Merge branch 'sr/perms-for-pr' of https://github.com/langchain-ai/langgraph into sr/perms-for-pr

update lockfiles / deps bounds

.github/ISSUE_TEMPLATE/config.yml

@@ -10,6 +10,6 @@ contact_links:
   - name: Show and tell
     about: Show what you built with LangChain
     url: https://github.com/langchain-ai/langgraph/discussions/categories/show-and-tell
-  - name: Slack
-    url:  https://www.langchain.com/join-community
-    about: General community discussions
+  - name: LangChain Forum
+    url:  https://forum.langchain.com/
+    about: General community discussions and support

.github/dependabot.yml

@@ -1,11 +1,18 @@
-# Please see the documentation for all configuration options:
-# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
-# and
-# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
-
 version: 2
 updates:
   - package-ecosystem: "github-actions"
     directory: "/"
     schedule:
       interval: "weekly"
+
+  - package-ecosystem: "pip"
+    directories:
+      - "libs/checkpoint"
+      - "libs/checkpoint-postgres"
+      - "libs/checkpoint-sqlite"
+      - "libs/cli"
+      - "libs/langgraph"
+      - "libs/prebuilt"
+      - "libs/sdk-py"
+    schedule:
+      interval: "weekly"

.github/workflows/ci.yml

@@ -22,6 +22,7 @@ jobs:
     outputs:
       python: ${{ steps.filter.outputs.python }}
       sdk-js: ${{ steps.filter.outputs.sdk-js }}
+      deps: ${{ steps.filter.outputs.deps }}
     steps:
       - uses: actions/checkout@v4
       - uses: dorny/paths-filter@v3
@@ -38,6 +39,9 @@ jobs:
               - 'libs/prebuilt/**'
             sdk-js:
               - 'libs/sdk-js/**'
+            deps:
+              - '**/pyproject.toml'
+              - '**/uv.lock'
 
   lint:
     needs: changes
@@ -55,7 +59,7 @@ jobs:
 
             "libs/prebuilt",
           ]
-    if: needs.changes.outputs.python == 'true'
+    if: needs.changes.outputs.python == 'true' || needs.changes.outputs.deps == 'true'
     uses: ./.github/workflows/_lint.yml
     with:
       working-directory: ${{ matrix.working-directory }}
@@ -74,7 +78,7 @@ jobs:
             "libs/checkpoint-postgres",
             "libs/prebuilt",
           ]
-    if: needs.changes.outputs.python == 'true'
+    if: needs.changes.outputs.python == 'true' || needs.changes.outputs.deps == 'true'
     uses: ./.github/workflows/_test.yml
     with:
       working-directory: ${{ matrix.working-directory }}
@@ -83,7 +87,7 @@ jobs:
   # NOTE: we're testing langgraph separately because it requires a different matrix
   test-langgraph:
     needs: changes
-    if: needs.changes.outputs.python == 'true'
+    if: needs.changes.outputs.python == 'true' || needs.changes.outputs.deps == 'true'
     name: "cd libs/langgraph"
     uses: ./.github/workflows/_test_langgraph.yml
     secrets: inherit
@@ -140,7 +144,7 @@ jobs:
 
   integration-test:
     needs: changes
-    if: needs.changes.outputs.python == 'true'
+    if: needs.changes.outputs.python == 'true' || needs.changes.outputs.deps == 'true'
     name: CLI integration test
     uses: ./.github/workflows/_integration_test.yml
     secrets: inherit

.github/workflows/uv_lock_ugprade.yml

@@ -0,0 +1,49 @@
+name: lockfile upgrades
+
+on:
+  schedule:
+    # run at midnight every Sunday
+    - cron: '0 0 * * 0'
+  # allow manual triggering
+  workflow_dispatch:
+  pull_request:
+    branches:
+      - main
+
+permissions:
+  contents: write
+  pull-requests: write
+
+jobs:
+  upgrade-dependencies:
+    runs-on: ubuntu-latest
+    
+    steps:
+      - uses: actions/checkout@v4
+      
+      - name: Set up uv
+        uses: astral-sh/setup-uv@v6
+        with:
+          # use minimum supported Python version
+          python-version: "3.9"
+          enable-cache: true
+          cache-suffix: "uv-lock-upgrade"
+          
+      - name: Run uv lock --upgrade in all Python packages
+        run: make lock-upgrade
+          
+      - name: Create Pull Request
+        uses: peter-evans/create-pull-request@v6
+        with:
+          token: ${{ secrets.LANGGRAPH_WRITE_TOKEN }}
+          commit-message: "chore: upgrade dependencies with `uv lock --upgrade`"
+          title: "chore: upgrade dependencies with `uv lock --upgrade`"
+          body: |
+            This PR updates the dependencies in all Python packages using `uv lock --upgrade`.
+            
+            This is an automated PR created by the "lockfile upgrades" workflow.
+          branch: deps/uv-lock-upgrade
+          base: main
+          delete-branch: true
+          labels: |
+            dependencies

Makefile

@@ -47,6 +47,16 @@ lock:
 		fi; \
 	done
 
+# Lock all projects and upgrade dependencies
+.PHONY: lock-upgrade
+lock-upgrade:
+	@for dir in $(LIBS_DIRS); do \
+		if [ -f $$dir/Makefile ]; then \
+			echo "Running lock-upgrade in $$dir"; \
+			(cd $$dir && uv lock --upgrade); \
+		fi; \
+	done
+
 # Test all projects
 .PHONY: test
 test:

README.md

@@ -63,7 +63,7 @@ LangGraph provides low-level supporting infrastructure for *any* long-running, s
 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/).
+- [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/).
 - [LangChain](https://python.langchain.com/docs/introduction/) – Provides integrations and composable components to streamline LLM application development.
 
 > [!NOTE]

docs/_scripts/notebook_hooks.py

@@ -100,9 +100,9 @@ REDIRECT_MAP = {
     "how-tos/create-react-agent-system-prompt.ipynb": "agents/context.md#prompts",
     "how-tos/create-react-agent-structured-output.ipynb": "agents/agents.md#structured-output",
     # Time-travel
-    "how-tos/human_in_the_loop/edit-graph-state.ipynb": "how-tos/human_in_the_loop/time-travel.ipynb",
+    "how-tos/human_in_the_loop/edit-graph-state.ipynb": "how-tos/human_in_the_loop/time-travel.md",
     # breakpoints
-    "how-tos/human_in_the_loop/dynamic_breakpoints.ipynb": "how-tos/human_in_the_loop/breakpoints.ipynb",
+    "how-tos/human_in_the_loop/dynamic_breakpoints.ipynb": "how-tos/human_in_the_loop/breakpoints.md",
     # misc
     "prebuilt.md": "agents/prebuilt.md",
     "reference/prebuilt.md": "reference/agents.md",
@@ -111,6 +111,7 @@ REDIRECT_MAP = {
     "concepts/v0-human-in-the-loop.md": "concepts/human-in-the-loop.md",
     "how-tos/index.md": "index.md",
     "tutorials/introduction.ipynb": "concepts/why-langgraph.md",
+    "agents/deployment.md": "tutorials/langgraph-platform/local-server.md",
     # deployment redirects
     "how-tos/deploy-self-hosted.md": "cloud/deployment/self_hosted_data_plane.md",
     "concepts/self_hosted.md": "concepts/langgraph_self_hosted_data_plane.md",

docs/docs/agents/context.md

@@ -1,17 +1,8 @@
----
-search:
-  boost: 2
-tags:
-  - agent
-hide:
-  - tags
----
-
 # Context
 
-Agents often require more than a list of messages to function effectively. They need **context**.
+**Context engineering** is the practice of building dynamic systems that provide the right information and tools, in the right format, so that a language model can plausibly accomplish a task.
 
-Context includes *any* data outside the message list that can shape agent behavior or tool execution. This can be:
+Context includes *any* data outside the message list that can shape behavior. This can be:
 
 - Information passed at runtime, like a `user_id` or API credentials.
 - Internal state updated during a multi-step reasoning process.
@@ -22,18 +13,10 @@ LangGraph provides **three** primary ways to supply context:
 | Type                                                                         | Description                                   | Mutable? | Lifetime                |
 |------------------------------------------------------------------------------|-----------------------------------------------|----------|-------------------------|
 | [**Config**](#config-static-context)                                         | data passed at the start of a run             | ❌        | per run                 |
-| [**State**](#state-mutable-context)                                          | dynamic data that can change during execution | ✅        | per run or conversation |
-| [**Long-term Memory (Store)**](#long-term-memory-cross-conversation-context) | data that can be shared between conversations | ✅        | across conversations    |
+| [**Short-term memory (State)**](#short-term-memory-mutable-context)          | dynamic data that can change during execution | ✅        | per run or conversation |
+| [**Long-term memory (Store)**](#long-term-memory-cross-conversation-context) | data that can be shared between conversations | ✅        | across conversations    |
 
-You can use context to:
-
-- Adjust the system prompt the model sees
-- Feed tools with necessary inputs
-- Track facts during an ongoing conversation
-
-## Providing Runtime Context
-
-Use this when you need to inject data into an agent at runtime.
+## Provide runtime context
 
 ### Config (static context)
 
@@ -44,88 +27,83 @@ Specify configuration using a key called **"configurable"** which is reserved
 for this purpose:
 
 ```python
-agent.invoke(
-    {"messages": [{"role": "user", "content": "hi!"}]},
+graph.invoke( # (1)!
+    {"messages": [{"role": "user", "content": "hi!"}]}, # (2)!
     # highlight-next-line
-    config={"configurable": {"user_id": "user_123"}}
+    config={"configurable": {"user_id": "user_123"}} # (3)!
 )
 ```
 
-### State (mutable context)
+1. This is the invocation of the agent or graph. The `invoke` method runs the underlying graph with the provided input.
+2. This example uses messages as an input, which is common, but your application may use different input structures.
+3. This is where you pass the configuration data. The `config` parameter allows you to provide additional context that the agent can use during its execution.
 
-State acts as short-term memory during a run. It holds dynamic data that can evolve during execution, such as values derived from tools or LLM outputs.
-
-```python
-class CustomState(AgentState):
-    # highlight-next-line
-    user_name: str
-
-agent = create_react_agent(
-    # Other agent parameters...
-    # highlight-next-line
-    state_schema=CustomState,
-)
-
-agent.invoke({
-    "messages": "hi!",
-    "user_name": "Jane"
-})
-```
-
-!!! tip "Turning on memory"
-
-    Please see the [memory guide](../how-tos/memory/add-memory.md) for more details on how to enable memory. This is a powerful feature that allows you to persist the agent's state across multiple invocations.
-    Otherwise, the state is scoped only to a single agent run.
-
-
-
-### Long-Term Memory (cross-conversation context)
-
-For context that spans *across* conversations or sessions, LangGraph allows access to **long-term memory** via a `store`. This can be used to read or update persistent facts (e.g., user profiles, preferences, prior interactions). For more, see the [Memory guide](../how-tos/memory/add-memory.md).
-
-## Customizing Prompts with Context { #prompts }
-
-Prompts define how the agent behaves. To incorporate runtime context, you can dynamically generate prompts based on the agent's state or config.
-
-Common use cases:
-
-- Personalization
-- Role or goal customization
-- Conditional behavior (e.g., user is admin)
-
-=== "Using config"
+=== "Agent prompt"
 
     ```python
     from langchain_core.messages import AnyMessage
     from langchain_core.runnables import RunnableConfig
-    from langgraph.prebuilt import create_react_agent
     from langgraph.prebuilt.chat_agent_executor import AgentState
+    from langgraph.prebuilt import create_react_agent
 
-    def prompt(
-        state: AgentState,
-        # highlight-next-line
-        config: RunnableConfig,
-    ) -> list[AnyMessage]:
-        # highlight-next-line
+    # highlight-next-line
+    def prompt(state: AgentState, config: RunnableConfig) -> list[AnyMessage]:
         user_name = config["configurable"].get("user_name")
-        system_msg = f"You are a helpful assistant. User's name is {user_name}"
+        system_msg = f"You are a helpful assistant. Address the user as {user_name}."
         return [{"role": "system", "content": system_msg}] + state["messages"]
 
     agent = create_react_agent(
         model="anthropic:claude-3-7-sonnet-latest",
         tools=[get_weather],
-        # highlight-next-line
         prompt=prompt
     )
 
     agent.invoke(
-        ...,
+        {"messages": [{"role": "user", "content": "what is the weather in sf"}]},
         # highlight-next-line
         config={"configurable": {"user_name": "John Smith"}}
     )
     ```
 
-=== "Using state"
+    * See [Agents](../agents/agents.md) for details.
+
+=== "Workflow node"
+
+    ```python
+    from langchain_core.runnables import RunnableConfig
+
+    # highlight-next-line
+    def node(state: State, config: RunnableConfig):
+        user_name = config["configurable"].get("user_name")
+        ...
+    ```
+
+    * See [the Graph API](https://langchain-ai.github.io/langgraph/how-tos/graph-api/#add-runtime-configuration) for details.
+
+=== "In a tool"
+
+    ```python
+    from langchain_core.runnables import RunnableConfig
+
+    @tool
+    # highlight-next-line
+    def get_user_info(config: RunnableConfig) -> str:
+        """Retrieve user information based on user ID."""
+        user_id = config["configurable"].get("user_id")
+        return "User is John Smith" if user_id == "user_123" else "Unknown user"
+    ```
+
+    See the [tool calling guide](../how-tos/tool-calling.md#configuration) for details.
+
+### Short-term memory (mutable context)
+
+State acts as [short-term memory](../concepts/memory.md) during a run. It holds dynamic data that can evolve during execution, such as values derived from tools or LLM outputs.
+
+=== "In an agent"
+
+    Example shows how to incorporate state into an agent **prompt**.
+
+    State can also be accessed by the agent's **tools**, which can read or update the state as needed. See [tool calling guide](../how-tos/tool-calling.md#short-term-memory) for details.
 
     ```python
     from langchain_core.messages import AnyMessage
@@ -133,15 +111,14 @@ Common use cases:
     from langgraph.prebuilt import create_react_agent
     from langgraph.prebuilt.chat_agent_executor import AgentState
 
-    class CustomState(AgentState):
-        # highlight-next-line
+    # highlight-next-line
+    class CustomState(AgentState): # (1)!
         user_name: str
 
     def prompt(
         # highlight-next-line
         state: CustomState
     ) -> list[AnyMessage]:
-        # highlight-next-line
         user_name = state["user_name"]
         system_msg = f"You are a helpful assistant. User's name is {user_name}"
         return [{"role": "system", "content": system_msg}] + state["messages"]
@@ -150,87 +127,58 @@ Common use cases:
         model="anthropic:claude-3-7-sonnet-latest",
         tools=[...],
         # highlight-next-line
-        state_schema=CustomState,
-        # highlight-next-line
+        state_schema=CustomState, # (2)!
         prompt=prompt
     )
 
     agent.invoke({
         "messages": "hi!",
-        # highlight-next-line
         "user_name": "John Smith"
     })
     ```
 
-## Accessing Context in Tools { #tools }
-
-Tools can access context through special parameter **annotations**.
-
-* Use `RunnableConfig` for config access
-* Use `Annotated[StateSchema, InjectedState]` for agent state
+    1. Define a custom state schema that extends `AgentState` or `MessagesState`.
+    2. Pass the custom state schema to the agent. This allows the agent to access and modify the state during execution.
 
 
-!!! tip 
-
-    These annotations prevent LLMs from attempting to fill in the values. These parameters will be **hidden** from the LLM.
-
-=== "Using config"
+=== "In a workflow"
 
     ```python
-    def get_user_info(
-        # highlight-next-line
-        config: RunnableConfig,
-    ) -> str:
-        """Look up user info."""
-        # highlight-next-line
-        user_id = config["configurable"].get("user_id")
-        return "User is John Smith" if user_id == "user_123" else "Unknown user"
+    from typing_extensions import TypedDict
+    from langchain_core.messages import AnyMessage
+    from langgraph.graph import StateGraph
 
-    agent = create_react_agent(
-        model="anthropic:claude-3-7-sonnet-latest",
-        tools=[get_user_info],
-    )
+    # highlight-next-line
+    class CustomState(TypedDict): # (1)!
+        messages: list[AnyMessage]
+        extra_field: int
 
-    agent.invoke(
-        {"messages": [{"role": "user", "content": "look up user information"}]},
-        # highlight-next-line
-        config={"configurable": {"user_id": "user_123"}}
-    )
+    # highlight-next-line
+    def node(state: CustomState): # (2)!
+        messages = state["messages"]
+        ...
+        return { # (3)!
+            # highlight-next-line
+            "extra_field": state["extra_field"] + 1
+        }
+
+    builder = StateGraph(State)
+    builder.add_node(node)
+    builder.set_entry_point("node")
+    graph = builder.compile()
     ```
+    
+    1. Define a custom state
+    2. Access the state in any node or tool
+    3. The Graph API is designed to work as easily as possible with state. The return value of a node represents a requested update to the state.
 
-=== "Using State"
 
-    ```python
-    from typing import Annotated
-    from langgraph.prebuilt import InjectedState
+!!! tip "Turning on memory"
 
-    class CustomState(AgentState):
-        # highlight-next-line
-        user_id: str
+    Please see the [memory guide](../how-tos/memory/add-memory.md) for more details on how to enable memory. This is a powerful feature that allows you to persist the agent's state across multiple invocations. Otherwise, the state is scoped only to a single run.
 
-    def get_user_info(
-        # highlight-next-line
-        state: Annotated[CustomState, InjectedState]
-    ) -> str:
-        """Look up user info."""
-        # highlight-next-line
-        user_id = state["user_id"]
-        return "User is John Smith" if user_id == "user_123" else "Unknown user"
+### Long-term memory (cross-conversation context)
 
-    agent = create_react_agent(
-        model="anthropic:claude-3-7-sonnet-latest",
-        tools=[get_user_info],
-        # highlight-next-line
-        state_schema=CustomState,
-    )
+For context that spans *across* conversations or sessions, LangGraph allows access to **long-term memory** via a `store`. This can be used to read or update persistent facts (e.g., user profiles, preferences, prior interactions). 
 
-    agent.invoke({
-        "messages": "look up user information",
-        # highlight-next-line
-        "user_id": "user_123"
-    })
-    ```
-
-### Update Context from Tools
-
-Tools can update agent's context (state and long-term memory) during execution. This is useful for persisting intermediate results or making information accessible to subsequent tools or prompts. See [Memory](../how-tos/memory/add-memory.md#read-short-term) guide for more information.
+For more information, see the [Memory guide](../how-tos/memory/add-memory.md).

docs/docs/agents/deployment.md

@@ -1,92 +0,0 @@
----
-search:
-  boost: 2
-tags:
-  - agent
-hide:
-  - tags
----
-
-# Deployment
-
-To deploy your LangGraph agent, create and configure a LangGraph app. This setup supports both local development and production deployments.
-
-Features: 
-
-* 🖥️ Local server for development
-* 🧩 Studio Web UI for visual debugging
-* ☁️ Cloud and 🔧 self-hosted deployment options
-* 📊 LangSmith integration for tracing and observability
-
-!!! info "Requirements" 
-
-    - ✅ You **must** have a [LangSmith account](https://www.langchain.com/langsmith). You can sign up for **free** and get started with the free tier.
-
-## Create a LangGraph app
-
-```bash
-pip install -U "langgraph-cli[inmem]"
-langgraph new path/to/your/app --template new-langgraph-project-python
-```
-
-This will create an empty LangGraph project. You can modify it by replacing the code in `src/agent/graph.py` with your agent code. For example:
-
-```python
-from langgraph.prebuilt import create_react_agent
-
-def get_weather(city: str) -> str:
-    """Get weather for a given city."""
-    return f"It's always sunny in {city}!"
-
-graph = create_react_agent(
-    model="anthropic:claude-3-7-sonnet-latest",
-    tools=[get_weather],
-    prompt="You are a helpful assistant"
-)
-```
-
-### Install dependencies
-
-In the root of your new LangGraph app, install the dependencies in `edit` mode so your local changes are used by the server:
-
-```shell
-pip install -e .
-```
-
-### Create an `.env` file
-
-You will find a `.env.example` in the root of your new LangGraph app. Create
-a `.env` file in the root of your new LangGraph app and copy the contents of the `.env.example` file into it, filling in the necessary API keys:
-
-```bash
-LANGSMITH_API_KEY=lsv2...
-ANTHROPIC_API_KEY=sk-
-```
-
-## Launch LangGraph server locally
-
-```shell
-langgraph dev
-```
-
-This will start up the LangGraph API server locally. If this runs successfully, you should see something like:
-
->    Ready!
-> 
->    - API: [http://localhost:2024](http://localhost:2024/)
->     
->    - Docs: http://localhost:2024/docs
->     
->    - LangGraph Studio Web UI: https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024
-
-See this [tutorial](https://langchain-ai.github.io/langgraph/tutorials/langgraph-platform/local-server/) to learn more about running LangGraph app locally.
-
-## LangGraph Studio Web UI
-
-LangGraph Studio Web is a specialized UI that you can connect to LangGraph API server to enable visualization, interaction, and debugging of your application locally. Test your graph in the LangGraph Studio Web UI by visiting the URL provided in the output of the `langgraph dev` command.
-
->    - LangGraph Studio Web UI: https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024
-
-## Deployment
-
-Once your LangGraph app is running locally, you can deploy it using LangGraph Platform. Refer to the [deployment options guide](../concepts/deployment_options.md) for detailed instructions on all supported deployment models.

docs/docs/agents/overview.md

@@ -8,9 +8,9 @@ hide:
   - tags
 ---
 
-# Agent development with LangGraph
+# Agent development using prebuilt components
 
-**LangGraph** provides both low-level primitives and high-level prebuilt components for building agent-based applications. This section focuses on the **prebuilt**, **reusable** components designed to help you construct agentic systems quickly and reliably—without the need to implement orchestration, memory, or human feedback handling from scratch.
+LangGraph provides both low-level primitives and high-level prebuilt components for building agent-based applications. This section focuses on the prebuilt, ready-to-use components designed to help you construct agentic systems quickly and reliably—without the need to implement orchestration, memory, or human feedback handling from scratch.
 
 ## What is an agent?
 

docs/docs/cloud/deployment/self_hosted_control_plane.md

@@ -3,7 +3,7 @@
 Before deploying, review the [conceptual guide for the Self-Hosted Control Plane](../../concepts/langgraph_self_hosted_control_plane.md) deployment option.
 
 !!! info "Important"
-    The Self-Hosted Control Plane deployment option is currently in beta stage and requires an [Enterprise](../../concepts/plans.md) plan.
+    The Self-Hosted Control Plane deployment option requires an [Enterprise](../../concepts/plans.md) plan.
 
 ## Prerequisites
 

docs/docs/cloud/deployment/self_hosted_data_plane.md

@@ -3,7 +3,7 @@
 Before deploying, review the [conceptual guide for the Self-Hosted Data Plane](../../concepts/langgraph_self_hosted_data_plane.md) deployment option.
 
 !!! info "Important"
-    The Self-Hosted Data Plane deployment option is currently in beta stage and requires an [Enterprise](../../concepts/plans.md) plan.
+    The Self-Hosted Data Plane deployment option requires an [Enterprise](../../concepts/plans.md) plan.
 
 ## Prerequisites
 
@@ -15,11 +15,15 @@ Before deploying, review the [conceptual guide for the Self-Hosted Data Plane](.
 ### Prerequisites
 1. `KEDA` is installed on your cluster.
 
-        helm repo add kedacore https://kedacore.github.io/charts 
+        helm repo add kedacore https://kedacore.github.io/charts
         helm install keda kedacore/keda --namespace keda --create-namespace
 
 1. A valid `Ingress` controller is installed on your cluster.
 1. You have slack space in your cluster for multiple deployments. `Cluster-Autoscaler` is recommended to automatically provision new nodes.
+1. You will need to enable egress to two control plane URLs. The listener polls these endpoints for deployments:
+
+        https://api.host.langchain.com
+        https://api.smith.langchain.com
 
 ### Setup
 

docs/docs/cloud/how-tos/add-human-in-the-loop.md

@@ -1,4 +1,4 @@
-# Human-in-the-loop in LangGraph Server
+# Human-in-the-loop using Server API
 
 To review, edit, and approve tool calls in an agent or workflow, use LangGraph's [human-in-the-loop](../../concepts/human_in_the_loop.md) features.
 

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

@@ -1,10 +1,16 @@
-# Breakpoints
+# Set breakpoints using Server API
 
 [Breakpoints](../../concepts/breakpoints.md) pause graph execution at defined points and let you step through each stage. They use LangGraph's [**persistence layer**](../../concepts/persistence.md), which saves the graph state after each step.
 
-With breakpoints, you can inspect the graph's state and node inputs at any point. Execution pauses **indefinitely** until you resume, as the checkpointer preserves the state.
+With breakpoints, you can inspect the graph's state and node inputs at any point. Execution pauses indefinitely until you resume, as the checkpointer preserves the state.
 
-## Set breakpoints
+!!! tip
+
+    For conceptual information on breakpoints, see [Breakpoints](../../concepts/breakpoints.md).
+
+## Set static breakpoints
+
+Static breakpoints are triggered either before or after a node executes. You can set static breakpoints by specifying `interrupt_before` and `interrupt_after` at compile time or run time.
 
 === "Compile time"
 
@@ -78,10 +84,9 @@ With breakpoints, you can inspect the graph's state and node inputs at any point
         }"
         ```
 
-!!! tip
-
-    This example shows how to add **static** breakpoints. See [this guide](../../how-tos/human_in_the_loop/breakpoints.ipynb) for more options for how to add breakpoints.
+## Example
 
+This example shows how to add **static** breakpoints. See [Use breakpoints](../../how-tos/human_in_the_loop/breakpoints.md) for more options on adding breakpoints.
 
 === "Python"
 
@@ -177,8 +182,4 @@ With breakpoints, you can inspect the graph's state and node inputs at any point
     --data "{
       \"assistant_id\": \"agent\"
     }"
-    ```
-
-## Learn more
-
-- [**LangGraph breakpoints guide**](../../how-tos/human_in_the_loop/breakpoints.ipynb): learn more about adding breakpoints in LangGraph.
+    ```

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

@@ -1,10 +1,8 @@
-# Time travel
+# Time travel using Server API
 
-LangGraph provides [**time travel**](../../concepts/time-travel.md) functionality to **resume execution from a prior checkpoint** — either replaying the same state or modifying it to explore alternatives. In all cases, resuming past execution produces a **new fork** in the history.
+LangGraph provides the [**time travel**](../../concepts/time-travel.md) functionality to resume execution from a prior checkpoint, either replaying the same state or modifying it to explore alternatives. In all cases, resuming past execution produces a new fork in the history.
 
-## Use time travel
-
-To use time-travel in LangGraph:
+To time travel using the LangGraph Server API (via the LangGraph SDK):
 
 1. **Run the graph** with initial inputs using [LangGraph SDK](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/python_sdk_ref/)'s [`client.runs.wait`][langgraph_sdk.client.RunsClient.wait] or [`client.runs.stream`][langgraph_sdk.client.RunsClient.stream] APIs.
 2. **Identify a checkpoint in an existing thread**: Use [`client.threads.get_history`][langgraph_sdk.client.ThreadsClient.get_history] method to retrieve the execution history for a specific `thread_id` and locate the desired `checkpoint_id`.
@@ -12,7 +10,7 @@ To use time-travel in LangGraph:
 3. **(Optional) modify the graph state**: Use the [`client.threads.update_state`][langgraph_sdk.client.ThreadsClient.update_state] method to modify the graph’s state at the checkpoint and resume execution from alternative state.
 4. **Resume execution from the checkpoint**: Use the [`client.runs.wait`][langgraph_sdk.client.RunsClient.wait] or [`client.runs.stream`][langgraph_sdk.client.RunsClient.stream] APIs with an input of `None` and the appropriate `thread_id` and `checkpoint_id`.
 
-## Example
+## Use time travel in a workflow
 
 ??? example "Example graph"
 
@@ -237,4 +235,4 @@ To use time-travel in LangGraph:
 
 ## Learn more
 
-- [**LangGraph time travel guide**](../../how-tos/human_in_the_loop/time-travel.ipynb): learn more about using time travel in LangGraph.
+- [**LangGraph time travel guide**](../../how-tos/human_in_the_loop/time-travel.md): learn more about using time travel in LangGraph.

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

@@ -1,4 +1,4 @@
-How to integrate LangGraph into your React application# How to integrate LangGraph into your React application
+# How to integrate LangGraph into your React application
 
 !!! info "Prerequisites"
 
@@ -503,6 +503,74 @@ const handleSubmit = (text: string) => {
 };
 ```
 
+### Cached Thread Display
+
+Use the `initialValues` option to display cached thread data immediately while the history is being loaded from the server. This improves user experience by showing cached data instantly when navigating to existing threads.
+
+```tsx
+import { useStream } from "@langchain/langgraph-sdk/react";
+
+const CachedThreadExample = ({ threadId, cachedThreadData }) => {
+  const stream = useStream({
+    apiUrl: "http://localhost:2024",
+    assistantId: "agent",
+    threadId,
+    // Show cached data immediately while history loads
+    initialValues: cachedThreadData?.values,
+    messagesKey: "messages",
+  });
+
+  return (
+    <div>
+      {stream.messages.map((message) => (
+        <div key={message.id}>{message.content as string}</div>
+      ))}
+    </div>
+  );
+};
+```
+
+### Optimistic Thread Creation
+
+Use the `threadId` option in `submit` function to enable optimistic UI patterns where you need to know the thread ID before the thread is actually created.
+
+```tsx
+import { useState } from "react";
+import { useStream } from "@langchain/langgraph-sdk/react";
+
+const OptimisticThreadExample = () => {
+  const [threadId, setThreadId] = useState<string | null>(null);
+  const [optimisticThreadId] = useState(() => crypto.randomUUID());
+
+  const stream = useStream({
+    apiUrl: "http://localhost:2024",
+    assistantId: "agent",
+    threadId,
+    onThreadId: setThreadId, // (3) Updated after thread has been created.
+    messagesKey: "messages",
+  });
+
+  const handleSubmit = (text: string) => {
+    // (1) Perform a soft navigation to /threads/${optimisticThreadId}
+    // without waiting for thread creation.
+    window.history.pushState({}, "", `/threads/${optimisticThreadId}`);
+
+    // (2) Submit message to create thread with the predetermined ID.
+    stream.submit(
+      { messages: [{ type: "human", content: text }] },
+      { threadId: optimisticThreadId }
+    );
+  };
+
+  return (
+    <div>
+      <p>Thread ID: {threadId ?? optimisticThreadId}</p>
+      {/* Rest of component */}
+    </div>
+  );
+};
+```
+
 ### TypeScript
 
 The `useStream()` hook is friendly for apps written in TypeScript and you can specify types for the state to get better type safety and IDE support.

docs/docs/cloud/reference/cli.md

@@ -395,7 +395,7 @@ The LangGraph CLI requires a JSON configuration file that follows this [schema](
 
 === "Python"
 
-    Start LangGraph API server. For local testing, requires a LangSmith API key with access to LangGraph Platform closed beta. Requires a license key for production use.
+    Start LangGraph API server. For local testing, requires a LangSmith API key with access to LangGraph Platform. Requires a license key for production use.
 
     **Usage**
 
@@ -422,7 +422,7 @@ The LangGraph CLI requires a JSON configuration file that follows this [schema](
 
 === "JS"
 
-    Start LangGraph API server. For local testing, requires a LangSmith API key with access to LangGraph Platform closed beta. Requires a license key for production use.
+    Start LangGraph API server. For local testing, requires a LangSmith API key with access to LangGraph Platform. Requires a license key for production use.
 
     **Usage**
 

docs/docs/concepts/application_structure.md

@@ -48,7 +48,7 @@ Below are examples of directory structures for Python and JavaScript application
     │   ├── utils # utilities for your graph
     │   │   ├── __init__.py
     │   │   ├── tools.py # tools for your graph
-    │   │   ├── nodes.py # node functions for you graph
+    │   │   ├── nodes.py # node functions for your graph
     │   │   └── state.py # state definition of your graph
     │   ├── __init__.py
     │   └── agent.py # code for constructing your graph
@@ -64,7 +64,7 @@ Below are examples of directory structures for Python and JavaScript application
     ├── src # all project code lies within here
     │   ├── utils # optional utilities for your graph
     │   │   ├── tools.ts # tools for your graph
-    │   │   ├── nodes.ts # node functions for you graph
+    │   │   ├── nodes.ts # node functions for your graph
     │   │   └── state.ts # state definition of your graph
     │   └── agent.ts # code for constructing your graph
     ├── package.json # package dependencies

docs/docs/concepts/breakpoints.md

@@ -5,10 +5,14 @@ search:
 
 # Breakpoints
 
-Breakpoints pause graph execution at defined points and let you step through each stage. They use LangGraph's [**persistence layer**](./persistence.md), which saves the graph state after each step.
+[Breakpoints](../how-tos/human_in_the_loop/breakpoints.md) pause graph execution at defined points and let you step through each stage. They use LangGraph's [**persistence layer**](./persistence.md), which saves the graph state after each step.
 
 With breakpoints, you can inspect the graph's state and node inputs at any point. Execution pauses **indefinitely** until you resume, as the checkpointer preserves the state.
 
 <figure markdown="1">
 ![image](img/breakpoints.png){: style="max-height:400px"}
 <figcaption>An example graph consisting of 3 sequential steps with a breakpoint before step_3. </figcaption> </figure>
+
+!!! tip
+
+    For information on how to use breakpoints, see [Set breakpoints](../how-tos/human_in_the_loop/breakpoints.md) and [Set breakpoints using Server API](../cloud/how-tos/human_in_the_loop_breakpoint.md).

docs/docs/concepts/deployment_options.md

@@ -18,9 +18,9 @@ There are 4 main options for deploying with the [LangGraph Platform](langgraph_p
 
 1. [Cloud SaaS](#cloud-saas)
 
-1. [Self-Hosted Data Plane<sup>(Beta)</sup>](#self-hosted-data-plane)
+1. [Self-Hosted Data Plane](#self-hosted-data-plane)
 
-1. [Self-Hosted Control Plane<sup>(Beta)</sup>](#self-hosted-control-plane)
+1. [Self-Hosted Control Plane](#self-hosted-control-plane)
 
 1. [Standalone Container](#standalone-container)
 
@@ -50,7 +50,7 @@ For more information, please see:
 ## Self-Hosted Data Plane
 
 !!! info "Important"
-    The Self-Hosted Data Plane deployment option is currently in beta stage and requires an [Enterprise](../concepts/plans.md) plan.
+    The Self-Hosted Data Plane deployment option requires an [Enterprise](../concepts/plans.md) plan.
 
 The [Self-Hosted Data Plane](./langgraph_self_hosted_data_plane.md) deployment option is a "hybrid" model for deployment where we manage the [control plane](./langgraph_control_plane.md) in our cloud and you manage the [data plane](./langgraph_data_plane.md) in your cloud. This option provides a way to securely manage your data plane infrastructure, while offloading control plane management to us.
 
@@ -66,7 +66,7 @@ For more information, please see:
 ## Self-Hosted Control Plane
 
 !!! info "Important"
-    The Self-Hosted Control Plane deployment option is currently in beta stage and requires an [Enterprise](../concepts/plans.md) plan.
+    The Self-Hosted Control Plane deployment option requires an [Enterprise](../concepts/plans.md) plan.
 
 The [Self-Hosted Control Plane](./langgraph_self_hosted_control_plane.md) deployment option is a fully self-hosted model for deployment where you manage the [control plane](./langgraph_control_plane.md) and [data plane](./langgraph_data_plane.md) in your cloud. This option gives you full control and responsibility of the control plane and data plane infrastructure.
 

docs/docs/concepts/faq.md

@@ -47,7 +47,7 @@ LangGraph is a stateful, orchestration framework that brings added control to ag
 
 No. LangGraph Platform is proprietary software.
 
-There is a free, self-hosted version of LangGraph Platform with access to basic features. The Cloud SaaS deployment option is free while in beta, but will eventually be a paid service. We will always give ample notice before charging for a service and reward our early adopters with preferential pricing. The Self-Hosted deployment options are paid services. [Contact our sales team](https://www.langchain.com/contact-sales) to learn more.
+There is a free, self-hosted version of LangGraph Platform with access to basic features. The Cloud SaaS deployment option and the Self-Hosted deployment options are paid services. [Contact our sales team](https://www.langchain.com/contact-sales) to learn more.
 
 For more information, see our [LangGraph Platform pricing page](https://www.langchain.com/pricing-langgraph-platform).
 

docs/docs/concepts/functional_api.md

@@ -18,10 +18,21 @@ The Functional API uses two key building blocks:
 
 This provides a minimal abstraction for building workflows with state management and streaming.
 
-!!! tip 
+!!! tip
+
+    For information on how to use the functional API, see [Use Functional API](../how-tos/use-functional-api.md).
+
+## Functional API vs. Graph API
+
+For users who prefer a more declarative approach, LangGraph's [Graph API](./low_level.md) allows you to define workflows using a Graph paradigm. Both APIs share the same underlying runtime, so you can use them together in the same application.
+
+Here are some key differences:
+
+- **Control flow**: The Functional API does not require thinking about graph structure. You can use standard Python constructs to define workflows. This will usually trim the amount of code you need to write.
+- **Short-term memory**: The **GraphAPI** requires declaring a [**State**](./low_level.md#state) and may require defining [**reducers**](./low_level.md#reducers) to manage updates to the graph state. `@entrypoint` and `@tasks` do not require explicit state management as their state is scoped to the function and is not shared across functions.
+- **Checkpointing**: Both APIs generate and use checkpoints. In the **Graph API** a new checkpoint is generated after every [superstep](./low_level.md). In the **Functional API**, when tasks are executed, their results are saved to an existing checkpoint associated with the given entrypoint instead of creating a new checkpoint.
+- **Visualization**: The Graph API makes it easy to visualize the workflow as a graph which can be useful for debugging, understanding the workflow, and sharing with others. The Functional API does not support visualization as the graph is dynamically generated during runtime.
 
-    For users who prefer a more declarative approach, LangGraph's [Graph API](./low_level.md) allows you to define workflows using a Graph paradigm. Both APIs share the same underlying runtime, so you can use them together in the same application.
-    Please see the [Functional API vs. Graph API](#functional-api-vs-graph-api) section for a comparison of the two paradigms.
 
 ## Example
 
@@ -532,15 +543,6 @@ While different runs of a workflow can produce different results, resuming a **s
 
 Idempotency ensures that running the same operation multiple times produces the same result. This helps prevent duplicate API calls and redundant processing if a step is rerun due to a failure. Always place API calls inside **tasks** functions for checkpointing, and design them to be idempotent in case of re-execution. Re-execution can occur if a **task** starts, but does not complete successfully. Then, if the workflow is resumed, the **task** will run again. Use idempotency keys or verify existing results to avoid duplication.
 
-## Functional API vs. Graph API
-
-The **Functional API** and the [Graph APIs (StateGraph)](./low_level.md#stategraph) provide two different paradigms to create applications with LangGraph. Here are some key differences:
-
-- **Control flow**: The Functional API does not require thinking about graph structure. You can use standard Python constructs to define workflows. This will usually trim the amount of code you need to write.
-- **Short-term memory**: The **GraphAPI** requires declaring a [**State**](./low_level.md#state) and may require defining [**reducers**](./low_level.md#reducers) to manage updates to the graph state. `@entrypoint` and `@tasks` do not require explicit state management as their state is scoped to the function and is not shared across functions.
-- **Checkpointing**: Both APIs generate and use checkpoints. In the **Graph API** a new checkpoint is generated after every [superstep](./low_level.md). In the **Functional API**, when tasks are executed, their results are saved to an existing checkpoint associated with the given entrypoint instead of creating a new checkpoint.
-- **Visualization**: The Graph API makes it easy to visualize the workflow as a graph which can be useful for debugging, understanding the workflow, and sharing with others. The Functional API does not support visualization as the graph is dynamically generated during runtime.
-
 ## Common Pitfalls
 
 ### Handling side effects

docs/docs/concepts/human_in_the_loop.md

@@ -17,6 +17,10 @@ To review, edit, and approve tool calls in an agent or workflow, [use LangGraph'
 ![image](../concepts/img/human_in_the_loop/tool-call-review.png){: style="max-height:400px"}
 </figure>
 
+!!! tip
+
+    For information on how to use human-in-the-loop, see [Enable human intervention](../how-tos/human_in_the_loop/add-human-in-the-loop.md) and [Human-in-the-loop using Server API](../cloud/how-tos/add-human-in-the-loop.md).
+
 ## Key capabilities
 
 * **Persistent execution state**: LangGraph allows you to pause execution **indefinitely** — for minutes, hours, or even days—until human input is received. This is possible because LangGraph checkpoints the graph state after each step, which allows the system to persist execution context and later resume the workflow, continuing from where it left off. This supports asynchronous human review or input without time constraints.

docs/docs/concepts/langgraph_self_hosted_control_plane.md

@@ -3,7 +3,7 @@
 There are two versions of the self-hosted deployment: [Self-Hosted Data Plane](./deployment_options.md#self-hosted-data-plane) and [Self-Hosted Control Plane](./deployment_options.md#self-hosted-control-plane).
 
 !!! info "Important"
-    The Self-Hosted Control Plane deployment option is currently in beta stage and requires an [Enterprise](plans.md) plan.
+    The Self-Hosted Control Plane deployment option requires an [Enterprise](plans.md) plan.
 
 ## Requirements
 

docs/docs/concepts/langgraph_self_hosted_data_plane.md

@@ -8,7 +8,7 @@ search:
 There are two versions of the self-hosted deployment: [Self-Hosted Data Plane](./deployment_options.md#self-hosted-data-plane) and [Self-Hosted Control Plane](./deployment_options.md#self-hosted-control-plane).
 
 !!! info "Important"
-    The Self-Hosted Data Plane deployment option is currently in beta stage and requires an [Enterprise](plans.md) plan.
+    The Self-Hosted Data Plane deployment option requires an [Enterprise](plans.md) plan.
 
 ## Requirements
 

docs/docs/concepts/langgraph_standalone_container.md

@@ -17,6 +17,10 @@ The Standalone Container deployment option is the least restrictive model for de
 | **Where is it hosted?** | n/a | Your cloud |
 | **Who provisions and manages it?** | n/a | You |
 
+!!! warning
+
+      LangGraph Platform should not be deployed in serverless environments. Scale to zero may cause task loss and scaling up will not work reliably.
+
 ## Architecture
 
 ![Standalone Container](./img/langgraph_platform_deployment_architecture.png)

docs/docs/concepts/persistence.md

@@ -33,7 +33,7 @@ The state of a thread at a particular point in time is called a checkpoint. Chec
 - `metadata`: Metadata associated with this checkpoint.
 - `values`: Values of the state channels at this point in time.
 - `next` A tuple of the node names to execute next in the graph.
-- `tasks`: A tuple of `PregelTask` objects that contain information about next tasks to be executed. If the step was previously attempted, it will include error information. If a graph was interrupted [dynamically](../how-tos/human_in_the_loop/breakpoints.ipynb#dynamic-breakpoints) from within a node, tasks will contain additional data associated with interrupts.
+- `tasks`: A tuple of `PregelTask` objects that contain information about next tasks to be executed. If the step was previously attempted, it will include error information. If a graph was interrupted [dynamically](../how-tos/human_in_the_loop/breakpoints.md#dynamic-breakpoints) from within a node, tasks will contain additional data associated with interrupts.
 
 Checkpoints are persisted and can be used to restore the state of a thread at a later time.
 
@@ -174,7 +174,7 @@ config = {"configurable": {"thread_id": "1", "checkpoint_id": "0c62ca34-ac19-445
 graph.invoke(None, config=config)
 ```
 
-Importantly, LangGraph knows whether a particular step has been executed previously. If it has, LangGraph simply *re-plays* that particular step in the graph and does not re-execute the step, but only for the steps _before_ the provided `checkpoint_id`. All of the steps _after_ `checkpoint_id` will be executed (i.e., a new fork), even if they have been executed previously. See this [how to guide on time-travel to learn more about replaying](../how-tos/human_in_the_loop/time-travel.ipynb).
+Importantly, LangGraph knows whether a particular step has been executed previously. If it has, LangGraph simply *re-plays* that particular step in the graph and does not re-execute the step, but only for the steps _before_ the provided `checkpoint_id`. All of the steps _after_ `checkpoint_id` will be executed (i.e., a new fork), even if they have been executed previously. See this [how to guide on time-travel to learn more about replaying](../how-tos/human_in_the_loop/time-travel.md).
 
 ![Replay](img/persistence/re_play.png)
 
@@ -224,7 +224,7 @@ The `foo` key (channel) is completely changed (because there is no reducer speci
 
 #### `as_node`
 
-The final thing you can optionally specify when calling `update_state` is `as_node`. If you provided it, the update will be applied as if it came from node `as_node`. If `as_node` is not provided, it will be set to the last node that updated the state, if not ambiguous. The reason this matters is that the next steps to execute depend on the last node to have given an update, so this can be used to control which node executes next. See this [how to guide on time-travel to learn more about forking state](../how-tos/human_in_the_loop/time-travel.ipynb).
+The final thing you can optionally specify when calling `update_state` is `as_node`. If you provided it, the update will be applied as if it came from node `as_node`. If `as_node` is not provided, it will be set to the last node that updated the state, if not ambiguous. The reason this matters is that the next steps to execute depend on the last node to have given an update, so this can be used to control which node executes next. See this [how to guide on time-travel to learn more about forking state](../how-tos/human_in_the_loop/time-travel.md).
 
 ![Update](img/persistence/checkpoints_full_story.jpg)
 
@@ -525,7 +525,7 @@ When running on LangGraph Platform, encryption is automatically enabled whenever
 
 ### Human-in-the-loop
 
-First, checkpointers facilitate [human-in-the-loop workflows](agentic_concepts.md#human-in-the-loop) workflows by allowing humans to inspect, interrupt, and approve graph steps. Checkpointers are needed for these workflows as the human has to be able to view the state of a graph at any point in time, and the graph has to be to resume execution after the human has made any updates to the state. See [these how-to guides](../how-tos/human_in_the_loop/breakpoints.ipynb) for concrete examples.
+First, checkpointers facilitate [human-in-the-loop workflows](agentic_concepts.md#human-in-the-loop) workflows by allowing humans to inspect, interrupt, and approve graph steps. Checkpointers are needed for these workflows as the human has to be able to view the state of a graph at any point in time, and the graph has to be to resume execution after the human has made any updates to the state. See [these how-to guides](../how-tos/human_in_the_loop/breakpoints.md) for concrete examples.
 
 ### Memory
 

docs/docs/concepts/time-travel.md

@@ -7,9 +7,12 @@ search:
 
 When working with non-deterministic systems that make model-based decisions (e.g., agents powered by LLMs), it can be useful to examine their decision-making process in detail:
 
-1. 🤔 **Understand Reasoning**: Analyze the steps that led to a successful result.
-2. 🐞 **Debug Mistakes**: Identify where and why errors occurred.
-3. 🔍 **Explore Alternatives**: Test different paths to uncover better solutions.
+1. 🤔 **Understand reasoning**: Analyze the steps that led to a successful result.
+2. 🐞 **Debug mistakes**: Identify where and why errors occurred.
+3. 🔍 **Explore alternatives**: Test different paths to uncover better solutions.
 
+LangGraph provides [time travel functionality](../how-tos/human_in_the_loop/time-travel.md) to support these use cases. Specifically, you can resume execution from a prior checkpoint — either replaying the same state or modifying it to explore alternatives. In all cases, resuming past execution produces a new fork in the history.
 
-LangGraph provides **time travel** functionality to support these use cases. Specifically, you can **resume execution from a prior checkpoint** — either replaying the same state or modifying it to explore alternatives. In all cases, resuming past execution produces a **new fork** in the history.
+!!! tip
+
+    For information on how to use time travel, see [Use time travel](../how-tos/human_in_the_loop/time-travel.md) and [Time travel using Server API](../cloud/how-tos/human_in_the_loop_time_travel.md).

docs/docs/how-tos/human_in_the_loop/add-human-in-the-loop.md

@@ -883,7 +883,7 @@ def node_in_parent_graph(state: State):
 
 ### Using multiple interrupts
 
-Using multiple interrupts within a **single** node can be helpful for patterns like [validating human input](../how-tos/human_in_the_loop/add-human-in-the-loop.md#validate-human-input). However, using multiple interrupts in the same node can lead to unexpected behavior if not handled carefully.
+Using multiple interrupts within a **single** node can be helpful for patterns like [validating human input](#validate-human-input). However, using multiple interrupts in the same node can lead to unexpected behavior if not handled carefully.
 
 When a node contains multiple interrupt calls, LangGraph keeps a list of resume values specific to the task executing the node. Whenever execution resumes, it starts at the beginning of the node. For each interrupt encountered, LangGraph checks if a matching value exists in the task's resume list. Matching is **strictly index-based**, so the order of interrupt calls within the node is critical.
 

docs/docs/how-tos/human_in_the_loop/breakpoints.md

@@ -0,0 +1,342 @@
+# Set breakpoints
+
+There are two places where you can set breakpoints:
+
+1. **Before** or **after** a node executes by setting breakpoints at **compile time** or **run time**. We call these [**static breakpoints**](#static-breakpoints).
+2. **Inside** a node using the `NodeInterrupt` exception. We call these [**dynamic breakpoints**](#dynamic-breakpoints).
+
+To use breakpoints, you will need to:
+
+1. [**Specify a checkpointer**](../../concepts/persistence.md#checkpoints) to save the graph state after each step.
+2. **Set breakpoints** to specify where execution should pause.
+3. **Run the graph** with a [**thread ID**](../../concepts/persistence.md#threads) to pause execution at the breakpoint.
+4. **Resume execution** using `invoke`/`ainvoke`/`stream`/`astream` passing a `None` as the argument for the inputs.
+
+!!! tip
+
+    For a conceptual overview of breakpoints, see [Breakpoints](../../concepts/breakpoints.md).
+
+## Static breakpoints
+
+Static breakpoints are triggered either before or after a node executes. You can set static breakpoints by specifying `interrupt_before` and `interrupt_after` at compile time or run time.
+
+Static breakpoints can be especially useful for debugging if you want to step through the graph execution one
+node at a time or if you want to pause the graph execution at specific nodes.
+
+=== "Compile time"
+
+    ```python
+    # highlight-next-line
+    graph = graph_builder.compile( # (1)!
+        # highlight-next-line
+        interrupt_before=["node_a"], # (2)!
+        # highlight-next-line
+        interrupt_after=["node_b", "node_c"], # (3)!
+        checkpointer=checkpointer, # (4)!
+    )
+
+    config = {
+        "configurable": {
+            "thread_id": "some_thread"
+        }
+    }
+
+    # Run the graph until the breakpoint
+    graph.invoke(inputs, config=thread_config) # (5)!
+
+    # Resume the graph
+    graph.invoke(None, config=thread_config) # (6)!
+    ```
+
+    1. The breakpoints are set during `compile` time.
+    2. `interrupt_before` specifies the nodes where execution should pause before the node is executed.
+    3. `interrupt_after` specifies the nodes where execution should pause after the node is executed.
+    4. A checkpointer is required to enable breakpoints.
+    5. The graph is run until the first breakpoint is hit.
+    6. The graph is resumed by passing in `None` for the input. This will run the graph until the next breakpoint is hit.
+
+=== "Run time"
+
+    ```python
+    # highlight-next-line
+    graph.invoke( # (1)!
+        inputs, 
+        # highlight-next-line
+        interrupt_before=["node_a"], # (2)!
+        # highlight-next-line
+        interrupt_after=["node_b", "node_c"] # (3)!
+        config={
+            "configurable": {"thread_id": "some_thread"}
+        }, 
+    )
+
+    config = {
+        "configurable": {
+            "thread_id": "some_thread"
+        }
+    }
+
+    # Run the graph until the breakpoint
+    graph.invoke(inputs, config=config) # (4)!
+
+    # Resume the graph
+    graph.invoke(None, config=config) # (5)!
+    ```
+
+    1. `graph.invoke` is called with the `interrupt_before` and `interrupt_after` parameters. This is a run-time configuration and can be changed for every invocation.
+    2. `interrupt_before` specifies the nodes where execution should pause before the node is executed.
+    3. `interrupt_after` specifies the nodes where execution should pause after the node is executed.
+    4. The graph is run until the first breakpoint is hit.
+    5. The graph is resumed by passing in `None` for the input. This will run the graph until the next breakpoint is hit.
+
+    !!! note
+
+        You cannot set static breakpoints at runtime for **sub-graphs**.
+        If you have a sub-graph, you must set the breakpoints at compilation time.
+
+??? example "Setting static breakpoints"
+
+    ```python
+    from IPython.display import Image, display
+    from typing_extensions import TypedDict
+    
+    from langgraph.checkpoint.memory import InMemorySaver 
+    from langgraph.graph import StateGraph, START, END
+    
+    
+    class State(TypedDict):
+        input: str
+    
+    
+    def step_1(state):
+        print("---Step 1---")
+        pass
+    
+    
+    def step_2(state):
+        print("---Step 2---")
+        pass
+    
+    
+    def step_3(state):
+        print("---Step 3---")
+        pass
+    
+    
+    builder = StateGraph(State)
+    builder.add_node("step_1", step_1)
+    builder.add_node("step_2", step_2)
+    builder.add_node("step_3", step_3)
+    builder.add_edge(START, "step_1")
+    builder.add_edge("step_1", "step_2")
+    builder.add_edge("step_2", "step_3")
+    builder.add_edge("step_3", END)
+    
+    # Set up a checkpointer 
+    checkpointer = InMemorySaver() # (1)!
+    
+    graph = builder.compile(
+        checkpointer=checkpointer, # (2)!
+        interrupt_before=["step_3"] # (3)!
+    )
+    
+    # View
+    display(Image(graph.get_graph().draw_mermaid_png()))
+    
+    
+    # Input
+    initial_input = {"input": "hello world"}
+    
+    # Thread
+    thread = {"configurable": {"thread_id": "1"}}
+    
+    # Run the graph until the first interruption
+    for event in graph.stream(initial_input, thread, stream_mode="values"):
+        print(event)
+        
+    # This will run until the breakpoint
+    # You can get the state of the graph at this point
+    print(graph.get_state(config))
+    
+    # You can continue the graph execution by passing in `None` for the input
+    for event in graph.stream(None, thread, stream_mode="values"):
+        print(event)
+    ```
+
+## Dynamic breakpoints
+
+Use dynamic breakpoints if you need to interrupt the graph from inside a given node based on a condition.
+
+```python
+from langgraph.errors import NodeInterrupt
+
+def step_2(state: State) -> State:
+    # highlight-next-line
+    if len(state["input"]) > 5:
+        # highlight-next-line
+        raise NodeInterrupt( # (1)!
+            f"Received input that is longer than 5 characters: {state['foo']}"
+        )
+    return state
+```
+
+1. raise NodeInterrupt exception based on a some condition. In this example, we create a dynamic breakpoint if the length of the attribute `input` is longer than 5 characters.
+
+<details class="example"><summary>Using dynamic breakpoints</summary>
+
+```python
+from typing_extensions import TypedDict
+from IPython.display import Image, display
+
+from langgraph.graph import StateGraph, START, END
+from langgraph.checkpoint.memory import MemorySaver
+from langgraph.errors import NodeInterrupt
+
+
+class State(TypedDict):
+    input: str
+
+
+def step_1(state: State) -> State:
+    print("---Step 1---")
+    return state
+
+
+def step_2(state: State) -> State:
+    # Let's optionally raise a NodeInterrupt
+    # if the length of the input is longer than 5 characters
+    if len(state["input"]) > 5:
+        raise NodeInterrupt(
+            f"Received input that is longer than 5 characters: {state['input']}"
+        )
+    print("---Step 2---")
+    return state
+
+
+def step_3(state: State) -> State:
+    print("---Step 3---")
+    return state
+
+
+builder = StateGraph(State)
+builder.add_node("step_1", step_1)
+builder.add_node("step_2", step_2)
+builder.add_node("step_3", step_3)
+builder.add_edge(START, "step_1")
+builder.add_edge("step_1", "step_2")
+builder.add_edge("step_2", "step_3")
+builder.add_edge("step_3", END)
+
+# Set up memory
+memory = MemorySaver()
+
+# Compile the graph with memory
+graph = builder.compile(checkpointer=memory)
+
+# View
+display(Image(graph.get_graph().draw_mermaid_png()))
+```
+
+First, let's run the graph with an input that <= 5 characters long. This should safely ignore the interrupt condition we defined and return the original input at the end of the graph execution.
+
+```python
+initial_input = {"input": "hello"}
+thread_config = {"configurable": {"thread_id": "1"}}
+
+for event in graph.stream(initial_input, thread_config, stream_mode="values"):
+    print(event)
+```
+
+If we inspect the graph at this point, we can see that there are no more tasks left to run and that the graph indeed finished execution.
+
+```python
+state = graph.get_state(thread_config)
+print(state.next)
+print(state.tasks)
+```
+
+Now, let's run the graph with an input that's longer than 5 characters. This should trigger the dynamic interrupt we defined via raising a `NodeInterrupt` error inside the `step_2` node.
+
+```python
+initial_input = {"input": "hello world"}
+thread_config = {"configurable": {"thread_id": "2"}}
+
+# Run the graph until the first interruption
+for event in graph.stream(initial_input, thread_config, stream_mode="values"):
+    print(event)
+```
+
+We can see that the graph now stopped while executing `step_2`. If we inspect the graph state at this point, we can see the information on what node is set to execute next (`step_2`), as well as what node raised the interrupt (also `step_2`), and additional information about the interrupt.
+
+```python
+state = graph.get_state(thread_config)
+print(state.next)
+print(state.tasks)
+```
+
+If we try to resume the graph from the breakpoint, we will simply interrupt again as our inputs & graph state haven't changed.
+
+```python
+# NOTE: to resume the graph from a dynamic interrupt we use the same syntax as with regular interrupts -- we pass None as the input
+for event in graph.stream(None, thread_config, stream_mode="values"):
+    print(event)
+```
+
+```python
+state = graph.get_state(thread_config)
+print(state.next)
+print(state.tasks)
+```
+
+</details>
+
+## Use with subgraphs
+
+To add breakpoints to subgraph either:
+
+* Define [static breakpoints](#static-breakpoints) by specifying them when **compiling** the subgraph.
+* Define [dynamic breakpoints](#dynamic-breakpoints).
+
+<details class="example"><summary>Add breakpoints to subgraphs</summary>
+
+```python
+from typing_extensions import TypedDict
+
+from langgraph.graph import START, StateGraph
+from langgraph.checkpoint.memory import InMemorySaver
+from langgraph.types import interrupt
+
+
+class State(TypedDict):
+    foo: str
+
+
+def subgraph_node_1(state: State):
+    return {"foo": state["foo"]}
+
+
+subgraph_builder = StateGraph(State)
+subgraph_builder.add_node(subgraph_node_1)
+subgraph_builder.add_edge(START, "subgraph_node_1")
+
+subgraph = subgraph_builder.compile(interrupt_before=["subgraph_node_1"])
+
+builder = StateGraph(State)
+builder.add_node("node_1", subgraph)  # directly include subgraph as a node
+builder.add_edge(START, "node_1")
+
+checkpointer = InMemorySaver()
+graph = builder.compile(checkpointer=checkpointer)
+
+config = {"configurable": {"thread_id": "1"}}
+
+graph.invoke({"foo": ""}, config)
+
+# Fetch state including subgraph state.
+print(graph.get_state(config, subgraphs=True).tasks[0].state)
+
+# resume the subgraph
+graph.invoke(None, config)
+```
+
+</details> 

docs/docs/how-tos/human_in_the_loop/time-travel.md

@@ -0,0 +1,190 @@
+# Use time-travel
+
+To use [time-travel](../../concepts/time-travel.md) in LangGraph:
+
+1. [Run the graph](#1-run-the-graph) with initial inputs using [`invoke`][langgraph.graph.state.CompiledStateGraph.invoke] or [`stream`][langgraph.graph.state.CompiledStateGraph.stream] methods.
+2. [Identify a checkpoint in an existing thread](#2-identify-a-checkpoint): Use the [`get_state_history()`][langgraph.graph.state.CompiledStateGraph.get_state_history] method to retrieve the execution history for a specific `thread_id` and locate the desired `checkpoint_id`.  
+   Alternatively, set a [breakpoint](../../concepts/breakpoints.md) before the node(s) where you want execution to pause. You can then find the most recent checkpoint recorded up to that breakpoint.
+3. [Update the graph state (optional)](#3-update-the-state-optional): Use the [`update_state`][langgraph.graph.state.CompiledStateGraph.update_state] method to modify the graph's state at the checkpoint and resume execution from alternative state.
+4. [Resume execution from the checkpoint](#4-resume-execution-from-the-checkpoint): Use the `invoke` or `stream` methods with an input of `None` and a configuration containing the appropriate `thread_id` and `checkpoint_id`.
+
+!!! tip
+
+    For a conceptual overview of time-travel, see [Time travel](../../concepts/time-travel.md).
+
+## In a workflow
+
+This example builds a simple LangGraph workflow that generates a joke topic and writes a joke using an LLM. It demonstrates how to run the graph, retrieve past execution checkpoints, optionally modify the state, and resume execution from a chosen checkpoint to explore alternate outcomes.
+
+### Setup
+
+First we need to install the packages required
+
+```python
+%%capture --no-stderr
+%pip install --quiet -U langgraph langchain_anthropic
+```
+
+Next, we need to set API keys for Anthropic (the LLM we will use)
+
+```python
+import getpass
+import os
+
+
+def _set_env(var: str):
+    if not os.environ.get(var):
+        os.environ[var] = getpass.getpass(f"{var}: ")
+
+
+_set_env("ANTHROPIC_API_KEY")
+```
+
+<div class="admonition tip">
+    <p class="admonition-title">Set up <a href="https://smith.langchain.com">LangSmith</a> for LangGraph development</p>
+    <p style="padding-top: 5px;">
+        Sign up for LangSmith to quickly spot issues and improve the performance of your LangGraph projects. LangSmith lets you use trace data to debug, test, and monitor your LLM apps built with LangGraph — read more about how to get started <a href="https://docs.smith.langchain.com">here</a>. 
+    </p>
+</div>
+
+```python
+import uuid
+
+from typing_extensions import TypedDict, NotRequired
+from langgraph.graph import StateGraph, START, END
+from langchain.chat_models import init_chat_model
+from langgraph.checkpoint.memory import InMemorySaver
+
+
+class State(TypedDict):
+    topic: NotRequired[str]
+    joke: NotRequired[str]
+
+
+llm = init_chat_model(
+    "anthropic:claude-3-7-sonnet-latest",
+    temperature=0,
+)
+
+
+def generate_topic(state: State):
+    """LLM call to generate a topic for the joke"""
+    msg = llm.invoke("Give me a funny topic for a joke")
+    return {"topic": msg.content}
+
+
+def write_joke(state: State):
+    """LLM call to write a joke based on the topic"""
+    msg = llm.invoke(f"Write a short joke about {state['topic']}")
+    return {"joke": msg.content}
+
+
+# Build workflow
+workflow = StateGraph(State)
+
+# Add nodes
+workflow.add_node("generate_topic", generate_topic)
+workflow.add_node("write_joke", write_joke)
+
+# Add edges to connect nodes
+workflow.add_edge(START, "generate_topic")
+workflow.add_edge("generate_topic", "write_joke")
+workflow.add_edge("write_joke", END)
+
+# Compile
+checkpointer = InMemorySaver()
+graph = workflow.compile(checkpointer=checkpointer)
+graph
+```
+
+### 1. Run the graph
+
+```python
+config = {
+    "configurable": {
+        "thread_id": uuid.uuid4(),
+    }
+}
+state = graph.invoke({}, config)
+
+print(state["topic"])
+print()
+print(state["joke"])
+```
+
+**Output:**
+```
+How about "The Secret Life of Socks in the Dryer"? You know, exploring the mysterious phenomenon of how socks go into the laundry as pairs but come out as singles. Where do they go? Are they starting new lives elsewhere? Is there a sock paradise we don't know about? There's a lot of comedic potential in the everyday mystery that unites us all!
+
+# The Secret Life of Socks in the Dryer
+
+I finally discovered where all my missing socks go after the dryer. Turns out they're not missing at all—they've just eloped with someone else's socks from the laundromat to start new lives together.
+
+My blue argyle is now living in Bermuda with a red polka dot, posting vacation photos on Sockstagram and sending me lint as alimony.
+```
+
+### 2. Identify a checkpoint
+
+```python
+# The states are returned in reverse chronological order.
+states = list(graph.get_state_history(config))
+
+for state in states:
+    print(state.next)
+    print(state.config["configurable"]["checkpoint_id"])
+    print()
+```
+
+**Output:**
+```
+()
+1f02ac4a-ec9f-6524-8002-8f7b0bbeed0e
+
+('write_joke',)
+1f02ac4a-ce2a-6494-8001-cb2e2d651227
+
+('generate_topic',)
+1f02ac4a-a4e0-630d-8000-b73c254ba748
+
+('__start__',)
+1f02ac4a-a4dd-665e-bfff-e6c8c44315d9
+```
+
+```python
+# This is the state before last (states are listed in chronological order)
+selected_state = states[1]
+print(selected_state.next)
+print(selected_state.values)
+```
+
+**Output:**
+```
+('write_joke',)
+{'topic': 'How about "The Secret Life of Socks in the Dryer"? You know, exploring the mysterious phenomenon of how socks go into the laundry as pairs but come out as singles. Where do they go? Are they starting new lives elsewhere? Is there a sock paradise we don\\'t know about? There\\'s a lot of comedic potential in the everyday mystery that unites us all!'}
+```
+
+### 3. Update the state (optional)
+
+`update_state` will create a new checkpoint. The new checkpoint will be associated with the same thread, but a new checkpoint ID.
+
+```python
+new_config = graph.update_state(selected_state.config, values={"topic": "chickens"})
+print(new_config)
+```
+
+**Output:**
+```
+{'configurable': {'thread_id': 'c62e2e03-c27b-4cb6-8cea-ea9bfedae006', 'checkpoint_ns': '', 'checkpoint_id': '1f02ac4a-ecee-600b-8002-a1d21df32e4c'}}
+```
+
+### 4. Resume execution from the checkpoint
+
+```python
+graph.invoke(None, new_config)
+```
+
+**Output:**
+```python
+{'topic': 'chickens',
+ 'joke': 'Why did the chicken join a band?\n\nBecause it had excellent drumsticks!'}
+``` 

docs/docs/how-tos/tool-calling.md

@@ -507,7 +507,7 @@ def update_user_name(
     new_name: str,
     tool_call_id: Annotated[str, InjectedToolCallId]
 ) -> Command:
-    """Update user name in short-term memory."""
+    """Update user-name in short-term memory."""
     # highlight-next-line
     return Command(update={
         # highlight-next-line

docs/docs/how-tos/use-functional-api.md

@@ -1,5 +1,12 @@
 # Use the functional API
 
+The [**Functional API**](../concepts/functional_api.md) allows you to add LangGraph's key features — [persistence](../concepts/persistence.md), [memory](../how-tos/memory/add-memory.md), [human-in-the-loop](../concepts/human_in_the_loop.md), and [streaming](../concepts/streaming.md) — to your applications with minimal changes to your existing code.
+
+!!! tip
+
+    For conceptual information on the functional API, see [Functional API](../concepts/functional_api.md).
+
+
 ## Creating a simple workflow
 
 When defining an `entrypoint`, input is restricted to the first argument of the function. To pass multiple inputs, you can use a dictionary.
@@ -832,4 +839,4 @@ for chunk in workflow.stream([input_message], config, stream_mode="values"):
 
 ## Integrate with other libraries
 
-* [Add LangGraph's features to other frameworks using the functional API](./autogen-integration-functional.ipynb): Add LangGraph features like persistence, memory and streaming to other agent frameworks that do not provide them out of the box.
+* [Add LangGraph's features to other frameworks using the functional API](./autogen-integration-functional.ipynb): Add LangGraph features like persistence, memory and streaming to other agent frameworks that do not provide them out of the box.

docs/docs/tutorials/langgraph-platform/local-server.md

@@ -1,4 +1,4 @@
-# LangGraph Platform quickstart
+# Run a local server
 
 This guide shows you how to run a LangGraph application locally.
 

docs/docs/tutorials/rag/langgraph_adaptive_rag.ipynb

@@ -336,7 +336,8 @@
     "rag_chain = prompt | llm | StrOutputParser()\n",
     "\n",
     "# Run\n",
-    "generation = rag_chain.invoke({\"context\": docs, \"question\": question})\n",
+    "docs_txt = format_docs(docs)\n",
+    "generation = rag_chain.invoke({\"context\": docs_txt, \"question\": question})\n",
     "print(generation)"
    ]
   },
@@ -625,7 +626,8 @@
     "    documents = state[\"documents\"]\n",
     "\n",
     "    # RAG generation\n",
-    "    generation = rag_chain.invoke({\"context\": documents, \"question\": question})\n",
+    "    docs_txt = format_docs(documents)\n",
+    "    generation = rag_chain.invoke({\"context\": docs_txt, \"question\": question})\n",
     "    return {\"documents\": documents, \"question\": question, \"generation\": generation}\n",
     "\n",
     "\n",

docs/mkdocs.yml

@@ -92,30 +92,75 @@ nav:
   - Get started:
     - index.md
     - Quickstarts:
-      - Agent: agents/agents.md
-      - Local server: tutorials/langgraph-platform/local-server.md
-      - Deployment: cloud/quick_start.md
-    - General concepts:
-      - Common patterns:
-        - Agent architectures: concepts/agentic_concepts.md
-        - Workflows & agents: tutorials/workflows.md
-      - Agent development: agents/overview.md
-      - Workflow orchestration:
-        - Graphs: concepts/low_level.md
-        - Subgraphs: concepts/subgraphs.md
-        - Runtime: concepts/pregel.md
-        - Functional API: concepts/functional_api.md
+      - Start with a prebuilt agent: agents/agents.md
+      - Build a custom workflow:
+          -  concepts/why-langgraph.md
+          -  1. Build a basic chatbot: tutorials/get-started/1-build-basic-chatbot.md
+          -  2. Add tools: tutorials/get-started/2-add-tools.md
+          -  3. Add memory: tutorials/get-started/3-add-memory.md
+          -  4. Add human-in-the-loop: tutorials/get-started/4-human-in-the-loop.md
+          -  5. Customize state: tutorials/get-started/5-customize-state.md
+          -  6. Time travel: tutorials/get-started/6-time-travel.md
+      - Run a local server: tutorials/langgraph-platform/local-server.md
+    - Agent development:
+      - Workflows & agents: tutorials/workflows.md
+      - Prebuilt components: agents/overview.md
+      - Run an agent: agents/run_agents.md
+      - Agent architectures: concepts/agentic_concepts.md
+
+  - Guides:
+    - LangGraph APIs:
+      - Graph API:
+          - Overview: concepts/low_level.md
+          - Use the Graph API: how-tos/graph-api.ipynb
+      - Functional API:
+          - Overview: concepts/functional_api.md
+          - Use the Functional API: how-tos/use-functional-api.md
+      - Runtime: concepts/pregel.md
     - Core capabilities:
-      - Streaming: concepts/streaming.md
-      - Persistence: concepts/persistence.md
-      - Durable execution: concepts/durable_execution.md
-      - Memory: concepts/memory.md
-      - Tools: concepts/tools.md
-      - Human-in-the-loop: concepts/human_in_the_loop.md
-      - Breakpoints: concepts/breakpoints.md
-      - Time travel: concepts/time-travel.md
-      - Multi-agent: concepts/multi_agent.md
-    - Platform capabilities:
+      - Streaming:
+          - Overview: concepts/streaming.md
+          - Stream outputs: how-tos/streaming.md
+          - Use Server API: cloud/how-tos/streaming.md
+      - Persistence:
+          - Overview: concepts/persistence.md
+      - Durable execution:
+          - Overview: concepts/durable_execution.md
+      - Memory:
+          - Overview: concepts/memory.md
+          - Add memory: how-tos/memory/add-memory.md
+      - Context:
+          - Add context: agents/context.md
+      - Models:
+          - Configure model: agents/models.md
+      - Tools:
+          - Overview: concepts/tools.md
+          - Call tools: how-tos/tool-calling.md
+      - Human-in-the-loop:
+          - Overview: concepts/human_in_the_loop.md
+          - Add human intervention: how-tos/human_in_the_loop/add-human-in-the-loop.md
+          - Use Server API: cloud/how-tos/add-human-in-the-loop.md
+      - Breakpoints:
+          - Overview: concepts/breakpoints.md
+          - Set breakpoints: how-tos/human_in_the_loop/breakpoints.md
+          - Use Server API: cloud/how-tos/human_in_the_loop_breakpoint.md
+      - Time travel:
+          - Overview: concepts/time-travel.md
+          - Use time travel: how-tos/human_in_the_loop/time-travel.md
+          - Use Server API: cloud/how-tos/human_in_the_loop_time_travel.md
+      - Subgraphs:
+          - Overview: concepts/subgraphs.md
+          - Use subgraphs: how-tos/subgraph.ipynb
+      - Multi-agent:
+          - Overview: concepts/multi_agent.md
+          - Prebuilt implementation: agents/multi-agent.md
+          - Custom implementation: how-tos/multi_agent.ipynb
+      - MCP:
+          - Use MCP: agents/mcp.md
+          - Server API: concepts/server-mcp.md
+      - Evaluation:
+          - Basic implementation: agents/evals.md
+    - Platform-only capabilities:
       - LangGraph Platform:
           - Overview: concepts/langgraph_platform.md
           - Components:
@@ -125,105 +170,72 @@ nav:
               - Data plane: concepts/langgraph_data_plane.md
               - Control plane: concepts/langgraph_control_plane.md
             - LangGraph CLI: concepts/langgraph_cli.md
-            - LangGraph Studio: concepts/langgraph_studio.md
+            - LangGraph Studio: 
+              - Overview: concepts/langgraph_studio.md
+              - Quickstart: cloud/how-tos/studio/quick_start.md
+              - cloud/how-tos/invoke_studio.md
+              - cloud/how-tos/studio/manage_assistants.md
+              - cloud/how-tos/threads_studio.md
+              - cloud/how-tos/iterate_graph_studio.md
+              - cloud/how-tos/studio/run_evals.md
+              - cloud/how-tos/clone_traces_studio.md
+              - cloud/how-tos/datasets_studio.md
             - LangGraph SDK: concepts/sdk.md
           - Plans & pricing: concepts/plans.md
           - Application structure: concepts/application_structure.md
           - Scalability & resilience: concepts/scalability_and_resilience.md
-      - Authentication & access control: concepts/auth.md
-      - Assistants: concepts/assistants.md
-      - Double-texting: concepts/double_texting.md
-      - Webhooks: cloud/concepts/webhooks.md
-      - Cron jobs: cloud/concepts/cron_jobs.md
-      - Deployment:
-        - Overview: concepts/deployment_options.md
-        - Deployment options:
-          - Cloud SaaS: concepts/langgraph_cloud.md
-          - Self-Hosted Data Plane: concepts/langgraph_self_hosted_data_plane.md
-          - Self-Hosted Control Plane: concepts/langgraph_self_hosted_control_plane.md
-          - Standalone Container: concepts/langgraph_standalone_container.md
-    
-  - Guides:
-    - LangGraph APIs:
-      - Use the Graph API: how-tos/graph-api.ipynb
-      - Use the Functional API: how-tos/use-functional-api.md
-    - Models:
-      - Configure model: agents/models.md
-    - Streaming:
-      - Stream outputs: how-tos/streaming.md
-      - Use Server API: cloud/how-tos/streaming.md
-    - Context:
-      - Use in agent: agents/context.md
-    - Memory:
-      - Add memory: how-tos/memory/add-memory.md
-    - Human-in-the-loop:
-      - how-tos/human_in_the_loop/add-human-in-the-loop.md
-      - Use Server API: cloud/how-tos/add-human-in-the-loop.md
-    - Time travel:
-      - Use Server API: cloud/how-tos/human_in_the_loop_time_travel.md
-    - Breakpoints:
-      - Set breakpoints: how-tos/human_in_the_loop/breakpoints.ipynb
-      - Use Server API: cloud/how-tos/human_in_the_loop_breakpoint.md
-    - Tools:
-      - Call tools: how-tos/tool-calling.md
-    - Subgraphs:
-      - Use subgraphs: how-tos/subgraph.ipynb
-    - Multi-agent:
-      - Prebuilt implementation: agents/multi-agent.md
-      - Custom implementation: how-tos/multi_agent.ipynb
-    - MCP:
-      - Use MCP: agents/mcp.md
-      - Server API: concepts/server-mcp.md
-    - Deployment:
-      - Basic deployment: agents/deployment.md
-      - Set up your application:
-        - Use requirements.txt: cloud/deployment/setup.md
-        - Use pyproject.toml: cloud/deployment/setup_pyproject.md
-        - Use JavaScript: cloud/deployment/setup_javascript.md
-        - Use custom Docker: cloud/deployment/custom_docker.md
-      - Deploy to production:
-         - Cloud SaaS: cloud/deployment/cloud.md
-         - Self-Hosted Data Plane: cloud/deployment/self_hosted_data_plane.md
-         - Self-Hosted Control Plane: cloud/deployment/self_hosted_control_plane.md
-         - Standalone Container: cloud/deployment/standalone_container.md
-    - Evaluation:
-      - Basic implementation: agents/evals.md
-    - Platform capabilities:
-      - LangGraph Studio:
-        - Quickstart: cloud/how-tos/studio/quick_start.md
-        - cloud/how-tos/invoke_studio.md
-        - cloud/how-tos/studio/manage_assistants.md
-        - cloud/how-tos/threads_studio.md
-        - cloud/how-tos/iterate_graph_studio.md
-        - cloud/how-tos/studio/run_evals.md
-        - cloud/how-tos/clone_traces_studio.md
-        - cloud/how-tos/datasets_studio.md
       - Authentication & access control:
-        - how-tos/auth/custom_auth.md
-        - how-tos/auth/openapi_security.md
+          - Overview: concepts/auth.md
+          - how-tos/auth/custom_auth.md
+          - how-tos/auth/openapi_security.md
       - Assistants:
-        - cloud/how-tos/configuration_cloud.md
-        - Threads: cloud/how-tos/use_threads.md
-        - Runs:
-          - cloud/how-tos/background_run.md
-          - cloud/how-tos/same-thread.md
+          - Overview: concepts/assistants.md
+          - cloud/how-tos/configuration_cloud.md
+          - Threads: cloud/how-tos/use_threads.md
+          - Runs:
+            - cloud/how-tos/background_run.md
+            - cloud/how-tos/same-thread.md
+            - cloud/how-tos/cron_jobs.md
+            - cloud/how-tos/stateless_runs.md
+            - cloud/how-tos/configurable_headers.md
+      - Double-texting: 
+          - Overview: concepts/double_texting.md
+          - cloud/how-tos/interrupt_concurrent.md
+          - cloud/how-tos/rollback_concurrent.md
+          - cloud/how-tos/reject_concurrent.md
+          - cloud/how-tos/enqueue_concurrent.md
+      - Webhooks:
+          - Overview: cloud/concepts/webhooks.md
+          - Use webhooks: cloud/how-tos/webhooks.md
+      - Cron jobs:
+          - Overview: cloud/concepts/cron_jobs.md
           - cloud/how-tos/cron_jobs.md
-          - cloud/how-tos/stateless_runs.md
-          - cloud/how-tos/configurable_headers.md
-      - Double-texting:
-        - cloud/how-tos/interrupt_concurrent.md
-        - cloud/how-tos/rollback_concurrent.md
-        - cloud/how-tos/reject_concurrent.md
-        - cloud/how-tos/enqueue_concurrent.md
-      - Webhooks: cloud/how-tos/webhooks.md
-      - Cron jobs: cloud/how-tos/cron_jobs.md
       - Server customization:
-        - how-tos/http/custom_lifespan.md
-        - how-tos/http/custom_middleware.md
-        - how-tos/http/custom_routes.md
+          - how-tos/http/custom_lifespan.md
+          - how-tos/http/custom_middleware.md
+          - how-tos/http/custom_routes.md
       - Data management:
         - Add semantic search: cloud/deployment/semantic_search.md
         - Add TTLs: how-tos/ttl/configure_ttl.md
+      - Deployment:
+          - Overview: concepts/deployment_options.md
+          - Quickstart: cloud/quick_start.md
+          - Set up your application:
+            - Use requirements.txt: cloud/deployment/setup.md
+            - Use pyproject.toml: cloud/deployment/setup_pyproject.md
+            - Use JavaScript: cloud/deployment/setup_javascript.md
+            - Use custom Docker: cloud/deployment/custom_docker.md
+            - Rebuild graph at runtime: cloud/deployment/graph_rebuild.md
+          - Deployment options:
+            - Cloud SaaS: concepts/langgraph_cloud.md
+            - Self-Hosted Data Plane: concepts/langgraph_self_hosted_data_plane.md
+            - Self-Hosted Control Plane: concepts/langgraph_self_hosted_control_plane.md
+            - Standalone Container: concepts/langgraph_standalone_container.md
+          - Deploy to production:
+            - Cloud SaaS: cloud/deployment/cloud.md
+            - Self-Hosted Data Plane: cloud/deployment/self_hosted_data_plane.md
+            - Self-Hosted Control Plane: cloud/deployment/self_hosted_control_plane.md
+            - Standalone Container: cloud/deployment/standalone_container.md
 
   - Reference:
     - reference/index.md
@@ -253,15 +265,6 @@ nav:
       - Environment variables: cloud/reference/env_var.md
 
   - Examples:
-    - agents/run_agents.md
-    - LangGraph basics:
-      -  concepts/why-langgraph.md
-      -  Build a basic chatbot: tutorials/get-started/1-build-basic-chatbot.md
-      -  tutorials/get-started/2-add-tools.md
-      -  tutorials/get-started/3-add-memory.md
-      -  Add human-in-the-loop: tutorials/get-started/4-human-in-the-loop.md
-      -  tutorials/get-started/5-customize-state.md
-      -  tutorials/get-started/6-time-travel.md
     - Template applications: concepts/template_applications.md  # TODO: make tutorial
     - Agentic RAG: tutorials/rag/langgraph_agentic_rag.ipynb
     - Agent Supervisor: tutorials/multi_agent/agent_supervisor.ipynb
@@ -273,7 +276,6 @@ nav:
         - tutorials/auth/getting_started.md
         - tutorials/auth/resource_auth.md
         - tutorials/auth/add_auth_server.md
-      - Rebuild graph at runtime: cloud/deployment/graph_rebuild.md
       - Use RemoteGraph: how-tos/use-remote-graph.md
       - Deploy CrewAI, AutoGen, and other frameworks: how-tos/autogen-langgraph-platform.ipynb
         # combine with how-tos/autogen-integration.ipynb
@@ -287,6 +289,7 @@ nav:
     - Case studies: adopters.md
     - concepts/faq.md
     - llms.txt: llms-txt-overview.md
+    - LangChain Forum: https://forum.langchain.com/
     - Troubleshooting:
         - Errors:
           - troubleshooting/errors/index.md

docs/uv.lock

@@ -2590,7 +2590,7 @@ wheels = [
 
 [[package]]
 name = "langgraph"
-version = "0.5.0rc1"
+version = "0.5.0"
 source = { editable = "../libs/langgraph" }
 dependencies = [
     { name = "langchain-core" },
@@ -2894,7 +2894,7 @@ test = [
 
 [[package]]
 name = "langgraph-prebuilt"
-version = "0.5.0rc0"
+version = "0.5.1"
 source = { editable = "../libs/prebuilt" }
 dependencies = [
     { name = "langchain-core" },
@@ -2925,7 +2925,7 @@ dev = [
 
 [[package]]
 name = "langgraph-sdk"
-version = "0.1.70"
+version = "0.1.72"
 source = { editable = "../libs/sdk-py" }
 dependencies = [
     { name = "httpx" },

examples/human_in_the_loop/breakpoints.ipynb

@@ -1,33 +1 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "ac22b8de",
-   "metadata": {},
-   "source": [
-    "This file has been moved to https://github.com/langchain-ai/langgraph/blob/main/docs/docs/how-tos/human_in_the_loop/breakpoints.ipynb"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}
+ 

libs/checkpoint-postgres/pyproject.toml

@@ -12,7 +12,7 @@ readme = "README.md"
 license = "MIT"
 license-files = ['LICENSE']
 dependencies = [
-  "langgraph-checkpoint>=2.0.21",
+  "langgraph-checkpoint>=2.0.21,<3.0.0",
   "orjson>=3.10.1",
   "psycopg>=3.2.0",
   "psycopg-pool>=3.2.0",

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

@@ -223,10 +223,9 @@ class AsyncSqliteStore(AsyncBatchedBaseStore, BaseSqliteStore):
         Yields:
             An SQLite cursor object.
         """
+        if not self.is_setup:
+            await self.setup()
         async with self.lock:
-            if not self.is_setup:
-                await self.setup()
-
             if transaction:
                 await self.conn.execute("BEGIN")
 

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

@@ -981,10 +981,9 @@ class SqliteStore(BaseSqliteStore, BaseStore):
         Args:
             transaction (bool): whether to use transaction for the DB operations
         """
+        if not self.is_setup:
+            self.setup()
         with self.lock:
-            if not self.is_setup:
-                self.setup()
-
             if transaction:
                 self.conn.execute("BEGIN")
 
@@ -1002,10 +1001,10 @@ class SqliteStore(BaseSqliteStore, BaseStore):
         This method creates the necessary tables in the SQLite database if they don't
         already exist and runs database migrations. It should be called before first use.
         """
-        if self.is_setup:
-            return
 
         with self.lock:
+            if self.is_setup:
+                return
             # Create migrations table if it doesn't exist
             self.conn.executescript(
                 """

libs/checkpoint-sqlite/pyproject.toml

@@ -12,7 +12,7 @@ readme = "README.md"
 license = "MIT"
 license-files = ['LICENSE']
 dependencies = [
-    "langgraph-checkpoint>=2.0.21",
+    "langgraph-checkpoint>=2.0.21,<3.0.0",
     "aiosqlite>=0.20",
     "sqlite-vec>=0.1.6",
 ]

libs/cli/langgraph_cli/cli.py

@@ -208,7 +208,7 @@ def up(
 ):
     click.secho("Starting LangGraph API server...", fg="green")
     click.secho(
-        """For local dev, requires env var LANGSMITH_API_KEY with access to LangGraph Platform closed beta.
+        """For local dev, requires env var LANGSMITH_API_KEY with access to LangGraph Platform.
 For production use, requires a license key in env var LANGGRAPH_CLOUD_LICENSE_KEY.""",
     )
     with Runner() as runner, Progress(message="Pulling...") as set:

libs/cli/pyproject.toml

@@ -18,8 +18,8 @@ dependencies = [
 
 [project.optional-dependencies]
 inmem = [
-    "langgraph-api>=0.2.67 ; python_version >= '3.11'",
-    "langgraph-runtime-inmem>=0.3.0 ; python_version >= '3.11'",
+    "langgraph-api>=0.2.67,<0.3.0 ; python_version >= '3.11'",
+    "langgraph-runtime-inmem>=0.3.0,<0.4.0 ; python_version >= '3.11'",
     "python-dotenv>=0.8.0",
 ]
 

libs/cli/uv.lock

@@ -530,8 +530,8 @@ dev = [
 [package.metadata]
 requires-dist = [
     { name = "click", specifier = ">=8.1.7" },
-    { name = "langgraph-api", marker = "python_full_version >= '3.11' and extra == 'inmem'", specifier = ">=0.2.67" },
-    { name = "langgraph-runtime-inmem", marker = "python_full_version >= '3.11' and extra == 'inmem'", specifier = ">=0.3.0" },
+    { name = "langgraph-api", marker = "python_full_version >= '3.11' and extra == 'inmem'", specifier = ">=0.2.67,<0.3.0" },
+    { name = "langgraph-runtime-inmem", marker = "python_full_version >= '3.11' and extra == 'inmem'", specifier = ">=0.3.0,<0.4.0" },
     { name = "langgraph-sdk", marker = "python_full_version >= '3.11'", specifier = ">=0.1.0" },
     { name = "python-dotenv", marker = "extra == 'inmem'", specifier = ">=0.8.0" },
 ]

libs/langgraph/README.md

@@ -63,7 +63,7 @@ LangGraph provides low-level supporting infrastructure for *any* long-running, s
 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/).
+- [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/).
 - [LangChain](https://python.langchain.com/docs/introduction/) – Provides integrations and composable components to streamline LLM application development.
 
 > [!NOTE]

libs/langgraph/pyproject.toml

@@ -13,9 +13,9 @@ license = "MIT"
 license-files = ['LICENSE']
 dependencies = [
     "langchain-core>=0.1",
-    "langgraph-checkpoint>=2.1.0",
-    "langgraph-sdk>=0.1.42",
-    "langgraph-prebuilt>=0.5.0",
+    "langgraph-checkpoint>=2.1.0,<3.0.0",
+    "langgraph-sdk>=0.1.42,<0.2.0",
+    "langgraph-prebuilt>=0.5.0,<0.6.0",
     "xxhash>=3.5.0",
     "pydantic>=2.7.4",
 ]

libs/langgraph/uv.lock

@@ -1183,7 +1183,7 @@ wheels = [
 
 [[package]]
 name = "langchain-core"
-version = "0.3.63"
+version = "0.3.67"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "jsonpatch" },
@@ -1194,9 +1194,9 @@ dependencies = [
     { name = "tenacity" },
     { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/b9/0a/b71a9a5d42e743d6876cce23d803e284b191ed4d6544e2f7fe1b37f7854c/langchain_core-0.3.63.tar.gz", hash = "sha256:e2e30cfbb7684a5a0319f6cbf065fc3c438bfd1060302f085a122527890fb01e", size = 558302, upload-time = "2025-05-29T18:57:19.933Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/c2/40/875af0194024d0006874f061958fa417d3500bbfdc9a57e1bd1c2f4e6ed2/langchain_core-0.3.67.tar.gz", hash = "sha256:2c14aa44a0e78e014e96d7f2f8916ac109d0a0ba87ed67ee25bf7296bed7e7ba", size = 561952, upload-time = "2025-06-30T17:09:35.142Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/5c/71/a748861e6a69ab6ef50ab8e65120422a1f36245c71a0dd0f02de49c208e1/langchain_core-0.3.63-py3-none-any.whl", hash = "sha256:f91db8221b1bc6808f70b2e72fded1a94d50ee3f1dff1636fb5a5a514c64b7f5", size = 438468, upload-time = "2025-05-29T18:57:17.424Z" },
+    { url = "https://files.pythonhosted.org/packages/9f/2b/a0d283089c6d08c12d47dca39a55029ff714e939ec04f4560420426ab613/langchain_core-0.3.67-py3-none-any.whl", hash = "sha256:b699f1f24b24fa2747c05e2daa280aa64478a51e01a4e82c7f8e20b6167dfa99", size = 440237, upload-time = "2025-06-30T17:09:33.323Z" },
 ]
 
 [[package]]
@@ -1423,7 +1423,7 @@ inmem = [
 
 [[package]]
 name = "langgraph-prebuilt"
-version = "0.5.0"
+version = "0.5.2"
 source = { editable = "../prebuilt" }
 dependencies = [
     { name = "langchain-core" },
@@ -1432,7 +1432,7 @@ dependencies = [
 
 [package.metadata]
 requires-dist = [
-    { name = "langchain-core", specifier = ">=0.3.22" },
+    { name = "langchain-core", specifier = ">=0.3.67" },
     { name = "langgraph-checkpoint", editable = "../checkpoint" },
 ]
 
@@ -1497,7 +1497,7 @@ dev = [
 
 [[package]]
 name = "langsmith"
-version = "0.3.43"
+version = "0.4.4"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "httpx" },
@@ -1508,9 +1508,9 @@ dependencies = [
     { name = "requests-toolbelt" },
     { name = "zstandard" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/02/21/df84fe8b5c16971999650cbfc95a49f176d044a606e2b4eb957bbc122e1c/langsmith-0.3.43.tar.gz", hash = "sha256:7dab99b635859e24a1a252ad4f7e23170a45f4ea742567a10b4b26c50478ed43", size = 346328, upload-time = "2025-05-29T00:21:11.637Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/20/c8/8d2e0fc438d2d3d8d4300f7684ea30a754344ed00d7ba9cc2705241d2a5f/langsmith-0.4.4.tar.gz", hash = "sha256:70c53bbff24a7872e88e6fa0af98270f4986a6e364f9e85db1cc5636defa4d66", size = 352105, upload-time = "2025-06-27T19:20:36.207Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/e2/72/f5304de3e7e80e6dc266c161230aecb7895958f78b5af1541317d7615fc6/langsmith-0.3.43-py3-none-any.whl", hash = "sha256:2d4558068abf2eeb60ff80871187724e07f5e657d7d6be9e0c603df36c41140a", size = 361148, upload-time = "2025-05-29T00:21:08.759Z" },
+    { url = "https://files.pythonhosted.org/packages/1d/33/a3337eb70d795495a299a1640d7a75f17fb917155a64309b96106e7b9452/langsmith-0.4.4-py3-none-any.whl", hash = "sha256:014c68329bd085bd6c770a6405c61bb6881f82eb554ce8c4d1984b0035fd1716", size = 367687, upload-time = "2025-06-27T19:20:33.839Z" },
 ]
 
 [[package]]

libs/prebuilt/langgraph/prebuilt/chat_agent_executor.py

@@ -448,7 +448,7 @@ def create_react_agent(
 
     if (
         _should_bind_tools(model, tool_classes, num_builtin=len(llm_builtin_tools))
-        and len(tool_classes) > 0
+        and len(tool_classes + llm_builtin_tools) > 0
     ):
         model = cast(BaseChatModel, model).bind_tools(tool_classes + llm_builtin_tools)  # type: ignore[operator]
 

libs/prebuilt/langgraph/prebuilt/tool_node.py

@@ -30,7 +30,10 @@ from langchain_core.runnables.config import (
 )
 from langchain_core.tools import BaseTool, InjectedToolArg
 from langchain_core.tools import tool as create_tool
-from langchain_core.tools.base import get_all_basemodel_annotations
+from langchain_core.tools.base import (
+    TOOL_MESSAGE_BLOCK_TYPES,
+    get_all_basemodel_annotations,
+)
 from pydantic import BaseModel
 from typing_extensions import Annotated, get_args, get_origin
 
@@ -46,12 +49,11 @@ TOOL_CALL_ERROR_TEMPLATE = "Error: {error}\n Please fix your mistakes."
 
 
 def msg_content_output(output: Any) -> Union[str, list[dict]]:
-    recognized_content_block_types = ("image", "image_url", "text", "json")
     if isinstance(output, str):
         return output
     elif isinstance(output, list) and all(
         [
-            isinstance(x, dict) and x.get("type") in recognized_content_block_types
+            isinstance(x, dict) and x.get("type") in TOOL_MESSAGE_BLOCK_TYPES
             for x in output
         ]
     ):

libs/prebuilt/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "langgraph-prebuilt"
-version = "0.5.0"
+version = "0.5.2"
 description = "Library with high-level APIs for creating and executing LangGraph agents and tools."
 authors = []
 requires-python = ">=3.9"
@@ -12,8 +12,8 @@ readme = "README.md"
 license = "MIT"
 license-files = ['LICENSE']
 dependencies = [
-    "langgraph-checkpoint>=2.1.0",
-    "langchain-core>=0.3.22",
+    "langgraph-checkpoint>=2.1.0,<3.0.0",
+    "langchain-core>=0.3.67",
 ]
 
 [project.urls]

libs/prebuilt/uv.lock

@@ -302,7 +302,7 @@ wheels = [
 
 [[package]]
 name = "langchain-core"
-version = "0.3.60"
+version = "0.3.67"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "jsonpatch" },
@@ -313,9 +313,9 @@ dependencies = [
     { name = "tenacity" },
     { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/5b/75/95129aaada92980a002a31e002610a80af3c8967ae7884710372e89cdde0/langchain_core-0.3.60.tar.gz", hash = "sha256:63dd1bdf7939816115399522661ca85a2f3686a61440f2f46ebd86d1b028595b", size = 557456, upload-time = "2025-05-15T15:23:23.642Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/c2/40/875af0194024d0006874f061958fa417d3500bbfdc9a57e1bd1c2f4e6ed2/langchain_core-0.3.67.tar.gz", hash = "sha256:2c14aa44a0e78e014e96d7f2f8916ac109d0a0ba87ed67ee25bf7296bed7e7ba", size = 561952, upload-time = "2025-06-30T17:09:35.142Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/2d/bc/344f5b11fdfe0e27f7064d2e829921a791461dc32e5ed285fe6325518c26/langchain_core-0.3.60-py3-none-any.whl", hash = "sha256:2ccdf06b12e699b1b0962bc02837056c075b4981c3d13f82a4d4c30bb22ea3dc", size = 437890, upload-time = "2025-05-15T15:23:22.278Z" },
+    { url = "https://files.pythonhosted.org/packages/9f/2b/a0d283089c6d08c12d47dca39a55029ff714e939ec04f4560420426ab613/langchain_core-0.3.67-py3-none-any.whl", hash = "sha256:b699f1f24b24fa2747c05e2daa280aa64478a51e01a4e82c7f8e20b6167dfa99", size = 440237, upload-time = "2025-06-30T17:09:33.323Z" },
 ]
 
 [[package]]
@@ -464,7 +464,7 @@ dev = [
 
 [[package]]
 name = "langgraph-prebuilt"
-version = "0.5.0"
+version = "0.5.2"
 source = { editable = "." }
 dependencies = [
     { name = "langchain-core" },
@@ -489,7 +489,7 @@ dev = [
 
 [package.metadata]
 requires-dist = [
-    { name = "langchain-core", specifier = ">=0.3.22" },
+    { name = "langchain-core", specifier = ">=0.3.67" },
     { name = "langgraph-checkpoint", editable = "../checkpoint" },
 ]
 
@@ -537,7 +537,7 @@ dev = [
 
 [[package]]
 name = "langsmith"
-version = "0.3.42"
+version = "0.4.4"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "httpx" },
@@ -548,9 +548,9 @@ dependencies = [
     { name = "requests-toolbelt" },
     { name = "zstandard" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/3a/44/fe171c0b0fb0377b191aebf0b7779e0c7b2a53693c6a01ddad737212495d/langsmith-0.3.42.tar.gz", hash = "sha256:2b5cbc450ab808b992362aac6943bb1d285579aa68a3a8be901d30a393458f25", size = 345619, upload-time = "2025-05-03T03:07:17.873Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/20/c8/8d2e0fc438d2d3d8d4300f7684ea30a754344ed00d7ba9cc2705241d2a5f/langsmith-0.4.4.tar.gz", hash = "sha256:70c53bbff24a7872e88e6fa0af98270f4986a6e364f9e85db1cc5636defa4d66", size = 352105, upload-time = "2025-06-27T19:20:36.207Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/89/8e/e8a58e0abaae3f3ac4702e9ca35d1fc6159711556b64ffd0e247771a3f12/langsmith-0.3.42-py3-none-any.whl", hash = "sha256:18114327f3364385dae4026ebfd57d1c1cb46d8f80931098f0f10abe533475ff", size = 360334, upload-time = "2025-05-03T03:07:15.491Z" },
+    { url = "https://files.pythonhosted.org/packages/1d/33/a3337eb70d795495a299a1640d7a75f17fb917155a64309b96106e7b9452/langsmith-0.4.4-py3-none-any.whl", hash = "sha256:014c68329bd085bd6c770a6405c61bb6881f82eb554ce8c4d1984b0035fd1716", size = 367687, upload-time = "2025-06-27T19:20:33.839Z" },
 ]
 
 [[package]]

libs/sdk-js/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@langchain/langgraph-sdk",
-  "version": "0.0.86",
+  "version": "0.0.88",
   "description": "Client library for interacting with the LangGraph API",
   "type": "module",
   "packageManager": "yarn@1.22.19",
@@ -22,7 +22,9 @@
     "uuid": "^9.0.0"
   },
   "devDependencies": {
-    "@langchain/core": "^0.3.31",
+    "@langchain/langgraph-api": "~0.0.41",
+    "@langchain/core": "^0.3.61",
+    "@langchain/langgraph": "^0.3.5",
     "@langchain/scripts": "^0.1.4",
     "@testing-library/dom": "^10.4.0",
     "@testing-library/jest-dom": "^6.6.3",
@@ -35,6 +37,7 @@
     "@types/uuid": "^9.0.1",
     "@vitejs/plugin-react": "^4.4.1",
     "concat-md": "^0.5.1",
+    "hono": "^4.8.2",
     "jsdom": "^26.1.0",
     "msw": "^2.8.2",
     "prettier": "^3.2.5",

libs/sdk-js/src/client.ts

@@ -1014,8 +1014,8 @@ export class RunsClient<
     const stream: ReadableStream<{ event: any; data: any }> = (
       response.body || new ReadableStream({ start: (ctrl) => ctrl.close() })
     )
-      .pipeThrough(new BytesLineDecoder())
-      .pipeThrough(new SSEDecoder());
+      .pipeThrough(BytesLineDecoder())
+      .pipeThrough(SSEDecoder());
 
     yield* IterableReadableStream.fromReadableStream(stream);
   }
@@ -1318,8 +1318,8 @@ export class RunsClient<
     const stream: ReadableStream<{ event: string; data: any }> = (
       response.body || new ReadableStream({ start: (ctrl) => ctrl.close() })
     )
-      .pipeThrough(new BytesLineDecoder())
-      .pipeThrough(new SSEDecoder());
+      .pipeThrough(BytesLineDecoder())
+      .pipeThrough(SSEDecoder());
 
     yield* IterableReadableStream.fromReadableStream(stream);
   }
@@ -1658,7 +1658,30 @@ export class Client<
    */
   public "~ui": UiClient;
 
+  /**
+   * @internal Used to obtain a stable key representing the client.
+   */
+  private "~configHash": string | undefined;
+
   constructor(config?: ClientConfig) {
+    this["~configHash"] = (() =>
+      JSON.stringify({
+        apiUrl: config?.apiUrl,
+        apiKey: config?.apiKey,
+        timeoutMs: config?.timeoutMs,
+        defaultHeaders: config?.defaultHeaders,
+
+        maxConcurrency: config?.callerOptions?.maxConcurrency,
+        maxRetries: config?.callerOptions?.maxRetries,
+
+        callbacks: {
+          onFailedResponseHook:
+            config?.callerOptions?.onFailedResponseHook != null,
+          onRequest: config?.onRequest != null,
+          fetch: config?.callerOptions?.fetch != null,
+        },
+      }))();
+
     this.assistants = new AssistantsClient(config);
     this.threads = new ThreadsClient(config);
     this.runs = new RunsClient(config);
@@ -1667,3 +1690,10 @@ export class Client<
     this["~ui"] = new UiClient(config);
   }
 }
+
+/**
+ * @internal Used to obtain a stable key representing the client.
+ */
+export function getClientConfigHash(client: Client): string | undefined {
+  return client["~configHash"];
+}

libs/sdk-js/src/react/stream.tsx

@@ -1,7 +1,7 @@
 /* __LC_ALLOW_ENTRYPOINT_SIDE_EFFECTS__ */
 "use client";
 
-import { Client, type ClientConfig } from "../client.js";
+import { Client, getClientConfigHash, type ClientConfig } from "../client.js";
 import type {
   Command,
   DisconnectMode,
@@ -31,7 +31,7 @@ import type {
 } from "../types.stream.js";
 
 import {
-  type MutableRefObject,
+  type RefObject,
   useCallback,
   useEffect,
   useMemo,
@@ -316,16 +316,21 @@ function fetchHistory<StateType extends Record<string, unknown>>(
 function useThreadHistory<StateType extends Record<string, unknown>>(
   threadId: string | undefined | null,
   client: Client,
-  clearCallbackRef: MutableRefObject<(() => void) | undefined>,
-  submittingRef: MutableRefObject<boolean>,
+  clearCallbackRef: RefObject<(() => void) | undefined>,
+  submittingRef: RefObject<boolean>,
 ) {
   const [history, setHistory] = useState<ThreadState<StateType>[]>([]);
 
+  const clientHash = getClientConfigHash(client);
+  const clientRef = useRef(client);
+  clientRef.current = client;
+
   const fetcher = useCallback(
     (
       threadId: string | undefined | null,
     ): Promise<ThreadState<StateType>[]> => {
       if (threadId != null) {
+        const client = clientRef.current;
         return fetchHistory<StateType>(client, threadId).then((history) => {
           setHistory(history);
           return history;
@@ -342,7 +347,7 @@ function useThreadHistory<StateType extends Record<string, unknown>>(
   useEffect(() => {
     if (submittingRef.current) return;
     fetcher(threadId);
-  }, [fetcher, submittingRef, threadId]);
+  }, [fetcher, clientHash, submittingRef, threadId]);
 
   return {
     data: history,
@@ -506,6 +511,31 @@ export interface UseStreamOptions<
    */
   onDebugEvent?: (data: DebugStreamEvent["data"]) => void;
 
+  /**
+   * Callback that is called when the stream is stopped by the user.
+   * Provides a mutate function to update the stream state immediately
+   * without requiring a server roundtrip.
+   *
+   * @example
+   * ```typescript
+   * onStop: ({ mutate }) => {
+   *   mutate((prev) => ({
+   *     ...prev,
+   *     ui: prev.ui?.map(component =>
+   *       component.props.isLoading
+   *         ? { ...component, props: { ...component.props, stopped: true, isLoading: false }}
+   *         : component
+   *     )
+   *   }));
+   * }
+   * ```
+   */
+  onStop?: (options: {
+    mutate: (
+      update: Partial<StateType> | ((prev: StateType) => Partial<StateType>),
+    ) => void;
+  }) => void;
+
   /**
    * The ID of the thread to fetch history and current values from.
    */
@@ -518,6 +548,17 @@ export interface UseStreamOptions<
 
   /** Will reconnect the stream on mount */
   reconnectOnMount?: boolean | (() => RunMetadataStorage);
+
+  /**
+   * Initial values to display immediately when loading a thread.
+   * Useful for displaying cached thread data while official history loads.
+   * These values will be replaced when official thread data is fetched.
+   *
+   * Note: UI components from initialValues will render immediately if they're
+   * predefined in LoadExternalComponent's components prop, providing instant
+   * cached UI display without server fetches.
+   */
+  initialValues?: StateType | null;
 }
 
 interface RunMetadataStorage {
@@ -616,7 +657,11 @@ export interface UseStream<
   /**
    * Join an active stream.
    */
-  joinStream: (runId: string) => Promise<void>;
+  joinStream: (
+    runId: string,
+    lastEventId?: string,
+    options?: { streamMode?: StreamMode | StreamMode[] },
+  ) => Promise<void>;
 }
 
 type ConfigWithConfigurable<ConfigurableType extends Record<string, unknown>> =
@@ -647,6 +692,61 @@ interface SubmitOptions<
    */
   streamSubgraphs?: boolean;
   streamResumable?: boolean;
+  /**
+   * The ID to use when creating a new thread. When provided, this ID will be used
+   * for thread creation when threadId is `null` or `undefined`.
+   * This enables optimistic UI updates where you know the thread ID
+   * before the thread is actually created.
+   */
+  threadId?: string;
+}
+
+function useStreamValuesState<StateType extends Record<string, unknown>>() {
+  type Kind = "stream" | "stop";
+  type Values = StateType | null;
+  type Update = Values | ((prev: Values, kind?: Kind) => Values);
+  type Mutate = Partial<StateType> | ((prev: StateType) => Partial<StateType>);
+
+  const [values, setValues] = useState<[values: StateType, kind: Kind] | null>(
+    null,
+  );
+
+  const setStreamValues = useCallback(
+    (values: Update, kind: Kind = "stream") => {
+      if (typeof values === "function") {
+        setValues((prevTuple) => {
+          const [prevValues, prevKind] = prevTuple ?? [null, "stream"];
+          const next = values(prevValues, prevKind);
+
+          if (next == null) return null;
+          return [next, kind] as [StateType, Kind];
+        });
+
+        return;
+      }
+
+      if (values == null) setValues(null);
+      setValues([values, kind] as [StateType, Kind]);
+    },
+    [],
+  );
+
+  const mutate = useCallback(
+    (kind: Kind, serverValues: StateType) => (update: Mutate) => {
+      setStreamValues((clientValues) => {
+        const prev = { ...serverValues, ...clientValues };
+        const next = typeof update === "function" ? update(prev) : update;
+        return { ...prev, ...next };
+      }, kind);
+    },
+    [setStreamValues],
+  );
+
+  return [values?.[0] ?? null, setStreamValues, mutate] as [
+    Values,
+    (update: Update, kind?: Kind) => void,
+    (kind: Kind, serverValues: StateType) => (update: Mutate) => void,
+  ];
 }
 
 export function useStream<
@@ -712,7 +812,8 @@ export function useStream<
   const [isLoading, setIsLoading] = useState(false);
 
   const [streamError, setStreamError] = useState<unknown>(undefined);
-  const [streamValues, setStreamValues] = useState<StateType | null>(null);
+  const [streamValues, setStreamValues, getMutateFn] =
+    useStreamValuesState<StateType>();
 
   const messageManagerRef = useRef(new MessageTupleManager());
   const submittingRef = useRef(false);
@@ -783,7 +884,9 @@ export function useStream<
   );
 
   const threadHead: ThreadState<StateType> | undefined = flatHistory.at(-1);
-  const historyValues = threadHead?.values ?? ({} as StateType);
+  const historyValues =
+    threadHead?.values ?? options.initialValues ?? ({} as StateType);
+
   const historyError = (() => {
     const error = threadHead?.tasks?.at(-1)?.error;
     if (error == null) return undefined;
@@ -848,6 +951,8 @@ export function useStream<
       if (runId) client.runs.cancel(threadId, runId);
       runMetadataStorage.removeItem(`lg:stream:${threadId}`);
     }
+
+    options?.onStop?.({ mutate: getMutateFn("stop", historyValues) });
   };
 
   async function consumeStream(
@@ -880,15 +985,7 @@ export function useStream<
         if (event === "updates") options.onUpdateEvent?.(data);
         if (event === "custom")
           options.onCustomEvent?.(data, {
-            mutate: (update) =>
-              setStreamValues((prev) => {
-                // should not happen
-                if (prev == null) return prev;
-                return {
-                  ...prev,
-                  ...(typeof update === "function" ? update(prev) : update),
-                };
-              }),
+            mutate: getMutateFn("stream", historyValues),
           });
         if (event === "metadata") options.onMetadataEvent?.(data);
         if (event === "events") options.onLangChainEvent?.(data);
@@ -930,8 +1027,11 @@ export function useStream<
 
       // TODO: stream created checkpoints to avoid an unnecessary network request
       const result = await run.onSuccess();
-
-      setStreamValues(null);
+      setStreamValues((values, kind) => {
+        // Do not clear out the user values set on `stop`.
+        if (kind === "stop") return values;
+        return null;
+      });
       if (streamError != null) throw streamError;
 
       const lastHead = result.at(0);
@@ -957,13 +1057,18 @@ export function useStream<
     }
   }
 
-  const joinStream = async (runId: string, lastEventId?: string) => {
+  const joinStream = async (
+    runId: string,
+    lastEventId?: string,
+    options?: { streamMode?: StreamMode | StreamMode[] },
+  ) => {
     lastEventId ??= "-1";
     if (!threadId) return;
     await consumeStream(async (signal: AbortSignal) => {
       const stream = client.runs.joinStream(threadId, runId, {
         signal,
         lastEventId,
+        streamMode: options?.streamMode,
       }) as AsyncGenerator<EventStreamEvent>;
 
       return {
@@ -989,26 +1094,24 @@ export function useStream<
 
       if (newPath != null) setBranch(newPath ?? "");
 
-      // Assumption: we're setting the initial value
-      // Used for instant feedback
       setStreamValues(() => {
-        const values = { ...historyValues };
-
         if (submitOptions?.optimisticValues != null) {
           return {
-            ...values,
+            ...historyValues,
             ...(typeof submitOptions.optimisticValues === "function"
-              ? submitOptions.optimisticValues(values)
+              ? submitOptions.optimisticValues(historyValues)
               : submitOptions.optimisticValues),
           };
         }
 
-        return values;
+        return { ...historyValues };
       });
 
       let usableThreadId = threadId;
       if (!usableThreadId) {
-        const thread = await client.threads.create();
+        const thread = await client.threads.create({
+          threadId: submitOptions?.threadId,
+        });
         onThreadId(thread.thread_id);
         usableThreadId = thread.thread_id;
       }

libs/sdk-js/src/tests/sse.test.ts

@@ -20,7 +20,7 @@ describe("BytesLineDecoder", () => {
 
   test("handles single line with newline", async () => {
     const input = createStream([textEncoder.encode("hello\n")]);
-    const decoded = input.pipeThrough(new BytesLineDecoder());
+    const decoded = input.pipeThrough(BytesLineDecoder());
     const results = await gather(decoded);
 
     expect(results.length).toBe(1);
@@ -29,7 +29,7 @@ describe("BytesLineDecoder", () => {
 
   test("handles multiple lines", async () => {
     const input = createStream([textEncoder.encode("line1\nline2\nline3\n")]);
-    const decoded = input.pipeThrough(new BytesLineDecoder());
+    const decoded = input.pipeThrough(BytesLineDecoder());
     const results = await gather(decoded);
 
     expect(results.length).toBe(3);
@@ -44,7 +44,7 @@ describe("BytesLineDecoder", () => {
       textEncoder.encode("ne1\nli"),
       textEncoder.encode("ne2\n"),
     ]);
-    const decoded = input.pipeThrough(new BytesLineDecoder());
+    const decoded = input.pipeThrough(BytesLineDecoder());
     const results = await gather(decoded);
 
     expect(results.length).toBe(2);
@@ -54,7 +54,7 @@ describe("BytesLineDecoder", () => {
 
   test("handles CR LF line endings", async () => {
     const input = createStream([textEncoder.encode("line1\r\nline2\r\n")]);
-    const decoded = input.pipeThrough(new BytesLineDecoder());
+    const decoded = input.pipeThrough(BytesLineDecoder());
     const results = await gather(decoded);
 
     expect(results.length).toBe(2);
@@ -67,7 +67,7 @@ describe("BytesLineDecoder", () => {
       textEncoder.encode("line1\r"),
       textEncoder.encode("\nline2\r\n"),
     ]);
-    const decoded = input.pipeThrough(new BytesLineDecoder());
+    const decoded = input.pipeThrough(BytesLineDecoder());
     const results = await gather(decoded);
 
     expect(results.length).toBe(2);
@@ -77,7 +77,7 @@ describe("BytesLineDecoder", () => {
 
   test("handles stale line", async () => {
     const input = createStream([textEncoder.encode("hello")]);
-    const decoded = input.pipeThrough(new BytesLineDecoder());
+    const decoded = input.pipeThrough(BytesLineDecoder());
     const results = await gather(decoded);
 
     expect(results.length).toBe(1);
@@ -99,8 +99,8 @@ describe("SSEDecoder", () => {
       "\n",
     ]);
     const decoded = input
-      .pipeThrough(new BytesLineDecoder())
-      .pipeThrough(new SSEDecoder());
+      .pipeThrough(BytesLineDecoder())
+      .pipeThrough(SSEDecoder());
 
     const results = await gather(decoded);
     expect(results.length).toBe(1);
@@ -117,8 +117,8 @@ describe("SSEDecoder", () => {
       'data: {"message": "hello"}\n',
     ]);
     const decoded = input
-      .pipeThrough(new BytesLineDecoder())
-      .pipeThrough(new SSEDecoder());
+      .pipeThrough(BytesLineDecoder())
+      .pipeThrough(SSEDecoder());
 
     const results = await gather(decoded);
     expect(results.length).toBe(1);
@@ -138,8 +138,8 @@ describe("SSEDecoder", () => {
       "\n",
     ]);
     const decoded = input
-      .pipeThrough(new BytesLineDecoder())
-      .pipeThrough(new SSEDecoder());
+      .pipeThrough(BytesLineDecoder())
+      .pipeThrough(SSEDecoder());
 
     const results = await gather(decoded);
     expect(results.length).toBe(2);
@@ -156,8 +156,8 @@ describe("SSEDecoder", () => {
   test("end event without data", async () => {
     const input = createStream(["event: test\n"]);
     const decoded = input
-      .pipeThrough(new BytesLineDecoder())
-      .pipeThrough(new SSEDecoder());
+      .pipeThrough(BytesLineDecoder())
+      .pipeThrough(SSEDecoder());
 
     const results = await gather(decoded);
     expect(results.length).toBe(1);
@@ -170,8 +170,8 @@ describe("SSEDecoder", () => {
   test("end event without newline", async () => {
     const input = createStream(["event: end"]);
     const decoded = input
-      .pipeThrough(new BytesLineDecoder())
-      .pipeThrough(new SSEDecoder());
+      .pipeThrough(BytesLineDecoder())
+      .pipeThrough(SSEDecoder());
 
     const results = await gather(decoded);
     expect(results.length).toBe(1);

libs/sdk-js/src/tests/stream.test.tsx

@@ -1,14 +1,58 @@
+import "@testing-library/jest-dom/vitest";
+
 import { describe, it, expect, beforeEach, afterEach, vi } from "vitest";
 import { render, screen, waitFor } from "@testing-library/react";
 import { userEvent } from "@testing-library/user-event";
 import { setupServer } from "msw/node";
-import { http, HttpResponse } from "msw";
+import { http } from "msw";
 import { useStream } from "../react/stream.js";
-import "@testing-library/jest-dom/vitest";
+import type { Message } from "../types.messages.js";
+
+import { StateGraph, MessagesAnnotation, START } from "@langchain/langgraph";
+import { MemorySaver } from "@langchain/langgraph-checkpoint";
+import { FakeStreamingChatModel } from "@langchain/core/utils/testing";
+import { AIMessage } from "@langchain/core/messages";
+import { createEmbedServer } from "@langchain/langgraph-api/experimental/embed";
+import { randomUUID } from "node:crypto";
+import { useState } from "react";
+
+const threads = (() => {
+  const THREADS: Record<
+    string,
+    { thread_id: string; metadata: Record<string, unknown> }
+  > = {};
+
+  return {
+    get: async (id: string) => THREADS[id],
+    put: async (
+      threadId: string,
+      { metadata }: { metadata?: Record<string, unknown> },
+    ) => {
+      THREADS[threadId] = { thread_id: threadId, metadata: metadata ?? {} };
+    },
+    delete: async (threadId: string) => {
+      delete THREADS[threadId];
+    },
+  };
+})();
+
+const checkpointer = new MemorySaver();
+
+const model = new FakeStreamingChatModel({ responses: [new AIMessage("Hey")] });
+const agent = new StateGraph(MessagesAnnotation)
+  .addNode("agent", async (state: { messages: Message[] }) => {
+    const response = await model.invoke(state.messages);
+    return { messages: [response] };
+  })
+  .addEdge(START, "agent")
+  .compile();
+
+const app = createEmbedServer({ graph: { agent }, checkpointer, threads });
+const server = setupServer(http.all("*", (ctx) => app.fetch(ctx.request)));
 
 function TestChatComponent() {
   const { messages, isLoading, error, submit, stop } = useStream({
-    assistantId: "test-assistant",
+    assistantId: "agent",
     apiKey: "test-api-key",
   });
 
@@ -42,353 +86,6 @@ function TestChatComponent() {
   );
 }
 
-// Mock server setup
-
-const server = setupServer(
-  // Mock thread creation
-  http.post("*/threads", () => {
-    return HttpResponse.json({ thread_id: "test-thread-id" });
-  }),
-
-  // Mock stream endpoint
-  http.post("*/threads/:threadId/runs/stream", async () => {
-    const encoder = new TextEncoder();
-    const sendSSE = (event: string, data: unknown) =>
-      encoder.encode(`event: ${event}\ndata: ${JSON.stringify(data)}\n\n`);
-
-    const stream = new ReadableStream({
-      async start(controller) {
-        await new Promise((resolve) => setTimeout(resolve, 10));
-
-        controller.enqueue(
-          sendSSE("metadata", {
-            run_id: "1f03278a-1734-6518-80a4-3390db59f960",
-            attempt: 1,
-          }),
-        );
-
-        controller.enqueue(
-          sendSSE("values", {
-            messages: [
-              {
-                content: "Hey",
-                additional_kwargs: {},
-                response_metadata: {},
-                type: "human",
-                name: null,
-                id: "2d8c0d9f-a614-4e44-b474-6a56e9471cf5",
-                example: false,
-              },
-            ],
-          }),
-        );
-
-        controller.enqueue(
-          sendSSE("messages", [
-            {
-              content: "",
-              additional_kwargs: {},
-              response_metadata: { model_name: "claude-3-7-sonnet-latest" },
-              type: "AIMessageChunk",
-              name: null,
-              id: "run-3e90ba6a-71d6-49e7-94a8-6bcac2fd0f40",
-              tool_calls: [],
-              invalid_tool_calls: [],
-              tool_call_chunks: [],
-            },
-            { run_attempt: 1 },
-          ]),
-        );
-
-        controller.enqueue(
-          sendSSE("messages", [
-            {
-              content: "Hello",
-              additional_kwargs: {},
-              response_metadata: { model_name: "claude-3-7-sonnet-latest" },
-              type: "AIMessageChunk",
-              name: null,
-              id: "run-3e90ba6a-71d6-49e7-94a8-6bcac2fd0f40",
-              tool_calls: [],
-              invalid_tool_calls: [],
-              tool_call_chunks: [],
-            },
-            { run_attempt: 1 },
-          ]),
-        );
-
-        controller.enqueue(
-          sendSSE("messages", [
-            {
-              content: "! How can I assist you today?",
-              additional_kwargs: {},
-              response_metadata: { model_name: "claude-3-7-sonnet-latest" },
-              type: "AIMessageChunk",
-              name: null,
-              id: "run-3e90ba6a-71d6-49e7-94a8-6bcac2fd0f40",
-              tool_calls: [],
-              invalid_tool_calls: [],
-              tool_call_chunks: [],
-            },
-            { run_attempt: 1 },
-          ]),
-        );
-
-        controller.enqueue(
-          sendSSE("messages", [
-            {
-              content: "",
-              additional_kwargs: {},
-              response_metadata: {
-                stop_reason: "end_turn",
-                stop_sequence: null,
-              },
-              type: "AIMessageChunk",
-              name: null,
-              id: "run-3e90ba6a-71d6-49e7-94a8-6bcac2fd0f40",
-              tool_calls: [],
-              invalid_tool_calls: [],
-              tool_call_chunks: [],
-            },
-            { run_attempt: 1 },
-          ]),
-        );
-
-        controller.enqueue(
-          sendSSE("values", {
-            messages: [
-              {
-                content: "Hey",
-                additional_kwargs: {},
-                response_metadata: {},
-                type: "human",
-                name: null,
-                id: "2d8c0d9f-a614-4e44-b474-6a56e9471cf5",
-                example: false,
-              },
-              {
-                content: "Hello! How can I assist you today?",
-                additional_kwargs: {},
-                response_metadata: {
-                  model_name: "claude-3-7-sonnet-latest",
-                  stop_reason: "end_turn",
-                  stop_sequence: null,
-                },
-                type: "ai",
-                name: null,
-                id: "run-3e90ba6a-71d6-49e7-94a8-6bcac2fd0f40",
-                tool_calls: [],
-                invalid_tool_calls: [],
-              },
-            ],
-          }),
-        );
-
-        controller.close();
-      },
-    });
-
-    server.use(
-      http.post("*/threads/:threadId/history", () => {
-        return HttpResponse.json([
-          {
-            values: {
-              messages: [
-                {
-                  content: "Hey",
-                  additional_kwargs: {},
-                  response_metadata: {},
-                  type: "human",
-                  name: null,
-                  id: "2d8c0d9f-a614-4e44-b474-6a56e9471cf5",
-                  example: false,
-                },
-                {
-                  content: "Hello! How can I assist you today?",
-                  additional_kwargs: {},
-                  response_metadata: {
-                    model_name: "claude-3-7-sonnet-latest",
-                    stop_reason: "end_turn",
-                    stop_sequence: null,
-                  },
-                  type: "ai",
-                  name: null,
-                  id: "run-3e90ba6a-71d6-49e7-94a8-6bcac2fd0f40",
-                  example: false,
-                  tool_calls: [],
-                  invalid_tool_calls: [],
-                },
-              ],
-            },
-            next: [],
-            tasks: [],
-            metadata: {
-              run_attempt: 1,
-              source: "loop",
-              writes: {
-                agent: {
-                  messages: [
-                    {
-                      content: "Hello! How can I assist you today?",
-                      additional_kwargs: {},
-                      response_metadata: {
-                        model_name: "claude-3-7-sonnet-latest",
-                        stop_reason: "end_turn",
-                        stop_sequence: null,
-                      },
-                      type: "ai",
-                      name: null,
-                      id: "run-3e90ba6a-71d6-49e7-94a8-6bcac2fd0f40",
-                      example: false,
-                      tool_calls: [],
-                      invalid_tool_calls: [],
-                    },
-                  ],
-                },
-              },
-              step: 1,
-              parents: {},
-            },
-            created_at: "2025-05-16T17:10:16.987537+00:00",
-            checkpoint: {
-              checkpoint_id: "1f03278a-38cf-6c68-8001-22b77ac43ff6",
-              thread_id: "b06fd92a-955c-446e-b233-7977716c4a9c",
-              checkpoint_ns: "",
-            },
-            parent_checkpoint: {
-              checkpoint_id: "1f03278a-206b-67c6-8000-ac34a0872e1a",
-              thread_id: "b06fd92a-955c-446e-b233-7977716c4a9c",
-              checkpoint_ns: "",
-            },
-            checkpoint_id: "1f03278a-38cf-6c68-8001-22b77ac43ff6",
-            parent_checkpoint_id: "1f03278a-206b-67c6-8000-ac34a0872e1a",
-          },
-          {
-            values: {
-              messages: [
-                {
-                  content: "Hey",
-                  additional_kwargs: {},
-                  response_metadata: {},
-                  type: "human",
-                  name: null,
-                  id: "2d8c0d9f-a614-4e44-b474-6a56e9471cf5",
-                  example: false,
-                },
-              ],
-            },
-            next: ["agent"],
-            tasks: [
-              {
-                id: "e1b7b52b-a78e-4b32-0c89-e06bf46405ed",
-                name: "agent",
-                path: ["__pregel_pull", "agent"],
-                error: null,
-                interrupts: [],
-                checkpoint: null,
-                state: null,
-                result: {
-                  messages: [
-                    {
-                      content: "Hello! How can I assist you today?",
-                      additional_kwargs: {},
-                      response_metadata: {
-                        model_name: "claude-3-7-sonnet-latest",
-                        stop_reason: "end_turn",
-                        stop_sequence: null,
-                      },
-                      type: "ai",
-                      name: null,
-                      id: "run-3e90ba6a-71d6-49e7-94a8-6bcac2fd0f40",
-                      example: false,
-                      tool_calls: [],
-                      invalid_tool_calls: [],
-                    },
-                  ],
-                },
-              },
-            ],
-            metadata: {
-              run_attempt: 1,
-            },
-            created_at: "2025-05-16T17:10:14.429889+00:00",
-            checkpoint: {
-              checkpoint_id: "1f03278a-206b-67c6-8000-ac34a0872e1a",
-              thread_id: "b06fd92a-955c-446e-b233-7977716c4a9c",
-              checkpoint_ns: "",
-            },
-            parent_checkpoint: {
-              checkpoint_id: "1f03278a-2067-6590-bfff-3fb740466fc3",
-              thread_id: "b06fd92a-955c-446e-b233-7977716c4a9c",
-              checkpoint_ns: "",
-            },
-            checkpoint_id: "1f03278a-206b-67c6-8000-ac34a0872e1a",
-            parent_checkpoint_id: "1f03278a-2067-6590-bfff-3fb740466fc3",
-          },
-          {
-            values: {
-              messages: [],
-            },
-            next: ["__start__"],
-            tasks: [
-              {
-                id: "291af033-2ddc-3320-8bbc-28060057cae5",
-                name: "__start__",
-                path: ["__pregel_pull", "__start__"],
-                error: null,
-                interrupts: [],
-                checkpoint: null,
-                state: null,
-                result: {
-                  messages: [
-                    {
-                      id: "2d8c0d9f-a614-4e44-b474-6a56e9471cf5",
-                      type: "human",
-                      content: "Hey",
-                    },
-                  ],
-                },
-              },
-            ],
-            metadata: {
-              run_attempt: 1,
-              source: "input",
-              writes: {
-                __start__: {
-                  messages: [
-                    {
-                      id: "2d8c0d9f-a614-4e44-b474-6a56e9471cf5",
-                      type: "human",
-                      content: "Hey",
-                    },
-                  ],
-                },
-              },
-              step: -1,
-              parents: {},
-            },
-            created_at: "2025-05-16T17:10:14.428191+00:00",
-            checkpoint: {
-              checkpoint_id: "1f03278a-2067-6590-bfff-3fb740466fc3",
-              thread_id: "b06fd92a-955c-446e-b233-7977716c4a9c",
-              checkpoint_ns: "",
-            },
-            parent_checkpoint: null,
-            checkpoint_id: "1f03278a-2067-6590-bfff-3fb740466fc3",
-            parent_checkpoint_id: null,
-          },
-        ]);
-      }),
-    );
-
-    return new HttpResponse(stream, {
-      headers: { "Content-Type": "text/event-stream" },
-    });
-  }),
-);
-
-server.use;
-
 describe("useStream", () => {
   beforeEach(() => server.listen());
 
@@ -417,10 +114,8 @@ describe("useStream", () => {
 
     // Wait for messages to appear
     await waitFor(() => {
-      expect(screen.getByTestId("message-0")).toHaveTextContent("Hey");
-      expect(screen.getByTestId("message-1")).toHaveTextContent(
-        "Hello! How can I assist you today?",
-      );
+      expect(screen.getByTestId("message-0")).toHaveTextContent("Hello");
+      expect(screen.getByTestId("message-1")).toHaveTextContent("Hey");
     });
 
     // Check final state
@@ -440,4 +135,316 @@ describe("useStream", () => {
       expect(screen.getByTestId("loading")).toHaveTextContent("Not loading");
     });
   });
+
+  it("displays initial values immediately and clears them when submitting", async () => {
+    const user = userEvent.setup();
+
+    function TestCachedComponent() {
+      const { messages, values, submit } = useStream<{
+        messages: Message[];
+      }>({
+        assistantId: "agent",
+        apiKey: "test-api-key",
+        initialValues: {
+          messages: [
+            { id: "cached-1", type: "human", content: "Cached user message" },
+            { id: "cached-2", type: "ai", content: "Cached AI response" },
+          ],
+        },
+      });
+
+      return (
+        <div>
+          <div data-testid="messages">
+            {messages.map((msg, i) => (
+              <div
+                key={msg.id ?? i}
+                data-testid={
+                  msg.id?.includes("cached")
+                    ? `message-cached-${i}`
+                    : `message-${i}`
+                }
+              >
+                {typeof msg.content === "string"
+                  ? msg.content
+                  : JSON.stringify(msg.content)}
+              </div>
+            ))}
+          </div>
+          <div data-testid="values">{JSON.stringify(values)}</div>
+          <button
+            data-testid="submit"
+            onClick={() =>
+              submit({ messages: [{ content: "Hello", type: "human" }] })
+            }
+          >
+            Submit
+          </button>
+        </div>
+      );
+    }
+
+    render(<TestCachedComponent />);
+
+    // Should immediately show cached messages
+    expect(screen.getByTestId("message-cached-0")).toHaveTextContent(
+      "Cached user message",
+    );
+    expect(screen.getByTestId("message-cached-1")).toHaveTextContent(
+      "Cached AI response",
+    );
+
+    // Values should include initial values
+    expect(screen.getByTestId("values")).toHaveTextContent(
+      "Cached user message",
+    );
+
+    // Submitting should clear out the cached messages
+    await user.click(screen.getByTestId("submit"));
+
+    // Wait for messages to appear
+    await waitFor(() => {
+      expect(screen.getByTestId("message-0")).toHaveTextContent("Hello");
+      expect(screen.getByTestId("message-1")).toHaveTextContent("Hey");
+    });
+  });
+
+  it("accepts newThreadId option without errors", async () => {
+    const user = userEvent.setup();
+
+    const spy = vi.fn();
+    const predeterminedThreadId = randomUUID();
+
+    // Test that newThreadId option can be passed without causing errors
+    function TestNewThreadComponent() {
+      const stream = useStream<{ messages: Message[] }>({
+        assistantId: "agent",
+        apiKey: "test-api-key",
+        threadId: null, // Start with no thread
+        onThreadId: spy, // Mock callback
+      });
+
+      return (
+        <div>
+          <div data-testid="loading">
+            {stream.isLoading ? "Loading..." : "Not loading"}
+          </div>
+          <div data-testid="thread-id">
+            {stream.client ? "Client ready" : "No client"}
+          </div>
+          <button
+            data-testid="submit"
+            onClick={() =>
+              stream.submit({}, { threadId: predeterminedThreadId })
+            }
+          >
+            Submit
+          </button>
+        </div>
+      );
+    }
+
+    render(<TestNewThreadComponent />);
+
+    // Should render without errors
+    expect(screen.getByTestId("loading")).toHaveTextContent("Not loading");
+    expect(screen.getByTestId("thread-id")).toHaveTextContent("Client ready");
+
+    await user.click(screen.getByTestId("submit"));
+    expect(spy).toHaveBeenCalledWith(predeterminedThreadId);
+    expect(await threads.get(predeterminedThreadId)).toEqual({
+      thread_id: predeterminedThreadId,
+      metadata: {
+        graph_id: "agent",
+        assistant_id: "agent",
+      },
+    });
+  });
+
+  it("onStop callback is called when stop is called", async () => {
+    const user = userEvent.setup();
+    const onStopCallback = vi.fn();
+
+    function TestComponent() {
+      const { submit, stop } = useStream({
+        assistantId: "agent",
+        apiKey: "test-api-key",
+        onStop: onStopCallback,
+      });
+
+      return (
+        <div>
+          <button data-testid="submit" onClick={() => submit({})}>
+            Send
+          </button>
+          <button data-testid="stop" onClick={stop}>
+            Stop
+          </button>
+        </div>
+      );
+    }
+
+    render(<TestComponent />);
+
+    // Start a stream and stop it
+    await user.click(screen.getByTestId("submit"));
+    await user.click(screen.getByTestId("stop"));
+
+    // Verify onStop was called with mutate function
+    expect(onStopCallback).toHaveBeenCalledTimes(1);
+    expect(onStopCallback).toHaveBeenCalledWith(
+      expect.objectContaining({
+        mutate: expect.any(Function),
+      }),
+    );
+  });
+
+  it("onStop mutate function updates stream values immediately", async () => {
+    const user = userEvent.setup();
+
+    function TestComponent() {
+      const [stopped, setStopped] = useState(false);
+      const { submit, stop, messages } = useStream<{ messages: Message[] }>({
+        assistantId: "agent",
+        apiKey: "test-api-key",
+        onStop: ({ mutate }) => {
+          setStopped(true);
+          mutate((prev) => ({
+            ...prev,
+            messages: [
+              ...(prev.messages ?? []),
+              { type: "ai", content: "Stream stopped" },
+            ],
+          }));
+        },
+      });
+
+      return (
+        <div>
+          <div data-testid="stopped-status">
+            {stopped ? "Stopped" : "Not stopped"}
+          </div>
+          <div data-testid="messages">
+            {messages.map((msg, i) => (
+              <div key={msg.id ?? i} data-testid={`message-${i}`}>
+                {typeof msg.content === "string"
+                  ? msg.content
+                  : JSON.stringify(msg.content)}
+              </div>
+            ))}
+          </div>
+          <button data-testid="submit" onClick={() => submit({})}>
+            Send
+          </button>
+          <button data-testid="stop" onClick={stop}>
+            Stop
+          </button>
+        </div>
+      );
+    }
+
+    render(<TestComponent />);
+
+    // Initial state
+    expect(screen.getByTestId("stopped-status")).toHaveTextContent(
+      "Not stopped",
+    );
+
+    // Start and stop stream
+    await user.click(screen.getByTestId("submit"));
+    await user.click(screen.getByTestId("stop"));
+
+    // Verify state was updated immediately
+    await waitFor(() => {
+      expect(screen.getByTestId("stopped-status")).toHaveTextContent("Stopped");
+      expect(screen.getByTestId("message-0")).toHaveTextContent(
+        "Stream stopped",
+      );
+    });
+  });
+
+  it("onStop handles functional updates correctly", async () => {
+    const user = userEvent.setup();
+
+    function TestComponent() {
+      const { submit, stop, values } = useStream({
+        assistantId: "agent",
+        apiKey: "test-api-key",
+        initialValues: {
+          counter: 5,
+          items: ["item1", "item2"],
+        },
+        onStop: ({ mutate }) => {
+          mutate((prev: any) => ({
+            ...prev,
+            counter: (prev.counter || 0) + 10,
+            items: [...(prev.items || []), "stopped"],
+          }));
+        },
+      });
+
+      return (
+        <div>
+          <div data-testid="counter">{(values as any).counter}</div>
+          <div data-testid="items">{(values as any).items?.join(", ")}</div>
+          <button data-testid="submit" onClick={() => submit({})}>
+            Send
+          </button>
+          <button data-testid="stop" onClick={stop}>
+            Stop
+          </button>
+        </div>
+      );
+    }
+
+    render(<TestComponent />);
+
+    // Initial state
+    expect(screen.getByTestId("counter")).toHaveTextContent("5");
+    expect(screen.getByTestId("items")).toHaveTextContent("item1, item2");
+
+    // Start and stop stream
+    await user.click(screen.getByTestId("submit"));
+    await user.click(screen.getByTestId("stop"));
+
+    // Verify functional update was applied correctly
+    await waitFor(() => {
+      expect(screen.getByTestId("counter")).toHaveTextContent("15");
+      expect(screen.getByTestId("items")).toHaveTextContent(
+        "item1, item2, stopped",
+      );
+    });
+  });
+
+  it("onStop is not called when stream completes naturally", async () => {
+    const user = userEvent.setup();
+
+    const onStopCallback = vi.fn();
+
+    function TestComponent() {
+      const { submit } = useStream({
+        assistantId: "agent",
+        apiKey: "test-api-key",
+        onStop: onStopCallback,
+      });
+
+      return (
+        <div>
+          <button data-testid="submit" onClick={() => submit({})}>
+            Send
+          </button>
+        </div>
+      );
+    }
+
+    render(<TestComponent />);
+
+    // Start a stream and let it complete naturally
+    await user.click(screen.getByTestId("submit"));
+
+    // Wait for stream to complete naturally
+    await waitFor(() => {
+      expect(onStopCallback).not.toHaveBeenCalled();
+    });
+  });
 });

libs/sdk-js/src/types.messages.ts

@@ -13,16 +13,22 @@ type MessageContent = string | MessageContentComplex[];
  */
 type MessageAdditionalKwargs = Record<string, unknown>;
 
-export type HumanMessage = {
-  type: "human";
-  id?: string | undefined;
+type BaseMessage = {
+  additional_kwargs?: MessageAdditionalKwargs | undefined;
   content: MessageContent;
+  id?: string | undefined;
+  name?: string | undefined;
+  response_metadata?: Record<string, unknown> | undefined;
 };
 
-export type AIMessage = {
+export type HumanMessage = BaseMessage & {
+  type: "human";
+  example?: boolean | undefined;
+};
+
+export type AIMessage = BaseMessage & {
   type: "ai";
-  id?: string | undefined;
-  content: MessageContent;
+  example?: boolean | undefined;
   tool_calls?:
     | {
         name: string;
@@ -57,19 +63,12 @@ export type AIMessage = {
           | undefined;
       }
     | undefined;
-  additional_kwargs?: MessageAdditionalKwargs | undefined;
-  response_metadata?: Record<string, unknown> | undefined;
 };
 
-export type ToolMessage = {
+export type ToolMessage = BaseMessage & {
   type: "tool";
-  name?: string | undefined;
-  id?: string | undefined;
-  content: MessageContent;
   status?: "error" | "success" | undefined;
   tool_call_id: string;
-  additional_kwargs?: MessageAdditionalKwargs | undefined;
-  response_metadata?: Record<string, unknown> | undefined;
   /**
    * Artifact of the Tool execution which is not meant to be sent to the model.
    *
@@ -81,22 +80,16 @@ export type ToolMessage = {
   artifact?: any;
 };
 
-export type SystemMessage = {
+export type SystemMessage = BaseMessage & {
   type: "system";
-  id?: string | undefined;
-  content: MessageContent;
 };
 
-export type FunctionMessage = {
+export type FunctionMessage = BaseMessage & {
   type: "function";
-  id?: string | undefined;
-  content: MessageContent;
 };
 
-export type RemoveMessage = {
+export type RemoveMessage = BaseMessage & {
   type: "remove";
-  id: string;
-  content: MessageContent;
 };
 
 export type Message =

libs/sdk-js/src/utils/sse.ts

@@ -6,90 +6,88 @@ const SPACE = " ".charCodeAt(0);
 
 const TRAILING_NEWLINE = [CR, LF];
 
-export class BytesLineDecoder extends TransformStream<Uint8Array, Uint8Array> {
-  constructor() {
-    let buffer: Uint8Array[] = [];
-    let trailingCr = false;
+export function BytesLineDecoder() {
+  let buffer: Uint8Array[] = [];
+  let trailingCr = false;
 
-    super({
-      start() {
-        buffer = [];
+  return new TransformStream<Uint8Array, Uint8Array>({
+    start() {
+      buffer = [];
+      trailingCr = false;
+    },
+
+    transform(chunk, controller) {
+      // See https://docs.python.org/3/glossary.html#term-universal-newlines
+      let text = chunk;
+
+      // Handle trailing CR from previous chunk
+      if (trailingCr) {
+        text = joinArrays([[CR], text]);
         trailingCr = false;
-      },
+      }
 
-      transform(chunk, controller) {
-        // See https://docs.python.org/3/glossary.html#term-universal-newlines
-        let text = chunk;
+      // Check for trailing CR in current chunk
+      if (text.length > 0 && text.at(-1) === CR) {
+        trailingCr = true;
+        text = text.subarray(0, -1);
+      }
 
-        // Handle trailing CR from previous chunk
-        if (trailingCr) {
-          text = joinArrays([[CR], text]);
-          trailingCr = false;
-        }
+      if (!text.length) return;
+      const trailingNewline = TRAILING_NEWLINE.includes(text.at(-1)!);
 
-        // Check for trailing CR in current chunk
-        if (text.length > 0 && text.at(-1) === CR) {
-          trailingCr = true;
-          text = text.subarray(0, -1);
-        }
+      const lastIdx = text.length - 1;
+      const { lines } = text.reduce<{ lines: Uint8Array[]; from: number }>(
+        (acc, cur, idx) => {
+          if (acc.from > idx) return acc;
 
-        if (!text.length) return;
-        const trailingNewline = TRAILING_NEWLINE.includes(text.at(-1)!);
-
-        const lastIdx = text.length - 1;
-        const { lines } = text.reduce<{ lines: Uint8Array[]; from: number }>(
-          (acc, cur, idx) => {
-            if (acc.from > idx) return acc;
-
-            if (cur === CR || cur === LF) {
-              acc.lines.push(text.subarray(acc.from, idx));
-              if (cur === CR && text[idx + 1] === LF) {
-                acc.from = idx + 2;
-              } else {
-                acc.from = idx + 1;
-              }
+          if (cur === CR || cur === LF) {
+            acc.lines.push(text.subarray(acc.from, idx));
+            if (cur === CR && text[idx + 1] === LF) {
+              acc.from = idx + 2;
+            } else {
+              acc.from = idx + 1;
             }
+          }
 
-            if (idx === lastIdx && acc.from <= lastIdx) {
-              acc.lines.push(text.subarray(acc.from));
-            }
+          if (idx === lastIdx && acc.from <= lastIdx) {
+            acc.lines.push(text.subarray(acc.from));
+          }
 
-            return acc;
-          },
-          { lines: [], from: 0 },
-        );
+          return acc;
+        },
+        { lines: [], from: 0 },
+      );
 
-        if (lines.length === 1 && !trailingNewline) {
-          buffer.push(lines[0]);
-          return;
-        }
+      if (lines.length === 1 && !trailingNewline) {
+        buffer.push(lines[0]);
+        return;
+      }
 
-        if (buffer.length) {
-          // Include existing buffer in first line
-          buffer.push(lines[0]);
-          lines[0] = joinArrays(buffer);
-          buffer = [];
-        }
+      if (buffer.length) {
+        // Include existing buffer in first line
+        buffer.push(lines[0]);
+        lines[0] = joinArrays(buffer);
+        buffer = [];
+      }
 
-        if (!trailingNewline) {
-          // If the last segment is not newline terminated,
-          // buffer it for the next chunk
-          if (lines.length) buffer = [lines.pop()!];
-        }
+      if (!trailingNewline) {
+        // If the last segment is not newline terminated,
+        // buffer it for the next chunk
+        if (lines.length) buffer = [lines.pop()!];
+      }
 
-        // Enqueue complete lines
-        for (const line of lines) {
-          controller.enqueue(line);
-        }
-      },
+      // Enqueue complete lines
+      for (const line of lines) {
+        controller.enqueue(line);
+      }
+    },
 
-      flush(controller) {
-        if (buffer.length) {
-          controller.enqueue(joinArrays(buffer));
-        }
-      },
-    });
-  }
+    flush(controller) {
+      if (buffer.length) {
+        controller.enqueue(joinArrays(buffer));
+      }
+    },
+  });
 }
 
 interface StreamPart {
@@ -98,69 +96,67 @@ interface StreamPart {
   data: unknown;
 }
 
-export class SSEDecoder extends TransformStream<Uint8Array, StreamPart> {
-  constructor() {
-    let event = "";
-    let data: Uint8Array[] = [];
-    let lastEventId = "";
-    let retry: number | null = null;
+export function SSEDecoder() {
+  let event = "";
+  let data: Uint8Array[] = [];
+  let lastEventId = "";
+  let retry: number | null = null;
 
-    const decoder = new TextDecoder();
+  const decoder = new TextDecoder();
 
-    super({
-      transform(chunk, controller) {
-        // Handle empty line case
-        if (!chunk.length) {
-          if (!event && !data.length && !lastEventId && retry == null) return;
+  return new TransformStream<Uint8Array, StreamPart>({
+    transform(chunk, controller) {
+      // Handle empty line case
+      if (!chunk.length) {
+        if (!event && !data.length && !lastEventId && retry == null) return;
 
-          const sse = {
-            id: lastEventId || undefined,
-            event,
-            data: data.length ? decodeArraysToJson(decoder, data) : null,
-          };
+        const sse = {
+          id: lastEventId || undefined,
+          event,
+          data: data.length ? decodeArraysToJson(decoder, data) : null,
+        };
 
-          // NOTE: as per the SSE spec, do not reset lastEventId
-          event = "";
-          data = [];
-          retry = null;
+        // NOTE: as per the SSE spec, do not reset lastEventId
+        event = "";
+        data = [];
+        retry = null;
 
-          controller.enqueue(sse);
-          return;
-        }
+        controller.enqueue(sse);
+        return;
+      }
 
-        // Ignore comments
-        if (chunk[0] === COLON) return;
+      // Ignore comments
+      if (chunk[0] === COLON) return;
 
-        const sepIdx = chunk.indexOf(COLON);
-        if (sepIdx === -1) return;
+      const sepIdx = chunk.indexOf(COLON);
+      if (sepIdx === -1) return;
 
-        const fieldName = decoder.decode(chunk.subarray(0, sepIdx));
-        let value = chunk.subarray(sepIdx + 1);
-        if (value[0] === SPACE) value = value.subarray(1);
+      const fieldName = decoder.decode(chunk.subarray(0, sepIdx));
+      let value = chunk.subarray(sepIdx + 1);
+      if (value[0] === SPACE) value = value.subarray(1);
 
-        if (fieldName === "event") {
-          event = decoder.decode(value);
-        } else if (fieldName === "data") {
-          data.push(value);
-        } else if (fieldName === "id") {
-          if (value.indexOf(NULL) === -1) lastEventId = decoder.decode(value);
-        } else if (fieldName === "retry") {
-          const retryNum = Number.parseInt(decoder.decode(value));
-          if (!Number.isNaN(retryNum)) retry = retryNum;
-        }
-      },
+      if (fieldName === "event") {
+        event = decoder.decode(value);
+      } else if (fieldName === "data") {
+        data.push(value);
+      } else if (fieldName === "id") {
+        if (value.indexOf(NULL) === -1) lastEventId = decoder.decode(value);
+      } else if (fieldName === "retry") {
+        const retryNum = Number.parseInt(decoder.decode(value));
+        if (!Number.isNaN(retryNum)) retry = retryNum;
+      }
+    },
 
-      flush(controller) {
-        if (event) {
-          controller.enqueue({
-            id: lastEventId || undefined,
-            event,
-            data: data.length ? decodeArraysToJson(decoder, data) : null,
-          });
-        }
-      },
-    });
-  }
+    flush(controller) {
+      if (event) {
+        controller.enqueue({
+          id: lastEventId || undefined,
+          event,
+          data: data.length ? decodeArraysToJson(decoder, data) : null,
+        });
+      }
+    },
+  });
 }
 
 function joinArrays(data: ArrayLike<number>[]) {