fix(cli): only render progress when in TTY (#4299)

Prevents logging terminal clear commands in non-TTY environments
(LangSmith / CI)

.github/workflows/_integration_test.yml

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

.github/workflows/_lint.yml

@@ -9,7 +9,7 @@ on:
         description: "From which folder this pipeline executes"
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "2.1.2"
 
   # This env var allows us to get inline annotations when ruff has complaints.
   RUFF_OUTPUT_FORMAT: github
@@ -50,12 +50,6 @@ jobs:
         working-directory: ${{ inputs.working-directory }}
         run: poetry check
 
-      - name: Check lock file
-        if: steps.changed-files.outputs.all
-        shell: bash
-        working-directory: ${{ inputs.working-directory }}
-        run: poetry check --lock
-
       - name: Install dependencies
         if: steps.changed-files.outputs.all
         # Also installs dev/lint/test/typing dependencies, to ensure we have

.github/workflows/_test.yml

@@ -9,7 +9,7 @@ on:
         description: "From which folder this pipeline executes"
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "2.1.2"
 
 jobs:
   build:
@@ -39,12 +39,6 @@ jobs:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_RO_TOKEN }}
 
-      - name: Check Lock
-        shell: bash
-        working-directory: ${{ inputs.working-directory }}
-        run: |
-          poetry check --lock
-
       - name: Install dependencies
         shell: bash
         working-directory: ${{ inputs.working-directory }}

.github/workflows/_test_langgraph.yml

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

.github/workflows/_test_release.yml

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

.github/workflows/_test_scheduler_kafka.yml

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

.github/workflows/baseline.yml

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

.github/workflows/bench.yml

@@ -6,7 +6,7 @@ on:
       - "libs/**"
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "2.1.2"
 
 jobs:
   benchmark:

.github/workflows/ci.yml

@@ -17,7 +17,7 @@ concurrency:
   cancel-in-progress: true
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "2.1.2"
 
 jobs:
   changes:

.github/workflows/deploy_docs.yml

@@ -10,7 +10,7 @@ on:
   workflow_dispatch:
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "2.1.2"
 
 permissions:
   contents: read

.github/workflows/link_check.yml

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

.github/workflows/release.yml

@@ -10,7 +10,7 @@ on:
 
 env:
   PYTHON_VERSION: "3.11"
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "2.1.2"
 
 jobs:
   build:

.github/workflows/run_notebooks.yml

@@ -9,7 +9,7 @@ on:
         type: string
         description: "JSON string of changed files"
   schedule:
-    - cron: '0 13 * * *'
+    - cron: "0 13 * * *"
 
 defaults:
   run:
@@ -30,12 +30,12 @@ jobs:
         uses: "./.github/actions/poetry_setup"
         with:
           python-version: 3.11
-          poetry-version: 1.7.1
+          poetry-version: 2.1.2
           cache-key: test-langgraph-notebooks
 
       - name: Install dependencies
         run: |
-          poetry install --with test
+          poetry install --with test --no-root
           poetry run pip install jupyter
 
       - name: Start services

README.md

@@ -40,6 +40,9 @@ agent.invoke(
 )
 ```
 
+> [!TIP]
+> Check out [this guide](https://langchain-ai.github.io/langgraph/tutorials/workflows/) that walks through implementing common patterns (workflows and agents) in LangGraph. 
+
 ## Why use LangGraph?
 
 LangGraph is built for developers who want to build powerful, adaptable AI agents. Developers choose LangGraph for:

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

@@ -0,0 +1 @@
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

docs/docs/cloud/deployment/cloud.md

@@ -1,6 +1,6 @@
-# How to Deploy to LangGraph Cloud
+# How to Deploy to Cloud SaaS (Beta)
 
-LangGraph Cloud is available within <a href="https://www.langchain.com/langsmith" target="_blank">LangSmith</a>. To deploy a LangGraph Cloud API, navigate to the <a href="https://smith.langchain.com/" target="_blank">LangSmith UI</a>.
+Before deploying, review the [conceptual guide for the Cloud SaaS](../../concepts/langgraph_cloud.md) deployment option.
 
 ## Prerequisites
 

docs/docs/cloud/deployment/self_hosted_control_plane.md

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

docs/docs/cloud/deployment/self_hosted_data_plane.md

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

docs/docs/cloud/deployment/standalone_container.md

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

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

@@ -12,10 +12,6 @@ Generative user interfaces (Generative UI) allows agents to go beyond text and g
 
 LangGraph Platform supports colocating your React components with your graph code. This allows you to focus on building specific UI components for your graph while easily plugging into existing chat interfaces such as [Agent Chat](https://agentchat.vercel.app) and loading the code only when actually needed.
 
-!!! warning "LangGraph.js only"
-
-    Currently only LangGraph.js supports Generative UI. Support for Python is coming soon.
-
 ## Tutorial
 
 ### 1. Define and configure UI components
@@ -74,58 +70,105 @@ CSS and Tailwind 4.x is also supported out of the box, so you can freely use Tai
 
 ### 2. Send the UI components in your graph
 
-Use the `typedUi` utility to emit UI elements from your agent nodes:
+=== "Python"
 
-```typescript title="src/agent/index.ts"
-import {
-  typedUi,
-  uiMessageReducer,
-} from "@langchain/langgraph-sdk/react-ui/server";
+    ```python title="src/agent.py"
+    import uuid
+    from typing import Annotated, Sequence, TypedDict
 
-import { ChatOpenAI } from "@langchain/openai";
-import { v4 as uuidv4 } from "uuid";
-import { z } from "zod";
+    from langchain_core.messages import AIMessage, BaseMessage
+    from langchain_openai import ChatOpenAI
+    from langgraph.graph import StateGraph
+    from langgraph.graph.message import add_messages
+    from langgraph.graph.ui import AnyUIMessage, ui_message_reducer, push_ui_message
 
-import type ComponentMap from "./ui.js";
 
-import {
-  Annotation,
-  MessagesAnnotation,
-  StateGraph,
-  type LangGraphRunnableConfig,
-} from "@langchain/langgraph";
+    class AgentState(TypedDict):  # noqa: D101
+        messages: Annotated[Sequence[BaseMessage], add_messages]
+        ui: Annotated[Sequence[AnyUIMessage], ui_message_reducer]
 
-const AgentState = Annotation.Root({
-  ...MessagesAnnotation.spec,
-  ui: Annotation({ reducer: uiMessageReducer, default: () => [] }),
-});
 
-export const graph = new StateGraph(AgentState)
-  .addNode("weather", async (state, config) => {
-    // Provide the type of the component map to ensure
-    // type safety of `ui.push()` calls as well as
-    // pushing the messages to the `ui` and sending a custom event as well.
-    const ui = typedUi<typeof ComponentMap>(config);
+    async def weather(state: AgentState):
+        class WeatherOutput(TypedDict):
+            city: str
 
-    const weather = await new ChatOpenAI({ model: "gpt-4o-mini" })
-      .withStructuredOutput(z.object({ city: z.string() }))
-      .withConfig({ tags: ["langsmith:nostream"] })
-      .invoke(state.messages);
+        weather: WeatherOutput = (
+            await ChatOpenAI(model="gpt-4o-mini")
+            .with_structured_output(WeatherOutput)
+            .with_config({"tags": ["nostream"]})
+            .ainvoke(state["messages"])
+        )
 
-    const response = {
-      id: uuidv4(),
-      type: "ai",
-      content: `Here's the weather for ${weather.city}`,
-    };
+        message = AIMessage(
+            id=str(uuid.uuid4()),
+            content=f"Here's the weather for {weather['city']}",
+        )
 
-    // Emit UI elements with associated AI message
-    ui.push({ name: "weather", props: weather }, { message: response });
+        # Emit UI elements associated with the message
+        push_ui_message("weather", weather, message=message)
+        return {"messages": [message]}
 
-    return { messages: [response] };
-  })
-  .addEdge("__start__", "weather")
-  .compile();
-```
+
+    workflow = StateGraph(AgentState)
+    workflow.add_node(weather)
+    workflow.add_edge("__start__", "weather")
+    graph = workflow.compile()
+    ```
+
+=== "JS"
+
+    Use the `typedUi` utility to emit UI elements from your agent nodes:
+
+    ```typescript title="src/agent/index.ts"
+    import {
+      typedUi,
+      uiMessageReducer,
+    } from "@langchain/langgraph-sdk/react-ui/server";
+
+    import { ChatOpenAI } from "@langchain/openai";
+    import { v4 as uuidv4 } from "uuid";
+    import { z } from "zod";
+
+    import type ComponentMap from "./ui.js";
+
+    import {
+      Annotation,
+      MessagesAnnotation,
+      StateGraph,
+      type LangGraphRunnableConfig,
+    } from "@langchain/langgraph";
+
+    const AgentState = Annotation.Root({
+      ...MessagesAnnotation.spec,
+      ui: Annotation({ reducer: uiMessageReducer, default: () => [] }),
+    });
+
+    export const graph = new StateGraph(AgentState)
+      .addNode("weather", async (state, config) => {
+        // Provide the type of the component map to ensure
+        // type safety of `ui.push()` calls as well as
+        // pushing the messages to the `ui` and sending a custom event as well.
+        const ui = typedUi<typeof ComponentMap>(config);
+
+        const weather = await new ChatOpenAI({ model: "gpt-4o-mini" })
+          .withStructuredOutput(z.object({ city: z.string() }))
+          .withConfig({ tags: ["nostream"] })
+          .invoke(state.messages);
+
+        const response = {
+          id: uuidv4(),
+          type: "ai",
+          content: `Here's the weather for ${weather.city}`,
+        };
+
+        // Emit UI elements associated with the AI message
+        ui.push({ name: "weather", props: weather }, { message: response });
+
+        return { messages: [response] };
+      })
+      .addEdge("__start__", "weather")
+      .compile();
+    ```
 
 ### 3. Handle UI elements in your React application
 
@@ -294,18 +337,29 @@ const { thread, submit } = useStream({
 
 ### Remove UI messages from state
 
-Similar to how messages can be removed from the state by appending a RemoveMessage you can remove an UI message from the state by calling `ui.delete` with the ID of the UI message.
+Similar to how messages can be removed from the state by appending a RemoveMessage you can remove an UI message from the state by calling `remove_ui_message` / `ui.delete` with the ID of the UI message.
 
-```tsx
-// pushed message
-const message = ui.push({ name: "weather", props: { city: "London" } });
+=== "Python"
 
-// remove said message
-ui.delete(message.id);
+    ```python
+    from langgraph.graph.ui import push_ui_message, delete_ui_message
 
-// return new state to persist changes
-return { ui: ui.items };
-```
+    # push message
+    message = push_ui_message("weather", {"city": "London"})
+
+    # remove said message
+    delete_ui_message(message["id"])
+    ```
+
+=== "JS"
+
+    ```tsx
+    // push message
+    const message = ui.push({ name: "weather", props: { city: "London" } });
+
+    // remove said message
+    ui.delete(message.id);
+    ```
 
 ## Learn more
 

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

@@ -1,6 +1,9 @@
 # How to integrate LangGraph into your React application
 
-!!! info "Prerequisites" - [LangGraph Platform](../../concepts/langgraph_platform.md) - [LangGraph Server](../../concepts/langgraph_server.md)
+!!! info "Prerequisites" 
+
+    - [LangGraph Platform](../../concepts/langgraph_platform.md) 
+    - [LangGraph Server](../../concepts/langgraph_server.md)
 
 The `useStream()` React hook provides a seamless way to integrate LangGraph into your React applications. It handles all the complexities of streaming, state management, and branching logic, letting you focus on building great chat experiences.
 
@@ -155,7 +158,7 @@ export default function HomePage() {
 }
 ```
 
-Under the hood, the `useStream()` hook will use the `streamMode: "messages-key"` to receive a stream of messages (i.e. individual LLM tokens) from any LangChain chat model invocations inside your graph nodes. Learn more about messages streaming in the [How to stream messages from your graph](./stream_messages.md) guide.
+Under the hood, the `useStream()` hook will use the `streamMode: "messages-tuple"` to receive a stream of messages (i.e. individual LLM tokens) from any LangChain chat model invocations inside your graph nodes. Learn more about messages streaming in the [How to stream messages from your graph](./stream_messages.md) guide.
 
 ### Interrupts
 

docs/docs/cloud/reference/cli.md

@@ -29,7 +29,7 @@ The LangGraph command line interface includes commands to build and run a LangGr
 
 ## Configuration File {#configuration-file}
 
-The LangGraph CLI requires a JSON configuration file with the following keys:
+The LangGraph CLI requires a JSON configuration file that follows this [schema](https://raw.githubusercontent.com/langchain-ai/langgraph/refs/heads/main/libs/cli/schemas/schema.json). It contains the following properties:
 
 <div class="admonition tip">
     <p class="admonition-title">Note</p>
@@ -46,11 +46,12 @@ The LangGraph CLI requires a JSON configuration file with the following keys:
     | <span style="white-space: nowrap;">`graphs`</span>           | **Required**. Mapping from graph ID to path where the compiled graph or a function that makes a graph is defined. Example: <ul><li>`./your_package/your_file.py:variable`, where `variable` is an instance of `langgraph.graph.state.CompiledStateGraph`</li><li>`./your_package/your_file.py:make_graph`, where `make_graph` is a function that takes a config dictionary (`langchain_core.runnables.RunnableConfig`) and creates an instance of `langgraph.graph.state.StateGraph` / `langgraph.graph.state.CompiledStateGraph`.</li></ul>                                    |
     | <span style="white-space: nowrap;">`auth`</span>             | _(Added in v0.0.11)_ Auth configuration containing the path to your authentication handler. Example: `./your_package/auth.py:auth`, where `auth` is an instance of `langgraph_sdk.Auth`. See [authentication guide](../../concepts/auth.md) for details.                                                                                                                                                                                                                                                                                                                        |
     | <span style="white-space: nowrap;">`env`</span>              | Path to `.env` file or a mapping from environment variable to its value.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
-    | <span style="white-space: nowrap;">`store`</span>            | Configuration for adding semantic search to the BaseStore. Contains the following fields: <ul><li>`index`: Configuration for semantic search indexing with fields:<ul><li>`embed`: Embedding provider (e.g., "openai:text-embedding-3-small") or path to custom embedding function</li><li>`dims`: Dimension size of the embedding model. Used to initialize the vector table.</li><li>`fields` (optional): List of fields to index. Defaults to `["$"]`, which means to index entire documents. Can be specific fields like `["text", "summary", "some.value"]`</li></ul></li></ul> |
+    | <span style="white-space: nowrap;">`store`</span>            | Configuration for adding semantic search and/or time-to-live (TTL) to the BaseStore. Contains the following fields: <ul><li>`index` (optional): Configuration for semantic search indexing with fields `embed`, `dims`, and optional `fields`.</li><li>`ttl` (optional): Configuration for item expiration. An object with optional fields: `refresh_on_read` (boolean, defaults to `true`), `default_ttl` (float, lifespan in **minutes**, defaults to no expiration), and `sweep_interval_minutes` (integer, how often to check for expired items, defaults to no sweeping).</li></ul> |
     | <span style="white-space: nowrap;">`python_version`</span>   | `3.11`, `3.12`, or `3.13`. Defaults to `3.11`.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
     | <span style="white-space: nowrap;">`node_version`</span>     | Specify `node_version: 20` to use LangGraph.js.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
     | <span style="white-space: nowrap;">`pip_config_file`</span>  | Path to `pip` config file.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
     | <span style="white-space: nowrap;">`dockerfile_lines`</span> | Array of additional lines to add to Dockerfile following the import from parent image.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+    | <span style="white-space: nowrap;">`checkpointer`</span>   | Configuration for the checkpointer. Contains a `ttl` field which is an object with the following keys: <ul><li>`strategy`: How to handle expired checkpoints (e.g., `"delete"`).</li><li>`sweep_interval_minutes`: How often to check for expired checkpoints (integer).</li><li>`default_ttl`: Default time-to-live for checkpoints in **minutes** (integer). Defines how long checkpoints are kept before the specified strategy is applied.</li></ul> |
     | <span style="white-space: nowrap;">`http`</span>            | HTTP server configuration with the following fields: <ul><li>`app`: Path to custom Starlette/FastAPI app (e.g., `"./src/agent/webapp.py:app"`). See [custom routes guide](../../how-tos/http/custom_routes.md).</li><li>`disable_assistants`: Disable `/assistants` routes</li><li>`disable_threads`: Disable `/threads` routes</li><li>`disable_runs`: Disable `/runs` routes</li><li>`disable_store`: Disable `/store` routes</li><li>`disable_meta`: Disable `/ok`, `/info`, `/metrics`, and `/docs` routes</li><li>`cors`: CORS configuration with fields for `allow_origins`, `allow_methods`, `allow_headers`, etc.</li></ul> |
 
 === "JS"
@@ -59,9 +60,10 @@ The LangGraph CLI requires a JSON configuration file with the following keys:
     | ------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
     | <span style="white-space: nowrap;">`graphs`</span>           | **Required**. Mapping from graph ID to path where the compiled graph or a function that makes a graph is defined. Example: <ul><li>`./src/graph.ts:variable`, where `variable` is an instance of `CompiledStateGraph`</li><li>`./src/graph.ts:makeGraph`, where `makeGraph` is a function that takes a config dictionary (`LangGraphRunnableConfig`) and creates an instance of `StateGraph` / `CompiledStateGraph`.</li></ul>                                    |
     | <span style="white-space: nowrap;">`env`</span>              | Path to `.env` file or a mapping from environment variable to its value.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
-    | <span style="white-space: nowrap;">`store`</span>            | Configuration for adding semantic search to the BaseStore. Contains the following fields: <ul><li>`index`: Configuration for semantic search indexing with fields:<ul><li>`embed`: Embedding provider (e.g., "openai:text-embedding-3-small") or path to custom embedding function</li><li>`dims`: Dimension size of the embedding model. Used to initialize the vector table.</li><li>`fields` (optional): List of fields to index. Defaults to `["$"]`, which means to index entire documents. Can be specific fields like `["text", "summary", "some.value"]`</li></ul></li></ul> |
+    | <span style="white-space: nowrap;">`store`</span>            | Configuration for adding semantic search and/or time-to-live (TTL) to the BaseStore. Contains the following fields: <ul><li>`index` (optional): Configuration for semantic search indexing with fields `embed`, `dims`, and optional `fields`.</li><li>`ttl` (optional): Configuration for item expiration. An object with optional fields: `refresh_on_read` (boolean, defaults to `true`), `default_ttl` (float, lifespan in **minutes**, defaults to no expiration), and `sweep_interval_minutes` (integer, how often to check for expired items, defaults to no sweeping).</li></ul> |
     | <span style="white-space: nowrap;">`node_version`</span>     | Specify `node_version: 20` to use LangGraph.js.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
     | <span style="white-space: nowrap;">`dockerfile_lines`</span> | Array of additional lines to add to Dockerfile following the import from parent image.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+    | <span style="white-space: nowrap;">`checkpointer`</span>   | Configuration for the checkpointer. Contains a `ttl` field which is an object with the following keys: <ul><li>`strategy`: How to handle expired checkpoints (e.g., `"delete"`).</li><li>`sweep_interval_minutes`: How often to check for expired checkpoints (integer).</li><li>`default_ttl`: Default time-to-live for checkpoints in **minutes** (integer). Defines how long checkpoints are kept before the specified strategy is applied.</li></ul> |
 
 ### Examples
 
@@ -82,7 +84,7 @@ The LangGraph CLI requires a JSON configuration file with the following keys:
 
     All deployments come with a DB-backed BaseStore. Adding an "index" configuration to your `langgraph.json` will enable [semantic search](../deployment/semantic_search.md) within the BaseStore of your deployment.
 
-    The `fields` configuration determines which parts of your documents to embed:
+    The `index.fields` configuration determines which parts of your documents to embed:
 
     - If omitted or set to `["$"]`, the entire document will be embedded
     - To embed specific fields, use JSON path notation: `["metadata.title", "content.text"]`
@@ -171,6 +173,62 @@ The LangGraph CLI requires a JSON configuration file with the following keys:
 
     See the [authentication conceptual guide](../../concepts/auth.md) for details, and the [setting up custom authentication](../../tutorials/auth/getting_started.md) guide for a practical walk through of the process.
 
+    #### Configuring Store Item Time-to-Live (TTL)
+
+    You can configure default data expiration for items/memories in the BaseStore using the `store.ttl` key. This determines how long items are retained after they are last accessed (with reads potentially refreshing the timer based on `refresh_on_read`). Note that these defaults can be overwritten on a per-call basis by modifying the corresponding arguments in `get`, `search`, etc.
+    
+    The `ttl` configuration is an object containing optional fields:
+
+    - `refresh_on_read`: If `true` (the default), accessing an item via `get` or `search` resets its expiration timer. Set to `false` to only refresh TTL on writes (`put`).
+    - `default_ttl`: The default lifespan of an item in **minutes**. If not set, items do not expire by default.
+    - `sweep_interval_minutes`: How frequently (in minutes) the system should run a background process to delete expired items. If not set, sweeping does not occur automatically.
+
+    Here is an example enabling a 7-day TTL (10080 minutes), refreshing on reads, and sweeping every hour:
+
+    ```json
+    {
+      "dependencies": ["."],
+      "graphs": {
+        "memory_agent": "./agent/graph.py:graph"
+      },
+      "store": {
+        "ttl": {
+          "refresh_on_read": true,
+          "sweep_interval_minutes": 60,
+          "default_ttl": 10080 
+        }
+      }
+    }
+    ```
+
+    #### Configuring Checkpoint Time-to-Live (TTL)
+
+    You can configure the time-to-live (TTL) for checkpoints using the `checkpointer` key. This determines how long checkpoint data is retained before being automatically handled according to the specified strategy (e.g., deletion). The `ttl` configuration is an object containing:
+
+    - `strategy`: The action to take on expired checkpoints (currently `"delete"` is the only accepted option).
+    - `sweep_interval_minutes`: How frequently (in minutes) the system checks for expired checkpoints.
+    - `default_ttl`: The default lifespan of a checkpoint in **minutes**.
+
+    Here's an example setting a default TTL of 30 days (43200 minutes):
+
+    ```json
+    {
+      "dependencies": ["."],
+      "graphs": {
+        "chat": "./chat/graph.py:graph"
+      },
+      "checkpointer": {
+        "ttl": {
+          "strategy": "delete",
+          "sweep_interval_minutes": 10,
+          "default_ttl": 43200
+        }
+      }
+    }
+    ```
+
+    In this example, checkpoints older than 30 days will be deleted, and the check runs every 10 minutes.
+
 
 === "JS"
     

docs/docs/cloud/reference/env_var.md

@@ -1,6 +1,6 @@
 # Environment Variables
 
-The LangGraph Cloud Server supports specific environment variables for configuring a deployment.
+The LangGraph Server supports specific environment variables for configuring a deployment.
 
 ## `BG_JOB_ISOLATED_LOOPS`
 
@@ -32,7 +32,7 @@ See <a href="https://docs.smith.langchain.com/how_to_guides/tracing/sample_trace
 
 ## `LANGGRAPH_AUTH_TYPE`
 
-Type of authentication for the LangGraph Cloud Server deployment. Valid values: `langsmith`, `noop`.
+Type of authentication for the LangGraph Server deployment. Valid values: `langsmith`, `noop`.
 
 For deployments to LangGraph Cloud, this environment variable is set automatically. For local development or deployments where authentication is handled externally (e.g. self-hosted), set this environment variable to `noop`.
 
@@ -44,19 +44,27 @@ Set this environment variable to have a BYOC deployment send traces to a self-ho
 
 `SELF_HOSTED_LANGSMITH_HOSTNAME` is the hostname of the self-hosted LangSmith instance. It must be accessible to the BYOC deployment. `LANGSMITH_API_KEY` is a LangSmith API generated from the self-hosted LangSmith instance.
 
+## `LANGSMITH_TRACING`
+
+!!! info "Only for Self-Hosted Data Plane, Self-Hosted Control Plane, and Standalone Container"
+    Disabling LangSmith tracing is only available for [Self-Hosted Data Plane](../../concepts/langgraph_self_hosted_data_plane.md), [Self-Hosted Control Plane](../../concepts/langgraph_self_hosted_control_plane.md), and [Standalone Container](../../concepts/langgraph_standalone_container.md) deployments.
+
+Set `LANGSMITH_TRACING` to `false` to disable tracing to LangSmith.
+
 ## `LOG_LEVEL`
 
 Configure [log level](https://docs.python.org/3/library/logging.html#logging-levels). Defaults to `INFO`.
 
 ## `N_JOBS_PER_WORKER`
 
-Number of jobs per worker for the LangGraph Cloud task queue. Defaults to `10`.
+Number of jobs per worker for the LangGraph Server task queue. Defaults to `10`.
 
 ## `POSTGRES_URI_CUSTOM`
 
-For [Bring Your Own Cloud (BYOC)](../../concepts/bring_your_own_cloud.md) deployments only.
+!!! info "Only for Self-Hosted Data Plane and Self-Hosted Control Plane"
+    Custom Postgres instances are only available for [Self-Hosted Data Plane](../../concepts/langgraph_self_hosted_data_plane.md) and [Self-Hosted Control Plane](../../concepts/langgraph_self_hosted_control_plane.md) deployments.
 
-Specify `POSTGRES_URI_CUSTOM` to use an externally managed Postgres instance. The value of `POSTGRES_URI_CUSTOM` must be a valid [Postgres connection URI](https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNSTRING-URIS).
+Specify `POSTGRES_URI_CUSTOM` to use a custom Postgres instance. The value of `POSTGRES_URI_CUSTOM` must be a valid [Postgres connection URI](https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNSTRING-URIS).
 
 Postgres:
 
@@ -73,11 +81,11 @@ Control Plane Functionality:
 
 Database Connectivity:
 
-- The externally managed Postgres instance must be accessible by the LangGraph Server service in the ECS cluster. The BYOC user is responsible for ensuring connectivity.
-- For example, if an AWS RDS Postgres instance is provisioned, it can be provisioned in the same VPC (`langgraph-cloud-vpc`) as the ECS cluster with the `langgraph-cloud-service-sg` security group to ensure connectivity.
+- The custom Postgres instance must be accessible by the LangGraph Server. The user is responsible for ensuring connectivity.
 
 ## `REDIS_URI_CUSTOM`
 
-For [Bring Your Own Cloud (BYOC)](../../concepts/bring_your_own_cloud.md) deployments only.
+!!! info "Only for Self-Hosted Data Plane and Self-Hosted Control Plane"
+    Custom Redis instances are only available for [Self-Hosted Data Plane](../../concepts/langgraph_self_hosted_data_plane.md) and [Self-Hosted Control Plane](../../concepts/langgraph_self_hosted_control_plane.md) deployments.
 
-Specify `REDIS_URI_CUSTOM` to use an externally managed Redis instance. The value of `REDIS_URI_CUSTOM` must be a valid [Redis connection URI](https://redis-py.readthedocs.io/en/stable/connections.html#redis.Redis.from_url).
+Specify `REDIS_URI_CUSTOM` to use a custom Redis instance. The value of `REDIS_URI_CUSTOM` must be a valid [Redis connection URI](https://redis-py.readthedocs.io/en/stable/connections.html#redis.Redis.from_url).

docs/docs/concepts/auth.md

@@ -2,10 +2,6 @@
 
 LangGraph Platform provides a flexible authentication and authorization system that can integrate with most authentication schemes.
 
-!!! note "Python only"
-
-    We currently only support custom authentication and authorization in Python deployments with `langgraph-api>=0.0.11`. Support for LangGraph.JS will be added soon.
-
 ## Core Concepts
 
 ### Authentication vs Authorization
@@ -146,7 +142,7 @@ The returned user information is available:
 
 After authentication, LangGraph calls your [`@auth.on`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.Auth.on) handlers to control access to specific resources (e.g., threads, assistants, crons). These handlers can:
 
-1. Add metadata to be saved during resource creation by mutating the `value["metadata"]` dictionary directly. See the [supported actions table](##supported-actions) for the list of types the value can take for each action.
+1. Add metadata to be saved during resource creation by mutating the `value["metadata"]` dictionary directly. See the [supported actions table](#supported-actions) for the list of types the value can take for each action.
 2. Filter resources by metadata during search/list or read operations by returning a [filter dictionary](#filter-operations).
 3. Raise an HTTP exception if access is denied.
 
@@ -289,7 +285,7 @@ async def on_assistant_create(
         )
 ```
 
-Notice that we are mixing global and resource-specific handlers in the above example. Since each request is handled by the most specific handler, a request to create a `thread` would match the `on_thread_create` handler but NOT the `reject_unhandled_requests` handler. A request to `update` a thread, however would be handled by the global handler, since we don't have a more specific handler for that resource and action. Requests to create, update, 
+Notice that we are mixing global and resource-specific handlers in the above example. Since each request is handled by the most specific handler, a request to create a `thread` would match the `on_thread_create` handler but NOT the `reject_unhandled_requests` handler. A request to `update` a thread, however would be handled by the global handler, since we don't have a more specific handler for that resource and action.
 
 ### Filter Operations {#filter-operations}
 
@@ -423,6 +419,7 @@ Here are all the supported action handlers:
 | | `@auth.on.crons.search` | Listing cron jobs | [`CronsSearch`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.types.CronsSearch) |
 
 ???+ note "About Runs"
+
     Runs are scoped to their parent thread for access control. This means permissions are typically inherited from the thread, reflecting the conversational nature of the data model. All run operations (reading, listing) except creation are controlled by the thread's handlers.
     There is a specific `create_run` handler for creating new runs because it had more arguments that you can view in the handler.
 

docs/docs/concepts/deployment_options.md

@@ -10,90 +10,65 @@
 
 There are 4 main options for deploying with the LangGraph Platform:
 
-1. **[Self-Hosted Lite](#self-hosted-lite)**: Available for all plans.
+1. **<a href="#cloud-saas">Cloud SaaS<sup>(Beta)</sup></a>**: Available for **Plus** and **Enterprise** plans.
 
-2. **[Self-Hosted Enterprise](#self-hosted-enterprise)**: Available for the **Enterprise** plan.
+1. **<a href="#self-hosted-data-plane">Self-Hosted Data Plane<sup>(Beta)</sup></a>**: Available for the **Enterprise** plan.
 
-3. **[Cloud SaaS](#cloud-saas)**: Available for **Plus** and **Enterprise** plans.
+1. **<a href="#self-hosted-control-plane">Self-Hosted Control Plane<sup>(Beta)</sup></a>**: Available for the **Enterprise** plan.
 
-4. **[Bring Your Own Cloud](#bring-your-own-cloud)**: Available only for **Enterprise** plans and **only on AWS**.
+1. **[Standalone Container](#standalone-container)**: Available for all plans.
 
 Please see the [LangGraph Platform Plans](./plans.md) for more information on the different plans.
 
 The guide below will explain the differences between the deployment options.
 
-## Self-Hosted Enterprise
-
-!!! important
-
-    The Self-Hosted Enterprise version is only available for the **Enterprise** plan.
-
-!!! warning "Note"
-
-    The LangGraph Platform Deployments view is optionally available for Self-Hosted Enterprise LangGraph deployments. With one click, self-hosted LangGraph deployments can be deployed in the same Kubernetes cluster where a self-hosted LangSmith instance is deployed.
-
-With a Self-Hosted Enterprise deployment, you are responsible for managing the infrastructure, including setting up and maintaining required databases and Redis instances.
-
-You’ll build a Docker image using the [LangGraph CLI](./langgraph_cli.md), which can then be deployed on your own infrastructure.
-
-For more information, please see:
-
-* [Self-Hosted conceptual guide](./self_hosted.md)
-* [Self-Hosted Deployment how-to guide](../how-tos/deploy-self-hosted.md)
-
-## Self-Hosted Lite
-
-!!! important
-
-    The Self-Hosted Lite version is available for all plans.
-
-!!! warning "Note"
-
-    The LangGraph Platform Deployments view is optionally available for Self-Hosted Lite LangGraph deployments. With one click, self-hosted LangGraph deployments can be deployed in the same Kubernetes cluster where a self-hosted LangSmith instance is deployed.
-
-The Self-Hosted Lite deployment option is a free (up to 1 million nodes executed per year), limited version of LangGraph Platform that you can run locally or in a self-hosted manner.
-
-With a Self-Hosted Lite deployment, you are responsible for managing the infrastructure, including setting up and maintaining required databases and Redis instances.
-
-You’ll build a Docker image using the [LangGraph CLI](./langgraph_cli.md), which can then be deployed on your own infrastructure.
-
-[Cron jobs](../cloud/how-tos/cron_jobs.md) are not available for Self-Hosted Lite deployments.
-
-For more information, please see:
-
-* [Self-Hosted conceptual guide](./self_hosted.md)
-* [Self-Hosted deployment how-to guide](../how-tos/deploy-self-hosted.md)
-
 ## Cloud SaaS
 
-!!! important
+The [Cloud SaaS](./langgraph_cloud.md) deployment option is a fully managed model for deployment where we manage the [control plane](./langgraph_control_plane.md) and [data plane](./langgraph_data_plane.md) in our cloud. This option provides a simple way to deploy and manage your LangGraph Servers.
 
-    The Cloud SaaS version of LangGraph Platform is only available for **Plus** and **Enterprise** plans.
-
-The [Cloud SaaS](./langgraph_cloud.md) version of LangGraph Platform is hosted as part of [LangSmith](https://smith.langchain.com/).
-
-The Cloud SaaS version of LangGraph Platform provides a simple way to deploy and manage your LangGraph applications.
-
-This deployment option provides access to the LangGraph Platform UI (within LangSmith) and an integration with GitHub, allowing you to deploy code from any of your repositories on GitHub.
+Connect your GitHub repositories to the platform and deploy your LangGraph Servers from the [Control Plane UI](./langgraph_control_plane.md#control-plane-ui). The build process (i.e. CI/CD) is managed internally by the platform.
 
 For more information, please see:
 
 * [Cloud SaaS Conceptual Guide](./langgraph_cloud.md)
 * [How to deploy to Cloud SaaS](../cloud/deployment/cloud.md)
 
+## Self-Hosted Data Plane
 
-## Bring Your Own Cloud
+The [Self-Hosted Data Plane](./langgraph_self_hosted_data_plane.md) deployment option is a "hybrid" model for deployemnt where we manage the [control plane](./langgraph_control_plane.md) in our cloud and you manage the [data plane](./langgraph_data_plane.md) in your cloud. This option provides a way to securely manage your data plane infrastructure, while offloading control plane management to us.
 
-!!! important
+Build a Docker image using the [LangGraph CLI](./langgraph_cli.md) and deploy your LangGraph Server from the [Control Plane UI](./langgraph_control_plane.md#control-plane-ui).
 
-    The Bring Your Own Cloud version of LangGraph Platform is only available for **Enterprise** plans.
+Supported Compute Platforms: [Kubernetes](https://kubernetes.io/), [Amazon ECS](https://aws.amazon.com/ecs/) (coming soon!)
 
+For more information, please see:
 
-This combines the best of both worlds for Cloud and Self-Hosted. Create your deployments through the LangGraph Platform UI (within LangSmith) and we manage the infrastructure so you don't have to. The infrastructure all runs within your cloud. This is currently only available on AWS.
+* [Self-Hosted Data Plane Conceptual Guide](./langgraph_self_hosted_data_plane.md)
+* [How to deploy the Self-Hosted Data Plane](../cloud/deployment/self_hosted_data_plane.md)
 
-For more information please see:
+## Self-Hosted Control Plane
 
-* [Bring Your Own Cloud Conceptual Guide](./bring_your_own_cloud.md)
+The [Self-Hosted Control Plane](./langgraph_self_hosted_control_plane.md) deployment option is a fully self-hosted model for deployment where you manage the [control plane](./langgraph_control_plane.md) and [data plane](./langgraph_data_plane.md) in your cloud. This option give you full control and responsibility of the control plane and data plane infrastructure.
+
+Build a Docker image using the [LangGraph CLI](./langgraph_cli.md) and deploy your LangGraph Server from the [Control Plane UI](./langgraph_control_plane.md#control-plane-ui).
+
+Supported Compute Platforms: [Kubernetes](https://kubernetes.io/)
+
+For more information, please see:
+
+* [Self-Hosted Control Plane Conceptual Guide](./langgraph_self_hosted_control_plane.md)
+* [How to deploy the Self-Hosted Control Plane](../cloud/deployment/self_hosted_control_plane.md)
+
+## Standalone Container
+
+The [Standalone Container](./langgraph_standalone_container.md) deployment option is the least restrictive model for deployment. Deploy standalone instances of a LangGraph Server in your cloud.
+
+Build a Docker image using the [LangGraph CLI](./langgraph_cli.md) and deploy your LangGraph Server using the container deployment tooling of your choice. Images can be deployed to any compute platform.
+
+For more information, please see:
+
+* [Sandalone Container Conceptual Guide](./langgraph_standalone_container.md)
+* [How to deploy a Standalone Container](../cloud/deployment/standalone_container.md)
 
 ## Related
 

docs/docs/concepts/functional_api.md

@@ -23,9 +23,11 @@ This provides a minimal abstraction for building workflows with state management
 Below we demonstrate a simple application that writes an essay and [interrupts](human_in_the_loop.md) to request human review.
 
 ```python
+from langgraph.checkpoint.memory import MemorySaver
 from langgraph.func import entrypoint, task
 from langgraph.types import interrupt
 
+
 @task
 def write_essay(topic: str) -> str:
     """Write an essay about the given topic."""

docs/docs/concepts/index.md

@@ -49,7 +49,7 @@ The LangGraph Platform offers a few different deployment options described in th
 - [Why LangGraph Platform?](./langgraph_platform.md): The LangGraph platform is an opinionated way to deploy and manage LangGraph applications. This guide provides an overview of the key features and concepts behind LangGraph Platform.
 - [Platform Architecture](./platform_architecture.md): A high-level overview of the architecture of the LangGraph Platform.
 - [Scalability and Resilience](./scalability_and_resilience.md): LangGraph Platform is designed to be scalable and resilient. This document explains how the platform achieves this.
-- [Deployment Options](./deployment_options.md): LangGraph Platform offers four deployment options: [Self-Hosted Lite](./self_hosted.md#self-hosted-lite), [Self-Hosted Enterprise](./self_hosted.md#self-hosted-enterprise), [bring your own cloud (BYOC)](./bring_your_own_cloud.md), and [Cloud SaaS](./langgraph_cloud.md). This guide explains the differences between these options, and which Plans they are available on.
+- [Deployment Options](./deployment_options.md): LangGraph Platform offers four deployment options: [Cloud SaaS](./langgraph_cloud.md), [Self-Hosted Data Plane](./langgraph_self_hosted_data_plane.md), [Self-Hosted Control Plane](./langgraph_self_hosted_control_plane.md), and [Standalone Container](./langgraph_standalone_container.md). This guide explains the differences between these options, and which Plans they are available on.
 - [Plans](./plans.md): LangGraph Platforms offer three different plans: Developer, Plus, Enterprise. This guide explains the differences between these options, what deployment options are available for each, and how to sign up for each one.
 - [Template Applications](./template_applications.md): Reference applications designed to help you get started quickly when building with LangGraph.
 
@@ -62,6 +62,8 @@ The LangGraph Platform comprises several components that work together to suppor
 - [LangGraph CLI](./langgraph_cli.md): LangGraph CLI is a command-line interface that helps to interact with a local LangGraph
 - [Python/JS SDK](./sdk.md): The Python/JS SDK provides a programmatic way to interact with deployed LangGraph Applications.
 - [Remote Graph](../how-tos/use-remote-graph.md): A RemoteGraph allows you to interact with any deployed LangGraph application as though it were running locally.
+- [LangGraph Control Plane](./langgraph_control_plane.md): The LangGraph Control Plane refers to the Control Plane UI where users create and update LangGraph Servers and the Control Plane APIs that support the UI experience.
+- [LangGraph Data Plane](./langgraph_data_plane.md): The LangGraph Data Plane refers to LangGraph Servers, the corresponding infrastructure for each server, and the "listener" application that continuously polls for updates from the LangGraph Control Plane.
 
 ### LangGraph Server
 
@@ -74,7 +76,7 @@ The LangGraph Platform comprises several components that work together to suppor
 
 ### Deployment Options
 
-- [Self-Hosted Lite](./self_hosted.md): A free (up to 1 million nodes executed per year), limited version of LangGraph Platform that you can run locally or in a self-hosted manner
-- [Cloud SaaS](./langgraph_cloud.md): Hosted as part of LangSmith.
-- [Bring Your Own Cloud](./bring_your_own_cloud.md): We manage the infrastructure, so you don't have to, but the infrastructure all runs within your cloud.
-- [Self-Hosted Enterprise](./self_hosted.md): Completely managed by you.
+- <a href="./langgraph_cloud/">Cloud SaaS<sup>(Beta)</sup></a>: Connect to your GitHub repositories and deploy LangGraph Servers to LangChain's cloud. We manage everything.
+- <a href="./langgraph_self_hosted_data_plane/">Self-Hosted Data Plane<sup>(Beta)</sup></a>: Create deployments from the [Control Plane UI](../concepts/langgraph_control_plane.md#control-plane-ui) and deploy LangGraph Servers to your cloud. We manage the [control plane](../concepts/langgraph_control_plane.md), you manage the deployments.
+- <a href="./langgraph_self_hosted_control_plane/">Self-Hosted Control Plane<sup>(Beta)</sup></a>: Create deployments from a self-hosted [Control Plane UI](../concepts/langgraph_control_plane.md#control-plane-ui) and deploy LangGraph Servers to your cloud. You manage everything.
+- [Standalone Container](../concepts/langgraph_standalone_container.md): Deploy LangGraph Server Docker images however you like.

docs/docs/concepts/langgraph_cloud.md

@@ -1,107 +1,17 @@
-# Cloud SaaS
+# Cloud SaaS (Beta)
 
-!!! info "Prerequisites" 
-    - [LangGraph Platform](./langgraph_platform.md) 
-    - [LangGraph Server](./langgraph_server.md)
+To deploy a [LangGraph Server](../concepts/langgraph_server.md), follow the how-to guide for [how to deploy to Cloud SaaS](../cloud/deployment/cloud.md).
 
 ## Overview
 
-LangGraph's Cloud SaaS is a managed service for deploying LangGraph Servers, regardless of its definition or dependencies. The service offers managed implementations of checkpointers and stores, allowing you to focus on building the right cognitive architecture for your use case. By handling scalable & secure infrastructure, LangGraph Cloud SaaS offers the fastest path to getting your LangGraph Server deployed to production.
+The Cloud SaaS deployment option is a fully managed model for deployment where we manage the [control plane](./langgraph_control_plane.md) and [data plane](./langgraph_data_plane.md) in our cloud.
 
-## Deployment
-
-A **deployment** is an instance of a LangGraph Server. A single deployment can have many [revisions](#revision). When a deployment is created, all the necessary infrastructure (e.g. database, containers, secrets store) are automatically provisioned. See the [architecture diagram](#architecture) below for more details.
-
-Resource Allocation:
-
-| **Deployment Type** | **CPU** | **Memory** | **Scaling**         |
-|---------------------|---------|------------|---------------------|
-| Development         | 1 CPU   | 1 GB       | Up to 1 container   |
-| Production          | 2 CPU   | 2 GB       | Up to 10 containers |
-
-CPU and memory resources are per container.
-
-For **Production type** deployments, resources can be manually increased on a case-by-case basis depending on use case and capacity constraints. Contact support@langchain.dev to request an increase in resources.
-
-See the [how-to guide](../cloud/deployment/cloud.md#create-new-deployment) for creating a new deployment.
-
-## Revision
-
-A revision is an iteration of a [deployment](#deployment). When a new deployment is created, an initial revision is automatically created. To deploy new code changes or update environment variable configurations for a deployment, a new revision must be created. When a revision is created, a new container image is built automatically.
-
-See the [how-to guide](../cloud/deployment/cloud.md#create-new-revision) for creating a new revision.
-
-## Persistence
-
-A dedicated database is automatically created for each deployment. The database serves as the [persistence layer](../concepts/persistence.md) for the deployment.
-
-When defining a graph to be deployed to LangGraph Cloud SaaS, a [checkpointer](../concepts/persistence.md#checkpointer-libraries) should not be configured by the user. Instead, a checkpointer is automatically configured for the graph.
-
-There is no direct access to the database. All access to the database occurs through the LangGraph Server APIs.
-
-The database is never deleted until the deployment itself is deleted. See [Automatic Deletion](#automatic-deletion) for additional details.
-
-## Autoscaling
-`Production` type deployments automatically scale up to 10 containers. Scaling is based on the current request load for a single container. Specifically, the autoscaling implementation scales the deployment so that each container is processing about 10 concurrent requests. For example... 
-
-- If the deployment is processing 20 concurrent requests, the deployment will scale up from 1 container to 2 containers (20 requests / 2 containers = 10 requests per container).
-- If a deployment of 2 containers is processing 10 requests, the deployment will scale down from 2 containers to 1 container (10 requests / 1 container = 10 requests per container).
-
-10 concurrent requests per container is the target threshold. However, 10 concurrent requests per container is not a hard limit. The number of concurrent requests can exceed 10 if there is a sudden burst of requests.
-
-Scale down actions are delayed for 30 minutes before any action is taken. In other words, if the autoscaling implementation decides to scale down a deployment, it will first wait for 30 minutes before scaling down. After 30 minutes, the concurrency metric is recomputed and the deployment will scale down if the concurrency metric has met the target threshold. Otherwise, the deployment remains scaled up. This "cool down" period ensures that deployments do not scale up and down too frequently.
-
-In the future, the autoscaling implementation may evolve to accommodate other metrics such as background run queue size.
-
-## Asynchronous Deployment
-
-Infrastructure for [deployments](#deployment) and [revisions](#revision) are provisioned and deployed asynchronously. They are not deployed immediately after submission. Currently, deployment can take up to several minutes.
-
-- When a new deployment is created, a new database is created for the deployment. Database creation is a one-time step. This step contributes to a longer deployment time for the initial revision of the deployment.
-- When a subsequent revision is created for a deployment, there is no database creation step. The deployment time for a subsequent revision is significantly faster compared to the deployment time of the initial revision.
-- The deployment process for each revision contains a build step, which can take up to a few minutes.
-
-## LangSmith Integration
-
-A [LangSmith](https://docs.smith.langchain.com/) tracing project is automatically created for each deployemnt. The tracing project has the same name as the deployment. When creating a deployment, the `LANGCHAIN_TRACING` and `LANGSMITH_API_KEY`/`LANGCHAIN_API_KEY` environment variables do not need to be specified; they are set internally, automatically. Traces are created for each run and are emitted to the tracing project automatically.
-
-When a deployment is deleted, the traces and the tracing project are not deleted.
-
-## Automatic Deletion
-
-Deployments are automatically deleted after 28 consecutive days of non-use (it is in an unused state). A deployment is in an unused state if there are no traces emitted to LangSmith from the deployment after 28 consecutive days. On any given day, if a deployment emits a trace to LangSmith, the counter for consecutive days of non-use is reset.
-
-- An email notification is sent after 7 consecutive days of non-use.
-- A deployment is deleted after 28 consecutive days of non-use.
-
-!!! danger "Data Cannot Be Recovered"
-    After a deployment is deleted, the data (i.e. [persistence](#persistence)) from the deployment cannot be recovered.
+|                   | [Control Plane](../concepts/langgraph_control_plane.md) | [Data Plane](../concepts/langgraph_data_plane.md) |
+|-------------------|-------------------|------------|
+| **What is it?** | <ul><li>Control Plane UI for creating deployments and revisions</li><li>Control Plane APIs for creating deployments and revisions</li></ul> | <ul><li>Data plane "listener" for reconciling deployments with control plane state</li><li>LangGraph Servers</li><li>Postgres, Redis, etc</li></ul> |
+| **Where is it hosted?** | LangChain's cloud | LangChain's cloud |
+| **Who provisions and manages it?** | LangChain | LangChain |
 
 ## Architecture
 
-!!! warning "Subject to Change"
-    The Cloud SaaS deployment architecture may change in the future.
-
-A high-level diagram of a Cloud SaaS deployment.
-
-![diagram](img/langgraph_cloud_architecture.png)
-
-## Whitelisting IP Addresses
-
-All traffic from `LangGraph Platform` deployments created after January 6th 2025 will come through a NAT gateway.
-This NAT gateway will have several static ip addresses depending on the region you are deploying in. Refer to the table below for the list of IP addresses to whitelist:
-
-| US             | EU             |
-|----------------|----------------|
-| 35.197.29.146  | 34.13.192.67   |
-| 34.145.102.123 | 34.147.105.64  |
-| 34.169.45.153  | 34.90.22.166   |
-| 34.82.222.17   | 34.147.36.213  |
-| 35.227.171.135 | 34.32.137.113  | 
-| 34.169.88.30   | 34.91.238.184  |
-| 34.19.93.202   | 35.204.101.241 |
-| 34.19.34.50    | 35.204.48.32   |
-
-## Related
-
-- [Deployment Options](./deployment_options.md)
+![Cloud SaaS](./img/self_hosted_control_plane_architecture.png)

docs/docs/concepts/langgraph_control_plane.md

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

docs/docs/concepts/langgraph_data_plane.md

@@ -0,0 +1,120 @@
+# LangGraph Data Plane
+
+The term "data plane" is used broadly to refer to [LangGraph Servers](./langgraph_server.md) (deployments), the corresponding infrastructure for each server, and the "listener" application that continuously polls for updates from the [LangGraph Control Plane](./langgraph_control_plane.md).
+
+## Server Infrastructure
+
+In addition to the [LangGraph Server](./langgraph_server.md) itself, the following infrastructure for each server are also included in the broad definition of "data plane":
+
+- [Postgres](../concepts/platform_architecture.md#how-we-use-postgres)
+- [Redis](../concepts/platform_architecture.md#how-we-use-redis)
+- Secrets store
+- Autoscalers
+
+See [LangGraph Platform Architecture](../concepts/platform_architecture.md) for more details.
+
+## "Listener" Application
+
+The data plane "listener" application periodically calls [Control Plane APIs](../concepts/langgraph_control_plane.md#control-plane-api) to:
+
+- Determine if new deployments should be created.
+- Determine if existing deployments should be updated (i.e. new revisions).
+- Determine if existing deployments should be deleted.
+
+In other words, the data plane "listener" reads the latest state of the control plane (desired state) and takes action to reconcile outstanding deployments (current state) to match the latest state.
+
+## Data Plane Features
+
+This section describes various features of the data plane.
+
+### Lite vs Enterprise
+
+There are two versions of the LangGraph Server: `Lite` and `Enterprise`.
+
+The `Lite` version is a limited version of the LangGraph Server that you can run locally or in a self-hosted manner (up to 1 million nodes executed per year). `Lite` is only available for the [Standalone Container](../concepts/langgraph_standalone_container.md) deployment option.
+
+The `Enterprise` version is the full version of the LangGraph Server. To use the `Enterprise` version, you must acquire a license key that you will need to specify when running the Docker image. To acquire a license key, please email sales@langchain.dev. `Enterprise` is available for [Cloud SaaS](../concepts/langgraph_cloud.md), [Self-Hosted Data Plane](../concepts/langgraph_self_hosted_data_plane.md), and [Self-Hosted Control Plane](../concepts/langgraph_self_hosted_control_plane.md) deployment options.
+
+Feature Differences:
+
+|       | Lite       | Enterprise |
+|-------|------------|------------|
+| [Cron Jobs](../concepts/langgraph_server.md#cron-jobs) |❌|✅|
+| [Custom Authentication](../concepts/auth.md) |❌|✅|
+
+### Autoscaling
+
+[`Production` type](../concepts/langgraph_control_plane.md#deployment-types) deployments automatically scale up to 10 containers. Scaling is based on 3 metrics:
+
+1. CPU utilization
+1. Memory utilization
+1. Number of pending (in progress) [runs](../concepts/langgraph_server.md#runs)
+
+For CPU utilization, the autoscaler targets 75% utilization. This means the autoscaler will scale the number of containers up or down to ensure that CPU utilization is at or near 75%. For memory utilization, the autoscaler targets 75% utilization as well.
+
+For number of pending runs, the autoscaler targets 10 pending runs. For example, if the current number of containers is 1, but the number of pending runs in 20, the autoscaler will scale up the deployment to 2 containers (20 pending runs / 2 containers = 10 pending runs per container).
+
+Each metric is computed independently and the autoscaler will determine the scaling action based on the metric that results in the most number of containers.
+
+Scale down actions are delayed for 30 minutes before any action is taken. In other words, if the autoscaler decides to scale down a deployment, it will first wait for 30 minutes before scaling down. After 30 minutes, the metrics are recomputed and the deployment will scale down if the recomputed metrics result in a lower number of containers than the current number. Otherwise, the deployment remains scaled up. This "cool down" period ensures that deployments do not scale up and down too frequently.
+
+### Static IP Addresses
+
+!!! info "Only for Cloud SaaS"
+    Static IP addresses are only available for [Cloud SaaS](../concepts/langgraph_cloud.md) deployments.
+
+All traffic from deployments created after January 6th 2025 will come through a NAT gateway. This NAT gateway will have several static IP addresses depending on the data region. Refer to the table below for the list of static IP addresses:
+
+| US             | EU             |
+|----------------|----------------|
+| 35.197.29.146  | 34.13.192.67   |
+| 34.145.102.123 | 34.147.105.64  |
+| 34.169.45.153  | 34.90.22.166   |
+| 34.82.222.17   | 34.147.36.213  |
+| 35.227.171.135 | 34.32.137.113  | 
+| 34.169.88.30   | 34.91.238.184  |
+| 34.19.93.202   | 35.204.101.241 |
+| 34.19.34.50    | 35.204.48.32   |
+
+### Custom Postgres
+
+!!! info "Only for Self-Hosted Data Plane and Self-Hosted Control Plane"
+    Custom Postgres instances are only available for [Self-Hosted Data Plane](../concepts/langgraph_self_hosted_data_plane.md) and [Self-Hosted Control Plane](../concepts/langgraph_self_hosted_control_plane.md) deployments.
+
+A custom Postgres instance can be used instead of the [one automatically created by the control plane](./langgraph_control_plane.md#database-provisioning). Specify the [`POSTGRES_URI_CUSTOM`](../cloud/reference/env_var.md#postgres_uri_custom) environment variable to use a custom Postgres instance.
+
+Multiple deployments can share the same Postgres instance. For example, for `Deployment A`, `POSTGRES_URI_CUSTOM` can be set to `postgres://<user>:<password>@/<database_name_1>?host=<hostname_1>` and for `Deployment B`, `POSTGRES_URI_CUSTOM` can be set to `postgres://<user>:<password>@/<database_name_2>?host=<hostname_1>`. `<database_name_1>` and `database_name_2` are different databases within the same instance, but `<hostname_1>` is shared. **The same database cannot be used for separate deployments**.
+
+### Custom Redis
+
+!!! info "Only for Self-Hosted Data Plane and Self-Hosted Control Plane"
+    Custom Redis instances are only available for [Self-Hosted Data Plane](../concepts/langgraph_self_hosted_data_plane.md) and [Self-Hosted Control Plane](../concepts/langgraph_self_hosted_control_plane.md) deployments.
+
+A custom Redis instance can be used instead of the one automatically created by the control plane. Specify the [REDIS_URI_CUSTOM](../cloud/reference/env_var.md#redis_uri_custom) environment variable to use a custom Redis instance.
+
+
+Multiple deployments can share the same Redis instance. For example, for `Deployment A`, `REDIS_URI_CUSTOM` can be set to `redis://<hostname_1>:<port>/1` and for `Deployment B`, `REDIS_URI_CUSTOM` can be set to `redis://<hostname_1>:<port>/2`. `1` and `2` are different database numbers within the same instance, but `<hostname_1>` is shared. **The same database number cannot be used for separate deployments**.
+
+### LangSmith Tracing
+
+LangGraph Server is automatically configured to send traces to LangSmith. See the table below for details with respect to each deployment option.
+
+| Cloud SaaS | Self-Hosted Data Plane | Self-Hosted Control Plane | Standalone Container |
+|------------|------------------------|---------------------------|----------------------|
+| Required<br><br>Trace to LangSmith SaaS. | Optional<br><br>Disable tracing or trace to LangSmith SaaS. | Optional<br><br>Disable tracing or trace to Self-Hosted LangSmith. | Optional<br><br>Disable tracing, trace to LangSmith SaaS, or trace to Self-Hosted LangSmith. |
+
+### Telemetry
+
+LangGraph Server is automatically configured to report telemetry metadata for billing purposes. See the table below for details with respect to each deployment option.
+
+| Cloud SaaS | Self-Hosted Data Plane | Self-Hosted Control Plane | Standalone Container |
+|------------|------------------------|---------------------------|----------------------|
+| Telemetry sent to LangSmith SaaS. | Telemetry sent to LangSmith SaaS. | Self-reported usage (audit) for air-gapped license key.<br><br>Telemetry sent to LangSmith SaaS for LangGraph Platform License Key. | Self-reported usage (audit) for air-gapped license key.<br><br>Telemetry sent to LangSmith SaaS for LangGraph Platform License Key. |
+
+### Licensing
+
+LangGraph Server is automatically configured to perform license key validation. See the table below for details with respect to each deployment option.
+
+| Cloud SaaS | Self-Hosted Data Plane | Self-Hosted Control Plane | Standalone Container |
+|------------|------------------------|---------------------------|----------------------|
+| LangSmith API Key validated against LangSmith SaaS. | LangSmith API Key validated against LangSmith SaaS. | Air-gapped license key or LangGraph Platform License Key validated against LangSmith SaaS. | Air-gapped license key or LangGraph Platform License Key validated against LangSmith SaaS. |

docs/docs/concepts/langgraph_platform.md

@@ -5,6 +5,10 @@ search:
 
 # LangGraph Platform
 
+Watch this 4-minute overview of LangGraph Platform to see how it helps you build, deploy, and evaluate agentic applications.
+
+<iframe width="560" height="315" src="https://www.youtube.com/embed/pfAQxBS5z88?si=XGS6Chydn6lhSO1S" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
+
 ## Overview
 
 LangGraph Platform is a commercial solution for deploying agentic applications to production, built on the open-source [LangGraph framework](./high_level.md).
@@ -16,6 +20,8 @@ The LangGraph Platform consists of several components that work together to supp
 - [LangGraph CLI](./langgraph_cli.md): LangGraph CLI is a command-line interface that helps to interact with a local LangGraph
 - [Python/JS SDK](./sdk.md): The Python/JS SDK provides a programmatic way to interact with deployed LangGraph Applications.
 - [Remote Graph](../how-tos/use-remote-graph.md): A RemoteGraph allows you to interact with any deployed LangGraph application as though it were running locally.
+- [LangGraph Control Plane](./langgraph_control_plane.md): The LangGraph Control Plane refers to the Control Plane UI where users create and update LangGraph Servers and the Control Plane APIs that support the UI experience.
+- [LangGraph Data Plane](./langgraph_data_plane.md): The LangGraph Data Plane refers to LangGraph Servers, the corresponding infrastructure for each server, and the "listener" application that continuously polls for updates from the LangGraph Control Plane.
 
 ![](img/lg_platform.png)
 

docs/docs/concepts/langgraph_self_hosted_control_plane.md

@@ -0,0 +1,23 @@
+# Self-Hosted Control Plane (Beta)
+
+To deploy a [LangGraph Server](../concepts/langgraph_server.md), follow the how-to guide for [how to deploy the Self-Hosted Control Plane](../cloud/deployment/self_hosted_control_plane.md).
+
+## Overview
+
+The Self-Hosted Control Plane deployment option is a fully self-hosted model for deployment where you manage the [control plane](./langgraph_control_plane.md) and [data plane](./langgraph_data_plane.md) in your cloud (this option implies that the data plane is self-hosted).
+
+|                   | [Control Plane](../concepts/langgraph_control_plane.md) | [Data Plane](../concepts/langgraph_data_plane.md) |
+|-------------------|-------------------|------------|
+| **What is it?** | <ul><li>Control Plane UI for creating deployments and revisions</li><li>Control Plane APIs for creating deployments and revisions</li></ul> | <ul><li>Data plane "listener" for reconciling deployments with control plane state</li><li>LangGraph Servers</li><li>Postgres, Redis, etc</li></ul> |
+| **Where is it hosted?** | Your cloud | Your cloud |
+| **Who provisions and manages it?** | You | You |
+
+## Architecture
+
+![Self-Hosted Control Plane Architecture](./img/self_hosted_control_plane_architecture.png)
+
+## Compute Platforms
+
+### Kubernetes
+
+The Self-Hosted Control Plane deployment option supports deploying control plane and data plane infrastructure to any Kubernetes cluster.

docs/docs/concepts/langgraph_self_hosted_data_plane.md

@@ -0,0 +1,27 @@
+# Self-Hosted Data Plane (Beta)
+
+To deploy a [LangGraph Server](../concepts/langgraph_server.md), follow the how-to guide for [how to deploy the Self-Hosted Data Plane](../cloud/deployment/self_hosted_data_plane.md).
+
+## Overview
+
+LangGraph Platform's Self-Hosted Data Plane deployment option is a "hybrid" model for deployemnt where we manage the [control plane](./langgraph_control_plane.md) in our cloud and you manage the [data plane](./langgraph_data_plane.md) in your cloud.
+
+|                   | [Control Plane](../concepts/langgraph_control_plane.md) | [Data Plane](../concepts/langgraph_data_plane.md) |
+|-------------------|-------------------|------------|
+| **What is it?** | <ul><li>Control Plane UI for creating deployments and revisions</li><li>Control Plane APIs for creating deployments and revisions</li></ul> | <ul><li>Data plane "listener" for reconciling deployments with control plane state</li><li>LangGraph Servers</li><li>Postgres, Redis, etc</li></ul> |
+| **Where is it hosted?** | LangChain's cloud | Your cloud |
+| **Who provisions and manages it?** | LangChain | You |
+
+## Architecture
+
+![Self-Hosted Data Plane Architecture](./img/self_hosted_data_plane_architecture.png)
+
+## Compute Platforms
+
+### Kubernetes
+
+The Self-Hosted Data Plane deployment option supports deploying data plane infrastructure to any Kubernetes cluster.
+
+### Amazon ECS
+
+Coming soon...

docs/docs/concepts/langgraph_standalone_container.md

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

docs/docs/concepts/multi_agent.md

@@ -50,7 +50,7 @@ def agent(state) -> Command[Literal["agent", "another_agent"]]:
 In a more complex scenario where each agent node is itself a graph (i.e., a [subgraph](./low_level.md#subgraphs)), a node in one of the agent subgraphs might want to navigate to a different agent. For example, if you have two agents, `alice` and `bob` (subgraph nodes in a parent graph), and `alice` needs to navigate to `bob`, you can set `graph=Command.PARENT` in the `Command` object:
 
 ```python
-def some_node_inside_alice(state)
+def some_node_inside_alice(state):
     return Command(
         goto="bob",
         update={"my_state_key": "my_state_value"},

docs/docs/concepts/persistence.md

@@ -4,6 +4,10 @@ LangGraph has a built-in persistence layer, implemented through checkpointers. W
 
 ![Checkpoints](img/persistence/checkpoints.jpg)
 
+!!! info "LangGraph API handles checkpointing automatically"
+
+    When using the LangGraph API, you don't need to implement or configure checkpointers manually. The API handles all persistence infrastructure for you behind the scenes.
+
 ## Threads
 
 A thread is a unique ID or [thread identifier](#threads) assigned to each checkpoint saved by a checkpointer. When invoking graph with a checkpointer, you **must** specify a `thread_id` as part of the `configurable` portion of the config:
@@ -26,7 +30,7 @@ Let's see what checkpoints are saved when a simple graph is invoked as follows:
 
 ```python
 from langgraph.graph import StateGraph, START, END
-from langgraph.checkpoint.memory import MemorySaver
+from langgraph.checkpoint.memory import InMemorySaver
 from typing import Annotated
 from typing_extensions import TypedDict
 from operator import add
@@ -49,7 +53,7 @@ workflow.add_edge(START, "node_a")
 workflow.add_edge("node_a", "node_b")
 workflow.add_edge("node_b", END)
 
-checkpointer = MemorySaver()
+checkpointer = InMemorySaver()
 graph = workflow.compile(checkpointer=checkpointer)
 
 config = {"configurable": {"thread_id": "1"}}
@@ -223,6 +227,10 @@ But, what if we want to retain some information *across threads*? Consider the c
 
 With checkpointers alone, we cannot share information across threads. This motivates the need for the [`Store`](../reference/store.md#langgraph.store.base.BaseStore) interface. As an illustration, we can define an `InMemoryStore` to store information about a user across threads. We simply compile our graph with a checkpointer, as before, and with our new `in_memory_store` variable.
 
+!!!  info "LangGraph API handles stores automatically"
+
+    When using the LangGraph API, you don't need to implement or configure stores manually. The API handles all storage infrastructure for you behind the scenes.
+
 ### Basic Usage
 
 First, let's showcase this in isolation without using LangGraph.
@@ -324,10 +332,10 @@ store.put(
 With this all in place, we use the `in_memory_store` in LangGraph. The `in_memory_store` works hand-in-hand with the checkpointer: the checkpointer saves state to threads, as discussed above, and the `in_memory_store` allows us to store arbitrary information for access *across* threads. We compile the graph with both the checkpointer and the `in_memory_store` as follows. 
 
 ```python
-from langgraph.checkpoint.memory import MemorySaver
+from langgraph.checkpoint.memory import InMemorySaver
 
 # We need this because we want to enable threads (conversations)
-checkpointer = MemorySaver()
+checkpointer = InMemorySaver()
 
 # ... Define the graph ...
 
@@ -440,6 +448,7 @@ Under the hood, checkpointing is powered by checkpointer objects that conform to
 * `langgraph-checkpoint-sqlite`: An implementation of LangGraph checkpointer that uses SQLite database ([SqliteSaver][langgraph.checkpoint.sqlite.SqliteSaver] / [AsyncSqliteSaver][langgraph.checkpoint.sqlite.aio.AsyncSqliteSaver]). Ideal for experimentation and local workflows. Needs to be installed separately.
 * `langgraph-checkpoint-postgres`: An advanced checkpointer that uses Postgres database ([PostgresSaver][langgraph.checkpoint.postgres.PostgresSaver] / [AsyncPostgresSaver][langgraph.checkpoint.postgres.aio.AsyncPostgresSaver]), used in LangGraph Cloud. Ideal for using in production. Needs to be installed separately.
 
+
 ### Checkpointer interface
 
 Each checkpointer conforms to [BaseCheckpointSaver][langgraph.checkpoint.base.BaseCheckpointSaver] interface and implements the following methods:
@@ -452,7 +461,7 @@ Each checkpointer conforms to [BaseCheckpointSaver][langgraph.checkpoint.base.Ba
 If the checkpointer is used with asynchronous graph execution (i.e. executing the graph via `.ainvoke`, `.astream`, `.abatch`), asynchronous versions of the above methods will be used (`.aput`, `.aput_writes`, `.aget_tuple`, `.alist`).
 
 !!! note Note
-    For running your graph asynchronously, you can use `MemorySaver`, or async versions of Sqlite/Postgres checkpointers -- `AsyncSqliteSaver` / `AsyncPostgresSaver` checkpointers.
+    For running your graph asynchronously, you can use `InMemorySaver`, or async versions of Sqlite/Postgres checkpointers -- `AsyncSqliteSaver` / `AsyncPostgresSaver` checkpointers.
 
 ### Serializer
 

docs/docs/concepts/platform_architecture.md

@@ -4,7 +4,7 @@
 
 ## How we use Postgres
 
-Postgres is the persistence layer for all user and run data in LGP. This stores both checkpoints (see more info [here](./persistence.md)) as well as the server resources (threads, runs, assistants and crons).
+Postgres is the persistence layer for all user, run, and long-term memory data in LGP. This stores both checkpoints (see more info [here](./persistence.md)), server resources (threads, runs, assistants and crons), as well as items saved in the long-term memory store (see more info [here](./persistence.md#memory-store)).
 
 ## How we use Redis
 

docs/docs/how-tos/auth/custom_auth.md

@@ -9,10 +9,6 @@
     
     For a more guided walkthrough, see [**setting up custom authentication**](../../tutorials/auth/getting_started.md) tutorial.
 
-???+ note "Python only"
-  
-    We currently only support custom authentication and authorization in Python deployments with `langgraph-api>=0.0.11`. Support for LangGraph.JS will be added soon.
-
 ???+ note "Support by deployment type"
 
     Custom auth is supported for all deployments in the **managed LangGraph Cloud**, as well as **Enterprise** self-hosted plans. It is not supported for **Lite** self-hosted plans.

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

@@ -8,10 +8,6 @@ Defining a custom app object lets you add any routes you'd like, so you can do a
 
 Below is an example using FastAPI.
 
-???+ note "Python only"
-
-    We currently only support custom authentication and authorization in Python deployments with `langgraph-api>=0.0.26`.
-
 ## Create app
 
 Starting from an **existing** LangGraph Platform application, add the following custom route code to your `webapp.py` file. If you are starting from scratch, you can create a new app from a template using the CLI.

docs/docs/how-tos/index.md

@@ -163,6 +163,7 @@ These guides show how to use the prebuilt ReAct agent:
 - [How to add human-in-the-loop processes to a ReAct agent](create-react-agent-hitl.ipynb)
 - [How to return structured output from a ReAct agent](create-react-agent-structured-output.ipynb)
 - [How to add semantic search for long-term memory to a ReAct agent](memory/semantic-search.ipynb#using-in-create-react-agent)
+- [How to manage message history in a ReAct agent](create-react-agent-manage-message-history.ipynb)
 
 Interested in further customizing the ReAct agent? This guide provides an
 overview of its underlying implementation to help you customize for your own needs:
@@ -201,11 +202,14 @@ Learn how to set up your app for deployment to LangGraph Platform:
 
 ### Deployment
 
-LangGraph applications can be deployed using LangGraph Cloud, which provides a range of services to help you deploy, manage, and scale your applications.
+LangGraph applications can be deployed using LangGraph Platform, which provides a range of services to help you deploy, manage, and scale your applications.
 
-- [How to deploy to LangGraph cloud](../cloud/deployment/cloud.md)
-- [How to deploy to a self-hosted environment](./deploy-self-hosted.md)
+- [How to deploy to Cloud SaaS](../cloud/deployment/cloud.md)
+- [How to deploy the Self-Hosted Data Plane](../cloud/deployment/self_hosted_data_plane.md)
+- [How to deploy the Self-Hosted Control Plane](../cloud/deployment/self_hosted_control_plane.md)
+- [How to deploy a Standalone Container](../cloud/deployment/standalone_container.md)
 - [How to interact with the deployment using RemoteGraph](./use-remote-graph.md)
+- [How to add TTLs to your LangGraph application](./ttl/configure_ttl.md)
 
 ### Authentication & Access Control
 

docs/docs/how-tos/persistence-functional.ipynb

@@ -16,6 +16,10 @@
     "    - [Memory](../../concepts/memory/)\n",
     "    - [Chat Models](https://python.langchain.com/docs/concepts/chat_models/)\n",
     "\n",
+    "!!! info \"Not needed for LangGraph API users\"\n",
+    "\n",
+    "    If you're using the LangGraph API, you needn't manually implement a checkpointer. The API automatically handles checkpointing for you. This guide is relevant when implementing LangGraph in your own custom server.\n",
+    "\n",
     "Many AI applications need memory to share context across multiple interactions on the same [thread](../../concepts/persistence#threads) (e.g., multiple turns of a conversation). In LangGraph functional API, this kind of memory can be added to any [entrypoint()][langgraph.func.entrypoint] workflow using [thread-level persistence](https://langchain-ai.github.io/langgraph/concepts/persistence).\n",
     "\n",
     "When creating a LangGraph workflow, you can set it up to persist its results by using a [checkpointer](https://langchain-ai.github.io/langgraph/reference/checkpoints/#basecheckpointsaver):\n",

docs/docs/how-tos/persistence.ipynb

@@ -31,6 +31,10 @@
     "    </p>\n",
     "</div> \n",
     "\n",
+    "!!! info \"Not needed for LangGraph API users\"\n",
+    "\n",
+    "    If you're using the LangGraph API, you needn't manually implement a checkpointer. The API automatically handles checkpointing for you. This guide is relevant when implementing LangGraph in your own custom server.\n",
+    "\n",
     "Many AI applications need memory to share context across multiple interactions. In LangGraph, this kind of memory can be added to any [StateGraph](https://langchain-ai.github.io/langgraph/reference/graphs/#langgraph.graph.StateGraph) using [thread-level persistence](https://langchain-ai.github.io/langgraph/concepts/persistence) .\n",
     "\n",
     "When creating any LangGraph graph, you can set it up to persist its state by adding a [checkpointer](https://langchain-ai.github.io/langgraph/reference/checkpoints/#basecheckpointsaver) when compiling the graph:\n",

docs/docs/how-tos/persistence_postgres.ipynb

@@ -26,6 +26,10 @@
     "    </p>\n",
     "</div> \n",
     "\n",
+    "!!! info \"Not needed for LangGraph API users\"\n",
+    "\n",
+    "    If you're using the LangGraph API, you needn't manually implement a checkpointer. The API automatically handles checkpointing for you. This guide is relevant when implementing LangGraph in your own custom server.\n",
+    "\n",
     "When creating LangGraph agents, you can also set them up so that they persist their state. This allows you to do things like interact with an agent multiple times and have it remember previous interactions.\n",
     "\n",
     "This how-to guide shows how to use `Postgres` as the backend for persisting checkpoint state using the [`langgraph-checkpoint-postgres`](https://github.com/langchain-ai/langgraph/tree/main/libs/checkpoint-postgres) library.\n",
@@ -44,7 +48,7 @@
     "...\n",
     "```\n",
     "\n",
-    "!!! info \"Setup\"",
+    "!!! info \"Setup\"\n",
     "\n",
     "    You need to run `.setup()` once on your checkpointer to initialize the database before you can use it."
    ]

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

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

docs/docs/index.md

@@ -1,6 +1,6 @@
 ---
 hide_comments: true
-title: Home
+title: LangGraph
 ---
 
 <script>
@@ -23,6 +23,9 @@ title: Home
 .md-content h1 {
   display: none;
 }
+.md-header__topic {
+  display: none;
+}
 </style>
 
 {!../README.md!}

docs/docs/tutorials/deployment.md

@@ -17,7 +17,18 @@ Get started deploying your LangGraph applications locally or on the cloud with
 
 ## Deployment Options
 
-- [Self-Hosted Lite](../concepts/self_hosted.md): A free (up to 1 million nodes executed per year), limited version of LangGraph Platform that you can run locally or in a self-hosted manner
-- [Cloud SaaS](../concepts/langgraph_cloud.md): Hosted as part of LangSmith.
-- [Bring Your Own Cloud](../concepts/bring_your_own_cloud.md): We manage the infrastructure, so you don't have to, but the infrastructure all runs within your cloud.
-- [Self-Hosted Enterprise](../concepts/self_hosted.md): Completely managed by you.
+- <a href="../../concepts/langgraph_cloud/">Cloud SaaS<sup>(Beta)</sup></a>: Connect to your GitHub repositories and deploy LangGraph Servers to LangChain's cloud. We manage everything.
+- <a href="../../concepts/langgraph_self_hosted_data_plane/">Self-Hosted Data Plane<sup>(Beta)</sup></a>: Create deployments from the [Control Plane UI](../concepts/langgraph_control_plane.md#control-plane-ui) and deploy LangGraph Servers to your cloud. We manage the [control plane](../concepts/langgraph_control_plane.md), you manage the deployments.
+- <a href="../../concepts/langgraph_self_hosted_control_plane/">Self-Hosted Control Plane<sup>(Beta)</sup></a>: Create deployments from a self-hosted [Control Plane UI](../concepts/langgraph_control_plane.md#control-plane-ui) and deploy LangGraph Servers to your cloud. You manage everything.
+- [Standalone Container](../concepts/langgraph_standalone_container.md): Deploy LangGraph Server Docker images however you like.
+
+A quick comparison...
+
+|                      | **Cloud SaaS** | **Self-Hosted [Data Plane](../concepts/langgraph_data_plane.md)** | **Self-Hosted [Control Plane](../concepts/langgraph_control_plane.md)** | **Standalone Container** |
+|----------------------|----------------|----------------------------|-------------------------------|--------------------------|
+| **[Control Plane UI/API](../concepts/langgraph_control_plane.md)** | Yes | Yes | Yes | No |
+| **CI/CD** | Managed internally by platform | Managed externally by you | Managed externally by you | Managed externally by you |
+| **Data/Compute Residency** | LangChain’s cloud | Your cloud | Your cloud | Your cloud |
+| **Required Permissions** | None | See details [here](). | See details [here](). | None |
+| **LangSmith Compatibility** | Trace to LangSmith SaaS | Trace to LangSmith SaaS | Trace to Self-Hosted LangSmith | Optional tracing |
+| **[Pricing](https://www.langchain.com/pricing-langgraph-platform)** | Plus | Enterprise | Enterprise | Developer |

docs/docs/tutorials/introduction.ipynb

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

docs/docs/tutorials/workflows/index.md

@@ -222,7 +222,7 @@ As noted in the Anthropic blog on `Building Effective Agents`:
 
 
     @entrypoint()
-    def parallel_workflow(topic: str):
+    def prompt_chaining_workflow(topic: str):
         original_joke = generate_joke(topic).result()
         if check_punchline(original_joke) == "Pass":
             return original_joke
@@ -231,7 +231,7 @@ As noted in the Anthropic blog on `Building Effective Agents`:
         return polish_joke(improved_joke).result()
 
     # Invoke
-    for step in parallel_workflow.stream("cats", stream_mode="updates"):
+    for step in prompt_chaining_workflow.stream("cats", stream_mode="updates"):
         print(step)
         print("\n")
     ```

docs/mkdocs.yml

@@ -57,12 +57,16 @@ plugins:
       separator: '[\s\u200b\-,:!=\[\]()"`/]+|\.(?!\d)|&[lg]t;'
   - autorefs
   - mkdocstrings:
+      custom_templates: templates
       handlers:
         python:
           import:
             - https://docs.python.org/3/objects.inv
             - https://python.langchain.com/api_reference/objects.inv
           options:
+            preload_modules:
+              - langchain
+              - langchain_core
             enable_inventory: true
             members_order: source
             allow_inspection: true
@@ -75,7 +79,10 @@ plugins:
               docstring_style: google
             docstring_section_style: list
             show_root_toc_entry: false
+            show_signature: true
             show_signature_annotations: true
+            separate_signature: true
+            line_length: 60
             show_symbol_type_heading: true
             show_symbol_type_toc: true
             signature_crossrefs: true
@@ -185,6 +192,7 @@ nav:
               - how-tos/create-react-agent-system-prompt.ipynb
               - how-tos/create-react-agent-hitl.ipynb
               - how-tos/create-react-agent-structured-output.ipynb
+              - how-tos/create-react-agent-manage-message-history.ipynb
               - how-tos/react-agent-from-scratch.ipynb
               - how-tos/react-agent-from-scratch-functional.ipynb
         - LangGraph Platform:
@@ -202,12 +210,18 @@ nav:
             - Deployment:
                 - Deployment: how-tos#deployment
                 - cloud/deployment/cloud.md
+                - cloud/deployment/self_hosted_data_plane.md
+                - cloud/deployment/self_hosted_control_plane.md
+                - cloud/deployment/standalone_container.md
                 - how-tos/deploy-self-hosted.md
                 - how-tos/use-remote-graph.md
+                - how-tos/ttl/configure_ttl.md
+            - Data Management:
+                - how-tos/ttl/configure_ttl.md
             - Authentication & Access Control:
                 - Authentication & Access Control: how-tos#authentication-access-control
-                - cloud/how-tos/auth/custom_auth_new.md
-                - cloud/how-tos/auth/openapi_security_new.md
+                - how-tos/auth/custom_auth.md
+                - how-tos/auth/openapi_security.md
             - Assistants:
                 - Assistants: how-tos#assistants
                 - cloud/how-tos/configuration_cloud.md
@@ -249,6 +263,11 @@ nav:
                 - cloud/how-tos/webhooks.md
             - Cron Jobs:
                 - cloud/how-tos/cron_jobs.md
+            - Modifying the API:
+                - Modifying the API: how-tos#modifying-the-api
+                - how-tos/http/custom_lifespan.md
+                - how-tos/http/custom_middleware.md
+                - how-tos/http/custom_routes.md
             - LangGraph Studio:
                 - LangGraph Studio: how-tos#langgraph-studio
                 - cloud/how-tos/test_deployment.md
@@ -258,6 +277,7 @@ nav:
                 - cloud/how-tos/datasets_studio.md
                 - cloud/how-tos/iterate_graph_studio.md
                 - cloud/how-tos/clone_traces_studio.md
+                - how-tos/local-studio.md
       - Concepts:
         - concepts/index.md
         - LangGraph:
@@ -266,8 +286,9 @@ nav:
           - concepts/low_level.md
           - concepts/agentic_concepts.md
           - concepts/multi_agent.md
-          - concepts/breakpoints
+          - concepts/breakpoints.md
           - concepts/human_in_the_loop.md
+          - concepts/v0-human-in-the-loop.md
           - concepts/time-travel.md
           - concepts/persistence.md
           - concepts/memory.md
@@ -280,11 +301,16 @@ nav:
           - High Level:
             - High Level: concepts#high-level
             - concepts/langgraph_platform.md
+            - concepts/platform_architecture.md
+            - concepts/scalability_and_resilience.md
             - concepts/deployment_options.md
+            - concepts/bring_your_own_cloud.md
             - concepts/plans.md
             - concepts/template_applications.md
           - Components:
             - Components: concepts#components
+            - concepts/langgraph_control_plane.md
+            - concepts/langgraph_data_plane.md
             - concepts/langgraph_server.md
             - concepts/langgraph_studio.md
             - concepts/langgraph_cli.md
@@ -298,9 +324,11 @@ nav:
             - concepts/auth.md
           - Deployment Options:
             - Deployment Options: concepts#deployment-options
-            - concepts/self_hosted.md
             - concepts/langgraph_cloud.md
-            - concepts/bring_your_own_cloud.md
+            - concepts/langgraph_self_hosted_data_plane.md
+            - concepts/langgraph_self_hosted_control_plane.md
+            - concepts/langgraph_standalone_container.md
+            - concepts/self_hosted.md
       - Tutorials:
         - tutorials/index.md
         - Quick Start:
@@ -377,6 +405,7 @@ nav:
       - LangGraph Academy Course: https://academy.langchain.com/courses/intro-to-langgraph
 
   - API reference:
+    - reference/index.md
     - Library:
       - Graphs: reference/graphs.md
       - Checkpointing: reference/checkpoints.md
@@ -487,13 +516,8 @@ extra:
             Thanks for your feedback! Please help us improve this page by adding to the discussion below.
 validation:
   # https://www.mkdocs.org/user-guide/configuration/
-  # We're `ignoring` nav.omitted_files because we are going to rely
-  # on files being properly links to from the index pages of:
-  # - tutorials
-  # - concepts
-  # - how-tos
-  # - reference
-  omitted_files: ignore
+  # We are still raising for omitted files because they determine the breadcrumbs for pages.
+  omitted_files: warn 
   absolute_links: warn
   unrecognized_links: warn
   # TODO: figure out how to enable 'warn' for this

docs/overrides/main.html

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

docs/pyproject.toml

@@ -11,6 +11,7 @@ python = "^3.10"
 aiohappyeyeballs = "2.4.3"
 hub = "^3.0.1"
 xxhash = "^3.5.0"
+black = "^25.1.0"
 
 [tool.poetry.group.docs.dependencies]
 langgraph = { path = "../libs/langgraph/", develop = true }
@@ -50,7 +51,8 @@ langchain-community = "^0.3.0"
 langchain-experimental = "^0.3.2"
 langchain-mistralai = "^0.2.6"
 langgraph-checkpoint-mongodb = "^0.1.0"
-langsmith = "^0.2.0"
+langmem = "^0.0.19"
+langsmith = "^0.3.0"
 chromadb = "^0.5.5"
 gpt4all = "^2.8.2"
 scikit-learn = "^1.5.2"

docs/templates/python/material/function.html.jinja

@@ -0,0 +1,121 @@
+{#- Template for Python functions.
+   
+This template renders a Python function or method.
+
+Context:
+  function (griffe.Function): The function to render.
+  root (bool): Whether this is the root object, injected with `:::` in a Markdown page.
+  heading_level (int): The HTML heading level to use.
+  config (dict): The configuration options.
+-#}
+
+{% block logs scoped %}
+  {{ log.debug("Rendering " + function.path) }}
+{% endblock logs %}
+
+{% import "language"|get_template as lang with context %}
+{#- Language module providing the `t` translation method. -#}
+
+<div class="doc doc-object doc-function">
+  {% with obj = function, html_id = function.path %}
+    {% if root %}
+      {% set show_full_path = config.show_root_full_path %}
+      {% set root_members = True %}
+    {% elif root_members %}
+      {% set show_full_path = config.show_root_members_full_path or config.show_object_full_path %}
+      {% set root_members = False %}
+    {% else %}
+      {% set show_full_path = config.show_object_full_path %}
+    {% endif %}
+
+    {% set function_name = function.path if show_full_path else function.name %}
+    {#- Brief or full function name depending on configuration. -#}
+    {% set symbol_type = "method" if function.parent.is_class else "function" %}
+    {#- Symbol type: method when parent is a class, function otherwise. -#}
+
+    {% if not root or config.show_root_heading %}
+      {% filter heading(
+          heading_level,
+          role="function",
+          id=html_id,
+          class="doc doc-heading",
+          toc_label=(('<code class="doc-symbol doc-symbol-toc doc-symbol-' + symbol_type + '"></code>&nbsp;')|safe if config.show_symbol_type_toc else '') + function.name,
+        ) %}
+      
+        {% block heading scoped %}
+          {% if config.show_symbol_type_heading %}<code class="doc-symbol doc-symbol-heading doc-symbol-{{ symbol_type }}"></code>{% endif %}
+          {% if config.separate_signature %}
+            <span class="doc doc-object-name doc-function-name">{{ config.heading if config.heading and root else function_name }}</span>
+          {% else %}
+            {%+ filter highlight(language="python", inline=True) %}
+              {{ function_name }}{% include "signature"|get_template with context %}
+            {% endfilter %}
+          {% endif %}
+        {% endblock heading %}
+
+        {% block labels scoped %}
+          {% with labels = function.labels %}
+            {% include "labels"|get_template with context %}
+          {% endwith %}
+        {% endblock labels %}
+
+      {% endfilter %}
+
+      {% block signature scoped %}
+        {#- Signature block.
+        
+        This block renders only the main signature and deliberately omits the overloads.
+        -#}
+        {% if config.separate_signature %}
+          {% filter format_signature(function, config.line_length, crossrefs=config.signature_crossrefs) %}
+            {{ function.name }}
+          {% endfilter %}
+        {% endif %}
+      {% endblock signature %}
+
+    {% else %}
+
+      {% if config.show_root_toc_entry %}
+        {% filter heading(
+            heading_level,
+            role="function",
+            id=html_id,
+            toc_label=(('<code class="doc-symbol doc-symbol-toc doc-symbol-' + symbol_type + '"></code>&nbsp;')|safe if config.show_symbol_type_toc else '') + (config.toc_label if config.toc_label and root else function.name),
+            hidden=True,
+          ) %}
+        {% endfilter %}
+      {% endif %}
+      {% set heading_level = heading_level - 1 %}
+    {% endif %}
+
+    <div class="doc doc-contents {% if root %}first{% endif %}">
+      {% block contents scoped %}
+        {#- Contents block.
+        
+        This block renders the function’s docstring and source.
+        -#}
+        {% block docstring scoped %}
+          {% with docstring_sections = function.docstring.parsed %}
+            {% include "docstring"|get_template with context %}
+          {% endwith %}
+        {% endblock docstring %}
+
+        {% block source scoped %}
+          {% if config.show_source and function.source %}
+            <details class="quote">
+              <summary>{{ lang.t("Source code in") }} <code>
+                {%- if function.relative_filepath.is_absolute() -%}
+                  {{ function.relative_package_filepath }}
+                {%- else -%}
+                  {{ function.relative_filepath }}
+                {%- endif -%}
+              </code></summary>
+              {{ function.source|highlight(language="python", linestart=function.lineno or 0, linenums=True) }}
+            </details>
+          {% endif %}
+        {% endblock source %}
+      {% endblock contents %}
+    </div>
+
+  {% endwith %}
+</div>

libs/checkpoint-postgres/langgraph/checkpoint/postgres/shallow.py

@@ -1,5 +1,6 @@
 import asyncio
 import threading
+import warnings
 from collections.abc import AsyncIterator, Iterator, Sequence
 from contextlib import asynccontextmanager, contextmanager
 from typing import Any, Optional
@@ -150,7 +151,7 @@ def _dump_blobs(
     checkpoint_ns: str,
     values: dict[str, Any],
     versions: ChannelVersions,
-) -> list[tuple[str, str, str, str, str, Optional[bytes]]]:
+) -> list[tuple[str, str, str, str, Optional[bytes]]]:
     if not versions:
         return []
 
@@ -188,6 +189,12 @@ class ShallowPostgresSaver(BasePostgresSaver):
         pipe: Optional[Pipeline] = None,
         serde: Optional[SerializerProtocol] = None,
     ) -> None:
+        warnings.warn(
+            "ShallowPostgresSaver is deprecated as of version 2.0.20 and will be removed in 3.0.0. "
+            "Use PostgresSaver instead, and invoke the graph with `graph.invoke(..., checkpoint_during=False)`.",
+            DeprecationWarning,
+            stacklevel=2,
+        )
         super().__init__(serde=serde)
         if isinstance(conn, ConnectionPool) and pipe is not None:
             raise ValueError(
@@ -528,6 +535,12 @@ class AsyncShallowPostgresSaver(BasePostgresSaver):
         pipe: Optional[AsyncPipeline] = None,
         serde: Optional[SerializerProtocol] = None,
     ) -> None:
+        warnings.warn(
+            "AsyncShallowPostgresSaver is deprecated as of version 2.0.20 and will be removed in 3.0.0. "
+            "Use AsyncPostgresSaver instead, and invoke the graph with `await graph.ainvoke(..., checkpoint_during=False)`.",
+            DeprecationWarning,
+            stacklevel=2,
+        )
         super().__init__(serde=serde)
         if isinstance(conn, AsyncConnectionPool) and pipe is not None:
             raise ValueError(

libs/checkpoint-sqlite/poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 2.0.0 and should not be changed by hand.
+# This file is automatically @generated by Poetry 2.1.1 and should not be changed by hand.
 
 [[package]]
 name = "aiosqlite"
@@ -51,7 +51,7 @@ typing-extensions = {version = ">=4.1", markers = "python_version < \"3.11\""}
 
 [package.extras]
 doc = ["Sphinx (>=7)", "packaging", "sphinx-autodoc-typehints (>=1.2.0)", "sphinx-rtd-theme"]
-test = ["anyio[trio]", "coverage[toml] (>=7)", "exceptiongroup (>=1.2.0)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "uvloop (>=0.17)"]
+test = ["anyio[trio]", "coverage[toml] (>=7)", "exceptiongroup (>=1.2.0)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "uvloop (>=0.17) ; platform_python_implementation == \"CPython\" and platform_system != \"Windows\""]
 trio = ["trio (>=0.23)"]
 
 [[package]]
@@ -181,7 +181,7 @@ files = [
 [package.extras]
 dev = ["Pygments", "build", "chardet", "pre-commit", "pytest", "pytest-cov", "pytest-dependency", "ruff", "tomli", "twine"]
 hard-encoding-detection = ["chardet"]
-toml = ["tomli"]
+toml = ["tomli ; python_version < \"3.11\""]
 types = ["chardet (>=5.1.0)", "mypy", "pytest", "pytest-cov", "pytest-dependency"]
 
 [[package]]
@@ -267,7 +267,7 @@ idna = "*"
 sniffio = "*"
 
 [package.extras]
-brotli = ["brotli", "brotlicffi"]
+brotli = ["brotli ; platform_python_implementation == \"CPython\"", "brotlicffi ; platform_python_implementation != \"CPython\""]
 cli = ["click (==8.*)", "pygments (==2.*)", "rich (>=10,<14)"]
 http2 = ["h2 (>=3,<5)"]
 socks = ["socksio (==1.*)"]
@@ -326,26 +326,26 @@ files = [
 
 [[package]]
 name = "langchain-core"
-version = "0.3.0"
+version = "0.3.15"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = "<4.0,>=3.9"
 groups = ["main", "dev"]
 files = [
-    {file = "langchain_core-0.3.0-py3-none-any.whl", hash = "sha256:bee6dae2366d037ef0c5b87401fed14b5497cad26f97724e8c9ca7bc9239e847"},
-    {file = "langchain_core-0.3.0.tar.gz", hash = "sha256:1249149ea3ba24c9c761011483c14091573a5eb1a773aa0db9c8ad155dd4a69d"},
+    {file = "langchain_core-0.3.15-py3-none-any.whl", hash = "sha256:3d4ca6dbb8ed396a6ee061063832a2451b0ce8c345570f7b086ffa7288e4fa29"},
+    {file = "langchain_core-0.3.15.tar.gz", hash = "sha256:b1a29787a4ffb7ec2103b4e97d435287201da7809b369740dd1e32f176325aba"},
 ]
 
 [package.dependencies]
 jsonpatch = ">=1.33,<2.0"
-langsmith = ">=0.1.117,<0.2.0"
+langsmith = ">=0.1.125,<0.2.0"
 packaging = ">=23.2,<25"
 pydantic = [
     {version = ">=2.5.2,<3.0.0", markers = "python_full_version < \"3.12.4\""},
     {version = ">=2.7.4,<3.0.0", markers = "python_full_version >= \"3.12.4\""},
 ]
 PyYAML = ">=5.3"
-tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<9.0.0"
+tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<10.0.0"
 typing-extensions = ">=4.7"
 
 [[package]]
@@ -368,24 +368,28 @@ url = "../checkpoint"
 
 [[package]]
 name = "langsmith"
-version = "0.1.120"
+version = "0.1.147"
 description = "Client library to connect to the LangSmith LLM Tracing and Evaluation Platform."
 optional = false
 python-versions = "<4.0,>=3.8.1"
 groups = ["main", "dev"]
 files = [
-    {file = "langsmith-0.1.120-py3-none-any.whl", hash = "sha256:54d2785e301646c0988e0a69ebe4d976488c87b41928b358cb153b6ddd8db62b"},
-    {file = "langsmith-0.1.120.tar.gz", hash = "sha256:25499ca187b41bd89d784b272b97a8d76f60e0e21bdf20336e8a2aa6a9b23ac9"},
+    {file = "langsmith-0.1.147-py3-none-any.whl", hash = "sha256:7166fc23b965ccf839d64945a78e9f1157757add228b086141eb03a60d699a15"},
+    {file = "langsmith-0.1.147.tar.gz", hash = "sha256:2e933220318a4e73034657103b3b1a3a6109cc5db3566a7e8e03be8d6d7def7a"},
 ]
 
 [package.dependencies]
 httpx = ">=0.23.0,<1"
-orjson = ">=3.9.14,<4.0.0"
+orjson = {version = ">=3.9.14,<4.0.0", markers = "platform_python_implementation != \"PyPy\""}
 pydantic = [
     {version = ">=1,<3", markers = "python_full_version < \"3.12.4\""},
     {version = ">=2.7.4,<3.0.0", markers = "python_full_version >= \"3.12.4\""},
 ]
 requests = ">=2,<3"
+requests-toolbelt = ">=1.0.0,<2.0.0"
+
+[package.extras]
+langsmith-pyo3 = ["langsmith-pyo3 (>=0.1.0rc2,<0.2.0)"]
 
 [[package]]
 name = "mypy"
@@ -454,6 +458,7 @@ description = "Fast, correct Python JSON library supporting dataclasses, datetim
 optional = false
 python-versions = ">=3.8"
 groups = ["main", "dev"]
+markers = "platform_python_implementation != \"PyPy\""
 files = [
     {file = "orjson-3.10.6-cp310-cp310-macosx_10_15_x86_64.macosx_11_0_arm64.macosx_10_15_universal2.whl", hash = "sha256:fb0ee33124db6eaa517d00890fc1a55c3bfe1cf78ba4a8899d71a06f2d6ff5c7"},
     {file = "orjson-3.10.6-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9c1c4b53b24a4c06547ce43e5fee6ec4e0d8fe2d597f4647fc033fd205707365"},
@@ -858,6 +863,21 @@ urllib3 = ">=1.21.1,<3"
 socks = ["PySocks (>=1.5.6,!=1.5.7)"]
 use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
 
+[[package]]
+name = "requests-toolbelt"
+version = "1.0.0"
+description = "A utility belt for advanced users of python-requests"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+groups = ["main", "dev"]
+files = [
+    {file = "requests-toolbelt-1.0.0.tar.gz", hash = "sha256:7681a0a3d047012b5bdc0ee37d7f8f07ebe76ab08caeccfc3921ce23c88d5bc6"},
+    {file = "requests_toolbelt-1.0.0-py2.py3-none-any.whl", hash = "sha256:cccfdd665f0a24fcf4726e690f65639d272bb0637b9b92dfd91a5568ccf6bd06"},
+]
+
+[package.dependencies]
+requests = ">=2.0.1,<3.0.0"
+
 [[package]]
 name = "ruff"
 version = "0.6.2"
@@ -952,7 +972,7 @@ files = [
 ]
 
 [package.extras]
-brotli = ["brotli (>=1.0.9)", "brotlicffi (>=0.8.0)"]
+brotli = ["brotli (>=1.0.9) ; platform_python_implementation == \"CPython\"", "brotlicffi (>=0.8.0) ; platform_python_implementation != \"CPython\""]
 h2 = ["h2 (>=4,<5)"]
 socks = ["pysocks (>=1.5.6,!=1.5.7,<2.0)"]
 zstd = ["zstandard (>=0.18.0)"]

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

@@ -30,6 +30,7 @@ from langgraph.checkpoint.serde.types import (
 
 V = TypeVar("V", int, float, str)
 PendingWrite = Tuple[str, str, Any]
+# Kept for backwards compat, newer versions of LangGraph no longer use this.
 LATEST_VERSION = 2
 
 
@@ -100,6 +101,7 @@ class Checkpoint(TypedDict):
     Cleared by the next checkpoint."""
 
 
+# Kept for backwards compat, newer versions of LangGraph no longer use this.
 def empty_checkpoint() -> Checkpoint:
     return Checkpoint(
         v=LATEST_VERSION,

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

@@ -38,6 +38,8 @@ class InMemorySaver(
         Only use `InMemorySaver` for debugging or testing purposes.
         For production use cases we recommend installing [langgraph-checkpoint-postgres](https://pypi.org/project/langgraph-checkpoint-postgres/) and using `PostgresSaver` / `AsyncPostgresSaver`.
 
+        If you are using the LangGraph Platform, no checkpointer needs to be specified. The correct managed checkpointer will be used automatically.
+
     Args:
         serde (Optional[SerializerProtocol]): The serializer to use for serializing and deserializing checkpoints. Defaults to None.
 

libs/checkpoint/poetry.lock

@@ -12,6 +12,29 @@ files = [
     {file = "annotated_types-0.7.0.tar.gz", hash = "sha256:aff07c09a53a08bc8cfccb9c85b05f1aa9a2a6f23728d790723543408344ce89"},
 ]
 
+[[package]]
+name = "anyio"
+version = "4.9.0"
+description = "High level compatibility layer for multiple asynchronous event loop implementations"
+optional = false
+python-versions = ">=3.9"
+groups = ["main"]
+files = [
+    {file = "anyio-4.9.0-py3-none-any.whl", hash = "sha256:9f76d541cad6e36af7beb62e978876f3b41e3e04f2c1fbf0884604c0a9c4d93c"},
+    {file = "anyio-4.9.0.tar.gz", hash = "sha256:673c0c244e15788651a4ff38710fea9675823028a6f08a5eda409e0c9840a028"},
+]
+
+[package.dependencies]
+exceptiongroup = {version = ">=1.0.2", markers = "python_version < \"3.11\""}
+idna = ">=2.8"
+sniffio = ">=1.1"
+typing_extensions = {version = ">=4.5", markers = "python_version < \"3.13\""}
+
+[package.extras]
+doc = ["Sphinx (>=8.2,<9.0)", "packaging", "sphinx-autodoc-typehints (>=1.2.0)", "sphinx_rtd_theme"]
+test = ["anyio[trio]", "blockbuster (>=1.5.23)", "coverage[toml] (>=7)", "exceptiongroup (>=1.2.0)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "trustme", "truststore (>=0.9.1)", "uvloop (>=0.21)"]
+trio = ["trio (>=0.26.1)"]
+
 [[package]]
 name = "certifi"
 version = "2024.7.4"
@@ -177,7 +200,7 @@ version = "1.2.2"
 description = "Backport of PEP 654 (exception groups)"
 optional = false
 python-versions = ">=3.7"
-groups = ["dev"]
+groups = ["main", "dev"]
 markers = "python_version < \"3.11\""
 files = [
     {file = "exceptiongroup-1.2.2-py3-none-any.whl", hash = "sha256:3111b9d131c238bec2f8f516e123e14ba243563fb135d3fe885990585aa7795b"},
@@ -187,6 +210,65 @@ files = [
 [package.extras]
 test = ["pytest (>=6)"]
 
+[[package]]
+name = "h11"
+version = "0.14.0"
+description = "A pure-Python, bring-your-own-I/O implementation of HTTP/1.1"
+optional = false
+python-versions = ">=3.7"
+groups = ["main"]
+files = [
+    {file = "h11-0.14.0-py3-none-any.whl", hash = "sha256:e3fe4ac4b851c468cc8363d500db52c2ead036020723024a109d37346efaa761"},
+    {file = "h11-0.14.0.tar.gz", hash = "sha256:8f19fbbe99e72420ff35c00b27a34cb9937e902a8b810e2c88300c6f0a3b699d"},
+]
+
+[[package]]
+name = "httpcore"
+version = "1.0.7"
+description = "A minimal low-level HTTP client."
+optional = false
+python-versions = ">=3.8"
+groups = ["main"]
+files = [
+    {file = "httpcore-1.0.7-py3-none-any.whl", hash = "sha256:a3fff8f43dc260d5bd363d9f9cf1830fa3a458b332856f34282de498ed420edd"},
+    {file = "httpcore-1.0.7.tar.gz", hash = "sha256:8551cb62a169ec7162ac7be8d4817d561f60e08eaa485234898414bb5a8a0b4c"},
+]
+
+[package.dependencies]
+certifi = "*"
+h11 = ">=0.13,<0.15"
+
+[package.extras]
+asyncio = ["anyio (>=4.0,<5.0)"]
+http2 = ["h2 (>=3,<5)"]
+socks = ["socksio (==1.*)"]
+trio = ["trio (>=0.22.0,<1.0)"]
+
+[[package]]
+name = "httpx"
+version = "0.28.1"
+description = "The next generation HTTP client."
+optional = false
+python-versions = ">=3.8"
+groups = ["main"]
+files = [
+    {file = "httpx-0.28.1-py3-none-any.whl", hash = "sha256:d909fcccc110f8c7faf814ca82a9a4d816bc5a6dbfea25d6591d6985b8ba59ad"},
+    {file = "httpx-0.28.1.tar.gz", hash = "sha256:75e98c5f16b0f35b567856f597f06ff2270a374470a5c2392242528e3e3e42fc"},
+]
+
+[package.dependencies]
+anyio = "*"
+certifi = "*"
+httpcore = "==1.*"
+idna = "*"
+
+[package.extras]
+brotli = ["brotli", "brotlicffi"]
+cli = ["click (==8.*)", "pygments (==2.*)", "rich (>=10,<14)"]
+http2 = ["h2 (>=3,<5)"]
+socks = ["socksio (==1.*)"]
+zstd = ["zstandard (>=0.18.0)"]
+
 [[package]]
 name = "idna"
 version = "3.7"
@@ -240,19 +322,19 @@ files = [
 
 [[package]]
 name = "langchain-core"
-version = "0.2.38"
+version = "0.2.43"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = "<4.0,>=3.8.1"
 groups = ["main"]
 files = [
-    {file = "langchain_core-0.2.38-py3-none-any.whl", hash = "sha256:8a5729bc7e68b4af089af20eff44fe4e7ca21d0e0c87ec21cef7621981fd1a4a"},
-    {file = "langchain_core-0.2.38.tar.gz", hash = "sha256:eb69dbedd344f2ee1f15bcea6c71a05884b867588fadc42d04632e727c1238f3"},
+    {file = "langchain_core-0.2.43-py3-none-any.whl", hash = "sha256:619601235113298ebf8252a349754b7c28d3cf7166c7c922da24944b78a9363a"},
+    {file = "langchain_core-0.2.43.tar.gz", hash = "sha256:42c2ef6adedb911f4254068b6adc9eb4c4075f6c8cb3d83590d3539a815695f5"},
 ]
 
 [package.dependencies]
 jsonpatch = ">=1.33,<2.0"
-langsmith = ">=0.1.75,<0.2.0"
+langsmith = ">=0.1.112,<0.2.0"
 packaging = ">=23.2,<25"
 pydantic = [
     {version = ">=1,<3", markers = "python_full_version < \"3.12.4\""},
@@ -264,23 +346,28 @@ typing-extensions = ">=4.7"
 
 [[package]]
 name = "langsmith"
-version = "0.1.93"
+version = "0.1.147"
 description = "Client library to connect to the LangSmith LLM Tracing and Evaluation Platform."
 optional = false
 python-versions = "<4.0,>=3.8.1"
 groups = ["main"]
 files = [
-    {file = "langsmith-0.1.93-py3-none-any.whl", hash = "sha256:811210b9d5f108f36431bd7b997eb9476a9ecf5a2abd7ddbb606c1cdcf0f43ce"},
-    {file = "langsmith-0.1.93.tar.gz", hash = "sha256:285b6ad3a54f50fa8eb97b5f600acc57d0e37e139dd8cf2111a117d0435ba9b4"},
+    {file = "langsmith-0.1.147-py3-none-any.whl", hash = "sha256:7166fc23b965ccf839d64945a78e9f1157757add228b086141eb03a60d699a15"},
+    {file = "langsmith-0.1.147.tar.gz", hash = "sha256:2e933220318a4e73034657103b3b1a3a6109cc5db3566a7e8e03be8d6d7def7a"},
 ]
 
 [package.dependencies]
-orjson = ">=3.9.14,<4.0.0"
+httpx = ">=0.23.0,<1"
+orjson = {version = ">=3.9.14,<4.0.0", markers = "platform_python_implementation != \"PyPy\""}
 pydantic = [
     {version = ">=1,<3", markers = "python_full_version < \"3.12.4\""},
     {version = ">=2.7.4,<3.0.0", markers = "python_full_version >= \"3.12.4\""},
 ]
 requests = ">=2,<3"
+requests-toolbelt = ">=1.0.0,<2.0.0"
+
+[package.extras]
+langsmith-pyo3 = ["langsmith-pyo3 (>=0.1.0rc2,<0.2.0)"]
 
 [[package]]
 name = "marshmallow"
@@ -369,6 +456,7 @@ description = "Fast, correct Python JSON library supporting dataclasses, datetim
 optional = false
 python-versions = ">=3.8"
 groups = ["main"]
+markers = "platform_python_implementation != \"PyPy\""
 files = [
     {file = "orjson-3.10.6-cp310-cp310-macosx_10_15_x86_64.macosx_11_0_arm64.macosx_10_15_universal2.whl", hash = "sha256:fb0ee33124db6eaa517d00890fc1a55c3bfe1cf78ba4a8899d71a06f2d6ff5c7"},
     {file = "orjson-3.10.6-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9c1c4b53b24a4c06547ce43e5fee6ec4e0d8fe2d597f4647fc033fd205707365"},
@@ -773,6 +861,21 @@ urllib3 = ">=1.21.1,<3"
 socks = ["PySocks (>=1.5.6,!=1.5.7)"]
 use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
 
+[[package]]
+name = "requests-toolbelt"
+version = "1.0.0"
+description = "A utility belt for advanced users of python-requests"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+groups = ["main"]
+files = [
+    {file = "requests-toolbelt-1.0.0.tar.gz", hash = "sha256:7681a0a3d047012b5bdc0ee37d7f8f07ebe76ab08caeccfc3921ce23c88d5bc6"},
+    {file = "requests_toolbelt-1.0.0-py2.py3-none-any.whl", hash = "sha256:cccfdd665f0a24fcf4726e690f65639d272bb0637b9b92dfd91a5568ccf6bd06"},
+]
+
+[package.dependencies]
+requests = ">=2.0.1,<3.0.0"
+
 [[package]]
 name = "ruff"
 version = "0.6.2"
@@ -801,6 +904,18 @@ files = [
     {file = "ruff-0.6.2.tar.gz", hash = "sha256:239ee6beb9e91feb8e0ec384204a763f36cb53fb895a1a364618c6abb076b3be"},
 ]
 
+[[package]]
+name = "sniffio"
+version = "1.3.1"
+description = "Sniff out which async library your code is running under"
+optional = false
+python-versions = ">=3.7"
+groups = ["main"]
+files = [
+    {file = "sniffio-1.3.1-py3-none-any.whl", hash = "sha256:2f6da418d1f1e0fddd844478f41680e794e6051915791a034ff65e5f100525a2"},
+    {file = "sniffio-1.3.1.tar.gz", hash = "sha256:f4324edc670a0f49750a81b895f35c3adb843cca46f0530f79fc1babb23789dc"},
+]
+
 [[package]]
 name = "tenacity"
 version = "8.5.0"

libs/checkpoint/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langgraph-checkpoint"
-version = "2.0.23"
+version = "2.0.24"
 description = "Library with base interfaces for LangGraph checkpoint savers."
 authors = []
 license = "MIT"

libs/cli/langgraph_cli/cli.py

@@ -274,23 +274,13 @@ def _build(
     tag: str,
     passthrough: Sequence[str] = (),
 ):
-    base_image = base_image or (
-        "langchain/langgraphjs-api"
-        if config_json.get("node_version")
-        else "langchain/langgraph-api"
-    )
-
     # pull latest images
     if pull:
         runner.run(
             subp_exec(
                 "docker",
                 "pull",
-                (
-                    f"{base_image}:{config_json['node_version']}"
-                    if config_json.get("node_version")
-                    else f"{base_image}:{config_json['python_version']}"
-                ),
+                langgraph_cli.config.docker_tag(config_json, base_image),
                 verbose=True,
             )
         )
@@ -450,11 +440,7 @@ def dockerfile(save_path: str, config: pathlib.Path, add_docker_compose: bool) -
     dockerfile, additional_contexts = langgraph_cli.config.config_to_docker(
         config,
         config_json,
-        (
-            "langchain/langgraphjs-api"
-            if config_json.get("node_version")
-            else "langchain/langgraph-api"
-        ),
+        None,
     )
     with open(str(save_path), "w", encoding="utf-8") as f:
         f.write(dockerfile)
@@ -665,6 +651,8 @@ def dev(
         wait_for_client=wait_for_client,
         auth=config_json.get("auth"),
         http=config_json.get("http"),
+        ui=config_json.get("ui"),
+        ui_config=config_json.get("ui_config"),
         studio_url=studio_url,
         allow_blocking=allow_blocking,
     )
@@ -717,11 +705,7 @@ def prepare_args_and_stdin(
         config_path,
         config,
         watch=watch,
-        base_image=(
-            "langchain/langgraphjs-api"
-            if config.get("node_version")
-            else "langchain/langgraph-api"
-        ),
+        base_image=langgraph_cli.config.default_base_image(config),
     )
     return args, stdin
 
@@ -748,11 +732,7 @@ def prepare(
             subp_exec(
                 "docker",
                 "pull",
-                (
-                    f"langchain/langgraphjs-api:{config_json['node_version']}"
-                    if config_json.get("node_version")
-                    else f"langchain/langgraph-api:{config_json['python_version']}"
-                ),
+                langgraph_cli.config.docker_tag(config_json),
                 verbose=verbose,
             )
         )

libs/cli/langgraph_cli/config.py

@@ -8,7 +8,10 @@ from typing import Any, Literal, NamedTuple, Optional, TypedDict, Union
 import click
 
 MIN_NODE_VERSION = "20"
+DEFAULT_NODE_VERSION = "20"
+
 MIN_PYTHON_VERSION = "3.11"
+DEFAULT_PYTHON_VERSION = "3.11"
 
 
 class TTLConfig(TypedDict, total=False):
@@ -406,6 +409,18 @@ class Config(TypedDict, total=False):
     """
 
 
+PIP_CLEANUP_LINES = """# -- Ensure user deps didn't inadvertently overwrite langgraph-api
+RUN mkdir -p /api/langgraph_api /api/langgraph_runtime /api/langgraph_license && \
+    touch /api/langgraph_api/__init__.py /api/langgraph_runtime/__init__.py /api/langgraph_license/__init__.py
+RUN PYTHONDONTWRITEBYTECODE=1 pip install --no-cache-dir --no-deps -e /api
+# -- End of ensuring user deps didn't inadvertently overwrite langgraph-api --
+# -- Removing pip from the final image ~<:===~~~ --
+RUN pip uninstall -y pip setuptools wheel && \
+    rm -rf /usr/local/lib/python*/site-packages/pip* /usr/local/lib/python*/site-packages/setuptools* /usr/local/lib/python*/site-packages/wheel* && \
+    find /usr/local/bin -name "pip*" -delete
+# -- End of pip removal --"""
+
+
 def _parse_version(version_str: str) -> tuple[int, int]:
     """Parse a version string into a tuple of (major, minor)."""
     try:
@@ -428,38 +443,54 @@ def _parse_node_version(version_str: str) -> int:
         ) from None
 
 
+def _is_node_graph(spec: Union[str, dict]) -> bool:
+    """Check if a graph is a Node.js graph based on the file extension."""
+    if isinstance(spec, dict):
+        spec = spec.get("path")
+
+    file_path = spec.split(":")[0]
+    file_ext = os.path.splitext(file_path)[1]
+
+    return file_ext in [
+        ".ts",
+        ".mts",
+        ".cts",
+        ".js",
+        ".mjs",
+        ".cjs",
+    ]
+
+
 def validate_config(config: Config) -> Config:
     """Validate a configuration dictionary."""
-    config = (
-        {
-            "node_version": config.get("node_version"),
-            "dockerfile_lines": config.get("dockerfile_lines", []),
-            "dependencies": config.get("dependencies", []),
-            "graphs": config.get("graphs", {}),
-            "env": config.get("env", {}),
-            "store": config.get("store"),
-            "auth": config.get("auth"),
-            "http": config.get("http"),
-            "checkpointer": config.get("checkpointer"),
-            "ui": config.get("ui"),
-            "ui_config": config.get("ui_config"),
-        }
-        if config.get("node_version")
-        else {
-            "python_version": config.get("python_version", "3.11"),
-            "pip_config_file": config.get("pip_config_file"),
-            "dockerfile_lines": config.get("dockerfile_lines", []),
-            "dependencies": config.get("dependencies", []),
-            "graphs": config.get("graphs", {}),
-            "env": config.get("env", {}),
-            "store": config.get("store"),
-            "auth": config.get("auth"),
-            "http": config.get("http"),
-            "checkpointer": config.get("checkpointer"),
-            "ui": config.get("ui"),
-            "ui_config": config.get("ui_config"),
-        }
+
+    graphs = config.get("graphs", {})
+
+    some_node = any(_is_node_graph(spec) for spec in graphs.values())
+    some_python = any(not _is_node_graph(spec) for spec in graphs.values())
+
+    node_version = config.get(
+        "node_version", DEFAULT_NODE_VERSION if some_node else None
     )
+    python_version = config.get(
+        "python_version", DEFAULT_PYTHON_VERSION if some_python else None
+    )
+
+    config = {
+        "node_version": node_version,
+        "python_version": python_version,
+        "pip_config_file": config.get("pip_config_file"),
+        "dependencies": config.get("dependencies", []),
+        "dockerfile_lines": config.get("dockerfile_lines", []),
+        "graphs": config.get("graphs", {}),
+        "env": config.get("env", {}),
+        "store": config.get("store"),
+        "auth": config.get("auth"),
+        "http": config.get("http"),
+        "checkpointer": config.get("checkpointer"),
+        "ui": config.get("ui"),
+        "ui_config": config.get("ui_config"),
+    }
 
     if config.get("node_version"):
         node_version = config["node_version"]
@@ -778,7 +809,22 @@ def _update_graph_paths(
         FileNotFoundError: If the local file (module) does not actually exist on disk.
         IsADirectoryError: If `module_str` points to a directory instead of a file.
     """
-    for graph_id, import_str in config["graphs"].items():
+    for graph_id, data in config["graphs"].items():
+        if isinstance(data, dict):
+            # Then we're looking for a 'path' key
+            if "path" not in data:
+                raise ValueError(
+                    f"Graph '{graph_id}' must contain a 'path' key if "
+                    f" it is a dictionary."
+                )
+            import_str = data["path"]
+        elif isinstance(data, str):
+            import_str = data
+        else:
+            raise ValueError(
+                f"Graph '{graph_id}' must be a string or a dictionary with a 'path' key."
+            )
+
         module_str, _, attr_str = import_str.partition(":")
         if not module_str or not attr_str:
             message = (
@@ -818,7 +864,10 @@ def _update_graph_paths(
                             "Add its containing package to 'dependencies' list."
                         )
             # update the config
-            config["graphs"][graph_id] = f"{module_str}:{attr_str}"
+            if isinstance(data, dict):
+                config["graphs"][graph_id]["path"] = f"{module_str}:{attr_str}"
+            else:
+                config["graphs"][graph_id] = f"{module_str}:{attr_str}"
 
 
 def _update_auth_path(
@@ -915,6 +964,66 @@ def _update_http_app_path(
         http_config["app"] = f"{module_str}:{attr_str}"
 
 
+def _get_node_pm_install_cmd(config_path: pathlib.Path, config: Config) -> str:
+    def test_file(file_name):
+        full_path = config_path.parent / file_name
+        try:
+            return full_path.is_file()
+        except OSError:
+            return False
+
+    # inspired by `package-manager-detector`
+    def get_pkg_manager_name():
+        try:
+            with open(config_path.parent / "package.json") as f:
+                pkg = json.load(f)
+
+                if (pkg_manager_name := pkg.get("packageManager")) and isinstance(
+                    pkg_manager_name, str
+                ):
+                    return pkg_manager_name.lstrip("^").split("@")[0]
+
+                if (
+                    dev_engine_name := (
+                        (pkg.get("devEngines") or {}).get("packageManager") or {}
+                    ).get("name")
+                ) and isinstance(dev_engine_name, str):
+                    return dev_engine_name
+
+                return None
+        except Exception:
+            return None
+
+    npm, yarn, pnpm, bun = [
+        test_file("package-lock.json"),
+        test_file("yarn.lock"),
+        test_file("pnpm-lock.yaml"),
+        test_file("bun.lockb"),
+    ]
+
+    if yarn:
+        install_cmd = "yarn install --frozen-lockfile"
+    elif pnpm:
+        install_cmd = "pnpm i --frozen-lockfile"
+    elif npm:
+        install_cmd = "npm ci"
+    elif bun:
+        install_cmd = "bun i"
+    else:
+        pkg_manager_name = get_pkg_manager_name()
+
+        if pkg_manager_name == "yarn":
+            install_cmd = "yarn install"
+        elif pkg_manager_name == "pnpm":
+            install_cmd = "pnpm i"
+        elif pkg_manager_name == "bun":
+            install_cmd = "bun i"
+        else:
+            install_cmd = "npm i"
+
+    return install_cmd
+
+
 def python_config_to_docker(
     config_path: pathlib.Path, config: Config, base_image: str
 ) -> tuple[str, dict[str, str]]:
@@ -995,10 +1104,17 @@ ADD {relpath} /deps/{name}
         for fullpath, (relpath, name) in local_deps.real_pkgs.items()
     )
 
+    install_node_str: str = (
+        "RUN /storage/install-node.sh"
+        if (config.get("ui") or config.get("node_version")) and local_deps.working_dir
+        else ""
+    )
+
     installs = f"{os.linesep}{os.linesep}".join(
         filter(
             None,
             [
+                install_node_str,
                 pip_config_file_str,
                 pip_pkgs_str,
                 pip_reqs_str,
@@ -1024,8 +1140,24 @@ ADD {relpath} /deps/{name}
             f"ENV LANGGRAPH_CHECKPOINTER='{json.dumps(checkpointer_config)}'"
         )
 
-    graphs = config["graphs"]
-    env_vars.append(f"ENV LANGSERVE_GRAPHS='{json.dumps(graphs)}'")
+    if (ui := config.get("ui")) is not None:
+        env_vars.append(f"ENV LANGGRAPH_UI='{json.dumps(ui)}'")
+
+    if (ui_config := config.get("ui_config")) is not None:
+        env_vars.append(f"ENV LANGGRAPH_UI_CONFIG='{json.dumps(ui_config)}'")
+
+    env_vars.append(f"ENV LANGSERVE_GRAPHS='{json.dumps(config['graphs'])}'")
+
+    js_inst_str: str = ""
+    if (config.get("ui") or config.get("node_version")) and local_deps.working_dir:
+        js_inst_str = os.linesep.join(
+            [
+                "# -- Installing JS dependencies --",
+                f"ENV NODE_VERSION={config.get('node_version') or DEFAULT_NODE_VERSION}",
+                f"RUN cd {local_deps.working_dir} && {_get_node_pm_install_cmd(config_path, config)} && tsx /api/langgraph_api/js/build.mts",
+                "# -- End of JS dependencies install --",
+            ]
+        )
 
     docker_file_contents = [
         f"FROM {base_image}:{config['python_version']}",
@@ -1039,6 +1171,10 @@ ADD {relpath} /deps/{name}
         "# -- End of local dependencies install --",
         os.linesep.join(env_vars),
         "",
+        js_inst_str,
+        "",
+        PIP_CLEANUP_LINES,  # Add pip cleanup after all installations are complete
+        "",
         f"WORKDIR {local_deps.working_dir}" if local_deps.working_dir else "",
     ]
 
@@ -1059,107 +1195,71 @@ def node_config_to_docker(
     config_path: pathlib.Path, config: Config, base_image: str
 ) -> tuple[str, dict[str, str]]:
     faux_path = f"/deps/{config_path.parent.name}"
+    install_cmd = _get_node_pm_install_cmd(config_path, config)
 
-    def test_file(file_name):
-        full_path = config_path.parent / file_name
-        try:
-            return full_path.is_file()
-        except OSError:
-            return False
+    env_vars: list[str] = []
 
-    # inspired by `package-manager-detector`
-    def get_pkg_manager_name():
-        try:
-            with open(config_path.parent / "package.json") as f:
-                pkg = json.load(f)
+    if (store_config := config.get("store")) is not None:
+        env_vars.append(f"ENV LANGGRAPH_STORE='{json.dumps(store_config)}'")
 
-                if (pkg_manager_name := pkg.get("packageManager")) and isinstance(
-                    pkg_manager_name, str
-                ):
-                    return pkg_manager_name.lstrip("^").split("@")[0]
+    if (auth_config := config.get("auth")) is not None:
+        env_vars.append(f"ENV LANGGRAPH_AUTH='{json.dumps(auth_config)}'")
 
-                if (
-                    dev_engine_name := (
-                        (pkg.get("devEngines") or {}).get("packageManager") or {}
-                    ).get("name")
-                ) and isinstance(dev_engine_name, str):
-                    return dev_engine_name
+    if (http_config := config.get("http")) is not None:
+        env_vars.append(f"ENV LANGGRAPH_HTTP='{json.dumps(http_config)}'")
 
-                return None
-        except Exception:
-            return None
+    if (checkpointer_config := config.get("checkpointer")) is not None:
+        env_vars.append(
+            f"ENV LANGGRAPH_CHECKPOINTER='{json.dumps(checkpointer_config)}'"
+        )
 
-    npm, yarn, pnpm, bun = [
-        test_file("package-lock.json"),
-        test_file("yarn.lock"),
-        test_file("pnpm-lock.yaml"),
-        test_file("bun.lockb"),
+    if ui := config.get("ui"):
+        env_vars.append(f"ENV LANGGRAPH_UI='{json.dumps(ui)}'")
+
+    if ui_config := config.get("ui_config"):
+        env_vars.append(f"ENV LANGGRAPH_UI_CONFIG='{json.dumps(ui_config)}'")
+
+    env_vars.append(f"ENV LANGSERVE_GRAPHS='{json.dumps(config['graphs'])}'")
+
+    docker_file_contents = [
+        f"FROM {base_image}:{config['node_version']}",
+        "",
+        os.linesep.join(config["dockerfile_lines"]),
+        "",
+        f"ADD . {faux_path}",
+        "",
+        f"RUN cd {faux_path} && {install_cmd}",
+        "",
+        os.linesep.join(env_vars),
+        "",
+        f"WORKDIR {faux_path}",
+        "",
+        'RUN (test ! -f /api/langgraph_api/js/build.mts && echo "Prebuild script not found, skipping") || tsx /api/langgraph_api/js/build.mts',
     ]
 
-    if yarn:
-        install_cmd = "yarn install --frozen-lockfile"
-    elif pnpm:
-        install_cmd = "pnpm i --frozen-lockfile"
-    elif npm:
-        install_cmd = "npm ci"
-    elif bun:
-        install_cmd = "bun i"
-    else:
-        pkg_manager_name = get_pkg_manager_name()
+    return os.linesep.join(docker_file_contents), {}
 
-        if pkg_manager_name == "yarn":
-            install_cmd = "yarn install"
-        elif pkg_manager_name == "pnpm":
-            install_cmd = "pnpm i"
-        elif pkg_manager_name == "bun":
-            install_cmd = "bun i"
-        else:
-            install_cmd = "npm i"
-    store_config = config.get("store")
-    env_additional_config = (
-        ""
-        if not store_config
-        else f"""
-ENV LANGGRAPH_STORE='{json.dumps(store_config)}'
-"""
-    )
-    if (auth_config := config.get("auth")) is not None:
-        env_additional_config += f"""
-ENV LANGGRAPH_AUTH='{json.dumps(auth_config)}'
-"""
-    if (http_config := config.get("http")) is not None:
-        env_additional_config += f"""
-ENV LANGGRAPH_HTTP='{json.dumps(http_config)}'
-"""
-    if (checkpointer_config := config.get("checkpointer")) is not None:
-        env_additional_config += f"""
-ENV LANGGRAPH_CHECKPOINTER='{json.dumps(checkpointer_config)}'
-"""
 
-    return (
-        f"""FROM {base_image}:{config['node_version']}
+def default_base_image(config: Config) -> str:
+    if config.get("node_version") and not config.get("python_version"):
+        return "langchain/langgraphjs-api"
+    return "langchain/langgraph-api"
 
-{os.linesep.join(config["dockerfile_lines"])}
 
-ADD . {faux_path}
+def docker_tag(config: Config, base_image: Optional[str] = None) -> str:
+    base_image = base_image or default_base_image(config)
 
-RUN cd {faux_path} && {install_cmd}
-{env_additional_config}
-ENV LANGSERVE_GRAPHS='{json.dumps(config["graphs"])}'
-{f"ENV LANGGRAPH_UI='{json.dumps(config['ui'])}'" if config.get("ui") else ""}
-{f"ENV LANGGRAPH_UI_CONFIG='{json.dumps(config['ui_config'])}'" if config.get("ui_config") else ""}
-
-WORKDIR {faux_path}
-
-RUN (test ! -f /api/langgraph_api/js/build.mts && echo "Prebuild script not found, skipping") || tsx /api/langgraph_api/js/build.mts""",
-        {},
-    )
+    if config.get("node_version") and not config.get("python_version"):
+        return f"{base_image}:{config['node_version']}"
+    return f"{base_image}:{config['python_version']}"
 
 
 def config_to_docker(
-    config_path: pathlib.Path, config: Config, base_image: str
+    config_path: pathlib.Path, config: Config, base_image: Optional[str] = None
 ) -> tuple[str, dict[str, str]]:
-    if config.get("node_version"):
+    base_image = base_image or default_base_image(config)
+
+    if config.get("node_version") and not config.get("python_version"):
         return node_config_to_docker(config_path, config, base_image)
 
     return python_config_to_docker(config_path, config, base_image)
@@ -1168,9 +1268,11 @@ def config_to_docker(
 def config_to_compose(
     config_path: pathlib.Path,
     config: Config,
-    base_image: str,
+    base_image: Optional[str] = None,
     watch: bool = False,
 ) -> str:
+    base_image = base_image or default_base_image(config)
+
     env_vars = config["env"].items() if isinstance(config["env"], dict) else {}
     env_vars_str = "\n".join(f'            {k}: "{v}"' for k, v in env_vars)
     env_file_str = (

libs/cli/langgraph_cli/progress.py

@@ -44,21 +44,30 @@ class Progress:
             sys.stdout.flush()
 
     def __enter__(self) -> Callable[[str], None]:
-        self.thread = threading.Thread(target=self.spinner_task)
-        self.thread.start()
+        if sys.stdout.isatty():
+            self.thread = threading.Thread(target=self.spinner_task)
+            self.thread.start()
 
-        def set_message(message):
-            self.message = message
-            if not message:
-                self.thread.join()
+            def set_message(message):
+                self.message = message
+                if not message:
+                    self.thread.join()
 
-        return set_message
+            return set_message
+        else:
+
+            def set_message(message):
+                sys.stderr.write(message + "\n")
+                sys.stderr.flush()
+
+            return set_message
 
     def __exit__(self, exception, value, tb):
-        self.message = ""
-        try:
-            self.thread.join()
-        finally:
-            del self.thread
-        if exception is not None:
-            return False
+        if sys.stdout.isatty():
+            self.message = ""
+            try:
+                self.thread.join()
+            finally:
+                del self.thread
+            if exception is not None:
+                return False

libs/cli/poetry.lock

@@ -20,7 +20,7 @@ description = "High level compatibility layer for multiple asynchronous event lo
 optional = true
 python-versions = ">=3.9"
 groups = ["main"]
-markers = "python_version >= \"3.11\" and extra == \"inmem\""
+markers = "python_version >= \"3.11\""
 files = [
     {file = "anyio-4.8.0-py3-none-any.whl", hash = "sha256:b5011f270ab5eb0abf13385f851315585cc37ef330dd88e27ec3d34d651fd47a"},
     {file = "anyio-4.8.0.tar.gz", hash = "sha256:1d9fe889df5212298c0c0723fa20479d1b94883a2df44bd3897aa91083316f7a"},
@@ -59,7 +59,7 @@ description = "Python package for providing Mozilla's CA Bundle."
 optional = true
 python-versions = ">=3.6"
 groups = ["main"]
-markers = "python_version >= \"3.11\" and extra == \"inmem\""
+markers = "python_version >= \"3.11\""
 files = [
     {file = "certifi-2025.1.31-py3-none-any.whl", hash = "sha256:ca78db4565a652026a4db2bcdf68f2fb589ea80d0be70e03929ed730746b84fe"},
     {file = "certifi-2025.1.31.tar.gz", hash = "sha256:3d5da6925056f6f18f119200434a4780a94263f10d1c21d032a6f6b2baa20651"},
@@ -405,7 +405,7 @@ description = "A pure-Python, bring-your-own-I/O implementation of HTTP/1.1"
 optional = true
 python-versions = ">=3.7"
 groups = ["main"]
-markers = "python_version >= \"3.11\" and extra == \"inmem\""
+markers = "python_version >= \"3.11\""
 files = [
     {file = "h11-0.14.0-py3-none-any.whl", hash = "sha256:e3fe4ac4b851c468cc8363d500db52c2ead036020723024a109d37346efaa761"},
     {file = "h11-0.14.0.tar.gz", hash = "sha256:8f19fbbe99e72420ff35c00b27a34cb9937e902a8b810e2c88300c6f0a3b699d"},
@@ -418,7 +418,7 @@ description = "A minimal low-level HTTP client."
 optional = true
 python-versions = ">=3.8"
 groups = ["main"]
-markers = "python_version >= \"3.11\" and extra == \"inmem\""
+markers = "python_version >= \"3.11\""
 files = [
     {file = "httpcore-1.0.7-py3-none-any.whl", hash = "sha256:a3fff8f43dc260d5bd363d9f9cf1830fa3a458b332856f34282de498ed420edd"},
     {file = "httpcore-1.0.7.tar.gz", hash = "sha256:8551cb62a169ec7162ac7be8d4817d561f60e08eaa485234898414bb5a8a0b4c"},
@@ -441,7 +441,7 @@ description = "The next generation HTTP client."
 optional = true
 python-versions = ">=3.8"
 groups = ["main"]
-markers = "python_version >= \"3.11\" and extra == \"inmem\""
+markers = "python_version >= \"3.11\""
 files = [
     {file = "httpx-0.28.1-py3-none-any.whl", hash = "sha256:d909fcccc110f8c7faf814ca82a9a4d816bc5a6dbfea25d6591d6985b8ba59ad"},
     {file = "httpx-0.28.1.tar.gz", hash = "sha256:75e98c5f16b0f35b567856f597f06ff2270a374470a5c2392242528e3e3e42fc"},
@@ -467,7 +467,7 @@ description = "Internationalized Domain Names in Applications (IDNA)"
 optional = true
 python-versions = ">=3.6"
 groups = ["main"]
-markers = "python_version >= \"3.11\" and extra == \"inmem\""
+markers = "python_version >= \"3.11\""
 files = [
     {file = "idna-3.10-py3-none-any.whl", hash = "sha256:946d195a0d259cbba61165e88e65941f16e9b36ea6ddb97f00452bae8b1287d3"},
     {file = "idna-3.10.tar.gz", hash = "sha256:12f65c9b470abda6dc35cf8e63cc574b1c52b11df2c86030af0ac09b01b13ea9"},
@@ -614,27 +614,27 @@ langgraph-sdk = ">=0.1.42,<0.2.0"
 
 [[package]]
 name = "langgraph-api"
-version = "0.0.42"
+version = "0.1.0"
 description = ""
 optional = true
 python-versions = "<4.0,>=3.11.0"
 groups = ["main"]
 markers = "python_version >= \"3.11\" and extra == \"inmem\""
 files = [
-    {file = "langgraph_api-0.0.42-py3-none-any.whl", hash = "sha256:19f69d9d39efde60a9bd3eeae6dc7dbe8d04b1b6fccf4ddf51d7e6b7187cc6ea"},
-    {file = "langgraph_api-0.0.42.tar.gz", hash = "sha256:a0a18545c73f9703d5d5907fc030e4a0acb79d1e6b79d4e38b3cac2bfb470e97"},
+    {file = "langgraph_api-0.1.0-py3-none-any.whl", hash = "sha256:93eb369849d5ea0dd6076f0a36fe0a9669415c46e95fcb28ccf30c73e13e5e01"},
+    {file = "langgraph_api-0.1.0.tar.gz", hash = "sha256:d02201d34172f3020af8f21c4560142b302474cee4a27f4335fbd950ab22f22f"},
 ]
 
 [package.dependencies]
 blockbuster = ">=1.5.24,<2.0.0"
 cloudpickle = ">=3.0.0,<4.0.0"
-cryptography = ">=43.0.3,<44.0.0"
+cryptography = ">=42.0.0,<45.0"
 httpx = ">=0.25.0"
 jsonschema-rs = ">=0.20.0,<0.30"
 langchain-core = ">=0.2.38,<0.4.0"
 langgraph = ">=0.2.56,<0.4.0"
 langgraph-checkpoint = ">=2.0.23,<3.0"
-langgraph-sdk = ">=0.1.59,<0.2.0"
+langgraph-sdk = ">=0.1.61,<0.2.0"
 langsmith = ">=0.1.63,<0.4.0"
 orjson = ">=3.9.7"
 pyjwt = ">=2.9.0,<3.0.0"
@@ -679,17 +679,30 @@ files = [
 langchain-core = ">=0.2.43,<0.3.0 || >0.3.0,<0.3.1 || >0.3.1,<0.3.2 || >0.3.2,<0.3.3 || >0.3.3,<0.3.4 || >0.3.4,<0.3.5 || >0.3.5,<0.3.6 || >0.3.6,<0.3.7 || >0.3.7,<0.3.8 || >0.3.8,<0.3.9 || >0.3.9,<0.3.10 || >0.3.10,<0.3.11 || >0.3.11,<0.3.12 || >0.3.12,<0.3.13 || >0.3.13,<0.3.14 || >0.3.14,<0.3.15 || >0.3.15,<0.3.16 || >0.3.16,<0.3.17 || >0.3.17,<0.3.18 || >0.3.18,<0.3.19 || >0.3.19,<0.3.20 || >0.3.20,<0.3.21 || >0.3.21,<0.3.22 || >0.3.22,<0.4.0"
 langgraph-checkpoint = ">=2.0.10,<3.0.0"
 
+[[package]]
+name = "langgraph-runtime-inmem"
+version = "0.0.1"
+description = "Inmem implementation for the LangGraph API server."
+optional = true
+python-versions = ">=3.11"
+groups = ["main"]
+markers = "python_version >= \"3.11\" and extra == \"inmem\""
+files = [
+    {file = "langgraph_runtime_inmem-0.0.1-py3-none-any.whl", hash = "sha256:a25ec8e3219f2fd60450de38412d24c83fbf0b2521c13871cc26ce9a68ead496"},
+    {file = "langgraph_runtime_inmem-0.0.1.tar.gz", hash = "sha256:144bf5217efec4969f7f9c5e8279d6914cc5133d4b1a19e466b4966fa05f00c5"},
+]
+
 [[package]]
 name = "langgraph-sdk"
-version = "0.1.60"
+version = "0.1.61"
 description = "SDK for interacting with LangGraph API"
 optional = true
 python-versions = "<4.0.0,>=3.9.0"
 groups = ["main"]
-markers = "python_version >= \"3.11\" and extra == \"inmem\""
+markers = "python_version >= \"3.11\""
 files = [
-    {file = "langgraph_sdk-0.1.60-py3-none-any.whl", hash = "sha256:953df85b0a6cc3a106f0496ce8f950a65d88b3ba8198c3b4bb58a54469b256a9"},
-    {file = "langgraph_sdk-0.1.60.tar.gz", hash = "sha256:7857a4a2a20a6a4c9934d1e7b5145eda92e3bc7286121813de2464d071050f88"},
+    {file = "langgraph_sdk-0.1.61-py3-none-any.whl", hash = "sha256:f2d774b12497c428862993090622d51e0dbc3f53e0cee3d74a13c7495d835cc6"},
+    {file = "langgraph_sdk-0.1.61.tar.gz", hash = "sha256:87dd1f07ab82da8875ac343268ece8bf5414632017ebc9d1cef4b523962fd601"},
 ]
 
 [package.dependencies]
@@ -851,7 +864,7 @@ description = "Fast, correct Python JSON library supporting dataclasses, datetim
 optional = true
 python-versions = ">=3.8"
 groups = ["main"]
-markers = "python_version >= \"3.11\" and extra == \"inmem\""
+markers = "python_version >= \"3.11\""
 files = [
     {file = "orjson-3.10.15-cp310-cp310-macosx_10_15_x86_64.macosx_11_0_arm64.macosx_10_15_universal2.whl", hash = "sha256:552c883d03ad185f720d0c09583ebde257e41b9521b74ff40e08b7dec4559c04"},
     {file = "orjson-3.10.15-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:616e3e8d438d02e4854f70bfdc03a6bcdb697358dbaa6bcd19cbe24d24ece1f8"},
@@ -1414,7 +1427,7 @@ description = "Sniff out which async library your code is running under"
 optional = true
 python-versions = ">=3.7"
 groups = ["main"]
-markers = "python_version >= \"3.11\" and extra == \"inmem\""
+markers = "python_version >= \"3.11\""
 files = [
     {file = "sniffio-1.3.1-py3-none-any.whl", hash = "sha256:2f6da418d1f1e0fddd844478f41680e794e6051915791a034ff65e5f100525a2"},
     {file = "sniffio-1.3.1.tar.gz", hash = "sha256:f4324edc670a0f49750a81b895f35c3adb843cca46f0530f79fc1babb23789dc"},
@@ -1550,7 +1563,7 @@ files = [
     {file = "typing_extensions-4.12.2-py3-none-any.whl", hash = "sha256:04e5ca0351e0f3f85c6853954072df659d0d13fac324d0072316b67d7794700d"},
     {file = "typing_extensions-4.12.2.tar.gz", hash = "sha256:1a7ead55c7e559dd4dee8856e3a88b41225abfe1ce8df57b7c13915fe121ffb8"},
 ]
-markers = {main = "python_version >= \"3.11\" and extra == \"inmem\""}
+markers = {main = "python_version >= \"3.11\" and (python_version < \"3.13\" or extra == \"inmem\")"}
 
 [[package]]
 name = "urllib3"
@@ -1834,9 +1847,9 @@ cffi = {version = ">=1.11", markers = "platform_python_implementation == \"PyPy\
 cffi = ["cffi (>=1.11)"]
 
 [extras]
-inmem = ["langgraph-api", "python-dotenv"]
+inmem = ["langgraph-api", "langgraph-runtime-inmem", "python-dotenv"]
 
 [metadata]
 lock-version = "2.1"
 python-versions = "^3.9.0,<4.0"
-content-hash = "4a45d739795019ae00e18ba8b0d366209deca9c5a5e65e9f387e5cf1d5aef187"
+content-hash = "afc2f8776b4b6144bd1197df49ba34089889e2a1110b8470d8f1b212e0b08380"

libs/cli/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langgraph-cli"
-version = "0.1.83"
+version = "0.2.4"
 description = "CLI for interacting with LangGraph API"
 authors = []
 license = "MIT"
@@ -14,7 +14,9 @@ langgraph = "langgraph_cli.cli:cli"
 [tool.poetry.dependencies]
 python = "^3.9.0,<4.0"
 click = "^8.1.7"
-langgraph-api = { version = ">=0.0.42,<0.1.0", optional = true, python = ">=3.11,<4.0" }
+langgraph-api = { version = ">=0.1.0,<0.2.0", optional = true, python = ">=3.11,<4.0" }
+langgraph-runtime-inmem = { version = ">=0.0.1,<0.1.0", optional = true, python = ">=3.11,<4.0" }
+langgraph-sdk = { version = ">=0.1.0,<0.2.0", optional = true, python = ">=3.11,<4.0" }
 python-dotenv = { version = ">=0.8.0", optional = true }
 
 [tool.poetry.group.dev.dependencies]
@@ -28,7 +30,7 @@ mypy = "^1.10.0"
 msgspec = "^0.19.0"
 
 [tool.poetry.extras]
-inmem = ["langgraph-api", "python-dotenv"]
+inmem = ["langgraph-api", "langgraph-runtime-inmem", "python-dotenv"]
 
 [tool.pytest.ini_options]
 # --strict-markers will raise errors on unknown marks.

libs/cli/tests/unit_tests/cli/test_cli.py

@@ -2,13 +2,14 @@ import json
 import pathlib
 import shutil
 import tempfile
+import textwrap
 from contextlib import contextmanager
 from pathlib import Path
 
 from click.testing import CliRunner
 
 from langgraph_cli.cli import cli, prepare_args_and_stdin
-from langgraph_cli.config import Config, validate_config
+from langgraph_cli.config import PIP_CLEANUP_LINES, Config, validate_config
 from langgraph_cli.docker import DEFAULT_POSTGRES_URI, DockerCapabilities, Version
 from langgraph_cli.util import clean_empty_lines
 
@@ -143,6 +144,7 @@ services:
                 RUN PYTHONDONTWRITEBYTECODE=1 pip install --no-cache-dir -c /api/constraints.txt -e /deps/*
                 # -- End of local dependencies install --
                 ENV LANGSERVE_GRAPHS='{{"agent": "agent.py:graph"}}'
+{textwrap.indent(textwrap.dedent(PIP_CLEANUP_LINES), "                ")}
                 WORKDIR /deps/cli
         
         develop:
@@ -176,8 +178,9 @@ def test_dockerfile_command_basic() -> None:
     """Test the 'dockerfile' command with basic configuration."""
     runner = CliRunner()
     config_content = {
-        "node_version": "20",  # Add any other necessary configuration fields
+        "python_version": "3.11",
         "graphs": {"agent": "agent.py:graph"},
+        "dependencies": ["."],
     }
 
     with temporary_config_folder(config_content) as temp_dir:
@@ -196,6 +199,50 @@ def test_dockerfile_command_basic() -> None:
         assert save_path.exists()
 
 
+def test_dockerfile_command_new_style_config() -> None:
+    """Test `dockerfile` command with a new style config.
+
+    This config format allows specifying agent data as a dictionary.
+    {
+        "graphs": {
+            "agent1": {
+                "path": ... # path to graph definition,
+                ... # other fields
+            }
+        }
+    }
+    """
+    runner = CliRunner()
+    config_content = {
+        "dependencies": ["./my_agent"],
+        "graphs": {
+            "agent": {
+                "path": "./my_agent/agent.py:graph",
+                "description": "This is a test agent",
+            }
+        },
+        "env": ".env",
+    }
+    with temporary_config_folder(config_content) as temp_dir:
+        save_path = temp_dir / "Dockerfile"
+        # Add agent.py file
+        agent_path = temp_dir / "my_agent" / "agent.py"
+        agent_path.parent.mkdir(parents=True, exist_ok=True)
+        agent_path.touch()
+
+        result = runner.invoke(
+            cli,
+            ["dockerfile", str(save_path), "--config", str(temp_dir / "config.json")],
+        )
+
+        # Assert command was successful
+        assert result.exit_code == 0, result.output
+        assert "✅ Created: Dockerfile" in result.output
+
+        # Check if Dockerfile was created
+        assert save_path.exists()
+
+
 def test_dockerfile_command_with_docker_compose() -> None:
     """Test the 'dockerfile' command with Docker Compose configuration."""
     runner = CliRunner()

libs/cli/tests/unit_tests/test_config.py

@@ -2,11 +2,13 @@ import json
 import os
 import pathlib
 import tempfile
+import textwrap
 
 import click
 import pytest
 
 from langgraph_cli.config import (
+    PIP_CLEANUP_LINES,
     config_to_compose,
     config_to_docker,
     validate_config,
@@ -25,8 +27,10 @@ def test_validate_config():
             "agent": "./agent.py:graph",
         },
     }
+    actual_config = validate_config(expected_config)
     expected_config = {
         "python_version": "3.11",
+        "node_version": None,
         "pip_config_file": None,
         "dockerfile_lines": [],
         "env": {},
@@ -38,13 +42,13 @@ def test_validate_config():
         "ui_config": None,
         **expected_config,
     }
-    actual_config = validate_config(expected_config)
     assert actual_config == expected_config
 
     # full config
     env = ".env"
     expected_config = {
         "python_version": "3.12",
+        "node_version": None,
         "pip_config_file": "pipconfig.txt",
         "dockerfile_lines": ["ARG meow"],
         "dependencies": [".", "langchain"],
@@ -67,16 +71,12 @@ def test_validate_config():
 
     # check wrong python version raises
     with pytest.raises(click.UsageError):
-        validate_config(
-            {
-                "python_version": "3.9",
-            }
-        )
+        validate_config({"python_version": "3.9"})
 
     # check missing dependencies key raises
     with pytest.raises(click.UsageError):
         validate_config(
-            {"python_version": "3.9", "graphs": {"agent": "./agent.py:graph"}},
+            {"python_version": "3.9", "graphs": {"agent": "./agent.py:graph"}}
         )
 
     # check missing graphs key raises
@@ -194,6 +194,58 @@ def test_validate_config_file():
             validate_config_file(config_path)
 
 
+def test_validate_config_multiplatform():
+    # default node
+    config = validate_config(
+        {"dependencies": ["."], "graphs": {"js": "./js.mts:graph"}}
+    )
+    assert config["node_version"] == "20"
+    assert config["python_version"] is None
+
+    # default multiplatform
+    config = validate_config(
+        {
+            "node_version": "22",
+            "python_version": "3.12",
+            "dependencies": ["."],
+            "graphs": {"python": "./python.py:graph", "js": "./js.mts:graph"},
+        }
+    )
+    assert config["node_version"] == "22"
+    assert config["python_version"] == "3.12"
+
+    # default multiplatform (full infer)
+    graphs = {"python": "./python.py:graph", "js": "./js.mts:graph"}
+    config = validate_config({"dependencies": ["."], "graphs": graphs})
+    assert config["node_version"] == "20"
+    assert config["python_version"] == "3.11"
+
+    # default multiplatform (partial node)
+    config = validate_config(
+        {"node_version": "22", "dependencies": ["."], "graphs": graphs}
+    )
+    assert config["node_version"] == "22"
+    assert config["python_version"] == "3.11"
+
+    # default multiplatform (partial python)
+    config = validate_config(
+        {"python_version": "3.12", "dependencies": ["."], "graphs": graphs}
+    )
+    assert config["node_version"] == "20"
+    assert config["python_version"] == "3.12"
+
+    # no known extension (assumes python)
+    config = validate_config(
+        {
+            "dependencies": ["./local", "./shared_utils"],
+            "graphs": {"agent": "local.workflow:graph"},
+            "env": ".env",
+        }
+    )
+    assert config["node_version"] is None
+    assert config["python_version"] == "3.11"
+
+
 # config_to_docker
 def test_config_to_docker_simple():
     graphs = {"agent": "./agent.py:graph"}
@@ -208,7 +260,7 @@ def test_config_to_docker_simple():
         ),
         "langchain/langgraph-api",
     )
-    expected_docker_stdin = """\
+    expected_docker_stdin = f"""\
 FROM langchain/langgraph-api:3.11
 # -- Installing local requirements --
 COPY --from=__outer_requirements.txt requirements.txt /deps/__outer_graphs_reqs_a/graphs_reqs_a/requirements.txt
@@ -242,8 +294,9 @@ RUN set -ex && \\
 # -- Installing all local dependencies --
 RUN PYTHONDONTWRITEBYTECODE=1 pip install --no-cache-dir -c /api/constraints.txt -e /deps/*
 # -- End of local dependencies install --
-ENV LANGGRAPH_HTTP='{"app": "/deps/examples/my_app.py:app"}'
-ENV LANGSERVE_GRAPHS='{"agent": "/deps/__outer_unit_tests/unit_tests/agent.py:graph"}'
+ENV LANGGRAPH_HTTP='{{"app": "/deps/examples/my_app.py:app"}}'
+ENV LANGSERVE_GRAPHS='{{"agent": "/deps/__outer_unit_tests/unit_tests/agent.py:graph"}}'
+{PIP_CLEANUP_LINES}
 WORKDIR /deps/__outer_unit_tests/unit_tests\
 """
     assert clean_empty_lines(actual_docker_stdin) == expected_docker_stdin
@@ -263,7 +316,8 @@ def test_config_to_docker_outside_path():
         validate_config({"dependencies": [".", ".."], "graphs": graphs}),
         "langchain/langgraph-api",
     )
-    expected_docker_stdin = """\
+    expected_docker_stdin = (
+        """\
 FROM langchain/langgraph-api:3.11
 # -- Adding non-package dependency unit_tests --
 ADD . /deps/__outer_unit_tests/unit_tests
@@ -291,8 +345,12 @@ RUN set -ex && \\
 RUN PYTHONDONTWRITEBYTECODE=1 pip install --no-cache-dir -c /api/constraints.txt -e /deps/*
 # -- End of local dependencies install --
 ENV LANGSERVE_GRAPHS='{"agent": "/deps/__outer_unit_tests/unit_tests/agent.py:graph"}'
+"""
+        + PIP_CLEANUP_LINES
+        + """
 WORKDIR /deps/__outer_unit_tests/unit_tests\
 """
+    )
     assert clean_empty_lines(actual_docker_stdin) == expected_docker_stdin
     assert additional_contexts == {
         "__outer_tests": str(pathlib.Path(__file__).parent.parent.absolute()),
@@ -312,7 +370,8 @@ def test_config_to_docker_pipconfig():
         ),
         "langchain/langgraph-api",
     )
-    expected_docker_stdin = """\
+    expected_docker_stdin = (
+        """\
 FROM langchain/langgraph-api:3.11
 ADD pipconfig.txt /pipconfig.txt
 # -- Adding non-package dependency unit_tests --
@@ -330,8 +389,12 @@ RUN set -ex && \\
 RUN PIP_CONFIG_FILE=/pipconfig.txt PYTHONDONTWRITEBYTECODE=1 pip install --no-cache-dir -c /api/constraints.txt -e /deps/*
 # -- End of local dependencies install --
 ENV LANGSERVE_GRAPHS='{"agent": "/deps/__outer_unit_tests/unit_tests/agent.py:graph"}'
+"""
+        + PIP_CLEANUP_LINES
+        + """
 WORKDIR /deps/__outer_unit_tests/unit_tests\
 """
+    )
     assert clean_empty_lines(actual_docker_stdin) == expected_docker_stdin
     assert additional_contexts == {}
 
@@ -368,7 +431,7 @@ def test_config_to_docker_local_deps():
         ),
         "langchain/langgraph-api-custom",
     )
-    expected_docker_stdin = """\
+    expected_docker_stdin = f"""\
 FROM langchain/langgraph-api-custom:3.11
 # -- Adding non-package dependency graphs --
 ADD ./graphs /deps/__outer_graphs/src
@@ -384,7 +447,8 @@ RUN set -ex && \\
 # -- Installing all local dependencies --
 RUN PYTHONDONTWRITEBYTECODE=1 pip install --no-cache-dir -c /api/constraints.txt -e /deps/*
 # -- End of local dependencies install --
-ENV LANGSERVE_GRAPHS='{"agent": "/deps/__outer_graphs/src/agent.py:graph"}'\
+ENV LANGSERVE_GRAPHS='{{"agent": "/deps/__outer_graphs/src/agent.py:graph"}}'
+{PIP_CLEANUP_LINES}\
 """
     assert clean_empty_lines(actual_docker_stdin) == expected_docker_stdin
     assert additional_contexts == {}
@@ -411,7 +475,8 @@ dependencies = ["langchain"]"""
         "langchain/langgraph-api",
     )
     os.remove(pyproject_path)
-    expected_docker_stdin = """FROM langchain/langgraph-api:3.11
+    expected_docker_stdin = (
+        """FROM langchain/langgraph-api:3.11
 # -- Adding local package . --
 ADD . /deps/unit_tests
 # -- End of local package . --
@@ -419,7 +484,12 @@ ADD . /deps/unit_tests
 RUN PYTHONDONTWRITEBYTECODE=1 pip install --no-cache-dir -c /api/constraints.txt -e /deps/*
 # -- End of local dependencies install --
 ENV LANGSERVE_GRAPHS='{"agent": "/deps/unit_tests/graphs/agent.py:graph"}'
-WORKDIR /deps/unit_tests"""
+"""
+        + PIP_CLEANUP_LINES
+        + "\n"
+        + "WORKDIR /deps/unit_tests"
+        ""
+    )
     assert clean_empty_lines(actual_docker_stdin) == expected_docker_stdin
     assert additional_contexts == {}
 
@@ -439,7 +509,7 @@ def test_config_to_docker_end_to_end():
         ),
         "langchain/langgraph-api",
     )
-    expected_docker_stdin = """FROM langchain/langgraph-api:3.12
+    expected_docker_stdin = f"""FROM langchain/langgraph-api:3.12
 ARG meow
 ARG foo
 ADD pipconfig.txt /pipconfig.txt
@@ -458,7 +528,8 @@ RUN set -ex && \\
 # -- Installing all local dependencies --
 RUN PIP_CONFIG_FILE=/pipconfig.txt PYTHONDONTWRITEBYTECODE=1 pip install --no-cache-dir -c /api/constraints.txt -e /deps/*
 # -- End of local dependencies install --
-ENV LANGSERVE_GRAPHS='{"agent": "/deps/__outer_graphs/src/agent.py:graph"}'"""
+ENV LANGSERVE_GRAPHS='{{"agent": "/deps/__outer_graphs/src/agent.py:graph"}}'
+{PIP_CLEANUP_LINES}"""
     assert clean_empty_lines(actual_docker_stdin) == expected_docker_stdin
     assert additional_contexts == {}
 
@@ -473,6 +544,7 @@ def test_config_to_docker_nodejs():
                 "node_version": "20",
                 "graphs": graphs,
                 "dockerfile_lines": ["ARG meow", "ARG foo"],
+                "auth": {"path": "./graphs/auth.mts:auth"},
                 "ui": {"agent": "./graphs/agent.ui.jsx"},
                 "ui_config": {"shared": ["nuqs"]},
             }
@@ -484,9 +556,10 @@ ARG meow
 ARG foo
 ADD . /deps/unit_tests
 RUN cd /deps/unit_tests && npm i
-ENV LANGSERVE_GRAPHS='{"agent": "./graphs/agent.js:graph"}'
+ENV LANGGRAPH_AUTH='{"path": "./graphs/auth.mts:auth"}'
 ENV LANGGRAPH_UI='{"agent": "./graphs/agent.ui.jsx"}'
 ENV LANGGRAPH_UI_CONFIG='{"shared": ["nuqs"]}'
+ENV LANGSERVE_GRAPHS='{"agent": "./graphs/agent.js:graph"}'
 WORKDIR /deps/unit_tests
 RUN (test ! -f /api/langgraph_api/js/build.mts && echo "Prebuild script not found, skipping") || tsx /api/langgraph_api/js/build.mts"""
 
@@ -494,11 +567,97 @@ RUN (test ! -f /api/langgraph_api/js/build.mts && echo "Prebuild script not foun
     assert additional_contexts == {}
 
 
+def test_config_to_docker_gen_ui_python():
+    graphs = {"agent": "./agent.py:graph"}
+    actual_docker_stdin, additional_contexts = config_to_docker(
+        PATH_TO_CONFIG,
+        validate_config(
+            {
+                "dependencies": ["."],
+                "graphs": graphs,
+                "ui": {"agent": "./graphs/agent.ui.jsx"},
+                "ui_config": {"shared": ["nuqs"]},
+            }
+        ),
+        "langchain/langgraph-api",
+    )
+
+    expected_docker_stdin = f"""FROM langchain/langgraph-api:3.11
+RUN /storage/install-node.sh
+# -- Adding non-package dependency unit_tests --
+ADD . /deps/__outer_unit_tests/unit_tests
+RUN set -ex && \\
+    for line in '[project]' \\
+                'name = "unit_tests"' \\
+                'version = "0.1"' \\
+                '[tool.setuptools.package-data]' \\
+                '"*" = ["**/*"]'; do \\
+        echo "$line" >> /deps/__outer_unit_tests/pyproject.toml; \\
+    done
+# -- End of non-package dependency unit_tests --
+# -- Installing all local dependencies --
+RUN PYTHONDONTWRITEBYTECODE=1 pip install --no-cache-dir -c /api/constraints.txt -e /deps/*
+# -- End of local dependencies install --
+ENV LANGGRAPH_UI='{{"agent": "./graphs/agent.ui.jsx"}}'
+ENV LANGGRAPH_UI_CONFIG='{{"shared": ["nuqs"]}}'
+ENV LANGSERVE_GRAPHS='{{"agent": "/deps/__outer_unit_tests/unit_tests/agent.py:graph"}}'
+# -- Installing JS dependencies --
+ENV NODE_VERSION=20
+RUN cd /deps/__outer_unit_tests/unit_tests && npm i && tsx /api/langgraph_api/js/build.mts
+# -- End of JS dependencies install --
+{PIP_CLEANUP_LINES}
+WORKDIR /deps/__outer_unit_tests/unit_tests"""
+
+    assert clean_empty_lines(actual_docker_stdin) == expected_docker_stdin
+    assert additional_contexts == {}
+
+
+def test_config_to_docker_multiplatform():
+    graphs = {
+        "python": "./multiplatform/python.py:graph",
+        "js": "./multiplatform/js.mts:graph",
+    }
+    actual_docker_stdin, additional_contexts = config_to_docker(
+        PATH_TO_CONFIG,
+        validate_config(
+            {"node_version": "22", "dependencies": ["."], "graphs": graphs}
+        ),
+        "langchain/langgraph-api",
+    )
+
+    expected_docker_stdin = f"""FROM langchain/langgraph-api:3.11
+RUN /storage/install-node.sh
+# -- Adding non-package dependency unit_tests --
+ADD . /deps/__outer_unit_tests/unit_tests
+RUN set -ex && \\
+    for line in '[project]' \\
+                'name = "unit_tests"' \\
+                'version = "0.1"' \\
+                '[tool.setuptools.package-data]' \\
+                '"*" = ["**/*"]'; do \\
+        echo "$line" >> /deps/__outer_unit_tests/pyproject.toml; \\
+    done
+# -- End of non-package dependency unit_tests --
+# -- Installing all local dependencies --
+RUN PYTHONDONTWRITEBYTECODE=1 pip install --no-cache-dir -c /api/constraints.txt -e /deps/*
+# -- End of local dependencies install --
+ENV LANGSERVE_GRAPHS='{{"python": "/deps/__outer_unit_tests/unit_tests/multiplatform/python.py:graph", "js": "/deps/__outer_unit_tests/unit_tests/multiplatform/js.mts:graph"}}'
+# -- Installing JS dependencies --
+ENV NODE_VERSION=22
+RUN cd /deps/__outer_unit_tests/unit_tests && npm i && tsx /api/langgraph_api/js/build.mts
+# -- End of JS dependencies install --
+{PIP_CLEANUP_LINES}
+WORKDIR /deps/__outer_unit_tests/unit_tests"""
+
+    assert clean_empty_lines(actual_docker_stdin) == expected_docker_stdin
+    assert additional_contexts == {}
+
+
 # config_to_compose
 def test_config_to_compose_simple_config():
     graphs = {"agent": "./agent.py:graph"}
-    expected_compose_stdin = """\
-        
+    # Create a properly indented version of PIP_CLEANUP_LINES for compose files
+    expected_compose_stdin = f"""
         pull_policy: build
         build:
             context: .
@@ -518,7 +677,8 @@ def test_config_to_compose_simple_config():
                 # -- Installing all local dependencies --
                 RUN PYTHONDONTWRITEBYTECODE=1 pip install --no-cache-dir -c /api/constraints.txt -e /deps/*
                 # -- End of local dependencies install --
-                ENV LANGSERVE_GRAPHS='{"agent": "/deps/__outer_unit_tests/unit_tests/agent.py:graph"}'
+                ENV LANGSERVE_GRAPHS='{{"agent": "/deps/__outer_unit_tests/unit_tests/agent.py:graph"}}'
+{textwrap.indent(textwrap.dedent(PIP_CLEANUP_LINES), "                ")}
                 WORKDIR /deps/__outer_unit_tests/unit_tests
         """
     actual_compose_stdin = config_to_compose(
@@ -526,12 +686,15 @@ def test_config_to_compose_simple_config():
         validate_config({"dependencies": ["."], "graphs": graphs}),
         "langchain/langgraph-api",
     )
-    assert clean_empty_lines(actual_compose_stdin) == expected_compose_stdin
+    assert (
+        clean_empty_lines(actual_compose_stdin).strip()
+        == expected_compose_stdin.strip()
+    )
 
 
 def test_config_to_compose_env_vars():
     graphs = {"agent": "./agent.py:graph"}
-    expected_compose_stdin = """                        OPENAI_API_KEY: "key"
+    expected_compose_stdin = f"""                        OPENAI_API_KEY: "key"
         
         pull_policy: build
         build:
@@ -552,7 +715,8 @@ def test_config_to_compose_env_vars():
                 # -- Installing all local dependencies --
                 RUN PYTHONDONTWRITEBYTECODE=1 pip install --no-cache-dir -c /api/constraints.txt -e /deps/*
                 # -- End of local dependencies install --
-                ENV LANGSERVE_GRAPHS='{"agent": "/deps/__outer_unit_tests/unit_tests/agent.py:graph"}'
+                ENV LANGSERVE_GRAPHS='{{"agent": "/deps/__outer_unit_tests/unit_tests/agent.py:graph"}}'
+{textwrap.indent(textwrap.dedent(PIP_CLEANUP_LINES), "                ")}
                 WORKDIR /deps/__outer_unit_tests/unit_tests
         """
     openai_api_key = "key"
@@ -572,7 +736,7 @@ def test_config_to_compose_env_vars():
 
 def test_config_to_compose_env_file():
     graphs = {"agent": "./agent.py:graph"}
-    expected_compose_stdin = """\
+    expected_compose_stdin = f"""\
         env_file: .env
         pull_policy: build
         build:
@@ -593,7 +757,8 @@ def test_config_to_compose_env_file():
                 # -- Installing all local dependencies --
                 RUN PYTHONDONTWRITEBYTECODE=1 pip install --no-cache-dir -c /api/constraints.txt -e /deps/*
                 # -- End of local dependencies install --
-                ENV LANGSERVE_GRAPHS='{"agent": "/deps/__outer_unit_tests/unit_tests/agent.py:graph"}'
+                ENV LANGSERVE_GRAPHS='{{"agent": "/deps/__outer_unit_tests/unit_tests/agent.py:graph"}}'
+{textwrap.indent(textwrap.dedent(PIP_CLEANUP_LINES), "                ")}
                 WORKDIR /deps/__outer_unit_tests/unit_tests
         """
     actual_compose_stdin = config_to_compose(
@@ -606,7 +771,7 @@ def test_config_to_compose_env_file():
 
 def test_config_to_compose_watch():
     graphs = {"agent": "./agent.py:graph"}
-    expected_compose_stdin = """\
+    expected_compose_stdin = f"""\
         
         pull_policy: build
         build:
@@ -627,7 +792,8 @@ def test_config_to_compose_watch():
                 # -- Installing all local dependencies --
                 RUN PYTHONDONTWRITEBYTECODE=1 pip install --no-cache-dir -c /api/constraints.txt -e /deps/*
                 # -- End of local dependencies install --
-                ENV LANGSERVE_GRAPHS='{"agent": "/deps/__outer_unit_tests/unit_tests/agent.py:graph"}'
+                ENV LANGSERVE_GRAPHS='{{"agent": "/deps/__outer_unit_tests/unit_tests/agent.py:graph"}}'
+{textwrap.indent(textwrap.dedent(PIP_CLEANUP_LINES), "                ")}
                 WORKDIR /deps/__outer_unit_tests/unit_tests
         
         develop:
@@ -649,7 +815,7 @@ def test_config_to_compose_watch():
 def test_config_to_compose_end_to_end():
     # test all of the above + langgraph API path
     graphs = {"agent": "./agent.py:graph"}
-    expected_compose_stdin = """\
+    expected_compose_stdin = f"""\
         env_file: .env
         pull_policy: build
         build:
@@ -670,7 +836,8 @@ def test_config_to_compose_end_to_end():
                 # -- Installing all local dependencies --
                 RUN PYTHONDONTWRITEBYTECODE=1 pip install --no-cache-dir -c /api/constraints.txt -e /deps/*
                 # -- End of local dependencies install --
-                ENV LANGSERVE_GRAPHS='{"agent": "/deps/__outer_unit_tests/unit_tests/agent.py:graph"}'
+                ENV LANGSERVE_GRAPHS='{{"agent": "/deps/__outer_unit_tests/unit_tests/agent.py:graph"}}'
+{textwrap.indent(textwrap.dedent(PIP_CLEANUP_LINES), "                ")}
                 WORKDIR /deps/__outer_unit_tests/unit_tests
         
         develop:

libs/langgraph/README.md

@@ -40,6 +40,9 @@ agent.invoke(
 )
 ```
 
+> [!TIP]
+> Check out [this guide](https://langchain-ai.github.io/langgraph/tutorials/workflows/) that walks through implementing common patterns (workflows and agents) in LangGraph. 
+
 ## Why use LangGraph?
 
 LangGraph is built for developers who want to build powerful, adaptable AI agents. Developers choose LangGraph for:

libs/langgraph/bench/__main__.py

@@ -9,6 +9,7 @@ from bench.fanout_to_subgraph import fanout_to_subgraph, fanout_to_subgraph_sync
 from bench.pydantic_state import pydantic_state
 from bench.react_agent import react_agent
 from bench.sequential import create_sequential
+from bench.wide_dict import wide_dict
 from bench.wide_state import wide_state
 from langgraph.checkpoint.memory import MemorySaver
 from langgraph.graph import StateGraph
@@ -25,6 +26,7 @@ async def arun(graph: Pregel, input: dict):
                     "configurable": {"thread_id": str(uuid4())},
                     "recursion_limit": 1000000000,
                 },
+                checkpoint_during=False,
             )
         ]
     )
@@ -41,6 +43,7 @@ async def arun_first_event_latency(graph: Pregel, input: dict) -> None:
             "configurable": {"thread_id": str(uuid4())},
             "recursion_limit": 1000000000,
         },
+        checkpoint_during=False,
     )
 
     try:
@@ -60,6 +63,7 @@ def run(graph: Pregel, input: dict):
                     "configurable": {"thread_id": str(uuid4())},
                     "recursion_limit": 1000000000,
                 },
+                checkpoint_during=False,
             )
         ]
     )
@@ -76,6 +80,7 @@ def run_first_event_latency(graph: Pregel, input: dict) -> None:
             "configurable": {"thread_id": str(uuid4())},
             "recursion_limit": 1000000000,
         },
+        checkpoint_during=False,
     )
 
     try:
@@ -251,6 +256,102 @@ benchmarks = (
             ]
         },
     ),
+    (
+        "wide_dict_25x300",
+        wide_dict(300).compile(checkpointer=None),
+        wide_dict(300).compile(checkpointer=None),
+        {
+            "messages": [
+                {
+                    str(i) * 10: {
+                        str(j) * 10: ["hi?" * 10, True, 1, 6327816386138, None] * 5
+                        for j in range(5)
+                    }
+                    for i in range(5)
+                }
+            ]
+        },
+    ),
+    (
+        "wide_dict_25x300_checkpoint",
+        wide_dict(300).compile(checkpointer=MemorySaver()),
+        wide_dict(300).compile(checkpointer=MemorySaver()),
+        {
+            "messages": [
+                {
+                    str(i) * 10: {
+                        str(j) * 10: ["hi?" * 10, True, 1, 6327816386138, None] * 5
+                        for j in range(5)
+                    }
+                    for i in range(5)
+                }
+            ]
+        },
+    ),
+    (
+        "wide_dict_15x600",
+        wide_dict(600).compile(checkpointer=None),
+        wide_dict(600).compile(checkpointer=None),
+        {
+            "messages": [
+                {
+                    str(i) * 10: {
+                        str(j) * 10: ["hi?" * 10, True, 1, 6327816386138, None] * 5
+                        for j in range(5)
+                    }
+                    for i in range(3)
+                }
+            ]
+        },
+    ),
+    (
+        "wide_dict_15x600_checkpoint",
+        wide_dict(600).compile(checkpointer=MemorySaver()),
+        wide_dict(600).compile(checkpointer=MemorySaver()),
+        {
+            "messages": [
+                {
+                    str(i) * 10: {
+                        str(j) * 10: ["hi?" * 10, True, 1, 6327816386138, None] * 5
+                        for j in range(5)
+                    }
+                    for i in range(3)
+                }
+            ]
+        },
+    ),
+    (
+        "wide_dict_9x1200",
+        wide_dict(1200).compile(checkpointer=None),
+        wide_dict(1200).compile(checkpointer=None),
+        {
+            "messages": [
+                {
+                    str(i) * 10: {
+                        str(j) * 10: ["hi?" * 10, True, 1, 6327816386138, None] * 5
+                        for j in range(3)
+                    }
+                    for i in range(3)
+                }
+            ]
+        },
+    ),
+    (
+        "wide_dict_9x1200_checkpoint",
+        wide_dict(1200).compile(checkpointer=MemorySaver()),
+        wide_dict(1200).compile(checkpointer=MemorySaver()),
+        {
+            "messages": [
+                {
+                    str(i) * 10: {
+                        str(j) * 10: ["hi?" * 10, True, 1, 6327816386138, None] * 5
+                        for j in range(3)
+                    }
+                    for i in range(3)
+                }
+            ]
+        },
+    ),
     (
         "sequential_10",
         create_sequential(10).compile(),

libs/langgraph/bench/fanout_to_subgraph.py

@@ -106,6 +106,7 @@ def fanout_to_subgraph_sync() -> StateGraph:
 if __name__ == "__main__":
     import asyncio
     import random
+    import time
 
     import uvloop
 
@@ -123,4 +124,7 @@ if __name__ == "__main__":
         len([c async for c in graph.astream(input, config=config)])
 
     uvloop.install()
+    start = time.time()
     asyncio.run(run())
+    end = time.time()
+    print(f"Time taken: {end - start:.4f} seconds")

libs/langgraph/bench/wide_dict.py

@@ -0,0 +1,153 @@
+import operator
+from functools import partial
+from random import choice
+from typing import Annotated, Optional, Sequence
+
+from typing_extensions import TypedDict
+
+from langgraph.constants import END, START
+from langgraph.graph.state import StateGraph
+
+
+def wide_dict(n: int) -> StateGraph:
+    class State(TypedDict):
+        messages: Annotated[list, operator.add]
+        trigger_events: Annotated[list, operator.add]
+        """The external events that are converted by the graph."""
+        primary_issue_medium: Annotated[str, lambda x, y: y or x]
+        autoresponse: Annotated[Optional[dict], lambda _, y: y]  # Always overwrite
+        issue: Annotated[dict | None, lambda x, y: y if y else x]
+        relevant_rules: Optional[list[dict]]
+        """SOPs fetched from the rulebook that are relevant to the current conversation."""
+        memory_docs: Optional[list[dict]]
+        """Memory docs fetched from the memory service that are relevant to the current conversation."""
+        categorizations: Annotated[list[dict], operator.add]
+        """The issue categorizations auto-generated by the AI."""
+        responses: Annotated[list[dict], operator.add]
+        """The draft responses recommended by the AI."""
+
+        user_info: Annotated[Optional[dict], lambda x, y: y if y is not None else x]
+        """The current user state (by email)."""
+        crm_info: Annotated[Optional[dict], lambda x, y: y if y is not None else x]
+        """The CRM information for organization the current user is from."""
+        email_thread_id: Annotated[
+            Optional[str], lambda x, y: y if y is not None else x
+        ]
+        """The current email thread ID."""
+        slack_participants: Annotated[dict, operator.or_]
+        """The growing list of current slack participants."""
+        bot_id: Optional[str]
+        """The ID of the bot user in the slack channel."""
+        notified_assignees: Annotated[dict, operator.or_]
+
+    list_fields = {
+        "messages",
+        "trigger_events",
+        "categorizations",
+        "responses",
+        "memory_docs",
+        "relevant_rules",
+    }
+    dict_fields = {
+        "user_info",
+        "crm_info",
+        "slack_participants",
+        "notified_assignees",
+        "autoresponse",
+        "issue",
+    }
+
+    def read_write(read: str, write: Sequence[str], input: State) -> dict:
+        val = input.get(read)
+        val = {val: val} if isinstance(val, str) else val
+        val_single = val[-1] if isinstance(val, list) else val
+        val_list = val if isinstance(val, list) else [val]
+        return {
+            k: val_list
+            if k in list_fields
+            else val_single
+            if k in dict_fields
+            else "".join(choice("abcdefghijklmnopqrstuvwxyz") for _ in range(n))
+            for k in write
+        }
+
+    builder = StateGraph(State)
+    builder.add_edge(START, "one")
+    builder.add_node(
+        "one",
+        partial(read_write, "messages", ["trigger_events", "primary_issue_medium"]),
+    )
+    builder.add_edge("one", "two")
+    builder.add_node(
+        "two",
+        partial(read_write, "trigger_events", ["autoresponse", "issue"]),
+    )
+    builder.add_edge("two", "three")
+    builder.add_edge("two", "four")
+    builder.add_node(
+        "three",
+        partial(read_write, "autoresponse", ["relevant_rules"]),
+    )
+    builder.add_node(
+        "four",
+        partial(
+            read_write,
+            "trigger_events",
+            ["categorizations", "responses", "memory_docs"],
+        ),
+    )
+    builder.add_node(
+        "five",
+        partial(
+            read_write,
+            "categorizations",
+            [
+                "user_info",
+                "crm_info",
+                "email_thread_id",
+                "slack_participants",
+                "bot_id",
+                "notified_assignees",
+            ],
+        ),
+    )
+    builder.add_edge(["three", "four"], "five")
+    builder.add_edge("five", "six")
+    builder.add_node(
+        "six",
+        partial(read_write, "responses", ["messages"]),
+    )
+    builder.add_conditional_edges(
+        "six", lambda state: END if len(state["messages"]) > n else "one"
+    )
+
+    return builder
+
+
+if __name__ == "__main__":
+    import asyncio
+
+    import uvloop
+
+    from langgraph.checkpoint.memory import MemorySaver
+
+    graph = wide_dict(1000).compile(checkpointer=MemorySaver())
+    input = {
+        "messages": [
+            {
+                str(i) * 10: {
+                    str(j) * 10: ["hi?" * 10, True, 1, 6327816386138, None] * 5
+                    for j in range(50)
+                }
+                for i in range(50)
+            }
+        ]
+    }
+    config = {"configurable": {"thread_id": "1"}, "recursion_limit": 20000000000}
+
+    async def run():
+        async for c in graph.astream(input, config=config):
+            print(c.keys())
+
+    uvloop.install()
+    asyncio.run(run())

libs/langgraph/bench/wide_state.py

@@ -1,6 +1,7 @@
 import operator
 from dataclasses import dataclass, field
 from functools import partial
+from random import choice
 from typing import Annotated, Optional, Sequence
 
 from langgraph.constants import END, START
@@ -49,12 +50,34 @@ def wide_state(n: int) -> StateGraph:
         """The ID of the bot user in the slack channel."""
         notified_assignees: Annotated[dict, operator.or_] = field(default_factory=dict)
 
+    list_fields = {
+        "messages",
+        "trigger_events",
+        "categorizations",
+        "responses",
+        "memory_docs",
+        "relevant_rules",
+    }
+    dict_fields = {
+        "user_info",
+        "crm_info",
+        "slack_participants",
+        "notified_assignees",
+        "autoresponse",
+        "issue",
+    }
+
     def read_write(read: str, write: Sequence[str], input: State) -> dict:
         val = getattr(input, read)
+        val = {val: val} if isinstance(val, str) else val
         val_single = val[-1] if isinstance(val, list) else val
         val_list = val if isinstance(val, list) else [val]
         return {
-            k: val_list if isinstance(getattr(input, k), list) else val_single
+            k: val_list
+            if k in list_fields
+            else val_single
+            if k in dict_fields
+            else "".join(choice("abcdefghijklmnopqrstuvwxyz") for _ in range(n))
             for k in write
         }
 

libs/langgraph/langgraph/constants.py

@@ -69,6 +69,8 @@ CONFIG_KEY_ENSURE_LATEST = sys.intern("__pregel_ensure_latest")
 # (for distributed mode)
 CONFIG_KEY_DELEGATE = sys.intern("__pregel_delegate")
 # holds a boolean indicating whether to delegate subgraphs (for distributed mode)
+CONFIG_KEY_THREAD_ID = sys.intern("thread_id")
+# holds the thread ID for the current invocation
 CONFIG_KEY_CHECKPOINT_MAP = sys.intern("checkpoint_map")
 # holds a mapping of checkpoint_ns -> checkpoint_id for parent graphs
 CONFIG_KEY_CHECKPOINT_ID = sys.intern("checkpoint_id")
@@ -83,6 +85,8 @@ CONFIG_KEY_PREVIOUS = sys.intern("__pregel_previous")
 # holds the previous return value from a stateful Pregel graph.
 CONFIG_KEY_RUNNER_SUBMIT = sys.intern("__pregel_runner_submit")
 # holds a function that receives tasks from runner, executes them and returns results
+CONFIG_KEY_CHECKPOINT_DURING = sys.intern("__pregel_checkpoint_during")
+# holds a boolean indicating whether to checkpoint during the run (or only at the end)
 
 # --- Other constants ---
 PUSH = sys.intern("__pregel_push")

libs/langgraph/langgraph/func/__init__.py

@@ -9,6 +9,7 @@ from typing import (
     Callable,
     Generic,
     Optional,
+    Sequence,
     TypeVar,
     Union,
     get_args,
@@ -19,7 +20,7 @@ from typing import (
 from langgraph.channels.ephemeral_value import EphemeralValue
 from langgraph.channels.last_value import LastValue
 from langgraph.checkpoint.base import BaseCheckpointSaver
-from langgraph.constants import END, PREVIOUS, START, TAG_HIDDEN
+from langgraph.constants import END, PREVIOUS, START
 from langgraph.pregel import Pregel
 from langgraph.pregel.call import (
     P,
@@ -38,7 +39,7 @@ from langgraph.types import _DC_KWARGS, RetryPolicy, StreamMode
 def task(
     *,
     name: Optional[str] = None,
-    retry: Optional[RetryPolicy] = None,
+    retry: Optional[Union[RetryPolicy, Sequence[RetryPolicy]]] = None,
 ) -> Callable[
     [Union[Callable[P, Awaitable[T]], Callable[P, T]]],
     Callable[P, SyncAsyncFuture[T]],
@@ -55,7 +56,7 @@ def task(
     __func_or_none__: Optional[Union[Callable[P, Awaitable[T]], Callable[P, T]]] = None,
     *,
     name: Optional[str] = None,
-    retry: Optional[RetryPolicy] = None,
+    retry: Optional[Union[RetryPolicy, Sequence[RetryPolicy]]] = None,
 ) -> Union[
     Callable[
         [Union[Callable[P, Awaitable[T]], Callable[P, T]]],
@@ -119,6 +120,10 @@ def task(
         await add_one.ainvoke([1, 2, 3])  # Returns [2, 3, 4]
         ```
     """
+    if isinstance(retry, RetryPolicy):
+        retry_policies: Optional[Sequence[RetryPolicy]] = (retry,)
+    else:
+        retry_policies = retry
 
     def decorator(
         func: Union[Callable[P, Awaitable[T]], Callable[P, T]],
@@ -137,7 +142,7 @@ def task(
                 # handle regular functions / partials / callable classes, etc.
                 func.__name__ = name
 
-        call_func = functools.partial(call, func, retry=retry)
+        call_func = functools.partial(call, func, retry=retry_policies)
         object.__setattr__(call_func, "_is_pregel_task", True)
         return functools.update_wrapper(call_func, func)
 
@@ -429,8 +434,7 @@ class entrypoint:
                             [
                                 ChannelWriteEntry(END, mapper=_pluck_return_value),
                                 ChannelWriteEntry(PREVIOUS, mapper=_pluck_save_value),
-                            ],
-                            tags=[TAG_HIDDEN],
+                            ]
                         )
                     ],
                 )

libs/langgraph/langgraph/graph/branch.py

@@ -1,4 +1,3 @@
-import asyncio
 from inspect import (
     isfunction,
     ismethod,
@@ -178,7 +177,7 @@ class Branch(NamedTuple):
         ],
     ) -> Runnable:
         if reader:
-            value = await asyncio.to_thread(reader, config)
+            value = reader(config)
             # passthrough additional keys from node to branch
             # only doable when using dict states
             if (

libs/langgraph/langgraph/graph/graph.py

@@ -366,16 +366,14 @@ class CompiledGraph(Pregel):
         self.nodes[key] = (
             PregelNode(channels=[], triggers=[], metadata=node.metadata)
             | node.runnable
-            | ChannelWrite([ChannelWriteEntry(key)], tags=[TAG_HIDDEN])
+            | ChannelWrite([ChannelWriteEntry(key)])
         )
         cast(list[str], self.stream_channels).append(key)
 
     def attach_edge(self, start: str, end: str) -> None:
         if end == END:
             # publish to end channel
-            self.nodes[start].writers.append(
-                ChannelWrite([ChannelWriteEntry(END)], tags=[TAG_HIDDEN])
-            )
+            self.nodes[start].writers.append(ChannelWrite([ChannelWriteEntry(END)]))
         else:
             # subscribe to start channel
             self.nodes[end].triggers.append(start)
@@ -393,10 +391,7 @@ class CompiledGraph(Pregel):
                 )
                 for p in packets
             ]
-            return ChannelWrite(
-                cast(Sequence[Union[ChannelWriteEntry, Send]], writes),
-                tags=[TAG_HIDDEN],
-            )
+            return ChannelWrite(cast(Sequence[Union[ChannelWriteEntry, Send]], writes))
 
         # add hidden start node
         if start == START and start not in self.nodes:

libs/langgraph/langgraph/graph/schema_utils.py

@@ -1,3 +1,4 @@
+import functools
 import logging
 import weakref
 from inspect import isclass
@@ -16,6 +17,8 @@ from pydantic import BaseModel
 from pydantic.v1 import BaseModel as BaseModelV1
 from typing_extensions import Annotated
 
+__all__ = ["SchemaCoercionMapper"]
+
 logger = logging.getLogger(__name__)
 
 
@@ -25,54 +28,60 @@ _cache: weakref.WeakKeyDictionary[Type[Any], dict[int, "SchemaCoercionMapper"]]
 
 
 class SchemaCoercionMapper:
+    """Lightweight coercion of *dict* → *BaseModel* instances."""
+
     def __new__(
         cls,
         schema: Type[Any],
         type_hints: Optional[dict[str, Any]] = None,
+        *,
         max_depth: int = 12,
     ) -> "SchemaCoercionMapper":
-        if schema not in _cache:
-            _cache[schema] = {}
-        if max_depth in _cache[schema]:
-            return _cache[schema][max_depth]
-
+        by_depth = _cache.setdefault(schema, {})
+        if max_depth in by_depth:
+            return by_depth[max_depth]
         inst = super().__new__(cls)
-        _cache[schema][max_depth] = inst
+        by_depth[max_depth] = inst
         return inst
 
     def __init__(
         self,
         schema: Type[Any],
         type_hints: Optional[dict[str, Any]] = None,
+        *,
         max_depth: int = 12,
-    ):
-        if hasattr(self, "_inited"):
+    ) -> None:
+        if hasattr(self, "_initialised"):
             return
-        self._inited = True
+        self._initialised = True
+
         self.schema = schema
+        self.max_depth = max_depth
+
         self.type_hints = (
             type_hints
             if type_hints is not None
             else get_type_hints(schema, localns={schema.__name__: schema})
         )
-        self.max_depth = max_depth
 
-        if issubclass(schema, BaseModel):
-            self._fields = {
-                n: self.type_hints.get(n, f.annotation)
-                for n, f in schema.model_fields.items()
-            }
-            self._construct: Callable[..., Any] = schema.model_construct
-
-        elif issubclass(schema, BaseModelV1):
+        if issubclass(schema, BaseModelV1):
             self._fields = {
                 n: self.type_hints.get(n, f.annotation)
                 for n, f in schema.__fields__.items()
             }
             self._construct = schema.construct
+
+        elif issubclass(schema, BaseModel):
+            self._fields = {
+                n: self.type_hints.get(n, f.annotation)
+                for n, f in schema.model_fields.items()
+            }
+            self._construct: Callable[..., Any] = schema.model_construct  # type: ignore
+
         else:
-            raise TypeError("Schema is neither valid Pydantic v1 nor v2 model.")
-        self._field_coercers: Optional[dict[str, Callable[[Any, Any], Any]]] = None
+            raise TypeError("Schema is neither a Pydantic v1 nor v2 model.")
+
+        self._field_coercers: Optional[dict[str, Callable[[Any, int], Any]]] = None
 
     def __call__(self, input_data: Any, depth: Optional[int] = None) -> Any:
         return self.coerce(input_data, depth)
@@ -82,45 +91,51 @@ class SchemaCoercionMapper:
             depth = self.max_depth
         if not isinstance(input_data, dict) or depth <= 0:
             return input_data
-        processed = {}
+
         if self._field_coercers is None:
             self._field_coercers = {
                 n: self._build_coercer(t, depth - 1) for n, t in self._fields.items()
             }
+
+        processed: dict[str, Any] = {}
         for k, v in input_data.items():
             fn = self._field_coercers.get(k)
             processed[k] = fn(v, depth - 1) if fn else v
         return self._construct(**processed)
 
     def _build_coercer(
-        self, field_type: Any, depth: int, throw: bool = False
+        self, field_type: Any, depth: int, *, throw: bool = False
     ) -> Callable[[Any, Any], Any]:
         if depth == 0:
             return self._passthrough
+
         origin = get_origin(field_type)
 
+        if (field_type in _IDENTITY_TYPES) or (origin in _IDENTITY_TYPES):
+            return self._passthrough
+
         if origin is Annotated:
             real_type, *_ = get_args(field_type)
             sub = self._build_coercer(real_type, depth - 1)
             return lambda v, d: sub(v, d)
+
         if isclass(field_type):
+            # This is needed bcs. of issubclass issues on older versions of python
             is_class_ = True
             try:
-                is_base_model = issubclass(field_type, BaseModel)
+                is_bm_v2 = issubclass(field_type, BaseModel)
             except TypeError:
+                # python < 3.11 issue.
                 is_class_ = False
-                is_base_model = False
+                is_bm_v2 = False
+            if is_bm_v2 or (is_class_ and issubclass(field_type, BaseModelV1)):
+                mapper = SchemaCoercionMapper(field_type, max_depth=depth - 1)
+                return lambda v, d: mapper.coerce(v, d) if isinstance(v, dict) else v
 
-            if is_base_model:
-                mapper = SchemaCoercionMapper(field_type, max_depth=depth - 1)
-                return lambda v, d: mapper.coerce(v, d) if isinstance(v, dict) else v
-            if is_class_ and issubclass(field_type, BaseModelV1):
-                mapper = SchemaCoercionMapper(field_type, max_depth=depth - 1)
-                return lambda v, d: mapper.coerce(v, d) if isinstance(v, dict) else v
-        if origin is list or field_type is list:
+        if origin is list:
             args = get_args(field_type)
             if len(args) != 1:
-                return lambda v, d: v
+                return self._passthrough
             sub = self._build_coercer(args[0], depth - 1)
 
             def list_coercer(v: Any, d: Any) -> Any:
@@ -129,15 +144,21 @@ class SchemaCoercionMapper:
                 return [sub(x, d - 1) for x in v]
 
             return list_coercer
+
         if origin is set or field_type is set:
             args = get_args(field_type)
-            if len(args) != 1:
-                return lambda v, d: v
-            sub = self._build_coercer(args[0], depth - 1)
+            if len(args) > 1:
+                return self._passthrough
+            elif len(args) == 1:
+                sub = self._build_coercer(args[0], depth - 1)
+            else:
+                sub = None  # type: ignore
 
             def set_coercer(v: Any, d: Any) -> Any:
                 if not isinstance(v, (list, tuple, set)):
                     return v
+                if sub is None:
+                    return set(v)
                 return {sub(x, d - 1) for x in v}
 
             return set_coercer
@@ -165,20 +186,19 @@ class SchemaCoercionMapper:
             return dict_coercer
 
         if origin is tuple:
-            targs = get_args(field_type)
-            if not targs:
-                return lambda v, d: v
-            subs = [self._build_coercer(a, depth - 1) for a in targs]
+            elem_types = get_args(field_type)
+            if not elem_types:
+                return self._passthrough
+            subs = [self._build_coercer(t, depth - 1) for t in elem_types]
+            return lambda v, d: (
+                tuple(
+                    subs[i](v[i] if i < len(v) else None, d - 1)
+                    for i in range(len(subs))
+                )
+                if isinstance(v, (list, tuple))
+                else v
+            )
 
-            def tuple_coercer(v: Any, d: Any) -> Any:
-                if not isinstance(v, (list, tuple)):
-                    return v
-                out = []
-                for i, sp in enumerate(subs):
-                    out.append(sp(v[i] if i < len(v) else None, d - 1))
-                return tuple(out)
-
-            return tuple_coercer
         if origin is Union:
             uargs = get_args(field_type)
             subs, none_in_union = [], False
@@ -204,7 +224,97 @@ class SchemaCoercionMapper:
                 return v
 
             return union_coercer
-        return self._passthrough
 
-    def _passthrough(self, v: Any, d: Any) -> Any:
+        adapter_fn = _get_adapter(field_type)
+        return lambda v, _d: adapter_fn(v)
+
+    @staticmethod
+    def _passthrough(v: Any, _d: Any) -> Any:  # noqa: D401
         return v
+
+
+_adapter_cache: dict[Any, Callable[[Any], Any]] = {}
+
+
+_IDENTITY_TYPES: tuple[type[Any], ...] = (
+    int,
+    float,
+    str,
+    bool,
+    bytes,
+    bytearray,
+    complex,
+    memoryview,
+    type(None),
+)
+
+try:
+    # Pydantic v2.
+    from pydantic import TypeAdapter
+
+    try:
+        import pydantic.v1.types as v1_types_
+        from pydantic.v1 import parse_obj_as
+
+        v1_types = tuple(
+            v for k, v in vars(v1_types_).items() if k in v1_types_.__all__
+        )
+    except ImportError:
+        v1_types = ()
+
+        def parse_obj_as(tp: Any, v: Any) -> Any:  # type: ignore
+            return v
+
+    try:
+        from pydantic.v1 import parse_obj_as
+        from pydantic.v1.main import create_model
+    except ImportError:
+        create_model = None  # type: ignore
+
+    def _get_v1_parser(tp: Any) -> Any:
+        if create_model is not None:
+            try:
+                parser = create_model(
+                    f"ParsingModel[{tp}]",
+                    __root__=(tp, ...),
+                )
+                return lambda v: parser(__root__=v).__root__  # type: ignore
+            except RuntimeError:
+                return lambda v: v
+        return lambda v: parse_obj_as(tp, v)
+
+    @functools.lru_cache(maxsize=2048)
+    def _adapter_for(tp: Any) -> Callable[[Any], Any]:  # noqa: D401
+        if tp in v1_types:
+            return _get_v1_parser(tp)
+        try:
+            return TypeAdapter(
+                tp, config={"arbitrary_types_allowed": True}
+            ).validate_python
+        except TypeError:
+            # Delayed classes like ConstrainedList
+            return _get_v1_parser(tp)
+
+except ImportError:
+    # Pydantic V1
+    from pydantic.v1.main import create_model
+
+    @functools.lru_cache(maxsize=2048)
+    def _adapter_for(tp: Any) -> Callable[[Any], Any]:  # noqa: D401
+        try:
+            parser = create_model(
+                f"ParsingModel[{tp}]",
+                __root__=(tp, ...),
+            )
+            return lambda v: parser(__root__=v).__root__  # type: ignore
+        except RuntimeError:
+            return lambda v: v
+
+
+def _get_adapter(tp: Any) -> Callable[[Any], Any]:
+    try:
+        return _adapter_cache[tp]
+    except KeyError:
+        fn = _adapter_for(tp)
+        _adapter_cache[tp] = fn
+        return fn

libs/langgraph/langgraph/graph/state.py

@@ -2,6 +2,7 @@ import inspect
 import logging
 import typing
 import warnings
+from collections import defaultdict
 from functools import partial
 from inspect import isclass, isfunction, ismethod, signature
 from types import FunctionType
@@ -35,7 +36,16 @@ from langgraph.channels.dynamic_barrier_value import DynamicBarrierValue, WaitFo
 from langgraph.channels.ephemeral_value import EphemeralValue
 from langgraph.channels.last_value import LastValue
 from langgraph.channels.named_barrier_value import NamedBarrierValue
-from langgraph.constants import EMPTY_SEQ, MISSING, NS_END, NS_SEP, SELF, TAG_HIDDEN
+from langgraph.checkpoint.base import Checkpoint
+from langgraph.constants import (
+    EMPTY_SEQ,
+    INTERRUPT,
+    MISSING,
+    NS_END,
+    NS_SEP,
+    TAG_HIDDEN,
+    TASKS,
+)
 from langgraph.errors import (
     ErrorCode,
     InvalidUpdateError,
@@ -67,9 +77,9 @@ from langgraph.pregel.write import (
 )
 from langgraph.store.base import BaseStore
 from langgraph.types import All, Checkpointer, Command, RetryPolicy
-from langgraph.utils.fields import get_field_default
+from langgraph.utils.fields import get_field_default, get_update_as_tuples
 from langgraph.utils.pydantic import create_model
-from langgraph.utils.runnable import RunnableCallable, RunnableLike, coerce_to_runnable
+from langgraph.utils.runnable import RunnableLike, coerce_to_runnable
 
 logger = logging.getLogger(__name__)
 
@@ -99,7 +109,7 @@ class StateNodeSpec(NamedTuple):
     runnable: Runnable
     metadata: Optional[dict[str, Any]]
     input: Type[Any]
-    retry_policy: Optional[RetryPolicy]
+    retry_policy: Optional[Union[RetryPolicy, Sequence[RetryPolicy]]]
     ends: Optional[Union[tuple[str, ...], dict[str, str]]] = EMPTY_SEQ
 
 
@@ -241,7 +251,7 @@ class StateGraph(Graph):
         *,
         metadata: Optional[dict[str, Any]] = None,
         input: Optional[Type[Any]] = None,
-        retry: Optional[RetryPolicy] = None,
+        retry: Optional[Union[RetryPolicy, Sequence[RetryPolicy]]] = None,
         destinations: Optional[Union[dict[str, str], tuple[str, ...]]] = None,
     ) -> Self:
         """Adds a new node to the state graph.
@@ -266,7 +276,7 @@ class StateGraph(Graph):
         *,
         metadata: Optional[dict[str, Any]] = None,
         input: Optional[Type[Any]] = None,
-        retry: Optional[RetryPolicy] = None,
+        retry: Optional[Union[RetryPolicy, Sequence[RetryPolicy]]] = None,
         destinations: Optional[Union[dict[str, str], tuple[str, ...]]] = None,
     ) -> Self:
         """Adds a new node to the state graph.
@@ -290,7 +300,7 @@ class StateGraph(Graph):
         *,
         metadata: Optional[dict[str, Any]] = None,
         input: Optional[Type[Any]] = None,
-        retry: Optional[RetryPolicy] = None,
+        retry: Optional[Union[RetryPolicy, Sequence[RetryPolicy]]] = None,
         destinations: Optional[Union[dict[str, str], tuple[str, ...]]] = None,
     ) -> Self:
         """Adds a new node to the state graph.
@@ -302,7 +312,8 @@ class StateGraph(Graph):
             action (Optional[RunnableLike]): The action associated with the node. (default: None)
             metadata (Optional[dict[str, Any]]): The metadata associated with the node. (default: None)
             input (Optional[Type[Any]]): The input schema for the node. (default: the graph's input schema)
-            retry (Optional[RetryPolicy]): The policy for retrying the node. (default: None)
+            retry (Optional[Union[RetryPolicy, Sequence[RetryPolicy]]]): The policy for retrying the node. (default: None)
+                If a sequence is provided, the first matching policy will be applied.
             destinations (Optional[Union[dict[str, str], tuple[str, ...]]]): Destinations that indicate where a node can route to.
                 This is useful for edgeless graphs with nodes that return `Command` objects.
                 If a dict is provided, the keys will be used as the target node names and the values will be used as the labels for the edges.
@@ -628,6 +639,7 @@ class StateGraph(Graph):
 
         compiled = CompiledStateGraph(
             builder=self,
+            schema_to_mapper={},
             config_type=self.config_schema,
             input_model=(
                 self.input
@@ -659,10 +671,6 @@ class StateGraph(Graph):
         for key, node in self.nodes.items():
             compiled.attach_node(key, node)
 
-        compiled.attach_branch(START, SELF, CONTROL_BRANCH, with_reader=False)
-        for key, node in self.nodes.items():
-            compiled.attach_branch(key, SELF, CONTROL_BRANCH, with_reader=False)
-
         for start, end in self.edges:
             compiled.attach_edge(start, end)
 
@@ -678,6 +686,16 @@ class StateGraph(Graph):
 
 class CompiledStateGraph(CompiledGraph):
     builder: StateGraph
+    schema_to_mapper: dict[Type[Any], Optional[Callable[[Any], Any]]]
+
+    def __init__(
+        self,
+        *,
+        schema_to_mapper: dict[Type[Any], Optional[Callable[[Any], Any]]],
+        **kwargs: Any,
+    ) -> None:
+        super().__init__(**kwargs)
+        self.schema_to_mapper = schema_to_mapper
 
     def get_input_schema(
         self, config: Optional[RunnableConfig] = None
@@ -713,28 +731,6 @@ class CompiledStateGraph(CompiledGraph):
                 if is_writable_managed_value(v)
             ]
 
-        def _get_root(input: Any) -> Optional[Sequence[tuple[str, Any]]]:
-            if isinstance(input, Command):
-                if input.graph == Command.PARENT:
-                    return ()
-                return input._update_as_tuples()
-            elif (
-                isinstance(input, (list, tuple))
-                and input
-                and any(isinstance(i, Command) for i in input)
-            ):
-                updates: list[tuple[str, Any]] = []
-                for i in input:
-                    if isinstance(i, Command):
-                        if i.graph == Command.PARENT:
-                            continue
-                        updates.extend(i._update_as_tuples())
-                    else:
-                        updates.append(("__root__", i))
-                return updates
-            elif input is not None:
-                return [("__root__", input)]
-
         def _get_updates(
             input: Union[None, dict, Any],
         ) -> Optional[Sequence[tuple[str, Any]]]:
@@ -765,32 +761,7 @@ class CompiledStateGraph(CompiledGraph):
                         updates.extend(_get_updates(i) or ())
                 return updates
             elif (t := type(input)) and get_type_hints(t):
-                # Pydantic v2
-                if isinstance(input, BaseModel):
-                    keep: Optional[set[str]] = input.model_fields_set
-                    defaults = {k: v.default for k, v in input.model_fields.items()}
-                # Pydantic v1
-                elif isinstance(input, BaseModelV1):
-                    keep = input.__fields_set__
-                    defaults = {k: v.default for k, v in t.__fields__.items()}
-                else:
-                    keep = None
-                    defaults = {}
-
-                # NOTE: This behavior for Pydantic is somewhat inelegant,
-                # but we keep around for backwards compatibility
-                # if input is a Pydantic model, only update values
-                # that are different from the default values or in the keep set
-                return [
-                    (k, value)
-                    for k in output_keys
-                    if (value := getattr(input, k, MISSING)) is not MISSING
-                    and (
-                        value is not None
-                        or defaults.get(k, MISSING) is not None
-                        or (keep is not None and k in keep)
-                    )
-                ]
+                return get_update_as_tuples(input, output_keys)
             else:
                 msg = create_error_message(
                     message=f"Expected dict, got {input}",
@@ -803,6 +774,7 @@ class CompiledStateGraph(CompiledGraph):
             ChannelWriteTupleEntry(
                 mapper=_get_root if output_keys == ["__root__"] else _get_updates
             ),
+            ChannelWriteTupleEntry(mapper=_control_branch),
         )
 
         # add node and output channel
@@ -811,12 +783,21 @@ class CompiledStateGraph(CompiledGraph):
                 tags=[TAG_HIDDEN],
                 triggers=[START],
                 channels=[START],
-                writers=[ChannelWrite(write_entries, tags=[TAG_HIDDEN])],
+                writers=[ChannelWrite(write_entries)],
             )
         elif node is not None:
             input_schema = node.input if node else self.builder.schema
             input_values = {k: k for k in self.builder.schemas[input_schema]}
             is_single_input = len(input_values) == 1 and "__root__" in input_values
+            if input_schema in self.schema_to_mapper:
+                mapper = self.schema_to_mapper[input_schema]
+            else:
+                mapper = _pick_mapper(
+                    list(input_values),
+                    input_schema,
+                    self.builder.type_hints[input_schema],
+                )
+                self.schema_to_mapper[input_schema] = mapper
 
             branch_channel = CHANNEL_BRANCH_TO.format(key)
             self.channels[branch_channel] = EphemeralValue(Any, guard=False)
@@ -825,13 +806,9 @@ class CompiledStateGraph(CompiledGraph):
                 # read state keys and managed values
                 channels=(list(input_values) if is_single_input else input_values),
                 # coerce state dict to schema class (eg. pydantic model)
-                mapper=_pick_mapper(
-                    list(input_values),
-                    input_schema,
-                    self.builder.type_hints[input_schema],
-                ),
+                mapper=mapper,
                 # publish to state keys
-                writers=[ChannelWrite(write_entries, tags=[TAG_HIDDEN])],
+                writers=[ChannelWrite(write_entries)],
                 metadata=node.metadata,
                 retry_policy=node.retry_policy,
                 bound=node.runnable,
@@ -857,9 +834,7 @@ class CompiledStateGraph(CompiledGraph):
             # publish to channel
             for start in starts:
                 self.nodes[start].writers.append(
-                    ChannelWrite(
-                        (ChannelWriteEntry(channel_name, start),), tags=[TAG_HIDDEN]
-                    )
+                    ChannelWrite((ChannelWriteEntry(channel_name, start),))
                 )
 
     def attach_branch(
@@ -890,19 +865,33 @@ class CompiledStateGraph(CompiledGraph):
                     config, cast(Sequence[Union[Send, ChannelWriteEntry]], writes)
                 )
 
-        schema = branch.input_schema or (
-            self.builder.nodes[start].input
-            if start in self.builder.nodes
-            else self.builder.schema
-        )
+        if with_reader:
+            # get schema
+            schema = branch.input_schema or (
+                self.builder.nodes[start].input
+                if start in self.builder.nodes
+                else self.builder.schema
+            )
+            channels = list(self.builder.schemas[schema])
+            # get mapper
+            if schema in self.schema_to_mapper:
+                mapper = self.schema_to_mapper[schema]
+            else:
+                mapper = _pick_mapper(channels, schema, self.builder.type_hints[schema])
+                self.schema_to_mapper[schema] = mapper
+            # create reader
+            reader: Optional[Callable[[RunnableConfig], Any]] = partial(
+                ChannelRead.do_read,
+                select=channels[0] if channels == ["__root__"] else channels,
+                fresh=True,
+                # coerce state dict to schema class (eg. pydantic model)
+                mapper=mapper,
+            )
+        else:
+            reader = None
 
         # attach branch publisher
-        self.nodes[start].writers.append(
-            branch.run(
-                branch_writer,
-                _get_state_reader(self.builder, schema) if with_reader else None,
-            )
-        )
+        self.nodes[start].writers.append(branch.run(branch_writer, reader))
 
         # attach then subscriber
         if branch.then and branch.then != END:
@@ -917,24 +906,112 @@ class CompiledStateGraph(CompiledGraph):
             for end in ends:
                 if end != END:
                     self.nodes[end].writers.append(
-                        ChannelWrite(
-                            [ChannelWriteEntry(channel_name, end)], tags=[TAG_HIDDEN]
-                        )
+                        ChannelWrite((ChannelWriteEntry(channel_name, end),))
                     )
 
+    def _migrate_checkpoint(self, checkpoint: Checkpoint) -> None:
+        """Migrate a checkpoint to new channel layout."""
 
-def _get_state_reader(
-    builder: StateGraph, schema: Type[Any]
-) -> Callable[[RunnableConfig], Any]:
-    state_keys = list(builder.channels)
-    select = list(builder.schemas[schema])
-    return partial(
-        ChannelRead.do_read,
-        select=select[0] if select == ["__root__"] else select,
-        fresh=True,
-        # coerce state dict to schema class (eg. pydantic model)
-        mapper=_pick_mapper(state_keys, schema, builder.type_hints[schema]),
-    )
+        values = checkpoint["channel_values"]
+        versions = checkpoint["channel_versions"]
+        seen = checkpoint["versions_seen"]
+
+        # empty checkpoints do not need migration
+        if not versions:
+            return
+
+        # current version
+        if checkpoint["v"] >= 3:
+            return
+
+        # Migrate from start:node to branch:to:node
+        for k in list(versions):
+            if k.startswith("start:"):
+                # confirm node is present
+                node = k.split(":")[1]
+                if node not in self.nodes:
+                    continue
+                # get next version
+                new_k = f"branch:to:{node}"
+                new_v = (
+                    max(versions[new_k], versions.pop(k))
+                    if new_k in versions
+                    else versions.pop(k)
+                )
+                # update seen
+                for ss in (seen.get(node, {}), seen.get(INTERRUPT, {})):
+                    if k in ss:
+                        s = ss.pop(k)
+                        if new_k in ss:
+                            ss[new_k] = max(s, ss[new_k])
+                        else:
+                            ss[new_k] = s
+                # update value
+                if new_k not in values and k in values:
+                    values[new_k] = values.pop(k)
+                # update version
+                versions[new_k] = new_v
+
+        # Migrate from branch:source:condition:node to branch:to:node
+        for k in list(versions):
+            if k.startswith("branch:") and k.count(":") == 3:
+                # confirm node is present
+                node = k.split(":")[-1]
+                if node not in self.nodes:
+                    continue
+                # get next version
+                new_k = f"branch:to:{node}"
+                new_v = (
+                    max(versions[new_k], versions.pop(k))
+                    if new_k in versions
+                    else versions.pop(k)
+                )
+                # update seen
+                for ss in (seen.get(node, {}), seen.get(INTERRUPT, {})):
+                    if k in ss:
+                        s = ss.pop(k)
+                        if new_k in ss:
+                            ss[new_k] = max(s, ss[new_k])
+                        else:
+                            ss[new_k] = s
+                # update value
+                if new_k not in values and k in values:
+                    values[new_k] = values.pop(k)
+                # update version
+                versions[new_k] = new_v
+
+        if not set(self.nodes).isdisjoint(versions):
+            # Migrate from "node" to "branch:to:node"
+            source_to_target = defaultdict(list)
+            for start, end in self.builder.edges:
+                if start != START and end != END:
+                    source_to_target[start].append(end)
+            for k in list(versions):
+                if k == START:
+                    continue
+                if k in self.nodes:
+                    v = versions.pop(k)
+                    c = values.pop(k, MISSING)
+                    for end in source_to_target[k]:
+                        # get next version
+                        new_k = f"branch:to:{end}"
+                        new_v = max(versions[new_k], v) if new_k in versions else v
+                        # update seen
+                        for ss in (seen.get(end, {}), seen.get(INTERRUPT, {})):
+                            if k in ss:
+                                s = ss.pop(k)
+                                if new_k in ss:
+                                    ss[new_k] = max(s, ss[new_k])
+                                else:
+                                    ss[new_k] = s
+                        # update value
+                        if new_k not in values and c is not MISSING:
+                            values[new_k] = c
+                        # update version
+                        versions[new_k] = new_v
+                    # pop interrupt seen
+                    if INTERRUPT in seen:
+                        seen[INTERRUPT].pop(k, MISSING)
 
 
 def _pick_mapper(
@@ -946,7 +1023,7 @@ def _pick_mapper(
         if issubclass(schema, dict):
             return None
         if issubclass(schema, (BaseModel, BaseModelV1)):
-            return SchemaCoercionMapper(schema, type_hints)
+            return SchemaCoercionMapper(schema, type_hints=type_hints)
     return partial(_coerce_state, schema)
 
 
@@ -954,9 +1031,9 @@ def _coerce_state(schema: Type[Any], input: dict[str, Any]) -> dict[str, Any]:
     return schema(**input)
 
 
-def _control_branch(value: Any) -> Sequence[Union[str, Send]]:
+def _control_branch(value: Any) -> Sequence[tuple[str, Any]]:
     if isinstance(value, Send):
-        return [value]
+        return ((TASKS, value),)
     commands: list[Command] = []
     if isinstance(value, Command):
         commands.append(value)
@@ -964,51 +1041,45 @@ def _control_branch(value: Any) -> Sequence[Union[str, Send]]:
         for cmd in value:
             if isinstance(cmd, Command):
                 commands.append(cmd)
-    rtn: list[Union[str, Send]] = []
+    rtn: list[tuple[str, Any]] = []
     for command in commands:
         if command.graph == Command.PARENT:
             raise ParentCommand(command)
         if isinstance(command.goto, Send):
-            rtn.append(command.goto)
+            rtn.append((TASKS, command.goto))
         elif isinstance(command.goto, str):
-            rtn.append(command.goto)
+            rtn.append((CHANNEL_BRANCH_TO.format(command.goto), None))
         else:
-            rtn.extend(command.goto)
+            rtn.extend(
+                (TASKS, go)
+                if isinstance(go, Send)
+                else (CHANNEL_BRANCH_TO.format(go), None)
+                for go in command.goto
+            )
     return rtn
 
 
-async def _acontrol_branch(value: Any) -> Sequence[Union[str, Send]]:
-    if isinstance(value, Send):
-        return [value]
-    commands: list[Command] = []
-    if isinstance(value, Command):
-        commands.append(value)
-    elif isinstance(value, (list, tuple)):
-        for cmd in value:
-            if isinstance(cmd, Command):
-                commands.append(cmd)
-    rtn: list[Union[str, Send]] = []
-    for command in commands:
-        if command.graph == Command.PARENT:
-            raise ParentCommand(command)
-        if isinstance(command.goto, Send):
-            rtn.append(command.goto)
-        elif isinstance(command.goto, str):
-            rtn.append(command.goto)
-        else:
-            rtn.extend(command.goto)
-    return rtn
-
-
-CONTROL_BRANCH_PATH = RunnableCallable(
-    _control_branch,
-    _acontrol_branch,
-    tags=[TAG_HIDDEN],
-    trace=False,
-    recurse=False,
-    func_accepts_config=False,
-)
-CONTROL_BRANCH = Branch(CONTROL_BRANCH_PATH, None)
+def _get_root(input: Any) -> Optional[Sequence[tuple[str, Any]]]:
+    if isinstance(input, Command):
+        if input.graph == Command.PARENT:
+            return ()
+        return input._update_as_tuples()
+    elif (
+        isinstance(input, (list, tuple))
+        and input
+        and any(isinstance(i, Command) for i in input)
+    ):
+        updates: list[tuple[str, Any]] = []
+        for i in input:
+            if isinstance(i, Command):
+                if i.graph == Command.PARENT:
+                    continue
+                updates.extend(i._update_as_tuples())
+            else:
+                updates.append(("__root__", i))
+        return updates
+    elif input is not None:
+        return [("__root__", input)]
 
 
 def _get_channels(

libs/langgraph/langgraph/graph/ui.py

@@ -0,0 +1,206 @@
+from typing import Any, Literal, Optional, Union
+from uuid import uuid4
+
+from langchain_core.messages import AnyMessage
+from typing_extensions import TypedDict
+
+from langgraph.constants import CONF, CONFIG_KEY_SEND
+from langgraph.utils.config import get_config, get_stream_writer
+
+
+class UIMessage(TypedDict):
+    """A message type for UI updates in LangGraph.
+
+    This TypedDict represents a UI message that can be sent to update the UI state.
+    It contains information about the UI component to render and its properties.
+
+    Attributes:
+        type: Literal type indicating this is a UI message.
+        id: Unique identifier for the UI message.
+        name: Name of the UI component to render.
+        props: Properties to pass to the UI component.
+        metadata: Additional metadata about the UI message.
+    """
+
+    type: Literal["ui"]
+    id: str
+    name: str
+    props: dict[str, Any]
+    metadata: dict[str, Any]
+
+
+class RemoveUIMessage(TypedDict):
+    """A message type for removing UI components in LangGraph.
+
+    This TypedDict represents a message that can be sent to remove a UI component
+    from the current state.
+
+    Attributes:
+        type: Literal type indicating this is a remove-ui message.
+        id: Unique identifier of the UI message to remove.
+    """
+
+    type: Literal["remove-ui"]
+    id: str
+
+
+AnyUIMessage = Union[UIMessage, RemoveUIMessage]
+
+
+def push_ui_message(
+    name: str,
+    props: dict[str, Any],
+    *,
+    id: Optional[str] = None,
+    metadata: Optional[dict[str, Any]] = None,
+    message: Optional[AnyMessage] = None,
+    state_key: str = "ui",
+) -> UIMessage:
+    """Push a new UI message to update the UI state.
+
+    This function creates and sends a UI message that will be rendered in the UI.
+    It also updates the graph state with the new UI message.
+
+    Args:
+        name: Name of the UI component to render.
+        props: Properties to pass to the UI component.
+        id: Optional unique identifier for the UI message.
+            If not provided, a random UUID will be generated.
+        metadata: Optional additional metadata about the UI message.
+        message: Optional message object to associate with the UI message.
+        state_key: Key in the graph state where the UI messages are stored.
+            Defaults to "ui".
+
+    Returns:
+        The created UI message.
+
+    Example:
+
+    .. code-block:: python
+
+        push_ui_message(
+            name="component-name",
+            props={"content": "Hello world"},
+        )
+
+    """
+    writer = get_stream_writer()
+    config = get_config()
+
+    message_id = None
+    if message:
+        if isinstance(message, dict) and "id" in message:
+            message_id = message.get("id")
+        elif hasattr(message, "id"):
+            message_id = message.id
+
+    evt: UIMessage = {
+        "type": "ui",
+        "id": id or str(uuid4()),
+        "name": name,
+        "props": props,
+        "metadata": {
+            **(config.get("metadata") or {}),
+            "tags": config.get("tags", None),
+            "name": config.get("run_name", None),
+            "run_id": config.get("run_id", None),
+            **(metadata or {}),
+            **({"message_id": message_id} if message_id else {}),
+        },
+    }
+
+    writer(evt)
+    config[CONF][CONFIG_KEY_SEND]([(state_key, evt)])
+
+    return evt
+
+
+def delete_ui_message(id: str, *, state_key: str = "ui") -> RemoveUIMessage:
+    """Delete a UI message by ID from the UI state.
+
+    This function creates and sends a message to remove a UI component from the current state.
+    It also updates the graph state to remove the UI message.
+
+    Args:
+        id: Unique identifier of the UI component to remove.
+        state_key: Key in the graph state where the UI messages are stored. Defaults to "ui".
+
+    Returns:
+        The remove UI message.
+
+    Example:
+
+    .. code-block:: python
+
+        delete_ui_message("message-123")
+
+    """
+    writer = get_stream_writer()
+    config = get_config()
+
+    evt: RemoveUIMessage = {"type": "remove-ui", "id": id}
+
+    writer(evt)
+    config[CONF][CONFIG_KEY_SEND]([(state_key, evt)])
+
+    return evt
+
+
+def ui_message_reducer(
+    left: Union[list[AnyUIMessage], AnyUIMessage],
+    right: Union[list[AnyUIMessage], AnyUIMessage],
+) -> list[AnyUIMessage]:
+    """Merge two lists of UI messages, supporting removing UI messages.
+
+    This function combines two lists of UI messages, handling both regular UI messages
+    and `remove-ui` messages. When a `remove-ui` message is encountered, it removes any
+    UI message with the matching ID from the current state.
+
+    Args:
+        left: First list of UI messages or single UI message.
+        right: Second list of UI messages or single UI message.
+
+    Returns:
+        Combined list of UI messages with removals applied.
+
+    Example:
+
+    .. code-block:: python
+
+        messages = ui_message_reducer(
+            [{"type": "ui", "id": "1", "name": "Chat", "props": {}}],
+            {"type": "remove-ui", "id": "1"}
+        )
+
+    """
+    if not isinstance(left, list):
+        left = [left]
+
+    if not isinstance(right, list):
+        right = [right]
+
+    # merge messages
+    merged = left.copy()
+    merged_by_id = {m.get("id"): i for i, m in enumerate(merged)}
+    ids_to_remove = set()
+
+    for msg in right:
+        msg_id = msg.get("id")
+
+        if (existing_idx := merged_by_id.get(msg_id)) is not None:
+            if msg.get("type") == "remove-ui":
+                ids_to_remove.add(msg_id)
+            else:
+                ids_to_remove.discard(msg_id)
+                merged[existing_idx] = msg
+        else:
+            if msg.get("type") == "remove-ui":
+                raise ValueError(
+                    f"Attempting to delete an UI message with an ID that doesn't exist ('{msg_id}')"
+                )
+
+            merged_by_id[msg_id] = len(merged)
+            merged.append(msg)
+
+    merged = [m for m in merged if m.get("id") not in ids_to_remove]
+    return merged

libs/langgraph/langgraph/pregel/__init__.py

@@ -39,7 +39,6 @@ from langchain_core.runnables.utils import (
     ConfigurableFieldSpec,
     get_unique_config_specs,
 )
-from langchain_core.tracers._streaming import _StreamingCallbackHandler
 from pydantic import BaseModel
 from typing_extensions import Self
 
@@ -48,12 +47,13 @@ from langgraph.channels.base import (
 )
 from langgraph.checkpoint.base import (
     BaseCheckpointSaver,
+    Checkpoint,
     CheckpointTuple,
     copy_checkpoint,
-    empty_checkpoint,
 )
 from langgraph.constants import (
     CONF,
+    CONFIG_KEY_CHECKPOINT_DURING,
     CONFIG_KEY_CHECKPOINT_ID,
     CONFIG_KEY_CHECKPOINT_NS,
     CONFIG_KEY_CHECKPOINTER,
@@ -66,6 +66,7 @@ from langgraph.constants import (
     CONFIG_KEY_STREAM,
     CONFIG_KEY_STREAM_WRITER,
     CONFIG_KEY_TASK_ID,
+    CONFIG_KEY_THREAD_ID,
     END,
     ERROR,
     INPUT,
@@ -90,7 +91,7 @@ from langgraph.pregel.algo import (
     local_write,
     prepare_next_tasks,
 )
-from langgraph.pregel.checkpoint import create_checkpoint
+from langgraph.pregel.checkpoint import create_checkpoint, empty_checkpoint
 from langgraph.pregel.debug import tasks_w_writes
 from langgraph.pregel.io import map_input, read_channels
 from langgraph.pregel.loop import AsyncPregelLoop, StreamProtocol, SyncPregelLoop
@@ -125,6 +126,11 @@ from langgraph.utils.fields import get_enhanced_type_hints
 from langgraph.utils.pydantic import create_model, is_supported_by_pydantic
 from langgraph.utils.queue import AsyncQueue, SyncQueue  # type: ignore[attr-defined]
 
+try:
+    from langchain_core.tracers._streaming import _StreamingCallbackHandler
+except ImportError:
+    _StreamingCallbackHandler = None  # type: ignore
+
 WriteValue = Union[Callable[[Input], Output], Any]
 
 
@@ -493,8 +499,8 @@ class Pregel(PregelProtocol):
     store: Optional[BaseStore] = None
     """Memory store to use for SharedValues. Defaults to None."""
 
-    retry_policy: Optional[RetryPolicy] = None
-    """Retry policy to use when running tasks. Set to None to disable."""
+    retry_policy: Optional[Sequence[RetryPolicy]] = None
+    """Retry policies to use when running tasks. Set to None to disable."""
 
     config_type: Optional[Type[Any]] = None
 
@@ -523,7 +529,7 @@ class Pregel(PregelProtocol):
         debug: Optional[bool] = None,
         checkpointer: Optional[BaseCheckpointSaver] = None,
         store: Optional[BaseStore] = None,
-        retry_policy: Optional[RetryPolicy] = None,
+        retry_policy: Optional[Union[RetryPolicy, Sequence[RetryPolicy]]] = None,
         config_type: Optional[Type[Any]] = None,
         input_model: Optional[Type[BaseModel]] = None,
         config: Optional[RunnableConfig] = None,
@@ -543,7 +549,10 @@ class Pregel(PregelProtocol):
         self.debug = debug if debug is not None else get_debug()
         self.checkpointer = checkpointer
         self.store = store
-        self.retry_policy = retry_policy
+        if isinstance(retry_policy, RetryPolicy):
+            self.retry_policy: Sequence[RetryPolicy] = (retry_policy,)
+        else:
+            self.retry_policy = retry_policy
         self.config_type = config_type
         self.input_model = input_model
         self.config = config
@@ -767,6 +776,10 @@ class Pregel(PregelProtocol):
         for name, node in self.get_subgraphs(namespace=namespace, recurse=recurse):
             yield name, node
 
+    def _migrate_checkpoint(self, checkpoint: Checkpoint) -> None:
+        """Migrate a saved checkpoint to new channel layout."""
+        pass
+
     def _prepare_state_snapshot(
         self,
         config: RunnableConfig,
@@ -785,6 +798,9 @@ class Pregel(PregelProtocol):
                 tasks=(),
             )
 
+        # migrate checkpoint if needed
+        self._migrate_checkpoint(saved.checkpoint)
+
         with ChannelsManager(
             self.channels,
             saved.checkpoint,
@@ -898,6 +914,9 @@ class Pregel(PregelProtocol):
                 tasks=(),
             )
 
+        # migrate checkpoint if needed
+        self._migrate_checkpoint(saved.checkpoint)
+
         async with AsyncChannelsManager(
             self.channels,
             saved.checkpoint,
@@ -1026,6 +1045,9 @@ class Pregel(PregelProtocol):
             config = merge_configs(
                 config, {CONF: {CONFIG_KEY_CHECKPOINT_NS: recast_checkpoint_ns(ns)}}
             )
+        thread_id = config[CONF][CONFIG_KEY_THREAD_ID]
+        if not isinstance(thread_id, str):
+            config[CONF][CONFIG_KEY_THREAD_ID] = str(thread_id)
 
         saved = checkpointer.get_tuple(config)
         return self._prepare_state_snapshot(
@@ -1065,6 +1087,9 @@ class Pregel(PregelProtocol):
             config = merge_configs(
                 config, {CONF: {CONFIG_KEY_CHECKPOINT_NS: recast_checkpoint_ns(ns)}}
             )
+        thread_id = config[CONF][CONFIG_KEY_THREAD_ID]
+        if not isinstance(thread_id, str):
+            config[CONF][CONFIG_KEY_THREAD_ID] = str(thread_id)
 
         saved = await checkpointer.aget_tuple(config)
         return await self._aprepare_state_snapshot(
@@ -1110,7 +1135,12 @@ class Pregel(PregelProtocol):
         config = merge_configs(
             self.config,
             config,
-            {CONF: {CONFIG_KEY_CHECKPOINT_NS: checkpoint_ns}},
+            {
+                CONF: {
+                    CONFIG_KEY_CHECKPOINT_NS: checkpoint_ns,
+                    CONFIG_KEY_THREAD_ID: str(config[CONF][CONFIG_KEY_THREAD_ID]),
+                }
+            },
         )
         # eagerly consume list() to avoid holding up the db cursor
         for checkpoint_tuple in list(
@@ -1157,7 +1187,12 @@ class Pregel(PregelProtocol):
         config = merge_configs(
             self.config,
             config,
-            {CONF: {CONFIG_KEY_CHECKPOINT_NS: checkpoint_ns}},
+            {
+                CONF: {
+                    CONFIG_KEY_CHECKPOINT_NS: checkpoint_ns,
+                    CONFIG_KEY_THREAD_ID: str(config[CONF][CONFIG_KEY_THREAD_ID]),
+                }
+            },
         )
         # eagerly consume list() to avoid holding up the db cursor
         for checkpoint_tuple in [
@@ -1223,6 +1258,8 @@ class Pregel(PregelProtocol):
             # get last checkpoint
             config = ensure_config(self.config, input_config)
             saved = checkpointer.get_tuple(config)
+            if saved is not None:
+                self._migrate_checkpoint(saved.checkpoint)
             checkpoint = (
                 copy_checkpoint(saved.checkpoint) if saved else empty_checkpoint()
             )
@@ -1575,7 +1612,9 @@ class Pregel(PregelProtocol):
 
             return patch_checkpoint_map(next_config, saved.metadata if saved else None)
 
-        current_config = config
+        current_config = patch_configurable(
+            config, {CONFIG_KEY_THREAD_ID: str(config[CONF][CONFIG_KEY_THREAD_ID])}
+        )
         for superstep in supersteps:
             current_config = perform_superstep(current_config, superstep)
         return current_config
@@ -1633,6 +1672,8 @@ class Pregel(PregelProtocol):
             # get last checkpoint
             config = ensure_config(self.config, input_config)
             saved = await checkpointer.aget_tuple(config)
+            if saved is not None:
+                self._migrate_checkpoint(saved.checkpoint)
             checkpoint = (
                 copy_checkpoint(saved.checkpoint) if saved else empty_checkpoint()
             )
@@ -1983,7 +2024,9 @@ class Pregel(PregelProtocol):
                     await checkpointer.aput_writes(next_config, push_writes, task_id)
             return patch_checkpoint_map(next_config, saved.metadata if saved else None)
 
-        current_config = config
+        current_config = patch_configurable(
+            config, {CONFIG_KEY_THREAD_ID: str(config[CONF][CONFIG_KEY_THREAD_ID])}
+        )
         for superstep in supersteps:
             current_config = await aperform_superstep(current_config, superstep)
         return current_config
@@ -2080,6 +2123,7 @@ class Pregel(PregelProtocol):
         output_keys: Optional[Union[str, Sequence[str]]] = None,
         interrupt_before: Optional[Union[All, Sequence[str]]] = None,
         interrupt_after: Optional[Union[All, Sequence[str]]] = None,
+        checkpoint_during: Optional[bool] = None,
         debug: Optional[bool] = None,
         subgraphs: bool = False,
     ) -> Iterator[Union[dict[str, Any], Any]]:
@@ -2101,6 +2145,7 @@ class Pregel(PregelProtocol):
             output_keys: The keys to stream, defaults to all non-context channels.
             interrupt_before: Nodes to interrupt before, defaults to all nodes in the graph.
             interrupt_after: Nodes to interrupt after, defaults to all nodes in the graph.
+            checkpoint_during: Whether to checkpoint intermediate steps, defaults to True. If False, only the final checkpoint is saved.
             debug: Whether to print debug information during execution, defaults to False.
             subgraphs: Whether to stream subgraphs, defaults to False.
 
@@ -2262,6 +2307,9 @@ class Pregel(PregelProtocol):
                 config[CONF][CONFIG_KEY_STREAM_WRITER] = lambda c: stream.put(
                     ((), "custom", c)
                 )
+            # set checkpointing mode for subgraphs
+            if checkpoint_during is not None:
+                config[CONF][CONFIG_KEY_CHECKPOINT_DURING] = checkpoint_during
             with SyncPregelLoop(
                 input,
                 input_model=self.input_model,
@@ -2277,7 +2325,11 @@ class Pregel(PregelProtocol):
                 interrupt_after=interrupt_after_,
                 manager=run_manager,
                 debug=debug,
+                checkpoint_during=checkpoint_during
+                if checkpoint_during is not None
+                else config[CONF].get(CONFIG_KEY_CHECKPOINT_DURING, True),
                 trigger_to_nodes=self.trigger_to_nodes,
+                migrate_checkpoint=self._migrate_checkpoint,
             ) as loop:
                 # create runner
                 runner = PregelRunner(
@@ -2358,6 +2410,7 @@ class Pregel(PregelProtocol):
         output_keys: Optional[Union[str, Sequence[str]]] = None,
         interrupt_before: Optional[Union[All, Sequence[str]]] = None,
         interrupt_after: Optional[Union[All, Sequence[str]]] = None,
+        checkpoint_during: Optional[bool] = None,
         debug: Optional[bool] = None,
         subgraphs: bool = False,
     ) -> AsyncIterator[Union[dict[str, Any], Any]]:
@@ -2379,6 +2432,7 @@ class Pregel(PregelProtocol):
             output_keys: The keys to stream, defaults to all non-context channels.
             interrupt_before: Nodes to interrupt before, defaults to all nodes in the graph.
             interrupt_after: Nodes to interrupt after, defaults to all nodes in the graph.
+            checkpoint_during: Whether to checkpoint intermediate steps, defaults to True. If False, only the final checkpoint is saved.
             debug: Whether to print debug information during execution, defaults to False.
             subgraphs: Whether to stream subgraphs, defaults to False.
 
@@ -2514,13 +2568,18 @@ class Pregel(PregelProtocol):
             run_id=config.get("run_id"),
         )
         # if running from astream_log() run each proc with streaming
-        do_stream = next(
-            (
-                cast(_StreamingCallbackHandler, h)
-                for h in run_manager.handlers
-                if isinstance(h, _StreamingCallbackHandler)
-            ),
-            None,
+        do_stream = (
+            next(
+                (
+                    True
+                    for h in run_manager.handlers
+                    if isinstance(h, _StreamingCallbackHandler)
+                    and not isinstance(h, StreamMessagesHandler)
+                ),
+                False,
+            )
+            if _StreamingCallbackHandler is not None
+            else False
         )
         try:
             # assign defaults
@@ -2556,6 +2615,9 @@ class Pregel(PregelProtocol):
                         stream.put_nowait, ((), "custom", c)
                     )
                 )
+            # set checkpointing mode for subgraphs
+            if checkpoint_during is not None:
+                config[CONF][CONFIG_KEY_CHECKPOINT_DURING] = checkpoint_during
             async with AsyncPregelLoop(
                 input,
                 input_model=self.input_model,
@@ -2571,12 +2633,11 @@ class Pregel(PregelProtocol):
                 interrupt_after=interrupt_after_,
                 manager=run_manager,
                 debug=debug,
-                # `self.nodes` can be modified after creation of `Pregel`. For example,
-                # that's how StateGraph compilation currently works.
-                # For now, we recompute the trigger_to_nodes mapping every time the
-                # loop is created. We could potentially memoize this if it becomes a
-                # performance issue.
-                trigger_to_nodes=_trigger_to_nodes(self.nodes),
+                checkpoint_during=checkpoint_during
+                if checkpoint_during is not None
+                else config[CONF].get(CONFIG_KEY_CHECKPOINT_DURING, True),
+                trigger_to_nodes=self.trigger_to_nodes,
+                migrate_checkpoint=self._migrate_checkpoint,
             ) as loop:
                 # create runner
                 runner = PregelRunner(
@@ -2585,7 +2646,7 @@ class Pregel(PregelProtocol):
                     ),
                     put_writes=weakref.WeakMethod(loop.put_writes),
                     schedule_task=weakref.WeakMethod(loop.accept_push),
-                    use_astream=do_stream is not None,
+                    use_astream=do_stream,
                     node_finished=config[CONF].get(CONFIG_KEY_NODE_FINISHED),
                 )
                 # enable subgraph streaming
@@ -2650,6 +2711,7 @@ class Pregel(PregelProtocol):
         output_keys: Optional[Union[str, Sequence[str]]] = None,
         interrupt_before: Optional[Union[All, Sequence[str]]] = None,
         interrupt_after: Optional[Union[All, Sequence[str]]] = None,
+        checkpoint_during: Optional[bool] = None,
         debug: Optional[bool] = None,
         **kwargs: Any,
     ) -> Union[dict[str, Any], Any]:
@@ -2681,6 +2743,7 @@ class Pregel(PregelProtocol):
             output_keys=output_keys,
             interrupt_before=interrupt_before,
             interrupt_after=interrupt_after,
+            checkpoint_during=checkpoint_during,
             debug=debug,
             **kwargs,
         ):
@@ -2702,6 +2765,7 @@ class Pregel(PregelProtocol):
         output_keys: Optional[Union[str, Sequence[str]]] = None,
         interrupt_before: Optional[Union[All, Sequence[str]]] = None,
         interrupt_after: Optional[Union[All, Sequence[str]]] = None,
+        checkpoint_during: Optional[bool] = None,
         debug: Optional[bool] = None,
         **kwargs: Any,
     ) -> Union[dict[str, Any], Any]:
@@ -2734,6 +2798,7 @@ class Pregel(PregelProtocol):
             output_keys=output_keys,
             interrupt_before=interrupt_before,
             interrupt_after=interrupt_after,
+            checkpoint_during=checkpoint_during,
             debug=debug,
             **kwargs,
         ):

libs/langgraph/langgraph/pregel/algo.py

@@ -3,13 +3,13 @@ import itertools
 import sys
 import threading
 from collections import defaultdict, deque
+from copy import copy
 from functools import partial
 from hashlib import sha1
 from typing import (
     Any,
     Callable,
     Iterable,
-    Iterator,
     Literal,
     Mapping,
     NamedTuple,
@@ -49,6 +49,7 @@ from langgraph.constants import (
     EMPTY_SEQ,
     ERROR,
     INTERRUPT,
+    MISSING,
     NO_WRITES,
     NS_END,
     NS_SEP,
@@ -63,12 +64,12 @@ from langgraph.constants import (
     TASKS,
     Send,
 )
-from langgraph.errors import EmptyChannelError, InvalidUpdateError
+from langgraph.errors import InvalidUpdateError
 from langgraph.managed.base import ManagedValueMapping
 from langgraph.pregel.call import get_runnable_for_task
-from langgraph.pregel.io import read_channel, read_channels
+from langgraph.pregel.io import read_channels
 from langgraph.pregel.log import logger
-from langgraph.pregel.read import PregelNode
+from langgraph.pregel.read import INPUT_CACHE_KEY_TYPE, PregelNode
 from langgraph.store.base import BaseStore
 from langgraph.types import (
     All,
@@ -115,7 +116,7 @@ class Call:
 
     func: Callable
     input: Any
-    retry: Optional[RetryPolicy]
+    retry: Optional[Sequence[RetryPolicy]]
     callbacks: Callbacks
 
     def __init__(
@@ -123,7 +124,7 @@ class Call:
         func: Callable,
         input: Any,
         *,
-        retry: Optional[RetryPolicy],
+        retry: Optional[Sequence[RetryPolicy]],
         callbacks: Callbacks,
     ) -> None:
         self.func = func
@@ -423,6 +424,7 @@ def prepare_next_tasks(
         are the tasks themselves. This is the union of all PUSH tasks (Sends)
         and PULL tasks (nodes triggered by edges).
     """
+    input_cache: dict[INPUT_CACHE_KEY_TYPE, Any] = {}
     checkpoint_id_bytes = binascii.unhexlify(checkpoint["id"].replace("-", ""))
     null_version = checkpoint_null_version(checkpoint)
     tasks: list[Union[PregelTask, PregelExecutableTask]] = []
@@ -444,6 +446,7 @@ def prepare_next_tasks(
             store=store,
             checkpointer=checkpointer,
             manager=manager,
+            input_cache=input_cache,
         ):
             tasks.append(task)
 
@@ -486,6 +489,7 @@ def prepare_next_tasks(
             store=store,
             checkpointer=checkpointer,
             manager=manager,
+            input_cache=input_cache,
         ):
             tasks.append(task)
     return {t.id: t for t in tasks}
@@ -511,6 +515,7 @@ def prepare_single_task(
     store: Optional[BaseStore] = None,
     checkpointer: Optional[BaseCheckpointSaver] = None,
     manager: Union[None, ParentRunManager, AsyncParentRunManager] = None,
+    input_cache: Optional[dict[INPUT_CACHE_KEY_TYPE, Any]] = None,
 ) -> Union[None, PregelTask, PregelExecutableTask]:
     """Prepares a single task for the next Pregel step, given a task path, which
     uniquely identifies a PUSH or PULL task within the graph."""
@@ -729,11 +734,15 @@ def prepare_single_task(
         ):
             triggers = tuple(sorted(proc.triggers))
             try:
-                val = next(
-                    _proc_input(proc, managed, channels, for_execution=for_execution)
+                val = _proc_input(
+                    proc,
+                    managed,
+                    channels,
+                    for_execution=for_execution,
+                    input_cache=input_cache,
                 )
-            except StopIteration:
-                return
+                if val is MISSING:
+                    return
             except Exception as exc:
                 if SUPPORTS_EXC_NOTES:
                     exc.add_note(
@@ -926,34 +935,32 @@ def _proc_input(
     channels: Mapping[str, BaseChannel],
     *,
     for_execution: bool,
-) -> Iterator[Any]:
+    input_cache: Optional[dict[INPUT_CACHE_KEY_TYPE, Any]],
+) -> Any:
     """Prepare input for a PULL task, based on the process's channels and triggers."""
+    # if in cache return shallow copy
+    if input_cache is not None and proc.input_cache_key in input_cache:
+        return copy(input_cache[proc.input_cache_key])
     # If all trigger channels subscribed by this process are not empty
     # then invoke the process with the values of all non-empty channels
     if isinstance(proc.channels, dict):
-        try:
-            val: dict[str, Any] = {}
-            for k, chan in proc.channels.items():
-                if chan in proc.triggers:
-                    val[k] = read_channel(channels, chan, catch=False)
-                elif chan in channels:
-                    try:
-                        val[k] = read_channel(channels, chan, catch=False)
-                    except EmptyChannelError:
-                        continue
-                else:
-                    val[k] = managed[k]()
-        except EmptyChannelError:
-            return
+        val: dict[str, Any] = {}
+        for k, chan in proc.channels.items():
+            if chan in channels:
+                if channels[chan].is_available():
+                    val[k] = channels[chan].get()
+            else:
+                val[k] = managed[k]()
     elif isinstance(proc.channels, list):
         for chan in proc.channels:
-            try:
-                val = read_channel(channels, chan, catch=False)
-                break
-            except EmptyChannelError:
-                pass
+            if chan in channels:
+                if channels[chan].is_available():
+                    val = channels[chan].get()
+                    break
+            else:
+                val[k] = managed[k]()
         else:
-            return
+            return MISSING
     else:
         raise RuntimeError(
             "Invalid channels type, expected list or dict, got {proc.channels}"
@@ -963,7 +970,11 @@ def _proc_input(
     if for_execution and proc.mapper is not None:
         val = proc.mapper(val)
 
-    yield val
+    # Cache the input value
+    if input_cache is not None:
+        input_cache[proc.input_cache_key] = val
+
+    return val
 
 
 def _uuid5_str(namespace: bytes, *parts: str) -> str:

libs/langgraph/langgraph/pregel/call.py

@@ -5,12 +5,12 @@ import functools
 import inspect
 import sys
 import types
-from typing import Any, Callable, Generator, Generic, Optional, TypeVar, cast
+from typing import Any, Callable, Generator, Generic, Optional, Sequence, TypeVar, cast
 
 from langchain_core.runnables import Runnable
 from typing_extensions import ParamSpec
 
-from langgraph.constants import CONF, CONFIG_KEY_CALL, RETURN, TAG_HIDDEN
+from langgraph.constants import CONF, CONFIG_KEY_CALL, RETURN
 from langgraph.pregel.write import ChannelWrite, ChannelWriteEntry
 from langgraph.types import RetryPolicy
 from langgraph.utils.config import get_config
@@ -197,7 +197,7 @@ def get_runnable_for_task(func: Callable[..., Any]) -> RunnableSeq:
             )
         seq = RunnableSeq(
             run,
-            ChannelWrite([ChannelWriteEntry(RETURN)], tags=[TAG_HIDDEN]),
+            ChannelWrite([ChannelWriteEntry(RETURN)]),
             name=name,
             trace_inputs=functools.partial(
                 _explode_args_trace_inputs, inspect.signature(func)
@@ -224,7 +224,7 @@ class SyncAsyncFuture(Generic[T], concurrent.futures.Future[T]):
 def call(
     func: Callable[P, T],
     *args: Any,
-    retry: Optional[RetryPolicy] = None,
+    retry: Optional[Sequence[RetryPolicy]] = None,
     **kwargs: Any,
 ) -> SyncAsyncFuture[T]:
     config = get_config()

libs/langgraph/langgraph/pregel/checkpoint.py

@@ -2,10 +2,24 @@ from datetime import datetime, timezone
 from typing import Mapping, Optional
 
 from langgraph.channels.base import BaseChannel
-from langgraph.checkpoint.base import LATEST_VERSION, Checkpoint
+from langgraph.checkpoint.base import Checkpoint
 from langgraph.checkpoint.base.id import uuid6
 from langgraph.constants import MISSING
 
+LATEST_VERSION = 3
+
+
+def empty_checkpoint() -> Checkpoint:
+    return Checkpoint(
+        v=LATEST_VERSION,
+        id=str(uuid6(clock_seq=-2)),
+        ts=datetime.now(timezone.utc).isoformat(),
+        channel_values={},
+        channel_versions={},
+        versions_seen={},
+        pending_sends=[],
+    )
+
 
 def create_checkpoint(
     checkpoint: Checkpoint,

libs/langgraph/langgraph/pregel/loop.py

@@ -30,6 +30,7 @@ from typing_extensions import ParamSpec, Self
 
 from langgraph.channels.base import BaseChannel
 from langgraph.checkpoint.base import (
+    EXCLUDED_METADATA_KEYS,
     WRITES_IDX_MAP,
     BaseCheckpointSaver,
     ChannelVersions,
@@ -38,7 +39,6 @@ from langgraph.checkpoint.base import (
     CheckpointTuple,
     PendingWrite,
     copy_checkpoint,
-    empty_checkpoint,
 )
 from langgraph.constants import (
     CONF,
@@ -52,6 +52,7 @@ from langgraph.constants import (
     CONFIG_KEY_SCRATCHPAD,
     CONFIG_KEY_STREAM,
     CONFIG_KEY_TASK_ID,
+    CONFIG_KEY_THREAD_ID,
     EMPTY_SEQ,
     ERROR,
     INPUT,
@@ -63,6 +64,7 @@ from langgraph.constants import (
     RESUME,
     SCHEDULED,
     TAG_HIDDEN,
+    TASKS,
 )
 from langgraph.errors import (
     CheckpointNotLatest,
@@ -87,7 +89,7 @@ from langgraph.pregel.algo import (
     should_interrupt,
     task_path_str,
 )
-from langgraph.pregel.checkpoint import create_checkpoint
+from langgraph.pregel.checkpoint import create_checkpoint, empty_checkpoint
 from langgraph.pregel.debug import (
     map_debug_checkpoint,
     map_debug_task_results,
@@ -155,7 +157,7 @@ class PregelLoop(LoopProtocol):
     manager: Union[None, AsyncParentRunManager, ParentRunManager]
     interrupt_after: Union[All, Sequence[str]]
     interrupt_before: Union[All, Sequence[str]]
-    checkpoint_every_step: bool
+    checkpoint_during: bool
     debug: bool
 
     checkpointer_get_next_version: GetNextVersion
@@ -175,10 +177,12 @@ class PregelLoop(LoopProtocol):
             Any,
         ]
     ]
+    _migrate_checkpoint: Optional[Callable[[Checkpoint], None]]
     submit: Submit
     channels: Mapping[str, BaseChannel]
     managed: ManagedValueMapping
     checkpoint: Checkpoint
+    checkpoint_id_saved: str
     checkpoint_ns: tuple[str, ...]
     checkpoint_config: RunnableConfig
     checkpoint_metadata: CheckpointMetadata
@@ -212,8 +216,9 @@ class PregelLoop(LoopProtocol):
         manager: Union[None, AsyncParentRunManager, ParentRunManager] = None,
         input_model: Optional[Type[BaseModel]] = None,
         debug: bool = False,
+        migrate_checkpoint: Optional[Callable[[Checkpoint], None]] = None,
         trigger_to_nodes: Optional[Mapping[str, Sequence[str]]] = None,
-        checkpoint_every_step: bool = True,
+        checkpoint_during: bool = True,
     ) -> None:
         super().__init__(
             step=0,
@@ -237,8 +242,9 @@ class PregelLoop(LoopProtocol):
             CONFIG_KEY_CHECKPOINT_ID not in config[CONF]
             or CONFIG_KEY_DEDUPE_TASKS in config[CONF]
         )
+        self._migrate_checkpoint = migrate_checkpoint
         self.trigger_to_nodes = trigger_to_nodes
-        self.checkpoint_every_step = checkpoint_every_step
+        self.checkpoint_during = checkpoint_during
         self.debug = debug
         if self.stream is not None and CONFIG_KEY_STREAM in config[CONF]:
             self.stream = DuplexStream(self.stream, config[CONF][CONFIG_KEY_STREAM])
@@ -280,6 +286,12 @@ class PregelLoop(LoopProtocol):
             )
         else:
             self.checkpoint_config = self.config
+        if thread_id := self.checkpoint_config[CONF].get(CONFIG_KEY_THREAD_ID):
+            if not isinstance(thread_id, str):
+                self.checkpoint_config = patch_configurable(
+                    self.checkpoint_config,
+                    {CONFIG_KEY_THREAD_ID: str(thread_id)},
+                )
         self.checkpoint_ns = (
             tuple(cast(str, self.config[CONF][CONFIG_KEY_CHECKPOINT_NS]).split(NS_SEP))
             if self.config[CONF].get(CONFIG_KEY_CHECKPOINT_NS)
@@ -291,29 +303,19 @@ class PregelLoop(LoopProtocol):
         """Put writes for a task, to be read by the next tick."""
         if not writes:
             return
+        # always checkpoint writes containing Send, as they are fetched from the
+        # parent checkpoint, not the current one
+        checkpoint_during = self.checkpoint_during or any(w[0] == TASKS for w in writes)
         # deduplicate writes to special channels, last write wins
         if all(w[0] in WRITES_IDX_MAP for w in writes):
             writes = list({w[0]: w for w in writes}.values())
+        # remove existing writes for this task
+        self.checkpoint_pending_writes = [
+            w for w in self.checkpoint_pending_writes if w[0] != task_id
+        ]
         # save writes
-        for c, v in writes:
-            if (
-                c in WRITES_IDX_MAP
-                and (
-                    idx := next(
-                        (
-                            i
-                            for i, w in enumerate(self.checkpoint_pending_writes)
-                            if w[0] == task_id and w[1] == c
-                        ),
-                        None,
-                    )
-                )
-                is not None
-            ):
-                self.checkpoint_pending_writes[idx] = (task_id, c, v)
-            else:
-                self.checkpoint_pending_writes.append((task_id, c, v))
-        if self.checkpointer_put_writes is not None:
+        self.checkpoint_pending_writes.extend((task_id, c, v) for c, v in writes)
+        if checkpoint_during and self.checkpointer_put_writes is not None:
             config = patch_configurable(
                 self.checkpoint_config,
                 {
@@ -346,6 +348,46 @@ class PregelLoop(LoopProtocol):
         if hasattr(self, "tasks"):
             self._output_writes(task_id, writes)
 
+    def _put_pending_writes(self) -> None:
+        if self.checkpointer_put_writes is None:
+            return
+        if not self.checkpoint_pending_writes:
+            return
+        # patch config
+        config = patch_configurable(
+            self.checkpoint_config,
+            {
+                CONFIG_KEY_CHECKPOINT_NS: self.config[CONF].get(
+                    CONFIG_KEY_CHECKPOINT_NS, ""
+                ),
+                CONFIG_KEY_CHECKPOINT_ID: self.checkpoint["id"],
+            },
+        )
+        # group by task id
+        by_task = defaultdict(list)
+        for task_id, channel, value in self.checkpoint_pending_writes:
+            by_task[task_id].append((channel, value))
+        # submit writes to checkpointer
+        for task_id, writes in by_task.items():
+            if self.checkpointer_put_writes_accepts_task_path and hasattr(
+                self, "tasks"
+            ):
+                task = self.tasks.get(task_id)
+                self.submit(
+                    self.checkpointer_put_writes,
+                    config,
+                    writes,
+                    task_id,
+                    task_path_str(task.path) if task else "",
+                )
+            else:
+                self.submit(
+                    self.checkpointer_put_writes,
+                    config,
+                    writes,
+                    task_id,
+                )
+
     def accept_push(
         self, task: PregelExecutableTask, write_idx: int, call: Optional[Call] = None
     ) -> Optional[PregelExecutableTask]:
@@ -708,29 +750,43 @@ class PregelLoop(LoopProtocol):
 
     def _put_checkpoint(self, metadata: CheckpointMetadata) -> None:
         # assign step and parents
-        metadata["step"] = self.step
-        metadata["parents"] = self.config[CONF].get(CONFIG_KEY_CHECKPOINT_MAP, {})
-        # debug flag
-        if self.debug:
-            print_step_checkpoint(
-                metadata,
-                self.channels,
-                (
-                    [self.stream_keys]
-                    if isinstance(self.stream_keys, str)
-                    else self.stream_keys
-                ),
-            )
-        # bail if no checkpointer
-        if self._checkpointer_put_after_previous is not None:
-            for k, v in self.config["metadata"].items():
-                metadata.setdefault(k, v)  # type: ignore
-
-            # create new checkpoint
-            self.checkpoint = create_checkpoint(
-                self.checkpoint, self.channels, self.step
-            )
+        exiting = metadata is self.checkpoint_metadata
+        if exiting and self.checkpoint["id"] == self.checkpoint_id_saved:
+            # checkpoint already saved
+            return
+        if not exiting:
+            metadata["step"] = self.step
+            metadata["parents"] = self.config[CONF].get(CONFIG_KEY_CHECKPOINT_MAP, {})
             self.checkpoint_metadata = metadata
+            # debug flag
+            if self.debug:
+                print_step_checkpoint(
+                    metadata,
+                    self.channels,
+                    (
+                        [self.stream_keys]
+                        if isinstance(self.stream_keys, str)
+                        else self.stream_keys
+                    ),
+                )
+            self.checkpoint_id_prev = self.checkpoint["id"] if self.step > -1 else None
+        # do checkpoint?
+        do_checkpoint = self._checkpointer_put_after_previous is not None and (
+            exiting or self.checkpoint_during
+        )
+        # create new checkpoint
+        self.checkpoint = create_checkpoint(
+            self.checkpoint,
+            self.channels if do_checkpoint else None,
+            self.step,
+            id=self.checkpoint["id"] if exiting else None,
+        )
+        # bail if no checkpointer
+        if do_checkpoint and self._checkpointer_put_after_previous is not None:
+            for k, v in self.config["metadata"].items():
+                if k in EXCLUDED_METADATA_KEYS:
+                    continue
+                metadata.setdefault(k, v)  # type: ignore
 
             self.prev_checkpoint_config = (
                 self.checkpoint_config
@@ -742,6 +798,8 @@ class PregelLoop(LoopProtocol):
                 **self.checkpoint_config,
                 CONF: {
                     **self.checkpoint_config[CONF],
+                    # this is guaranteed to be set by code above
+                    CONFIG_KEY_CHECKPOINT_ID: self.checkpoint_id_prev,
                     CONFIG_KEY_CHECKPOINT_NS: self.config[CONF].get(
                         CONFIG_KEY_CHECKPOINT_NS, ""
                     ),
@@ -772,8 +830,9 @@ class PregelLoop(LoopProtocol):
                     CONFIG_KEY_CHECKPOINT_ID: self.checkpoint["id"],
                 },
             }
-        # increment step
-        self.step += 1
+        if not exiting:
+            # increment step
+            self.step += 1
 
     def _update_mv(self, key: str, values: Sequence[Any]) -> None:
         raise NotImplementedError
@@ -784,6 +843,10 @@ class PregelLoop(LoopProtocol):
         exc_value: Optional[BaseException],
         traceback: Optional[TracebackType],
     ) -> Optional[bool]:
+        # persist current checkpoint and writes
+        if not self.checkpoint_during:
+            self._put_checkpoint(self.checkpoint_metadata)
+            self._put_pending_writes()
         # suppress interrupt
         suppress = isinstance(exc_value, GraphInterrupt) and not self.is_nested
         if suppress:
@@ -900,7 +963,9 @@ class SyncPregelLoop(PregelLoop, ContextManager):
         stream_keys: Union[str, Sequence[str]] = EMPTY_SEQ,
         input_model: Optional[Type[BaseModel]] = None,
         debug: bool = False,
+        migrate_checkpoint: Optional[Callable[[Checkpoint], None]] = None,
         trigger_to_nodes: Optional[Mapping[str, Sequence[str]]] = None,
+        checkpoint_during: bool = True,
     ) -> None:
         super().__init__(
             input,
@@ -917,7 +982,9 @@ class SyncPregelLoop(PregelLoop, ContextManager):
             interrupt_before=interrupt_before,
             manager=manager,
             debug=debug,
+            migrate_checkpoint=migrate_checkpoint,
             trigger_to_nodes=trigger_to_nodes,
+            checkpoint_during=checkpoint_during,
         )
         self.stack = ExitStack()
         if checkpointer:
@@ -983,18 +1050,21 @@ class SyncPregelLoop(PregelLoop, ContextManager):
             saved = None
         if saved is None:
             saved = CheckpointTuple(
-                self.config, empty_checkpoint(), {"step": -2}, None, []
+                self.checkpoint_config, empty_checkpoint(), {"step": -2}, None, []
             )
+        elif self._migrate_checkpoint is not None:
+            self._migrate_checkpoint(saved.checkpoint)
         self.checkpoint_config = {
-            **self.config,
+            **self.checkpoint_config,
             **saved.config,
             CONF: {
                 CONFIG_KEY_CHECKPOINT_NS: "",
-                **self.config.get(CONF, {}),
+                **self.checkpoint_config.get(CONF, {}),
                 **saved.config.get(CONF, {}),
             },
         }
         self.prev_checkpoint_config = saved.parent_config
+        self.checkpoint_id_saved = saved.checkpoint["id"]
         self.checkpoint = saved.checkpoint
         self.checkpoint_metadata = saved.metadata
         self.checkpoint_pending_writes = (
@@ -1043,7 +1113,9 @@ class AsyncPregelLoop(PregelLoop, AsyncContextManager):
         stream_keys: Union[str, Sequence[str]] = EMPTY_SEQ,
         input_model: Optional[Type[BaseModel]] = None,
         debug: bool = False,
+        migrate_checkpoint: Optional[Callable[[Checkpoint], None]] = None,
         trigger_to_nodes: Optional[Mapping[str, Sequence[str]]] = None,
+        checkpoint_during: bool = True,
     ) -> None:
         super().__init__(
             input,
@@ -1060,7 +1132,9 @@ class AsyncPregelLoop(PregelLoop, AsyncContextManager):
             interrupt_before=interrupt_before,
             manager=manager,
             debug=debug,
+            migrate_checkpoint=migrate_checkpoint,
             trigger_to_nodes=trigger_to_nodes,
+            checkpoint_during=checkpoint_during,
         )
         self.stack = AsyncExitStack()
         if checkpointer:
@@ -1126,18 +1200,21 @@ class AsyncPregelLoop(PregelLoop, AsyncContextManager):
             saved = None
         if saved is None:
             saved = CheckpointTuple(
-                self.config, empty_checkpoint(), {"step": -2}, None, []
+                self.checkpoint_config, empty_checkpoint(), {"step": -2}, None, []
             )
+        elif self._migrate_checkpoint is not None:
+            self._migrate_checkpoint(saved.checkpoint)
         self.checkpoint_config = {
-            **self.config,
+            **self.checkpoint_config,
             **saved.config,
             CONF: {
                 CONFIG_KEY_CHECKPOINT_NS: "",
-                **self.config.get(CONF, {}),
+                **self.checkpoint_config.get(CONF, {}),
                 **saved.config.get(CONF, {}),
             },
         }
         self.prev_checkpoint_config = saved.parent_config
+        self.checkpoint_id_saved = saved.checkpoint["id"]
         self.checkpoint = saved.checkpoint
         self.checkpoint_metadata = saved.metadata
         self.checkpoint_pending_writes = (

libs/langgraph/langgraph/pregel/messages.py

@@ -7,6 +7,7 @@ from typing import (
     List,
     Optional,
     Sequence,
+    TypeVar,
     Union,
     cast,
 )
@@ -15,11 +16,16 @@ from uuid import UUID, uuid4
 from langchain_core.callbacks import BaseCallbackHandler
 from langchain_core.messages import BaseMessage
 from langchain_core.outputs import ChatGenerationChunk, LLMResult
-from langchain_core.tracers._streaming import T, _StreamingCallbackHandler
 
 from langgraph.constants import NS_SEP, TAG_HIDDEN, TAG_NOSTREAM
-from langgraph.types import StreamChunk
+from langgraph.types import Command, StreamChunk
 
+try:
+    from langchain_core.tracers._streaming import _StreamingCallbackHandler
+except ImportError:
+    _StreamingCallbackHandler = object  # type: ignore
+
+T = TypeVar("T")
 Meta = tuple[tuple[str, ...], dict[str, Any]]
 
 
@@ -147,6 +153,17 @@ class StreamMessagesHandler(BaseCallbackHandler, _StreamingCallbackHandler):
         **kwargs: Any,
     ) -> Any:
         if meta := self.metadata.pop(run_id, None):
+            if isinstance(response, Command):
+                response = response.update
+
+            if isinstance(response, Sequence) and any(
+                isinstance(value, Command) for value in response
+            ):
+                response = [
+                    value.update if isinstance(value, Command) else value
+                    for value in response
+                ]
+
             if isinstance(response, BaseMessage):
                 self._emit(meta, response, dedupe=True)
             elif isinstance(response, Sequence):

libs/langgraph/langgraph/pregel/read.py

@@ -30,6 +30,7 @@ from langgraph.utils.config import merge_configs
 from langgraph.utils.runnable import RunnableCallable, RunnableSeq
 
 READ_TYPE = Callable[[Union[str, Sequence[str]], bool], Union[Any, dict[str, Any]]]
+INPUT_CACHE_KEY_TYPE = tuple[Callable[..., Any], tuple[str, ...]]
 
 
 class ChannelRead(RunnableCallable):
@@ -67,6 +68,7 @@ class ChannelRead(RunnableCallable):
             afunc=self._aread,
             tags=tags,
             name=None,
+            trace=False,
             func_accepts_config=True,
         )
         self.fresh = fresh
@@ -144,8 +146,8 @@ class PregelNode(Runnable):
     """The main logic of the node. This will be invoked with the input from 
     `channels`."""
 
-    retry_policy: Optional[RetryPolicy]
-    """The retry policy to use when invoking the node."""
+    retry_policy: Optional[Sequence[RetryPolicy]]
+    """The retry policies to use when invoking the node."""
 
     tags: Optional[Sequence[str]]
     """Tags to attach to the node for tracing."""
@@ -166,7 +168,7 @@ class PregelNode(Runnable):
         tags: Optional[list[str]] = None,
         metadata: Optional[Mapping[str, Any]] = None,
         bound: Optional[Runnable[Any, Any]] = None,
-        retry_policy: Optional[RetryPolicy] = None,
+        retry_policy: Optional[Union[RetryPolicy, Sequence[RetryPolicy]]] = None,
         subgraphs: Optional[Sequence[PregelProtocol]] = None,
     ) -> None:
         self.channels = channels
@@ -174,7 +176,10 @@ class PregelNode(Runnable):
         self.mapper = mapper
         self.writers = writers or []
         self.bound = bound if bound is not None else DEFAULT_BOUND
-        self.retry_policy = retry_policy
+        if isinstance(retry_policy, RetryPolicy):
+            self.retry_policy: Sequence[RetryPolicy] = (retry_policy,)
+        else:
+            self.retry_policy = retry_policy
         self.tags = tags
         self.metadata = metadata
         if subgraphs is not None:
@@ -228,6 +233,17 @@ class PregelNode(Runnable):
         else:
             return self.bound
 
+    @cached_property
+    def input_cache_key(self) -> INPUT_CACHE_KEY_TYPE:
+        """Get a cache key for the input to the node.
+        This is used to avoid calculating the same input multiple times."""
+        return (
+            self.mapper,
+            tuple(f"{key}:{value}" for key, value in self.channels.items())
+            if isinstance(self.channels, dict)
+            else tuple(self.channels),
+        )
+
     def join(self, channels: Sequence[str]) -> PregelNode:
         assert isinstance(channels, list) or isinstance(
             channels, tuple

libs/langgraph/langgraph/pregel/remote.py

@@ -10,7 +10,6 @@ from typing import (
     cast,
 )
 
-import orjson
 from langchain_core.runnables import RunnableConfig
 from langchain_core.runnables.graph import (
     Edge as DrawableEdge,
@@ -35,6 +34,8 @@ from typing_extensions import Self
 from langgraph.checkpoint.base import CheckpointMetadata
 from langgraph.constants import (
     CONF,
+    CONFIG_KEY_CHECKPOINT_ID,
+    CONFIG_KEY_CHECKPOINT_MAP,
     CONFIG_KEY_CHECKPOINT_NS,
     CONFIG_KEY_STREAM,
     INTERRUPT,
@@ -46,6 +47,14 @@ from langgraph.pregel.types import All, PregelTask, StateSnapshot, StreamMode
 from langgraph.types import Command, Interrupt, StreamProtocol
 from langgraph.utils.config import merge_configs
 
+CONF_DROPLIST = frozenset(
+    (
+        CONFIG_KEY_CHECKPOINT_MAP,
+        CONFIG_KEY_CHECKPOINT_ID,
+        CONFIG_KEY_CHECKPOINT_NS,
+    ),
+)
+
 
 class RemoteException(Exception):
     """Exception raised when an error occurs in the remote graph."""
@@ -290,47 +299,26 @@ class RemoteGraph(PregelProtocol):
         }
 
     def _sanitize_config(self, config: RunnableConfig) -> RunnableConfig:
-        reserved_configurable_keys = frozenset(
-            [
-                "callbacks",
-                "checkpoint_map",
-                "checkpoint_id",
-                "checkpoint_ns",
-            ]
-        )
-
-        def _sanitize_obj(obj: Any) -> Any:
-            """Remove non-JSON serializable fields from the given object."""
-            if isinstance(obj, dict):
-                return {k: _sanitize_obj(v) for k, v in obj.items()}
-            elif isinstance(obj, list):
-                return [_sanitize_obj(v) for v in obj]
-            else:
-                try:
-                    orjson.dumps(obj)
-                    return obj
-                except orjson.JSONEncodeError:
-                    return None
-
-        # Remove non-JSON serializable fields from the config.
-        config = _sanitize_obj(config)
-
-        # Only include configurable keys that are not reserved and
-        # not starting with "__pregel_" prefix.
-        new_configurable = {
-            k: v
-            for k, v in config["configurable"].items()
-            if k not in reserved_configurable_keys and not k.startswith("__pregel_")
-        }
-
-        sanitized: RunnableConfig = {
-            "tags": config.get("tags") or [],
-            "metadata": config.get("metadata") or {},
-            "configurable": new_configurable,
-        }
+        """Sanitize the config to remove non-serializable fields."""
+        sanitized: RunnableConfig = {}
         if "recursion_limit" in config:
             sanitized["recursion_limit"] = config["recursion_limit"]
-
+        if "tags" in config:
+            sanitized["tags"] = [tag for tag in config["tags"] if isinstance(tag, str)]
+        if "metadata" in config:
+            sanitized["metadata"] = {}
+            for k, v in config["metadata"].items():
+                if isinstance(k, str) and isinstance(v, (str, int, float, bool)):
+                    sanitized["metadata"][k] = v
+        if "configurable" in config:
+            sanitized["configurable"] = {}
+            for k, v in config["configurable"].items():
+                if (
+                    isinstance(k, str)
+                    and k not in CONF_DROPLIST
+                    and isinstance(v, (str, int, float, bool))
+                ):
+                    sanitized["configurable"][k] = v
         return sanitized
 
     def get_state(
@@ -654,9 +642,10 @@ class RemoteGraph(PregelProtocol):
             # raise interrupt or errors
             if chunk.event.startswith("updates"):
                 if isinstance(chunk.data, dict) and INTERRUPT in chunk.data:
-                    raise GraphInterrupt(
-                        [Interrupt(**i) for i in chunk.data[INTERRUPT]]
-                    )
+                    if caller_ns:
+                        raise GraphInterrupt(
+                            [Interrupt(**i) for i in chunk.data[INTERRUPT]]
+                        )
             elif chunk.event.startswith("error"):
                 raise RemoteException(chunk.data)
             # filter for what was actually requested
@@ -748,9 +737,10 @@ class RemoteGraph(PregelProtocol):
             # raise interrupt or errors
             if chunk.event.startswith("updates"):
                 if isinstance(chunk.data, dict) and INTERRUPT in chunk.data:
-                    raise GraphInterrupt(
-                        [Interrupt(**i) for i in chunk.data[INTERRUPT]]
-                    )
+                    if caller_ns:
+                        raise GraphInterrupt(
+                            [Interrupt(**i) for i in chunk.data[INTERRUPT]]
+                        )
             elif chunk.event.startswith("error"):
                 raise RemoteException(chunk.data)
             # filter for what was actually requested

libs/langgraph/langgraph/pregel/retry.py

@@ -22,12 +22,11 @@ SUPPORTS_EXC_NOTES = sys.version_info >= (3, 11)
 
 def run_with_retry(
     task: PregelExecutableTask,
-    retry_policy: Optional[RetryPolicy],
+    retry_policy: Optional[Sequence[RetryPolicy]],
     configurable: Optional[dict[str, Any]] = None,
 ) -> None:
     """Run a task with retries."""
     retry_policy = task.retry_policy or retry_policy
-    interval = retry_policy.initial_interval if retry_policy else 0
     attempts = 0
     config = task.config
     if configurable is not None:
@@ -63,38 +62,39 @@ def run_with_retry(
                 exc.add_note(f"During task with name '{task.name}' and id '{task.id}'")
             if retry_policy is None:
                 raise
+
+            # Check which retry policy applies to this exception
+            matching_policy = None
+            for policy in retry_policy:
+                if _should_retry_on(policy, exc):
+                    matching_policy = policy
+                    break
+
+            if not matching_policy:
+                raise
+
             # increment attempts
             attempts += 1
-            # check if we should retry
-            if isinstance(retry_policy.retry_on, Sequence):
-                if not isinstance(exc, tuple(retry_policy.retry_on)):
-                    raise
-            elif isinstance(retry_policy.retry_on, type) and issubclass(
-                retry_policy.retry_on, Exception
-            ):
-                if not isinstance(exc, retry_policy.retry_on):
-                    raise
-            elif callable(retry_policy.retry_on):
-                if not retry_policy.retry_on(exc):  # type: ignore[call-arg]
-                    raise
-            else:
-                raise TypeError(
-                    "retry_on must be an Exception class, a list or tuple of Exception classes, or a callable"
-                )
             # check if we should give up
-            if attempts >= retry_policy.max_attempts:
+            if attempts >= matching_policy.max_attempts:
                 raise
             # sleep before retrying
+            interval = matching_policy.initial_interval
+            # Apply backoff factor based on attempt count
             interval = min(
-                retry_policy.max_interval,
-                interval * retry_policy.backoff_factor,
+                matching_policy.max_interval,
+                interval * (matching_policy.backoff_factor ** (attempts - 1)),
             )
-            time.sleep(
-                interval + random.uniform(0, 1) if retry_policy.jitter else interval
+
+            # Apply jitter if configured
+            sleep_time = (
+                interval + random.uniform(0, 1) if matching_policy.jitter else interval
             )
+            time.sleep(sleep_time)
+
             # log the retry
             logger.info(
-                f"Retrying task {task.name} after {interval:.2f} seconds (attempt {attempts}) after {exc.__class__.__name__} {exc}",
+                f"Retrying task {task.name} after {sleep_time:.2f} seconds (attempt {attempts}) after {exc.__class__.__name__} {exc}",
                 exc_info=exc,
             )
             # signal subgraphs to resume (if available)
@@ -103,13 +103,12 @@ def run_with_retry(
 
 async def arun_with_retry(
     task: PregelExecutableTask,
-    retry_policy: Optional[RetryPolicy],
+    retry_policies: Optional[Sequence[RetryPolicy]],
     stream: bool = False,
     configurable: Optional[dict[str, Any]] = None,
 ) -> None:
     """Run a task asynchronously with retries."""
-    retry_policy = task.retry_policy or retry_policy
-    interval = retry_policy.initial_interval if retry_policy else 0
+    retry_policies = task.retry_policy or retry_policies
     attempts = 0
     config = task.config
     if configurable is not None:
@@ -149,41 +148,58 @@ async def arun_with_retry(
         except Exception as exc:
             if SUPPORTS_EXC_NOTES:
                 exc.add_note(f"During task with name '{task.name}' and id '{task.id}'")
-            if retry_policy is None:
+            if retry_policies is None:
                 raise
+
+            # Check which retry policy applies to this exception
+            matching_policy = None
+            for policy in retry_policies:
+                if _should_retry_on(policy, exc):
+                    matching_policy = policy
+                    break
+
+            if not matching_policy:
+                raise
+
             # increment attempts
             attempts += 1
-            # check if we should retry
-            if isinstance(retry_policy.retry_on, Sequence):
-                if not isinstance(exc, tuple(retry_policy.retry_on)):
-                    raise
-            elif isinstance(retry_policy.retry_on, type) and issubclass(
-                retry_policy.retry_on, Exception
-            ):
-                if not isinstance(exc, retry_policy.retry_on):
-                    raise
-            elif callable(retry_policy.retry_on):
-                if not retry_policy.retry_on(exc):  # type: ignore[call-arg]
-                    raise
-            else:
-                raise TypeError(
-                    "retry_on must be an Exception class, a list or tuple of Exception classes, or a callable"
-                )
             # check if we should give up
-            if attempts >= retry_policy.max_attempts:
+            if attempts >= matching_policy.max_attempts:
                 raise
             # sleep before retrying
+            interval = matching_policy.initial_interval
+            # Apply backoff factor based on attempt count
             interval = min(
-                retry_policy.max_interval,
-                interval * retry_policy.backoff_factor,
+                matching_policy.max_interval,
+                interval * (matching_policy.backoff_factor ** (attempts - 1)),
             )
-            await asyncio.sleep(
-                interval + random.uniform(0, 1) if retry_policy.jitter else interval
+
+            # Apply jitter if configured
+            sleep_time = (
+                interval + random.uniform(0, 1) if matching_policy.jitter else interval
             )
+            await asyncio.sleep(sleep_time)
+
             # log the retry
             logger.info(
-                f"Retrying task {task.name} after {interval:.2f} seconds (attempt {attempts}) after {exc.__class__.__name__} {exc}",
+                f"Retrying task {task.name} after {sleep_time:.2f} seconds (attempt {attempts}) after {exc.__class__.__name__} {exc}",
                 exc_info=exc,
             )
             # signal subgraphs to resume (if available)
             config = patch_configurable(config, {CONFIG_KEY_RESUMING: True})
+
+
+def _should_retry_on(retry_policy: RetryPolicy, exc: Exception) -> bool:
+    """Check if the given exception should be retried based on the retry policy."""
+    if isinstance(retry_policy.retry_on, Sequence):
+        return isinstance(exc, tuple(retry_policy.retry_on))
+    elif isinstance(retry_policy.retry_on, type) and issubclass(
+        retry_policy.retry_on, Exception
+    ):
+        return isinstance(exc, retry_policy.retry_on)
+    elif callable(retry_policy.retry_on):
+        return retry_policy.retry_on(exc)  # type: ignore[call-arg]
+    else:
+        raise TypeError(
+            "retry_on must be an Exception class, a list or tuple of Exception classes, or a callable"
+        )

libs/langgraph/langgraph/pregel/runner.py

@@ -140,7 +140,7 @@ class PregelRunner:
         *,
         reraise: bool = True,
         timeout: Optional[float] = None,
-        retry_policy: Optional[RetryPolicy] = None,
+        retry_policy: Optional[Sequence[RetryPolicy]] = None,
         get_waiter: Optional[Callable[[], concurrent.futures.Future[None]]] = None,
     ) -> Iterator[None]:
         tasks = tuple(tasks)
@@ -269,7 +269,7 @@ class PregelRunner:
         *,
         reraise: bool = True,
         timeout: Optional[float] = None,
-        retry_policy: Optional[RetryPolicy] = None,
+        retry_policy: Optional[Sequence[RetryPolicy]] = None,
         get_waiter: Optional[Callable[[], asyncio.Future[None]]] = None,
     ) -> AsyncIterator[None]:
         loop = asyncio.get_event_loop()
@@ -519,7 +519,7 @@ def _call(
     func: Callable[[Any], Union[Awaitable[Any], Any]],
     input: Any,
     *,
-    retry: Optional[RetryPolicy] = None,
+    retry: Optional[Sequence[RetryPolicy]] = None,
     callbacks: Callbacks = None,
     futures: weakref.ref[FuturesDict],
     schedule_task: weakref.ref[
@@ -600,7 +600,7 @@ def _acall(
     func: Callable[[Any], Union[Awaitable[Any], Any]],
     input: Any,
     *,
-    retry: Optional[RetryPolicy] = None,
+    retry: Optional[Sequence[RetryPolicy]] = None,
     callbacks: Callbacks = None,
     # injected dependencies
     futures: weakref.ref[FuturesDict],

libs/langgraph/langgraph/pregel/write.py

@@ -54,14 +54,14 @@ class ChannelWrite(RunnableCallable):
         self,
         writes: Sequence[Union[ChannelWriteEntry, ChannelWriteTupleEntry, Send]],
         *,
-        tags: Optional[Sequence[str]] = None,
+        tags: Optional[Sequence[str]] = None,  # ignored
         require_at_least_one_of: Optional[Sequence[str]] = None,  # ignored
     ):
         super().__init__(
             func=self._write,
             afunc=self._awrite,
             name=None,
-            tags=tags,
+            trace=False,
             func_accepts_config=True,
         )
         self.writes = cast(
@@ -152,6 +152,8 @@ class ChannelWrite(RunnableCallable):
                 tuples.append((w.channel, value))
             else:
                 raise ValueError(f"Invalid write entry: {w}")
+        # if we want to persist writes found before hitting a ParentCommand
+        # can move this to a finally block
         write: TYPE_SEND = config[CONF][CONFIG_KEY_SEND]
         write(tuples)
 

libs/langgraph/langgraph/types.py

@@ -23,6 +23,7 @@ from langchain_core.runnables import Runnable, RunnableConfig
 from typing_extensions import Self
 
 from langgraph.checkpoint.base import BaseCheckpointSaver, CheckpointMetadata
+from langgraph.utils.fields import get_update_as_tuples
 
 if TYPE_CHECKING:
     from langgraph.pregel.protocol import PregelProtocol
@@ -75,6 +76,10 @@ def default_retry_on(exc: Exception) -> bool:
 
     if isinstance(exc, ConnectionError):
         return True
+    if isinstance(exc, httpx.HTTPStatusError):
+        return 500 <= exc.response.status_code < 600
+    if isinstance(exc, requests.HTTPError):
+        return 500 <= exc.response.status_code < 600 if exc.response else True
     if isinstance(
         exc,
         (
@@ -93,10 +98,6 @@ def default_retry_on(exc: Exception) -> bool:
         ),
     ):
         return False
-    if isinstance(exc, httpx.HTTPStatusError):
-        return 500 <= exc.response.status_code < 600
-    if isinstance(exc, requests.HTTPError):
-        return 500 <= exc.response.status_code < 600 if exc.response else True
     return True
 
 
@@ -172,7 +173,7 @@ class PregelExecutableTask:
     writes: deque[tuple[str, Any]]
     config: RunnableConfig
     triggers: Sequence[str]
-    retry_policy: Optional[RetryPolicy]
+    retry_policy: Optional[Sequence[RetryPolicy]]
     cache_policy: Optional[CachePolicy]
     id: str
     path: tuple[Union[str, int, tuple], ...]
@@ -318,7 +319,7 @@ class Command(Generic[N], ToolOutputMixin):
         ):
             return self.update
         elif hints := get_type_hints(type(self.update)):
-            return [(k, getattr(self.update, k)) for k in hints]
+            return get_update_as_tuples(self.update, tuple(hints.keys()))
         elif self.update is not None:
             return [("__root__", self.update)]
         else:

libs/langgraph/langgraph/utils/fields.py

@@ -1,8 +1,14 @@
 import dataclasses
-from typing import Any, Generator, Optional, Type, Union, get_type_hints
+from typing import Any, Generator, Optional, Sequence, Type, Union, get_type_hints
 
+from pydantic import BaseModel
+from pydantic.v1 import BaseModel as BaseModelV1
 from typing_extensions import Annotated, NotRequired, ReadOnly, Required, get_origin
 
+# NOTE: this is redefined here separately from langgraph.constants
+# to avoid a circular import
+MISSING = object()
+
 
 def _is_optional_type(type_: Any) -> bool:
     """Check if a type is Optional."""
@@ -147,3 +153,33 @@ def get_enhanced_type_hints(
             pass
 
         yield name, typ, default, description
+
+
+def get_update_as_tuples(input: Any, keys: Sequence[str]) -> list[tuple[str, Any]]:
+    """Get Pydantic state update as a list of (key, value) tuples."""
+    # Pydantic v1
+    if isinstance(input, BaseModelV1):
+        keep: Optional[set[str]] = input.__fields_set__
+        defaults = {k: v.default for k, v in input.__fields__.items()}
+    # Pydantic v2
+    elif isinstance(input, BaseModel):
+        keep = input.model_fields_set
+        defaults = {k: v.default for k, v in input.model_fields.items()}
+    else:
+        keep = None
+        defaults = {}
+
+    # NOTE: This behavior for Pydantic is somewhat inelegant,
+    # but we keep around for backwards compatibility
+    # if input is a Pydantic model, only update values
+    # that are different from the default values or in the keep set
+    return [
+        (k, value)
+        for k in keys
+        if (value := getattr(input, k, MISSING)) is not MISSING
+        and (
+            value is not None
+            or defaults.get(k, MISSING) is not None
+            or (keep is not None and k in keep)
+        )
+    ]

libs/langgraph/langgraph/utils/runnable.py

@@ -36,7 +36,7 @@ from langchain_core.runnables.config import (
     var_child_runnable_config,
 )
 from langchain_core.runnables.utils import Input, Output
-from langchain_core.tracers._streaming import _StreamingCallbackHandler
+from langchain_core.tracers.langchain import LangChainTracer
 from typing_extensions import TypeGuard
 
 from langgraph.constants import (
@@ -54,60 +54,41 @@ from langgraph.utils.config import (
     patch_config,
 )
 
+try:
+    from langchain_core.tracers._streaming import _StreamingCallbackHandler
+except ImportError:
+    _StreamingCallbackHandler = None  # type: ignore
+
 
 def _set_config_context(
-    config: RunnableConfig,
-) -> tuple[Token[Optional[RunnableConfig]], Optional[dict[str, Any]]]:
+    config: RunnableConfig, run: Any = None
+) -> Token[Optional[RunnableConfig]]:
     """Set the child Runnable config + tracing context.
 
     Args:
         config (RunnableConfig): The config to set.
     """
-    from langchain_core.tracers.langchain import LangChainTracer
-
     config_token = var_child_runnable_config.set(config)
-    current_context = None
-    if (
-        (callbacks := config.get("callbacks"))
-        and (
-            parent_run_id := getattr(callbacks, "parent_run_id", None)
-        )  # Is callback manager
-        and (
-            tracer := next(
-                (
-                    handler
-                    for handler in getattr(callbacks, "handlers", [])
-                    if isinstance(handler, LangChainTracer)
-                ),
-                None,
-            )
-        )
-        and (run := tracer.run_map.get(str(parent_run_id)))
-    ):
-        from langsmith.run_helpers import _set_tracing_context, get_tracing_context
+    if run is not None:
+        from langsmith.run_helpers import _set_tracing_context
 
-        current_context = get_tracing_context()
         _set_tracing_context({"parent": run})
-    return config_token, current_context
+    return config_token
 
 
-@contextmanager
-def set_config_context(config: RunnableConfig) -> Generator[Context, None, None]:
+def _unset_config_context(
+    token: Token[Optional[RunnableConfig]], run: Any = None
+) -> None:
     """Set the child Runnable config + tracing context.
 
     Args:
         config (RunnableConfig): The config to set.
     """
-    from langsmith.run_helpers import _set_tracing_context
+    var_child_runnable_config.reset(token)
+    if run is not None:
+        from langsmith.run_helpers import _set_tracing_context
 
-    ctx = copy_context()
-    config_token, _ = ctx.run(_set_config_context, config)
-    try:
-        yield ctx
-    finally:
-        ctx.run(var_child_runnable_config.reset, config_token)
-        ctx.run(
-            _set_tracing_context,
+        _set_tracing_context(
             {
                 "parent": None,
                 "project_name": None,
@@ -115,10 +96,27 @@ def set_config_context(config: RunnableConfig) -> Generator[Context, None, None]
                 "metadata": None,
                 "enabled": None,
                 "client": None,
-            },
+            }
         )
 
 
+@contextmanager
+def set_config_context(
+    config: RunnableConfig, run: Any = None
+) -> Generator[Context, None, None]:
+    """Set the child Runnable config + tracing context.
+
+    Args:
+        config (RunnableConfig): The config to set.
+    """
+    ctx = copy_context()
+    config_token = ctx.run(_set_config_context, config, run)
+    try:
+        yield ctx
+    finally:
+        ctx.run(_unset_config_context, config_token, run)
+
+
 # Before Python 3.11 native StrEnum is not available
 class StrEnum(str, enum.Enum):
     """A string enum."""
@@ -359,7 +357,15 @@ class RunnableCallable(Runnable):
             )
             try:
                 child_config = patch_config(config, callbacks=run_manager.get_child())
-                with set_config_context(child_config) as context:
+                # get the run
+                for h in run_manager.handlers:
+                    if isinstance(h, LangChainTracer):
+                        run = h.run_map.get(str(run_manager.run_id))
+                        break
+                else:
+                    run = None
+                # run in context
+                with set_config_context(child_config, run) as context:
                     ret = context.run(self.func, *args, **kwargs)
             except BaseException as e:
                 run_manager.on_chain_error(e)
@@ -367,9 +373,8 @@ class RunnableCallable(Runnable):
             else:
                 run_manager.on_chain_end(ret)
         else:
-            with set_config_context(config) as context:
-                ret = context.run(self.func, *args, **kwargs)
-        if isinstance(ret, Runnable) and self.recurse:
+            ret = self.func(*args, **kwargs)
+        if self.recurse and isinstance(ret, Runnable):
             return ret.invoke(input, config)
         return ret
 
@@ -413,25 +418,26 @@ class RunnableCallable(Runnable):
             )
             try:
                 child_config = patch_config(config, callbacks=run_manager.get_child())
-                with set_config_context(child_config) as context:
-                    coro = cast(Coroutine[None, None, Any], self.afunc(*args, **kwargs))
-                    if ASYNCIO_ACCEPTS_CONTEXT:
-                        ret = await asyncio.create_task(coro, context=context)
+                coro = cast(Coroutine[None, None, Any], self.afunc(*args, **kwargs))
+                if ASYNCIO_ACCEPTS_CONTEXT:
+                    for h in run_manager.handlers:
+                        if isinstance(h, LangChainTracer):
+                            run = h.run_map.get(str(run_manager.run_id))
+                            break
                     else:
-                        ret = await coro
+                        run = None
+                    with set_config_context(child_config, run) as context:
+                        ret = await asyncio.create_task(coro, context=context)
+                else:
+                    ret = await coro
             except BaseException as e:
                 await run_manager.on_chain_error(e)
                 raise
             else:
                 await run_manager.on_chain_end(ret)
         else:
-            with set_config_context(config) as context:
-                if ASYNCIO_ACCEPTS_CONTEXT:
-                    coro = cast(Coroutine[None, None, Any], self.afunc(*args, **kwargs))
-                    ret = await asyncio.create_task(coro, context=context)
-                else:
-                    ret = await self.afunc(*args, **kwargs)
-        if isinstance(ret, Runnable) and self.recurse:
+            ret = await self.afunc(*args, **kwargs)
+        if self.recurse and isinstance(ret, Runnable):
             return await ret.ainvoke(input, config)
         return ret
 
@@ -594,7 +600,6 @@ class RunnableSeq(Runnable):
             name=config.get("run_name") or self.get_name(),
             run_id=config.pop("run_id", None),
         )
-
         # invoke all steps in sequence
         try:
             for i, step in enumerate(self.steps):
@@ -602,8 +607,19 @@ class RunnableSeq(Runnable):
                 config = patch_config(
                     config, callbacks=run_manager.get_child(f"seq:step:{i + 1}")
                 )
+                # 1st step is the actual node,
+                # others are writers which don't need to be run in context
                 if i == 0:
-                    input = step.invoke(input, config, **kwargs)
+                    # get the run object
+                    for h in run_manager.handlers:
+                        if isinstance(h, LangChainTracer):
+                            run = h.run_map.get(str(run_manager.run_id))
+                            break
+                    else:
+                        run = None
+                    # run in context
+                    with set_config_context(config, run) as context:
+                        input = context.run(step.invoke, input, config, **kwargs)
                 else:
                     input = step.invoke(input, config)
         # finish the root run
@@ -639,8 +655,24 @@ class RunnableSeq(Runnable):
                 config = patch_config(
                     config, callbacks=run_manager.get_child(f"seq:step:{i + 1}")
                 )
+                # 1st step is the actual node,
+                # others are writers which don't need to be run in context
                 if i == 0:
-                    input = await step.ainvoke(input, config, **kwargs)
+                    if ASYNCIO_ACCEPTS_CONTEXT:
+                        # get the run object
+                        for h in run_manager.handlers:
+                            if isinstance(h, LangChainTracer):
+                                run = h.run_map.get(str(run_manager.run_id))
+                                break
+                        else:
+                            run = None
+                        # run in context
+                        with set_config_context(config, run) as context:
+                            input = await asyncio.create_task(
+                                step.ainvoke(input, config, **kwargs), context=context
+                            )
+                    else:
+                        input = await step.ainvoke(input, config, **kwargs)
                 else:
                     input = await step.ainvoke(input, config)
         # finish the root run
@@ -668,51 +700,48 @@ class RunnableSeq(Runnable):
             name=config.get("run_name") or self.get_name(),
             run_id=config.pop("run_id", None),
         )
-
-        try:
-            # stream the last steps
-            # transform the input stream of each step with the next
-            # steps that don't natively support transforming an input stream will
-            # buffer input in memory until all available, and then start emitting output
-            for idx, step in enumerate(self.steps):
-                config = patch_config(
-                    config,
-                    callbacks=run_manager.get_child(f"seq:step:{idx + 1}"),
-                )
-                if idx == 0:
-                    iterator = step.stream(input, config, **kwargs)
-                else:
-                    iterator = step.transform(iterator, config)
-            if stream_handler := next(
-                (
-                    cast(_StreamingCallbackHandler, h)
-                    for h in run_manager.handlers
-                    if isinstance(h, _StreamingCallbackHandler)
-                ),
-                None,
-            ):
-                # populates streamed_output in astream_log() output if needed
-                iterator = stream_handler.tap_output_iter(run_manager.run_id, iterator)
-            output: Any = None
-            add_supported = False
-            for chunk in iterator:
-                yield chunk
-                # collect final output
-                if output is None:
-                    output = chunk
-                elif add_supported:
-                    try:
-                        output = output + chunk
-                    except TypeError:
-                        output = chunk
-                        add_supported = False
-                else:
-                    output = chunk
-        except BaseException as e:
-            run_manager.on_chain_error(e)
-            raise
+        # get the run object
+        for h in run_manager.handlers:
+            if isinstance(h, LangChainTracer):
+                run = h.run_map.get(str(run_manager.run_id))
+                break
         else:
-            run_manager.on_chain_end(output)
+            run = None
+        # create first step config
+        config = patch_config(
+            config,
+            callbacks=run_manager.get_child(f"seq:step:{1}"),
+        )
+        # run all in context
+        with set_config_context(config, run) as context:
+            try:
+                # stream the last steps
+                # transform the input stream of each step with the next
+                # steps that don't natively support transforming an input stream will
+                # buffer input in memory until all available, and then start emitting output
+                for idx, step in enumerate(self.steps):
+                    if idx == 0:
+                        iterator = step.stream(input, config, **kwargs)
+                    else:
+                        config = patch_config(
+                            config,
+                            callbacks=run_manager.get_child(f"seq:step:{idx + 1}"),
+                        )
+                        iterator = step.transform(iterator, config)
+                # populates streamed_output in astream_log() output if needed
+                if _StreamingCallbackHandler is not None:
+                    for h in run_manager.handlers:
+                        if isinstance(h, _StreamingCallbackHandler):
+                            iterator = h.tap_output_iter(run_manager.run_id, iterator)
+                # consume into final output
+                output = context.run(_consume_iter, iterator)
+                # sequence doesn't emit output, yield to mark as generator
+                yield
+            except BaseException as e:
+                run_manager.on_chain_error(e)
+                raise
+            else:
+                run_manager.on_chain_end(output)
 
     async def astream(
         self,
@@ -731,51 +760,121 @@ class RunnableSeq(Runnable):
             name=config.get("run_name") or self.get_name(),
             run_id=config.pop("run_id", None),
         )
-
-        try:
-            async with AsyncExitStack() as stack:
-                # stream the last steps
-                # transform the input stream of each step with the next
-                # steps that don't natively support transforming an input stream will
-                # buffer input in memory until all available, and then start emitting output
-                for idx, step in enumerate(self.steps):
-                    config = patch_config(
-                        config,
-                        callbacks=run_manager.get_child(f"seq:step:{idx + 1}"),
-                    )
-                    if idx == 0:
-                        aiterator = step.astream(input, config, **kwargs)
-                    else:
-                        aiterator = step.atransform(aiterator, config)
-                    if hasattr(aiterator, "aclose"):
-                        stack.push_async_callback(aiterator.aclose)
-                if stream_handler := next(
-                    (
-                        cast(_StreamingCallbackHandler, h)
-                        for h in run_manager.handlers
-                        if isinstance(h, _StreamingCallbackHandler)
-                    ),
-                    None,
-                ):
-                    # populates streamed_output in astream_log() output if needed
-                    aiterator = stream_handler.tap_output_aiter(
-                        run_manager.run_id, aiterator
-                    )
-                output: Any = None
-                add_supported = False
-                async for chunk in aiterator:
-                    yield chunk
-                    # collect final output
-                    if add_supported:
-                        try:
-                            output = output + chunk
-                        except TypeError:
-                            output = chunk
-                            add_supported = False
-                    else:
-                        output = chunk
-        except BaseException as e:
-            await run_manager.on_chain_error(e)
-            raise
+        # stream the last steps
+        # transform the input stream of each step with the next
+        # steps that don't natively support transforming an input stream will
+        # buffer input in memory until all available, and then start emitting output
+        if ASYNCIO_ACCEPTS_CONTEXT:
+            # get the run object
+            for h in run_manager.handlers:
+                if isinstance(h, LangChainTracer):
+                    run = h.run_map.get(str(run_manager.run_id))
+                    break
+            else:
+                run = None
+            # create first step config
+            config = patch_config(
+                config,
+                callbacks=run_manager.get_child(f"seq:step:{1}"),
+            )
+            # run all in context
+            with set_config_context(config, run) as context:
+                try:
+                    async with AsyncExitStack() as stack:
+                        for idx, step in enumerate(self.steps):
+                            if idx == 0:
+                                aiterator = step.astream(input, config, **kwargs)
+                            else:
+                                config = patch_config(
+                                    config,
+                                    callbacks=run_manager.get_child(
+                                        f"seq:step:{idx + 1}"
+                                    ),
+                                )
+                                aiterator = step.atransform(aiterator, config)
+                            if hasattr(aiterator, "aclose"):
+                                stack.push_async_callback(aiterator.aclose)
+                        # populates streamed_output in astream_log() output if needed
+                        if _StreamingCallbackHandler is not None:
+                            for h in run_manager.handlers:
+                                if isinstance(h, _StreamingCallbackHandler):
+                                    aiterator = h.tap_output_aiter(
+                                        run_manager.run_id, aiterator
+                                    )
+                        # consume into final output
+                        output = await asyncio.create_task(
+                            _consume_aiter(aiterator), context=context
+                        )
+                        # sequence doesn't emit output, yield to mark as generator
+                        yield
+                except BaseException as e:
+                    await run_manager.on_chain_error(e)
+                    raise
+                else:
+                    await run_manager.on_chain_end(output)
         else:
-            await run_manager.on_chain_end(output)
+            try:
+                async with AsyncExitStack() as stack:
+                    for idx, step in enumerate(self.steps):
+                        config = patch_config(
+                            config,
+                            callbacks=run_manager.get_child(f"seq:step:{idx + 1}"),
+                        )
+                        if idx == 0:
+                            aiterator = step.astream(input, config, **kwargs)
+                        else:
+                            aiterator = step.atransform(aiterator, config)
+                        if hasattr(aiterator, "aclose"):
+                            stack.push_async_callback(aiterator.aclose)
+                    # populates streamed_output in astream_log() output if needed
+                    if _StreamingCallbackHandler is not None:
+                        for h in run_manager.handlers:
+                            if isinstance(h, _StreamingCallbackHandler):
+                                aiterator = h.tap_output_aiter(
+                                    run_manager.run_id, aiterator
+                                )
+                    # consume into final output
+                    output = await _consume_aiter(aiterator)
+                    # sequence doesn't emit output, yield to mark as generator
+                    yield
+            except BaseException as e:
+                await run_manager.on_chain_error(e)
+                raise
+            else:
+                await run_manager.on_chain_end(output)
+
+
+def _consume_iter(it: Iterator[Any]) -> Any:
+    """Consume an iterator."""
+    output: Any = None
+    add_supported = False
+    for chunk in it:
+        # collect final output
+        if output is None:
+            output = chunk
+        elif add_supported:
+            try:
+                output = output + chunk
+            except TypeError:
+                output = chunk
+                add_supported = False
+        else:
+            output = chunk
+    return output
+
+
+async def _consume_aiter(it: AsyncIterator[Any]) -> Any:
+    """Consume an async iterator."""
+    output: Any = None
+    add_supported = False
+    async for chunk in it:
+        # collect final output
+        if add_supported:
+            try:
+                output = output + chunk
+            except TypeError:
+                output = chunk
+                add_supported = False
+        else:
+            output = chunk
+    return output