prebuilt: release 0.1.4 (#3977)

- This makes our checkpoint benchmarks more closely resemble the
behavior of our prod checkpointers
- Also found and fixed a bug w multiple subgraphs in same node
accidentally sharing checkpoints

.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/ci.yml

@@ -39,6 +39,7 @@ jobs:
               - 'libs/checkpoint-sqlite/**'
               - 'libs/checkpoint-postgres/**'
               - 'libs/scheduler-kafka/**'
+              - 'libs/prebuilt/**'
             sdk-js:
               - 'libs/sdk-js/**'
 
@@ -56,6 +57,7 @@ jobs:
             "libs/checkpoint-sqlite",
             "libs/checkpoint-postgres",
             "libs/scheduler-kafka",
+            "libs/prebuilt",
           ]
     if: needs.changes.outputs.python == 'true'
     uses: ./.github/workflows/_lint.yml
@@ -74,6 +76,7 @@ jobs:
             "libs/checkpoint",
             "libs/checkpoint-sqlite",
             "libs/checkpoint-postgres",
+            "libs/prebuilt",
           ]
     if: needs.changes.outputs.python == 'true'
     uses: ./.github/workflows/_test.yml
@@ -111,6 +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'
@@ -177,6 +216,8 @@ jobs:
         test,
         test-langgraph,
         test-scheduler-kafka,
+        check-sdk-methods,
+        check-schema,
         integration-test,
         test-js,
       ]

.github/workflows/deploy_docs.yml

@@ -102,7 +102,14 @@ 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
@@ -117,6 +124,7 @@ jobs:
               --check-links-ignore "https://(api|web|docs)\.smith\.langchain\.com/.*" \
               --check-links-ignore "https://academy\.langchain\.com/.*" \
               --check-links-ignore "https://x.com/.*" \
+              --check-links-ignore "https://twitter.com/.*" \
               --check-links-ignore "https://github\.com/.*" \
               --check-links-ignore "http://localhost:8123/.*" \
               --check-links-ignore "http://localhost:2024.*" \
@@ -126,6 +134,7 @@ 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
@@ -143,8 +152,10 @@ jobs:
                 --check-links-ignore "http://localhost:2024.*" \
                 --check-links-ignore "http://127.0.0.1:.*" \
                 --check-links-ignore "https://x.com/.*" \
+                --check-links-ignore "https://twitter.com/.*" \
                 --check-links-ignore "https://github\.com/.*" \
                 --check-links-ignore "/.*\.(ipynb|html)$" \
+                --check-links-ignore "docs/docs/static/wordmark_*" \
                 --check-links ${CHANGED_FILES} \
                 || ([ $? = 5 ] && exit 0 || exit $?)
             else

.github/workflows/release.yml

@@ -195,7 +195,11 @@ jobs:
               "$PKG_NAME==$VERSION" \
           )
 
-          if [[ "$PKG_NAME" == *checkpoint* ]]; then
+          if [[ "$PKG_NAME" == *prebuilt* ]]; then
+            poetry run pip install langgraph
+          fi
+
+          if [[ "$PKG_NAME" == *checkpoint* || "$PKG_NAME" == *prebuilt* ]]; then
             # since checkpoint packages are namespace packages, import them with . convention
             # i.e. import langgraph.checkpoint or langgraph.checkpoint.sqlite
             IMPORT_NAME="$(echo "$PKG_NAME" | sed s/-/./g)"

.github/workflows/run_notebooks.yml

@@ -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/create_third_party_page.py

@@ -83,14 +83,18 @@ def generate_markdown(resolved_packages: List[ResolvedPackage], language: str) -
         resolved_packages, key=lambda p: p["weekly_downloads"] or 0, reverse=True
     )
     rows = [
-        "| Name | GitHub URL | Description | Weekly Downloads |",
-        "| --- | --- | --- | --- |",
+        "| Name | GitHub URL | Description | Weekly Downloads | Stars |",
+        "| --- | --- | --- | --- | --- |",
     ]
     for package in sorted_packages:
         name = f"**{package['name']}**"
         repo_url = f"[{package['repo']}](https://github.com/{package['repo']})"
+        stars_badge = (
+            f"https://img.shields.io/github/stars/{package['repo']}?style=social"
+        )
+        stars = f"![GitHub stars]({stars_badge})"
         downloads = package["weekly_downloads"] or "-"
-        row = f"| {name} | {repo_url} | {package['description']} | {downloads} |"
+        row = f"| {name} | {repo_url} | {package['description']} | {downloads} | {stars}"
         rows.append(row)
     markdown_content = MARKDOWN.format(
         library_list="\n".join(rows), langgraph_url=langgraph_url

docs/_scripts/third_party_page/get_download_stats.py

@@ -30,10 +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

@@ -2,16 +2,37 @@
 packages:
   - name: "trustcall"
     repo: "hinthornw/trustcall"
-    description: "Tenacious tool calling built on LangGraph"
+    description: "Tenacious tool calling built on LangGraph."
   - name: "breeze-agent"
     repo: "andrestorres123/breeze-agent"
-    description: "A streamlined research system built inspired on STORM and built on LangGraph"
+    description: "A streamlined research system built inspired on STORM and built on LangGraph."
   - name: "langgraph-supervisor"
-    repo: "langchain-ai/langgraph-supervisor"
-    description: "Build supervisor multi-agent systems with LangGraph"
+    repo: "langchain-ai/langgraph-supervisor-py"
+    description: "Build supervisor multi-agent systems with LangGraph."
   - name: "langmem"
     repo: "langchain-ai/langmem"
     description: "Build agents that learn and adapt from interactions over time."
   - name: "langchain-mcp-adapters"
     repo: "langchain-ai/langchain-mcp-adapters"
-    description: "Make Anthropic Model Context Protocol (MCP) tools compatible with LangGraph agents."
+    description: "Make Anthropic Model Context Protocol (MCP) tools compatible with LangGraph agents."
+  - name: "open-deep-research"
+    repo: "langchain-ai/open_deep_research"
+    description: "Open source assistant for iterative web research and report writing."
+  - name: "langgraph-swarm"
+    repo: "langchain-ai/langgraph-swarm-py"
+    description: "Build swarm-style multi-agent systems using LangGraph."
+  - name: "delve-taxonomy-generator"
+    repo: "andrestorres123/delve"
+    description: "A taxonomy generator for unstructured data"
+  - name: "nodeology"
+    repo: "xyin-anl/Nodeology"
+    description: "Enable researcher to build scientific workflows easily with simplified interface."
+  - name: "langgraph-bigtool"
+    repo: "langchain-ai/langgraph-bigtool"
+    description: "Build LangGraph agents with large numbers of tools."
+  - name: "ai-data-science-team"
+    repo: "business-science/ai-data-science-team"
+    description: "An AI-powered data science team of agents to help you perform common data science tasks 10X faster."
+  - name: "langgraph-reflection"
+    repo: "langchain-ai/langgraph-reflection"
+    description: "LangGraph agent that runs a reflection step."

docs/docs/adopters.md

@@ -1,4 +1,4 @@
-# 🦜🕸️ LangGraph Adopters
+# 🦜🕸️ Companies using LangGraph
 
 This list of companies using LangGraph and their success stories is compiled from public sources. If your company uses LangGraph, we'd love for you to share your story and add it to the list. You’re also welcome to contribute updates based on publicly available information from other companies, such as blog posts or press releases.
 
@@ -9,9 +9,11 @@ This list of companies using LangGraph and their success stories is compiled fro
 | [AppFolio](https://www.appfolio.com/) | Real Estate | Copilot for domain-specific task | [Case study, 2024](https://blog.langchain.dev/customers-appfolio/) |
 | [Athena Intelligence](https://www.athenaintel.com/) | Software & Technology (GenAI Native) | Research & summarization | [Case study, 2024](https://blog.langchain.dev/customers-athena-intelligence/) |
 | [Captide](https://www.captide.co/) | Software & Technology (GenAI Native) | Data extraction | [Case study, 2025](https://blog.langchain.dev/how-captide-is-redefining-equity-research-with-agentic-workflows-built-on-langgraph-and-langsmith/) |
+| [Cisco Outshift](https://outshift.cisco.com/) | Software & Technology | DevOps | [Blog post, 2025](https://outshift.cisco.com/blog/build-react-agent-application-for-devops-tasks-using-rest-apis) |
 | [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/) |
 | [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/) |
@@ -22,4 +24,4 @@ This list of companies using LangGraph and their success stories is compiled fro
 | [Tradestack](https://www.tradestack.uk/) | Software & Technology (GenAI Native) | Copilot for domain-specific task | [Case study, 2024](https://blog.langchain.dev/customers-tradestack/) |
 | [Uber](https://www.uber.com/) | Transportation | Developer productivity; Code generation | [Presentation, 2024](https://dpe.org/sessions/ty-smith-adam-huda/this-year-in-ubers-ai-driven-developer-productivity-revolution/); [Video, 2024](https://www.youtube.com/watch?v=8rkA5vWUE4Y) |
 | [Unify](https://www.unifygtm.com/) | Software & Technology (GenAI Native) | Copilot for domain-specific task | [Blog post, 2024](https://blog.langchain.dev/unify-launches-agents-for-account-qualification-using-langgraph-and-langsmith/) |
-| [Vizient](https://www.vizientinc.com/) | Healthcare | Copilot for domain-specific task | [Case study, 2025](https://blog.langchain.dev/p/3d2cd58c-13a5-4df9-bd84-7d54ed0ed82c/) |
+| [Vizient](https://www.vizientinc.com/) | Healthcare | Copilot for domain-specific task | [Case study, 2025](https://blog.langchain.dev/p/3d2cd58c-13a5-4df9-bd84-7d54ed0ed82c/) |

docs/docs/cloud/deployment/cloud.md

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

docs/docs/cloud/deployment/semantic_search.md

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

docs/docs/cloud/deployment/setup.md

@@ -36,21 +36,20 @@ Dependencies can optionally be specified in one of the following files: `pyproje
 The dependencies below will be included in the image, you can also use them in your code, as long as with a compatible version range:
 
 ```
-langgraph>=0.2.56,<0.3.0
-langgraph-checkpoint>=2.0.5,<3.0
+langgraph>=0.2.56,<0.4.0
+langgraph-sdk>=0.1.53
+langgraph-checkpoint>=2.0.15,<3.0
 langchain-core>=0.2.38,<0.4.0
 langsmith>=0.1.63
 orjson>=3.9.7
 httpx>=0.25.0
 tenacity>=8.0.0
 uvicorn>=0.26.0
-sse-starlette>=2.1.0
+sse-starlette>=2.1.0,<2.2.0
 uvloop>=0.18.0
 httptools>=0.5.0
-jsonschema-rs>=0.16.3
-croniter>=1.0.1
+jsonschema-rs>=0.20.0
 structlog>=23.1.0
-redis>=5.0.0,<6.0.0
 ```
 
 Example `requirements.txt` file:

docs/docs/cloud/deployment/setup_pyproject.md

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

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

@@ -0,0 +1,312 @@
+# 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.
+
+!!! warning "LangGraph.js only"
+
+    Currently only LangGraph.js supports Generative UI. Support for Python is coming soon.
+
+## 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
+
+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: ["langsmith:nostream"] })
+      .invoke(state.messages);
+
+    const response = {
+      id: uuidv4(),
+      type: "ai",
+      content: `Here's the weather for ${weather.city}`,
+    };
+
+    // Emit UI elements with associated 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 `ui.delete` with the ID of the UI message.
+
+```tsx
+// pushed message
+const message = ui.push({ name: "weather", props: { city: "London" } });
+
+// remove said message
+ui.delete(message.id);
+
+// return new state to persist changes
+return { ui: ui.items };
+```
+
+## 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/test_deployment.md

@@ -1,10 +1,10 @@
-# Test Cloud Deployment
+# Test LangGraph Platform Deployment
 
-The LangGraph Studio UI connects directly to LangGraph Cloud deployments.
+The LangGraph Studio UI connects directly to LangGraph Platform deployments.
 
 Starting from the <a href="https://smith.langchain.com/" target="_blank">LangSmith UI</a>...
 
-1. In the left-hand navigation panel, select `LangGraph Cloud`. The `LangGraph Cloud` view contains a list of existing LangGraph Cloud deployments.
+1. In the left-hand navigation panel, select `LangGraph Platform`. The `LangGraph Platform` view contains a list of existing LangGraph Platform deployments.
 1. Select an existing deployment to test with LangGraph Studio.
 1. In the top-right corner, select `Open LangGraph Studio`.
 1. [Invoke an assistant](./invoke_studio.md) or [view an existing thread](./threads_studio.md).

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

@@ -9,19 +9,18 @@ The `useStream()` React hook provides a seamless way to integrate LangGraph into
 Key features:
 
 - Messages streaming: Handle a stream of message chunks to form a complete message
-- Automatic state management for messages, loading states, and errors
+- Automatic state management for messages, interrupts, loading states, and errors
 - Conversation branching: Create alternate conversation paths from any point in the chat history
-- UI-agnostic design - bring your own components and styling
+- UI-agnostic design: bring your own components and styling
 
 Let's explore how to use `useStream()` in your React application.
 
-The `useStream()` provides a solid foundation for creating bespoke chat experiences. For pre-built chat components and interfaces, we recommend checking out [CopilotKit](https://docs.copilotkit.ai/coagents/quickstart/langgraph) and [assistant-ui](https://www.assistant-ui.com/docs/runtimes/langgraph).
-
+The `useStream()` provides a solid foundation for creating bespoke chat experiences. For pre-built chat components and interfaces, we also recommend checking out [CopilotKit](https://docs.copilotkit.ai/coagents/quickstart/langgraph) and [assistant-ui](https://www.assistant-ui.com/docs/runtimes/langgraph).
 
 ## Installation
 
 ```bash
-npm install @langchain/langgraph-sdk @langchain/langchain-core react
+npm install @langchain/langgraph-sdk @langchain/core
 ```
 
 ## Example
@@ -65,9 +64,7 @@ export default function App() {
             Stop
           </button>
         ) : (
-          <button key="submit" type="submit">
-            Send
-          </button>
+          <button keytype="submit">Send</button>
         )}
       </form>
     </div>
@@ -81,6 +78,7 @@ The `useStream()` hook takes care of all the complex state management behind the
 
 - Thread state management
 - Loading and error states
+- Interrupts
 - Message handling and updates
 - Branching support
 
@@ -134,9 +132,9 @@ We recommend storing the `threadId` in your URL's query parameters to let users
 
 ### Messages Handling
 
-To enable messages handling, you need to pass the `messagesKey` option to the `useStream()` hook. 
+The `useStream()` hook will keep track of the message chunks received from the server and concatenate them together to form a complete message. The completed message chunks can be retrieved via the `messages` property.
 
-When enabled, the `useStream()` hook will keep track of the message chunks received from the server and concatenate them together to form a complete message. The completed message chunks can be retrieved via the `messages` property.
+By default, the `messagesKey` is set to `messages`, where it will append the new messages chunks to `values["messages"]`. If you store messages in a different key, you can change the value of `messagesKey`.
 
 ```tsx
 import type { Message } from "@langchain/langgraph-sdk";
@@ -159,9 +157,49 @@ export default function HomePage() {
 }
 ```
 
-### Branching Support
+Under the hood, the `useStream()` hook will use the `streamMode: "messages-key"` to receive a stream of messages (i.e. individual LLM tokens) from any LangChain chat model invocations inside your graph nodes. Learn more about messages streaming in the [How to stream messages from your graph](./stream_messages.md) guide.
 
-To enable branching, you need to enable messages handling. Pass the `messagesKey` option to the `useStream()` hook. For each message, you can use `getMessagesMetadata()` to get the first checkpoint from which the message has been first seen. You can then create a new run from the checkpoint preceding the first seen checkpoint to create a new branch in a thread.
+### Interrupts
+
+The `useStream()` hook exposes the `interrupt` property, which will be filled with the last interrupt from the thread. You can use interrupts to:
+
+- Render a confirmation UI before executing a node
+- Wait for human input, allowing agent to ask the user with clarifying questions
+
+Learn more about interrupts in the [How to handle interrupts](../../how-tos/human_in_the_loop/wait-user-input.ipynb) guide.
+
+```tsx
+const thread = useStream<
+  { messages: Message[] },
+  { InterruptType: string }
+>({
+  apiUrl: "http://localhost:2024",
+  assistantId: "agent",
+  messagesKey: "messages",
+});
+
+if (thread.interrupt) {
+  return (
+    <div>
+      Interrupted! {thread.interrupt.value}
+
+      <button
+        type="button"
+        onClick={() => {
+          // `resume` can be any value that the agent accepts
+          thread.submit(undefined, { command: { resume: true } });
+        }}
+      >
+        Resume
+      </button>
+    </div>
+  );
+}
+```
+
+### Branching
+
+For each message, you can use `getMessagesMetadata()` to get the first checkpoint from which the message has been first seen. You can then create a new run from the checkpoint preceding the first seen checkpoint to create a new branch in a thread.
 
 A branch can be created in following ways:
 
@@ -169,23 +207,12 @@ A branch can be created in following ways:
 2. Request a regeneration of a previous assistant message.
 
 ```tsx
-/* eslint-disable @typescript-eslint/no-floating-promises */
 "use client";
 
 import type { Message } from "@langchain/langgraph-sdk";
 import { useStream } from "@langchain/langgraph-sdk/react";
-import {
-  Annotation,
-  MessagesAnnotation,
-  type StateType,
-  type UpdateType,
-} from "@langchain/langgraph/web";
 import { useState } from "react";
 
-const AgentState = Annotation.Root({
-  ...MessagesAnnotation.spec,
-});
-
 function BranchSwitcher({
   branch,
   branchOptions,
@@ -263,10 +290,7 @@ function EditMessage({
 }
 
 export default function App() {
-  const thread = useStream<
-    StateType<typeof AgentState.spec>,
-    UpdateType<typeof AgentState.spec>
-  >({
+  const thread = useStream({
     apiUrl: "http://localhost:2024",
     assistantId: "agent",
     messagesKey: "messages",
@@ -289,7 +313,7 @@ export default function App() {
                   onEdit={(message) =>
                     thread.submit(
                       { messages: [message] },
-                      { checkpoint: parentCheckpoint }
+                      { checkpoint: parentCheckpoint },
                     )
                   }
                 />
@@ -344,13 +368,11 @@ 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.
+
 ### TypeScript
 
-The `useStream()` hook is fully typed to help catch errors early and provide better IDE support. You can specify types for:
-
-- State shape
-- Update format
-- Custom events
+The `useStream()` hook is friendly for apps written in TypeScript and you can specify types for the state to get better type safety and IDE support.
 
 ```tsx
 // Define your types
@@ -359,25 +381,44 @@ type State = {
   context?: Record<string, unknown>;
 };
 
-type Update = {
-  messages: Message[] | Message;
-  context?: Record<string, unknown>;
-};
-
-type CustomEvent = {
-  type: "progress" | "debug";
-  payload: unknown;
-};
-
 // Use them with the hook
-const thread = useStream<State, Update, CustomEvent>({
+const thread = useStream<State>({
   apiUrl: "http://localhost:2024",
   assistantId: "agent",
   messagesKey: "messages",
 });
 ```
 
-If you're using LangGraph.js, you can reuse your graph's annotation types:
+You can also optionally specify types for different scenarios, such as:
+
+- `ConfigurableType`: Type for the `config.configurable` property (default: `Record<string, unknown>`)
+- `InterruptType`: Type for the interrupt value - i.e. contents of `interrupt(...)` function (default: `unknown`)
+- `CustomEventType`: Type for the custom events (default: `unknown`)
+- `UpdateType`: Type for the submit function (default: `Partial<State>`)
+
+```tsx
+
+const thread = useStream<State, {
+  UpdateType: {
+    messages: Message[] | Message;
+    context?: Record<string, unknown>;
+  };
+  InterruptType: string;
+  CustomEventType: {
+    type: "progress" | "debug";
+    payload: unknown;
+  };
+  ConfigurableType: {
+    model: string;
+  };
+}>({
+  apiUrl: "http://localhost:2024",
+  assistantId: "agent",
+  messagesKey: "messages",
+});
+```
+
+If you're using LangGraph.js, you can also reuse your graph's annotation types. However, make sure to only import the types of the annotation schema in order to avoid importing the entire LangGraph.js runtime (i.e. via `import type { ... }` directive).
 
 ```tsx
 import {
@@ -394,7 +435,7 @@ const AgentState = Annotation.Root({
 
 const thread = useStream<
   StateType<typeof AgentState.spec>,
-  UpdateType<typeof AgentState.spec>
+  { UpdateType: UpdateType<typeof AgentState.spec> }
 >({
   apiUrl: "http://localhost:2024",
   assistantId: "agent",
@@ -410,7 +451,7 @@ The `useStream()` hook provides several callback options to help you respond to
 - `onFinish`: Called when the stream is finished.
 - `onUpdateEvent`: Called when an update event is received.
 - `onCustomEvent`: Called when a custom event is received. See [Custom events](../../concepts/streaming.md#custom) to learn how to stream custom events.
-- `onMetadataEvent`: Called when a metadata event is received.
+- `onMetadataEvent`: Called when a metadata event is received, which contains the Run ID and Thread ID.
 
 ## Learn More
 

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

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

docs/docs/cloud/reference/cli.md

@@ -1,6 +1,6 @@
 # LangGraph CLI
 
-The LangGraph command line interface includes commands to build and run a LangGraph Cloud API server locally in [Docker](https://www.docker.com/). For development and testing, you can use the CLI to deploy a local API server as an alternative to the [Studio desktop app](../../concepts/langgraph_studio.md).
+The LangGraph command line interface includes commands to build and run a LangGraph Cloud API server locally in [Docker](https://www.docker.com/). For development and testing, you can use the CLI to deploy a local API server.
 
 ## Installation
 
@@ -51,6 +51,7 @@ The LangGraph CLI requires a JSON configuration file with the following keys:
     | <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;">`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"
 

docs/docs/cloud/reference/env_var.md

@@ -2,6 +2,12 @@
 
 The LangGraph Cloud Server supports specific environment variables for configuring a deployment.
 
+## `DD_API_KEY`
+
+Specify `DD_API_KEY` (your [Datadog API Key](https://docs.datadoghq.com/account_management/api-app-keys/)) to automatically enable Datadog tracing for the deployment. Specify other [`DD_*` environment variables](https://ddtrace.readthedocs.io/en/stable/configuration.html) to configure the tracing instrumentation.
+
+If `DD_API_KEY` is specified, the application process is wrapped in the [`ddtrace-run` command](https://ddtrace.readthedocs.io/en/stable/installation_quickstart.html). Other `DD_*` environment variables (e.g. `DD_SITE`, `DD_ENV`, `DD_SERVICE`, `DD_TRACE_ENABLED`) are typically needed to properly configure the tracing instrumentation. See [`DD_*` environment variables](https://ddtrace.readthedocs.io/en/stable/configuration.html) for more details.
+
 ## `LANGCHAIN_TRACING_SAMPLING_RATE`
 
 Sampling rate for traces sent to LangSmith. Valid values: Any float between `0` and `1`.

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/faq.md

@@ -36,7 +36,7 @@ LangGraph is a stateful, orchestration framework that brings added control to ag
 | Concurrency Control | Simple threading                                          | Supports double-texting                                                                                |
 | Scheduling          | None                                                      | Cron scheduling                                                                                        |
 | Monitoring          | None                                                      | Integrated with LangSmith for observability                                                            |
-| IDE integration     | LangGraph Studio for Desktop                              | LangGraph Studio for Desktop & Cloud                                                                   |
+| IDE integration     | LangGraph Studio                                          | LangGraph Studio                                                                                       |
 
 ## What are my deployment options for LangGraph Platform?
 
@@ -62,3 +62,9 @@ Yes! You can use LangGraph with any LLMs. The main reason we use LLMs that suppo
 ## Does LangGraph work with OSS LLMs?
 
 Yes! LangGraph is totally ambivalent to what LLMs are used under the hood. The main reason we use closed LLMs in most of the tutorials is that they seamlessly support tool calling, while OSS LLMs often don't. But tool calling is not necessary (see [this section](#does-langgraph-work-with-llms-that-dont-support-tool-calling)) so you can totally use LangGraph with OSS LLMs.
+
+## Can I use LangGraph Studio without logging to LangSmith
+
+Yes! You can use the [development version of LangGraph Server](../tutorials/langgraph-platform/local-server.md) to run the backend locally.
+This will connect to the studio frontend hosted as part of LangSmith.
+If you set an environment variable of `LANGSMITH_TRACING=false` then no traces will be sent to LangSmith.

docs/docs/concepts/human_in_the_loop.md

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

docs/docs/concepts/index.md

@@ -30,6 +30,7 @@ The conceptual guide does not cover step-by-step instructions or specific implem
 - [Streaming](streaming.md): Streaming is crucial for enhancing the responsiveness of applications built on LLMs. By displaying output progressively, even before a complete response is ready, streaming significantly improves user experience (UX), particularly when dealing with the latency of LLMs.
 - [Functional API](functional_api.md): `@entrypoint` and `@task` decorators that allow you to add LangGraph functionality to an existing codebase.
 - [Durable Execution](durable_execution.md): LangGraph's built-in [persistence](./persistence.md) layer provides durable execution for workflows, ensuring that the state of each execution step is saved to a durable store. 
+- [Pregel](pregel.md): Pregel is LangGraph's runtime, which is responsible for managing the execution of LangGraph applications.
 - [FAQ](faq.md): Frequently asked questions about LangGraph.
 
 ## LangGraph Platform
@@ -47,6 +48,7 @@ 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.
 - [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.

docs/docs/concepts/langgraph_cli.md

@@ -4,7 +4,7 @@
     - [LangGraph Platform](./langgraph_platform.md)
     - [LangGraph Server](./langgraph_server.md)
 
-The LangGraph CLI is a multi-platform command-line tool for building and running the [LangGraph API server](./langgraph_server.md) locally. This offers an alternative to the [LangGraph Studio desktop app](./langgraph_studio.md) for developing and testing agents across all major operating systems (Linux, Windows, MacOS). The resulting server includes all API endpoints for your graph's runs, threads, assistants, etc. as well as the other services required to run your agent, including a managed database for checkpointing and storage.
+The LangGraph CLI is a multi-platform command-line tool for building and running the [LangGraph API server](./langgraph_server.md) locally. The resulting server includes all API endpoints for your graph's runs, threads, assistants, etc. as well as the other services required to run your agent, including a managed database for checkpointing and storage.
 
 ## Installation
 

docs/docs/concepts/langgraph_cloud.md

@@ -80,6 +80,22 @@ 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)

docs/docs/concepts/langgraph_platform.md

@@ -1,3 +1,8 @@
+---
+search:
+  boost: 2
+---
+
 # LangGraph Platform
 
 ## Overview

docs/docs/concepts/langgraph_studio.md

@@ -7,7 +7,7 @@
 
 LangGraph Studio offers a new way to develop LLM applications by providing a specialized agent IDE that enables visualization, interaction, and debugging of complex agentic applications.
 
-With visual graphs and the ability to edit state, you can better understand agent workflows and iterate faster. LangGraph Studio integrates with LangSmith allowing you to  collaborate with teammates to debug failure modes.
+With visual graphs and the ability to edit state, you can better understand agent workflows and iterate faster. LangGraph Studio integrates with LangSmith allowing you to collaborate with teammates to debug failure modes.
 
 ![](img/lg_studio.png)
 
@@ -15,7 +15,7 @@ With visual graphs and the ability to edit state, you can better understand agen
 
 The key features of LangGraph Studio are:
 
-- Visualizes your graph
+- Visualize your graphs
 - Test your graph by running it from the UI
 - Debug your agent by [modifying its state and rerunning](human_in_the_loop.md)
 - Create and manage [assistants](assistants.md)
@@ -23,86 +23,54 @@ The key features of LangGraph Studio are:
 - View and manage [long term memory](memory.md)
 - Add node input/outputs to [LangSmith](https://smith.langchain.com/) datasets for testing
 
-## Types
+## Getting started
 
-### Development server with web UI
+There are two ways to connect your LangGraph app with the studio:
 
-You can [run a local in-memory development server](../tutorials/langgraph-platform/local-server.md) that can be used to connect a local LangGraph app with a web version of the studio.
-For example, if you start the local server with `langgraph dev` (running at `http://127.0.0.1:2024` by default), you can connect to the studio by navigating to:
+### Deployed Application
+
+If you have deployed your LangGraph application on LangGraph Platform, you can access the studio as part of that deployment. To do so, navigate to the deployment in LangGraph Platform within the LangSmith UI and click the "LangGraph Studio" button.
+
+### Local Development Server
+
+If you have a LangGraph application that is [running locally in-memory](../tutorials/langgraph-platform/local-server.md), you can connect it to LangGraph Studio in the browser within LangSmith.
+
+By default, starting the local server with `langgraph dev` will run the server at `http://127.0.0.1:2024` and automatically open Studio in your browser. However, you can also manually connect to Studio by either:
+
+1. In LangGraph Platform, clicking the "LangGraph Studio" button and entering the server URL in the dialog that appears.
+
+   or
+
+2. Navigating to the URL in your browser:
 
 ```
 https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024
 ```
 
-See [instructions here](../cloud/reference/cli.md#dev) for more information.
+## Related
 
-The web UI version of the studio will connect to your locally running server — your agent is still running locally and never leaves your device.
+For more information please see the following:
 
-### Cloud studio
+- [LangGraph Studio how-to guides](../how-tos/index.md#langgraph-studio)
+- [LangGraph CLI Documentation](../cloud/reference/cli.md)
 
-If you have deployed your LangGraph application on LangGraph Platform (Cloud), you can access the studio as part of that
-
-### Desktop app
-
-LangGraph Studio is available as a [desktop app](https://studio.langchain.com/) for MacOS users.
-
-While in Beta, LangGraph Studio is available for free to all [LangSmith](https://smith.langchain.com/) users on any plan tier.
-
-## Studio FAQs
+## LangGraph Studio FAQs
 
 ### Why is my project failing to start?
 
-There are a few reasons that your project might fail to start, here are some of the most common ones.
-
-#### Docker issues (desktop only)
-
-LangGraph Studio (desktop) requires Docker Desktop version 4.24 or higher. Please make sure you have a version of Docker installed that satisfies that requirement and also make sure you have the Docker Desktop app up and running before trying to use LangGraph Studio. In addition, make sure you have docker-compose updated to version 2.22.0 or higher.
-
-#### Configuration or environment issues
-
-Another reason your project might fail to start is because your configuration file is defined incorrectly, or you are missing required environment variables.
-
-!!! Important "Note (desktop only)"
-
-    LangGraph Studio Desktop automatically populates `LANGCHAIN_*` environment variables for license verification and tracing, regardless of the contents of the `.env` file. All other environment variables defined in `.env` will be read as normal.
-
-#### Incorrect data region (desktop only)
-
-If you receive a license verification error when attempting to start the LangGraph Server, you may be logged into the incorrect LangSmith data region. Ensure that you're logged into the correct LangSmith data region and ensure that the LangSmith account has access to LangGraph platform.
-
-1. In the top right-hand corner, click the user icon and select `Logout`.
-1. At the login screen, click the `Data Region` dropdown menu and select the appropriate data region. Then click `Login to LangSmith`.
+A project may fail to start if the configuration file is defined incorrectly, or if required environment variables are missing. See [here](../cloud/reference/cli.md#configuration-file) for how your configuration file should be defined.
 
 ### How does interrupt work?
 
 When you select the `Interrupts` dropdown and select a node to interrupt the graph will pause execution before and after (unless the node goes straight to `END`) that node has run. This means that you will be able to both edit the state before the node is ran and the state after the node has ran. This is intended to allow developers more fine-grained control over the behavior of a node and make it easier to observe how the node is behaving. You will not be able to edit the state after the node has ran if the node is the final node in the graph.
 
-### How do I reload the app?  (desktop only)
+For more information on interrupts and human in the loop, see [here](./human_in_the_loop.md).
 
-If you would like to reload the app, don't use Command+R as you might normally do. Instead, close and reopen the app for a full refresh.
-
-### How does automatic rebuilding work?  (desktop only)
-
-One of the key features of LangGraph Studio is that it automatically rebuilds your image when you change the source code. This allows for a super fast development and testing cycle which makes it easy to iterate on your graph. There are two different ways that LangGraph rebuilds your image: either by editing the image or completely rebuilding it.
-
-#### Rebuilds from source code changes
-
-If you modified the source code only (no configuration or dependency changes!) then the image does not require a full rebuild, and LangGraph Studio will only update the relevant parts. The UI status in the bottom left will switch from `Online` to `Stopping` temporarily while the image gets edited. The logs will be shown as this process is happening, and after the image has been edited the status will change back to `Online` and you will be able to run your graph with the modified code!
-
-
-#### Rebuilds from configuration or dependency changes
-
-If you edit your graph configuration file (`langgraph.json`) or the dependencies (either `pyproject.toml` or `requirements.txt`) then the entire image will be rebuilt. This will cause the UI to switch away from the graph view and start showing the logs of the new image building process. This can take a minute or two, and once it is done your updated image will be ready to use!
-
-### Why is my graph taking so long to startup?  (desktop only)
-
-The LangGraph Studio interacts with a local LangGraph API server. To stay aligned with ongoing updates, the LangGraph API requires regular rebuilding. As a result, you may occasionally experience slight delays when starting up your project.
-
-## Why are extra edges showing up in my graph?
+### Why are extra edges showing up in my graph?
 
 If you don't define your conditional edges carefully, you might notice extra edges appearing in your graph. This is because without proper definition, LangGraph Studio assumes the conditional edge could access all other nodes. In order for this to not be the case, you need to be explicit about how you define the nodes the conditional edge routes to. There are two ways you can do this:
 
-### Solution 1: Include a path map
+#### Solution 1: Include a path map
 
 The first way to solve this is to add path maps to your conditional edges. A path map is just a dictionary or array that maps the possible outputs of your router function with the names of the nodes that each output corresponds to. The path map is passed as the third argument to the `add_conditional_edges` function like so:
 
@@ -120,7 +88,7 @@ The first way to solve this is to add path maps to your conditional edges. A pat
 
 In this case, the routing function returns either True or False, which map to `node_b` and `node_c` respectively.
 
-### Solution 2: Update the typing of the router (Python only)
+#### Solution 2: Update the typing of the router (Python only)
 
 Instead of passing a path map, you can also be explicit about the typing of your routing function by specifying the nodes it can map to using the `Literal` python definition. Here is an example of how to define a routing function in that way:
 
@@ -132,9 +100,48 @@ def routing_function(state: GraphState) -> Literal["node_b","node_c"]:
         return "node_c"
 ```
 
+### Studio Desktop FAQs
 
-## Related
+!!! warning "Deprecation Warning"
+    In order to support a wider range of platforms and users, we now recommend following the above instructions to connect to LangGraph Studio using the development server instead of the desktop app.
 
-For more information please see the following:
+The LangGraph Studio Desktop App is a standalone application that allows you to connect to your LangGraph application and visualize and interact with your graph. It is available for MacOS only and requires Docker to be installed.
 
-*  [LangGraph Studio how-to guides](../how-tos/index.md#langgraph-studio)
+#### Why is my project failing to start?
+
+In addition to the reasons listed above, for the desktop app there are a few more reasons that your project might fail to start:
+
+!!! Important "Note "
+
+    LangGraph Studio Desktop automatically populates `LANGCHAIN_*` environment variables for license verification and tracing, regardless of the contents of the `.env` file. All other environment variables defined in `.env` will be read as normal.
+
+##### Docker issues
+
+LangGraph Studio (desktop) requires Docker Desktop version 4.24 or higher. Please make sure you have a version of Docker installed that satisfies that requirement and also make sure you have the Docker Desktop app up and running before trying to use LangGraph Studio. In addition, make sure you have docker-compose updated to version 2.22.0 or higher.
+
+##### Incorrect data region
+
+If you receive a license verification error when attempting to start the LangGraph Server, you may be logged into the incorrect LangSmith data region. Ensure that you're logged into the correct LangSmith data region and ensure that the LangSmith account has access to LangGraph platform.
+
+1. In the top right-hand corner, click the user icon and select `Logout`.
+1. At the login screen, click the `Data Region` dropdown menu and select the appropriate data region. Then click `Login to LangSmith`.
+
+### How do I reload the app?
+
+If you would like to reload the app, don't use Command+R as you might normally do. Instead, close and reopen the app for a full refresh.
+
+### How does automatic rebuilding work?
+
+One of the key features of LangGraph Studio is that it automatically rebuilds your image when you change the source code. This allows for a super fast development and testing cycle which makes it easy to iterate on your graph. There are two different ways that LangGraph rebuilds your image: either by editing the image or completely rebuilding it.
+
+#### Rebuilds from source code changes
+
+If you modified the source code only (no configuration or dependency changes!) then the image does not require a full rebuild, and LangGraph Studio will only update the relevant parts. The UI status in the bottom left will switch from `Online` to `Stopping` temporarily while the image gets edited. The logs will be shown as this process is happening, and after the image has been edited the status will change back to `Online` and you will be able to run your graph with the modified code!
+
+#### Rebuilds from configuration or dependency changes
+
+If you edit your graph configuration file (`langgraph.json`) or the dependencies (either `pyproject.toml` or `requirements.txt`) then the entire image will be rebuilt. This will cause the UI to switch away from the graph view and start showing the logs of the new image building process. This can take a minute or two, and once it is done your updated image will be ready to use!
+
+### Why is my graph taking so long to startup?
+
+The LangGraph Studio interacts with a local LangGraph API server. To stay aligned with ongoing updates, the LangGraph API requires regular rebuilding. As a result, you may occasionally experience slight delays when starting up your project.

docs/docs/concepts/low_level.md

@@ -310,7 +310,7 @@ graph.add_conditional_edges(START, routing_function, {True: "node_b", False: "no
 
 ## `Send`
 
-By default, `Nodes` and `Edges` are defined ahead of time and operate on the same shared state. However, there can be cases where the exact edges are not known ahead of time and/or you may want different versions of `State` to exist at the same time. A common example of this is with `map-reduce` design patterns. In this design pattern, a first node may generate a list of objects, and you may want to apply some other node to all those objects. The number of objects may be unknown ahead of time (meaning the number of edges may not be known) and the input `State` to the downstream `Node` should be different (one for each generated object).
+By default, `Nodes` and `Edges` are defined ahead of time and operate on the same shared state. However, there can be cases where the exact edges are not known ahead of time and/or you may want different versions of `State` to exist at the same time. A common example of this is with [map-reduce](https://langchain-ai.github.io/langgraph/how-tos/map-reduce/) design patterns. In this design pattern, a first node may generate a list of objects, and you may want to apply some other node to all those objects. The number of objects may be unknown ahead of time (meaning the number of edges may not be known) and the input `State` to the downstream `Node` should be different (one for each generated object).
 
 To support this design pattern, LangGraph supports returning [`Send`][langgraph.types.Send] objects from conditional edges. `Send` takes two arguments: first is the name of the node, and second is the state to pass to that node.
 

docs/docs/concepts/multi_agent.md

@@ -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
 
@@ -112,6 +112,7 @@ In this architecture, agents are defined as graph nodes. Each agent can communic
 ```python
 from typing import Literal
 from langchain_openai import ChatOpenAI
+from langgraph.types import Command
 from langgraph.graph import StateGraph, MessagesState, START, END
 
 model = ChatOpenAI()
@@ -158,6 +159,7 @@ In this architecture, we define agents as nodes and add a supervisor node (LLM)
 ```python
 from typing import Literal
 from langchain_openai import ChatOpenAI
+from langgraph.types import Command
 from langgraph.graph import StateGraph, MessagesState, START, END
 
 model = ChatOpenAI()
@@ -233,7 +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.
 
@@ -337,9 +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

@@ -0,0 +1,347 @@
+# LangGraph's Runtime (Pregel)
+
+[Pregel][langgraph.pregel.Pregel] implements LangGraph's runtime, managing the execution of LangGraph applications.
+
+Compiling a [StateGraph][langgraph.graph.StateGraph] or creating an [entrypoint][langgraph.func.entrypoint] produces a [Pregel][langgraph.pregel.Pregel] instance that can be invoked with input.
+
+This guide explains the runtime at a high level and provides instructions for directly implementing applications with Pregel.
+
+> **Note:** The [Pregel][langgraph.pregel.Pregel] runtime is named after [Google's Pregel algorithm](https://research.google/pubs/pub37252/), which describes an efficient method for large-scale parallel computation using graphs.
+
+## Overview
+
+In LangGraph, Pregel combines [**actors**](https://en.wikipedia.org/wiki/Actor_model) and **channels** into a single application. **Actors** read data from channels and write data to channels. Pregel organizes the execution of the application into multiple steps, following the **Pregel Algorithm**/**Bulk Synchronous Parallel** model.
+
+Each step consists of three phases:
+
+- **Plan**: Determine which **actors** to execute in this step. For example, in the first step, select the **actors** that subscribe to the special **input** channels; in subsequent steps, select the **actors** that subscribe to channels updated in the previous step.
+- **Execution**: Execute all selected **actors** in parallel, until all complete, or one fails, or a timeout is reached. During this phase, channel updates are invisible to actors until the next step.
+- **Update**: Update the channels with the values written by the **actors** in this step.
+
+Repeat until no **actors** are selected for execution, or a maximum number of steps is reached.
+
+## Actors 
+
+An **actor** is a [PregelNode][langgraph.pregel.read.PregelNode]. It subscribes to channels, reads data from them, and writes data to them. It can be thought of as an **actor** in the Pregel algorithm. [PregelNodes][langgraph.pregel.read.PregelNode] implement LangChain's Runnable interface.
+
+## Channels
+
+Channels are used to communicate between actors (PregelNodes). Each channel has a value type, an update type, and an update function – which takes a sequence of updates and modifies the stored value. Channels can be used to send data from one chain to another, or to send data from a chain to itself in a future step. LangGraph provides a number of built-in channels:
+
+### Basic channels: LastValue and Topic
+
+- [LastValue][langgraph.channels.LastValue]: The default channel, stores the last value sent to the channel, useful for input and output values, or for sending data from one step to the next.
+- [Topic][langgraph.channels.Topic]: A configurable PubSub Topic, useful for sending multiple values between **actors**, or for accumulating output. Can be configured to deduplicate values or to accumulate values over the course of multiple steps.
+
+### Advanced channels: Context and BinaryOperatorAggregate
+
+- `Context`: exposes the value of a context manager, managing its lifecycle. Useful for accessing external resources that require setup and/or teardown; e.g., `client = Context(httpx.Client)`.
+- [BinaryOperatorAggregate][langgraph.channels.BinaryOperatorAggregate]: stores a persistent value, updated by applying a binary operator to the current value and each update sent to the channel, useful for computing aggregates over multiple steps; e.g.,`total = BinaryOperatorAggregate(int, operator.add)`
+
+## Examples
+
+While most users will interact with Pregel through the [StateGraph][langgraph.graph.StateGraph] API or 
+the [entrypoint][langgraph.func.entrypoint] decorator, it is possible to interact with Pregel directly.
+
+Below are a few different examples to give you a sense of the Pregel API.
+
+=== "Single node"
+
+    ```python
+
+    from langgraph.channels import EphemeralValue
+    from langgraph.pregel import Pregel, Channel 
+
+    node1 = (
+        Channel.subscribe_to("a")
+        | (lambda x: x + x)
+        | Channel.write_to("b")
+    )
+
+    app = Pregel(
+        nodes={"node1": node1},
+        channels={
+            "a": EphemeralValue(str),
+            "b": EphemeralValue(str),
+        },
+        input_channels=["a"],
+        output_channels=["b"],
+    )
+
+    app.invoke({"a": "foo"})
+    ```
+
+    ```con
+    {'b': 'foofoo'}
+    ```
+
+=== "Multiple nodes"
+
+    ```python
+    from langgraph.channels import LastValue, EphemeralValue
+    from langgraph.pregel import Pregel, Channel 
+
+    node1 = (
+        Channel.subscribe_to("a")
+        | (lambda x: x + x)
+        | Channel.write_to("b")
+    )
+
+    node2 = (
+        Channel.subscribe_to("b")
+        | (lambda x: x + x)
+        | Channel.write_to("c")
+    )
+
+
+    app = Pregel(
+        nodes={"node1": node1, "node2": node2},
+        channels={
+            "a": EphemeralValue(str),
+            "b": LastValue(str),
+            "c": EphemeralValue(str),
+        },
+        input_channels=["a"],
+        output_channels=["b", "c"],
+    )
+
+    app.invoke({"a": "foo"})
+    ```
+
+    ```con
+    {'b': 'foofoo', 'c': 'foofoofoofoo'}
+    ```
+
+=== "Topic"
+
+    ```python
+    from langgraph.channels import EphemeralValue, Topic
+    from langgraph.pregel import Pregel, Channel 
+
+    node1 = (
+        Channel.subscribe_to("a")
+        | (lambda x: x + x)
+        | {
+            "b": Channel.write_to("b"),
+            "c": Channel.write_to("c")
+        }
+    )
+
+    node2 = (
+        Channel.subscribe_to("b")
+        | (lambda x: x + x)
+        | {
+            "c": Channel.write_to("c"),
+        }
+    )
+
+    app = Pregel(
+        nodes={"node1": node1, "node2": node2},
+        channels={
+            "a": EphemeralValue(str),
+            "b": EphemeralValue(str),
+            "c": Topic(str, accumulate=True),
+        },
+        input_channels=["a"],
+        output_channels=["c"],
+    )
+
+    app.invoke({"a": "foo"})
+    ```
+
+    ```pycon
+    {'c': ['foofoo', 'foofoofoofoo']}
+    ```
+
+=== "BinaryOperatorAggregate"
+
+    This examples demonstrates how to use the BinaryOperatorAggregate channel to implement a reducer.
+
+    ```python
+    from langgraph.channels import EphemeralValue, BinaryOperatorAggregate
+    from langgraph.pregel import Pregel, Channel
+
+
+    node1 = (
+        Channel.subscribe_to("a")
+        | (lambda x: x + x)
+        | {
+            "b": Channel.write_to("b"),
+            "c": Channel.write_to("c")
+        }
+    )
+
+    node2 = (
+        Channel.subscribe_to("b")
+        | (lambda x: x + x)
+        | {
+            "c": Channel.write_to("c"),
+        }
+    )
+
+    def reducer(current, update):
+        if current:
+            return current + " | " + "update"
+        else:
+            return update
+
+    app = Pregel(
+        nodes={"node1": node1, "node2": node2},
+        channels={
+            "a": EphemeralValue(str),
+            "b": EphemeralValue(str),
+            "c": BinaryOperatorAggregate(str, operator=reducer),
+        },
+        input_channels=["a"],
+        output_channels=["c"],
+    )
+
+    app.invoke({"a": "foo"})
+    ```
+    
+    
+=== "Cycle"
+
+    This example demonstrates how to introduce a cycle in the graph, by having
+    a chain write to a channel it subscribes to. Execution will continue
+    until a None value is written to the channel.
+
+    ```python
+    from langgraph.channels import EphemeralValue
+    from langgraph.pregel import Pregel, Channel, ChannelWrite, ChannelWriteEntry
+
+    example_node = (
+        Channel.subscribe_to("value")
+        | (lambda x: x + x if len(x) < 10 else None)
+        | ChannelWrite(writes=[ChannelWriteEntry(channel="value", skip_none=True)])
+    )
+
+    app = Pregel(
+        nodes={"example_node": example_node},
+        channels={
+            "value": EphemeralValue(str),
+        },
+        input_channels=["value"],
+        output_channels=["value"],
+    )
+
+    app.invoke({"value": "a"})
+    ```
+
+    ```pycon
+    {'value': 'aaaaaaaaaaaaaaaa'}
+    ```
+
+## High-level API
+
+LangGraph provides two high-level APIs for creating a Pregel application: the [StateGraph (Graph API)](./low_level.md) and the [Functional API](functional_api.md).
+
+
+=== "StateGraph (Graph API)"
+
+    The [StateGraph (Graph API)][langgraph.graph.StateGraph] is a higher-level abstraction that simplifies the creation of Pregel applications. It allows you to define a graph of nodes and edges. When you compile the graph, the StateGraph API automatically creates the Pregel application for you.
+
+    ```python
+    from typing import TypedDict, Optional
+
+    from langgraph.constants import START
+    from langgraph.graph import StateGraph
+
+    class Essay(TypedDict):
+        topic: str
+        content: Optional[str]
+        score: Optional[float]
+
+    def write_essay(essay: Essay):
+        return {
+            "content": f"Essay about {essay['topic']}",
+        }
+
+    def score_essay(essay: Essay):
+        return {
+            "score": 10
+        }
+
+    builder = StateGraph(Essay)
+    builder.add_node(write_essay)
+    builder.add_node(score_essay)
+    builder.add_edge(START, "write_essay")
+
+    # Compile the graph. 
+    # This will return a Pregel instance.
+    graph = builder.compile()
+    ```
+
+    The compiled Pregel instance will be associated with a list of nodes and channels. You can inspect the nodes and channels by printing them.
+
+    ```python
+    print(graph.nodes)
+    ```
+
+    You will see something like this:
+
+    ```pycon 
+    {'__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)
+    ```
+
+    You should see something like this
+
+    ```pycon
+    {'topic': <langgraph.channels.last_value.LastValue at 0x7d05e3294d80>,
+     'content': <langgraph.channels.last_value.LastValue at 0x7d05e3295040>,
+     'score': <langgraph.channels.last_value.LastValue at 0x7d05e3295980>,
+     '__start__': <langgraph.channels.ephemeral_value.EphemeralValue at 0x7d05e3297e00>,
+     'write_essay': <langgraph.channels.ephemeral_value.EphemeralValue at 0x7d05e32960c0>,
+     'score_essay': <langgraph.channels.ephemeral_value.EphemeralValue at 0x7d05e2d8ab80>,
+     'branch:__start__:__self__:write_essay': <langgraph.channels.ephemeral_value.EphemeralValue at 0x7d05e32941c0>,
+     'branch:__start__:__self__:score_essay': <langgraph.channels.ephemeral_value.EphemeralValue at 0x7d05e2d88800>,
+     'branch:write_essay:__self__:write_essay': <langgraph.channels.ephemeral_value.EphemeralValue at 0x7d05e3295ec0>,
+     'branch:write_essay:__self__:score_essay': <langgraph.channels.ephemeral_value.EphemeralValue at 0x7d05e2d8ac00>,
+     'branch:score_essay:__self__:write_essay': <langgraph.channels.ephemeral_value.EphemeralValue at 0x7d05e2d89700>,
+     'branch:score_essay:__self__:score_essay': <langgraph.channels.ephemeral_value.EphemeralValue at 0x7d05e2d8b400>,
+     'start:write_essay': <langgraph.channels.ephemeral_value.EphemeralValue at 0x7d05e2d8b280>}
+    ```
+
+=== "Functional API"
+
+    In the [Functional API](functional_api.md), you can use an [`entrypoint`][langgraph.func.entrypoint] to create
+    a Pregel application. The `entrypoint` decorator allows you to define a function that takes input and returns output. 
+
+    ```python
+    from typing import TypedDict, Optional
+
+    from langgraph.checkpoint.memory import InMemorySaver
+    from langgraph.func import entrypoint
+
+    class Essay(TypedDict):
+        topic: str
+        content: Optional[str]
+        score: Optional[float]
+
+
+    checkpointer = InMemorySaver()
+
+    @entrypoint(checkpointer=checkpointer)
+    def write_essay(essay: Essay):
+        return {
+            "content": f"Essay about {essay['topic']}",
+        }
+
+    print("Nodes: ")
+    print(write_essay.nodes)
+    print("Channels: ")
+    print(write_essay.channels)
+    ```
+
+    ```pycon
+    Nodes: 
+    {'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/scalability_and_resilience.md

@@ -0,0 +1,35 @@
+# LangGraph Platform: Scalability & Resilience
+
+LangGraph Platform is designed to scale horizontally with your workload. Each instance of the service is stateless, and keeps no resources in memory. The service is designed to gracefully handle new instances being added or removed, including hard shutdown cases.
+
+## Server scalability
+
+As you add more instances to a service, they will share the HTTP load as long as an appropriate load balancer mechanism is placed in front of them. In most deployment modalities we configure a load balancer for the service automatically. In the “self-hosted without control plane” modality it’s your responsibility to add a load balancer. Since the instances are stateless any load balancing strategy will work, no session stickiness is needed, or recommended. Any instance of the server can communicate with any queue instance (through Redis PubSub), meaning that requests to cancel or stream an in-progress run can be handled by any arbitrary instance.
+
+## Queue scalability
+
+As you add more instances to a service, they will increase run throughput linearly, as each instance is configured to handle a set number of concurrent runs (by default 10). Each attempt for each run will be handled by a single instance, with exactly-once semantics enforced through Postgres’s MVCC model (refer to section below for crash resilience details). Attempts that fail due to transient database errors are retried up to 3 times. We do not make use of long-lived transactions or locks, this enables us to make more efficient use of Postgres resources.
+
+## Resilience
+
+While a run is being handled by a queue instance, a periodic heartbeat timestamp will be recorded in Redis by that queue worker.
+
+When a graceful shutdown request is received (SIGINT) an instance enters shutdown mode, which
+
+- stops accepting new HTTP requests
+- gives any in-progress runs a limited number of seconds to finish (if not finished it will be put back in the queue)
+- stops the instance from picking up more runs from the queue
+
+If a hard shutdown occurs, eg. due to a server crash, or an infra failure, any runs that were in progress will be picked up by a periodic sweeper task that looks for in-progress runs that have breached their heartbeat window, which will put them back in the queue for another instance to pick them up.
+
+## Postgres resilience
+
+For deployment modalities where we manage the Postgres database we have periodic backups, continuously replicated standby replicas for automatic failover. Optionally, on request, we can also setup read replicas as well as other advanced failover capabilities.
+
+All communication with Postgres implements retries for retry-able errors. If Postgres is momentarily unavailable, such as during a database restart, most/all traffic should continue to succeed. Prolonged failure of the Postgres instance will switch traffic to the failover replica. If the failover replica also fails before the primary is brought back online the service would become unavailable.
+
+## Redis resilience
+
+All data that requires durable storage is stored in Postgres, not Redis. Redis is used only for ephemeral metadata, and communication between instances. Refer to the [architecture](./platform_architecture.md) page for more details on how we use Redis. Therefore we place no durability requirements on Redis.
+
+All communication with Redis implements retries for retry-able errors. If Redis is momentarily unavailable, such as during a database restart, most/all traffic should continue to succeed. Prolonged failure of Redis will render the LGP service unavailable.

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/http/custom_lifespan.md

@@ -0,0 +1,82 @@
+# How to add custom lifespan events
+
+When deploying agents on the LangGraph platform, you often need to initialize resources like database connections when your server starts up, and ensure they're properly closed when it shuts down. Lifespan events let you hook into your server's startup and shutdown sequence to handle these critical setup and teardown tasks.
+
+This works the same way as [adding custom routes](./custom_routes.md) - you just need to provide your own [`Starlette`](https://www.starlette.io/applications/) app (including [`FastAPI`](https://fastapi.tiangolo.com/), [`FastHTML`](https://fastht.ml/) and other compatible apps).
+
+Below is an example using FastAPI.
+
+???+ note "Python only"
+
+    We currently only support custom lifespan events in Python deployments with `langgraph-api>=0.0.26`.
+
+## Create app
+
+Starting from an **existing** LangGraph Platform application, add the following lifespan code to your `webapp.py` file. If you are starting from scratch, you can create a new app from a template using the CLI.
+
+```bash
+langgraph new --template=new-langgraph-project-python my_new_project
+```
+
+Once you have a LangGraph project, add the following app code:
+
+```python
+# ./src/agent/webapp.py
+from contextlib import asynccontextmanager
+from fastapi import FastAPI
+from sqlalchemy.ext.asyncio import create_async_engine, AsyncSession
+from sqlalchemy.orm import sessionmaker
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    # for example...
+    engine = create_async_engine("postgresql+asyncpg://user:pass@localhost/db")
+    # Create reusable session factory
+    async_session = sessionmaker(engine, class_=AsyncSession)
+    # Store in app state
+    app.state.db_session = async_session
+    yield
+    # Clean up connections
+    await engine.dispose()
+
+# highlight-next-line
+app = FastAPI(lifespan=lifespan)
+
+# ... can add custom routes if needed.
+```
+
+## Configure `langgraph.json`
+
+Add the following to your `langgraph.json` file. Make sure the path points to the `webapp.py` file you created above.
+
+```json
+{
+  "dependencies": ["."],
+  "graphs": {
+    "agent": "./src/agent/graph.py:graph"
+  },
+  "env": ".env",
+  "http": {
+    "app": "./src/agent/webapp.py:app"
+  }
+  // Other configuration options like auth, store, etc.
+}
+```
+
+## Start server
+
+Test the server out locally:
+
+```bash
+langgraph dev --no-browser
+```
+
+You should see your startup message printed when the server starts, and your cleanup message when you stop it with Ctrl+C.
+
+## Deploying
+
+You can deploy your app as-is to the managed langgraph cloud or to your self-hosted platform.
+
+## Next steps
+
+Now that you've added lifespan events to your deployment, you can use similar techniques to add [custom routes](./custom_routes.md) or [custom middleware](./custom_middleware.md) to further customize your server's behavior.

docs/docs/how-tos/http/custom_middleware.md

@@ -0,0 +1,75 @@
+# How to add custom middleware
+
+When deploying agents on the LangGraph platform, you can add custom middleware to your server to handle cross-cutting concerns like logging request metrics, injecting or checking headers, and enforcing security policies without modifying core server logic. This works the same way as [adding custom routes](./custom_routes.md) - you just need to provide your own [`Starlette`](https://www.starlette.io/applications/) app (including [`FastAPI`](https://fastapi.tiangolo.com/), [`FastHTML`](https://fastht.ml/) and other compatible apps).
+
+Adding middleware lets you intercept and modify requests and responses globally across your deployment, whether they're hitting your custom endpoints or the built-in LangGraph Platform APIs.
+
+Below is an example using FastAPI.
+
+???+ note "Python only"
+
+    We currently only support custom middleware in Python deployments with `langgraph-api>=0.0.26`.
+
+## Create app
+
+Starting from an **existing** LangGraph Platform application, add the following middleware code to your `webapp.py` file. If you are starting from scratch, you can create a new app from a template using the CLI.
+
+```bash
+langgraph new --template=new-langgraph-project-python my_new_project
+```
+
+Once you have a LangGraph project, add the following app code:
+
+```python
+# ./src/agent/webapp.py
+from fastapi import FastAPI, Request
+from starlette.middleware.base import BaseHTTPMiddleware
+
+# highlight-next-line
+app = FastAPI()
+
+class CustomHeaderMiddleware(BaseHTTPMiddleware):
+    async def dispatch(self, request: Request, call_next):
+        response = await call_next(request)
+        response.headers['X-Custom-Header'] = 'Hello from middleware!'
+        return response
+
+# Add the middleware to the app
+app.add_middleware(CustomHeaderMiddleware)
+```
+
+## Configure `langgraph.json`
+
+Add the following to your `langgraph.json` file. Make sure the path points to the `webapp.py` file you created above.
+
+```json
+{
+  "dependencies": ["."],
+  "graphs": {
+    "agent": "./src/agent/graph.py:graph"
+  },
+  "env": ".env",
+  "http": {
+    "app": "./src/agent/webapp.py:app"
+  }
+  // Other configuration options like auth, store, etc.
+}
+```
+
+## Start server
+
+Test the server out locally:
+
+```bash
+langgraph dev --no-browser
+```
+
+Now any request to your server will include the custom header `X-Custom-Header` in its response.
+
+## Deploying
+
+You can deploy this app as-is to the managed langgraph cloud or to your self-hosted platform.
+
+## Next steps
+
+Now that you've added custom middleware to your deployment, you can use similar techniques to add [custom routes](./custom_routes.md) or define [custom lifespan events](./custom_lifespan.md) to further customize your server's behavior.

docs/docs/how-tos/http/custom_routes.md

@@ -0,0 +1,78 @@
+# How to add custom routes
+
+When deploying agents on the LangGraph platform, your server automatically exposes routes for creating runs and threads, interacting with the long-term memory store, managing configurable assistants, and other core functionality ([see all default API endpoints](../../cloud/reference/api/api_ref.md)).
+
+You can add custom routes by providing your own [`Starlette`](https://www.starlette.io/applications/) app (including [`FastAPI`](https://fastapi.tiangolo.com/), [`FastHTML`](https://fastht.ml/) and other compatible apps). You make LangGraph Platform aware of this by providing a path to the app in your `langgraph.json` configuration file. (`"http": {"app": "path/to/app.py:app"}`).
+
+Defining a custom app object lets you add any routes you'd like, so you can do anything from adding a `/login` endpoint to writing an entire full-stack web-app, all deployed in a single LangGraph deployment.
+
+Below is an example using FastAPI.
+
+???+ note "Python only"
+
+    We currently only support custom authentication and authorization in Python deployments with `langgraph-api>=0.0.26`.
+
+## Create app
+
+Starting from an **existing** LangGraph Platform application, add the following custom route code to your `webapp.py` file. If you are starting from scratch, you can create a new app from a template using the CLI.
+
+```bash
+langgraph new --template=new-langgraph-project-python my_new_project
+```
+
+Once you have a LangGraph project, add the following app code:
+
+```python
+# ./src/agent/webapp.py
+from fastapi import FastAPI
+
+# highlight-next-line
+app = FastAPI()
+
+
+@app.get("/hello")
+def read_root():
+    return {"Hello": "World"}
+
+```
+
+## Configure `langgraph.json`
+
+Add the following to your `langgraph.json` file. Make sure the path points to the `app.py` file you created above.
+
+```json
+{
+  "dependencies": ["."],
+  "graphs": {
+    "agent": "./src/agent/graph.py:graph"
+  },
+  "env": ".env",
+  "http": {
+    "app": "./src/agent/webapp.py:app"
+  }
+  // Other configuration options like auth, store, etc.
+}
+```
+
+## Start server
+
+Test the server out locally:
+
+```bash
+langgraph dev --no-browser
+```
+
+If you navigate to `localhost:2024/hello` in your browser (2024 is the default development port), you should see the `hello` endpoint returning `{"Hello": "World"}`.
+
+
+!!! note "Shadowing default endpoints"
+
+    The routes you create in the app are given priority over the system defaults, meaning you can shadow and redefine the behavior of any default endpoint.
+
+## Deploying
+
+You can deploy this app as-is to the managed langgraph cloud or to your self-hosted platform.
+
+## Next steps
+
+Now that you've added a custom route to your deployment, you can use this same technique to further customize how your server behaves, such as defining custom [custom middleware](./custom_middleware.md) and [custom lifespan events](./custom_lifespan.md). 

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

@@ -59,12 +59,10 @@ LangGraph makes it easy to manage conversation [memory](../concepts/memory.md) i
 [Human-in-the-loop](../concepts/human_in_the_loop.md) functionality allows
 you to involve humans in the decision-making process of your graph. These how-to guides show how to implement human-in-the-loop workflows in your graph.
 
-
 Key workflows:
 
 - [How to wait for user input](human_in_the_loop/wait-user-input.ipynb): A basic example that shows how to implement a human-in-the-loop workflow in your graph using the `interrupt` function.
 - [How to review tool calls](human_in_the_loop/review-tool-calls.ipynb): Incorporate human-in-the-loop for reviewing/editing/accepting tool call requests before they executed using the `interrupt` function.
- 
 
 Other methods:
 
@@ -200,7 +198,6 @@ 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
 
@@ -215,6 +212,12 @@ LangGraph applications can be deployed using LangGraph Cloud, which provides a r
 - [How to add custom authentication](./auth/custom_auth.md)
 - [How to update the security schema of your OpenAPI spec](./auth/openapi_security.md)
 
+### Modifying the API
+
+- [How to add custom routes](./http/custom_routes.md)
+- [How to add custom middleware](./http/custom_middleware.md)
+- [How to add custom lifespan events](./http/custom_lifespan.md)
+
 ### Assistants
 
 [Assistants](../concepts/assistants.md) is a configured instance of a template.
@@ -253,6 +256,13 @@ 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.
@@ -284,10 +294,9 @@ Graph execution can take a while, and sometimes users may change their mind abou
 
 LangGraph Studio is a built-in UI for visualizing, testing, and debugging your agents.
 
-- [How to connect to a LangGraph Cloud deployment](../cloud/how-tos/test_deployment.md)
+- [How to connect to a LangGraph Platform deployment](../cloud/how-tos/test_deployment.md)
 - [How to connect to a local dev server](../how-tos/local-studio.md)
 - [How to connect to a local deployment (Docker)](../cloud/how-tos/test_local_deployment.md)
-- [How to test your graph in LangGraph Studio (MacOS only)](../cloud/how-tos/invoke_studio.md)
 - [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)
@@ -306,4 +315,4 @@ These are the guides for resolving common errors you may find while building wit
 
 These guides provide troubleshooting information for errors that are specific to the LangGraph Platform.
 
-- [INVALID_LICENSE](../troubleshooting/errors/INVALID_LICENSE.md)
+- [INVALID_LICENSE](../troubleshooting/errors/INVALID_LICENSE.md)

docs/docs/how-tos/local-studio.md

@@ -1,15 +1,6 @@
 # How to connect a local agent to LangGraph Studio
 
-This guide shows you how to connect your local agent to [LangGraph Studio](../concepts/langgraph_studio.md) for visualization, interaction, and debugging.
-
-## Connection Options
-
-There are two ways to connect your local agent to LangGraph Studio:
-
-- [Development Server](../concepts/langgraph_studio.md#development-server-with-web-ui): Python package, all platforms, no Docker
-- [LangGraph Desktop](../concepts/langgraph_studio.md#desktop-app): Application, Mac only, requires Docker
-
-In this guide we will cover how to use the development server as that is generally an easier and better experience.
+This guide shows you how to connect your local agent to [LangGraph Studio](../concepts/langgraph_studio.md) for visualization, interaction, and debugging using the development server.
 
 ## Setup your application
 
@@ -24,9 +15,8 @@ You will need to make sure to install the `inmem` extras.
 
 ???+ note "Minimum version"
 
-  The minimum version to use the `inmem` extra with `langgraph-cli` is `0.1.55`.
-  Python 3.11 or higher is required.
-  
+The minimum version to use the `inmem` extra with `langgraph-cli` is `0.1.55`.
+Python 3.11 or higher is required.
 
 ```shell
 pip install -U "langgraph-cli[inmem]"
@@ -41,7 +31,7 @@ pip install -U "langgraph-cli[inmem]"
    langgraph dev
    ```
 
-This will look for the `langgraph.json` file in your current directory. 
+This will look for the `langgraph.json` file in your current directory.
 In there, it will find the paths to the graph(s), and start those up.
 It will then automatically connect to the cloud-hosted studio.
 
@@ -89,4 +79,4 @@ Then attach your preferred debugger:
     2. Click + and select "Python Debug Server"
     3. Set IDE host name: `localhost`
     4. Set port: `5678` (or the port number you chose in the previous step)
-    5. Click "OK" and start debugging
+    5. Click "OK" and start debugging

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/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 +1,36 @@
+# LLMs-txt for LangGraph
+
+## Overview
+
+LangGraph provides 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) |
+
+## 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 utilize `llms.txt` effectively through an MCP server.
+
+We provide an MCP server specifically designed to serve documentation, called [`mcpdoc`](https://github.com/langchain-ai/mcpdoc). This setup is compatible with IDEs and platforms such as Cursor, Windsurf, Claude, and Claude Code. Instructions for using `mcpdoc` with these tools 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 +1,191 @@
+# LangGraph
+
+## Quickstart
+
+These guides are designed to help you get started with LangGraph.
+
+- [LangGraph Quickstart](https://langchain-ai.github.io/langgraph/tutorials/introduction/): Build a chatbot that can use tools and keep track of conversation history. Add human-in-the-loop capabilities and explore how time-travel works.
+- [Common Workflows](https://langchain-ai.github.io/langgraph/tutorials/workflows/): Overview of the most common workflows using LLMs implemented with LangGraph.
+- [LangGraph Server Quickstart](https://langchain-ai.github.io/langgraph/tutorials/langgraph-platform/local-server/): Launch a LangGraph server locally and interact with it using REST API and LangGraph Studio Web UI.
+- [Deploy with LangGraph Cloud Quickstart](https://langchain-ai.github.io/langgraph/cloud/quick_start/): Deploy a LangGraph app using LangGraph Cloud.
+
+## Concepts
+
+These guides provide explanations of the key concepts behind the LangGraph framework.
+
+- [Why LangGraph?](https://langchain-ai.github.io/langgraph/concepts/high_level/): Motivation for LangGraph, a library for building agentic applications with LLMs.
+- [LangGraph Glossary](https://langchain-ai.github.io/langgraph/concepts/low_level/): LangGraph workflows are designed as graphs, with nodes representing different components and edges representing the flow of information between them. This guide provides an overview of the key concepts associated with LangGraph graph primitives.
+- [Common Agentic Patterns](https://langchain-ai.github.io/langgraph/concepts/agentic_concepts/): An agent uses an LLM to pick its own control flow to solve more complex problems! Agents are a key building block in many LLM applications. This guide explains the different types of agent architectures and how they can be used to control the flow of an application.
+- [Multi-Agent Systems](https://langchain-ai.github.io/langgraph/concepts/multi_agent/): Complex LLM applications can often be broken down into multiple agents, each responsible for a different part of the application. This guide explains common patterns for building multi-agent systems.
+- [Breakpoints](https://langchain-ai.github.io/langgraph/concepts/breakpoints/): Breakpoints allow pausing the execution of a graph at specific points. Breakpoints allow stepping through graph execution for debugging purposes.
+- [Human-in-the-Loop](https://langchain-ai.github.io/langgraph/concepts/human_in_the_loop/): Explains different ways of integrating human feedback into a LangGraph application.
+- [Time Travel](https://langchain-ai.github.io/langgraph/concepts/time-travel/): Time travel allows you to replay past actions in your LangGraph application to explore alternative paths and debug issues.
+- [Persistence](https://langchain-ai.github.io/langgraph/concepts/persistence/): LangGraph has a built-in persistence layer, implemented through checkpointers. This persistence layer helps to support powerful capabilities like human-in-the-loop, memory, time travel, and fault-tolerance.
+- [Memory](https://langchain-ai.github.io/langgraph/concepts/memory/): Memory in AI applications refers to the ability to process, store, and effectively recall information from past interactions. With memory, your agents can learn from feedback and adapt to users' preferences.
+- [Streaming](https://langchain-ai.github.io/langgraph/concepts/streaming/): Streaming is crucial for enhancing the responsiveness of applications built on LLMs. By displaying output progressively, even before a complete response is ready, streaming significantly improves user experience (UX), particularly when dealing with the latency of LLMs.
+- [Functional API](https://langchain-ai.github.io/langgraph/concepts/functional_api/): `@entrypoint` and `@task` decorators that allow you to add LangGraph functionality to an existing codebase.
+- [Durable Execution](https://langchain-ai.github.io/langgraph/concepts/durable_execution/): LangGraph's built-in [persistence](https://langchain-ai.github.io/langgraph/concepts/persistence/) layer provides durable execution for workflows, ensuring that the state of each execution step is saved to a durable store. 
+- [Pregel](https://langchain-ai.github.io/langgraph/concepts/pregel/): Pregel is LangGraph's runtime, which is responsible for managing the execution of LangGraph applications.
+- [FAQ](https://langchain-ai.github.io/langgraph/concepts/faq/): Frequently asked questions about LangGraph.
+
+## How-tos
+
+Here you’ll find answers to “How do I...?” types of questions. 
+
+These guides are **goal-oriented** and concrete. 
+
+They're meant to help you complete a specific task.
+
+### Graph API Basics
+
+- [How to update graph state from nodes](https://langchain-ai.github.io/langgraph/how-tos/state-reducers/)
+- [How to create a sequence of steps](https://langchain-ai.github.io/langgraph/how-tos/sequence/)
+- [How to create branches for parallel execution](https://langchain-ai.github.io/langgraph/how-tos/branching/)
+- [How to create and control loops with recursion limits](https://langchain-ai.github.io/langgraph/how-tos/recursion-limit/)
+- [How to visualize your graph](https://langchain-ai.github.io/langgraph/how-tos/visualization/)
+
+### Fine-grained Control
+
+These guides demonstrate LangGraph features that grant fine-grained control over the execution of your graph.
+
+- [How to create map-reduce branches for parallel execution](https://langchain-ai.github.io/langgraph/how-tos/map-reduce/)
+- [How to update state and jump to nodes in graphs and subgraphs](https://langchain-ai.github.io/langgraph/how-tos/command/)
+- [How to add runtime configuration to your graph](https://langchain-ai.github.io/langgraph/how-tos/configuration/)
+- [How to add node retries](https://langchain-ai.github.io/langgraph/how-tos/node-retries/)
+- [How to return state before hitting recursion limit](https://langchain-ai.github.io/langgraph/how-tos/return-when-recursion-limit-hits/)
+
+### Persistence
+ 
+Persistence makes it easy to persist state across graph runs (per-thread persistence) and across threads (cross-thread persistence). 
+
+These how-to guides show how to add persistence to your graph.
+
+- [How to add thread-level persistence to your graph](https://langchain-ai.github.io/langgraph/how-tos/persistence/)
+- [How to add thread-level persistence to a subgraph](https://langchain-ai.github.io/langgraph/how-tos/subgraph-persistence/)
+- [How to add cross-thread persistence to your graph](https://langchain-ai.github.io/langgraph/how-tos/cross-thread-persistence/)
+- [How to use Postgres checkpointer for persistence](https://langchain-ai.github.io/langgraph/how-tos/persistence_postgres/)
+- [How to use MongoDB checkpointer for persistence](https://langchain-ai.github.io/langgraph/how-tos/persistence_mongodb/)
+- [How to create a custom checkpointer using Redis](https://langchain-ai.github.io/langgraph/how-tos/persistence_redis/)
+
+See the below guides for how-to add persistence to your workflow using the [Functional API](https://langchain-ai.github.io/langgraph/concepts/functional_api/):
+
+- [How to add thread-level persistence (functional API)](https://langchain-ai.github.io/langgraph/how-tos/persistence-functional/)
+- [How to add cross-thread persistence (functional API)](https://langchain-ai.github.io/langgraph/how-tos/cross-thread-persistence-functional/)
+
+### Memory
+
+LangGraph makes it easy to manage conversation memory in your graph. These how-to guides show how to implement different strategies for that.
+
+- [How to manage conversation history](https://langchain-ai.github.io/langgraph/how-tos/memory/manage-conversation-history/)
+- [How to delete messages](https://langchain-ai.github.io/langgraph/how-tos/memory/delete-messages/)
+- [How to add summary conversation memory](https://langchain-ai.github.io/langgraph/how-tos/memory/add-summary-conversation-history/)
+- [How to add long-term memory (cross-thread)](https://langchain-ai.github.io/langgraph/how-tos/memory/cross-thread-persistence/)
+- [How to use semantic search for long-term memory](https://langchain-ai.github.io/langgraph/how-tos/memory/semantic-search/)
+
+### Human-in-the-loop
+
+Human-in-the-loop functionality allows you to involve humans in the decision-making process of your graph.
+
+These how-to guides show how to implement human-in-the-loop workflows in your graph.
+
+- [How to wait for user input](https://langchain-ai.github.io/langgraph/how-tos/human_in_the_loop/wait-user-input/): A basic example that shows how to implement a human-in-the-loop workflow in your graph using the `interrupt` function.
+- [How to review tool calls](https://langchain-ai.github.io/langgraph/how-tos/human_in_the_loop/review-tool-calls/): Incorporate human-in-the-loop for reviewing/editing/accepting tool call requests before they executed using the `interrupt` function.
+- [How to add static breakpoints](https://langchain-ai.github.io/langgraph/how-tos/human_in_the_loop/breakpoints/): Use for debugging purposes. For human-in-the-loop workflows, we recommend the [`interrupt` function](https://langchain-ai.github.io/langgraph/reference/types/#langgraph.types.interrupt) instead.
+- [How to edit graph state](https://langchain-ai.github.io/langgraph/how-tos/human_in_the_loop/edit-graph-state/): Edit graph state using `graph.update_state` method. Use this if implementing a **human-in-the-loop** workflow via **static breakpoints**.
+
+See the below guides for how-to implement human-in-the-loop workflows with the Functional API.
+
+- [How to wait for user input (Functional API)](https://langchain-ai.github.io/langgraph/how-tos/wait-user-input-functional/)
+- [How to review tool calls (Functional API)](https://langchain-ai.github.io/langgraph/how-tos/review-tool-calls-functional/)
+
+### Time Travel
+
+[Time travel](https://langchain-ai.github.io/langgraph/concepts/time-travel/) allows you to replay past actions in your LangGraph application to explore alternative paths and debug issues. These how-to guides show how to use time travel in your graph.
+
+- [How to view and update past graph state](https://langchain-ai.github.io/langgraph/how-tos/time-travel/)
+
+### Streaming
+
+[Streaming](https://langchain-ai.github.io/langgraph/concepts/streaming/) is crucial for enhancing the responsiveness of applications built on LLMs. By displaying output progressively, even before a complete response is ready, streaming significantly improves user experience (UX), particularly when dealing with the latency of LLMs.
+
+- [How to stream](https://langchain-ai.github.io/langgraph/how-tos/streaming/)
+- [How to stream LLM tokens](https://langchain-ai.github.io/langgraph/how-tos/streaming-tokens/)
+- [How to stream LLM tokens from specific nodes](https://langchain-ai.github.io/langgraph/how-tos/streaming-specific-nodes/)
+- [How to stream data from within a tool](https://langchain-ai.github.io/langgraph/how-tos/streaming-events-from-within-tools/)
+- [How to stream from subgraphs](https://langchain-ai.github.io/langgraph/how-tos/streaming-subgraphs/)
+- [How to disable streaming for models that don't support it](https://langchain-ai.github.io/langgraph/how-tos/disable-streaming/)
+
+### Tool calling
+
+[Tool calling](https://python.langchain.com/docs/concepts/tool_calling/) is a type of [chat model](https://python.langchain.com/docs/concepts/chat_models/) API.
+
+It accepts tool schemas, along with messages, as input and returns invocations of those tools as part of the output message.
+
+These how-to guides show common patterns for tool calling with LangGraph:
+
+- [How to call tools using ToolNode](https://langchain-ai.github.io/langgraph/how-tos/tool-calling/)
+- [How to handle tool calling errors](https://langchain-ai.github.io/langgraph/how-tos/tool-calling-errors/)
+- [How to pass runtime values to tools](https://langchain-ai.github.io/langgraph/how-tos/pass-run-time-values-to-tools/)
+- [How to pass config to tools](https://langchain-ai.github.io/langgraph/how-tos/pass-config-to-tools/)
+- [How to update graph state from tools](https://langchain-ai.github.io/langgraph/how-tos/update-state-from-tools/)
+- [How to handle large numbers of tools](https://langchain-ai.github.io/langgraph/how-tos/many-tools/)
+
+### Subgraphs
+
+Subgraphs allow you to reuse an existing graph from another graph. 
+
+These how-to guides show how to use subgraphs:
+
+- [How to use subgraphs](https://langchain-ai.github.io/langgraph/how-tos/subgraph/)
+- [How to view and update state in subgraphs](https://langchain-ai.github.io/langgraph/how-tos/subgraphs-manage-state/)
+- [How to transform inputs and outputs of a subgraph](https://langchain-ai.github.io/langgraph/how-tos/subgraph-transform-state/)
+
+### Multi-agent
+
+Multi-agent systems are useful to break down complex LLM applications into multiple agents, each responsible for a different part of the application. 
+
+These how-to guides show how to implement multi-agent systems in LangGraph:
+
+- [How to implement handoffs between agents](https://langchain-ai.github.io/langgraph/how-tos/agent-handoffs/)
+- [How to build a multi-agent network](https://langchain-ai.github.io/langgraph/how-tos/multi-agent-network/)
+- [How to add multi-turn conversation in a multi-agent application](https://langchain-ai.github.io/langgraph/how-tos/multi-agent-multi-turn-convo/)
+
+### State Management
+
+- [How to use Pydantic model as graph state](https://langchain-ai.github.io/langgraph/how-tos/state-model/)
+- [How to define input/output schema for your graph](https://langchain-ai.github.io/langgraph/how-tos/input_output_schema/)
+- [How to pass private state between nodes inside the graph](https://langchain-ai.github.io/langgraph/how-tos/pass_private_state/)
+
+### Other
+
+- [How to run graph asynchronously](https://langchain-ai.github.io/langgraph/how-tos/async/)
+- [How to force tool-calling agent to structure output](https://langchain-ai.github.io/langgraph/how-tos/react-agent-structured-output/)
+- [How to pass custom LangSmith run ID for graph runs](https://langchain-ai.github.io/langgraph/how-tos/run-id-langsmith/)
+- [How to integrate LangGraph with AutoGen, CrewAI, and other frameworks](https://langchain-ai.github.io/langgraph/how-tos/autogen-integration/)
+
+## Use cases 
+
+Explore practical implementations tailored for specific scenarios:
+
+### Chatbots
+
+- [Customer Support](https://langchain-ai.github.io/langgraph/tutorials/customer-support/customer-support/): Build a multi-functional support bot for flights, hotels, and car rentals.
+- [Prompt Generation from User Requirements](https://langchain-ai.github.io/langgraph/tutorials/chatbots/information-gather-prompting/): Build an information gathering chatbot.
+- [Code Assistant](https://langchain-ai.github.io/langgraph/tutorials/code_assistant/langgraph_code_assistant/): Build a code analysis and generation assistant.
+
+### RAG
+
+- [Agentic RAG](https://langchain-ai.github.io/langgraph/tutorials/rag/langgraph_agentic_rag/): Use an agent to figure out how to retrieve the most relevant information before using the retrieved information to answer the user's question.
+- [Adaptive RAG](https://langchain-ai.github.io/langgraph/tutorials/rag/langgraph_adaptive_rag/): Adaptive RAG is a strategy for RAG that unites (1) query analysis with (2) active / self-corrective RAG. Implementation of: https://arxiv.org/abs/2403.14403
+    - For a version that uses a local LLM: [Adaptive RAG using local LLMs](https://langchain-ai.github.io/langgraph/tutorials/rag/langgraph_adaptive_rag_local/)
+- [Corrective RAG](https://langchain-ai.github.io/langgraph/tutorials/rag/langgraph_crag/): Uses an LLM to grade the quality of the retrieved information from the given source, and if the quality is low, it will try to retrieve the information from another source. Implementation of: https://arxiv.org/pdf/2401.15884.pdf 
+    - For a version that uses a local LLM: [Corrective RAG using local LLMs](https://langchain-ai.github.io/langgraph/tutorials/rag/langgraph_crag_local/)
+- [Self-RAG](https://langchain-ai.github.io/langgraph/tutorials/rag/langgraph_self_rag/): Self-RAG is a strategy for RAG that incorporates self-reflection / self-grading on retrieved documents and generations. Implementation of https://arxiv.org/abs/2310.11511.
+    - For a version that uses a local LLM: [Self-RAG using local LLMs](https://langchain-ai.github.io/langgraph/tutorials/rag/langgraph_self_rag_local/) 
+- [SQL Agent](https://langchain-ai.github.io/langgraph/tutorials/sql-agent/): Build a SQL agent that can answer questions about a SQL database.
+
+### Multi-Agent Systems
+
+- [Network](https://langchain-ai.github.io/langgraph/tutorials/multi_agent/multi-agent-collaboration/): Enable two or more agents to collaborate on a task
+- [Supervisor](https://langchain-ai.github.io/langgraph/tutorials/multi_agent/agent_supervisor/): Use an LLM to orchestrate and delegate to individual agents
+- [Hierarchical Teams](https://langchain-ai.github.io/langgraph/tutorials/multi_agent/hierarchical_agent_teams/): Orchestrate nested teams of agents to solve problems

docs/docs/reference/pregel.md

@@ -1,9 +1,7 @@
-::: langgraph.pregel.Pregel
+# Pregel
+
+::: langgraph.pregel
     options:
       members:
-        - stream
-        - astream
-        - invoke
-        - ainvoke
-        - update_state
-        - aupdate_state
+        - Pregel 
+        - PregelNode 

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

docs/docs/tutorials/workflows/index.md

@@ -184,7 +184,7 @@ As noted in the [Anthropic blog](https://www.anthropic.com/research/building-eff
 
     See our lesson on Prompt Chaining [here](https://github.com/langchain-ai/langchain-academy/blob/main/module-1/chain.ipynb).
 
-=== "Functional API (beta)"
+=== "Functional API"
 
     ```python
     from langgraph.func import entrypoint, task
@@ -335,7 +335,7 @@ With parallelization, LLMs work simultaneously on a task:
 
     See our lesson on parallelization [here](https://github.com/langchain-ai/langchain-academy/blob/main/module-1/simple-graph.ipynb).
 
-=== "Functional API (beta)"
+=== "Functional API"
 
     ```python
     @task
@@ -524,7 +524,7 @@ Routing classifies an input and directs it to a followup task. As noted in the [
 
     [Here](https://langchain-ai.github.io/langgraph/tutorials/rag/langgraph_adaptive_rag_local/) is RAG workflow that routes questions. See our video [here](https://www.youtube.com/watch?v=bq1Plo2RhYI).
 
-=== "Functional API (beta)"
+=== "Functional API"
 
     ```python
     from typing_extensions import Literal
@@ -761,7 +761,7 @@ With orchestrator-worker, an orchestrator breaks down a task and delegates each
     [Here](https://github.com/langchain-ai/report-mAIstro) is a project that uses orchestrator-worker for report planning and writing. See our video [here](https://www.youtube.com/watch?v=wSxZ7yFbbas).
 
 
-=== "Functional API (beta)"
+=== "Functional API"
 
     ```python
     from typing import List
@@ -952,7 +952,7 @@ In the evaluator-optimizer workflow, one LLM call generates a response while ano
 
     [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).
 
-=== "Functional API (beta)"
+=== "Functional API"
 
     ```python
     # Schema for structured output to use in evaluation
@@ -1161,7 +1161,7 @@ llm_with_tools = llm.bind_tools(tools)
 
     [Here](https://github.com/langchain-ai/memory-agent) is a project that uses a tool calling agent to create / store long-term memories.
 
-=== "Functional API (beta)"
+=== "Functional API"
 
     ```python
     from langgraph.graph import add_messages
@@ -1270,4 +1270,4 @@ LangGraph provides several ways to stream workflow / agent outputs or intermedia
 
 ### Deployment
 
-LangGraph provides an easy on-ramp for deployment, observability, and evaluation. See [module 6](https://github.com/langchain-ai/langchain-academy/tree/main/module-6) of LangChain Academy.
+LangGraph provides an easy on-ramp for deployment, observability, and evaluation. See [module 6](https://github.com/langchain-ai/langchain-academy/tree/main/module-6) of LangChain Academy.

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:
@@ -231,6 +231,7 @@ 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
@@ -271,6 +272,7 @@ nav:
           - concepts/streaming.md
           - concepts/functional_api.md
           - concepts/durable_execution.md
+          - concepts/pregel.md
         - LangGraph Platform:
           - LangGraph Platform: concepts#langgraph-platform
           - High Level:
@@ -358,7 +360,8 @@ nav:
     - Resources:
       # NOTE: prebuilt.md is auto-generated by `make build-prebuilt`
       - Prebuilt Agents: prebuilt.md
-      - Adopters: adopters.md
+      - Companies using LangGraph: adopters.md
+      - LLMS-txt: llms-txt-overview.md
       - FAQ: concepts/faq.md
       - Troubleshooting:
           - Troubleshooting: troubleshooting/errors/index.md

docs/poetry.lock

@@ -169,15 +169,15 @@ files = [
 
 [[package]]
 name = "anthropic"
-version = "0.45.2"
+version = "0.47.2"
 description = "The official Python library for the anthropic API"
 optional = false
 python-versions = ">=3.8"
 groups = ["test"]
 markers = "python_version <= \"3.11\" or python_version >= \"3.12\""
 files = [
-    {file = "anthropic-0.45.2-py3-none-any.whl", hash = "sha256:ecd746f7274451dfcb7e1180571ead624c7e1195d1d46cb7c70143d2aedb4d35"},
-    {file = "anthropic-0.45.2.tar.gz", hash = "sha256:32a18b9ecd12c91b2be4cae6ca2ab46a06937b5aa01b21308d97a6d29794fb5e"},
+    {file = "anthropic-0.47.2-py3-none-any.whl", hash = "sha256:61b712a56308fce69f04d92ba0230ab2bc187b5bce17811d400843a8976bb67f"},
+    {file = "anthropic-0.47.2.tar.gz", hash = "sha256:452f4ca0c56ffab8b6ce9928bf8470650f88106a7001b250895eb65c54cfa44c"},
 ]
 
 [package.dependencies]
@@ -1299,7 +1299,7 @@ version = "0.7.1"
 description = "XML bomb protection for Python stdlib modules"
 optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
-groups = ["docs", "test"]
+groups = ["docs"]
 markers = "python_version <= \"3.11\" or python_version >= \"3.12\""
 files = [
     {file = "defusedxml-0.7.1-py2.py3-none-any.whl", hash = "sha256:a352e7e428770286cc899e2542b6cdaedb2b4953ff269a210103ec58f6198a61"},
@@ -3288,21 +3288,20 @@ together = ["langchain-together"]
 
 [[package]]
 name = "langchain-anthropic"
-version = "0.2.4"
+version = "0.3.8"
 description = "An integration package connecting AnthropicMessages and LangChain"
 optional = false
 python-versions = "<4.0,>=3.9"
 groups = ["test"]
 markers = "python_version <= \"3.11\" or python_version >= \"3.12\""
 files = [
-    {file = "langchain_anthropic-0.2.4-py3-none-any.whl", hash = "sha256:bcb6c2d0df4a67aff52816621079d6e743b260911caccf313a72b33b7edece6f"},
-    {file = "langchain_anthropic-0.2.4.tar.gz", hash = "sha256:0382d4c7b5236839b703f7b72b3e06de4bb5be99104b193f719adbe34c49562b"},
+    {file = "langchain_anthropic-0.3.8-py3-none-any.whl", hash = "sha256:05a70f51500d3c4e0f3e463730e193a25b6244e06b3bda3d7b2ec21d83d081ae"},
+    {file = "langchain_anthropic-0.3.8.tar.gz", hash = "sha256:1932977b8105744739ffdcb39861b041b73ae93846d0896a775fcea9a29e4b2b"},
 ]
 
 [package.dependencies]
-anthropic = ">=0.30.0,<1"
-defusedxml = ">=0.7.1,<0.8.0"
-langchain-core = ">=0.3.15,<0.4.0"
+anthropic = ">=0.47.0,<1"
+langchain-core = ">=0.3.39,<1.0.0"
 pydantic = ">=2.7.4,<3.0.0"
 
 [[package]]
@@ -3357,15 +3356,15 @@ tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<10"
 
 [[package]]
 name = "langchain-core"
-version = "0.3.34"
+version = "0.3.40"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = "<4.0,>=3.9"
 groups = ["docs", "test"]
 markers = "python_version <= \"3.11\" or python_version >= \"3.12\""
 files = [
-    {file = "langchain_core-0.3.34-py3-none-any.whl", hash = "sha256:a057ebeddd2158d3be14bde341b25640ddf958b6989bd6e47160396f5a8202ae"},
-    {file = "langchain_core-0.3.34.tar.gz", hash = "sha256:26504cf1e8e6c310adad907b890d4e3c147581cfa7434114f6dc1134fe4bc6d3"},
+    {file = "langchain_core-0.3.40-py3-none-any.whl", hash = "sha256:9f31358741f10a13db8531e8288b8a5ae91904018c5c2e6f739d6645a98fca03"},
+    {file = "langchain_core-0.3.40.tar.gz", hash = "sha256:893a238b38491967c804662c1ec7c3e6ebaf223d1125331249c3cf3862ff2746"},
 ]
 
 [package.dependencies]
@@ -3474,19 +3473,19 @@ ollama = ">=0.4.4,<1"
 
 [[package]]
 name = "langchain-openai"
-version = "0.3.4"
+version = "0.3.7"
 description = "An integration package connecting OpenAI and LangChain"
 optional = false
 python-versions = "<4.0,>=3.9"
 groups = ["test"]
 markers = "python_version <= \"3.11\" or python_version >= \"3.12\""
 files = [
-    {file = "langchain_openai-0.3.4-py3-none-any.whl", hash = "sha256:58d0c014620eb92f4f46ff9daf584c2a7794896b1379eb85ad7be8d9f3493b61"},
-    {file = "langchain_openai-0.3.4.tar.gz", hash = "sha256:c6645745a1d1bf19f21ea6fa473a746bd464053ff57ce563215e6165a0c4b9f1"},
+    {file = "langchain_openai-0.3.7-py3-none-any.whl", hash = "sha256:0aefc7bdf8e7398d41e09c4313cace816df6438f2aa93d34f79523487310f0da"},
+    {file = "langchain_openai-0.3.7.tar.gz", hash = "sha256:b8b51a3aaa1cc3bda060651ea41145f7728219e8a7150b5404fb1e8446de9cef"},
 ]
 
 [package.dependencies]
-langchain-core = ">=0.3.34,<1.0.0"
+langchain-core = ">=0.3.39,<1.0.0"
 openai = ">=1.58.1,<2.0.0"
 tiktoken = ">=0.7,<1"
 
@@ -3508,17 +3507,17 @@ langchain-core = ">=0.3.34,<1.0.0"
 
 [[package]]
 name = "langgraph"
-version = "0.2.71"
+version = "0.3.0"
 description = "Building stateful, multi-actor applications with LLMs"
 optional = false
 python-versions = ">=3.9.0,<4.0"
-groups = ["docs", "test"]
+groups = ["docs"]
 markers = "python_version <= \"3.11\" or python_version >= \"3.12\""
 files = []
 develop = true
 
 [package.dependencies]
-langchain-core = ">=0.2.43,<0.4.0,!=0.3.0,!=0.3.1,!=0.3.2,!=0.3.3,!=0.3.4,!=0.3.5,!=0.3.6,!=0.3.7,!=0.3.8,!=0.3.9,!=0.3.10,!=0.3.11,!=0.3.12,!=0.3.13,!=0.3.14,!=0.3.15,!=0.3.16,!=0.3.17,!=0.3.18,!=0.3.19,!=0.3.20,!=0.3.21,!=0.3.22"
+langchain-core = ">=0.1,<0.4"
 langgraph-checkpoint = "^2.0.10"
 langgraph-sdk = "^0.1.42"
 
@@ -3528,7 +3527,7 @@ url = "../libs/langgraph"
 
 [[package]]
 name = "langgraph-checkpoint"
-version = "2.0.13"
+version = "2.0.16"
 description = "Library with base interfaces for LangGraph checkpoint savers."
 optional = false
 python-versions = "^3.9.0,<4.0"
@@ -3547,26 +3546,25 @@ url = "../libs/checkpoint"
 
 [[package]]
 name = "langgraph-checkpoint-mongodb"
-version = "0.1.0"
+version = "0.1.1"
 description = "Library with a MongoDB implementation of LangGraph checkpoint saver."
 optional = false
-python-versions = "<4.0.0,>=3.9.0"
+python-versions = ">=3.9"
 groups = ["test"]
 markers = "python_version <= \"3.11\" or python_version >= \"3.12\""
 files = [
-    {file = "langgraph_checkpoint_mongodb-0.1.0-py3-none-any.whl", hash = "sha256:52f20956b36e0275ff805a1eea1db4c1a7e5e0ffe0a1ade65969004fa1654703"},
-    {file = "langgraph_checkpoint_mongodb-0.1.0.tar.gz", hash = "sha256:3165c134ad5c82a3fe02fef04c81dcd48a3f5d031e07a9d1cb84457241f76793"},
+    {file = "langgraph_checkpoint_mongodb-0.1.1-py3-none-any.whl", hash = "sha256:1ff2c3cb2a9139c38ea9cf398659b8b32d6bbfcc4999713b62014431477c5ac5"},
+    {file = "langgraph_checkpoint_mongodb-0.1.1.tar.gz", hash = "sha256:350d347b0458fb7977231ac1295095bef512458ee0debe09fd394d913b8d89d3"},
 ]
 
 [package.dependencies]
-langgraph = ">=0.2.38,<0.3.0"
-langgraph-checkpoint = ">=2.0.0,<3.0.0"
+langgraph-checkpoint = ">=2.0.0"
 motor = ">3.5.0"
-pymongo = ">=4.9.0,<4.10.0"
+pymongo = ">=4.9,<4.12"
 
 [[package]]
 name = "langgraph-checkpoint-postgres"
-version = "2.0.14"
+version = "2.0.15"
 description = "Library with a Postgres implementation of LangGraph checkpoint saver."
 optional = false
 python-versions = "^3.9.0,<4.0"
@@ -3576,7 +3574,7 @@ files = []
 develop = true
 
 [package.dependencies]
-langgraph-checkpoint = "^2.0.10"
+langgraph-checkpoint = "^2.0.15"
 orjson = ">=3.10.1"
 psycopg = "^3.2.0"
 psycopg-pool = "^3.2.0"
@@ -3587,7 +3585,7 @@ url = "../libs/checkpoint-postgres"
 
 [[package]]
 name = "langgraph-checkpoint-sqlite"
-version = "2.0.4"
+version = "2.0.5"
 description = "Library with a SQLite implementation of LangGraph checkpoint saver."
 optional = false
 python-versions = "^3.9.0"
@@ -3597,20 +3595,40 @@ files = []
 develop = true
 
 [package.dependencies]
-aiosqlite = "^0.20.0"
-langgraph-checkpoint = "^2.0.10"
+aiosqlite = ">=0.20,<0.22"
+langgraph-checkpoint = "^2.0.15"
 
 [package.source]
 type = "directory"
 url = "../libs/checkpoint-sqlite"
 
+[[package]]
+name = "langgraph-prebuilt"
+version = "1.0.0"
+description = "Library with high-level APIs for creating and executing LangGraph agents and tools."
+optional = false
+python-versions = "^3.9.0,<4.0"
+groups = ["docs"]
+markers = "python_version <= \"3.11\" or python_version >= \"3.12\""
+files = []
+develop = true
+
+[package.dependencies]
+langchain-core = ">=0.2.43,<0.4.0,!=0.3.0,!=0.3.1,!=0.3.2,!=0.3.3,!=0.3.4,!=0.3.5,!=0.3.6,!=0.3.7,!=0.3.8,!=0.3.9,!=0.3.10,!=0.3.11,!=0.3.12,!=0.3.13,!=0.3.14,!=0.3.15,!=0.3.16,!=0.3.17,!=0.3.18,!=0.3.19,!=0.3.20,!=0.3.21,!=0.3.22"
+langgraph = ">=0.3,<0.4"
+langgraph-checkpoint = "^2.0.10"
+
+[package.source]
+type = "directory"
+url = "../libs/prebuilt"
+
 [[package]]
 name = "langgraph-sdk"
-version = "0.1.51"
+version = "0.1.53"
 description = "SDK for interacting with LangGraph API"
 optional = false
 python-versions = "^3.9.0,<4.0"
-groups = ["docs", "test"]
+groups = ["docs"]
 markers = "python_version <= \"3.11\" or python_version >= \"3.12\""
 files = []
 develop = true
@@ -5939,7 +5957,6 @@ python-versions = ">=3.8"
 groups = ["test"]
 markers = "python_version <= \"3.11\" or python_version >= \"3.12\""
 files = [
-    {file = "pyasn1-0.6.1-py3-none-any.whl", hash = "sha256:0d632f46f2ba09143da3a8afe9e33fb6f92fa2320ab7e886e2d0f7672af84629"},
     {file = "pyasn1-0.6.1.tar.gz", hash = "sha256:6f580d2bdd84365380830acf45550f2511469f673cb4a5ae3857a3170128b034"},
 ]
 
@@ -5952,7 +5969,6 @@ python-versions = ">=3.8"
 groups = ["test"]
 markers = "python_version <= \"3.11\" or python_version >= \"3.12\""
 files = [
-    {file = "pyasn1_modules-0.4.1-py3-none-any.whl", hash = "sha256:49bfa96b45a292b711e986f222502c1c9a5e1f4e568fc30e2574a6c7d07838fd"},
     {file = "pyasn1_modules-0.4.1.tar.gz", hash = "sha256:c28e2dbf9c06ad61c71a075c7e0f9fd0f1b0bb2d2ad4377f240d33ac2ab60a7c"},
 ]
 
@@ -8634,4 +8650,4 @@ type = ["pytest-mypy"]
 [metadata]
 lock-version = "2.1"
 python-versions = "^3.10"
-content-hash = "06debb82135affdb2baf1fdcc028c062c236121508d787588cd0de1db2da11e4"
+content-hash = "ac9af57c6abaddd1f181551a7bb8194ef3e4491391a0f2dc71417d68e85cb5b3"

docs/pyproject.toml

@@ -13,6 +13,7 @@ hub = "^3.0.1"
 
 [tool.poetry.group.docs.dependencies]
 langgraph = { path = "../libs/langgraph/", develop = true }
+langgraph-prebuilt = {path = "../libs/prebuilt", develop = true}
 langgraph-checkpoint = { path = "../libs/checkpoint/", develop = true }
 langgraph-checkpoint-sqlite = { path = "../libs/checkpoint-sqlite", develop = true }
 langgraph-checkpoint-postgres = { path = "../libs/checkpoint-postgres", develop = true }
@@ -40,8 +41,8 @@ langchain-cohere = "^0.4.2"
 
 [tool.poetry.group.test.dependencies]
 langchain = "^0.3.8"
-langchain-openai = "^0.3.0"
-langchain-anthropic = "^0.2.1"
+langchain-openai = "^0.3.7"
+langchain-anthropic = "^0.3.8"
 langchain-nomic = "^0.1.3"
 langchain-fireworks = "^0.2.0"
 langchain-community = "^0.3.0"

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,
@@ -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
 
@@ -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/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

@@ -530,6 +530,7 @@ 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

@@ -1,23 +1,23 @@
-# This file is automatically @generated by Poetry 2.0.0 and should not be changed by hand.
+# This file is automatically @generated by Poetry 2.0.1 and should not be changed by hand.
 
 [[package]]
 name = "aiosqlite"
-version = "0.20.0"
+version = "0.21.0"
 description = "asyncio bridge to the standard sqlite3 module"
 optional = false
-python-versions = ">=3.8"
+python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "aiosqlite-0.20.0-py3-none-any.whl", hash = "sha256:36a1deaca0cac40ebe32aac9977a6e2bbc7f5189f23f4a54d5908986729e5bd6"},
-    {file = "aiosqlite-0.20.0.tar.gz", hash = "sha256:6d35c8c256637f4672f843c31021464090805bf925385ac39473fb16eaaca3d7"},
+    {file = "aiosqlite-0.21.0-py3-none-any.whl", hash = "sha256:2549cf4057f95f53dcba16f2b64e8e2791d7e1adedb13197dd8ed77bb226d7d0"},
+    {file = "aiosqlite-0.21.0.tar.gz", hash = "sha256:131bb8056daa3bc875608c631c678cda73922a2d4ba8aec373b19f18c17e7aa3"},
 ]
 
 [package.dependencies]
 typing_extensions = ">=4.0"
 
 [package.extras]
-dev = ["attribution (==1.7.0)", "black (==24.2.0)", "coverage[toml] (==7.4.1)", "flake8 (==7.0.0)", "flake8-bugbear (==24.2.6)", "flit (==3.9.0)", "mypy (==1.8.0)", "ufmt (==2.3.0)", "usort (==1.0.8.post1)"]
-docs = ["sphinx (==7.2.6)", "sphinx-mdinclude (==0.5.3)"]
+dev = ["attribution (==1.7.1)", "black (==24.3.0)", "build (>=1.2)", "coverage[toml] (==7.6.10)", "flake8 (==7.0.0)", "flake8-bugbear (==24.12.12)", "flit (==3.10.1)", "mypy (==1.14.1)", "ufmt (==2.5.1)", "usort (==1.0.8.post1)"]
+docs = ["sphinx (==8.1.3)", "sphinx-mdinclude (==0.6.1)"]
 
 [[package]]
 name = "annotated-types"
@@ -1043,4 +1043,4 @@ watchmedo = ["PyYAML (>=3.10)"]
 [metadata]
 lock-version = "2.1"
 python-versions = "^3.9.0"
-content-hash = "e6d3ca9bce723c05f4c5ae9dc4bee872f7581b7763680b34112f1d280f5a9b0a"
+content-hash = "21896b8d3d283d95bc3988aa93f06faf5c47dadc2a8822e5a35672b9cb054693"

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"
@@ -11,7 +11,7 @@ packages = [{ include = "langgraph" }]
 [tool.poetry.dependencies]
 python = "^3.9.0"
 langgraph-checkpoint = "^2.0.15"
-aiosqlite = "^0.20.0"
+aiosqlite = ">=0.20,<0.22"
 
 [tool.poetry.group.dev.dependencies]
 ruff = "^0.6.2"

libs/checkpoint/README.md

@@ -1,6 +1,6 @@
 # LangGraph Checkpoint
 
-This library defines the base interface for LangGraph checkpointers. Checkpointers provide persistence layer for LangGraph. They allow you to interact with and manage the graph's state. When you use a graph with a checkpointer, the checkpointer saves a _checkpoint_ of the graph state at every superstep, enabling several powerful capabilities like human-in-the-loop, "memory" between interactions and more.
+This library defines the base interface for LangGraph checkpointers. Checkpointers provide a persistence layer for LangGraph. They allow you to interact with and manage the graph's state. When you use a graph with a checkpointer, the checkpointer saves a _checkpoint_ of the graph state at every superstep, enabling several powerful capabilities like human-in-the-loop, "memory" between interactions and more.
 
 ## Key concepts
 
@@ -12,8 +12,8 @@ Checkpoint is a snapshot of the graph state at a given point in time. Checkpoint
 
 Threads enable the checkpointing of multiple different runs, making them essential for multi-tenant chat applications and other scenarios where maintaining separate states is necessary. A thread is a unique ID assigned to a series of checkpoints saved by a checkpointer. When using a checkpointer, you must specify a `thread_id` and optionally `checkpoint_id` when running the graph.
 
-- `thread_id` is simply the ID of a thread. This is always required
-- `checkpoint_id` can optionally be passed. This identifier refers to a specific checkpoint within a thread. This can be used to kick of a run of a graph from some point halfway through a thread.
+- `thread_id` is simply the ID of a thread. This is always required.
+- `checkpoint_id` can optionally be passed. This identifier refers to a specific checkpoint within a thread. This can be used to kick off a run of a graph from some point halfway through a thread.
 
 You must pass these when invoking the graph as part of the configurable part of the config, e.g.
 

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)

libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py

@@ -487,7 +487,12 @@ def _msgpack_ext_hook(code: int, data: bytes) -> Any:
             except Exception:
                 return cls.construct(**tup[2])
         except Exception:
-            return
+            # for pydantic objects we can't find/reconstruct
+            # let's return the kwargs dict instead
+            try:
+                return tup[2]
+            except NameError:
+                return
     elif code == EXT_PYDANTIC_V2:
         try:
             tup = msgpack.unpackb(
@@ -500,7 +505,12 @@ def _msgpack_ext_hook(code: int, data: bytes) -> Any:
             except Exception:
                 return cls.model_construct(**tup[2])
         except Exception:
-            return
+            # for pydantic objects we can't find/reconstruct
+            # let's return the kwargs dict instead
+            try:
+                return tup[2]
+            except NameError:
+                return
 
 
 def _msgpack_enc(data: Any) -> bytes:

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

@@ -11,9 +11,19 @@ Core types:
 
 from abc import ABC, abstractmethod
 from datetime import datetime
-from typing import Any, Iterable, Literal, NamedTuple, Optional, TypedDict, Union, cast
+from typing import (
+    Any,
+    Iterable,
+    Literal,
+    NamedTuple,
+    Optional,
+    TypedDict,
+    Union,
+    cast,
+)
 
 from langchain_core.embeddings import Embeddings
+from typing_extensions import override
 
 from langgraph.store.base.embed import (
     AEmbeddingsFunc,
@@ -24,6 +34,20 @@ from langgraph.store.base.embed import (
 )
 
 
+class NotProvided:
+    """Sentinel singleton."""
+
+    def __bool__(self) -> Literal[False]:
+        return False
+
+    @override
+    def __repr__(self) -> str:
+        return "NOT_GIVEN"
+
+
+NOT_PROVIDED = NotProvided()
+
+
 class Item:
     """Represents a stored item with metadata.
 
@@ -59,7 +83,7 @@ class Item:
             else created_at
         )
         self.updated_at = (
-            datetime.fromisoformat(cast(str, created_at))
+            datetime.fromisoformat(cast(str, updated_at))
             if isinstance(updated_at, str)
             else updated_at
         )
@@ -166,6 +190,13 @@ class GetOp(NamedTuple):
         "doc456"  # For a document
         ```
     """
+    refresh_ttl: bool = True
+    """Whether to refresh TTLs for the returned item.
+
+    If no TTL was specified for the original item(s),
+    or if TTL support is not enabled for your adapter,
+    this argument is ignored.
+    """
 
 
 class SearchOp(NamedTuple):
@@ -260,6 +291,13 @@ class SearchOp(NamedTuple):
         - "technical documentation about REST APIs"
         - "machine learning papers from 2023"
     """
+    refresh_ttl: bool = True
+    """Whether to refresh TTLs for the returned item.
+
+    If no TTL was specified for the original item(s),
+    or if TTL support is not enabled for your adapter,
+    this argument is ignored.
+    """
 
 
 # Type representing a namespace path that can include wildcards
@@ -463,6 +501,15 @@ class PutOp(NamedTuple):
         ]
         ```
     """
+    ttl: Optional[float] = None
+    """Controls the TTL (time-to-live) for the item in minutes.
+
+    If provided, and if the store you are using supports this feature, the item
+    will expire this many minutes after it was last accessed. The expiration timer
+    refreshes on both read operations (get/search) and write operations (put/update).
+    When the TTL expires, the item will be scheduled for deletion on a best-effort basis.
+    Defaults to None (no expiration).
+    """
 
 
 Op = Union[GetOp, SearchOp, PutOp, ListNamespacesOp]
@@ -473,6 +520,31 @@ class InvalidNamespaceError(ValueError):
     """Provided namespace is invalid."""
 
 
+class TTLConfig(TypedDict, total=False):
+    """Configuration for TTL (time-to-live) behavior in the store."""
+
+    refresh_on_read: bool
+    """Default behavior for refreshing TTLs on read operations (GET and SEARCH).
+    
+    If True, TTLs will be refreshed on read operations (get/search) by default.
+    This can be overridden per-operation by explicitly setting refresh_ttl.
+    Defaults to True if not configured.
+    """
+    default_ttl: Optional[float]
+    """Default TTL (time-to-live) in minutes for new items.
+    
+    If provided, new items will expire after this many minutes after their last access.
+    The expiration timer refreshes on both read and write operations.
+    Defaults to None (no expiration).
+    """
+    sweep_interval_minutes: Optional[int]
+    """Interval in minutes between TTL sweep operations.
+    
+    If provided, the store will periodically delete expired items based on TTL.
+    Defaults to None (no sweeping).
+    """
+
+
 class IndexConfig(TypedDict, total=False):
     """Configuration for indexing documents for semantic search in the store.
 
@@ -612,8 +684,14 @@ class BaseStore(ABC):
         by providing an `index` configuration at creation time. Without this
         configuration, semantic search is disabled and any `index` arguments
         to storage operations will have no effect.
+
+        Similarly, TTL (time-to-live) support is disabled by default.
+        Subclasses must explicitly set `supports_ttl = True` to enable this feature.
     """
 
+    supports_ttl: bool = False
+    ttl_config: Optional[TTLConfig] = None
+
     __slots__ = ("__weakref__",)
 
     @abstractmethod
@@ -640,17 +718,28 @@ class BaseStore(ABC):
             The order of results matches the order of input operations.
         """
 
-    def get(self, namespace: tuple[str, ...], key: str) -> Optional[Item]:
+    def get(
+        self,
+        namespace: tuple[str, ...],
+        key: str,
+        *,
+        refresh_ttl: Optional[bool] = None,
+    ) -> Optional[Item]:
         """Retrieve a single item.
 
         Args:
             namespace: Hierarchical path for the item.
             key: Unique identifier within the namespace.
+            refresh_ttl: Whether to refresh TTLs for the returned item.
+                If None (default), uses the store's default refresh_ttl setting.
+                If no TTL is specified, this argument is ignored.
 
         Returns:
             The retrieved item or None if not found.
         """
-        return self.batch([GetOp(namespace, key)])[0]
+        return self.batch(
+            [GetOp(namespace, str(key), _ensure_refresh(self.ttl_config, refresh_ttl))]
+        )[0]
 
     def search(
         self,
@@ -661,6 +750,7 @@ class BaseStore(ABC):
         filter: Optional[dict[str, Any]] = None,
         limit: int = 10,
         offset: int = 0,
+        refresh_ttl: Optional[bool] = None,
     ) -> list[SearchItem]:
         """Search for items within a namespace prefix.
 
@@ -670,6 +760,8 @@ class BaseStore(ABC):
             filter: Key-value pairs to filter results.
             limit: Maximum number of items to return.
             offset: Number of items to skip before returning results.
+            refresh_ttl: Whether to refresh TTLs for the returned items.
+                If no TTL is specified, this argument is ignored.
 
         Returns:
             List of items matching the search criteria.
@@ -707,7 +799,18 @@ class BaseStore(ABC):
             Note: Natural language search support depends on your store implementation
             and requires proper embedding configuration.
         """
-        return self.batch([SearchOp(namespace_prefix, filter, limit, offset, query)])[0]
+        return self.batch(
+            [
+                SearchOp(
+                    namespace_prefix,
+                    filter,
+                    limit,
+                    offset,
+                    query,
+                    _ensure_refresh(self.ttl_config, refresh_ttl),
+                )
+            ]
+        )[0]
 
     def put(
         self,
@@ -715,6 +818,8 @@ class BaseStore(ABC):
         key: str,
         value: dict[str, Any],
         index: Optional[Union[Literal[False], list[str]]] = None,
+        *,
+        ttl: Union[Optional[float], "NotProvided"] = NOT_PROVIDED,
     ) -> None:
         """Store or update an item in the store.
 
@@ -735,12 +840,20 @@ class BaseStore(ABC):
                     - Nested fields: "metadata.title"
                     - Array access: "chapters[*].content" (each indexed separately)
                     - Specific indices: "authors[0].name"
+            ttl: Time to live in minutes. Support for this argument depends on your store adapter.
+                If specified, the item will expire after this many minutes from when it was last accessed.
+                None means no expiration. Expired runs will be deleted opportunistically.
+                By default, the expiration timer refreshes on both read operations (get/search)
+                and write operations (put/update), whenever the item is included in the operation.
 
         Note:
             Indexing support depends on your store implementation.
             If you do not initialize the store with indexing capabilities,
             the `index` parameter will be ignored.
 
+            Similarly, TTL support depends on the specific store implementation.
+            Some implementations may not support expiration of items.
+
         ???+ example "Examples"
             Store item. Indexing depends on how you configure the store.
             ```python
@@ -759,7 +872,22 @@ class BaseStore(ABC):
             ```
         """
         _validate_namespace(namespace)
-        self.batch([PutOp(namespace, key, value, index=index)])
+        if ttl not in (NOT_PROVIDED, None) and not self.supports_ttl:
+            raise NotImplementedError(
+                f"TTL is not supported by {self.__class__.__name__}. "
+                f"Use a store implementation that supports TTL or set ttl=None."
+            )
+        self.batch(
+            [
+                PutOp(
+                    namespace,
+                    str(key),
+                    value,
+                    index=index,
+                    ttl=_ensure_ttl(self.ttl_config, ttl),
+                )
+            ]
+        )
 
     def delete(self, namespace: tuple[str, ...], key: str) -> None:
         """Delete an item.
@@ -768,7 +896,7 @@ class BaseStore(ABC):
             namespace: Hierarchical path for the item.
             key: Unique identifier within the namespace.
         """
-        self.batch([PutOp(namespace, key, None)])
+        self.batch([PutOp(namespace, str(key), None, ttl=None)])
 
     def list_namespaces(
         self,
@@ -823,7 +951,13 @@ class BaseStore(ABC):
         )
         return self.batch([op])[0]
 
-    async def aget(self, namespace: tuple[str, ...], key: str) -> Optional[Item]:
+    async def aget(
+        self,
+        namespace: tuple[str, ...],
+        key: str,
+        *,
+        refresh_ttl: Optional[bool] = None,
+    ) -> Optional[Item]:
         """Asynchronously retrieve a single item.
 
         Args:
@@ -833,7 +967,17 @@ class BaseStore(ABC):
         Returns:
             The retrieved item or None if not found.
         """
-        return (await self.abatch([GetOp(namespace, key)]))[0]
+        return (
+            await self.abatch(
+                [
+                    GetOp(
+                        namespace,
+                        str(key),
+                        _ensure_refresh(self.ttl_config, refresh_ttl),
+                    )
+                ]
+            )
+        )[0]
 
     async def asearch(
         self,
@@ -844,6 +988,7 @@ class BaseStore(ABC):
         filter: Optional[dict[str, Any]] = None,
         limit: int = 10,
         offset: int = 0,
+        refresh_ttl: Optional[bool] = None,
     ) -> list[SearchItem]:
         """Asynchronously search for items within a namespace prefix.
 
@@ -853,6 +998,9 @@ class BaseStore(ABC):
             filter: Key-value pairs to filter results.
             limit: Maximum number of items to return.
             offset: Number of items to skip before returning results.
+            refresh_ttl: Whether to refresh TTLs for the returned items.
+                If None (default), uses the store's TTLConfig.refresh_default setting.
+                If TTLConfig is not provided or no TTL is specified, this argument is ignored.
 
         Returns:
             List of items matching the search criteria.
@@ -892,7 +1040,16 @@ class BaseStore(ABC):
         """
         return (
             await self.abatch(
-                [SearchOp(namespace_prefix, filter, limit, offset, query)]
+                [
+                    SearchOp(
+                        namespace_prefix,
+                        filter,
+                        limit,
+                        offset,
+                        query,
+                        _ensure_refresh(self.ttl_config, refresh_ttl),
+                    )
+                ]
             )
         )[0]
 
@@ -902,6 +1059,8 @@ class BaseStore(ABC):
         key: str,
         value: dict[str, Any],
         index: Optional[Union[Literal[False], list[str]]] = None,
+        *,
+        ttl: Union[Optional[float], "NotProvided"] = NOT_PROVIDED,
     ) -> None:
         """Asynchronously store or update an item in the store.
 
@@ -922,12 +1081,20 @@ class BaseStore(ABC):
                     - Nested fields: "metadata.title"
                     - Array access: "chapters[*].content" (each indexed separately)
                     - Specific indices: "authors[0].name"
+            ttl: Time to live in minutes. Support for this argument depends on your store adapter.
+                If specified, the item will expire after this many minutes from when it was last accessed.
+                None means no expiration. Expired runs will be deleted opportunistically.
+                By default, the expiration timer refreshes on both read operations (get/search)
+                and write operations (put/update), whenever the item is included in the operation.
 
         Note:
             Indexing support depends on your store implementation.
             If you do not initialize the store with indexing capabilities,
             the `index` parameter will be ignored.
 
+            Similarly, TTL support depends on the specific store implementation.
+            Some implementations may not support expiration of items.
+
         ???+ example "Examples"
             Store item. Indexing depends on how you configure the store.
             ```python
@@ -954,7 +1121,22 @@ class BaseStore(ABC):
             ```
         """
         _validate_namespace(namespace)
-        await self.abatch([PutOp(namespace, key, value, index=index)])
+        if ttl not in (NOT_PROVIDED, None) and not self.supports_ttl:
+            raise NotImplementedError(
+                f"TTL is not supported by {self.__class__.__name__}. "
+                f"Use a store implementation that supports TTL or set ttl=None."
+            )
+        await self.abatch(
+            [
+                PutOp(
+                    namespace,
+                    str(key),
+                    value,
+                    index=index,
+                    ttl=_ensure_ttl(self.ttl_config, ttl),
+                )
+            ]
+        )
 
     async def adelete(self, namespace: tuple[str, ...], key: str) -> None:
         """Asynchronously delete an item.
@@ -963,7 +1145,7 @@ class BaseStore(ABC):
             namespace: Hierarchical path for the item.
             key: Unique identifier within the namespace.
         """
-        await self.abatch([PutOp(namespace, key, None)])
+        await self.abatch([PutOp(namespace, str(key), None)])
 
     async def alist_namespaces(
         self,
@@ -1043,6 +1225,27 @@ def _validate_namespace(namespace: tuple[str, ...]) -> None:
         )
 
 
+def _ensure_refresh(
+    ttl_config: Optional[TTLConfig], refresh_ttl: Optional[bool] = None
+) -> bool:
+    if refresh_ttl is not None:
+        return refresh_ttl
+    if ttl_config is not None:
+        return ttl_config.get("refresh_on_read", True)
+    return True
+
+
+def _ensure_ttl(
+    ttl_config: Optional[TTLConfig],
+    ttl: Union[Optional[float], "NotProvided"] = NOT_PROVIDED,
+) -> Optional[float]:
+    if ttl is NOT_PROVIDED:
+        if ttl_config:
+            return ttl_config.get("default_ttl")
+        return None
+    return ttl
+
+
 __all__ = [
     "BaseStore",
     "Item",

libs/checkpoint/langgraph/store/base/batch.py

@@ -5,17 +5,21 @@ from collections.abc import Iterable
 from typing import Any, Callable, Literal, Optional, TypeVar, Union
 
 from langgraph.store.base import (
+    NOT_PROVIDED,
     BaseStore,
     GetOp,
     Item,
     ListNamespacesOp,
     MatchCondition,
     NamespacePath,
+    NotProvided,
     Op,
     PutOp,
     Result,
     SearchItem,
     SearchOp,
+    _ensure_refresh,
+    _ensure_ttl,
     _validate_namespace,
 )
 
@@ -68,10 +72,21 @@ class AsyncBatchedBaseStore(BaseStore):
         self,
         namespace: tuple[str, ...],
         key: str,
+        *,
+        refresh_ttl: Optional[bool] = None,
     ) -> Optional[Item]:
         assert not self._task.done()
         fut = self._loop.create_future()
-        self._aqueue.put_nowait((fut, GetOp(namespace, key)))
+        self._aqueue.put_nowait(
+            (
+                fut,
+                GetOp(
+                    namespace,
+                    key,
+                    refresh_ttl=_ensure_refresh(self.ttl_config, refresh_ttl),
+                ),
+            )
+        )
         return await fut
 
     async def asearch(
@@ -83,11 +98,22 @@ class AsyncBatchedBaseStore(BaseStore):
         filter: Optional[dict[str, Any]] = None,
         limit: int = 10,
         offset: int = 0,
+        refresh_ttl: Optional[bool] = None,
     ) -> list[SearchItem]:
         assert not self._task.done()
         fut = self._loop.create_future()
         self._aqueue.put_nowait(
-            (fut, SearchOp(namespace_prefix, filter, limit, offset, query))
+            (
+                fut,
+                SearchOp(
+                    namespace_prefix,
+                    filter,
+                    limit,
+                    offset,
+                    query,
+                    refresh_ttl=_ensure_refresh(self.ttl_config, refresh_ttl),
+                ),
+            )
         )
         return await fut
 
@@ -97,11 +123,20 @@ class AsyncBatchedBaseStore(BaseStore):
         key: str,
         value: dict[str, Any],
         index: Optional[Union[Literal[False], list[str]]] = None,
+        *,
+        ttl: Union[Optional[float], "NotProvided"] = NOT_PROVIDED,
     ) -> None:
         assert not self._task.done()
         _validate_namespace(namespace)
         fut = self._loop.create_future()
-        self._aqueue.put_nowait((fut, PutOp(namespace, key, value, index)))
+        self._aqueue.put_nowait(
+            (
+                fut,
+                PutOp(
+                    namespace, key, value, index, ttl=_ensure_ttl(self.ttl_config, ttl)
+                ),
+            )
+        )
         return await fut
 
     async def adelete(
@@ -149,9 +184,11 @@ class AsyncBatchedBaseStore(BaseStore):
         self,
         namespace: tuple[str, ...],
         key: str,
+        *,
+        refresh_ttl: Optional[bool] = None,
     ) -> Optional[Item]:
         return asyncio.run_coroutine_threadsafe(
-            self.aget(namespace, key=key), self._loop
+            self.aget(namespace, key=key, refresh_ttl=refresh_ttl), self._loop
         ).result()
 
     @_check_loop
@@ -164,10 +201,16 @@ class AsyncBatchedBaseStore(BaseStore):
         filter: Optional[dict[str, Any]] = None,
         limit: int = 10,
         offset: int = 0,
+        refresh_ttl: Optional[bool] = None,
     ) -> list[SearchItem]:
         return asyncio.run_coroutine_threadsafe(
             self.asearch(
-                namespace_prefix, query=query, filter=filter, limit=limit, offset=offset
+                namespace_prefix,
+                query=query,
+                filter=filter,
+                limit=limit,
+                offset=offset,
+                refresh_ttl=refresh_ttl,
             ),
             self._loop,
         ).result()
@@ -179,10 +222,19 @@ class AsyncBatchedBaseStore(BaseStore):
         key: str,
         value: dict[str, Any],
         index: Optional[Union[Literal[False], list[str]]] = None,
+        *,
+        ttl: Union[Optional[float], "NotProvided"] = NOT_PROVIDED,
     ) -> None:
         _validate_namespace(namespace)
         asyncio.run_coroutine_threadsafe(
-            self.aput(namespace, key=key, value=value, index=index), self._loop
+            self.aput(
+                namespace,
+                key=key,
+                value=value,
+                index=index,
+                ttl=_ensure_ttl(self.ttl_config, ttl),
+            ),
+            self._loop,
         ).result()
 
     @_check_loop

libs/checkpoint/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langgraph-checkpoint"
-version = "2.0.16"
+version = "2.0.21"
 description = "Library with base interfaces for LangGraph checkpoint savers."
 authors = []
 license = "MIT"

libs/checkpoint/tests/test_jsonplus.py

@@ -130,7 +130,7 @@ def test_serde_jsonplus() -> None:
             key="my-key",
             namespace=("a", "name", " "),
             created_at=datetime(2024, 9, 24, 17, 29, 10, 128397),
-            updated_at=datetime(2024, 9, 24, 17, 29, 10, 128397),
+            updated_at=datetime(2024, 9, 24, 17, 29, 11, 128397),
         ),
     }
 

libs/checkpoint/tests/test_memory.py

@@ -68,7 +68,9 @@ class TestMemorySaver:
             },
             "metadata": {"run_id": "my_run_id"},
         }
-        self.memory_saver.put(config, self.chkpnt_2, self.metadata_2, {})
+        self.memory_saver.put(
+            config, self.chkpnt_2, self.metadata_2, self.chkpnt_2["channel_versions"]
+        )
         checkpoint = self.memory_saver.get_tuple(config)
         assert checkpoint is not None
         assert checkpoint.metadata == {
@@ -80,9 +82,24 @@ class TestMemorySaver:
     async def test_search(self) -> None:
         # set up test
         # save checkpoints
-        self.memory_saver.put(self.config_1, self.chkpnt_1, self.metadata_1, {})
-        self.memory_saver.put(self.config_2, self.chkpnt_2, self.metadata_2, {})
-        self.memory_saver.put(self.config_3, self.chkpnt_3, self.metadata_3, {})
+        self.memory_saver.put(
+            self.config_1,
+            self.chkpnt_1,
+            self.metadata_1,
+            self.chkpnt_1["channel_versions"],
+        )
+        self.memory_saver.put(
+            self.config_2,
+            self.chkpnt_2,
+            self.metadata_2,
+            self.chkpnt_2["channel_versions"],
+        )
+        self.memory_saver.put(
+            self.config_3,
+            self.chkpnt_3,
+            self.metadata_3,
+            self.chkpnt_3["channel_versions"],
+        )
 
         # call method / assertions
         query_1 = {"source": "input"}  # search by 1 key
@@ -129,9 +146,24 @@ class TestMemorySaver:
     async def test_asearch(self) -> None:
         # set up test
         # save checkpoints
-        self.memory_saver.put(self.config_1, self.chkpnt_1, self.metadata_1, {})
-        self.memory_saver.put(self.config_2, self.chkpnt_2, self.metadata_2, {})
-        self.memory_saver.put(self.config_3, self.chkpnt_3, self.metadata_3, {})
+        self.memory_saver.put(
+            self.config_1,
+            self.chkpnt_1,
+            self.metadata_1,
+            self.chkpnt_1["channel_versions"],
+        )
+        self.memory_saver.put(
+            self.config_2,
+            self.chkpnt_2,
+            self.metadata_2,
+            self.chkpnt_2["channel_versions"],
+        )
+        self.memory_saver.put(
+            self.config_3,
+            self.chkpnt_3,
+            self.metadata_3,
+            self.chkpnt_3["channel_versions"],
+        )
 
         # call method / assertions
         query_1 = {"source": "input"}  # search by 1 key

libs/checkpoint/tests/test_store.py

@@ -148,8 +148,8 @@ async def test_async_batch_store(mocker: MockerFixture) -> None:
     assert abatch.call_count == 1
     assert [tuple(c.args[0]) for c in abatch.call_args_list] == [
         (
-            GetOp(("a",), "b"),
-            GetOp(("c",), "d"),
+            GetOp(("a",), "b", refresh_ttl=True),
+            GetOp(("c",), "d", refresh_ttl=True),
         ),
     ]
 
@@ -467,8 +467,8 @@ async def test_async_batch_store_deduplication(mocker: MockerFixture) -> None:
     assert len(abatch.call_args_list) == 1
     ops = list(abatch.call_args_list[0].args[1])
     assert len(ops) == 2
-    assert GetOp(("test",), "same") in ops
-    assert GetOp(("test",), "different") in ops
+    assert GetOp(("test",), "same", refresh_ttl=True) in ops
+    assert GetOp(("test",), "different", refresh_ttl=True) in ops
 
     abatch.reset_mock()
 

libs/cli/Makefile

@@ -1,4 +1,4 @@
-.PHONY: test lint format test-integration
+.PHONY: test lint format test-integration update-schema
 
 ######################
 # TESTING AND COVERAGE
@@ -31,3 +31,6 @@ lint lint_diff lint_package lint_tests:
 format format_diff:
 	poetry run ruff format $(PYTHON_FILES)
 	poetry run ruff check --select I --fix $(PYTHON_FILES)
+
+update-schema:
+	poetry run python generate_schema.py

libs/cli/README.md

@@ -79,7 +79,7 @@ The CLI uses a `langgraph.json` configuration file with these key settings:
 }
 ```
 
-See the [full documentation](https://langchain-ai.github.io/langgraph/docs/cloud/reference/cli.html) for detailed configuration options.
+See the [full documentation](https://langchain-ai.github.io/langgraph/cloud/reference/cli/) for detailed configuration options.
 
 ## Development
 

libs/cli/generate_schema.py

@@ -0,0 +1,226 @@
+#!/usr/bin/env python3
+"""
+Script to generate a JSON schema for the langgraph-cli Config class.
+
+This script creates a schema.json file that can be referenced in langgraph.json files
+to provide IDE autocompletion and validation.
+"""
+
+import inspect
+import json
+import textwrap
+from pathlib import Path
+
+import msgspec
+
+from langgraph_cli.config import (
+    AuthConfig,
+    Config,
+    CorsConfig,
+    HttpConfig,
+    IndexConfig,
+    SecurityConfig,
+    StoreConfig,
+)
+
+
+def add_descriptions_to_schema(schema, cls):
+    """Add docstring descriptions to the schema properties."""
+    if schema.get("description"):
+        schema["description"] = inspect.cleandoc(schema["description"])
+    elif class_doc := inspect.getdoc(cls):
+        schema["description"] = inspect.cleandoc(class_doc)
+    # Get attribute docstrings from the class
+    attr_docs = {}
+
+    # Also check class annotations for docstrings
+    source_lines = inspect.getsourcelines(cls)[0]
+    current_attr = None
+    docstring_lines = []
+
+    for line in source_lines:
+        line = line.strip()
+
+        # Check for attribute definition (TypedDict style)
+        if ":" in line and not line.startswith("#") and not line.startswith('"""'):
+            parts = line.split(":", 1)
+            if len(parts) == 2 and parts[0].strip().isidentifier():
+                # If we were collecting a docstring, save it for the previous attribute
+                if current_attr and docstring_lines:
+                    attr_docs[current_attr] = "\n".join(docstring_lines).strip('"')
+                    docstring_lines = []
+
+                current_attr = parts[0].strip()
+
+        # Check for docstring after attribute
+        elif line.startswith('"""') and current_attr:
+            # Start or end of a docstring
+            if len(line) > 3 and line.endswith('"""'):
+                # Single line docstring
+                attr_docs[current_attr] = line.strip('"')
+                current_attr = None
+            elif docstring_lines:
+                # End of multi-line docstring
+                docstring_lines.append(line.rstrip('"'))
+                attr_docs[current_attr] = "\n".join(docstring_lines).strip('"')
+                docstring_lines = []
+                current_attr = None
+            else:
+                # Start of multi-line docstring
+                docstring_lines.append(line.lstrip('"'))
+
+        # Continue multi-line docstring
+        elif docstring_lines and current_attr:
+            docstring_lines.append(line.strip('"'))
+
+    # Add the last docstring if there is one
+    if current_attr and docstring_lines:
+        attr_docs[current_attr] = "\n".join(docstring_lines).strip('"')
+
+    # Add descriptions to properties
+    if "properties" in schema:
+        for prop_name, prop_schema in schema["properties"].items():
+            # First try to get from attribute docstrings
+            if prop_name in attr_docs and "description" not in prop_schema:
+                prop_schema["description"] = textwrap.dedent(attr_docs[prop_name])
+            # Fall back to class docstring parsing
+            elif class_doc:
+                for line in class_doc.split("\n"):
+                    if line.strip().startswith(
+                        f"{prop_name}:"
+                    ) or line.strip().startswith(f'"{prop_name}"'):
+                        description = line.split(":", 1)[1].strip()
+                        if description and "description" not in prop_schema:
+                            prop_schema["description"] = description
+                            break
+
+    # Recursively process nested definitions
+    if "$defs" in schema:
+        for def_name, def_schema in schema["$defs"].items():
+            # Find the class that corresponds to this definition
+            for potential_cls in [
+                Config,
+                StoreConfig,
+                IndexConfig,
+                AuthConfig,
+                SecurityConfig,
+                HttpConfig,
+                CorsConfig,
+            ]:
+                if potential_cls.__name__ == def_name:
+                    add_descriptions_to_schema(def_schema, potential_cls)
+                    break
+
+    return schema
+
+
+def generate_schema():
+    """Generate a JSON schema for the Config class using msgspec."""
+    # Generate the basic schema
+    schema = msgspec.json.schema(Config)
+
+    # Add title and description
+    schema["title"] = "LangGraph CLI Configuration"
+    schema["description"] = "Configuration schema for langgraph-cli"
+
+    # Add docstring descriptions
+    schema = add_descriptions_to_schema(schema, Config)
+
+    # Add constraint that only one of python_version or node_version should be specified
+    config_schema = schema["$defs"]["Config"]
+
+    # Create two subschemas: one with python_version and one with node_version
+    # Define properties specific to Python projects
+    python_specific_props = ["python_version", "pip_config_file"]
+    # Define properties specific to Node.js projects
+    node_specific_props = ["node_version"]
+    # Define properties common to both project types
+    common_props = [
+        k
+        for k in config_schema["properties"]
+        if k not in python_specific_props and k not in node_specific_props
+    ]
+
+    # Create Python schema with python_version and pip_config_file
+    python_schema = {
+        "type": "object",
+        "properties": {
+            # Include Python-specific properties
+            **{k: config_schema["properties"][k].copy() for k in python_specific_props},
+            # Include common properties
+            **{k: config_schema["properties"][k].copy() for k in common_props},
+        },
+        "required": ["dependencies", "graphs"],
+    }
+
+    # Add enum constraint for python_version
+    if "python_version" in python_schema["properties"]:
+        python_schema["properties"]["python_version"]["enum"] = ["3.11", "3.12"]
+
+    # Create Node.js schema with node_version
+    node_schema = {
+        "type": "object",
+        "properties": {
+            # Include Node-specific properties
+            **{k: config_schema["properties"][k].copy() for k in node_specific_props},
+            # Include common properties
+            **{k: config_schema["properties"][k].copy() for k in common_props},
+        },
+        "required": ["node_version", "graphs"],
+    }
+
+    # Add enum constraint for node_version
+    if "node_version" in node_schema["properties"]:
+        node_schema["properties"]["node_version"]["anyOf"] = [
+            {"type": "string", "enum": ["20"]},
+            {"type": "null"},
+        ]
+
+    # Replace the Config schema with a oneOf constraint
+    config_schema["oneOf"] = [python_schema, node_schema]
+
+    # Remove the properties field as it's now defined in the oneOf subschemas
+    if "properties" in config_schema:
+        del config_schema["properties"]
+
+    return schema
+
+
+def main():
+    """Generate the schema and write it to a file."""
+    schema = generate_schema()
+
+    # Add versioning to the schema
+    import importlib.metadata
+
+    try:
+        version = importlib.metadata.version("langgraph_cli").split(".")
+        schema_version = f"v{version[0]}"
+    except importlib.metadata.PackageNotFoundError:
+        schema_version = "v1"
+
+    # Add version to schema
+    schema["version"] = schema_version
+
+    config_dir = Path(__file__).parent / "schemas"
+
+    # Create versioned schema file
+    versioned_path = config_dir / f"schema.{schema_version}.json"
+    with open(versioned_path, "w") as f:
+        json.dump(schema, f, indent=2)
+
+    # Also create a latest version
+    latest_path = config_dir / "schema.json"
+    with open(latest_path, "w") as f:
+        json.dump(schema, f, indent=2)
+
+    print(f"Schema written to {versioned_path} and {latest_path}")
+    print(
+        f"You can now add '$schema: https://raw.githubusercontent.com/langchain-ai/langgraph/refs/heads/main/libs/cli/schemas/schema.json'"
+        f" or '$schema: https://raw.githubusercontent.com/langchain-ai/langgraph/refs/heads/main/libs/cli/schemas/schema.{schema_version}.json'"
+        " to your langgraph.json files"
+    )
+
+
+if __name__ == "__main__":
+    main()

libs/cli/langgraph_cli/cli.py

@@ -574,6 +574,12 @@ def dockerfile(save_path: str, config: pathlib.Path, add_docker_compose: bool) -
     help="Wait for a debugger client to connect to the debug port before starting the server",
     default=False,
 )
+@click.option(
+    "--studio_url",
+    type=str,
+    default=None,
+    help="URL of the LangGraph Studio instance to connect to. Defaults to https://smith.langchain.com",
+)
 @cli.command(
     "dev",
     help="🏃‍♀️‍➡️ Run LangGraph API server in development mode with hot reloading and debugging support",
@@ -588,6 +594,7 @@ def dev(
     no_browser: bool,
     debug_port: Optional[int],
     wait_for_client: bool,
+    studio_url: Optional[str],
 ):
     """CLI entrypoint for running the LangGraph API server."""
     try:
@@ -651,6 +658,7 @@ def dev(
         wait_for_client=wait_for_client,
         auth=config_json.get("auth"),
         http=config_json.get("http"),
+        studio_url=studio_url,
     )
 
 

libs/cli/langgraph_cli/config.py

@@ -3,7 +3,7 @@ import os
 import pathlib
 import textwrap
 from collections import Counter
-from typing import NamedTuple, Optional, TypedDict, Union
+from typing import Any, NamedTuple, Optional, TypedDict, Union
 
 import click
 
@@ -11,13 +11,43 @@ MIN_NODE_VERSION = "20"
 MIN_PYTHON_VERSION = "3.11"
 
 
+class TTLConfig(TypedDict, total=False):
+    """Configuration for TTL (time-to-live) behavior in the store."""
+
+    refresh_on_read: bool
+    """Default behavior for refreshing TTLs on read operations (GET and SEARCH).
+    
+    If True, TTLs will be refreshed on read operations (get/search) by default.
+    This can be overridden per-operation by explicitly setting refresh_ttl.
+    Defaults to True if not configured.
+    """
+    default_ttl: Optional[float]
+    """Optional. Default TTL (time-to-live) in minutes for new items.
+    
+    If provided, all new items will have this TTL unless explicitly overridden.
+    If omitted, items will have no TTL by default.
+    """
+    sweep_interval_minutes: Optional[int]
+    """Optional. Interval in minutes between TTL sweep iterations.
+    
+    If provided, the store will periodically delete expired items based on the TTL.
+    If omitted, no automatic sweeping will occur.
+    """
+
+
 class IndexConfig(TypedDict, total=False):
-    """Configuration for indexing documents for semantic search in the store."""
+    """Configuration for indexing documents for semantic search in the store.
+
+    This governs how text is converted into embeddings and stored for vector-based lookups.
+    """
 
     dims: int
-    """Number of dimensions in the embedding vectors.
+    """Required. Dimensionality of the embedding vectors you will store.
     
-    Common embedding models have the following dimensions:
+    Must match the output dimension of your selected embedding model or custom embed function.
+    If mismatched, you will likely encounter shape/size errors when inserting or querying vectors.
+    
+    Common embedding model output dimensions:
         - openai:text-embedding-3-large: 3072
         - openai:text-embedding-3-small: 1536
         - openai:text-embedding-ada-002: 1536
@@ -28,42 +58,130 @@ class IndexConfig(TypedDict, total=False):
     """
 
     embed: str
-    """Optional model (string) to generate embeddings from text or path to model or function.
+    """Required. Identifier or reference to the embedding model or a custom embedding function.
     
-    Examples:
+    The format can vary:
+      - "<provider>:<model_name>" for recognized providers (e.g., "openai:text-embedding-3-large")
+      - "path/to/module.py:function_name" for your own local embedding function
+      - "my_custom_embed" if it's a known alias in your system
+
+     Examples:
         - "openai:text-embedding-3-large"
         - "cohere:embed-multilingual-v3.0"
-        - "src/app.py:embeddings
+        - "src/app.py:embeddings"
+    
+    Note: Must return embeddings of dimension `dims`.
     """
 
     fields: Optional[list[str]]
-    """Fields to extract text from for embedding generation.
+    """Optional. List of JSON fields to extract before generating embeddings.
     
-    Defaults to the root ["$"], which embeds the json object as a whole.
+    Defaults to ["$"], which means the entire JSON object is embedded as one piece of text.
+    If you provide multiple fields (e.g. ["title", "content"]), each is extracted and embedded separately,
+    often saving token usage if you only care about certain parts of the data.
+    
+    Example:
+        fields=["title", "abstract", "author.biography"]
     """
 
 
 class StoreConfig(TypedDict, total=False):
-    embed: Optional[IndexConfig]
-    """Configuration for vector embeddings in store."""
+    """Configuration for the built-in long-term memory store.
+
+    This store can optionally perform semantic search. If you omit `index`,
+    the store will just handle traditional (non-embedded) data without vector lookups.
+    """
+
+    index: Optional[IndexConfig]
+    """Optional. Defines the vector-based semantic search configuration.
+    
+    If provided, the store will:
+      - Generate embeddings according to `index.embed`
+      - Enforce the embedding dimension given by `index.dims`
+      - Embed only specified JSON fields (if any) from `index.fields`
+    
+    If omitted, no vector index is initialized.
+    """
+
+    ttl: Optional[TTLConfig]
+    """Optional. Defines the TTL (time-to-live) behavior configuration.
+    
+    If provided, the store will apply TTL settings according to the configuration.
+    If omitted, no TTL behavior is configured.
+    """
 
 
 class SecurityConfig(TypedDict, total=False):
-    securitySchemes: dict
-    security: list
+    """Configuration for OpenAPI security definitions and requirements.
+
+    Useful for specifying global or path-level authentication and authorization flows
+    (e.g., OAuth2, API key headers, etc.).
+    """
+
+    securitySchemes: dict[str, dict[str, Any]]
+    """Required. Dict describing each security scheme recognized by your OpenAPI spec.
+    
+    Keys are scheme names (e.g. "OAuth2", "ApiKeyAuth") and values are their definitions.
+    Example:
+        {
+            "OAuth2": {
+                "type": "oauth2",
+                "flows": {
+                    "password": {
+                        "tokenUrl": "/token",
+                        "scopes": {"read": "Read data", "write": "Write data"}
+                    }
+                }
+            }
+        }
+    """
+    security: list[dict[str, list[str]]]
+    """Optional. Global security requirements across all endpoints.
+    
+    Each element in the list maps a security scheme (e.g. "OAuth2") to a list of scopes (e.g. ["read", "write"]).
+    Example:
+        [
+            {"OAuth2": ["read", "write"]},
+            {"ApiKeyAuth": []}
+        ]
+    """
     # path => {method => security}
-    paths: dict[str, dict[str, list]]
+    paths: dict[str, dict[str, list[dict[str, list[str]]]]]
+    """Optional. Path-specific security overrides.
+    
+    Keys are path templates (e.g., "/items/{item_id}"), mapping to:
+      - Keys that are HTTP methods (e.g., "GET", "POST"),
+      - Values are lists of security definitions (just like `security`) for that method.
+    
+    Example:
+        {
+            "/private_data": {
+                "GET": [{"OAuth2": ["read"]}],
+                "POST": [{"OAuth2": ["write"]}]
+            }
+        }
+    """
 
 
 class AuthConfig(TypedDict, total=False):
-    path: str
-    """Path to the authentication function in a Python file."""
-    disable_studio_auth: bool
-    """Whether to disable auth when connecting from the LangSmith Studio."""
-    openapi: SecurityConfig
-    """The schema to use for updating the openapi spec.
+    """Configuration for custom authentication logic and how it integrates into the OpenAPI spec."""
 
-    Example:
+    path: str
+    """Required. Path to an instance of the Auth() class that implements custom authentication.
+    
+    Format: "path/to/file.py:my_auth"
+    """
+    disable_studio_auth: bool
+    """Optional. Whether to disable LangSmith API-key authentication for requests originating the Studio. 
+    
+    Defaults to False, meaning that if a particular header is set, the server will verify the `x-api-key` header
+    value is a valid API key for the deployment's workspace. If True, all requests will go through your custom
+    authentication logic, regardless of origin of the request.
+    """
+    openapi: SecurityConfig
+    """Required. Detailed security configuration that merges into your deployment's OpenAPI spec.
+    
+    Example (OAuth2):
         {
             "securitySchemes": {
                 "OAuth2": {
@@ -71,88 +189,185 @@ class AuthConfig(TypedDict, total=False):
                     "flows": {
                         "password": {
                             "tokenUrl": "/token",
-                            "scopes": {
-                                "me": "Read information about the current user",
-                                "items": "Access to create and manage items"
-                            }
+                            "scopes": {"me": "Read user info", "items": "Manage items"}
                         }
                     }
                 }
             },
             "security": [
-                {"OAuth2": ["me"]}  # Default security requirement for all endpoints
+                {"OAuth2": ["me"]}
             ]
         }
     """
 
 
 class CorsConfig(TypedDict, total=False):
+    """Specifies Cross-Origin Resource Sharing (CORS) rules for your server.
+
+    If omitted, defaults are typically very restrictive (often no cross-origin requests).
+    Configure carefully if you want to allow usage from browsers hosted on other domains.
+    """
+
     allow_origins: list[str]
+    """Optional. List of allowed origins (e.g., "https://example.com").
+    
+    Default is often an empty list (no external origins). 
+    Use "*" only if you trust all origins, as that bypasses most restrictions.
+    """
     allow_methods: list[str]
+    """Optional. HTTP methods permitted for cross-origin requests (e.g. ["GET", "POST"]).
+    
+    Default might be ["GET", "POST", "OPTIONS"] depending on your server framework.
+    """
     allow_headers: list[str]
+    """Optional. HTTP headers that can be used in cross-origin requests (e.g. ["Content-Type", "Authorization"])."""
     allow_credentials: bool
+    """Optional. If True, cross-origin requests can include credentials (cookies, auth headers).
+    
+    Default False to avoid accidentally exposing secured endpoints to untrusted sites.
+    """
     allow_origin_regex: str
+    """Optional. A regex pattern for matching allowed origins, used if you have dynamic subdomains.
+    
+    Example: "^https://.*\.mycompany\.com$"
+    """
     expose_headers: list[str]
+    """Optional. List of headers that browsers are allowed to read from the response in cross-origin contexts."""
     max_age: int
+    """Optional. How many seconds the browser may cache preflight responses.
+    
+    Default might be 600 (10 minutes). Larger values reduce preflight requests but can cause stale configurations.
+    """
 
 
 class HttpConfig(TypedDict, total=False):
+    """Configuration for the built-in HTTP server that powers your deployment's routes and endpoints."""
+
     app: str
-    """Import path for a custom Starlette/FastAPI app to mount"""
+    """Optional. Import path to a custom Starlette/FastAPI application to mount.
+    
+    Format: "path/to/module.py:app_var"
+    If provided, it can override or extend the default routes.
+    """
     disable_assistants: bool
-    """Disable /assistants routes"""
+    """Optional. If True, /assistants routes are removed from the server.
+    
+    Default is False (meaning /assistants is enabled).
+    """
     disable_threads: bool
-    """Disable /threads routes"""
+    """Optional. If True, /threads routes are removed.
+    
+    Default is False.
+    """
     disable_runs: bool
-    """Disable /runs routes"""
+    """Optional. If True, /runs routes are removed.
+    
+    Default is False.
+    """
     disable_store: bool
-    """Disable /store routes"""
+    """Optional. If True, /store routes are removed, disabling direct store interactions via HTTP.
+    
+    Default is False.
+    """
     disable_meta: bool
-    """Disable /ok, /info, /metrics, and /docs routes"""
+    """Optional. If True, all meta endpoints (/ok, /info, /metrics, /docs) are disabled.
+    
+    Default is False.
+    """
     cors: Optional[CorsConfig]
-    """Cross-Origin Resource Sharing (CORS) configuration"""
+    """Optional. Defines CORS restrictions. If omitted, no special rules are set and 
+    cross-origin behavior depends on default server settings.
+    """
 
 
 class Config(TypedDict, total=False):
-    """Configuration for langgraph-cli."""
+    """Top-level config for langgraph-cli or similar deployment tooling."""
 
     python_version: str
-    """Python version to use."""
+    """Optional. Python version in 'major.minor' format (e.g. '3.11'). 
+    Must be at least 3.11 or greater for this deployment to function properly.
+    """
 
     node_version: Optional[str]
-    """Node.js version to use."""
+    """Optional. Node.js version as a major version (e.g. '20'), if your deployment needs Node.
+    Must be >= 20 if provided.
+    """
 
     pip_config_file: Optional[str]
-    """Path to a pip configuration file."""
+    """Optional. Path to a pip config file (e.g., "/etc/pip.conf" or "pip.ini") for controlling
+    package installation (custom indices, credentials, etc.).
+    
+    Only relevant if Python dependencies are installed via pip. If omitted, default pip settings are used.
+    """
 
     dockerfile_lines: list[str]
-    """Additional lines to add to the Dockerfile."""
+    """Optional. Additional Docker instructions that will be appended to your base Dockerfile.
+    
+    Useful for installing OS packages, setting environment variables, etc. 
+    Example:
+        dockerfile_lines=[
+            "RUN apt-get update && apt-get install -y libmagic-dev",
+            "ENV MY_CUSTOM_VAR=hello_world"
+        ]
+    """
 
     dependencies: list[str]
-    """Additional Python dependencies to install."""
+    """List of Python dependencies to install, either from PyPI or local paths.
+    
+    Examples:
+      - "." or "./src" if you have a local Python package
+      - str (aka "anthropic") for a PyPI package
+      - "git+https://github.com/org/repo.git@main" for a Git-based package
+    Defaults to an empty list, meaning no additional packages installed beyond your base environment.
+    """
 
     graphs: dict[str, str]
-    """Mapping of graph names to their definitions."""
+    """Optional. Named definitions of graphs, each pointing to a Python object.
+
+    
+    Graphs can be StateGraph, @entrypoint, or any other Pregel object OR they can point to (async) context
+    managers that accept a single configuration argument (of type RunnableConfig) and return a pregel object
+    (instance of Stategraph, etc.).
+    
+    Keys are graph names, values are "path/to/file.py:object_name".
+    Example:
+        {
+            "mygraph": "graphs/my_graph.py:graph_definition",
+            "anothergraph": "graphs/another.py:get_graph"
+        }
+    """
 
     env: Union[dict[str, str], str]
-    """Environment variables to set.
-
-    If a dictionary is provided, the keys are environment variable names
-    and the values are the corresponding environment variable values.
-
-    If a string is provided, it is interpreted as a path to a file containing
-    environment variables in the format KEY=VALUE, with one environment variable
-    per line.
+    """Optional. Environment variables to set for your deployment.
+    
+    - If given as a dict, keys are variable names and values are their values.
+    - If given as a string, it must be a path to a file containing lines in KEY=VALUE format.
+    
+    Example as a dict:
+        env={"API_TOKEN": "abc123", "DEBUG": "true"}
+    Example as a file path:
+        env=".env"
     """
 
     store: Optional[StoreConfig]
-    """Configuration for vector embeddings in store."""
+    """Optional. Configuration for the built-in long-term memory store, including semantic search indexing.
+    
+    If omitted, no vector index is set up (the object store will still be present, however).
+    """
 
     auth: Optional[AuthConfig]
-    """Configuration for authentication."""
+    """Optional. Custom authentication config, including the path to your Python auth logic and 
+    the OpenAPI security definitions it uses.
+    """
 
     http: Optional[HttpConfig]
-    """Configuration for HTTP server."""
+    """Optional. Configuration for the built-in HTTP server, controlling which custom routes are exposed
+    and how cross-origin requests are handled.
+    """
+
+    ui: Optional[dict[str, str]]
+    """Optional. Named definitions of UI components emitted by the agent, each pointing to a JS/TS file.
+    """
 
 
 def _parse_version(version_str: str) -> tuple[int, int]:
@@ -189,6 +404,7 @@ def validate_config(config: Config) -> Config:
             "store": config.get("store"),
             "auth": config.get("auth"),
             "http": config.get("http"),
+            "ui": config.get("ui"),
         }
         if config.get("node_version")
         else {
@@ -201,6 +417,7 @@ def validate_config(config: Config) -> Config:
             "store": config.get("store"),
             "auth": config.get("auth"),
             "http": config.get("http"),
+            "ui": config.get("ui"),
         }
     )
 
@@ -687,9 +904,11 @@ def python_config_to_docker(
     pip_pkgs_str = f"RUN {pip_install} {' '.join(pypi_deps)}" if pypi_deps else ""
     if local_deps.pip_reqs:
         pip_reqs_str = os.linesep.join(
-            f"COPY --from=__outer_{reqpath.name} requirements.txt {destpath}"
-            if reqpath.parent in local_deps.additional_contexts
-            else f"ADD {reqpath.relative_to(config_path.parent)} {destpath}"
+            (
+                f"COPY --from=__outer_{reqpath.name} requirements.txt {destpath}"
+                if reqpath.parent in local_deps.additional_contexts
+                else f"ADD {reqpath.relative_to(config_path.parent)} {destpath}"
+            )
             for reqpath, destpath in local_deps.pip_reqs
         )
         pip_reqs_str += f'{os.linesep}RUN {pip_install} {" ".join("-r " + r for _,r in local_deps.pip_reqs)}'
@@ -724,13 +943,15 @@ RUN set -ex && \\
     )
 
     local_pkgs_str = os.linesep.join(
-        f"""# -- Adding local package {relpath} --
+        (
+            f"""# -- Adding local package {relpath} --
 COPY --from={name} . /deps/{name}
 # -- End of local package {relpath} --"""
-        if fullpath in local_deps.additional_contexts
-        else f"""# -- Adding local package {relpath} --
+            if fullpath in local_deps.additional_contexts
+            else f"""# -- Adding local package {relpath} --
 ADD {relpath} /deps/{name}
 # -- End of local package {relpath} --"""
+        )
         for fullpath, (relpath, name) in local_deps.real_pkgs.items()
     )
 
@@ -845,6 +1066,7 @@ ADD . {faux_path}
 RUN cd {faux_path} && {install_cmd}
 {env_additional_config}
 ENV LANGSERVE_GRAPHS='{json.dumps(config["graphs"])}'
+{f"ENV LANGGRAPH_UI='{json.dumps(config['ui'])}'" if config.get("ui") else ""}
 
 WORKDIR {faux_path}
 

libs/cli/poetry.lock

@@ -446,54 +446,47 @@ files = [
 
 [[package]]
 name = "jsonschema-rs"
-version = "0.25.1"
+version = "0.20.0"
 description = "A high-performance JSON Schema validator for Python"
 optional = true
 python-versions = ">=3.8"
 files = [
-    {file = "jsonschema_rs-0.25.1-cp310-cp310-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:0dc49a465a02f97a8c747e852bc82322dd56ff7d66b3058c9656e15b8a5e381c"},
-    {file = "jsonschema_rs-0.25.1-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:cf196d06dea3af58a23e6a03e363140ee307fc80fc77d8c71068df3de1bca588"},
-    {file = "jsonschema_rs-0.25.1-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:f7bc2cac3891b75c301090effba458b6e7108d568aa2aeadb5695d7788991fa3"},
-    {file = "jsonschema_rs-0.25.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3bc130df50b530c57524c7edc29808700d51304f94477833fb0062e0f3df1dfb"},
-    {file = "jsonschema_rs-0.25.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8dace81a4652029493a19e24454bb5f821acdacf65da4f6472bbdc6751c45b79"},
-    {file = "jsonschema_rs-0.25.1-cp310-none-win32.whl", hash = "sha256:dc9771bbe5672f89a974b7302f5e4421559a8d0903eab2c38510dd61bd526086"},
-    {file = "jsonschema_rs-0.25.1-cp310-none-win_amd64.whl", hash = "sha256:7be237cc251c0fe9fe196adf4a7a8402339bbf58ef8710ab76b9e4b845fc94bd"},
-    {file = "jsonschema_rs-0.25.1-cp311-cp311-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:df22e50adba344efc018322305386357bf30c4b6a9b48349f565ff410d1eb78e"},
-    {file = "jsonschema_rs-0.25.1-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:db9fb2086a8a64e40e95e0f6bb0a91ea387419d0d239fc59d468586702286a89"},
-    {file = "jsonschema_rs-0.25.1-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:a168559e9f1fff42d9a2a78c46143fda7ee58a90b85a7d11140dfe16e609e92b"},
-    {file = "jsonschema_rs-0.25.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6e4f659487071009749077b4f5ee69300772fa321f92fa831e71fd4218839958"},
-    {file = "jsonschema_rs-0.25.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0b1e9f7c05c8c9656bb98ecc93a0b91408a6e73063956dea7452cd64277f3b9f"},
-    {file = "jsonschema_rs-0.25.1-cp311-none-win32.whl", hash = "sha256:406a18dafac01b7799dd86b1b05bf14e8628d1f8bc0a1a9c187458f246c2f6cc"},
-    {file = "jsonschema_rs-0.25.1-cp311-none-win_amd64.whl", hash = "sha256:3546274ae6e11fcc1b058cdd763803c4db24e49bac125076bc4fab0ab61d4786"},
-    {file = "jsonschema_rs-0.25.1-cp312-cp312-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:cfaed89ef79cc972d11c50889fa02e8265aa5b6b6826c40749b956888712909d"},
-    {file = "jsonschema_rs-0.25.1-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:87432343bcbd91475af28c765caa0bbde534bbfb6fac1245735a5a1dd6b522a4"},
-    {file = "jsonschema_rs-0.25.1-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:e69c9faed321b7cfbeb37e98e385a0392ad8d25896fd3def56afd080e56e294c"},
-    {file = "jsonschema_rs-0.25.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f004018ffb7fbffc8f1dbeb1bda44f322c924e007bb6966ab3466bdffbc06e62"},
-    {file = "jsonschema_rs-0.25.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b05e2f6bf86ced9d912d72329a19d39a86fcc49a85e31b923456d982733eaa7f"},
-    {file = "jsonschema_rs-0.25.1-cp312-none-win32.whl", hash = "sha256:b3d2ea6217e3618ba587d374b89f4660de59293b0a2fa43278131bc2cb339f57"},
-    {file = "jsonschema_rs-0.25.1-cp312-none-win_amd64.whl", hash = "sha256:6ceeaec97e77d14d6355aec9e55b2356d6376fdf94f6fed10c29cadc8e51fdf6"},
-    {file = "jsonschema_rs-0.25.1-cp313-cp313-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:4696a580f54855cda68c05bbd7c25328eadca34b6a31b36495961235c511148d"},
-    {file = "jsonschema_rs-0.25.1-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:a2d9844d70e5a481a1c363b8b02a3862cc1dbc3b14551a8060436e53243d5447"},
-    {file = "jsonschema_rs-0.25.1-cp313-cp313-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:fd168893519bae7c09fb7226f4ac4b6e73bc1ce9397c3846870cf980135762e8"},
-    {file = "jsonschema_rs-0.25.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8e6627f4ecf1cb12765734f39a536bb4a062e35c9db756d52581b4d045489025"},
-    {file = "jsonschema_rs-0.25.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4784b0c1a0596595e0ea482d6656ccd33d7f14fbf32456e76fead0a67c6a7ec5"},
-    {file = "jsonschema_rs-0.25.1-cp313-none-win32.whl", hash = "sha256:7e6984721dbaaffc6a32ba15b4988df56e4069c9f867370a8a3c48a69a311ac3"},
-    {file = "jsonschema_rs-0.25.1-cp313-none-win_amd64.whl", hash = "sha256:62234e768a1cc57690602711e37f2b936b0f081dcd34a9c2b3e20ba0dafcbceb"},
-    {file = "jsonschema_rs-0.25.1-cp38-cp38-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:346a46f25d974b4ae1d36ac3c02677a699b46404b019a688ddabef40840019fc"},
-    {file = "jsonschema_rs-0.25.1-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:32f4908bc5c958a0a94a25260f5be59fba0062a60a40b61f0faedf12eed82063"},
-    {file = "jsonschema_rs-0.25.1-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:ce090f2038f1a01836adf9f821f7e8c82073710c7a55b002a2e7a1625c3f3954"},
-    {file = "jsonschema_rs-0.25.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d4ef0f3b0760ab151c35f5c8e090cdb201fb81eae2cf5ea1771f4d827d0cfbb1"},
-    {file = "jsonschema_rs-0.25.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2c732bd71da96d6600ae550401e7997fb470f73f95af8defefe4fcbc5e4e9043"},
-    {file = "jsonschema_rs-0.25.1-cp38-none-win32.whl", hash = "sha256:b9ea15dfa5c47b1658e77c3a04e7c38b66e6a617617e1b9f5dba53b67712da1e"},
-    {file = "jsonschema_rs-0.25.1-cp38-none-win_amd64.whl", hash = "sha256:0d8438bea4c09994973ac60c645f4735808329908f4b9421f07d7f2ddf8ac860"},
-    {file = "jsonschema_rs-0.25.1-cp39-cp39-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:6c9ea0b69fab4a27e0c8c0edbee24db2da44d2a97657469ee30a2b980b0b445c"},
-    {file = "jsonschema_rs-0.25.1-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:9de3946a1cd66daae805578ad5cbf21ff4d590d7206048f0eb2999aab056a78a"},
-    {file = "jsonschema_rs-0.25.1-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:3bd2ae54066e840cb5595d135b40c9458a0155e482998e00e922ea6b5ab57a24"},
-    {file = "jsonschema_rs-0.25.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:eb7e2a6777e78a699d09e5c6e84318e97a8e80727939fcde3d0faff7f9da85f3"},
-    {file = "jsonschema_rs-0.25.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8a87babb64a93bad6bfbf2ddad0e33cab6c3f395e9572fe027387c7767e9741c"},
-    {file = "jsonschema_rs-0.25.1-cp39-none-win32.whl", hash = "sha256:570dffc76f0b4e9fa93cf4678a6b07d6fa446f1e5557525703160a94c0ab7968"},
-    {file = "jsonschema_rs-0.25.1-cp39-none-win_amd64.whl", hash = "sha256:9117e105f979f11f55ae940949a544e7e1a304b56ae65f535fa82cc8af4dc2e1"},
-    {file = "jsonschema_rs-0.25.1.tar.gz", hash = "sha256:f2fe71253bb0315061a5025b9336fd49660bca4094b04948f53e3acfd4197a64"},
+    {file = "jsonschema_rs-0.20.0-cp310-cp310-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:d4b12f8aaec5037529fd11e5f71032cb53d44e8e2236bb7c3fb35e6efc7ce7f2"},
+    {file = "jsonschema_rs-0.20.0-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:25d512c47c5c391020c9fc4223f270cf42fbdd39b2906dbc894fe0205168b8f8"},
+    {file = "jsonschema_rs-0.20.0-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:5e4d449a8c2d67c774b8719964cf4dc8eb453a6c665ddf0815780dbcc46a31be"},
+    {file = "jsonschema_rs-0.20.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:60e14bd30306f300d194d6053a8b7dc3723bac20edc2c27db055e45bcc02687c"},
+    {file = "jsonschema_rs-0.20.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2ea9cd8058c6d8ace05fd60a4e11d5bd933f4c21d55c4cccb2bdb6faba9b0319"},
+    {file = "jsonschema_rs-0.20.0-cp310-none-win32.whl", hash = "sha256:ef3198e43addd93619242a30ba40962521b384d68c05507fc680b549d95f7cc0"},
+    {file = "jsonschema_rs-0.20.0-cp310-none-win_amd64.whl", hash = "sha256:ab5a5c6b7282242c64bfc812c10d72dcbd9f5fe083cf81ae94de3cc2da7f0e1e"},
+    {file = "jsonschema_rs-0.20.0-cp311-cp311-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:2f76153d57c8c3778829e14867dd6479eaba17f56e2ba42da82494663200b37a"},
+    {file = "jsonschema_rs-0.20.0-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:1a2b24871ade985580a3f10cfde2a52673823163813fe311abffb30e0aeb4181"},
+    {file = "jsonschema_rs-0.20.0-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:6bf5afaa6e80aa59fae06ca92efb1f8e29b2679f8f8884585272f7c100f04c69"},
+    {file = "jsonschema_rs-0.20.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42d180b318653184eb69d9641dfded6b2d59c88db8fb82012d3d20e1582af5cd"},
+    {file = "jsonschema_rs-0.20.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7aa67bf6338fbce3a2a3f9f408413aad7a72593ed73c846bc2667a20b747327f"},
+    {file = "jsonschema_rs-0.20.0-cp311-none-win32.whl", hash = "sha256:55c255ca6ee44177b7b5c773a8edb25af34be0d6a454e602be92cc183d6dcbe7"},
+    {file = "jsonschema_rs-0.20.0-cp311-none-win_amd64.whl", hash = "sha256:3b6effefdef590854522517b84081214b46a8fba9a5d60c538c6f1ff819609c5"},
+    {file = "jsonschema_rs-0.20.0-cp312-cp312-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:8b9d044ecdef9a15e350a35e950c9797c804f185b547bcb56bb91fef9bf31827"},
+    {file = "jsonschema_rs-0.20.0-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:d43b6a65c159f7aed82dca846f93a4c5ffd013ff0c87a5668a645a81792c8001"},
+    {file = "jsonschema_rs-0.20.0-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:9a6500934be21fe64bd65d9e75a67941b675091b8e2154df0a04f5b57073b8bf"},
+    {file = "jsonschema_rs-0.20.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:41e42c80eed641a848ee38039291e6ca90e61de1a0b695e706894b175f45c741"},
+    {file = "jsonschema_rs-0.20.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c4e0945cb1ff4d183e855ae975839d648df24604d71827951f57a8b7edabb8ca"},
+    {file = "jsonschema_rs-0.20.0-cp312-none-win32.whl", hash = "sha256:00016bfdc132aa8c728fe012e9ed2b5c9d0d3dd5c37368990d58288e121a6d79"},
+    {file = "jsonschema_rs-0.20.0-cp312-none-win_amd64.whl", hash = "sha256:2c5abcf6185a4eea7185aadb132f92f6bc1d808d3debe775f0e4608baba8501e"},
+    {file = "jsonschema_rs-0.20.0-cp38-cp38-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:e51888f8c6c6434fc4037db71fe366c78d3bec8b8b200b6fc70d80266b932d77"},
+    {file = "jsonschema_rs-0.20.0-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:7ff31a9bb78813e2d3331aa0e4b558d34d7aaa89ab518b2313ecd53c0b3fb4ef"},
+    {file = "jsonschema_rs-0.20.0-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:c7dfb51026ce11ca5b657022a149b7324c81bbe8ff43b57439421b0b57d623ce"},
+    {file = "jsonschema_rs-0.20.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3278fd2f0a47a0e479b551f526778da76006798dd0fc3c19155223b402b110cf"},
+    {file = "jsonschema_rs-0.20.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6cc6b6935e6a8716b532b09f231d37e6dd39fa5bec3d87aad036a13206e601bd"},
+    {file = "jsonschema_rs-0.20.0-cp38-none-win32.whl", hash = "sha256:8ae5f0a04dd4ed2a801df814e67436b6c2cafc127485003382e24a7831f46be3"},
+    {file = "jsonschema_rs-0.20.0-cp38-none-win_amd64.whl", hash = "sha256:ee28d48e8dd9f3da8d5dbe190ff769940a606792be16eeb1fe23a62ec0900297"},
+    {file = "jsonschema_rs-0.20.0-cp39-cp39-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:2a698ba8170dbb9fc32e1d0043c8f85903ffbcca56d7dc9ad8a9f169c72eae60"},
+    {file = "jsonschema_rs-0.20.0-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:a4dcba330d2196f7af8229aca43178bdcacd8a393c76dee7b3763e7e2ac40457"},
+    {file = "jsonschema_rs-0.20.0-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:0afa2f4b2e4cd6688866a490f3d9d9bfa97a7f19aabd860cfc1c00b54f957a5e"},
+    {file = "jsonschema_rs-0.20.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:18acb318a367fdae7161126e36ecbc005b713684b7178ba853efdcac22d3f41f"},
+    {file = "jsonschema_rs-0.20.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:75d0c7a497dbd59369018d6056f5ff54bf955ca385d186bfcf3529432323686f"},
+    {file = "jsonschema_rs-0.20.0-cp39-none-win32.whl", hash = "sha256:16d670954877226b7ea66d777e7aba9ca0b6c70772630af67c836aa1e99ba143"},
+    {file = "jsonschema_rs-0.20.0-cp39-none-win_amd64.whl", hash = "sha256:12f62a745ee72a5ce109f7412d0f8c55f510158c7a69171d261f1da9bc8b4059"},
+    {file = "jsonschema_rs-0.20.0.tar.gz", hash = "sha256:f76d52b7755d184844f1bfedc209c5107b5be3b6b2ae8531db4a0e563b8317ae"},
 ]
 
 [package.extras]
@@ -502,13 +495,13 @@ tests = ["flask (>=2.2.5)", "hypothesis (>=6.79.4)", "pytest (>=7.4.4)"]
 
 [[package]]
 name = "langchain-core"
-version = "0.3.37"
+version = "0.3.40"
 description = "Building applications with LLMs through composability"
 optional = true
 python-versions = "<4.0,>=3.9"
 files = [
-    {file = "langchain_core-0.3.37-py3-none-any.whl", hash = "sha256:8202fd6506ce139a3a1b1c4c3006216b1c7fffa40bdd1779f7d2c67f75eb5f79"},
-    {file = "langchain_core-0.3.37.tar.gz", hash = "sha256:cda8786e616caa2f68f7cc9e811b9b50e3b63fb2094333318b348e5961a7ea01"},
+    {file = "langchain_core-0.3.40-py3-none-any.whl", hash = "sha256:9f31358741f10a13db8531e8288b8a5ae91904018c5c2e6f739d6645a98fca03"},
+    {file = "langchain_core-0.3.40.tar.gz", hash = "sha256:893a238b38491967c804662c1ec7c3e6ebaf223d1125331249c3cf3862ff2746"},
 ]
 
 [package.dependencies]
@@ -525,73 +518,89 @@ typing-extensions = ">=4.7"
 
 [[package]]
 name = "langgraph"
-version = "0.2.74"
+version = "0.3.1"
 description = "Building stateful, multi-actor applications with LLMs"
 optional = true
 python-versions = "<4.0,>=3.9.0"
 files = [
-    {file = "langgraph-0.2.74-py3-none-any.whl", hash = "sha256:91a522df764e66068f1a6de09ea748cea0687912838f29218c1d1b92b1ca025f"},
-    {file = "langgraph-0.2.74.tar.gz", hash = "sha256:db6e63e0771e2e8fb17dc0e040007b32f009e0f114e35d8348e336eb15f068e5"},
+    {file = "langgraph-0.3.1-py3-none-any.whl", hash = "sha256:212e1220d6a2af27048109604c816ccfbceb53a9aa93721be874305d8e28b7f5"},
+    {file = "langgraph-0.3.1.tar.gz", hash = "sha256:81cb89c381b089a20eac9a247f7ebcf3f41c922ac79e06dbcc4fc136c6f73dd5"},
 ]
 
 [package.dependencies]
-langchain-core = ">=0.2.43,<0.3.0 || >0.3.0,<0.3.1 || >0.3.1,<0.3.2 || >0.3.2,<0.3.3 || >0.3.3,<0.3.4 || >0.3.4,<0.3.5 || >0.3.5,<0.3.6 || >0.3.6,<0.3.7 || >0.3.7,<0.3.8 || >0.3.8,<0.3.9 || >0.3.9,<0.3.10 || >0.3.10,<0.3.11 || >0.3.11,<0.3.12 || >0.3.12,<0.3.13 || >0.3.13,<0.3.14 || >0.3.14,<0.3.15 || >0.3.15,<0.3.16 || >0.3.16,<0.3.17 || >0.3.17,<0.3.18 || >0.3.18,<0.3.19 || >0.3.19,<0.3.20 || >0.3.20,<0.3.21 || >0.3.21,<0.3.22 || >0.3.22,<0.4.0"
+langchain-core = ">=0.1,<0.4"
 langgraph-checkpoint = ">=2.0.10,<3.0.0"
+langgraph-prebuilt = ">=0.1.1,<0.2"
 langgraph-sdk = ">=0.1.42,<0.2.0"
 
 [[package]]
 name = "langgraph-api"
-version = "0.0.26"
+version = "0.0.32"
 description = ""
 optional = true
 python-versions = "<4.0,>=3.11.0"
 files = [
-    {file = "langgraph_api-0.0.26-py3-none-any.whl", hash = "sha256:ecec9f0378f73dc0f0a30c43e1b920fe1f00821c82056efeb0de0ad81cdf4305"},
-    {file = "langgraph_api-0.0.26.tar.gz", hash = "sha256:2a7606d6a8cf82774f4c5603d291835dec4fbb1dd93f3bba842cf5932c042da7"},
+    {file = "langgraph_api-0.0.32-py3-none-any.whl", hash = "sha256:7990cedc65f784813aba867c5bde3fdfae3fa4588baef1aa346cbeac7c3aebf1"},
+    {file = "langgraph_api-0.0.32.tar.gz", hash = "sha256:6f5b698ad8d136b73c2c53bcfa30670e9244a318b08b5e9cf00a707ea57c058c"},
 ]
 
 [package.dependencies]
 cryptography = ">=43.0.3,<44.0.0"
-httpx = ">=0.27.0"
-jsonschema-rs = ">=0.25.0,<0.26.0"
+httpx = ">=0.25.0"
+jsonschema-rs = ">=0.20.0,<0.30"
 langchain-core = ">=0.2.38,<0.4.0"
-langgraph = ">=0.2.56,<0.3.0"
-langgraph-checkpoint = ">=2.0.15,<3.0"
-langgraph-sdk = ">=0.1.53,<0.2.0"
+langgraph = ">=0.2.56,<0.4.0"
+langgraph-checkpoint = ">=2.0.21,<3.0"
+langgraph-sdk = ">=0.1.58,<0.2.0"
 langsmith = ">=0.1.63,<0.4.0"
-orjson = ">=3.10.1"
+orjson = ">=3.9.7"
 pyjwt = ">=2.9.0,<3.0.0"
 sse-starlette = ">=2.1.0,<2.2.0"
 starlette = ">=0.38.6"
-structlog = ">=24.4.0,<25.0.0"
-tenacity = ">=8.3.0,<10"
+structlog = ">=24.1.0,<26"
+tenacity = ">=8.0.0"
 uvicorn = ">=0.26.0"
 watchfiles = ">=0.13"
 
 [[package]]
 name = "langgraph-checkpoint"
-version = "2.0.16"
+version = "2.0.21"
 description = "Library with base interfaces for LangGraph checkpoint savers."
 optional = true
 python-versions = "<4.0.0,>=3.9.0"
 files = [
-    {file = "langgraph_checkpoint-2.0.16-py3-none-any.whl", hash = "sha256:dfab51076a6eddb5f9e146cfe1b977e3dd6419168b2afa23ff3f4e47973bf06f"},
-    {file = "langgraph_checkpoint-2.0.16.tar.gz", hash = "sha256:49ba8cfa12b2aae845ccc3b1fbd1d7a8d3a6c4a2e387ab3a92fca40dd3d4baa5"},
+    {file = "langgraph_checkpoint-2.0.21-py3-none-any.whl", hash = "sha256:ca89c2090cd9729f83f9782226935dc5ff9fe7756c24936f484ccb0ce367f87b"},
+    {file = "langgraph_checkpoint-2.0.21.tar.gz", hash = "sha256:52beeb6dc1bd8c487b8315466cab271093b65eb97f54a0942dfe105cd20b237f"},
 ]
 
 [package.dependencies]
 langchain-core = ">=0.2.38,<0.4"
 msgpack = ">=1.1.0,<2.0.0"
 
+[[package]]
+name = "langgraph-prebuilt"
+version = "0.1.1"
+description = "Library with high-level APIs for creating and executing LangGraph agents and tools."
+optional = true
+python-versions = "<4.0.0,>=3.9.0"
+files = [
+    {file = "langgraph_prebuilt-0.1.1-py3-none-any.whl", hash = "sha256:148a9558a36ec7e83cc6512f3521425c862b0463251ae0242ade52a448c54e78"},
+    {file = "langgraph_prebuilt-0.1.1.tar.gz", hash = "sha256:420a748ff93842f2b1a345a0c1ca3939d2bc7a2d46c20e9a9a0d8f148152cc47"},
+]
+
+[package.dependencies]
+langchain-core = ">=0.2.43,<0.3.0 || >0.3.0,<0.3.1 || >0.3.1,<0.3.2 || >0.3.2,<0.3.3 || >0.3.3,<0.3.4 || >0.3.4,<0.3.5 || >0.3.5,<0.3.6 || >0.3.6,<0.3.7 || >0.3.7,<0.3.8 || >0.3.8,<0.3.9 || >0.3.9,<0.3.10 || >0.3.10,<0.3.11 || >0.3.11,<0.3.12 || >0.3.12,<0.3.13 || >0.3.13,<0.3.14 || >0.3.14,<0.3.15 || >0.3.15,<0.3.16 || >0.3.16,<0.3.17 || >0.3.17,<0.3.18 || >0.3.18,<0.3.19 || >0.3.19,<0.3.20 || >0.3.20,<0.3.21 || >0.3.21,<0.3.22 || >0.3.22,<0.4.0"
+langgraph-checkpoint = ">=2.0.10,<3.0.0"
+
 [[package]]
 name = "langgraph-sdk"
-version = "0.1.53"
+version = "0.1.58"
 description = "SDK for interacting with LangGraph API"
 optional = true
 python-versions = "<4.0.0,>=3.9.0"
 files = [
-    {file = "langgraph_sdk-0.1.53-py3-none-any.whl", hash = "sha256:4fab62caad73661ffe4c3ababedcd0d7bfaaba986bee4416b9c28948458a3af5"},
-    {file = "langgraph_sdk-0.1.53.tar.gz", hash = "sha256:12906ed965905fa27e0c28d9fa07dc6fd89e6895ff321ff049fdf3965d057cc4"},
+    {file = "langgraph_sdk-0.1.58-py3-none-any.whl", hash = "sha256:65f88cf5582da0c316714dc475126fa03c5f74d72bc0b9221dd42649de8e23d4"},
+    {file = "langgraph_sdk-0.1.58.tar.gz", hash = "sha256:ef8b0e4c08af8c7efd3919497879c87a3627806b51e4ba5e8b06e0717e3d44cd"},
 ]
 
 [package.dependencies]
@@ -600,18 +609,19 @@ orjson = ">=3.10.1"
 
 [[package]]
 name = "langsmith"
-version = "0.3.8"
+version = "0.3.11"
 description = "Client library to connect to the LangSmith LLM Tracing and Evaluation Platform."
 optional = true
 python-versions = "<4.0,>=3.9"
 files = [
-    {file = "langsmith-0.3.8-py3-none-any.whl", hash = "sha256:fbb9dd97b0f090219447fca9362698d07abaeda1da85aa7cc6ec6517b36581b1"},
-    {file = "langsmith-0.3.8.tar.gz", hash = "sha256:97f9bebe0b7cb0a4f278e6ff30ae7d5ededff3883b014442ec6d7d575b02a0f1"},
+    {file = "langsmith-0.3.11-py3-none-any.whl", hash = "sha256:0cca22737ef07d3b038a437c141deda37e00add56022582680188b681bec095e"},
+    {file = "langsmith-0.3.11.tar.gz", hash = "sha256:ddf29d24352e99de79c9618aaf95679214324e146c5d3d9475a7ddd2870018b1"},
 ]
 
 [package.dependencies]
 httpx = ">=0.23.0,<1"
 orjson = {version = ">=3.9.14,<4.0.0", markers = "platform_python_implementation != \"PyPy\""}
+packaging = ">=23.2"
 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\""},
@@ -697,6 +707,58 @@ files = [
     {file = "msgpack-1.1.0.tar.gz", hash = "sha256:dd432ccc2c72b914e4cb77afce64aab761c1137cc698be3984eee260bcb2896e"},
 ]
 
+[[package]]
+name = "msgspec"
+version = "0.19.0"
+description = "A fast serialization and validation library, with builtin support for JSON, MessagePack, YAML, and TOML."
+optional = false
+python-versions = ">=3.9"
+files = [
+    {file = "msgspec-0.19.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d8dd848ee7ca7c8153462557655570156c2be94e79acec3561cf379581343259"},
+    {file = "msgspec-0.19.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:0553bbc77662e5708fe66aa75e7bd3e4b0f209709c48b299afd791d711a93c36"},
+    {file = "msgspec-0.19.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fe2c4bf29bf4e89790b3117470dea2c20b59932772483082c468b990d45fb947"},
+    {file = "msgspec-0.19.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:00e87ecfa9795ee5214861eab8326b0e75475c2e68a384002aa135ea2a27d909"},
+    {file = "msgspec-0.19.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:3c4ec642689da44618f68c90855a10edbc6ac3ff7c1d94395446c65a776e712a"},
+    {file = "msgspec-0.19.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:2719647625320b60e2d8af06b35f5b12d4f4d281db30a15a1df22adb2295f633"},
+    {file = "msgspec-0.19.0-cp310-cp310-win_amd64.whl", hash = "sha256:695b832d0091edd86eeb535cd39e45f3919f48d997685f7ac31acb15e0a2ed90"},
+    {file = "msgspec-0.19.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:aa77046904db764b0462036bc63ef71f02b75b8f72e9c9dd4c447d6da1ed8f8e"},
+    {file = "msgspec-0.19.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:047cfa8675eb3bad68722cfe95c60e7afabf84d1bd8938979dd2b92e9e4a9551"},
+    {file = "msgspec-0.19.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e78f46ff39a427e10b4a61614a2777ad69559cc8d603a7c05681f5a595ea98f7"},
+    {file = "msgspec-0.19.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c7adf191e4bd3be0e9231c3b6dc20cf1199ada2af523885efc2ed218eafd011"},
+    {file = "msgspec-0.19.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:f04cad4385e20be7c7176bb8ae3dca54a08e9756cfc97bcdb4f18560c3042063"},
+    {file = "msgspec-0.19.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:45c8fb410670b3b7eb884d44a75589377c341ec1392b778311acdbfa55187716"},
+    {file = "msgspec-0.19.0-cp311-cp311-win_amd64.whl", hash = "sha256:70eaef4934b87193a27d802534dc466778ad8d536e296ae2f9334e182ac27b6c"},
+    {file = "msgspec-0.19.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:f98bd8962ad549c27d63845b50af3f53ec468b6318400c9f1adfe8b092d7b62f"},
+    {file = "msgspec-0.19.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:43bbb237feab761b815ed9df43b266114203f53596f9b6e6f00ebd79d178cdf2"},
+    {file = "msgspec-0.19.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4cfc033c02c3e0aec52b71710d7f84cb3ca5eb407ab2ad23d75631153fdb1f12"},
+    {file = "msgspec-0.19.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d911c442571605e17658ca2b416fd8579c5050ac9adc5e00c2cb3126c97f73bc"},
+    {file = "msgspec-0.19.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:757b501fa57e24896cf40a831442b19a864f56d253679f34f260dcb002524a6c"},
+    {file = "msgspec-0.19.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:5f0f65f29b45e2816d8bded36e6b837a4bf5fb60ec4bc3c625fa2c6da4124537"},
+    {file = "msgspec-0.19.0-cp312-cp312-win_amd64.whl", hash = "sha256:067f0de1c33cfa0b6a8206562efdf6be5985b988b53dd244a8e06f993f27c8c0"},
+    {file = "msgspec-0.19.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:f12d30dd6266557aaaf0aa0f9580a9a8fbeadfa83699c487713e355ec5f0bd86"},
+    {file = "msgspec-0.19.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:82b2c42c1b9ebc89e822e7e13bbe9d17ede0c23c187469fdd9505afd5a481314"},
+    {file = "msgspec-0.19.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:19746b50be214a54239aab822964f2ac81e38b0055cca94808359d779338c10e"},
+    {file = "msgspec-0.19.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:60ef4bdb0ec8e4ad62e5a1f95230c08efb1f64f32e6e8dd2ced685bcc73858b5"},
+    {file = "msgspec-0.19.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:ac7f7c377c122b649f7545810c6cd1b47586e3aa3059126ce3516ac7ccc6a6a9"},
+    {file = "msgspec-0.19.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:a5bc1472223a643f5ffb5bf46ccdede7f9795078194f14edd69e3aab7020d327"},
+    {file = "msgspec-0.19.0-cp313-cp313-win_amd64.whl", hash = "sha256:317050bc0f7739cb30d257ff09152ca309bf5a369854bbf1e57dffc310c1f20f"},
+    {file = "msgspec-0.19.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:15c1e86fff77184c20a2932cd9742bf33fe23125fa3fcf332df9ad2f7d483044"},
+    {file = "msgspec-0.19.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:3b5541b2b3294e5ffabe31a09d604e23a88533ace36ac288fa32a420aa38d229"},
+    {file = "msgspec-0.19.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0f5c043ace7962ef188746e83b99faaa9e3e699ab857ca3f367b309c8e2c6b12"},
+    {file = "msgspec-0.19.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ca06aa08e39bf57e39a258e1996474f84d0dd8130d486c00bec26d797b8c5446"},
+    {file = "msgspec-0.19.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:e695dad6897896e9384cf5e2687d9ae9feaef50e802f93602d35458e20d1fb19"},
+    {file = "msgspec-0.19.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:3be5c02e1fee57b54130316a08fe40cca53af92999a302a6054cd451700ea7db"},
+    {file = "msgspec-0.19.0-cp39-cp39-win_amd64.whl", hash = "sha256:0684573a821be3c749912acf5848cce78af4298345cb2d7a8b8948a0a5a27cfe"},
+    {file = "msgspec-0.19.0.tar.gz", hash = "sha256:604037e7cd475345848116e89c553aa9a233259733ab51986ac924ab1b976f8e"},
+]
+
+[package.extras]
+dev = ["attrs", "coverage", "eval-type-backport", "furo", "ipython", "msgpack", "mypy", "pre-commit", "pyright", "pytest", "pyyaml", "sphinx", "sphinx-copybutton", "sphinx-design", "tomli", "tomli_w"]
+doc = ["furo", "ipython", "sphinx", "sphinx-copybutton", "sphinx-design"]
+test = ["attrs", "eval-type-backport", "msgpack", "pytest", "pyyaml", "tomli", "tomli_w"]
+toml = ["tomli", "tomli_w"]
+yaml = ["pyyaml"]
+
 [[package]]
 name = "mypy"
 version = "1.15.0"
@@ -1278,13 +1340,13 @@ examples = ["fastapi"]
 
 [[package]]
 name = "starlette"
-version = "0.45.3"
+version = "0.46.0"
 description = "The little ASGI library that shines."
 optional = true
 python-versions = ">=3.9"
 files = [
-    {file = "starlette-0.45.3-py3-none-any.whl", hash = "sha256:dfb6d332576f136ec740296c7e8bb8c8a7125044e7c6da30744718880cdd059d"},
-    {file = "starlette-0.45.3.tar.gz", hash = "sha256:2cbcba2a75806f8a41c722141486f37c28e30a0921c5f6fe4346cb0dcee1302f"},
+    {file = "starlette-0.46.0-py3-none-any.whl", hash = "sha256:913f0798bd90ba90a9156383bcf1350a17d6259451d0d8ee27fc0cf2db609038"},
+    {file = "starlette-0.46.0.tar.gz", hash = "sha256:b359e4567456b28d473d0193f34c0de0ed49710d75ef183a74a5ce0499324f50"},
 ]
 
 [package.dependencies]
@@ -1295,13 +1357,13 @@ full = ["httpx (>=0.27.0,<0.29.0)", "itsdangerous", "jinja2", "python-multipart
 
 [[package]]
 name = "structlog"
-version = "24.4.0"
+version = "25.2.0"
 description = "Structured Logging for Python"
 optional = true
 python-versions = ">=3.8"
 files = [
-    {file = "structlog-24.4.0-py3-none-any.whl", hash = "sha256:597f61e80a91cc0749a9fd2a098ed76715a1c8a01f73e336b746504d1aad7610"},
-    {file = "structlog-24.4.0.tar.gz", hash = "sha256:b27bfecede327a6d2da5fbc96bd859f114ecc398a6389d664f62085ee7ae6fc4"},
+    {file = "structlog-25.2.0-py3-none-any.whl", hash = "sha256:0fecea2e345d5d491b72f3db2e5fcd6393abfc8cd06a4851f21fcd4d1a99f437"},
+    {file = "structlog-25.2.0.tar.gz", hash = "sha256:d9f9776944207d1035b8b26072b9b140c63702fd7aa57c2f85d28ab701bd8e92"},
 ]
 
 [package.extras]
@@ -1655,4 +1717,4 @@ inmem = ["langgraph-api", "python-dotenv"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.9.0,<4.0"
-content-hash = "48e374a559e6d8339c82b5271dea910f8ddfb6baf8436153ca54faefb8b2b220"
+content-hash = "f5aa4d66f9c0b98b8321a70a82387dc6e5f3a3a7ecedd87ac00d6415199038f9"

libs/cli/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langgraph-cli"
-version = "0.1.73"
+version = "0.1.78"
 description = "CLI for interacting with LangGraph API"
 authors = []
 license = "MIT"
@@ -14,7 +14,7 @@ langgraph = "langgraph_cli.cli:cli"
 [tool.poetry.dependencies]
 python = "^3.9.0,<4.0"
 click = "^8.1.7"
-langgraph-api = { version = ">=0.0.26,<0.1.0", optional = true, python = ">=3.11,<4.0" }
+langgraph-api = { version = ">=0.0.32,<0.1.0", optional = true, python = ">=3.11,<4.0" }
 python-dotenv = { version = ">=0.8.0", optional = true }
 
 [tool.poetry.group.dev.dependencies]
@@ -25,6 +25,7 @@ pytest-asyncio = "^0.21.1"
 pytest-mock = "^3.11.1"
 pytest-watch = "^4.2.0"
 mypy = "^1.10.0"
+msgspec = "^0.19.0"
 
 [tool.poetry.extras]
 inmem = ["langgraph-api", "python-dotenv"]

libs/cli/schemas/schema.json

@@ -0,0 +1,480 @@
+{
+  "$ref": "#/$defs/Config",
+  "$defs": {
+    "Config": {
+      "title": "Config",
+      "description": "Top-level config for langgraph-cli or similar deployment tooling.",
+      "type": "object",
+      "required": [],
+      "oneOf": [
+        {
+          "type": "object",
+          "properties": {
+            "python_version": {
+              "type": "string",
+              "description": "Optional. Python version in 'major.minor' format (e.g. '3.11').\nMust be at least 3.11 or greater for this deployment to function properly.\n",
+              "enum": [
+                "3.11",
+                "3.12"
+              ]
+            },
+            "pip_config_file": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Optional. Path to a pip config file (e.g., \"/etc/pip.conf\" or \"pip.ini\") for controlling\npackage installation (custom indices, credentials, etc.).\n\nOnly relevant if Python dependencies are installed via pip. If omitted, default pip settings are used.\n"
+            },
+            "auth": {
+              "anyOf": [
+                {
+                  "$ref": "#/$defs/AuthConfig"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Optional. Custom authentication config, including the path to your Python auth logic and\nthe OpenAPI security definitions it uses.\n"
+            },
+            "dependencies": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              },
+              "description": "List of Python dependencies to install, either from PyPI or local paths.\n"
+            },
+            "dockerfile_lines": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              },
+              "description": "Optional. Additional Docker instructions that will be appended to your base Dockerfile.\n\nUseful for installing OS packages, setting environment variables, etc."
+            },
+            "env": {
+              "anyOf": [
+                {
+                  "type": "object",
+                  "additionalProperties": {
+                    "type": "string"
+                  }
+                },
+                {
+                  "type": "string"
+                }
+              ],
+              "description": "Optional. Environment variables to set for your deployment.\n\n- If given as a dict, keys are variable names and values are their values.\n- If given as a string, it must be a path to a file containing lines in KEY=VALUE format.\n\nenv=\".env\n"
+            },
+            "graphs": {
+              "type": "object",
+              "additionalProperties": {
+                "type": "string"
+              },
+              "description": "Optional. Named definitions of graphs, each pointing to a Python object.\n\n\nGraphs can be StateGraph, @entrypoint, or any other Pregel object OR they can point to (async) context\nmanagers that accept a single configuration argument (of type RunnableConfig) and return a pregel object\n(instance of Stategraph, etc.).\n"
+            },
+            "http": {
+              "anyOf": [
+                {
+                  "$ref": "#/$defs/HttpConfig"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Optional. Configuration for the built-in HTTP server, controlling which custom routes are exposed\nand how cross-origin requests are handled.\n"
+            },
+            "store": {
+              "anyOf": [
+                {
+                  "$ref": "#/$defs/StoreConfig"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Optional. Configuration for the built-in long-term memory store, including semantic search indexing.\n\nIf omitted, no vector index is set up (the object store will still be present, however).\n"
+            },
+            "ui": {
+              "anyOf": [
+                {
+                  "type": "object",
+                  "additionalProperties": {
+                    "type": "string"
+                  }
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Optional. Named definitions of UI components emitted by the agent, each pointing to a JS/TS file.\n"
+            }
+          },
+          "required": [
+            "dependencies",
+            "graphs"
+          ]
+        },
+        {
+          "type": "object",
+          "properties": {
+            "node_version": {
+              "anyOf": [
+                {
+                  "type": "string",
+                  "enum": [
+                    "20"
+                  ]
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Optional. Node.js version as a major version (e.g. '20'), if your deployment needs Node.\nMust be >= 20 if provided.\n"
+            },
+            "auth": {
+              "anyOf": [
+                {
+                  "$ref": "#/$defs/AuthConfig"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Optional. Custom authentication config, including the path to your Python auth logic and\nthe OpenAPI security definitions it uses.\n"
+            },
+            "dependencies": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              },
+              "description": "List of Python dependencies to install, either from PyPI or local paths.\n"
+            },
+            "dockerfile_lines": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              },
+              "description": "Optional. Additional Docker instructions that will be appended to your base Dockerfile.\n\nUseful for installing OS packages, setting environment variables, etc."
+            },
+            "env": {
+              "anyOf": [
+                {
+                  "type": "object",
+                  "additionalProperties": {
+                    "type": "string"
+                  }
+                },
+                {
+                  "type": "string"
+                }
+              ],
+              "description": "Optional. Environment variables to set for your deployment.\n\n- If given as a dict, keys are variable names and values are their values.\n- If given as a string, it must be a path to a file containing lines in KEY=VALUE format.\n\nenv=\".env\n"
+            },
+            "graphs": {
+              "type": "object",
+              "additionalProperties": {
+                "type": "string"
+              },
+              "description": "Optional. Named definitions of graphs, each pointing to a Python object.\n\n\nGraphs can be StateGraph, @entrypoint, or any other Pregel object OR they can point to (async) context\nmanagers that accept a single configuration argument (of type RunnableConfig) and return a pregel object\n(instance of Stategraph, etc.).\n"
+            },
+            "http": {
+              "anyOf": [
+                {
+                  "$ref": "#/$defs/HttpConfig"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Optional. Configuration for the built-in HTTP server, controlling which custom routes are exposed\nand how cross-origin requests are handled.\n"
+            },
+            "store": {
+              "anyOf": [
+                {
+                  "$ref": "#/$defs/StoreConfig"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Optional. Configuration for the built-in long-term memory store, including semantic search indexing.\n\nIf omitted, no vector index is set up (the object store will still be present, however).\n"
+            },
+            "ui": {
+              "anyOf": [
+                {
+                  "type": "object",
+                  "additionalProperties": {
+                    "type": "string"
+                  }
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Optional. Named definitions of UI components emitted by the agent, each pointing to a JS/TS file.\n"
+            }
+          },
+          "required": [
+            "node_version",
+            "graphs"
+          ]
+        }
+      ]
+    },
+    "AuthConfig": {
+      "title": "AuthConfig",
+      "description": "Configuration for custom authentication logic and how it integrates into the OpenAPI spec.",
+      "type": "object",
+      "properties": {
+        "disable_studio_auth": {
+          "type": "boolean",
+          "description": "Optional. Whether to disable LangSmith API-key authentication for requests originating the Studio.\n\nDefaults to False, meaning that if a particular header is set, the server will verify the `x-api-key` header\nvalue is a valid API key for the deployment's workspace. If True, all requests will go through your custom\nauthentication logic, regardless of origin of the request.\n"
+        },
+        "openapi": {
+          "$ref": "#/$defs/SecurityConfig",
+          "description": "Required. Detailed security configuration that merges into your deployment's OpenAPI spec.\n\n{\n}\n}\n}\n},\n]\n}\n"
+        },
+        "path": {
+          "type": "string",
+          "description": "Required. Path to an instance of the Auth() class that implements custom authentication.\n"
+        }
+      },
+      "required": []
+    },
+    "SecurityConfig": {
+      "title": "SecurityConfig",
+      "description": "Configuration for OpenAPI security definitions and requirements.\n\nUseful for specifying global or path-level authentication and authorization flows\n(e.g., OAuth2, API key headers, etc.).",
+      "type": "object",
+      "properties": {
+        "paths": {
+          "type": "object",
+          "additionalProperties": {
+            "type": "object",
+            "additionalProperties": {
+              "type": "array",
+              "items": {
+                "type": "object",
+                "additionalProperties": {
+                  "type": "array",
+                  "items": {
+                    "type": "string"
+                  }
+                }
+              }
+            }
+          },
+          "description": "Optional. Path-specific security overrides.\n\n- Keys that are HTTP methods (e.g., \"GET\", \"POST\"),\n- Values are lists of security definitions (just like `security`) for that method.\n"
+        },
+        "security": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "additionalProperties": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          "description": "Optional. Global security requirements across all endpoints.\n\nEach element in the list maps a security scheme (e.g. \"OAuth2\") to a list of scopes (e.g. [\"read\", \"write\"])."
+        },
+        "securitySchemes": {
+          "type": "object",
+          "additionalProperties": {
+            "type": "object"
+          },
+          "description": "Required. Dict describing each security scheme recognized by your OpenAPI spec.\n\nKeys are scheme names (e.g. \"OAuth2\", \"ApiKeyAuth\") and values are their definitions."
+        }
+      },
+      "required": []
+    },
+    "HttpConfig": {
+      "title": "HttpConfig",
+      "description": "Configuration for the built-in HTTP server that powers your deployment's routes and endpoints.",
+      "type": "object",
+      "properties": {
+        "app": {
+          "type": "string",
+          "description": "Optional. Import path to a custom Starlette/FastAPI application to mount.\n"
+        },
+        "cors": {
+          "anyOf": [
+            {
+              "$ref": "#/$defs/CorsConfig"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "description": "Optional. Defines CORS restrictions. If omitted, no special rules are set and\ncross-origin behavior depends on default server settings.\n"
+        },
+        "disable_assistants": {
+          "type": "boolean",
+          "description": "Optional. If True, /assistants routes are removed from the server.\n\nDefault is False (meaning /assistants is enabled).\n"
+        },
+        "disable_meta": {
+          "type": "boolean",
+          "description": "Optional. If True, all meta endpoints (/ok, /info, /metrics, /docs) are disabled.\n\nDefault is False.\n"
+        },
+        "disable_runs": {
+          "type": "boolean",
+          "description": "Optional. If True, /runs routes are removed.\n\nDefault is False.\n"
+        },
+        "disable_store": {
+          "type": "boolean",
+          "description": "Optional. If True, /store routes are removed, disabling direct store interactions via HTTP.\n\nDefault is False.\n"
+        },
+        "disable_threads": {
+          "type": "boolean",
+          "description": "Optional. If True, /threads routes are removed.\n\nDefault is False.\n"
+        }
+      },
+      "required": []
+    },
+    "CorsConfig": {
+      "title": "CorsConfig",
+      "description": "Specifies Cross-Origin Resource Sharing (CORS) rules for your server.\n\nIf omitted, defaults are typically very restrictive (often no cross-origin requests).\nConfigure carefully if you want to allow usage from browsers hosted on other domains.",
+      "type": "object",
+      "properties": {
+        "allow_credentials": {
+          "type": "boolean",
+          "description": "Optional. If True, cross-origin requests can include credentials (cookies, auth headers).\n\nDefault False to avoid accidentally exposing secured endpoints to untrusted sites.\n"
+        },
+        "allow_headers": {
+          "type": "array",
+          "items": {
+            "type": "string"
+          },
+          "description": "Optional. HTTP headers that can be used in cross-origin requests (e.g. [\"Content-Type\", \"Authorization\"])."
+        },
+        "allow_methods": {
+          "type": "array",
+          "items": {
+            "type": "string"
+          },
+          "description": "Optional. HTTP methods permitted for cross-origin requests (e.g. [\"GET\", \"POST\"]).\n\nDefault might be [\"GET\", \"POST\", \"OPTIONS\"] depending on your server framework.\n"
+        },
+        "allow_origin_regex": {
+          "type": "string",
+          "description": "Optional. A regex pattern for matching allowed origins, used if you have dynamic subdomains.\n"
+        },
+        "allow_origins": {
+          "type": "array",
+          "items": {
+            "type": "string"
+          },
+          "description": "Optional. List of allowed origins (e.g., \"https://example.com\").\n\nDefault is often an empty list (no external origins).\nUse \"*\" only if you trust all origins, as that bypasses most restrictions.\n"
+        },
+        "expose_headers": {
+          "type": "array",
+          "items": {
+            "type": "string"
+          },
+          "description": "Optional. List of headers that browsers are allowed to read from the response in cross-origin contexts."
+        },
+        "max_age": {
+          "type": "integer",
+          "description": "Optional. How many seconds the browser may cache preflight responses.\n\nDefault might be 600 (10 minutes). Larger values reduce preflight requests but can cause stale configurations.\n"
+        }
+      },
+      "required": []
+    },
+    "StoreConfig": {
+      "title": "StoreConfig",
+      "description": "Configuration for the built-in long-term memory store.\n\nThis store can optionally perform semantic search. If you omit `index`,\nthe store will just handle traditional (non-embedded) data without vector lookups.",
+      "type": "object",
+      "properties": {
+        "index": {
+          "anyOf": [
+            {
+              "$ref": "#/$defs/IndexConfig"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "description": "Optional. Defines the vector-based semantic search configuration.\n\n- Generate embeddings according to `index.embed`\n- Enforce the embedding dimension given by `index.dims`\n- Embed only specified JSON fields (if any) from `index.fields`\n\nIf omitted, no vector index is initialized.\n"
+        },
+        "ttl": {
+          "anyOf": [
+            {
+              "$ref": "#/$defs/TTLConfig"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "description": "Optional. Defines the TTL (time-to-live) behavior configuration.\n\nIf provided, the store will apply TTL settings according to the configuration.\nIf omitted, no TTL behavior is configured.\n"
+        }
+      },
+      "required": []
+    },
+    "IndexConfig": {
+      "title": "IndexConfig",
+      "description": "Configuration for indexing documents for semantic search in the store.\n\nThis governs how text is converted into embeddings and stored for vector-based lookups.",
+      "type": "object",
+      "properties": {
+        "dims": {
+          "type": "integer",
+          "description": "Required. Dimensionality of the embedding vectors you will store.\n\nMust match the output dimension of your selected embedding model or custom embed function.\nIf mismatched, you will likely encounter shape/size errors when inserting or querying vectors.\n\n"
+        },
+        "embed": {
+          "type": "string",
+          "description": "Required. Identifier or reference to the embedding model or a custom embedding function.\n\n- \"my_custom_embed\" if it's a known alias in your system\n"
+        },
+        "fields": {
+          "anyOf": [
+            {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "description": "Optional. List of JSON fields to extract before generating embeddings.\n\nDefaults to [\"$\"], which means the entire JSON object is embedded as one piece of text.\nIf you provide multiple fields (e.g. [\"title\", \"content\"]), each is extracted and embedded separately,\noften saving token usage if you only care about certain parts of the data.\n"
+        }
+      },
+      "required": []
+    },
+    "TTLConfig": {
+      "title": "TTLConfig",
+      "description": "Configuration for TTL (time-to-live) behavior in the store.",
+      "type": "object",
+      "properties": {
+        "default_ttl": {
+          "anyOf": [
+            {
+              "type": "number"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "refresh_on_read": {
+          "type": "boolean"
+        },
+        "sweep_interval_minutes": {
+          "anyOf": [
+            {
+              "type": "integer"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        }
+      },
+      "required": []
+    }
+  },
+  "title": "LangGraph CLI Configuration",
+  "description": "Configuration schema for langgraph-cli",
+  "version": "v0"
+}

libs/cli/schemas/schema.v0.json

@@ -0,0 +1,480 @@
+{
+  "$ref": "#/$defs/Config",
+  "$defs": {
+    "Config": {
+      "title": "Config",
+      "description": "Top-level config for langgraph-cli or similar deployment tooling.",
+      "type": "object",
+      "required": [],
+      "oneOf": [
+        {
+          "type": "object",
+          "properties": {
+            "python_version": {
+              "type": "string",
+              "description": "Optional. Python version in 'major.minor' format (e.g. '3.11').\nMust be at least 3.11 or greater for this deployment to function properly.\n",
+              "enum": [
+                "3.11",
+                "3.12"
+              ]
+            },
+            "pip_config_file": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Optional. Path to a pip config file (e.g., \"/etc/pip.conf\" or \"pip.ini\") for controlling\npackage installation (custom indices, credentials, etc.).\n\nOnly relevant if Python dependencies are installed via pip. If omitted, default pip settings are used.\n"
+            },
+            "auth": {
+              "anyOf": [
+                {
+                  "$ref": "#/$defs/AuthConfig"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Optional. Custom authentication config, including the path to your Python auth logic and\nthe OpenAPI security definitions it uses.\n"
+            },
+            "dependencies": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              },
+              "description": "List of Python dependencies to install, either from PyPI or local paths.\n"
+            },
+            "dockerfile_lines": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              },
+              "description": "Optional. Additional Docker instructions that will be appended to your base Dockerfile.\n\nUseful for installing OS packages, setting environment variables, etc."
+            },
+            "env": {
+              "anyOf": [
+                {
+                  "type": "object",
+                  "additionalProperties": {
+                    "type": "string"
+                  }
+                },
+                {
+                  "type": "string"
+                }
+              ],
+              "description": "Optional. Environment variables to set for your deployment.\n\n- If given as a dict, keys are variable names and values are their values.\n- If given as a string, it must be a path to a file containing lines in KEY=VALUE format.\n\nenv=\".env\n"
+            },
+            "graphs": {
+              "type": "object",
+              "additionalProperties": {
+                "type": "string"
+              },
+              "description": "Optional. Named definitions of graphs, each pointing to a Python object.\n\n\nGraphs can be StateGraph, @entrypoint, or any other Pregel object OR they can point to (async) context\nmanagers that accept a single configuration argument (of type RunnableConfig) and return a pregel object\n(instance of Stategraph, etc.).\n"
+            },
+            "http": {
+              "anyOf": [
+                {
+                  "$ref": "#/$defs/HttpConfig"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Optional. Configuration for the built-in HTTP server, controlling which custom routes are exposed\nand how cross-origin requests are handled.\n"
+            },
+            "store": {
+              "anyOf": [
+                {
+                  "$ref": "#/$defs/StoreConfig"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Optional. Configuration for the built-in long-term memory store, including semantic search indexing.\n\nIf omitted, no vector index is set up (the object store will still be present, however).\n"
+            },
+            "ui": {
+              "anyOf": [
+                {
+                  "type": "object",
+                  "additionalProperties": {
+                    "type": "string"
+                  }
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Optional. Named definitions of UI components emitted by the agent, each pointing to a JS/TS file.\n"
+            }
+          },
+          "required": [
+            "dependencies",
+            "graphs"
+          ]
+        },
+        {
+          "type": "object",
+          "properties": {
+            "node_version": {
+              "anyOf": [
+                {
+                  "type": "string",
+                  "enum": [
+                    "20"
+                  ]
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Optional. Node.js version as a major version (e.g. '20'), if your deployment needs Node.\nMust be >= 20 if provided.\n"
+            },
+            "auth": {
+              "anyOf": [
+                {
+                  "$ref": "#/$defs/AuthConfig"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Optional. Custom authentication config, including the path to your Python auth logic and\nthe OpenAPI security definitions it uses.\n"
+            },
+            "dependencies": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              },
+              "description": "List of Python dependencies to install, either from PyPI or local paths.\n"
+            },
+            "dockerfile_lines": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              },
+              "description": "Optional. Additional Docker instructions that will be appended to your base Dockerfile.\n\nUseful for installing OS packages, setting environment variables, etc."
+            },
+            "env": {
+              "anyOf": [
+                {
+                  "type": "object",
+                  "additionalProperties": {
+                    "type": "string"
+                  }
+                },
+                {
+                  "type": "string"
+                }
+              ],
+              "description": "Optional. Environment variables to set for your deployment.\n\n- If given as a dict, keys are variable names and values are their values.\n- If given as a string, it must be a path to a file containing lines in KEY=VALUE format.\n\nenv=\".env\n"
+            },
+            "graphs": {
+              "type": "object",
+              "additionalProperties": {
+                "type": "string"
+              },
+              "description": "Optional. Named definitions of graphs, each pointing to a Python object.\n\n\nGraphs can be StateGraph, @entrypoint, or any other Pregel object OR they can point to (async) context\nmanagers that accept a single configuration argument (of type RunnableConfig) and return a pregel object\n(instance of Stategraph, etc.).\n"
+            },
+            "http": {
+              "anyOf": [
+                {
+                  "$ref": "#/$defs/HttpConfig"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Optional. Configuration for the built-in HTTP server, controlling which custom routes are exposed\nand how cross-origin requests are handled.\n"
+            },
+            "store": {
+              "anyOf": [
+                {
+                  "$ref": "#/$defs/StoreConfig"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Optional. Configuration for the built-in long-term memory store, including semantic search indexing.\n\nIf omitted, no vector index is set up (the object store will still be present, however).\n"
+            },
+            "ui": {
+              "anyOf": [
+                {
+                  "type": "object",
+                  "additionalProperties": {
+                    "type": "string"
+                  }
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Optional. Named definitions of UI components emitted by the agent, each pointing to a JS/TS file.\n"
+            }
+          },
+          "required": [
+            "node_version",
+            "graphs"
+          ]
+        }
+      ]
+    },
+    "AuthConfig": {
+      "title": "AuthConfig",
+      "description": "Configuration for custom authentication logic and how it integrates into the OpenAPI spec.",
+      "type": "object",
+      "properties": {
+        "disable_studio_auth": {
+          "type": "boolean",
+          "description": "Optional. Whether to disable LangSmith API-key authentication for requests originating the Studio.\n\nDefaults to False, meaning that if a particular header is set, the server will verify the `x-api-key` header\nvalue is a valid API key for the deployment's workspace. If True, all requests will go through your custom\nauthentication logic, regardless of origin of the request.\n"
+        },
+        "openapi": {
+          "$ref": "#/$defs/SecurityConfig",
+          "description": "Required. Detailed security configuration that merges into your deployment's OpenAPI spec.\n\n{\n}\n}\n}\n},\n]\n}\n"
+        },
+        "path": {
+          "type": "string",
+          "description": "Required. Path to an instance of the Auth() class that implements custom authentication.\n"
+        }
+      },
+      "required": []
+    },
+    "SecurityConfig": {
+      "title": "SecurityConfig",
+      "description": "Configuration for OpenAPI security definitions and requirements.\n\nUseful for specifying global or path-level authentication and authorization flows\n(e.g., OAuth2, API key headers, etc.).",
+      "type": "object",
+      "properties": {
+        "paths": {
+          "type": "object",
+          "additionalProperties": {
+            "type": "object",
+            "additionalProperties": {
+              "type": "array",
+              "items": {
+                "type": "object",
+                "additionalProperties": {
+                  "type": "array",
+                  "items": {
+                    "type": "string"
+                  }
+                }
+              }
+            }
+          },
+          "description": "Optional. Path-specific security overrides.\n\n- Keys that are HTTP methods (e.g., \"GET\", \"POST\"),\n- Values are lists of security definitions (just like `security`) for that method.\n"
+        },
+        "security": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "additionalProperties": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          "description": "Optional. Global security requirements across all endpoints.\n\nEach element in the list maps a security scheme (e.g. \"OAuth2\") to a list of scopes (e.g. [\"read\", \"write\"])."
+        },
+        "securitySchemes": {
+          "type": "object",
+          "additionalProperties": {
+            "type": "object"
+          },
+          "description": "Required. Dict describing each security scheme recognized by your OpenAPI spec.\n\nKeys are scheme names (e.g. \"OAuth2\", \"ApiKeyAuth\") and values are their definitions."
+        }
+      },
+      "required": []
+    },
+    "HttpConfig": {
+      "title": "HttpConfig",
+      "description": "Configuration for the built-in HTTP server that powers your deployment's routes and endpoints.",
+      "type": "object",
+      "properties": {
+        "app": {
+          "type": "string",
+          "description": "Optional. Import path to a custom Starlette/FastAPI application to mount.\n"
+        },
+        "cors": {
+          "anyOf": [
+            {
+              "$ref": "#/$defs/CorsConfig"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "description": "Optional. Defines CORS restrictions. If omitted, no special rules are set and\ncross-origin behavior depends on default server settings.\n"
+        },
+        "disable_assistants": {
+          "type": "boolean",
+          "description": "Optional. If True, /assistants routes are removed from the server.\n\nDefault is False (meaning /assistants is enabled).\n"
+        },
+        "disable_meta": {
+          "type": "boolean",
+          "description": "Optional. If True, all meta endpoints (/ok, /info, /metrics, /docs) are disabled.\n\nDefault is False.\n"
+        },
+        "disable_runs": {
+          "type": "boolean",
+          "description": "Optional. If True, /runs routes are removed.\n\nDefault is False.\n"
+        },
+        "disable_store": {
+          "type": "boolean",
+          "description": "Optional. If True, /store routes are removed, disabling direct store interactions via HTTP.\n\nDefault is False.\n"
+        },
+        "disable_threads": {
+          "type": "boolean",
+          "description": "Optional. If True, /threads routes are removed.\n\nDefault is False.\n"
+        }
+      },
+      "required": []
+    },
+    "CorsConfig": {
+      "title": "CorsConfig",
+      "description": "Specifies Cross-Origin Resource Sharing (CORS) rules for your server.\n\nIf omitted, defaults are typically very restrictive (often no cross-origin requests).\nConfigure carefully if you want to allow usage from browsers hosted on other domains.",
+      "type": "object",
+      "properties": {
+        "allow_credentials": {
+          "type": "boolean",
+          "description": "Optional. If True, cross-origin requests can include credentials (cookies, auth headers).\n\nDefault False to avoid accidentally exposing secured endpoints to untrusted sites.\n"
+        },
+        "allow_headers": {
+          "type": "array",
+          "items": {
+            "type": "string"
+          },
+          "description": "Optional. HTTP headers that can be used in cross-origin requests (e.g. [\"Content-Type\", \"Authorization\"])."
+        },
+        "allow_methods": {
+          "type": "array",
+          "items": {
+            "type": "string"
+          },
+          "description": "Optional. HTTP methods permitted for cross-origin requests (e.g. [\"GET\", \"POST\"]).\n\nDefault might be [\"GET\", \"POST\", \"OPTIONS\"] depending on your server framework.\n"
+        },
+        "allow_origin_regex": {
+          "type": "string",
+          "description": "Optional. A regex pattern for matching allowed origins, used if you have dynamic subdomains.\n"
+        },
+        "allow_origins": {
+          "type": "array",
+          "items": {
+            "type": "string"
+          },
+          "description": "Optional. List of allowed origins (e.g., \"https://example.com\").\n\nDefault is often an empty list (no external origins).\nUse \"*\" only if you trust all origins, as that bypasses most restrictions.\n"
+        },
+        "expose_headers": {
+          "type": "array",
+          "items": {
+            "type": "string"
+          },
+          "description": "Optional. List of headers that browsers are allowed to read from the response in cross-origin contexts."
+        },
+        "max_age": {
+          "type": "integer",
+          "description": "Optional. How many seconds the browser may cache preflight responses.\n\nDefault might be 600 (10 minutes). Larger values reduce preflight requests but can cause stale configurations.\n"
+        }
+      },
+      "required": []
+    },
+    "StoreConfig": {
+      "title": "StoreConfig",
+      "description": "Configuration for the built-in long-term memory store.\n\nThis store can optionally perform semantic search. If you omit `index`,\nthe store will just handle traditional (non-embedded) data without vector lookups.",
+      "type": "object",
+      "properties": {
+        "index": {
+          "anyOf": [
+            {
+              "$ref": "#/$defs/IndexConfig"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "description": "Optional. Defines the vector-based semantic search configuration.\n\n- Generate embeddings according to `index.embed`\n- Enforce the embedding dimension given by `index.dims`\n- Embed only specified JSON fields (if any) from `index.fields`\n\nIf omitted, no vector index is initialized.\n"
+        },
+        "ttl": {
+          "anyOf": [
+            {
+              "$ref": "#/$defs/TTLConfig"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "description": "Optional. Defines the TTL (time-to-live) behavior configuration.\n\nIf provided, the store will apply TTL settings according to the configuration.\nIf omitted, no TTL behavior is configured.\n"
+        }
+      },
+      "required": []
+    },
+    "IndexConfig": {
+      "title": "IndexConfig",
+      "description": "Configuration for indexing documents for semantic search in the store.\n\nThis governs how text is converted into embeddings and stored for vector-based lookups.",
+      "type": "object",
+      "properties": {
+        "dims": {
+          "type": "integer",
+          "description": "Required. Dimensionality of the embedding vectors you will store.\n\nMust match the output dimension of your selected embedding model or custom embed function.\nIf mismatched, you will likely encounter shape/size errors when inserting or querying vectors.\n\n"
+        },
+        "embed": {
+          "type": "string",
+          "description": "Required. Identifier or reference to the embedding model or a custom embedding function.\n\n- \"my_custom_embed\" if it's a known alias in your system\n"
+        },
+        "fields": {
+          "anyOf": [
+            {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "description": "Optional. List of JSON fields to extract before generating embeddings.\n\nDefaults to [\"$\"], which means the entire JSON object is embedded as one piece of text.\nIf you provide multiple fields (e.g. [\"title\", \"content\"]), each is extracted and embedded separately,\noften saving token usage if you only care about certain parts of the data.\n"
+        }
+      },
+      "required": []
+    },
+    "TTLConfig": {
+      "title": "TTLConfig",
+      "description": "Configuration for TTL (time-to-live) behavior in the store.",
+      "type": "object",
+      "properties": {
+        "default_ttl": {
+          "anyOf": [
+            {
+              "type": "number"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "refresh_on_read": {
+          "type": "boolean"
+        },
+        "sweep_interval_minutes": {
+          "anyOf": [
+            {
+              "type": "integer"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        }
+      },
+      "required": []
+    }
+  },
+  "title": "LangGraph CLI Configuration",
+  "description": "Configuration schema for langgraph-cli",
+  "version": "v0"
+}

libs/cli/tests/unit_tests/test_config.py

@@ -33,6 +33,7 @@ def test_validate_config():
         "store": None,
         "auth": None,
         "http": None,
+        "ui": None,
         **expected_config,
     }
     actual_config = validate_config(expected_config)
@@ -52,6 +53,7 @@ def test_validate_config():
         "store": None,
         "auth": None,
         "http": None,
+        "ui": None,
     }
     actual_config = validate_config(expected_config)
     assert actual_config == expected_config
@@ -467,6 +469,7 @@ def test_config_to_docker_nodejs():
                 "node_version": "20",
                 "graphs": graphs,
                 "dockerfile_lines": ["ARG meow", "ARG foo"],
+                "ui": {"agent": "./graphs/agent.ui.jsx"},
             }
         ),
         "langchain/langgraphjs-api",
@@ -477,6 +480,7 @@ ARG foo
 ADD . /deps/unit_tests
 RUN cd /deps/unit_tests && npm i
 ENV LANGSERVE_GRAPHS='{"agent": "./graphs/agent.js:graph"}'
+ENV LANGGRAPH_UI='{"agent": "./graphs/agent.ui.jsx"}'
 WORKDIR /deps/unit_tests
 RUN (test ! -f /api/langgraph_api/js/build.mts && echo "Prebuild script not found, skipping") || tsx /api/langgraph_api/js/build.mts"""