op.key)] = op
@@ -281,15 +328,26 @@ class BasePostgresStore(Generic[C]):
             insertion_params = []
             vector_values = []
             embedding_request_params = []
+            # Handle TTL expiration
 
             # First handle main store insertions
             for op in inserts:
-                values.append("(%s, %s, %s, CURRENT_TIMESTAMP, CURRENT_TIMESTAMP)")
+                if op.ttl is not None:
+                    expires_at_str = f"NOW() + INTERVAL '{op.ttl*60} seconds'"
+                    ttl_minutes = op.ttl
+                else:
+                    expires_at_str = "NULL"
+                    ttl_minutes = None
+
+                values.append(
+                    f"(%s, %s, %s, CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, {expires_at_str}, %s)"
+                )
                 insertion_params.extend(
                     [
                         _namespace_to_text(op.namespace),
                         op.key,
                         Jsonb(cast(dict, op.value)),
+                        ttl_minutes,
                     ]
                 )
 
@@ -303,7 +361,7 @@ class BasePostgresStore(Generic[C]):
                     k = op.key
 
                     if op.index is None:
-                        paths = self.index_config["__tokenized_fields"]
+                        paths = cast(dict, self.index_config)["__tokenized_fields"]
                     else:
                         paths = [(ix, tokenize_path(ix)) for ix in op.index]
 
@@ -318,11 +376,13 @@ class BasePostgresStore(Generic[C]):
 
             values_str = ",".join(values)
             query = f"""
-                INSERT INTO store (prefix, key, value, created_at, updated_at)
+                INSERT INTO store (prefix, key, value, created_at, updated_at, expires_at, ttl_minutes)
                 VALUES {values_str}
                 ON CONFLICT (prefix, key) DO UPDATE
                 SET value = EXCLUDED.value,
-                    updated_at = CURRENT_TIMESTAMP
+                    updated_at = CURRENT_TIMESTAMP,
+                    expires_at = EXCLUDED.expires_at,
+                    ttl_minutes = EXCLUDED.ttl_minutes
             """
             queries.append((query, insertion_params))
 
@@ -346,117 +406,151 @@ class BasePostgresStore(Generic[C]):
         list[tuple[str, list[Union[None, str, list[float]]]]],  # queries, params
         list[tuple[int, str]],  # idx, query_text pairs to embed
     ]:
+        """
+        Build per-SearchOp SQL queries (with optional TTL refresh) plus embedding requests.
+        Returns:
+        - queries: list of (SQL, param_list)
+        - embedding_requests: list of (original_index_in_search_ops, text_query)
+        """
+
         queries = []
         embedding_requests = []
-
         for idx, (_, op) in enumerate(search_ops):
-            # Build filter conditions first
             filter_params = []
-            filter_conditions = []
+            filter_clauses = []
             if op.filter:
                 for key, value in op.filter.items():
                     if isinstance(value, dict):
                         for op_name, val in value.items():
-                            condition, filter_params_ = self._get_filter_condition(
+                            condition, params_ = self._get_filter_condition(
                                 key, op_name, val
                             )
-                            filter_conditions.append(condition)
-                            filter_params.extend(filter_params_)
+                            filter_clauses.append(condition)
+                            filter_params.extend(params_)
                     else:
-                        filter_conditions.append("value->%s = %s::jsonb")
-                        filter_params.extend([key, json.dumps(value)])
+                        filter_clauses.append("value->%s = %s::jsonb")
+                        filter_params.extend([key, orjson.dumps(value).decode("utf-8")])
+
+            ns_condition = "TRUE"
+            ns_param: Optional[Sequence[Union[str]]] = None
+            if op.namespace_prefix:
+                ns_condition = "store.prefix LIKE %s"
+                ns_param = (f"{_namespace_to_text(op.namespace_prefix)}%",)
+            else:
+                ns_param = ()
+
+            extra_filters = (
+                " AND " + " AND ".join(filter_clauses) if filter_clauses else ""
+            )
 
-            # Vector search branch
             if op.query and self.index_config:
+                # We'll embed the text later, so record the request.
                 embedding_requests.append((idx, op.query))
 
-                score_operator, post_operator = _get_distance_operator(self)
+                score_operator, post_operator = get_distance_operator(self)
+                post_operator = post_operator.replace("scored", "uniq")
                 vector_type = (
                     cast(PostgresIndexConfig, self.index_config)
                     .get("ann_index_config", {})
                     .get("vector_type", "vector")
                 )
 
+                # For hamming bit vectors, or “regular” vectors
                 if (
                     vector_type == "bit"
-                    and self.index_config.get("distance_type") == "hamming"
+                    and cast(dict, self.index_config).get("distance_type") == "hamming"
                 ):
                     score_operator = score_operator % (
                         "%s",
-                        self.index_config["dims"],
+                        cast(dict, self.index_config)["dims"],
                     )
                 else:
-                    score_operator = score_operator % (
-                        "%s",
-                        vector_type,
-                    )
+                    score_operator = score_operator % ("%s", vector_type)
 
-                vectors_per_doc_estimate = self.index_config["__estimated_num_vectors"]
+                vectors_per_doc_estimate = cast(dict, self.index_config)[
+                    "__estimated_num_vectors"
+                ]
                 expanded_limit = (op.limit * vectors_per_doc_estimate * 2) + 1
 
-                # Vector search with CTE for proper score handling
-                filter_str = (
-                    ""
-                    if not filter_conditions
-                    else " AND " + " AND ".join(filter_conditions)
-                )
-                if op.namespace_prefix:
-                    prefix_filter_str = f"WHERE s.prefix LIKE %s {filter_str} "
-                    ns_args: Sequence = (f"{_namespace_to_text(op.namespace_prefix)}%",)
-                else:
-                    ns_args = ()
-                    if filter_str:
-                        prefix_filter_str = f"WHERE {filter_str} "
-                    else:
-                        prefix_filter_str = ""
-
-                base_query = f"""
-                    WITH scored AS (
-                        SELECT s.prefix, s.key, s.value, s.created_at, s.updated_at, {score_operator} AS neg_score
-                        FROM store s
-                        JOIN store_vectors sv ON s.prefix = sv.prefix AND s.key = sv.key
-                        {prefix_filter_str}
-                        ORDER BY {score_operator} ASC 
+                # “sub_scored” does the main vector search
+                # Then we do DISTINCT ON to drop duplicates if your store can have them
+                # Finally we limit & offset
+                vector_search_cte = f"""
+                        SELECT store.prefix, store.key, store.value, store.created_at, store.updated_at,
+                            {score_operator} AS neg_score
+                        FROM store
+                        JOIN store_vectors sv ON store.prefix = sv.prefix AND store.key = sv.key
+                        WHERE {ns_condition} {extra_filters}
+                        ORDER BY {score_operator} ASC
                         LIMIT %s
-                    )
-                    SELECT * FROM (
-                        SELECT DISTINCT ON (prefix, key) 
-                            prefix, key, value, created_at, updated_at, {post_operator} as score 
-                        FROM scored 
-                        ORDER BY prefix, key, score DESC
-                    ) AS unique_docs
-                    ORDER BY score DESC
-                    LIMIT %s
-                    OFFSET %s
-                """
-                params = [
-                    _PLACEHOLDER,  # Vector placeholder
-                    *ns_args,
+                    """
+
+                search_results_sql = f"""
+                        WITH scored AS (
+                            {vector_search_cte}
+                        )
+                        SELECT uniq.prefix, uniq.key, uniq.value, uniq.created_at, uniq.updated_at,
+                            {post_operator} AS score
+                        FROM (
+                            SELECT DISTINCT ON (scored.prefix, scored.key)
+                                scored.prefix, scored.key, scored.value, scored.created_at, scored.updated_at, scored.neg_score
+                            FROM scored
+                            ORDER BY scored.prefix, scored.key, scored.neg_score ASC
+                        ) uniq
+                        ORDER BY score DESC
+                        LIMIT %s
+                        OFFSET %s
+                    """
+
+                search_results_params = [
+                    PLACEHOLDER,
+                    *ns_param,
                     *filter_params,
-                    _PLACEHOLDER,
+                    PLACEHOLDER,
                     expanded_limit,
                     op.limit,
                     op.offset,
                 ]
 
-            # Regular search branch
             else:
-                base_query = """
-                    SELECT prefix, key, value, created_at, updated_at
-                    FROM store
-                    WHERE prefix LIKE %s
-                """
-                params = [f"{_namespace_to_text(op.namespace_prefix)}%"]
+                base_query = f"""
+                        SELECT store.prefix, store.key, store.value, store.created_at, store.updated_at, NULL AS score
+                        FROM store
+                        WHERE {ns_condition} {extra_filters}
+                        ORDER BY store.updated_at DESC
+                        LIMIT %s
+                        OFFSET %s
+                    """
+                search_results_sql = base_query
+                search_results_params = [
+                    *ns_param,
+                    *filter_params,
+                    op.limit,
+                    op.offset,
+                ]
 
-                if filter_conditions:
-                    params.extend(filter_params)
-                    base_query += " AND " + " AND ".join(filter_conditions)
-
-                base_query += " ORDER BY updated_at DESC"
-                base_query += " LIMIT %s OFFSET %s"
-                params.extend([op.limit, op.offset])
-
-            queries.append((base_query, params))
+            if op.refresh_ttl:
+                # Wrap entire primary query in a CTE, then perform "update_at"
+                final_sql = f"""
+                        WITH search_results AS (
+                            {search_results_sql}
+                        ),
+                        updated AS (
+                            UPDATE store s
+                            SET expires_at = NOW() + (s.ttl_minutes || ' minutes')::interval
+                            FROM search_results sr
+                            WHERE s.prefix = sr.prefix
+                            AND s.key = sr.key
+                            AND s.ttl_minutes IS NOT NULL
+                        )
+                        SELECT sr.prefix, sr.key, sr.value, sr.created_at, sr.updated_at, sr.score
+                        FROM search_results sr
+                    """
+                final_params = search_results_params[:]  # copy
+            else:
+                final_sql = search_results_sql
+                final_params = search_results_params
+            queries.append((final_sql, final_params))
 
         return queries, embedding_requests
 
@@ -590,7 +684,7 @@ class PostgresStore(BaseStore, BasePostgresStore[_pg_internal.Conn]):
             store.put(("docs",), "doc2", {"text": "Other guide"}, index=False) # don't index
 
             # Search by similarity
-            results = store.search(("docs",), "programming guides", limit=2)
+            results = store.search(("docs",), query="programming guides", limit=2)
         ```
 
     Note:
@@ -602,6 +696,11 @@ class PostgresStore(BaseStore, BasePostgresStore[_pg_internal.Conn]):
         Make sure to call `setup()` before first use to create necessary tables and indexes.
         The pgvector extension must be available to use vector search.
 
+    Note:
+        If you provide a TTL configuration, you must explicitly call `start_ttl_sweeper()` to begin
+        the background thread that removes expired items. Call `stop_ttl_sweeper()` to properly
+        clean up resources when you're done with the store.
+
     """
 
     __slots__ = (
@@ -611,7 +710,10 @@ class PostgresStore(BaseStore, BasePostgresStore[_pg_internal.Conn]):
         "supports_pipeline",
         "index_config",
         "embeddings",
+        "_ttl_sweeper_thread",
+        "_ttl_stop_event",
     )
+    supports_ttl: bool = True
 
     def __init__(
         self,
@@ -622,6 +724,7 @@ class PostgresStore(BaseStore, BasePostgresStore[_pg_internal.Conn]):
             Callable[[Union[bytes, orjson.Fragment]], dict[str, Any]]
         ] = None,
         index: Optional[PostgresIndexConfig] = None,
+        ttl: Optional[TTLConfig] = None,
     ) -> None:
         super().__init__()
         self._deserializer = deserializer
@@ -634,6 +737,9 @@ class PostgresStore(BaseStore, BasePostgresStore[_pg_internal.Conn]):
             self.embeddings, self.index_config = _ensure_index_config(self.index_config)
         else:
             self.embeddings = None
+        self.ttl_config = ttl
+        self._ttl_sweeper_thread: Optional[threading.Thread] = None
+        self._ttl_stop_event = threading.Event()
 
     @classmethod
     @contextmanager
@@ -644,6 +750,7 @@ class PostgresStore(BaseStore, BasePostgresStore[_pg_internal.Conn]):
         pipeline: bool = False,
         pool_config: Optional[PoolConfig] = None,
         index: Optional[PostgresIndexConfig] = None,
+        ttl: Optional[TTLConfig] = None,
     ) -> Iterator["PostgresStore"]:
         """Create a new PostgresStore instance from a connection string.
 
@@ -675,16 +782,123 @@ class PostgresStore(BaseStore, BasePostgresStore[_pg_internal.Conn]):
                     **cast(dict, pc),
                 ),
             ) as pool:
-                yield cls(conn=pool, index=index)
+                yield cls(conn=pool, index=index, ttl=ttl)
         else:
             with Connection.connect(
                 conn_string, autocommit=True, prepare_threshold=0, row_factory=dict_row
             ) as conn:
                 if pipeline:
                     with conn.pipeline() as pipe:
-                        yield cls(conn, pipe=pipe, index=index)
+                        yield cls(conn, pipe=pipe, index=index, ttl=ttl)
                 else:
-                    yield cls(conn, index=index)
+                    yield cls(conn, index=index, ttl=ttl)
+
+    def sweep_ttl(self) -> int:
+        """Delete expired store items based on TTL.
+
+        Returns:
+            int: The number of deleted items.
+        """
+        with self._cursor() as cur:
+            cur.execute(
+                """
+                DELETE FROM store
+                WHERE expires_at IS NOT NULL AND expires_at < NOW()
+                """
+            )
+            deleted_count = cur.rowcount
+            return deleted_count
+
+    def start_ttl_sweeper(
+        self, sweep_interval_minutes: Optional[int] = None
+    ) -> concurrent.futures.Future[None]:
+        """Periodically delete expired store items based on TTL.
+
+        Returns:
+            Future that can be waited on or cancelled.
+        """
+        if not self.ttl_config:
+            future: concurrent.futures.Future[None] = concurrent.futures.Future()
+            future.set_result(None)
+            return future
+
+        if self._ttl_sweeper_thread and self._ttl_sweeper_thread.is_alive():
+            logger.info("TTL sweeper thread is already running")
+            # Return a future that can be used to cancel the existing thread
+            future = concurrent.futures.Future()
+            future.add_done_callback(
+                lambda f: self._ttl_stop_event.set() if f.cancelled() else None
+            )
+            return future
+
+        self._ttl_stop_event.clear()
+
+        interval = float(
+            sweep_interval_minutes or self.ttl_config.get("sweep_interval_minutes") or 5
+        )
+        logger.info(f"Starting store TTL sweeper with interval {interval} minutes")
+
+        future = concurrent.futures.Future()
+
+        def _sweep_loop() -> None:
+            try:
+                while not self._ttl_stop_event.is_set():
+                    if self._ttl_stop_event.wait(interval * 60):
+                        break
+
+                    try:
+                        expired_items = self.sweep_ttl()
+                        if expired_items > 0:
+                            logger.info(f"Store swept {expired_items} expired items")
+                    except Exception as exc:
+                        logger.exception(
+                            "Store TTL sweep iteration failed", exc_info=exc
+                        )
+                future.set_result(None)
+            except Exception as exc:
+                future.set_exception(exc)
+
+        thread = threading.Thread(target=_sweep_loop, daemon=True, name="ttl-sweeper")
+        self._ttl_sweeper_thread = thread
+        thread.start()
+
+        future.add_done_callback(
+            lambda f: self._ttl_stop_event.set() if f.cancelled() else None
+        )
+        return future
+
+    def stop_ttl_sweeper(self, timeout: Optional[float] = None) -> bool:
+        """Stop the TTL sweeper thread if it's running.
+
+        Args:
+            timeout: Maximum time to wait for the thread to stop, in seconds.
+                If None, wait indefinitely.
+
+        Returns:
+            bool: True if the thread was successfully stopped or wasn't running,
+                False if the timeout was reached before the thread stopped.
+        """
+        if not self._ttl_sweeper_thread or not self._ttl_sweeper_thread.is_alive():
+            return True
+
+        logger.info("Stopping TTL sweeper thread")
+        self._ttl_stop_event.set()
+
+        self._ttl_sweeper_thread.join(timeout)
+        success = not self._ttl_sweeper_thread.is_alive()
+
+        if success:
+            self._ttl_sweeper_thread = None
+            logger.info("TTL sweeper thread stopped")
+        else:
+            logger.warning("Timed out waiting for TTL sweeper thread to stop")
+
+        return success
+
+    def __del__(self) -> None:
+        """Ensure the TTL sweeper thread is stopped when the object is garbage collected."""
+        if hasattr(self, "_ttl_stop_event") and hasattr(self, "_ttl_sweeper_thread"):
+            self.stop_ttl_sweeper(timeout=0.1)
 
     @contextmanager
     def _cursor(self, *, pipeline: bool = False) -> Iterator[Cursor[DictRow]]:
@@ -828,7 +1042,7 @@ class PostgresStore(BaseStore, BasePostgresStore[_pg_internal.Conn]):
             for (idx, _), embedding in zip(embedding_requests, embeddings):
                 _paramslist = queries[idx][1]
                 for i in range(len(_paramslist)):
-                    if _paramslist[i] is _PLACEHOLDER:
+                    if _paramslist[i] is PLACEHOLDER:
                         _paramslist[i] = embedding
 
         for (idx, _), (query, params) in zip(search_ops, queries):
@@ -883,8 +1097,14 @@ class PostgresStore(BaseStore, BasePostgresStore[_pg_internal.Conn]):
         with self._cursor() as cur:
             version = _get_version(cur, table="store_migrations")
             for v, sql in enumerate(self.MIGRATIONS[version + 1 :], start=version + 1):
-                cur.execute(sql)
-                cur.execute("INSERT INTO store_migrations (v) VALUES (%s)", (v,))
+                try:
+                    cur.execute(sql)
+                    cur.execute("INSERT INTO store_migrations (v) VALUES (%s)", (v,))
+                except Exception as e:
+                    logger.error(
+                        f"Failed to apply migration {v}.\nSql={sql}\nError={e}"
+                    )
+                    raise
 
             if self.index_config:
                 version = _get_version(cur, table="vector_migrations")
@@ -1055,7 +1275,7 @@ def _decode_ns_bytes(namespace: Union[str, bytes, list]) -> tuple[str, ...]:
     return tuple(namespace.split("."))
 
 
-def _get_distance_operator(store: Any) -> tuple[str, str]:
+def get_distance_operator(store: Any) -> tuple[str, str]:
     """Get the distance operator and score expression based on config."""
     # Note: Today, we are not using ANN indices due to restrictions
     # on PGVector's support for mixing vector and non-vector filters
@@ -1121,4 +1341,4 @@ def _ensure_index_config(
     return embeddings, index_config
 
 
-_PLACEHOLDER = object()
+PLACEHOLDER = object()

libs/checkpoint-postgres/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langgraph-checkpoint-postgres"
-version = "2.0.15"
+version = "2.0.19"
 description = "Library with a Postgres implementation of LangGraph checkpoint saver."
 authors = []
 license = "MIT"
@@ -10,7 +10,7 @@ packages = [{ include = "langgraph" }]
 
 [tool.poetry.dependencies]
 python = "^3.9.0,<4.0"
-langgraph-checkpoint = "^2.0.15"
+langgraph-checkpoint = "^2.0.21"
 orjson = ">=3.10.1"
 psycopg = "^3.2.0"
 psycopg-pool = "^3.2.0"

libs/checkpoint-postgres/tests/test_async_store.py

@@ -26,6 +26,9 @@ from tests.conftest import (
     CharacterEmbeddings,
 )
 
+TTL_SECONDS = 6
+TTL_MINUTES = TTL_SECONDS / 60
+
 
 @pytest.fixture(scope="function", params=["default", "pipe", "pool"])
 async def store(request) -> AsyncIterator[AsyncPostgresStore]:
@@ -42,28 +45,54 @@ async def store(request) -> AsyncIterator[AsyncPostgresStore]:
 
     conn_string = f"{uri_base}/{database}{query_params}"
     admin_conn_string = DEFAULT_URI
-
+    ttl_config = {
+        "default_ttl": TTL_MINUTES,
+        "refresh_on_read": True,
+        "sweep_interval_minutes": TTL_MINUTES / 2,
+    }
     async with await AsyncConnection.connect(
         admin_conn_string, autocommit=True
     ) as conn:
         await conn.execute(f"CREATE DATABASE {database}")
     try:
-        async with AsyncPostgresStore.from_conn_string(conn_string) as store:
+        async with AsyncPostgresStore.from_conn_string(
+            conn_string, ttl=ttl_config
+        ) as store:
+            store.MIGRATIONS = [
+                (
+                    mig.replace("ttl_minutes INT;", "ttl_minutes FLOAT;")
+                    if isinstance(mig, str)
+                    else mig
+                )
+                for mig in store.MIGRATIONS
+            ]
             await store.setup()
+            async with store._cursor() as cur:
+                # drop the migration index
+                await cur.execute("DROP TABLE IF EXISTS store_migrations")
+            await store.setup()  # Will fail if migrations aren't idempotent
 
         if request.param == "pipe":
             async with AsyncPostgresStore.from_conn_string(
-                conn_string, pipeline=True
+                conn_string, pipeline=True, ttl=ttl_config
             ) as store:
+                await store.start_ttl_sweeper()
                 yield store
+                await store.stop_ttl_sweeper()
         elif request.param == "pool":
             async with AsyncPostgresStore.from_conn_string(
-                conn_string, pool_config={"min_size": 1, "max_size": 10}
+                conn_string, pool_config={"min_size": 1, "max_size": 10}, ttl=ttl_config
             ) as store:
+                await store.start_ttl_sweeper()
                 yield store
+                await store.stop_ttl_sweeper()
         else:  # default
-            async with AsyncPostgresStore.from_conn_string(conn_string) as store:
+            async with AsyncPostgresStore.from_conn_string(
+                conn_string, ttl=ttl_config
+            ) as store:
+                await store.start_ttl_sweeper()
                 yield store
+                await store.stop_ttl_sweeper()
     finally:
         async with await AsyncConnection.connect(
             admin_conn_string, autocommit=True
@@ -635,3 +664,28 @@ async def test_search_sorting(
         assert len(set(r.key for r in results)) == 10
         assert results[0].key == "M"
         assert results[0].score > results[1].score
+
+
+async def test_store_ttl(store):
+    # Assumes a TTL of 1 minute = 60 seconds
+    ns = ("foo",)
+    await store.start_ttl_sweeper()
+    await store.aput(
+        ns,
+        key="item1",
+        value={"foo": "bar"},
+        ttl=TTL_MINUTES,  # type: ignore
+    )
+    await asyncio.sleep(TTL_SECONDS - 2)
+    res = await store.aget(ns, key="item1", refresh_ttl=True)
+    assert res is not None
+    await asyncio.sleep(TTL_SECONDS - 2)
+    results = await store.asearch(ns, query="foo", refresh_ttl=True)
+    assert len(results) == 1
+    await asyncio.sleep(TTL_SECONDS - 2)
+    res = await store.aget(ns, key="item1", refresh_ttl=False)
+    assert res is not None
+    await asyncio.sleep(TTL_SECONDS - 1)
+    # Now has been (TTL_SECONDS-2)*2 > TTL_SECONDS + TTL_SECONDS/2
+    results = await store.asearch(ns, query="bar", refresh_ttl=False)
+    assert len(results) == 0

libs/checkpoint-postgres/tests/test_store.py

@@ -1,6 +1,7 @@
 # type: ignore
 
 import re
+import time
 from contextlib import contextmanager
 from typing import Any, Optional
 from uuid import uuid4
@@ -24,6 +25,9 @@ from tests.conftest import (
     CharacterEmbeddings,
 )
 
+TTL_SECONDS = 6
+TTL_MINUTES = TTL_SECONDS / 60
+
 
 @pytest.fixture(scope="function", params=["default", "pipe", "pool"])
 def store(request) -> PostgresStore:
@@ -32,29 +36,56 @@ def store(request) -> PostgresStore:
     uri_base = "/".join(uri_parts[:-1])
     query_params = ""
     if "?" in uri_parts[-1]:
-        db_name, query_params = uri_parts[-1].split("?", 1)
+        _, query_params = uri_parts[-1].split("?", 1)
         query_params = "?" + query_params
 
     conn_string = f"{uri_base}/{database}{query_params}"
     admin_conn_string = DEFAULT_URI
-
+    ttl_config = {
+        "default_ttl": TTL_MINUTES,
+        "refresh_on_read": True,
+        "sweep_interval_minutes": TTL_MINUTES / 2,
+    }
     with Connection.connect(admin_conn_string, autocommit=True) as conn:
         conn.execute(f"CREATE DATABASE {database}")
     try:
-        with PostgresStore.from_conn_string(conn_string) as store:
+        with PostgresStore.from_conn_string(conn_string, ttl=ttl_config) as store:
+            store.MIGRATIONS = [
+                (
+                    mig.replace("ttl_minutes INT;", "ttl_minutes FLOAT;")
+                    if isinstance(mig, str)
+                    else mig
+                )
+                for mig in store.MIGRATIONS
+            ]
             store.setup()
 
         if request.param == "pipe":
-            with PostgresStore.from_conn_string(conn_string, pipeline=True) as store:
+            with PostgresStore.from_conn_string(
+                conn_string,
+                pipeline=True,
+                ttl=ttl_config,
+            ) as store:
+                store.start_ttl_sweeper()
                 yield store
+
+                store.stop_ttl_sweeper()
         elif request.param == "pool":
             with PostgresStore.from_conn_string(
-                conn_string, pool_config={"min_size": 1, "max_size": 10}
+                conn_string,
+                pool_config={"min_size": 1, "max_size": 10},
+                ttl=ttl_config,
             ) as store:
+                store.start_ttl_sweeper()
                 yield store
+
+                store.stop_ttl_sweeper()
         else:  # default
-            with PostgresStore.from_conn_string(conn_string) as store:
+            with PostgresStore.from_conn_string(conn_string, ttl=ttl_config) as store:
+                store.start_ttl_sweeper()
                 yield store
+
+                store.stop_ttl_sweeper()
     finally:
         with Connection.connect(admin_conn_string, autocommit=True) as conn:
             conn.execute(f"DROP DATABASE {database}")
@@ -220,134 +251,127 @@ def test_batch_list_namespaces_ops(store: PostgresStore) -> None:
     assert all(ns[-1] == "public" for ns in results[2])
 
 
-class TestPostgresStore:
-    @pytest.fixture(autouse=True)
-    def setup(self) -> None:
-        with PostgresStore.from_conn_string(DEFAULT_URI) as store:
-            store.setup()
+def test_basic_store_ops(store) -> None:
+    namespace = ("test", "documents")
+    item_id = "doc1"
+    item_value = {"title": "Test Document", "content": "Hello, World!"}
 
-    def test_basic_store_ops(self) -> None:
-        with PostgresStore.from_conn_string(DEFAULT_URI) as store:
-            namespace = ("test", "documents")
-            item_id = "doc1"
-            item_value = {"title": "Test Document", "content": "Hello, World!"}
+    store.put(namespace, item_id, item_value)
+    item = store.get(namespace, item_id)
 
-            store.put(namespace, item_id, item_value)
-            item = store.get(namespace, item_id)
+    assert item
+    assert item.namespace == namespace
+    assert item.key == item_id
+    assert item.value == item_value
 
-            assert item
-            assert item.namespace == namespace
-            assert item.key == item_id
-            assert item.value == item_value
+    # Test update
+    updated_value = {"title": "Updated Document", "content": "Hello, Updated!"}
+    store.put(namespace, item_id, updated_value)
+    updated_item = store.get(namespace, item_id)
 
-            # Test update
-            updated_value = {"title": "Updated Document", "content": "Hello, Updated!"}
-            store.put(namespace, item_id, updated_value)
-            updated_item = store.get(namespace, item_id)
+    assert updated_item.value == updated_value
+    assert updated_item.updated_at > item.updated_at
 
-            assert updated_item.value == updated_value
-            assert updated_item.updated_at > item.updated_at
+    # Test get from non-existent namespace
+    different_namespace = ("test", "other_documents")
+    item_in_different_namespace = store.get(different_namespace, item_id)
+    assert item_in_different_namespace is None
 
-            # Test get from non-existent namespace
-            different_namespace = ("test", "other_documents")
-            item_in_different_namespace = store.get(different_namespace, item_id)
-            assert item_in_different_namespace is None
+    # Test delete
+    store.delete(namespace, item_id)
+    deleted_item = store.get(namespace, item_id)
+    assert deleted_item is None
 
-            # Test delete
-            store.delete(namespace, item_id)
-            deleted_item = store.get(namespace, item_id)
-            assert deleted_item is None
 
-    def test_list_namespaces(self) -> None:
-        with PostgresStore.from_conn_string(DEFAULT_URI) as store:
-            # Create test data with various namespaces
-            test_namespaces = [
-                ("test", "documents", "public"),
-                ("test", "documents", "private"),
-                ("test", "images", "public"),
-                ("test", "images", "private"),
-                ("prod", "documents", "public"),
-                ("prod", "documents", "private"),
-            ]
+def test_list_namespaces(store) -> None:
+    # Create test data with various namespaces
+    test_namespaces = [
+        ("test", "documents", "public"),
+        ("test", "documents", "private"),
+        ("test", "images", "public"),
+        ("test", "images", "private"),
+        ("prod", "documents", "public"),
+        ("prod", "documents", "private"),
+    ]
 
-            # Insert test data
-            for namespace in test_namespaces:
-                store.put(namespace, "dummy", {"content": "dummy"})
+    # Insert test data
+    for namespace in test_namespaces:
+        store.put(namespace, "dummy", {"content": "dummy"})
 
-            # Test listing with various filters
-            all_namespaces = store.list_namespaces()
-            assert len(all_namespaces) == len(test_namespaces)
+    # Test listing with various filters
+    all_namespaces = store.list_namespaces()
+    assert len(all_namespaces) == len(test_namespaces)
 
-            # Test prefix filtering
-            test_prefix_namespaces = store.list_namespaces(prefix=["test"])
-            assert len(test_prefix_namespaces) == 4
-            assert all(ns[0] == "test" for ns in test_prefix_namespaces)
+    # Test prefix filtering
+    test_prefix_namespaces = store.list_namespaces(prefix=["test"])
+    assert len(test_prefix_namespaces) == 4
+    assert all(ns[0] == "test" for ns in test_prefix_namespaces)
 
-            # Test suffix filtering
-            public_namespaces = store.list_namespaces(suffix=["public"])
-            assert len(public_namespaces) == 3
-            assert all(ns[-1] == "public" for ns in public_namespaces)
+    # Test suffix filtering
+    public_namespaces = store.list_namespaces(suffix=["public"])
+    assert len(public_namespaces) == 3
+    assert all(ns[-1] == "public" for ns in public_namespaces)
 
-            # Test max depth
-            depth_2_namespaces = store.list_namespaces(max_depth=2)
-            assert all(len(ns) <= 2 for ns in depth_2_namespaces)
+    # Test max depth
+    depth_2_namespaces = store.list_namespaces(max_depth=2)
+    assert all(len(ns) <= 2 for ns in depth_2_namespaces)
 
-            # Test pagination
-            paginated_namespaces = store.list_namespaces(limit=3)
-            assert len(paginated_namespaces) == 3
+    # Test pagination
+    paginated_namespaces = store.list_namespaces(limit=3)
+    assert len(paginated_namespaces) == 3
 
-            # Cleanup
-            for namespace in test_namespaces:
-                store.delete(namespace, "dummy")
+    # Cleanup
+    for namespace in test_namespaces:
+        store.delete(namespace, "dummy")
 
-    def test_search(self) -> None:
-        with PostgresStore.from_conn_string(DEFAULT_URI) as store:
-            # Create test data
-            test_data = [
-                (
-                    ("test", "docs"),
-                    "doc1",
-                    {"title": "First Doc", "author": "Alice", "tags": ["important"]},
-                ),
-                (
-                    ("test", "docs"),
-                    "doc2",
-                    {"title": "Second Doc", "author": "Bob", "tags": ["draft"]},
-                ),
-                (
-                    ("test", "images"),
-                    "img1",
-                    {"title": "Image 1", "author": "Alice", "tags": ["final"]},
-                ),
-            ]
 
-            for namespace, key, value in test_data:
-                store.put(namespace, key, value)
+def test_search(store) -> None:
+    # Create test data
+    test_data = [
+        (
+            ("test", "docs"),
+            "doc1",
+            {"title": "First Doc", "author": "Alice", "tags": ["important"]},
+        ),
+        (
+            ("test", "docs"),
+            "doc2",
+            {"title": "Second Doc", "author": "Bob", "tags": ["draft"]},
+        ),
+        (
+            ("test", "images"),
+            "img1",
+            {"title": "Image 1", "author": "Alice", "tags": ["final"]},
+        ),
+    ]
 
-            # Test basic search
-            all_items = store.search(["test"])
-            assert len(all_items) == 3
+    for namespace, key, value in test_data:
+        store.put(namespace, key, value)
 
-            # Test namespace filtering
-            docs_items = store.search(["test", "docs"])
-            assert len(docs_items) == 2
-            assert all(item.namespace == ("test", "docs") for item in docs_items)
+    # Test basic search
+    all_items = store.search(["test"])
+    assert len(all_items) == 3
 
-            # Test value filtering
-            alice_items = store.search(["test"], filter={"author": "Alice"})
-            assert len(alice_items) == 2
-            assert all(item.value["author"] == "Alice" for item in alice_items)
+    # Test namespace filtering
+    docs_items = store.search(["test", "docs"])
+    assert len(docs_items) == 2
+    assert all(item.namespace == ("test", "docs") for item in docs_items)
 
-            # Test pagination
-            paginated_items = store.search(["test"], limit=2)
-            assert len(paginated_items) == 2
+    # Test value filtering
+    alice_items = store.search(["test"], filter={"author": "Alice"})
+    assert len(alice_items) == 2
+    assert all(item.value["author"] == "Alice" for item in alice_items)
 
-            offset_items = store.search(["test"], offset=2)
-            assert len(offset_items) == 1
+    # Test pagination
+    paginated_items = store.search(["test"], limit=2)
+    assert len(paginated_items) == 2
 
-            # Cleanup
-            for namespace, key, _ in test_data:
-                store.delete(namespace, key)
+    offset_items = store.search(["test"], offset=2)
+    assert len(offset_items) == 1
+
+    # Cleanup
+    for namespace, key, _ in test_data:
+        store.delete(namespace, key)
 
 
 @contextmanager
@@ -356,6 +380,7 @@ def _create_vector_store(
     distance_type: str,
     fake_embeddings: Embeddings,
     text_fields: Optional[list[str]] = None,
+    enable_ttl: bool = True,
 ) -> PostgresStore:
     """Create a store with vector search enabled."""
     database = f"test_{uuid4().hex[:16]}"
@@ -385,23 +410,32 @@ def _create_vector_store(
         with PostgresStore.from_conn_string(
             conn_string,
             index=index_config,
+            ttl={"default_ttl": 2, "refresh_on_read": True} if enable_ttl else None,
         ) as store:
             store.setup()
+            with store._cursor() as cur:
+                # drop the migration index
+                cur.execute("DROP TABLE IF EXISTS store_migrations")
+            store.setup()  # Will fail if migrations aren't idempotent
             yield store
     finally:
         with Connection.connect(admin_conn_string, autocommit=True) as conn:
             conn.execute(f"DROP DATABASE {database}")
 
 
+_vector_params = [
+    (vector_type, distance_type, True)
+    for vector_type in VECTOR_TYPES
+    for distance_type in (
+        ["hamming"] if vector_type == "bit" else ["l2", "inner_product", "cosine"]
+    )
+]
+_vector_params += [(*_vector_params[-1][:2], False)]
+
+
 @pytest.fixture(
     scope="function",
-    params=[
-        (vector_type, distance_type)
-        for vector_type in VECTOR_TYPES
-        for distance_type in (
-            ["hamming"] if vector_type == "bit" else ["l2", "inner_product", "cosine"]
-        )
-    ],
+    params=_vector_params,
     ids=lambda p: f"{p[0]}_{p[1]}",
 )
 def vector_store(
@@ -409,8 +443,10 @@ def vector_store(
     fake_embeddings: Embeddings,
 ) -> PostgresStore:
     """Create a store with vector search enabled."""
-    vector_type, distance_type = request.param
-    with _create_vector_store(vector_type, distance_type, fake_embeddings) as store:
+    vector_type, distance_type, enable_ttl = request.param
+    with _create_vector_store(
+        vector_type, distance_type, fake_embeddings, enable_ttl=enable_ttl
+    ) as store:
         yield store
 
 
@@ -474,7 +510,10 @@ def test_vector_update_with_embedding(vector_store: PostgresStore) -> None:
     assert not any(r.key == "doc4" for r in results_new)
 
 
-def test_vector_search_with_filters(vector_store: PostgresStore) -> None:
+@pytest.mark.parametrize("refresh_ttl", [True, False])
+def test_vector_search_with_filters(
+    vector_store: PostgresStore, refresh_ttl: bool
+) -> None:
     """Test combining vector search with filters."""
     # Insert test documents
     docs = [
@@ -487,16 +526,23 @@ def test_vector_search_with_filters(vector_store: PostgresStore) -> None:
     for key, value in docs:
         vector_store.put(("test",), key, value)
 
-    results = vector_store.search(("test",), query="apple", filter={"color": "red"})
+    results = vector_store.search(
+        ("test",), query="apple", filter={"color": "red"}, refresh_ttl=refresh_ttl
+    )
     assert len(results) == 2
     assert results[0].key == "doc1"
 
-    results = vector_store.search(("test",), query="car", filter={"color": "red"})
+    results = vector_store.search(
+        ("test",), query="car", filter={"color": "red"}, refresh_ttl=refresh_ttl
+    )
     assert len(results) == 2
     assert results[0].key == "doc2"
 
     results = vector_store.search(
-        ("test",), query="bbbbluuu", filter={"score": {"$gt": 3.2}}
+        ("test",),
+        query="bbbbluuu",
+        filter={"score": {"$gt": 3.2}},
+        refresh_ttl=refresh_ttl,
     )
     assert len(results) == 3
     assert results[0].key == "doc4"
@@ -688,7 +734,7 @@ def test_embed_with_path_operation_config(
         store.put(("test",), "doc5", doc5, index=False)
         results = store.search(("test",))
         assert len(results) == 3
-        assert all(r.score is None for r in results)
+        assert all(r.score is None for r in results), f"{results}"
         assert any(r.key == "doc5" for r in results)
 
         results = store.search(("test",), query="hhh")
@@ -790,3 +836,27 @@ def test_nonnull_migrations() -> None:
     for migration in PostgresStore.MIGRATIONS:
         statement = _leading_comment_remover.sub("", migration).split()[0]
         assert statement.strip()
+
+
+def test_store_ttl(store):
+    # Assumes a TTL of 1 minute = 60 seconds
+    ns = ("foo",)
+    store.put(
+        ns,
+        key="item1",
+        value={"foo": "bar"},
+        ttl=TTL_MINUTES,  # type: ignore
+    )
+    time.sleep(TTL_SECONDS - 2)
+    res = store.get(ns, key="item1", refresh_ttl=True)
+    assert res is not None
+    time.sleep(TTL_SECONDS - 2)
+    results = store.search(ns, query="foo", refresh_ttl=True)
+    assert len(results) == 1
+    time.sleep(TTL_SECONDS - 2)
+    res = store.get(ns, key="item1", refresh_ttl=False)
+    assert res is not None
+    time.sleep(TTL_SECONDS - 1)
+    # Now has been (TTL_SECONDS-2)*2 > TTL_SECONDS + TTL_SECONDS/2
+    res = store.search(ns, query="bar", refresh_ttl=False)
+    assert len(res) == 0

libs/checkpoint-sqlite/README.md

@@ -12,7 +12,7 @@ read_config = {"configurable": {"thread_id": "1"}}
 
 with SqliteSaver.from_conn_string(":memory:") as checkpointer:
     checkpoint = {
-        "v": 1,
+        "v": 2,
         "ts": "2024-07-31T20:14:19.804150+00:00",
         "id": "1ef4f797-8335-6428-8001-8a1503f9b875",
         "channel_values": {
@@ -54,7 +54,7 @@ from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver
 
 async with AsyncSqliteSaver.from_conn_string(":memory:") as checkpointer:
     checkpoint = {
-        "v": 1,
+        "v": 2,
         "ts": "2024-07-31T20:14:19.804150+00:00",
         "id": "1ef4f797-8335-6428-8001-8a1503f9b875",
         "channel_values": {

libs/checkpoint-sqlite/langgraph/checkpoint/sqlite/__init__.py

@@ -56,7 +56,10 @@ class SqliteSaver(BaseCheckpointSaver[str]):
         >>> builder.add_node("add_one", lambda x: x + 1)
         >>> builder.set_entry_point("add_one")
         >>> builder.set_finish_point("add_one")
-        >>> conn = sqlite3.connect("checkpoints.sqlite")
+        >>> # Create a new SqliteSaver instance
+        >>> # Note: check_same_thread=False is OK as the implementation uses a lock
+        >>> # to ensure thread safety.
+        >>> conn = sqlite3.connect("checkpoints.sqlite", check_same_thread=False)
         >>> memory = SqliteSaver(conn)
         >>> graph = builder.compile(checkpointer=memory)
         >>> config = {"configurable": {"thread_id": "1"}}

libs/checkpoint-sqlite/langgraph/checkpoint/sqlite/aio.py

@@ -70,15 +70,18 @@ class AsyncSqliteSaver(BaseCheckpointSaver[str]):
         >>> from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver
         >>> from langgraph.graph import StateGraph
         >>>
-        >>> builder = StateGraph(int)
-        >>> builder.add_node("add_one", lambda x: x + 1)
-        >>> builder.set_entry_point("add_one")
-        >>> builder.set_finish_point("add_one")
-        >>> async with AsyncSqliteSaver.from_conn_string("checkpoints.db") as memory:
-        >>>     graph = builder.compile(checkpointer=memory)
-        >>>     coro = graph.ainvoke(1, {"configurable": {"thread_id": "thread-1"}})
-        >>>     print(asyncio.run(coro))
-        Output: 2
+        >>> async def main():
+        >>>     builder = StateGraph(int)
+        >>>     builder.add_node("add_one", lambda x: x + 1)
+        >>>     builder.set_entry_point("add_one")
+        >>>     builder.set_finish_point("add_one")
+        >>>     async with AsyncSqliteSaver.from_conn_string("checkpoints.db") as memory:
+        >>>         graph = builder.compile(checkpointer=memory)
+        >>>         coro = graph.ainvoke(1, {"configurable": {"thread_id": "thread-1"}})
+        >>>         print(await asyncio.gather(coro))
+        >>>
+        >>> asyncio.run(main())
+        Output: [2]
         ```
         Raw usage:
 
@@ -90,12 +93,12 @@ class AsyncSqliteSaver(BaseCheckpointSaver[str]):
         >>> async def main():
         >>>     async with aiosqlite.connect("checkpoints.db") as conn:
         ...         saver = AsyncSqliteSaver(conn)
-        ...         config = {"configurable": {"thread_id": "1"}}
-        ...         checkpoint = {"ts": "2023-05-03T10:00:00Z", "data": {"key": "value"}}
+        ...         config = {"configurable": {"thread_id": "1", "checkpoint_ns": ""}}
+        ...         checkpoint = {"ts": "2023-05-03T10:00:00Z", "data": {"key": "value"}, "id": "0c62ca34-ac19-445d-bbb0-5b4984975b2a"}
         ...         saved_config = await saver.aput(config, checkpoint, {}, {})
         ...         print(saved_config)
         >>> asyncio.run(main())
-        {"configurable": {"thread_id": "1", "checkpoint_id": "0c62ca34-ac19-445d-bbb0-5b4984975b2a"}}
+        {'configurable': {'thread_id': '1', 'checkpoint_ns': '', 'checkpoint_id': '0c62ca34-ac19-445d-bbb0-5b4984975b2a'}}
         ```
     """
 
@@ -530,6 +533,7 @@ class AsyncSqliteSaver(BaseCheckpointSaver[str]):
                     for idx, (channel, value) in enumerate(writes)
                 ],
             )
+            await self.conn.commit()
 
     def get_next_version(self, current: Optional[str], channel: ChannelProtocol) -> str:
         """Generate the next version ID for a channel.

libs/checkpoint-sqlite/poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 2.0.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 2.1.1 and should not be changed by hand.
 
 [[package]]
 name = "aiosqlite"
@@ -51,7 +51,7 @@ typing-extensions = {version = ">=4.1", markers = "python_version < \"3.11\""}
 
 [package.extras]
 doc = ["Sphinx (>=7)", "packaging", "sphinx-autodoc-typehints (>=1.2.0)", "sphinx-rtd-theme"]
-test = ["anyio[trio]", "coverage[toml] (>=7)", "exceptiongroup (>=1.2.0)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "uvloop (>=0.17)"]
+test = ["anyio[trio]", "coverage[toml] (>=7)", "exceptiongroup (>=1.2.0)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "uvloop (>=0.17) ; platform_python_implementation == \"CPython\" and platform_system != \"Windows\""]
 trio = ["trio (>=0.23)"]
 
 [[package]]
@@ -181,7 +181,7 @@ files = [
 [package.extras]
 dev = ["Pygments", "build", "chardet", "pre-commit", "pytest", "pytest-cov", "pytest-dependency", "ruff", "tomli", "twine"]
 hard-encoding-detection = ["chardet"]
-toml = ["tomli"]
+toml = ["tomli ; python_version < \"3.11\""]
 types = ["chardet (>=5.1.0)", "mypy", "pytest", "pytest-cov", "pytest-dependency"]
 
 [[package]]
@@ -267,7 +267,7 @@ idna = "*"
 sniffio = "*"
 
 [package.extras]
-brotli = ["brotli", "brotlicffi"]
+brotli = ["brotli ; platform_python_implementation == \"CPython\"", "brotlicffi ; platform_python_implementation != \"CPython\""]
 cli = ["click (==8.*)", "pygments (==2.*)", "rich (>=10,<14)"]
 http2 = ["h2 (>=3,<5)"]
 socks = ["socksio (==1.*)"]
@@ -326,31 +326,31 @@ files = [
 
 [[package]]
 name = "langchain-core"
-version = "0.3.0"
+version = "0.3.15"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = "<4.0,>=3.9"
 groups = ["main", "dev"]
 files = [
-    {file = "langchain_core-0.3.0-py3-none-any.whl", hash = "sha256:bee6dae2366d037ef0c5b87401fed14b5497cad26f97724e8c9ca7bc9239e847"},
-    {file = "langchain_core-0.3.0.tar.gz", hash = "sha256:1249149ea3ba24c9c761011483c14091573a5eb1a773aa0db9c8ad155dd4a69d"},
+    {file = "langchain_core-0.3.15-py3-none-any.whl", hash = "sha256:3d4ca6dbb8ed396a6ee061063832a2451b0ce8c345570f7b086ffa7288e4fa29"},
+    {file = "langchain_core-0.3.15.tar.gz", hash = "sha256:b1a29787a4ffb7ec2103b4e97d435287201da7809b369740dd1e32f176325aba"},
 ]
 
 [package.dependencies]
 jsonpatch = ">=1.33,<2.0"
-langsmith = ">=0.1.117,<0.2.0"
+langsmith = ">=0.1.125,<0.2.0"
 packaging = ">=23.2,<25"
 pydantic = [
     {version = ">=2.5.2,<3.0.0", markers = "python_full_version < \"3.12.4\""},
     {version = ">=2.7.4,<3.0.0", markers = "python_full_version >= \"3.12.4\""},
 ]
 PyYAML = ">=5.3"
-tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<9.0.0"
+tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<10.0.0"
 typing-extensions = ">=4.7"
 
 [[package]]
 name = "langgraph-checkpoint"
-version = "2.0.15"
+version = "2.0.21"
 description = "Library with base interfaces for LangGraph checkpoint savers."
 optional = false
 python-versions = "^3.9.0,<4.0"
@@ -360,7 +360,7 @@ develop = true
 
 [package.dependencies]
 langchain-core = ">=0.2.38,<0.4"
-msgpack = "^1.1.0"
+ormsgpack = "^1.8.0"
 
 [package.source]
 type = "directory"
@@ -368,98 +368,28 @@ url = "../checkpoint"
 
 [[package]]
 name = "langsmith"
-version = "0.1.120"
+version = "0.1.147"
 description = "Client library to connect to the LangSmith LLM Tracing and Evaluation Platform."
 optional = false
 python-versions = "<4.0,>=3.8.1"
 groups = ["main", "dev"]
 files = [
-    {file = "langsmith-0.1.120-py3-none-any.whl", hash = "sha256:54d2785e301646c0988e0a69ebe4d976488c87b41928b358cb153b6ddd8db62b"},
-    {file = "langsmith-0.1.120.tar.gz", hash = "sha256:25499ca187b41bd89d784b272b97a8d76f60e0e21bdf20336e8a2aa6a9b23ac9"},
+    {file = "langsmith-0.1.147-py3-none-any.whl", hash = "sha256:7166fc23b965ccf839d64945a78e9f1157757add228b086141eb03a60d699a15"},
+    {file = "langsmith-0.1.147.tar.gz", hash = "sha256:2e933220318a4e73034657103b3b1a3a6109cc5db3566a7e8e03be8d6d7def7a"},
 ]
 
 [package.dependencies]
 httpx = ">=0.23.0,<1"
-orjson = ">=3.9.14,<4.0.0"
+orjson = {version = ">=3.9.14,<4.0.0", markers = "platform_python_implementation != \"PyPy\""}
 pydantic = [
     {version = ">=1,<3", markers = "python_full_version < \"3.12.4\""},
     {version = ">=2.7.4,<3.0.0", markers = "python_full_version >= \"3.12.4\""},
 ]
 requests = ">=2,<3"
+requests-toolbelt = ">=1.0.0,<2.0.0"
 
-[[package]]
-name = "msgpack"
-version = "1.1.0"
-description = "MessagePack serializer"
-optional = false
-python-versions = ">=3.8"
-groups = ["main", "dev"]
-files = [
-    {file = "msgpack-1.1.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:7ad442d527a7e358a469faf43fda45aaf4ac3249c8310a82f0ccff9164e5dccd"},
-    {file = "msgpack-1.1.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:74bed8f63f8f14d75eec75cf3d04ad581da6b914001b474a5d3cd3372c8cc27d"},
-    {file = "msgpack-1.1.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:914571a2a5b4e7606997e169f64ce53a8b1e06f2cf2c3a7273aa106236d43dd5"},
-    {file = "msgpack-1.1.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c921af52214dcbb75e6bdf6a661b23c3e6417f00c603dd2070bccb5c3ef499f5"},
-    {file = "msgpack-1.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d8ce0b22b890be5d252de90d0e0d119f363012027cf256185fc3d474c44b1b9e"},
-    {file = "msgpack-1.1.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:73322a6cc57fcee3c0c57c4463d828e9428275fb85a27aa2aa1a92fdc42afd7b"},
-    {file = "msgpack-1.1.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:e1f3c3d21f7cf67bcf2da8e494d30a75e4cf60041d98b3f79875afb5b96f3a3f"},
-    {file = "msgpack-1.1.0-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:64fc9068d701233effd61b19efb1485587560b66fe57b3e50d29c5d78e7fef68"},
-    {file = "msgpack-1.1.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:42f754515e0f683f9c79210a5d1cad631ec3d06cea5172214d2176a42e67e19b"},
-    {file = "msgpack-1.1.0-cp310-cp310-win32.whl", hash = "sha256:3df7e6b05571b3814361e8464f9304c42d2196808e0119f55d0d3e62cd5ea044"},
-    {file = "msgpack-1.1.0-cp310-cp310-win_amd64.whl", hash = "sha256:685ec345eefc757a7c8af44a3032734a739f8c45d1b0ac45efc5d8977aa4720f"},
-    {file = "msgpack-1.1.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:3d364a55082fb2a7416f6c63ae383fbd903adb5a6cf78c5b96cc6316dc1cedc7"},
-    {file = "msgpack-1.1.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:79ec007767b9b56860e0372085f8504db5d06bd6a327a335449508bbee9648fa"},
-    {file = "msgpack-1.1.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:6ad622bf7756d5a497d5b6836e7fc3752e2dd6f4c648e24b1803f6048596f701"},
-    {file = "msgpack-1.1.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8e59bca908d9ca0de3dc8684f21ebf9a690fe47b6be93236eb40b99af28b6ea6"},
-    {file = "msgpack-1.1.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5e1da8f11a3dd397f0a32c76165cf0c4eb95b31013a94f6ecc0b280c05c91b59"},
-    {file = "msgpack-1.1.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:452aff037287acb1d70a804ffd022b21fa2bb7c46bee884dbc864cc9024128a0"},
-    {file = "msgpack-1.1.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:8da4bf6d54ceed70e8861f833f83ce0814a2b72102e890cbdfe4b34764cdd66e"},
-    {file = "msgpack-1.1.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:41c991beebf175faf352fb940bf2af9ad1fb77fd25f38d9142053914947cdbf6"},
-    {file = "msgpack-1.1.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:a52a1f3a5af7ba1c9ace055b659189f6c669cf3657095b50f9602af3a3ba0fe5"},
-    {file = "msgpack-1.1.0-cp311-cp311-win32.whl", hash = "sha256:58638690ebd0a06427c5fe1a227bb6b8b9fdc2bd07701bec13c2335c82131a88"},
-    {file = "msgpack-1.1.0-cp311-cp311-win_amd64.whl", hash = "sha256:fd2906780f25c8ed5d7b323379f6138524ba793428db5d0e9d226d3fa6aa1788"},
-    {file = "msgpack-1.1.0-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:d46cf9e3705ea9485687aa4001a76e44748b609d260af21c4ceea7f2212a501d"},
-    {file = "msgpack-1.1.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:5dbad74103df937e1325cc4bfeaf57713be0b4f15e1c2da43ccdd836393e2ea2"},
-    {file = "msgpack-1.1.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:58dfc47f8b102da61e8949708b3eafc3504509a5728f8b4ddef84bd9e16ad420"},
-    {file = "msgpack-1.1.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4676e5be1b472909b2ee6356ff425ebedf5142427842aa06b4dfd5117d1ca8a2"},
-    {file = "msgpack-1.1.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:17fb65dd0bec285907f68b15734a993ad3fc94332b5bb21b0435846228de1f39"},
-    {file = "msgpack-1.1.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a51abd48c6d8ac89e0cfd4fe177c61481aca2d5e7ba42044fd218cfd8ea9899f"},
-    {file = "msgpack-1.1.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:2137773500afa5494a61b1208619e3871f75f27b03bcfca7b3a7023284140247"},
-    {file = "msgpack-1.1.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:398b713459fea610861c8a7b62a6fec1882759f308ae0795b5413ff6a160cf3c"},
-    {file = "msgpack-1.1.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:06f5fd2f6bb2a7914922d935d3b8bb4a7fff3a9a91cfce6d06c13bc42bec975b"},
-    {file = "msgpack-1.1.0-cp312-cp312-win32.whl", hash = "sha256:ad33e8400e4ec17ba782f7b9cf868977d867ed784a1f5f2ab46e7ba53b6e1e1b"},
-    {file = "msgpack-1.1.0-cp312-cp312-win_amd64.whl", hash = "sha256:115a7af8ee9e8cddc10f87636767857e7e3717b7a2e97379dc2054712693e90f"},
-    {file = "msgpack-1.1.0-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:071603e2f0771c45ad9bc65719291c568d4edf120b44eb36324dcb02a13bfddf"},
-    {file = "msgpack-1.1.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:0f92a83b84e7c0749e3f12821949d79485971f087604178026085f60ce109330"},
-    {file = "msgpack-1.1.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:4a1964df7b81285d00a84da4e70cb1383f2e665e0f1f2a7027e683956d04b734"},
-    {file = "msgpack-1.1.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:59caf6a4ed0d164055ccff8fe31eddc0ebc07cf7326a2aaa0dbf7a4001cd823e"},
-    {file = "msgpack-1.1.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0907e1a7119b337971a689153665764adc34e89175f9a34793307d9def08e6ca"},
-    {file = "msgpack-1.1.0-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:65553c9b6da8166e819a6aa90ad15288599b340f91d18f60b2061f402b9a4915"},
-    {file = "msgpack-1.1.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:7a946a8992941fea80ed4beae6bff74ffd7ee129a90b4dd5cf9c476a30e9708d"},
-    {file = "msgpack-1.1.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:4b51405e36e075193bc051315dbf29168d6141ae2500ba8cd80a522964e31434"},
-    {file = "msgpack-1.1.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:b4c01941fd2ff87c2a934ee6055bda4ed353a7846b8d4f341c428109e9fcde8c"},
-    {file = "msgpack-1.1.0-cp313-cp313-win32.whl", hash = "sha256:7c9a35ce2c2573bada929e0b7b3576de647b0defbd25f5139dcdaba0ae35a4cc"},
-    {file = "msgpack-1.1.0-cp313-cp313-win_amd64.whl", hash = "sha256:bce7d9e614a04d0883af0b3d4d501171fbfca038f12c77fa838d9f198147a23f"},
-    {file = "msgpack-1.1.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c40ffa9a15d74e05ba1fe2681ea33b9caffd886675412612d93ab17b58ea2fec"},
-    {file = "msgpack-1.1.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f1ba6136e650898082d9d5a5217d5906d1e138024f836ff48691784bbe1adf96"},
-    {file = "msgpack-1.1.0-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e0856a2b7e8dcb874be44fea031d22e5b3a19121be92a1e098f46068a11b0870"},
-    {file = "msgpack-1.1.0-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:471e27a5787a2e3f974ba023f9e265a8c7cfd373632247deb225617e3100a3c7"},
-    {file = "msgpack-1.1.0-cp38-cp38-musllinux_1_2_i686.whl", hash = "sha256:646afc8102935a388ffc3914b336d22d1c2d6209c773f3eb5dd4d6d3b6f8c1cb"},
-    {file = "msgpack-1.1.0-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:13599f8829cfbe0158f6456374e9eea9f44eee08076291771d8ae93eda56607f"},
-    {file = "msgpack-1.1.0-cp38-cp38-win32.whl", hash = "sha256:8a84efb768fb968381e525eeeb3d92857e4985aacc39f3c47ffd00eb4509315b"},
-    {file = "msgpack-1.1.0-cp38-cp38-win_amd64.whl", hash = "sha256:879a7b7b0ad82481c52d3c7eb99bf6f0645dbdec5134a4bddbd16f3506947feb"},
-    {file = "msgpack-1.1.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:53258eeb7a80fc46f62fd59c876957a2d0e15e6449a9e71842b6d24419d88ca1"},
-    {file = "msgpack-1.1.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:7e7b853bbc44fb03fbdba34feb4bd414322180135e2cb5164f20ce1c9795ee48"},
-    {file = "msgpack-1.1.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:f3e9b4936df53b970513eac1758f3882c88658a220b58dcc1e39606dccaaf01c"},
-    {file = "msgpack-1.1.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:46c34e99110762a76e3911fc923222472c9d681f1094096ac4102c18319e6468"},
-    {file = "msgpack-1.1.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8a706d1e74dd3dea05cb54580d9bd8b2880e9264856ce5068027eed09680aa74"},
-    {file = "msgpack-1.1.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:534480ee5690ab3cbed89d4c8971a5c631b69a8c0883ecfea96c19118510c846"},
-    {file = "msgpack-1.1.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:8cf9e8c3a2153934a23ac160cc4cba0ec035f6867c8013cc6077a79823370346"},
-    {file = "msgpack-1.1.0-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:3180065ec2abbe13a4ad37688b61b99d7f9e012a535b930e0e683ad6bc30155b"},
-    {file = "msgpack-1.1.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:c5a91481a3cc573ac8c0d9aace09345d989dc4a0202b7fcb312c88c26d4e71a8"},
-    {file = "msgpack-1.1.0-cp39-cp39-win32.whl", hash = "sha256:f80bc7d47f76089633763f952e67f8214cb7b3ee6bfa489b3cb6a84cfac114cd"},
-    {file = "msgpack-1.1.0-cp39-cp39-win_amd64.whl", hash = "sha256:4d1b7ff2d6146e16e8bd665ac726a89c74163ef8cd39fa8c1087d4e52d3a2325"},
-    {file = "msgpack-1.1.0.tar.gz", hash = "sha256:dd432ccc2c72b914e4cb77afce64aab761c1137cc698be3984eee260bcb2896e"},
-]
+[package.extras]
+langsmith-pyo3 = ["langsmith-pyo3 (>=0.1.0rc2,<0.2.0)"]
 
 [[package]]
 name = "mypy"
@@ -528,6 +458,7 @@ description = "Fast, correct Python JSON library supporting dataclasses, datetim
 optional = false
 python-versions = ">=3.8"
 groups = ["main", "dev"]
+markers = "platform_python_implementation != \"PyPy\""
 files = [
     {file = "orjson-3.10.6-cp310-cp310-macosx_10_15_x86_64.macosx_11_0_arm64.macosx_10_15_universal2.whl", hash = "sha256:fb0ee33124db6eaa517d00890fc1a55c3bfe1cf78ba4a8899d71a06f2d6ff5c7"},
     {file = "orjson-3.10.6-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9c1c4b53b24a4c06547ce43e5fee6ec4e0d8fe2d597f4647fc033fd205707365"},
@@ -584,6 +515,42 @@ files = [
     {file = "orjson-3.10.6.tar.gz", hash = "sha256:e54b63d0a7c6c54a5f5f726bc93a2078111ef060fec4ecbf34c5db800ca3b3a7"},
 ]
 
+[[package]]
+name = "ormsgpack"
+version = "1.9.0"
+description = "Fast, correct Python msgpack library supporting dataclasses, datetimes, and numpy"
+optional = false
+python-versions = ">=3.9"
+groups = ["main", "dev"]
+files = [
+    {file = "ormsgpack-1.9.0-cp310-cp310-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:9c7cc221489aaf8bf394225a275edf068f3531529def415a8e6e32d6228ee138"},
+    {file = "ormsgpack-1.9.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42a5c5028417e710e5169c77d90b08891299f77ffd87abbb2855ffc62314740a"},
+    {file = "ormsgpack-1.9.0-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:350fdfac11215234b14d7fb484cf8f3f524eb0e7c6a3614bf878f4d034c1cef2"},
+    {file = "ormsgpack-1.9.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ebb49ca6d3f8dca7b667397016cb2cab7e6581b1d85b30f2697824479150e31e"},
+    {file = "ormsgpack-1.9.0-cp310-cp310-win_amd64.whl", hash = "sha256:ec9ad897bf00c4933bea519d505b82e20f9e0972bdd458dd1e06d6d5e0b8eec6"},
+    {file = "ormsgpack-1.9.0-cp311-cp311-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:5b473282dacddf20f03b99971e3fc3691bbeafc6142c8e51e80f137e35147ec9"},
+    {file = "ormsgpack-1.9.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:84bbd03ebca6efb38cb697e2e24f9ae22feb58ef1e6e664239ae68f4ccb3db76"},
+    {file = "ormsgpack-1.9.0-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:49e7e3612f1930267ddf85e914ba417bf5fa801e4a045acb466fa8a8bf7f8bf8"},
+    {file = "ormsgpack-1.9.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:da0aa79373e70c8ad32c0a23f410a7d611a13ea4f1e427f501307a487caf0557"},
+    {file = "ormsgpack-1.9.0-cp311-cp311-win_amd64.whl", hash = "sha256:6dfecbe00e504ccf946fc168ad56d038682fd17592da1be44368ab996fbeae3e"},
+    {file = "ormsgpack-1.9.0-cp312-cp312-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:6f13a538674ee42764278b418f9e97743401cd3895c7c473d45abd03f650169b"},
+    {file = "ormsgpack-1.9.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:332d85cbf3775b96b6eacdd0c03758517b530365dfa6e55981190062d840be47"},
+    {file = "ormsgpack-1.9.0-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:4b9de72dc94f73d63047ad40cfdd6e9dd2b28c51e9ccbc72117d5146b4f5fc18"},
+    {file = "ormsgpack-1.9.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4577cf304fa4c079092280e9ed4858cd9bd8b1475a803c206a449a3830b499ef"},
+    {file = "ormsgpack-1.9.0-cp312-cp312-win_amd64.whl", hash = "sha256:32302872cf10e4eccc8437cdaf46ac8e5e56cbb7519734a0b8f8a1ed2cbdfd44"},
+    {file = "ormsgpack-1.9.0-cp313-cp313-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:6ccbdf412af6c46b3549929d90a960ebe1b45f9b3e6c530774cd29de0846ce4d"},
+    {file = "ormsgpack-1.9.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5a6e113502c002f12f6bcf100eb8c2ccb85d1e75931ede669765ffaf5cc0e69d"},
+    {file = "ormsgpack-1.9.0-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:afd8bc92bb903fc37ce16921bb522d205ba02b90871dc4edc6fac13ac9226481"},
+    {file = "ormsgpack-1.9.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:800d918e6bca16d01c382015a4c05b00cabafa7c2070126b7feaefe2cf1437f0"},
+    {file = "ormsgpack-1.9.0-cp313-cp313-win_amd64.whl", hash = "sha256:305ec6de5fd687b7de0861673e967b4f6474a634b159a3a82e481707308203c9"},
+    {file = "ormsgpack-1.9.0-cp39-cp39-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:ecd28f5e0a07578972c9681034f1a6413ac0d0f016ff09db47dd9a7e8191d57a"},
+    {file = "ormsgpack-1.9.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0767bde96b932c70f3e1dd0e82a5c3dd969e2223edd7e8b3303cba1fa38473d1"},
+    {file = "ormsgpack-1.9.0-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:58b7c35bb813bb461b2bf848e99e129d536f6ed47f1d1c49e3de02748fe8554f"},
+    {file = "ormsgpack-1.9.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9aa6bc3904fbc4e6538e1bb3f2748f5cbc34906597724a3f0b8f578972a21fae"},
+    {file = "ormsgpack-1.9.0-cp39-cp39-win_amd64.whl", hash = "sha256:09f7b11abc0b493735870f3dea5daf36a147916b0609f394d45373f5ae4b6850"},
+    {file = "ormsgpack-1.9.0.tar.gz", hash = "sha256:015e8e6e74e5a1c2bcb9c25fdd8205cad0e8e2d1d32c6a259615aa189b61b8b4"},
+]
+
 [[package]]
 name = "packaging"
 version = "24.1"
@@ -896,6 +863,21 @@ urllib3 = ">=1.21.1,<3"
 socks = ["PySocks (>=1.5.6,!=1.5.7)"]
 use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
 
+[[package]]
+name = "requests-toolbelt"
+version = "1.0.0"
+description = "A utility belt for advanced users of python-requests"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+groups = ["main", "dev"]
+files = [
+    {file = "requests-toolbelt-1.0.0.tar.gz", hash = "sha256:7681a0a3d047012b5bdc0ee37d7f8f07ebe76ab08caeccfc3921ce23c88d5bc6"},
+    {file = "requests_toolbelt-1.0.0-py2.py3-none-any.whl", hash = "sha256:cccfdd665f0a24fcf4726e690f65639d272bb0637b9b92dfd91a5568ccf6bd06"},
+]
+
+[package.dependencies]
+requests = ">=2.0.1,<3.0.0"
+
 [[package]]
 name = "ruff"
 version = "0.6.2"
@@ -990,7 +972,7 @@ files = [
 ]
 
 [package.extras]
-brotli = ["brotli (>=1.0.9)", "brotlicffi (>=0.8.0)"]
+brotli = ["brotli (>=1.0.9) ; platform_python_implementation == \"CPython\"", "brotlicffi (>=0.8.0) ; platform_python_implementation != \"CPython\""]
 h2 = ["h2 (>=4,<5)"]
 socks = ["pysocks (>=1.5.6,!=1.5.7,<2.0)"]
 zstd = ["zstandard (>=0.18.0)"]

libs/checkpoint-sqlite/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langgraph-checkpoint-sqlite"
-version = "2.0.5"
+version = "2.0.6"
 description = "Library with a SQLite implementation of LangGraph checkpoint saver."
 authors = []
 license = "MIT"

libs/checkpoint/README.md

@@ -51,7 +51,7 @@ read_config = {"configurable": {"thread_id": "1"}}
 
 checkpointer = MemorySaver()
 checkpoint = {
-    "v": 1,
+    "v": 2,
     "ts": "2024-07-31T20:14:19.804150+00:00",
     "id": "1ef4f797-8335-6428-8001-8a1503f9b875",
     "channel_values": {

libs/checkpoint/langgraph/checkpoint/base/__init__.py

@@ -30,6 +30,8 @@ from langgraph.checkpoint.serde.types import (
 
 V = TypeVar("V", int, float, str)
 PendingWrite = Tuple[str, str, Any]
+# Kept for backwards compat, newer versions of LangGraph no longer use this.
+LATEST_VERSION = 2
 
 
 # Marked as total=False to allow for future expansion.
@@ -99,9 +101,10 @@ class Checkpoint(TypedDict):
     Cleared by the next checkpoint."""
 
 
+# Kept for backwards compat, newer versions of LangGraph no longer use this.
 def empty_checkpoint() -> Checkpoint:
     return Checkpoint(
-        v=1,
+        v=LATEST_VERSION,
         id=str(uuid6(clock_seq=-2)),
         ts=datetime.now(timezone.utc).isoformat(),
         channel_values={},
@@ -123,6 +126,7 @@ def copy_checkpoint(checkpoint: Checkpoint) -> Checkpoint:
     )
 
 
+# Kept for backwards compat, newer versions of LangGraph no longer use this.
 def create_checkpoint(
     checkpoint: Checkpoint,
     channels: Optional[Mapping[str, ChannelProtocol]],
@@ -144,7 +148,7 @@ def create_checkpoint(
             except EmptyChannelError:
                 pass
     return Checkpoint(
-        v=1,
+        v=LATEST_VERSION,
         ts=ts,
         id=id or str(uuid6(clock_seq=step)),
         channel_values=values,

libs/checkpoint/langgraph/checkpoint/memory/__init__.py

@@ -7,7 +7,7 @@ from collections import defaultdict
 from collections.abc import AsyncIterator, Iterator, Sequence
 from contextlib import AbstractAsyncContextManager, AbstractContextManager, ExitStack
 from types import TracebackType
-from typing import Any, Optional
+from typing import Any, Optional, Union
 
 from langchain_core.runnables import RunnableConfig
 
@@ -70,6 +70,12 @@ class InMemorySaver(
         tuple[str, str, str],
         dict[tuple[str, int], tuple[str, str, tuple[str, bytes], str]],
     ]
+    blobs: dict[
+        tuple[
+            str, str, str, Union[str, int, float]
+        ],  # thread id, checkpoint ns, channel, version
+        tuple[str, bytes],
+    ]
 
     def __init__(
         self,
@@ -80,6 +86,7 @@ class InMemorySaver(
         super().__init__(serde=serde)
         self.storage = factory(lambda: defaultdict(dict))
         self.writes = factory(dict)
+        self.blobs = factory()
         self.stack = ExitStack()
         if factory is not defaultdict:
             self.stack.enter_context(self.storage)  # type: ignore[arg-type]
@@ -107,6 +114,18 @@ class InMemorySaver(
     ) -> Optional[bool]:
         return self.stack.__exit__(__exc_type, __exc_value, __traceback)
 
+    def _load_blobs(
+        self, thread_id: str, checkpoint_ns: str, versions: ChannelVersions
+    ) -> dict[str, Any]:
+        channel_values: dict[str, Any] = {}
+        for k, v in versions.items():
+            kk = (thread_id, checkpoint_ns, k, v)
+            if kk in self.blobs:
+                vv = self.blobs[kk]
+                if vv[0] != "empty":
+                    channel_values[k] = self.serde.loads_typed(vv)
+        return channel_values
+
     def get_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
         """Get a checkpoint tuple from the in-memory storage.
 
@@ -121,8 +140,8 @@ class InMemorySaver(
         Returns:
             Optional[CheckpointTuple]: The retrieved checkpoint tuple, or None if no matching checkpoint was found.
         """
-        thread_id = config["configurable"]["thread_id"]
-        checkpoint_ns = config["configurable"].get("checkpoint_ns", "")
+        thread_id: str = config["configurable"]["thread_id"]
+        checkpoint_ns: str = config["configurable"].get("checkpoint_ns", "")
         if checkpoint_id := get_checkpoint_id(config):
             if saved := self.storage[thread_id][checkpoint_ns].get(checkpoint_id):
                 checkpoint, metadata, parent_checkpoint_id = saved
@@ -140,10 +159,14 @@ class InMemorySaver(
                     )
                 else:
                     sends = []
+                checkpoint_: Checkpoint = self.serde.loads_typed(checkpoint)
                 return CheckpointTuple(
                     config=config,
                     checkpoint={
-                        **self.serde.loads_typed(checkpoint),
+                        **checkpoint_,
+                        "channel_values": self._load_blobs(
+                            thread_id, checkpoint_ns, checkpoint_["channel_versions"]
+                        ),
                         "pending_sends": [self.serde.loads_typed(s[2]) for s in sends],
                     },
                     metadata=self.serde.loads_typed(metadata),
@@ -180,6 +203,9 @@ class InMemorySaver(
                     )
                 else:
                     sends = []
+
+                checkpoint_ = self.serde.loads_typed(checkpoint)
+
                 return CheckpointTuple(
                     config={
                         "configurable": {
@@ -189,7 +215,10 @@ class InMemorySaver(
                         }
                     },
                     checkpoint={
-                        **self.serde.loads_typed(checkpoint),
+                        **checkpoint_,
+                        "channel_values": self._load_blobs(
+                            thread_id, checkpoint_ns, checkpoint_["channel_versions"]
+                        ),
                         "pending_sends": [self.serde.loads_typed(s[2]) for s in sends],
                     },
                     metadata=self.serde.loads_typed(metadata),
@@ -297,6 +326,8 @@ class InMemorySaver(
                     else:
                         sends = []
 
+                    checkpoint_: Checkpoint = self.serde.loads_typed(checkpoint)
+
                     yield CheckpointTuple(
                         config={
                             "configurable": {
@@ -306,7 +337,12 @@ class InMemorySaver(
                             }
                         },
                         checkpoint={
-                            **self.serde.loads_typed(checkpoint),
+                            **checkpoint_,
+                            "channel_values": self._load_blobs(
+                                thread_id,
+                                checkpoint_ns,
+                                checkpoint_["channel_versions"],
+                            ),
                             "pending_sends": [
                                 self.serde.loads_typed(s[2]) for s in sends
                             ],
@@ -353,6 +389,11 @@ class InMemorySaver(
         c.pop("pending_sends")  # type: ignore[misc]
         thread_id = config["configurable"]["thread_id"]
         checkpoint_ns = config["configurable"]["checkpoint_ns"]
+        values: dict[str, Any] = c.pop("channel_values")  # type: ignore[misc]
+        for k, v in new_versions.items():
+            self.blobs[(thread_id, checkpoint_ns, k, v)] = (
+                self.serde.dumps_typed(values[k]) if k in values else ("empty", b"")
+            )
         self.storage[thread_id][checkpoint_ns].update(
             {
                 checkpoint["id"]: (

libs/checkpoint/langgraph/checkpoint/serde/base.py

@@ -45,3 +45,18 @@ def maybe_add_typed_methods(serde: SerializerProtocol) -> SerializerProtocol:
         return SerializerCompat(serde)
 
     return serde
+
+
+class CipherProtocol(Protocol):
+    """Protocol for encryption and decryption of data.
+    - `encrypt`: Encrypt plaintext.
+    - `decrypt`: Decrypt ciphertext.
+    """
+
+    def encrypt(self, plaintext: bytes) -> tuple[str, bytes]:
+        """Encrypt plaintext. Returns a tuple (cipher name, ciphertext)."""
+        ...
+
+    def decrypt(self, ciphername: str, ciphertext: bytes) -> bytes:
+        """Decrypt ciphertext. Returns the plaintext."""
+        ...

libs/checkpoint/langgraph/checkpoint/serde/encrypted.py

@@ -0,0 +1,86 @@
+import os
+from typing import Any
+
+from langgraph.checkpoint.serde.base import CipherProtocol, SerializerProtocol
+from langgraph.checkpoint.serde.jsonplus import JsonPlusSerializer
+
+
+class EncryptedSerializer(SerializerProtocol):
+    """Serializer that encrypts and decrypts data using an encryption protocol."""
+
+    def __init__(
+        self, cipher: CipherProtocol, serde: SerializerProtocol = JsonPlusSerializer()
+    ) -> None:
+        self.cipher = cipher
+        self.serde = serde
+
+    def dumps(self, obj: Any) -> bytes:
+        return self.serde.dumps(obj)
+
+    def loads(self, data: bytes) -> Any:
+        return self.serde.loads(data)
+
+    def dumps_typed(self, obj: Any) -> tuple[str, bytes]:
+        """Serialize an object to a tuple (type, bytes) and encrypt the bytes."""
+        # serialize data
+        typ, data = self.serde.dumps_typed(obj)
+        # encrypt data
+        ciphername, ciphertext = self.cipher.encrypt(data)
+        # add cipher name to type
+        return f"{typ}+{ciphername}", ciphertext
+
+    def loads_typed(self, data: tuple[str, bytes]) -> Any:
+        enc_cipher, ciphertext = data
+        # unencrypted data
+        if "+" not in enc_cipher:
+            return self.serde.loads_typed(data)
+        # extract cipher name
+        typ, ciphername = enc_cipher.split("+", 1)
+        # decrypt data
+        decrypted_data = self.cipher.decrypt(ciphername, ciphertext)
+        # deserialize data
+        return self.serde.loads_typed((typ, decrypted_data))
+
+    @classmethod
+    def from_pycryptodome_aes(
+        cls, serde: SerializerProtocol = JsonPlusSerializer(), **kwargs: Any
+    ) -> "EncryptedSerializer":
+        """Create an EncryptedSerializer using AES encryption."""
+        try:
+            from Crypto.Cipher import AES  # type: ignore
+        except ImportError:
+            raise ImportError(
+                "Pycryptodome is not installed. Please install it with `pip install pycryptodome`."
+            ) from None
+
+        # check if AES key is provided
+        if "key" in kwargs:
+            key: bytes = kwargs.pop("key")
+        else:
+            key_str = os.getenv("LANGGRAPH_AES_KEY")
+            if key_str is None:
+                raise ValueError("LANGGRAPH_AES_KEY environment variable is not set.")
+            key = key_str.encode()
+            if len(key) not in (16, 24, 32):
+                raise ValueError("LANGGRAPH_AES_KEY must be 16, 24, or 32 bytes long.")
+
+        # set default mode to EAX if not provided
+        if kwargs.get("mode") is None:
+            kwargs["mode"] = AES.MODE_EAX
+
+        class PycryptodomeAesCipher(CipherProtocol):
+            def encrypt(self, plaintext: bytes) -> tuple[str, bytes]:
+                cipher = AES.new(key, **kwargs)
+                ciphertext, tag = cipher.encrypt_and_digest(plaintext)
+                return "aes", cipher.nonce + tag + ciphertext
+
+            def decrypt(self, ciphername: str, ciphertext: bytes) -> bytes:
+                assert ciphername == "aes", f"Unsupported cipher: {ciphername}"
+                nonce = ciphertext[:16]
+                tag = ciphertext[16:32]
+                actual_ciphertext = ciphertext[32:]
+
+                cipher = AES.new(key, **kwargs, nonce=nonce)
+                return cipher.decrypt_and_verify(actual_ciphertext, tag)
+
+        return cls(PycryptodomeAesCipher(), serde)