x

feat(prebuilt): Add structured output tools to ToolNode (#5899 )
* Add structured output tools to ToolNode * Fix default tool node name to match the actual default ('tools') * Update doc-strings to explain what inputs/outputs are for the ToolNode. * Mark internal attributes as private (potentially breaking -- although hopefully users aren't accessing these) ## Decisions points * OK with two properties? Done since users may be relying on `tools_by_name` and expanding the return type will break user code. ## Changes in public/private interface ### Marked as public * Make `tools_by_name` an official public property * Make `structured_output_tools` a public property ### Marked as private There should be no reason why users are accessing these attributes ```python _tool_to_state_args _tool_to_store_arg _handle_tool_errors _messages_key ``` ### Usage ```python class OutputSchema(BaseModel): name: str age: int location: str tool_node = ToolNode([OutputSchema]) # Test that the structured output tool is registered correctly assert "OutputSchema" in tool_node.structured_output_tools # Create a tool call that matches the schema tool_call = { "name": "OutputSchema", "args": {"name": "Alice", "age": 30, "location": "NYC"}, "id": "call_123", "type": "tool_call", } # Test sync execution result = tool_node.invoke( {"messages": [AIMessage(content="", tool_calls=[tool_call])]} ) # Should return a Command with structured response assert isinstance(result, list) assert len(result) == 1 command = result[0] assert isinstance(command, Command) # Check the update structure assert "messages" in command.update assert "structured_response" in command.update # Check the tool message tool_message = command.update["messages"][0] assert isinstance(tool_message, ToolMessage) assert tool_message.name == "OutputSchema" assert tool_message.tool_call_id == "call_123" # Check the structured response structured_response = command.update["structured_response"] assert isinstance(structured_response, OutputSchema) assert structured_response.name == "Alice" assert structured_response.age == 30 assert structured_response.location == "NYC" ```
2026-09-03 01:58:45 +02:00 · 2025-08-13 15:43:00 -04:00 · 2025-08-13 15:16:53 -04:00 · 2025-08-13 11:15:10 -04:00 · 2025-08-13 09:49:27 -04:00 · 2025-08-12 21:52:21 -04:00
91 changed files with 6178 additions and 1610 deletions
@@ -3,7 +3,8 @@ name: CI

 on:
  push:
-    branches: [main, v1]
+    branches:
+      - main
  pull_request:

 permissions:
@@ -18,6 +18,9 @@ build-prebuilt:
 build-docs: build-prebuilt
 	TARGET_LANGUAGE=python uv run python -m mkdocs build --clean -f mkdocs.yml --strict

+build-docs-js: build-prebuilt
+	TARGET_LANGUAGE=js uv run python -m mkdocs build --clean -f mkdocs.yml --strict
+
 llms-text:
 	uv run python -m _scripts.generate_llms_text docs/llms-full.txt

@@ -4,52 +4,48 @@ This module provides link mappings for different language/framework scopes
 to resolve @[link_name] references to actual URLs.
 """

-# Python-specific link mappings
 # Python-specific link mappings
 PYTHON_LINK_MAP = {
    "StateGraph": "reference/graphs/#langgraph.graph.StateGraph",
-    "add_conditional_edges": "reference/graphs/#langgraph.graph.StateGraph.add_conditional_edges",
-    "add_edge": "reference/graphs/#langgraph.graph.StateGraph.add_edge",
-    "add_node": "reference/graphs/#langgraph.graph.StateGraph.add_node",
-    "add_messages": "reference/messages/#langgraph.graph.message.add_messages",
-    "ToolNode": "reference/prebuilt/#langgraph.prebuilt.tool_node.ToolNode",
+    "add_conditional_edges": "reference/graphs/#langgraph.graph.state.StateGraph.add_conditional_edges",
+    "add_edge": "reference/graphs/#langgraph.graph.state.StateGraph.add_edge",
+    "add_node": "reference/graphs/#langgraph.graph.state.StateGraph.add_node",
+    "add_messages": "reference/graphs/#langgraph.graph.message.add_messages",
+    "ToolNode": "reference/agents/#langgraph.prebuilt.tool_node.ToolNode",
    "CompiledStateGraph.astream": "reference/graphs/#langgraph.graph.state.CompiledStateGraph.astream",
-    "Pregel.astream": "reference/graphs/#langgraph.pregel.Pregel.astream",
+    "Pregel.astream": "reference/pregel/#langgraph.pregel.Pregel.astream",
    "AsyncPostgresSaver": "reference/checkpoints/#langgraph.checkpoint.postgres.aio.AsyncPostgresSaver",
    "AsyncSqliteSaver": "reference/checkpoints/#langgraph.checkpoint.sqlite.aio.AsyncSqliteSaver",
    "BaseCheckpointSaver": "reference/checkpoints/#langgraph.checkpoint.base.BaseCheckpointSaver",
-    "BaseStore": "reference/stores/#langgraph.store.base.BaseStore",
-    "BaseStore.put": "reference/stores/#langgraph.store.base.BaseStore.put",
-    "BinaryOperatorAggregate": "reference/channels/#langgraph.channels.BinaryOperatorAggregate",
+    "BaseStore": "reference/store/#langgraph.store.base.BaseStore",
+    "BaseStore.put": "reference/store/#langgraph.store.base.BaseStore.put",
+    "BinaryOperatorAggregate": "reference/pregel/#langgraph.pregel.Pregel--advanced-channels-context-and-binaryoperatoraggregate",
    "CipherProtocol": "reference/checkpoints/#langgraph.checkpoint.serde.base.CipherProtocol",
-    "client.runs.stream": "reference/client/#langgraph_sdk.client.RunsClient.stream",
-    "client.runs.wait": "reference/client/#langgraph_sdk.client.RunsClient.wait",
-    "client.threads.get_history": "reference/client/#langgraph_sdk.client.ThreadsClient.get_history",
-    "client.threads.update_state": "reference/client/#langgraph_sdk.client.ThreadsClient.update_state",
+    "client.runs.stream": "cloud/reference/sdk/python_sdk_ref/#langgraph_sdk.client.RunsClient.stream",
+    "client.runs.wait": "cloud/reference/sdk/python_sdk_ref/#langgraph_sdk.client.RunsClient.wait",
+    "client.threads.get_history": "cloud/reference/sdk/python_sdk_ref/#langgraph_sdk.client.ThreadsClient.get_history",
+    "client.threads.update_state": "cloud/reference/sdk/python_sdk_ref/#langgraph_sdk.client.ThreadsClient.update_state",
    "Command": "reference/types/#langgraph.types.Command",
    "CompiledStateGraph": "reference/graphs/#langgraph.graph.state.CompiledStateGraph",
    "create_react_agent": "reference/prebuilt/#langgraph.prebuilt.chat_agent_executor.create_react_agent",
    "create_supervisor": "reference/supervisor/#langgraph_supervisor.supervisor.create_supervisor",
    "EncryptedSerializer": "reference/checkpoints/#langgraph.checkpoint.serde.encrypted.EncryptedSerializer",
-    "entrypoint.final": "reference/functions/#langgraph.func.entrypoint.final",
-    "entrypoint": "reference/functions/#langgraph.func.entrypoint",
+    "entrypoint.final": "reference/func/#langgraph.func.entrypoint.final",
+    "entrypoint": "reference/func/#langgraph.func.entrypoint",
    "from_pycryptodome_aes": "reference/checkpoints/#langgraph.checkpoint.serde.encrypted.EncryptedSerializer.from_pycryptodome_aes",
-    # "getContextVariable": "<insert-ref>",
    "get_state_history": "reference/graphs/#langgraph.graph.state.CompiledStateGraph.get_state_history",
    "get_stream_writer": "reference/config/#langgraph.config.get_stream_writer",
    "HumanInterrupt": "reference/prebuilt/#langgraph.prebuilt.interrupt.HumanInterrupt",
-    "InjectedState": "reference/prebuilt/#langgraph.prebuilt.InjectedState",
+    "InjectedState": "reference/agents/#langgraph.prebuilt.tool_node.InjectedState",
    "InMemorySaver": "reference/checkpoints/#langgraph.checkpoint.memory.InMemorySaver",
-    "interrupt": "reference/graphs/#langgraph.graph.interrupt",
+    "interrupt": "reference/types/#langgraph.types.Interrupt",
    "CompiledStateGraph.invoke": "reference/graphs/#langgraph.graph.state.CompiledStateGraph.invoke",
    "JsonPlusSerializer": "reference/checkpoints/#langgraph.checkpoint.serde.jsonplus.JsonPlusSerializer",
-    "langgraph.json": "reference/configuration/#configuration-file",
+    "langgraph.json": "cloud/reference/cli/#configuration-file",
    "LastValue": "reference/channels/#langgraph.channels.LastValue",
-    # "MemorySaver": "<insert-ref>",
-    # "messagesStateReducer": "<insert-ref>",
    "PostgresSaver": "reference/checkpoints/#langgraph.checkpoint.postgres.PostgresSaver",
-    "Pregel": "reference/graphs/#langgraph.pregel.Pregel",
-    "Pregel.stream": "reference/graphs/#langgraph.pregel.Pregel.stream",
+    "Pregel": "reference/pregel/",
+    "Pregel.stream": "reference/pregel/#langgraph.pregel.Pregel.stream",
    "pre_model_hook": "reference/prebuilt/#langgraph.prebuilt.chat_agent_executor.create_react_agent",
    "protocol": "reference/checkpoints/#langgraph.checkpoint.serde.base.SerializerProtocol",
    "Send": "reference/types/#langgraph.types.Send",
@@ -57,68 +53,56 @@ PYTHON_LINK_MAP = {
    "SqliteSaver": "reference/checkpoints/#langgraph.checkpoint.sqlite.SqliteSaver",
    "START": "reference/constants/#langgraph.constants.START",
    "CompiledStateGraph.stream": "reference/graphs/#langgraph.graph.state.CompiledStateGraph.stream",
-    "task": "reference/functions/#langgraph.func.task",
+    "task": "reference/func/#langgraph.func.task",
    "Topic": "reference/channels/#langgraph.channels.Topic",
    "update_state": "reference/graphs/#langgraph.graph.state.CompiledStateGraph.update_state",
 }

-
 # JavaScript-specific link mappings
 JS_LINK_MAP = {
    "Auth": "reference/classes/sdk_auth.Auth.html",
    "StateGraph": "reference/classes/langgraph.StateGraph.html",
-    "add_conditional_edges": "reference/functions/langgraph_StateGraph.addConditionalEdges.html",
-    "add_edge": "reference/functions/langgraph_StateGraph.addEdge.html",
-    "add_node": "reference/functions/langgraph_StateGraph.addNode.html",
-    "add_messages": "reference/functions/langgraph_message.addMessages.html",
+    "add_conditional_edges": "/reference/classes/langgraph.StateGraph.html#addConditionalEdges",
+    "add_edge": "reference/classes/langgraph.StateGraph.html#addEdge",
+    "add_node": "reference/classes/langgraph.StateGraph.html#addNode",
+    "add_messages": "reference/modules/langgraph.html#addMessages",
    "ToolNode": "reference/classes/langgraph_prebuilt.ToolNode.html",
-    "CompiledStateGraph.astream()": "reference/functions/langgraph_CompiledStateGraph.astream.html",
-    "Pregel.astream": "reference/functions/langgraph_Pregel.astream.html",
-    "AsyncPostgresSaver": "reference/classes/langgraph_checkpoint_postgres_aio.AsyncPostgresSaver.html",
-    "AsyncSqliteSaver": "reference/classes/langgraph_checkpoint_sqlite_aio.AsyncSqliteSaver.html",
-    "BaseCheckpointSaver": "reference/classes/langgraph_checkpoint_base.BaseCheckpointSaver.html",
-    "BaseStore": "reference/classes/langgraph_store_base.BaseStore.html",
-    "BaseStore.put": "reference/functions/langgraph_store_base.BaseStore.put.html",
-    "BinaryOperatorAggregate": "reference/classes/langgraph_channels.BinaryOperatorAggregate.html",
-    "CipherProtocol": "reference/classes/langgraph_checkpoint_serde_base.CipherProtocol.html",
-    "client.runs.stream": "reference/functions/langgraph_sdk_client.RunsClient.stream.html",
-    "client.runs.wait": "reference/functions/langgraph_sdk_client.RunsClient.wait.html",
-    "client.threads.get_history": "reference/functions/langgraph_sdk_client.ThreadsClient.getHistory.html",
-    "client.threads.update_state": "reference/functions/langgraph_sdk_client.ThreadsClient.updateState.html",
+    "BaseCheckpointSaver": "reference/classes/checkpoint.BaseCheckpointSaver.html",
+    "BaseStore": "reference/classes/checkpoint.BaseStore.html",
+    "BaseStore.put": "reference/classes/checkpoint.BaseStore.html#put",
+    "BinaryOperatorAggregate": "reference/classes/langgraph.BinaryOperatorAggregate.html",
+    "client.runs.stream": "reference/classes/sdk_client.RunsClient.html#stream",
+    "client.runs.wait": "reference/classes/sdk_client.RunsClient.html#wait",
+    "client.threads.get_history": "reference/classes/sdk_client.ThreadsClient.html#getHistory",
+    "client.threads.update_state": "reference/classes/sdk_client.ThreadsClient.html#updateState",
    "Command": "reference/classes/langgraph.Command.html",
    "CompiledStateGraph": "reference/classes/langgraph.CompiledStateGraph.html",
    "create_react_agent": "reference/functions/langgraph_prebuilt.createReactAgent.html",
    "create_supervisor": "reference/functions/langgraph_supervisor.createSupervisor.html",
-    "EncryptedSerializer": "reference/classes/langgraph_checkpoint_serde_encrypted.EncryptedSerializer.html",
-    "entrypoint.final": "reference/functions/langgraph_func.entrypoint.final.html",
-    "entrypoint": "reference/functions/langgraph_func.entrypoint.html",
-    "from_pycryptodome_aes": "reference/functions/langgraph_checkpoint_serde_encrypted.EncryptedSerializer.fromPycryptodomeAes.html",
+    "entrypoint.final": "reference/functions/langgraph.entrypoint.html#final",
+    "entrypoint": "reference/functions/langgraph.entrypoint.html",
    "getContextVariable": "https://v03.api.js.langchain.com/functions/_langchain_core.context.getContextVariable.html",
-    "get_state_history": "reference/functions/langgraph_CompiledStateGraph.getStateHistory.html",
-    "get_stream_writer": "reference/functions/langgraph_config.getStreamWriter.html",
-    "HumanInterrupt": "reference/classes/langgraph_prebuilt.HumanInterrupt.html",
-    "InjectedState": "reference/classes/langgraph_prebuilt.InjectedState.html",
-    "InMemorySaver": "reference/classes/langgraph_checkpoint_memory.InMemorySaver.html",
+    "get_state_history": "reference/classes/langgraph.CompiledStateGraph.html#getStateHistory",
+    "HumanInterrupt": "reference/interfaces/langgraph_prebuilt.HumanInterrupt.html",
    "interrupt": "reference/functions/langgraph.interrupt-2.html",
-    "CompiledStateGraph.invoke": "reference/functions/langgraph_CompiledStateGraph.invoke.html",
-    "JsonPlusSerializer": "reference/classes/langgraph_checkpoint_serde_jsonplus.JsonPlusSerializer.html",
-    "langgraph.json": "reference/configuration.html",
-    "LastValue": "reference/classes/langgraph_channels.LastValue.html",
+    "CompiledStateGraph.invoke": "reference/classes/langgraph.CompiledStateGraph.html#invoke",
+    "langgraph.json": "cloud/reference/cli/#configuration-file",
    "MemorySaver": "reference/classes/checkpoint.MemorySaver.html",
    "messagesStateReducer": "reference/functions/langgraph.messagesStateReducer.html",
-    "PostgresSaver": "reference/classes/langgraph_checkpoint_postgres.PostgresSaver.html",
+    "PostgresSaver": "reference/classes/checkpoint_postgres.PostgresSaver.html",
    "Pregel": "reference/classes/langgraph.Pregel.html",
-    "Pregel.stream": "reference/functions/langgraph_Pregel.stream.html",
+    "Pregel.stream": "reference/classes/langgraph.Pregel.html#stream",
    "pre_model_hook": "reference/functions/langgraph_prebuilt.createReactAgent.html",
-    "protocol": "reference/classes/langgraph_checkpoint_serde_base.SerializerProtocol.html",
+    "protocol": "reference/interfaces/checkpoint.SerializerProtocol.html",
    "Send": "reference/classes/langgraph.Send.html",
-    "SerializerProtocol": "reference/classes/langgraph_checkpoint_serde_base.SerializerProtocol.html",
-    "SqliteSaver": "reference/classes/langgraph_checkpoint_sqlite.SqliteSaver.html",
-    "START": "reference/constants.html#START",
-    "CompiledStateGraph.stream": "reference/functions/langgraph_CompiledStateGraph.stream.html",
-    "task": "reference/functions/langgraph_func.task.html",
-    "Topic": "reference/classes/langgraph_channels.Topic.html",
-    "update_state": "reference/functions/langgraph_CompiledStateGraph.updateState.html",
+    "SerializerProtocol": "reference/interfaces/checkpoint.SerializerProtocol.html",
+    "SqliteSaver": "reference/classes/checkpoint_sqlite.SqliteSaver.html",
+    "START": "reference/variables/langgraph.START.html",
+    "CompiledStateGraph.stream": "reference/classes/langgraph.CompiledStateGraph.html#stream",
+    "task": "reference/functions/langgraph.task.html",
+    ## TODO (hntrl): export Topic from langgraphjs
+    # "Topic": "reference/classes/langgraph_channels.Topic.html",
+    "update_state": "reference/classes/langgraph.CompiledStateGraph.html#updateState",
 }

 # TODO: Allow updating these to localhost for local development
@@ -88,12 +88,12 @@ REDIRECT_MAP = {
    "cloud/how-tos/human_in_the_loop_user_input.md": "cloud/how-tos/add-human-in-the-loop.md",
    "concepts/platform_architecture.md": "concepts/langgraph_cloud#architecture",
    # cloud streaming redirects
-    "cloud/how-tos/stream_values.md": "cloud/how-tos/streaming.md#stream-graph-state",
-    "cloud/how-tos/stream_updates.md": "cloud/how-tos/streaming.md#stream-graph-state",
-    "cloud/how-tos/stream_messages.md": "cloud/how-tos/streaming.md#messages",
-    "cloud/how-tos/stream_events.md": "cloud/how-tos/streaming.md#stream-events",
-    "cloud/how-tos/stream_debug.md": "cloud/how-tos/streaming.md#debug",
-    "cloud/how-tos/stream_multiple.md": "cloud/how-tos/streaming.md#stream-multiple-modes",
+    "cloud/how-tos/stream_values.md": "https://docs.langchain.com/langgraph-platform/streaming",
+    "cloud/how-tos/stream_updates.md": "https://docs.langchain.com/langgraph-platform/streaming",
+    "cloud/how-tos/stream_messages.md": "https://docs.langchain.com/langgraph-platform/streaming",
+    "cloud/how-tos/stream_events.md": "https://docs.langchain.com/langgraph-platform/streaming",
+    "cloud/how-tos/stream_debug.md": "https://docs.langchain.com/langgraph-platform/streaming",
+    "cloud/how-tos/stream_multiple.md": "https://docs.langchain.com/langgraph-platform/streaming",
    "cloud/concepts/streaming.md": "concepts/streaming.md",
    "agents/streaming.md": "how-tos/streaming.md",
    # prebuilt redirects
@@ -128,78 +128,84 @@ REDIRECT_MAP = {
    "cloud/how-tos/human_in_the_loop_breakpoint.md": "cloud/how-tos/add-human-in-the-loop.md",
    "how-tos/human_in_the_loop/edit-graph-state.ipynb": "how-tos/human_in_the_loop/time-travel.md",

-    # mintlify 
-    # "tutorials/auth/getting_started.md": "https://docs.langchain.com/langgraph-platform/",
-    # "tutorials/auth/resource_auth.md": "https://docs.langchain.com/langgraph-platform/",
-    # "tutorials/auth/add_auth_server.md": "https://docs.langchain.com/langgraph-platform/",
-    # "how-tos/use-remote-graph.md": "https://docs.langchain.com/langgraph-platform/",
-    # "how-tos/autogen-integration.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/use_stream_react.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/generative_ui_react.md": "https://docs.langchain.com/langgraph-platform/",
-    # "concepts/langgraph_platform.md": "https://docs.langchain.com/langgraph-platform/",
-    # "concepts/langgraph_components.md": "https://docs.langchain.com/langgraph-platform/",
-    # "concepts/langgraph_server.md": "https://docs.langchain.com/langgraph-platform/",
-    # "concepts/langgraph_data_plane.md": "https://docs.langchain.com/langgraph-platform/",
-    # "concepts/langgraph_control_plane.md": "https://docs.langchain.com/langgraph-platform/",
-    # "concepts/langgraph_cli.md": "https://docs.langchain.com/langgraph-platform/",
-    # "concepts/langgraph_studio.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/studio/quick_start.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/invoke_studio.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/studio/manage_assistants.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/threads_studio.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/iterate_graph_studio.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/studio/run_evals.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/clone_traces_studio.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/datasets_studio.md": "https://docs.langchain.com/langgraph-platform/",
-    # "concepts/sdk.md": "https://docs.langchain.com/langgraph-platform/",
-    # "concepts/plans.md": "https://docs.langchain.com/langgraph-platform/",
-    # "concepts/application_structure.md": "https://docs.langchain.com/langgraph-platform/",
-    # "concepts/scalability_and_resilience.md": "https://docs.langchain.com/langgraph-platform/",
-    # "concepts/auth.md": "https://docs.langchain.com/langgraph-platform/",
-    # "how-tos/auth/custom_auth.md": "https://docs.langchain.com/langgraph-platform/",
-    # "how-tos/auth/openapi_security.md": "https://docs.langchain.com/langgraph-platform/",
-    # "concepts/assistants.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/configuration_cloud.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/use_threads.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/background_run.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/same-thread.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/cron_jobs.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/stateless_runs.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/configurable_headers.md": "https://docs.langchain.com/langgraph-platform/",
-    # "concepts/double_texting.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/interrupt_concurrent.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/rollback_concurrent.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/reject_concurrent.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/enqueue_concurrent.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/concepts/webhooks.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/webhooks.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/concepts/cron_jobs.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/cron_jobs.md": "https://docs.langchain.com/langgraph-platform/",
-    # "how-tos/http/custom_lifespan.md": "https://docs.langchain.com/langgraph-platform/",
-    # "how-tos/http/custom_middleware.md": "https://docs.langchain.com/langgraph-platform/",
-    # "how-tos/http/custom_routes.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/concepts/data_storage_and_privacy.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/deployment/semantic_search.md": "https://docs.langchain.com/langgraph-platform/",
-    # "how-tos/ttl/configure_ttl.md": "https://docs.langchain.com/langgraph-platform/",
-    # "concepts/deployment_options.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/quick_start.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/deployment/setup.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/deployment/setup_pyproject.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/deployment/setup_javascript.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/deployment/custom_docker.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/deployment/graph_rebuild.md": "https://docs.langchain.com/langgraph-platform/",
-    # "concepts/langgraph_cloud.md": "https://docs.langchain.com/langgraph-platform/",
-    # "concepts/langgraph_self_hosted_data_plane.md": "https://docs.langchain.com/langgraph-platform/",
-    # "concepts/langgraph_self_hosted_control_plane.md": "https://docs.langchain.com/langgraph-platform/",
-    # "concepts/langgraph_standalone_container.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/deployment/cloud.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/deployment/self_hosted_data_plane.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/deployment/self_hosted_control_plane.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/deployment/standalone_container.md": "https://docs.langchain.com/langgraph-platform/",
-    # "concepts/server-mcp.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/human_in_the_loop_time_travel.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/add-human-in-the-loop.md": "https://docs.langchain.com/langgraph-platform/",
-    # "cloud/how-tos/streaming.md": "https://docs.langchain.com/langgraph-platform/",
+    # LGP mintlify migration redirects
+    "tutorials/auth/getting_started.md": "https://docs.langchain.com/langgraph-platform/auth",
+    "tutorials/auth/resource_auth.md": "https://docs.langchain.com/langgraph-platform/resource-auth",
+    "tutorials/auth/add_auth_server.md": "https://docs.langchain.com/langgraph-platform/add-auth-server",
+    "how-tos/use-remote-graph.md": "https://docs.langchain.com/langgraph-platform/use-remote-graph",
+    "how-tos/autogen-integration.md": "https://docs.langchain.com/langgraph-platform/autogen-integration",
+    "cloud/how-tos/use_stream_react.md": "https://docs.langchain.com/langgraph-platform/use-stream-react",
+    "cloud/how-tos/generative_ui_react.md": "https://docs.langchain.com/langgraph-platform/generative-ui-react",
+    "concepts/langgraph_platform.md": "https://docs.langchain.com/langgraph-platform/index",
+    "concepts/langgraph_components.md": "https://docs.langchain.com/langgraph-platform/components",
+    "concepts/langgraph_server.md": "https://docs.langchain.com/langgraph-platform/langgraph-server",
+    "concepts/langgraph_data_plane.md": "https://docs.langchain.com/langgraph-platform/data-plane",
+    "concepts/langgraph_control_plane.md": "https://docs.langchain.com/langgraph-platform/control-plane",
+    "concepts/langgraph_cli.md": "https://docs.langchain.com/langgraph-platform/langgraph-cli",
+    "concepts/langgraph_studio.md": "https://docs.langchain.com/langgraph-platform/langgraph-studio",
+    "cloud/how-tos/studio/quick_start.md": "https://docs.langchain.com/langgraph-platform/quick-start-studio",
+    "cloud/how-tos/invoke_studio.md": "https://docs.langchain.com/langgraph-platform/invoke-studio",
+    "cloud/how-tos/studio/manage_assistants.md": "https://docs.langchain.com/langgraph-platform/manage-assistants-studio",
+    "cloud/how-tos/threads_studio.md": "https://docs.langchain.com/langgraph-platform/threads-studio",
+    "cloud/how-tos/iterate_graph_studio.md": "https://docs.langchain.com/langgraph-platform/iterate-graph-studio",
+    "cloud/how-tos/studio/run_evals.md": "https://docs.langchain.com/langgraph-platform/run-evals-studio",
+    "cloud/how-tos/clone_traces_studio.md": "https://docs.langchain.com/langgraph-platform/clone-traces-studio",
+    "cloud/how-tos/datasets_studio.md": "https://docs.langchain.com/langgraph-platform/datasets-studio",
+    "concepts/sdk.md": "https://docs.langchain.com/langgraph-platform/sdk",
+    "concepts/plans.md": "https://docs.langchain.com/langgraph-platform/plans",
+    "concepts/application_structure.md": "https://docs.langchain.com/langgraph-platform/application-structure",
+    "concepts/scalability_and_resilience.md": "https://docs.langchain.com/langgraph-platform/scalability-and-resilience",
+    "concepts/auth.md": "https://docs.langchain.com/langgraph-platform/auth",
+    "how-tos/auth/custom_auth.md": "https://docs.langchain.com/langgraph-platform/custom-auth",
+    "how-tos/auth/openapi_security.md": "https://docs.langchain.com/langgraph-platform/openapi-security",
+    "concepts/assistants.md": "https://docs.langchain.com/langgraph-platform/assistants",
+    "cloud/how-tos/configuration_cloud.md": "https://docs.langchain.com/langgraph-platform/configuration-cloud",
+    "cloud/how-tos/use_threads.md": "https://docs.langchain.com/langgraph-platform/use-threads",
+    "cloud/how-tos/background_run.md": "https://docs.langchain.com/langgraph-platform/background-run",
+    "cloud/how-tos/same-thread.md": "https://docs.langchain.com/langgraph-platform/same-thread",
+    "cloud/how-tos/stateless_runs.md": "https://docs.langchain.com/langgraph-platform/stateless-runs",
+    "cloud/how-tos/configurable_headers.md": "https://docs.langchain.com/langgraph-platform/configurable-headers",
+    "concepts/double_texting.md": "https://docs.langchain.com/langgraph-platform/double-texting",
+    "cloud/how-tos/interrupt_concurrent.md": "https://docs.langchain.com/langgraph-platform/interrupt-concurrent",
+    "cloud/how-tos/rollback_concurrent.md": "https://docs.langchain.com/langgraph-platform/rollback-concurrent",
+    "cloud/how-tos/reject_concurrent.md": "https://docs.langchain.com/langgraph-platform/reject-concurrent",
+    "cloud/how-tos/enqueue_concurrent.md": "https://docs.langchain.com/langgraph-platform/enqueue-concurrent",
+    "cloud/concepts/webhooks.md": "https://docs.langchain.com/langgraph-platform/use-webhooks",
+    "cloud/how-tos/webhooks.md": "https://docs.langchain.com/langgraph-platform/use-webhooks",
+    "cloud/concepts/cron_jobs.md": "https://docs.langchain.com/langgraph-platform/cron-jobs",
+    "cloud/how-tos/cron_jobs.md": "https://docs.langchain.com/langgraph-platform/cron-jobs",
+    "how-tos/http/custom_lifespan.md": "https://docs.langchain.com/langgraph-platform/custom-lifespan",
+    "how-tos/http/custom_middleware.md": "https://docs.langchain.com/langgraph-platform/custom-middleware",
+    "how-tos/http/custom_routes.md": "https://docs.langchain.com/langgraph-platform/custom-routes",
+    "cloud/concepts/data_storage_and_privacy.md": "https://docs.langchain.com/langgraph-platform/data-storage-and-privacy",
+    "cloud/deployment/semantic_search.md": "https://docs.langchain.com/langgraph-platform/semantic-search",
+    "how-tos/ttl/configure_ttl.md": "https://docs.langchain.com/langgraph-platform/configure-ttl",
+    "concepts/deployment_options.md": "https://docs.langchain.com/langgraph-platform/deployment-options",
+    "cloud/quick_start.md": "https://docs.langchain.com/langgraph-platform/deployment-quickstart",
+    "cloud/deployment/setup.md": "https://docs.langchain.com/langgraph-platform/setup-app-requirements-txt",
+    "cloud/deployment/setup_pyproject.md": "https://docs.langchain.com/langgraph-platform/setup-pyproject",
+    "cloud/deployment/setup_javascript.md": "https://docs.langchain.com/langgraph-platform/setup-javascript",
+    "cloud/deployment/custom_docker.md": "https://docs.langchain.com/langgraph-platform/custom-docker",
+    "cloud/deployment/graph_rebuild.md": "https://docs.langchain.com/langgraph-platform/graph-rebuild",
+    "concepts/langgraph_cloud.md": "https://docs.langchain.com/langgraph-platform/cloud",
+    "concepts/langgraph_self_hosted_data_plane.md": "https://docs.langchain.com/langgraph-platform/hybrid",
+    "concepts/langgraph_self_hosted_control_plane.md": "https://docs.langchain.com/langgraph-platform/self-hosted",
+    "concepts/langgraph_standalone_container.md": "https://docs.langchain.com/langgraph-platform/self-hosted#data-plane-only",
+    "cloud/deployment/cloud.md": "https://docs.langchain.com/langgraph-platform/cloud",
+    "cloud/deployment/self_hosted_data_plane.md": "https://docs.langchain.com/langgraph-platform/deploy-hybrid",
+    "cloud/deployment/self_hosted_control_plane.md": "https://docs.langchain.com/langgraph-platform/deploy-self-hosted-full-platform",
+    "cloud/deployment/standalone_container.md": "https://docs.langchain.com/langgraph-platform/deploy-data-plane-only",
+    "concepts/server-mcp.md": "https://docs.langchain.com/langgraph-platform/server-mcp",
+    "cloud/how-tos/human_in_the_loop_time_travel.md": "https://docs.langchain.com/langgraph-platform/human-in-the-loop-time-travel",
+    "cloud/how-tos/add-human-in-the-loop.md": "https://docs.langchain.com/langgraph-platform/add-human-in-the-loop",
+    "cloud/deployment/egress.md": "https://docs.langchain.com/langgraph-platform/env-var",
+    "cloud/how-tos/streaming.md": "https://docs.langchain.com/langgraph-platform/streaming",
+    "cloud/reference/api/api_ref.md": "https://docs.langchain.com/langgraph-platform/server-api-ref",
+    "cloud/reference/langgraph_server_changelog.md": "https://docs.langchain.com/langgraph-platform/langgraph-server-changelog",
+    "cloud/reference/api/api_ref_control_plane.md": "https://docs.langchain.com/langgraph-platform/api-ref-control-plane",
+    "cloud/reference/cli.md": "https://docs.langchain.com/langgraph-platform/cli",
+    "cloud/reference/env_var.md": "https://docs.langchain.com/langgraph-platform/env-var",
+    "troubleshooting/studio.md": "https://docs.langchain.com/langgraph-platform/troubleshooting-studio",
 }


@@ -29,7 +29,7 @@ pip install -U langgraph "langchain[anthropic]"

 !!! info

-    LangChain is installed so the agent can call the [model](https://python.langchain.com/docs/integrations/chat/).
+    `langchain[anthropic]` is installed so the agent can call the [model](https://python.langchain.com/docs/integrations/chat/).

 :::

@@ -41,7 +41,7 @@ npm install @langchain/langgraph @langchain/core @langchain/anthropic

 !!! info

-    LangChain is installed so the agent can call the [model](https://js.langchain.com/docs/integrations/chat/).
+    `@langchain/core` `@langchain/anthropic` are installed so the agent can call the [model](https://js.langchain.com/docs/integrations/chat/).

 :::

@@ -145,6 +145,76 @@ const agent = createReactAgent({

 :::

+:::python
+
+### Dynamic model selection
+
+Pass a callable function to `create_react_agent` to dynamically select the model at runtime. This is useful for scenarios where you want to choose a model based on user input, configuration settings, or other runtime conditions.
+
+The selector function must return a chat model. If you're using tools, you must bind the tools to the model within the selector function.
+
+  ```python
+from dataclasses import dataclass
+from typing import Literal
+from langchain.chat_models import init_chat_model
+from langchain_core.language_models import BaseChatModel
+from langchain_core.tools import tool
+from langgraph.prebuilt import create_react_agent
+from langgraph.prebuilt.chat_agent_executor import AgentState
+from langgraph.runtime import Runtime
+
+@tool
+def weather() -> str:
+    """Returns the current weather conditions."""
+    return "It's nice and sunny."
+
+
+# Define the runtime context
+@dataclass
+class CustomContext:
+    provider: Literal["anthropic", "openai"]
+
+# Initialize models
+openai_model = init_chat_model("openai:gpt-4o")
+anthropic_model = init_chat_model("anthropic:claude-sonnet-4-20250514")
+
+
+# Selector function for model choice
+def select_model(state: AgentState, runtime: Runtime[CustomContext]) -> BaseChatModel:
+    if runtime.context.provider == "anthropic":
+        model = anthropic_model
+    elif runtime.context.provider == "openai":
+        model = openai_model
+    else:
+        raise ValueError(f"Unsupported provider: {runtime.context.provider}")
+
+    # With dynamic model selection, you must bind tools explicitly
+    return model.bind_tools([weather])
+
+
+# Create agent with dynamic model selection
+agent = create_react_agent(select_model, tools=[weather])
+
+# Invoke with context to select model
+output = agent.invoke(
+    {
+        "messages": [
+            {
+                "role": "user",
+                "content": "Which model is handling this?",
+            }
+        ]
+    },
+    context=CustomContext(provider="openai"),
+)
+
+print(output["messages"][-1].text())
+```
+
+!!! version-added "New in LangGraph v0.6"
+
+:::
+
 ## Advanced model configuration

 ### Disable streaming
@@ -367,13 +367,13 @@ To implement handoffs with `createReactAgent`, you need to:

 3.  Define a parent graph that contains individual agents as nodes:

-        ```typescript
-        import { StateGraph, MessagesZodState } from "@langchain/langgraph";
-        const multiAgentGraph = new StateGraph(MessagesZodState)
-          .addNode("flight_assistant", flightAssistant)
-          .addNode("hotel_assistant", hotelAssistant)
-          // ...
-        ```
+    ```typescript
+    import { StateGraph, MessagesZodState } from "@langchain/langgraph";
+    const multiAgentGraph = new StateGraph(MessagesZodState)
+      .addNode("flight_assistant", flightAssistant)
+      .addNode("hotel_assistant", hotelAssistant)
+      // ...
+    ```

    :::

@@ -619,7 +619,8 @@ for await (const chunk of multiAgentGraph.stream({
 3. Name of the agent or node to hand off to.
 4. Take the agent's messages and **add** them to the parent's **state** as part of the handoff. The next agent will see the parent state.
 5. Indicate to LangGraph that we need to navigate to agent node in a **parent** multi-agent graph.
-   :::
+
+:::

 !!! Note

@@ -159,7 +159,7 @@ function generateCodeSnippet({ tools, pre, post, response }) {
  if (post) lines.push("    post_model_hook=post_model_hook,");
  if (response) lines.push("    response_format=ResponseFormat,");

-  lines.push(")", "", "agent.get_graph().draw_mermaid_png()");
+  lines.push(")", "", "# Visualize the graph", "# For Jupyter or GUI environments:", "agent.get_graph().draw_mermaid_png()", "", "# To save PNG to file:", "png_data = agent.get_graph().draw_mermaid_png()", "with open(\"graph.png\", \"wb\") as f:", "    f.write(png_data)", "", "# For terminal/ASCII output:", "agent.get_graph().draw_ascii()");

  return lines.join("\n");
 }
@@ -21,7 +21,6 @@ Before deploying, review the [conceptual guide for the Standalone Container](../

            `<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_server.md#server-versions)) 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#licensing)) 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.
 1. Egress to `https://beacon.langchain.com` from your network. This is required for license verification and usage reporting if not running in air-gapped mode. See the [Egress documentation](../../cloud/deployment/egress.md) for more details.
@@ -1,16 +1,11 @@
 # LangGraph Server Changelog

+> **Note:** This changelog is no longer actively maintained. For the most up-to-date LangGraph Server changelog, please visit our new documentation site: [LangGraph Server Changelog](https://docs.langchain.com/langgraph-platform/langgraph-server-changelog#langgraph-server-changelog)
+
 [LangGraph Server](../../concepts/langgraph_server.md) is an API platform for creating and managing agent-based applications. It provides built-in persistence, a task queue, and supports deploying, configuring, and running assistants (agentic workflows) at scale. This changelog documents all notable updates, features, and fixes to LangGraph Server releases.

 ---

-## v0.2.113 (2025-07-30)
- Improved thread search pagination by refining response headers for better navigation and accuracy.
-
-## v0.2.112 (2025-07-30)
- Ensured asynchronous handling for sync logging methods and added a linter to prevent future issues.
- Fixed an issue where JavaScript tasks were not populating correctly in graphs.
-
 ## v0.2.111 (2025-07-29)
 - Started the heartbeat immediately upon connection to prevent JS graph streaming errors during long startups.

@@ -35,7 +35,8 @@ LangGraph Platform provides different security defaults:
 - Can be customized with your auth handler

 !!! note "Custom auth"
-Custom auth **is supported** for all plans in LangGraph Platform.
+
+   Custom auth **is supported** for all plans in LangGraph Platform.

 ### Self-Hosted

@@ -43,11 +44,6 @@ Custom auth **is supported** for all plans in LangGraph Platform.
 - Complete flexibility to implement your security model
 - You control all aspects of authentication and authorization

-!!! note "Custom auth"
-
-    Custom auth is supported for **Enterprise** self-hosted deployments.
-    Standalone Container (Lite) deployments do not support custom auth natively.
-
 ## System Architecture

 A typical authentication setup involves three main components:
@@ -7,10 +7,7 @@ search:

 ## Free deployment

-There are two free options for deploying LangGraph applications via the LangGraph Server:
-
-1. [Local](../tutorials/langgraph-platform/local-server.md): Deploy for local testing and development. 
-1. [Standalone Container (Lite)](../concepts/langgraph_standalone_container.md): A limited version of Standalone Container for deployments unlikely to see more than 1 million node executions per year and that do not need crons and other enterprise features. Standalone Container (Lite) deployment option is free with a LangSmith API key.
+[Local](../tutorials/langgraph-platform/local-server.md): Deploy for local testing and development.

 ## Production deployment

@@ -33,8 +30,7 @@ A quick comparison:
 | **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 |
 | **LangSmith compatibility** | Trace to LangSmith SaaS | Trace to LangSmith SaaS | Trace to Self-Hosted LangSmith | Optional tracing |
-| **[Server version compatibility](../concepts/langgraph_server.md#server-versions)** | Enterprise | Enterprise | Enterprise | Lite, Enterprise |
-| **[Pricing](https://www.langchain.com/pricing-langgraph-platform)** | Plus | Enterprise | Enterprise | Developer |
+| **[Pricing](https://www.langchain.com/pricing-langgraph-platform)** | Plus | Enterprise | Enterprise | Enterprise |

 ## Cloud SaaS

@@ -51,6 +51,51 @@ For some examples of pitfalls to avoid, see the [Common Pitfalls](./functional_a
 how to structure your code using **tasks** to avoid these issues. The same principles apply to the @[StateGraph (Graph API)][StateGraph].
 :::

+## Durability modes
+
+LangGraph supports three durability modes that allow you to balance performance and data consistency based on your application's requirements. The durability modes, from least to most durable, are as follows:
+
+- [`"exit"`](#exit)
+- [`"async"`](#async)
+- [`"sync"`](#sync)
+
+A higher durability mode add more overhead to the workflow execution.
+
+!!! version-added "Added in v0.6.0"
+
+    Use the `durability` parameter instead of `checkpoint_during` (deprecated in v0.6.0) for persistence policy management:
+    
+    * `durability="async"` replaces `checkpoint_during=True`
+    * `durability="exit"` replaces `checkpoint_during=False`
+    
+    for persistence policy management, with the following mapping:
+
+    * `checkpoint_during=True` -> `durability="async"`
+    * `checkpoint_during=False` -> `durability="exit"`
+
+
+### `"exit"`
+Changes are persisted only when graph execution completes (either successfully or with an error). This provides the best performance for long-running graphs but means intermediate state is not saved, so you cannot recover from mid-execution failures or interrupt the graph execution.
+
+### `"async"`
+Changes are persisted asynchronously while the next step executes. This provides good performance and durability, but there's a small risk that checkpoints might not be written if the process crashes during execution.
+
+### `"sync"`
+Changes are persisted synchronously before the next step starts. This ensures that every checkpoint is written before continuing execution, providing high durability at the cost of some performance overhead.
+
+You can specify the durability mode when calling any graph execution method:
+
+:::python
+
+```python
+graph.stream(
+    {"input": "test"}, 
+    durability="sync"
+)
+```
+
+:::
+
 ## Using tasks in nodes

 If a [node](./low_level.md#nodes) contains multiple operations, you may find it easier to convert each operation into a **task** rather than refactor the operations into individual nodes.
@@ -13,21 +13,6 @@ Use LangGraph Server to create and manage [assistants](assistants.md), [threads]
  
    For detailed information on the API endpoints and data models, see [LangGraph Platform API reference docs](../cloud/reference/api/api_ref.html).

-## Server versions
-
-There are two versions of LangGraph Server:
-
- `Lite` 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](../concepts/faq.md#what-does-nodes-executed-mean-for-langgraph-platform-usage) per year).
- `Enterprise` 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.
-
-Feature Differences:
-
-|       | Lite       | Enterprise |
-|-------|------------|------------|
-| [Cron Jobs](../cloud/concepts/cron_jobs.md) |❌|✅|
-| [Custom Authentication](../concepts/auth.md) |❌|✅|
-| [Deployment options](../concepts/deployment_options.md) | Standalone container | Cloud SaaS, Self-Hosted Data Plane, Self-Hosted Control Plane, Standalone container
-
 ## Application structure

 To deploy a LangGraph Server application, you need to specify the graph(s) you want to deploy, as well as any relevant configuration settings, such as dependencies and environment variables.
@@ -34,12 +34,3 @@ The Standalone Container deployment option supports deploying data plane infrast
 ### Docker

 The Standalone Container deployment option supports deploying data plane infrastructure to any Docker-supported compute platform.
-
-## Lite vs. Enterprise
-
-The Standalone Container deployment option supports both of the [server versions](../concepts/langgraph_server.md#langgraph-server):
-
- The `Lite` version is free, but has limited features.
- The `Enterprise` version has custom pricing and is fully featured.
-
-For more details on feature difference, see [LangGraph Server](../concepts/langgraph_server.md#server-versions).
@@ -88,8 +88,6 @@ Typically, all graph nodes communicate with a single schema. This means that the

 It is possible to have nodes write to private state channels inside the graph for internal node communication. We can simply define a private schema, `PrivateState`.

-See [this guide](../how-tos/graph-api.ipynb#pass-private-state-between-nodes) for more detail.
-
 It is also possible to define explicit input and output schemas for a graph. In these cases, we define an "internal" schema that contains _all_ keys relevant to graph operations. But, we also define `input` and `output` schemas that are sub-sets of the "internal" schema to constrain the input and output of the graph. See [this guide](../how-tos/graph-api.md#define-input-and-output-schemas) for more detail.

 Let's look at an example:
@@ -473,7 +471,7 @@ const builder = new StateGraph(State);

 :::

-Behind the scenes, functions are converted to [RunnableLambda](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.RunnableLambda.html#langchain_core.runnables.base.RunnableLambda)s, which add batch and async support to your function, along with native tracing and debugging.
+Behind the scenes, functions are converted to [RunnableLambda](https://python.langchain.com/api_reference/core/runnables/langchain_core.runnables.base.RunnableLambda.html)s, which add batch and async support to your function, along with native tracing and debugging.

 If you add a node to a graph without specifying a name, it will be given a default name equivalent to the function name.

@@ -701,7 +699,8 @@ graph.addConditionalEdges("nodeA", routingFunction, {
 :::

 !!! tip
-Use [`Command`](#command) instead of conditional edges if you want to combine state updates and routing in a single function.
+
+    Use [`Command`](#command) instead of conditional edges if you want to combine state updates and routing in a single function.

 ### Entry Point

@@ -820,7 +819,6 @@ def my_node(state: State) -> Command[Literal["my_other_node"]]:
        return Command(update={"foo": "baz"}, goto="my_other_node")
 ```

-Check out this [how-to guide](../how-tos/graph-api.ipynb#combine-control-flow-and-state-updates-with-command) for an end-to-end example of how to use `Command`.
 :::

 :::js
@@ -860,7 +858,6 @@ builder.addNode("myNode", myNode, {
 });
 ```

-Check out this [how-to guide](../how-tos/graph-api.ipynb#combine-control-flow-and-state-updates-with-command) for an end-to-end example of how to use `Command`.
 :::

 !!! important
@@ -6,52 +6,14 @@

 Install the `langchain-mcp-adapters` library to use MCP tools in LangGraph:

+:::python
 ```bash
 pip install langchain-mcp-adapters
 ```
+:::

-## Authenticate to an MCP server
-
-You can set up [custom authentication middleware](../how-tos/auth/custom_auth.md) to authenticate a user with an MCP server to get access to user-scoped tools within your LangGraph Platform deployment.
-
-!!! note
-
-    Custom authentication is a LangGraph Platform feature.
-
-An example architecture for this flow:
-
-```mermaid
-sequenceDiagram
-  %% Actors
-  participant ClientApp as Client
-  participant AuthProv  as Auth Provider
-  participant LangGraph as LangGraph Backend
-  participant SecretStore as Secret Store
-  participant MCPServer as MCP Server
-
-  %% Platform login / AuthN
-  ClientApp  ->> AuthProv: 1. Login (username / password)
-  AuthProv   -->> ClientApp: 2. Return token
-  ClientApp  ->> LangGraph: 3. Request with token
-
-  Note over LangGraph: 4. Validate token (@auth.authenticate)
-  LangGraph  -->> AuthProv: 5. Fetch user info
-  AuthProv   -->> LangGraph: 6. Confirm validity
-
-  %% Fetch user tokens from secret store
-  LangGraph  ->> SecretStore: 6a. Fetch user tokens
-  SecretStore -->> LangGraph: 6b. Return tokens
-
-  Note over LangGraph: 7. Apply access control (@auth.on.*)
-
-  %% MCP round-trip
-  Note over LangGraph: 8. Build MCP client with user token
-  LangGraph  ->> MCPServer: 9. Call MCP tool (with header)
-  Note over MCPServer: 10. MCP validates header and runs tool
-  MCPServer  -->> LangGraph: 11. Tool response
-
-  %% Return to caller
-  LangGraph  -->> ClientApp: 12. Return resources / tool output
+:::js
+```bash
+npm install @langchain/mcp-adapters
 ```
-
-For more information, see [MCP endpoint in LangGraph Server](../concepts/server-mcp.md).
+:::
@@ -10,7 +10,7 @@ search:
 LangGraph Platform is a solution for deploying agentic applications in production.
 There are three different plans for using it.

- **Developer**: All [LangSmith](https://smith.langchain.com/) users have access to this plan. You can sign up for this plan simply by creating a LangSmith account. This gives you access to the [Standalone Container (Lite)](./deployment_options.md) deployment option.
+- **Developer**: All [LangSmith](https://smith.langchain.com/) users have access to this plan. You can sign up for this plan simply by creating a LangSmith account. This gives you access to the [local deployment](./deployment_options.md#free-deployment) option.
 - **Plus**: All [LangSmith](https://smith.langchain.com/) users with a [Plus account](https://docs.smith.langchain.com/administration/pricing) have access to this plan. You can sign up for this plan simply by upgrading your LangSmith account to the Plus plan type. This gives you access to the [Cloud](./deployment_options.md#cloud-saas) deployment option.
 - **Enterprise**: This is separate from LangSmith plans. You can sign up for this plan by contacting sales@langchain.dev. This gives you access to all [deployment options](./deployment_options.md).

@@ -19,8 +19,8 @@ There are three different plans for using it.

 |                                                                  | Developer                                   | Plus                                                  | Enterprise                                          |
 |------------------------------------------------------------------|---------------------------------------------|-------------------------------------------------------|-----------------------------------------------------|
-| Deployment Options                                               | Standalone Container (Lite)                          | Cloud SaaS                                         | <ul><li>Cloud SaaS</li><li>Self-Hosted Data Plane</li><li>Self-Hosted Control Plane</li><li>Standalone Container (Enterprise)</li></ul> |
-| Usage                                                            | Free, limited to 1M [nodes executed](../concepts/faq.md#what-does-nodes-executed-mean-for-langgraph-platform-usage) per year | See [Pricing](https://www.langchain.com/langgraph-platform-pricing) | Custom                                              |
+| Deployment Options                                               | Local                          | Cloud SaaS                                         | <ul><li>Cloud SaaS</li><li>Self-Hosted Data Plane</li><li>Self-Hosted Control Plane</li><li>Standalone Container</li></ul> |
+| Usage                                                            | Free | See [Pricing](https://www.langchain.com/langgraph-platform-pricing) | Custom                                              |
 | APIs for retrieving and updating state and conversational history | ✅                                           | ✅                                                     | ✅                                                   |
 | APIs for retrieving and updating long-term memory                | ✅                                           | ✅                                                     | ✅                                                   |
 | Horizontally scalable task queues and servers                    | ✅                                           | ✅                                                     | ✅                                                   |
@@ -9,15 +9,4 @@ The pages in this section provide end-to-end examples for the following topics:
 - [Agent Supervisor](../tutorials/multi_agent/agent_supervisor.md): Build a supervisor agent that can manage a team of agents.
 - [SQL agent](../tutorials/sql/sql-agent.md): Build a SQL agent that can execute SQL queries and return the results.
 - [Prebuilt chat UI](../agents/ui.md): Use a prebuilt chat UI to interact with any LangGraph agent.
- [Graph runs in LangSmith](../how-tos/run-id-langsmith.md): Use LangSmith to track and analyze graph runs.
-
-## LangGraph Platform
-
- [Set up custom authentication](../tutorials/auth/getting_started.md): Set up custom authentication for your LangGraph application.
- [Make conversations private](../tutorials/auth/resource_auth.md): Make conversations private by using resource-based authentication.
- [Connect an authentication provider](../tutorials/auth/add_auth_server.md): Connect an authentication provider to your LangGraph application.
- [Rebuild graph at runtime](../cloud/deployment/graph_rebuild.md): Rebuild a graph at runtime.
- [Use RemoteGraph](../how-tos/use-remote-graph.md): Use RemoteGraph to deploy your LangGraph application to a remote server.
- [Deploy CrewAI, AutoGen, and other frameworks](../how-tos/autogen-integration.md): Deploy CrewAI, AutoGen, and other frameworks with LangGraph.
- [Integrate LangGraph into a React app](../cloud/how-tos/use_stream_react.md)
- [Implement Generative User Interfaces with LangGraph](../cloud/how-tos/generative_ui_react.md)
+- [Graph runs in LangSmith](../how-tos/run-id-langsmith.md): Use LangSmith to track and analyze graph runs.
@@ -31,15 +31,3 @@ These capabilities are available in both LangGraph OSS and the LangGraph Platfor
 - [MCP](../concepts/mcp.md): Use MCP servers in a LangGraph graph.
 - [Evaluation](../agents/evals.md): Use LangSmith to evaluate your graph's performance.

-## Platform-only capabilities
-
-These capabilities are only available in [LangGraph Platform](../concepts/langgraph_platform.md).
-
- [Authentication and access control](../concepts/auth.md): Authenticate and authorize users to access a LangGraph graph.
- [Assistants](../concepts/assistants.md): Build assistants that can be used to interact with a LangGraph graph.
- [Double-texting](../concepts/double_texting.md): Handle double-texting (consecutive messages before a first response is returned) in a LangGraph graph.
- [Webhooks](../cloud/concepts/webhooks.md): Send webhooks to a LangGraph graph.
- [Cron jobs](../cloud/concepts/cron_jobs.md): Schedule jobs to run at a specific time.
- [Server customization](../how-tos/http/custom_lifespan.md): Customize the server that runs a LangGraph graph.
- [Data management](../cloud/concepts/data_storage_and_privacy.md): Manage data in a LangGraph graph.
- [Deployment](../concepts/deployment_options.md): Deploy a LangGraph graph to a server.
@@ -11,13 +11,13 @@

 ???+ note "Support by deployment type"

-    Custom auth is supported for all deployments in the **managed LangGraph Platform**, as well as **Enterprise** self-hosted plans. It is not supported for **Lite** self-hosted plans.
+    Custom auth is supported for all deployments in the **managed LangGraph Platform**, as well as **Enterprise** self-hosted plans.

 This guide shows how to add custom authentication to your LangGraph Platform application. This guide applies to both LangGraph Platform and self-hosted deployments. It does not apply to isolated usage of the LangGraph open source library in your own custom server.

 !!! note

-    Custom auth is supported for all **managed LangGraph Platform** deployments, as well as **Enterprise** self-hosted plans. It is not supported for **Lite** self-hosted plans.
+    Custom auth is supported for all **managed LangGraph Platform** deployments, as well as **Enterprise** self-hosted plans.

 ## Add custom authentication to your deployment

@@ -145,7 +145,7 @@ def my_node(state, config):
 By default, if you add custom authorization on your resources, this will also apply to interactions made from the Studio. If you want, you can handle logged-in Studio users differently by checking [is_studio_user()](../../reference/functions/sdk_auth.isStudioUser.html).

 !!! note
-`is_studio_user` was added in version 0.1.73 of the langgraph-sdk. If you're on an older version, you can still check whether `isinstance(ctx.user, StudioUser)`.
+    `is_studio_user` was added in version 0.1.73 of the langgraph-sdk. If you're on an older version, you can still check whether `isinstance(ctx.user, StudioUser)`.

 ```python
 from langgraph_sdk.auth import is_studio_user, Auth
@@ -1436,6 +1436,7 @@ await agent.invoke(
 from typing_extensions import TypedDict

 from langgraph.config import get_store
+from langchain_core.runnables import RunnableConfig
 from langgraph.prebuilt import create_react_agent
 from langgraph.store.memory import InMemoryStore

@@ -2797,4 +2798,6 @@ await checkpointer.deleteThread(threadId);
 ## Prebuilt memory tools

 **LangMem** is a LangChain-maintained library that offers tools for managing long-term memories in your agent. See the [LangMem documentation](https://langchain-ai.github.io/langmem/) for usage examples.
+
 :::
+
@@ -22,6 +22,7 @@ To set up communication between the agents in a multi-agent system you can use [

 To implement handoffs, you can return `Command` objects from your agent nodes or tools:

+:::python
 ```python
 from typing import Annotated
 from langchain_core.tools import tool, InjectedToolCallId
@@ -57,7 +58,7 @@ def create_handoff_tool(*, agent_name: str, description: str | None = None):
    return handoff_tool
 ```

-1. Access the [state](../concepts/low_level.md#state) of the agent that is calling the handoff tool using the @[InjectedState][InjectedState] annotation. 
+1. Access the [state](../concepts/low_level.md#state) of the agent that is calling the handoff tool using the @[InjectedState] annotation. 
 2. The `Command` primitive allows specifying a state update and a node transition as a single operation, making it useful for implementing handoffs.
 3. Name of the agent or node to hand off to.
 4. Take the agent's messages and **add** them to the parent's **state** as part of the handoff. The next agent will see the parent state.
@@ -73,25 +74,109 @@ def create_handoff_tool(*, agent_name: str, description: str | None = None):
        commands = [tools_by_name[tool_call["name"]].invoke(tool_call) for tool_call in tool_calls]
        return commands
    ```
+:::
+
+:::js
+```typescript
+import { tool } from "@langchain/core/tools";
+import { Command, MessagesZodState } from "@langchain/langgraph";
+import { z } from "zod";
+
+function createHandoffTool({
+  agentName,
+  description,
+}: {
+  agentName: string;
+  description?: string;
+}) {
+  const name = `transfer_to_${agentName}`;
+  const toolDescription = description || `Transfer to ${agentName}`;
+
+  return tool(
+    async (_, config) => {
+      // (1)!
+      const state = config.state;
+      const toolCallId = config.toolCall.id;
+
+      const toolMessage = {
+        role: "tool" as const,
+        content: `Successfully transferred to ${agentName}`,
+        name: name,
+        tool_call_id: toolCallId,
+      };
+
+      return new Command({
+        // (3)!
+        goto: agentName,
+        // (4)!
+        update: { messages: [...state.messages, toolMessage] },
+        // (5)!
+        graph: Command.PARENT,
+      });
+    },
+    {
+      name,
+      description: toolDescription,
+      schema: z.object({}),
+    }
+  );
+}
+```
+
+1. Access the [state](../concepts/low_level.md#state) of the agent that is calling the handoff tool through the `config` parameter.
+2. The `Command` primitive allows specifying a state update and a node transition as a single operation, making it useful for implementing handoffs.
+3. Name of the agent or node to hand off to.
+4. Take the agent's messages and **add** them to the parent's **state** as part of the handoff. The next agent will see the parent state.
+5. Indicate to LangGraph that we need to navigate to agent node in a **parent** multi-agent graph.
+
+!!! tip
+
+    If you want to use tools that return `Command`, you can either use prebuilt @[`create_react_agent`][create_react_agent] / @[`ToolNode`][ToolNode] components, or implement your own tool-executing node that collects `Command` objects returned by the tools and returns a list of them, e.g.:
+    
+    ```typescript
+    const callTools = async (state) => {
+      // ...
+      const commands = await Promise.all(
+        toolCalls.map(toolCall => toolsByName[toolCall.name].invoke(toolCall))
+      );
+      return commands;
+    };
+    ```
+:::

 !!! Important

    This handoff implementation assumes that:
    
-      - each agent receives overall message history (across all agents) in the multi-agent system as its input. If you want more control over agent inputs, see [this section](#control-agent-inputs)
-      - each agent outputs its internal messages history to the overall message history of the multi-agent system. If you want more control over **how agent outputs are added**, wrap the agent in a separate node function:
+    - each agent receives overall message history (across all agents) in the multi-agent system as its input. If you want more control over agent inputs, see [this section](#control-agent-inputs)
+    - each agent outputs its internal messages history to the overall message history of the multi-agent system. If you want more control over **how agent outputs are added**, wrap the agent in a separate node function:

-        ```python
-        def call_hotel_assistant(state):
-            # return agent's final response,
-            # excluding inner monologue
-            response = hotel_assistant.invoke(state)
-            # highlight-next-line
-            return {"messages": response["messages"][-1]}
-        ```
+      :::python
+      ```python
+      def call_hotel_assistant(state):
+          # return agent's final response,
+          # excluding inner monologue
+          response = hotel_assistant.invoke(state)
+          # highlight-next-line
+          return {"messages": response["messages"][-1]}
+      ```
+      :::
+
+      :::js
+      ```typescript
+      const callHotelAssistant = async (state) => {
+        // return agent's final response,
+        // excluding inner monologue
+        const response = await hotelAssistant.invoke(state);
+        // highlight-next-line
+        return { messages: [response.messages.at(-1)] };
+      };
+      ```
+      :::

 ### Control agent inputs

+:::python
 You can use the @[`Send()`][Send] primitive to directly send data to the worker agents during the handoff. For example, you can request that the calling agent populate a task description for the next agent:

 ```python
@@ -129,6 +214,63 @@ def create_task_description_handoff_tool(

    return handoff_tool
 ```
+:::
+
+:::js
+You can use the @[`Send()`][Send] primitive to directly send data to the worker agents during the handoff. For example, you can request that the calling agent populate a task description for the next agent:
+
+```typescript
+import { tool } from "@langchain/core/tools";
+import { Command, Send, MessagesZodState } from "@langchain/langgraph";
+import { z } from "zod";
+
+function createTaskDescriptionHandoffTool({
+  agentName,
+  description,
+}: {
+  agentName: string;
+  description?: string;
+}) {
+  const name = `transfer_to_${agentName}`;
+  const toolDescription = description || `Ask ${agentName} for help.`;
+
+  return tool(
+    async (
+      { taskDescription },
+      config
+    ) => {
+      const state = config.state;
+      
+      const taskDescriptionMessage = {
+        role: "user" as const,
+        content: taskDescription,
+      };
+      const agentInput = {
+        ...state,
+        messages: [taskDescriptionMessage],
+      };
+      
+      return new Command({
+        // highlight-next-line
+        goto: [new Send(agentName, agentInput)],
+        graph: Command.PARENT,
+      });
+    },
+    {
+      name,
+      description: toolDescription,
+      schema: z.object({
+        taskDescription: z
+          .string()
+          .describe(
+            "Description of what the next agent should do, including all of the relevant context."
+          ),
+      }),
+    }
+  );
+}
+```
+:::

 See the multi-agent [supervisor](../tutorials/multi_agent/agent_supervisor.md#4-create-delegation-tasks) example for a full example of using @[`Send()`][Send] in handoffs.

@@ -136,6 +278,7 @@ See the multi-agent [supervisor](../tutorials/multi_agent/agent_supervisor.md#4-

 You can use handoffs in any agents built with LangGraph. We recommend using the prebuilt [agent](../agents/overview.md) or [`ToolNode`](./tool-calling.md#toolnode), as they natively support handoffs tools returning `Command`. Below is an example of how you can implement a multi-agent system for booking travel using handoffs:

+:::python
 ```python
 from langgraph.prebuilt import create_react_agent
 from langgraph.graph import StateGraph, START, MessagesState
@@ -176,9 +319,65 @@ multi_agent_graph = (
    .compile()
 )
 ```
+:::
+
+:::js
+```typescript
+import { createReactAgent } from "@langchain/langgraph/prebuilt";
+import { StateGraph, START, MessagesZodState } from "@langchain/langgraph";
+import { z } from "zod";
+
+function createHandoffTool({
+  agentName,
+  description,
+}: {
+  agentName: string;
+  description?: string;
+}) {
+  // same implementation as above
+  // ...
+  return new Command(/* ... */);
+}
+
+// Handoffs
+const transferToHotelAssistant = createHandoffTool({
+  agentName: "hotel_assistant",
+});
+const transferToFlightAssistant = createHandoffTool({
+  agentName: "flight_assistant",
+});
+
+// Define agents
+const flightAssistant = createReactAgent({
+  llm: model,
+  // highlight-next-line
+  tools: [/* ... */, transferToHotelAssistant],
+  // highlight-next-line
+  name: "flight_assistant",
+});
+
+const hotelAssistant = createReactAgent({
+  llm: model,
+  // highlight-next-line
+  tools: [/* ... */, transferToFlightAssistant],
+  // highlight-next-line
+  name: "hotel_assistant",
+});
+
+// Define multi-agent graph
+const multiAgentGraph = new StateGraph(MessagesZodState)
+  // highlight-next-line
+  .addNode("flight_assistant", flightAssistant)
+  // highlight-next-line
+  .addNode("hotel_assistant", hotelAssistant)
+  .addEdge(START, "flight_assistant")
+  .compile();
+```
+:::

 ??? example "Full example: Multi-agent system for booking travel"

+    :::python
    ```python
    from typing import Annotated
    from langchain_core.messages import convert_to_messages
@@ -323,6 +522,183 @@ multi_agent_graph = (
    3. Name of the agent or node to hand off to.
    4. Take the agent's messages and **add** them to the parent's **state** as part of the handoff. The next agent will see the parent state.
    5. Indicate to LangGraph that we need to navigate to agent node in a **parent** multi-agent graph.
+    :::
+
+    :::js
+    ```typescript
+    import { tool } from "@langchain/core/tools";
+    import { createReactAgent } from "@langchain/langgraph/prebuilt";
+    import { StateGraph, START, MessagesZodState, Command } from "@langchain/langgraph";
+    import { ChatAnthropic } from "@langchain/anthropic";
+    import { isBaseMessage } from "@langchain/core/messages";
+    import { z } from "zod";
+
+    // We'll use a helper to render the streamed agent outputs nicely
+    const prettyPrintMessages = (update: Record<string, any>) => {
+      // Handle tuple case with namespace
+      if (Array.isArray(update)) {
+        const [ns, updateData] = update;
+        // Skip parent graph updates in the printouts
+        if (ns.length === 0) {
+          return;
+        }
+
+        const graphId = ns[ns.length - 1].split(":")[0];
+        console.log(`Update from subgraph ${graphId}:\n`);
+        update = updateData;
+      }
+
+      for (const [nodeName, updateValue] of Object.entries(update)) {
+        console.log(`Update from node ${nodeName}:\n`);
+
+        const messages = updateValue.messages || [];
+        for (const message of messages) {
+          if (isBaseMessage(message)) {
+            const textContent =
+              typeof message.content === "string"
+                ? message.content
+                : JSON.stringify(message.content);
+            console.log(`${message.getType()}: ${textContent}`);
+          }
+        }
+        console.log("\n");
+      }
+    };
+
+    function createHandoffTool({
+      agentName,
+      description,
+    }: {
+      agentName: string;
+      description?: string;
+    }) {
+      const name = `transfer_to_${agentName}`;
+      const toolDescription = description || `Transfer to ${agentName}`;
+
+      return tool(
+        async (_, config) => {
+          // highlight-next-line
+          const state = config.state; // (1)!
+          const toolCallId = config.toolCall.id;
+
+          const toolMessage = {
+            role: "tool" as const,
+            content: `Successfully transferred to ${agentName}`,
+            name: name,
+            tool_call_id: toolCallId,
+          };
+
+          return new Command({
+            // highlight-next-line
+            goto: agentName, // (3)!
+            // highlight-next-line
+            update: { messages: [...state.messages, toolMessage] }, // (4)!
+            // highlight-next-line
+            graph: Command.PARENT, // (5)!
+          });
+        },
+        {
+          name,
+          description: toolDescription,
+          schema: z.object({}),
+        }
+      );
+    }
+
+    // Handoffs
+    const transferToHotelAssistant = createHandoffTool({
+      agentName: "hotel_assistant",
+      description: "Transfer user to the hotel-booking assistant.",
+    });
+
+    const transferToFlightAssistant = createHandoffTool({
+      agentName: "flight_assistant",
+      description: "Transfer user to the flight-booking assistant.",
+    });
+
+    // Simple agent tools
+    const bookHotel = tool(
+      async ({ hotelName }) => {
+        return `Successfully booked a stay at ${hotelName}.`;
+      },
+      {
+        name: "book_hotel",
+        description: "Book a hotel",
+        schema: z.object({
+          hotelName: z.string(),
+        }),
+      }
+    );
+
+    const bookFlight = tool(
+      async ({ fromAirport, toAirport }) => {
+        return `Successfully booked a flight from ${fromAirport} to ${toAirport}.`;
+      },
+      {
+        name: "book_flight",
+        description: "Book a flight",
+        schema: z.object({
+          fromAirport: z.string(),
+          toAirport: z.string(),
+        }),
+      }
+    );
+
+    const model = new ChatAnthropic({
+      model: "claude-3-5-sonnet-latest",
+    });
+
+    // Define agents
+    const flightAssistant = createReactAgent({
+      llm: model,
+      // highlight-next-line
+      tools: [bookFlight, transferToHotelAssistant],
+      prompt: "You are a flight booking assistant",
+      // highlight-next-line
+      name: "flight_assistant",
+    });
+
+    const hotelAssistant = createReactAgent({
+      llm: model,
+      // highlight-next-line
+      tools: [bookHotel, transferToFlightAssistant],
+      prompt: "You are a hotel booking assistant",
+      // highlight-next-line
+      name: "hotel_assistant",
+    });
+
+    // Define multi-agent graph
+    const multiAgentGraph = new StateGraph(MessagesZodState)
+      .addNode("flight_assistant", flightAssistant)
+      .addNode("hotel_assistant", hotelAssistant)
+      .addEdge(START, "flight_assistant")
+      .compile();
+
+    // Run the multi-agent graph
+    const stream = await multiAgentGraph.stream(
+      {
+        messages: [
+          {
+            role: "user",
+            content: "book a flight from BOS to JFK and a stay at McKittrick Hotel",
+          },
+        ],
+      },
+      // highlight-next-line
+      { subgraphs: true }
+    );
+
+    for await (const chunk of stream) {
+      prettyPrintMessages(chunk);
+    }
+    ```
+
+    1. Access agent's state
+    2. The `Command` primitive allows specifying a state update and a node transition as a single operation, making it useful for implementing handoffs.
+    3. Name of the agent or node to hand off to.
+    4. Take the agent's messages and **add** them to the parent's **state** as part of the handoff. The next agent will see the parent state.
+    5. Indicate to LangGraph that we need to navigate to agent node in a **parent** multi-agent graph.
+    :::

 ## Multi-turn conversation

@@ -333,6 +709,7 @@ The agents can then be implemented as nodes in a graph that executes agent steps
 1. **Wait for user input** to continue the conversation, or  
 2. **Route to another agent** (or back to itself, such as in a loop) via a [handoff](#handoffs)

+:::python
 ```python
 def human(state) -> Command[Literal["agent", "another_agent"]]:
    """A node for collecting user input."""
@@ -360,6 +737,44 @@ def agent(state) -> Command[Literal["agent", "another_agent", "human"]]:
    else:
        return Command(goto="human") # Go to human node
 ```
+:::
+
+:::js
+```typescript
+import { interrupt, Command } from "@langchain/langgraph";
+
+function human(state: MessagesState): Command {
+  const userInput: string = interrupt("Ready for user input.");
+
+  // Determine the active agent
+  const activeAgent = /* ... */;
+
+  return new Command({
+    update: {
+      messages: [{
+        role: "human",
+        content: userInput,
+      }]
+    },
+    goto: activeAgent,
+  });
+}
+
+function agent(state: MessagesState): Command {
+  // The condition for routing/halting can be anything, e.g. LLM tool call / structured output, etc.
+  const goto = getNextAgent(/* ... */); // 'agent' / 'anotherAgent'
+
+  if (goto) {
+    return new Command({
+      goto,
+      update: { myStateKey: "myStateValue" }
+    });
+  }
+
+  return new Command({ goto: "human" });
+}
+```
+:::

 ??? example "Full example: multi-agent system for travel recommendations"

@@ -370,6 +785,7 @@ def agent(state) -> Command[Literal["agent", "another_agent", "human"]]:
    * travel_advisor: can help with travel destination recommendations. Can ask hotel_advisor for help.
    * hotel_advisor: can help with hotel recommendations. Can ask travel_advisor for help.

+    :::python
    ```python
    from langchain_anthropic import ChatAnthropic
    from langgraph.graph import MessagesState, StateGraph, START
@@ -571,10 +987,267 @@ def agent(state) -> Command[Literal["agent", "another_agent", "human"]]:
    
    Would you like more specific information about any of these activities or would you like to know about other options in the area?
    ```
+    :::
+
+    :::js
+    ```typescript
+    import { ChatAnthropic } from "@langchain/anthropic";
+    import { StateGraph, START, MessagesZodState, Command, interrupt, MemorySaver } from "@langchain/langgraph";
+    import { createReactAgent } from "@langchain/langgraph/prebuilt";
+    import { tool } from "@langchain/core/tools";
+    import { z } from "zod";
+
+    const model = new ChatAnthropic({ model: "claude-3-5-sonnet-latest" });
+
+    const MultiAgentState = MessagesZodState.extend({
+      lastActiveAgent: z.string().optional(),
+    });
+
+    // Define travel advisor tools
+    const getTravelRecommendations = tool(
+      async () => {
+        // Placeholder implementation
+        return "Based on current trends, I recommend visiting Japan, Portugal, or New Zealand.";
+      },
+      {
+        name: "get_travel_recommendations",
+        description: "Get current travel destination recommendations",
+        schema: z.object({}),
+      }
+    );
+
+    const makeHandoffTool = (agentName: string) => {
+      return tool(
+        async (_, config) => {
+          const state = config.state;
+          const toolCallId = config.toolCall.id;
+
+          const toolMessage = {
+            role: "tool" as const,
+            content: `Successfully transferred to ${agentName}`,
+            name: `transfer_to_${agentName}`,
+            tool_call_id: toolCallId,
+          };
+
+          return new Command({
+            goto: agentName,
+            update: { messages: [...state.messages, toolMessage] },
+            graph: Command.PARENT,
+          });
+        },
+        {
+          name: `transfer_to_${agentName}`,
+          description: `Transfer to ${agentName}`,
+          schema: z.object({}),
+        }
+      );
+    };
+
+    const travelAdvisorTools = [
+      getTravelRecommendations,
+      makeHandoffTool("hotel_advisor"),
+    ];
+
+    const travelAdvisor = createReactAgent({
+      llm: model,
+      tools: travelAdvisorTools,
+      prompt: [
+        "You are a general travel expert that can recommend travel destinations (e.g. countries, cities, etc). ",
+        "If you need hotel recommendations, ask 'hotel_advisor' for help. ",
+        "You MUST include human-readable response before transferring to another agent."
+      ].join("")
+    });
+
+    const callTravelAdvisor = async (
+      state: z.infer<typeof MultiAgentState>
+    ): Promise<Command> => {
+      const response = await travelAdvisor.invoke(state);
+      const update = { ...response, lastActiveAgent: "travel_advisor" };
+      return new Command({ update, goto: "human" });
+    };
+
+    // Define hotel advisor tools
+    const getHotelRecommendations = tool(
+      async () => {
+        // Placeholder implementation
+        return "I recommend the Ritz-Carlton for luxury stays or boutique hotels for unique experiences.";
+      },
+      {
+        name: "get_hotel_recommendations",
+        description: "Get hotel recommendations for destinations",
+        schema: z.object({}),
+      }
+    );
+
+    const hotelAdvisorTools = [
+      getHotelRecommendations,
+      makeHandoffTool("travel_advisor"),
+    ];
+
+    const hotelAdvisor = createReactAgent({
+      llm: model,
+      tools: hotelAdvisorTools,
+      prompt: [
+        "You are a hotel expert that can provide hotel recommendations for a given destination. ",
+        "If you need help picking travel destinations, ask 'travel_advisor' for help.",
+        "You MUST include human-readable response before transferring to another agent."
+      ].join("")
+    });
+
+    const callHotelAdvisor = async (
+      state: z.infer<typeof MultiAgentState>
+    ): Promise<Command> => {
+      const response = await hotelAdvisor.invoke(state);
+      const update = { ...response, lastActiveAgent: "hotel_advisor" };
+      return new Command({ update, goto: "human" });
+    };
+
+    const humanNode = async (
+      state: z.infer<typeof MultiAgentState>
+    ): Promise<Command> => {
+      const userInput: string = interrupt("Ready for user input.");
+      const activeAgent = state.lastActiveAgent || "travel_advisor";
+
+      return new Command({
+        update: {
+          messages: [
+            {
+              role: "human",
+              content: userInput,
+            }
+          ]
+        },
+        goto: activeAgent,
+      });
+    };
+
+    const builder = new StateGraph(MultiAgentState)
+      .addNode("travel_advisor", callTravelAdvisor)
+      .addNode("hotel_advisor", callHotelAdvisor)
+      .addNode("human", humanNode)
+      .addEdge(START, "travel_advisor");
+
+    const checkpointer = new MemorySaver();
+    const graph = builder.compile({ checkpointer });
+    ```
+    
+    Let's test a multi turn conversation with this application.
+
+    ```typescript
+    import { v4 as uuidv4 } from "uuid";
+    import { Command } from "@langchain/langgraph";
+
+    const threadConfig = { configurable: { thread_id: uuidv4() } };
+
+    const inputs = [
+      // 1st round of conversation
+      {
+        messages: [
+          { role: "user", content: "i wanna go somewhere warm in the caribbean" }
+        ]
+      },
+      // Since we're using `interrupt`, we'll need to resume using the Command primitive.
+      // 2nd round of conversation
+      new Command({
+        resume: "could you recommend a nice hotel in one of the areas and tell me which area it is."
+      }),
+      // 3rd round of conversation
+      new Command({
+        resume: "i like the first one. could you recommend something to do near the hotel?"
+      }),
+    ];
+
+    for (const [idx, userInput] of inputs.entries()) {
+      console.log();
+      console.log(`--- Conversation Turn ${idx + 1} ---`);
+      console.log();
+      console.log(`User: ${JSON.stringify(userInput)}`);
+      console.log();
+      
+      for await (const update of await graph.stream(
+        userInput,
+        { ...threadConfig, streamMode: "updates" }
+      )) {
+        for (const [nodeId, value] of Object.entries(update)) {
+          if (value?.messages?.length) {
+            const lastMessage = value.messages.at(-1);
+            if (lastMessage?.getType?.() === "ai") {
+              console.log(`${nodeId}: ${lastMessage.content}`);
+            }
+          }
+        }
+      }
+    }
+    ```
+    
+    ```
+    --- Conversation Turn 1 ---
+    
+    User: {"messages":[{"role":"user","content":"i wanna go somewhere warm in the caribbean"}]}
+    
+    travel_advisor: Based on the recommendations, Aruba would be an excellent choice for your Caribbean getaway! Aruba is known as "One Happy Island" and offers:
+    - Year-round warm weather with consistent temperatures around 82°F (28°C)
+    - Beautiful white sand beaches like Eagle Beach and Palm Beach
+    - Clear turquoise waters perfect for swimming and snorkeling
+    - Minimal rainfall and location outside the hurricane belt
+    - A blend of Caribbean and Dutch culture
+    - Great dining options and nightlife
+    - Various water sports and activities
+    
+    Would you like me to get some specific hotel recommendations in Aruba for your stay? I can transfer you to our hotel advisor who can help with accommodations.
+    
+    --- Conversation Turn 2 ---
+    
+    User: Command { resume: 'could you recommend a nice hotel in one of the areas and tell me which area it is.' }
+    
+    hotel_advisor: Based on the recommendations, I can suggest two excellent options:
+    
+    1. The Ritz-Carlton, Aruba - Located in Palm Beach
+    - This luxury resort is situated in the vibrant Palm Beach area
+    - Known for its exceptional service and amenities
+    - Perfect if you want to be close to dining, shopping, and entertainment
+    - Features multiple restaurants, a casino, and a world-class spa
+    - Located on a pristine stretch of Palm Beach
+    
+    2. Bucuti & Tara Beach Resort - Located in Eagle Beach
+    - An adults-only boutique resort on Eagle Beach
+    - Known for being more intimate and peaceful
+    - Award-winning for its sustainability practices
+    - Perfect for a romantic getaway or peaceful vacation
+    - Located on one of the most beautiful beaches in the Caribbean
+    
+    Would you like more specific information about either of these properties or their locations?
+    
+    --- Conversation Turn 3 ---
+    
+    User: Command { resume: 'i like the first one. could you recommend something to do near the hotel?' }
+    
+    travel_advisor: Near the Ritz-Carlton in Palm Beach, here are some highly recommended activities:
+    
+    1. Visit the Palm Beach Plaza Mall - Just a short walk from the hotel, featuring shopping, dining, and entertainment
+    2. Try your luck at the Stellaris Casino - It's right in the Ritz-Carlton
+    3. Take a sunset sailing cruise - Many depart from the nearby pier
+    4. Visit the California Lighthouse - A scenic landmark just north of Palm Beach
+    5. Enjoy water sports at Palm Beach:
+       - Jet skiing
+       - Parasailing
+       - Snorkeling
+       - Stand-up paddleboarding
+    
+    Would you like more specific information about any of these activities or would you like to know about other options in the area?
+    ```
+    :::

 ## Prebuilt implementations

 LangGraph comes with prebuilt implementations of two of the most popular multi-agent architectures:

+:::python
 - [supervisor](../agents/multi-agent.md#supervisor) — individual agents are coordinated by a central supervisor agent. The supervisor controls all communication flow and task delegation, making decisions about which agent to invoke based on the current context and task requirements. You can use [`langgraph-supervisor`](https://github.com/langchain-ai/langgraph-supervisor-py) library to create a supervisor multi-agent systems.
- [swarm](../agents/multi-agent.md#supervisor) — agents dynamically hand off control to one another based on their specializations. The system remembers which agent was last active, ensuring that on subsequent interactions, the conversation resumes with that agent. You can use [`langgraph-swarm`](https://github.com/langchain-ai/langgraph-swarm-py) library to create a swarm multi-agent systems. 
+- [swarm](../agents/multi-agent.md#supervisor) — agents dynamically hand off control to one another based on their specializations. The system remembers which agent was last active, ensuring that on subsequent interactions, the conversation resumes with that agent. You can use [`langgraph-swarm`](https://github.com/langchain-ai/langgraph-swarm-py) library to create a swarm multi-agent systems.
+:::
+
+:::js
+- [supervisor](../agents/multi-agent.md#supervisor) — individual agents are coordinated by a central supervisor agent. The supervisor controls all communication flow and task delegation, making decisions about which agent to invoke based on the current context and task requirements. You can use [`langgraph-supervisor`](https://github.com/langchain-ai/langgraph-supervisor-js) library to create a supervisor multi-agent systems.
+- [swarm](../agents/multi-agent.md#supervisor) — agents dynamically hand off control to one another based on their specializations. The system remembers which agent was last active, ensuring that on subsequent interactions, the conversation resumes with that agent. You can use [`langgraph-swarm`](https://github.com/langchain-ai/langgraph-swarm-js) library to create a swarm multi-agent systems.
+:::
@@ -9,11 +9,20 @@ When adding subgraphs, you need to define how the parent graph and the subgraph

 ## Setup

+:::python
 ```bash
 pip install -U langgraph
 ```
+:::
+
+:::js
+```bash
+npm install @langchain/langgraph
+```
+:::

 !!! tip "Set up LangSmith for LangGraph development"
+
    Sign up for [LangSmith](https://smith.langchain.com) to quickly spot issues and improve the performance of your LangGraph projects. LangSmith lets you use trace data to debug, test, and monitor your LLM apps built with LangGraph — read more about how to get started [here](https://docs.smith.langchain.com).

 ## Shared state schemas
@@ -22,6 +31,7 @@ A common case is for the parent graph and subgraph to communicate over a shared

 If your subgraph shares state keys with the parent graph, you can follow these steps to add it to your graph:

+:::python
 1. Define the subgraph workflow (`subgraph_builder` in the example below) and compile it
 2. Pass compiled subgraph to the `.add_node` method when defining the parent graph workflow

@@ -49,9 +59,41 @@ builder.add_node("node_1", subgraph)
 builder.add_edge(START, "node_1")
 graph = builder.compile()
 ```
+:::
+
+:::js
+1. Define the subgraph workflow (`subgraphBuilder` in the example below) and compile it
+2. Pass compiled subgraph to the `.addNode` method when defining the parent graph workflow
+
+```typescript
+import { StateGraph, START } from "@langchain/langgraph";
+import { z } from "zod";
+
+const State = z.object({
+  foo: z.string(),
+});
+
+// Subgraph
+const subgraphBuilder = new StateGraph(State)
+  .addNode("subgraphNode1", (state) => {
+    return { foo: "hi! " + state.foo };
+  })
+  .addEdge(START, "subgraphNode1");
+
+const subgraph = subgraphBuilder.compile();
+
+// Parent graph
+const builder = new StateGraph(State)
+  .addNode("node1", subgraph)
+  .addEdge(START, "node1");
+
+const graph = builder.compile();
+```
+:::

 ??? example "Full example: shared state schemas"

+    :::python
    ```python
    from typing_extensions import TypedDict
    from langgraph.graph.state import StateGraph, START
@@ -101,6 +143,61 @@ graph = builder.compile()
    {'node_1': {'foo': 'hi! foo'}}
    {'node_2': {'foo': 'hi! foobar'}}
    ```
+    :::
+
+    :::js
+    ```typescript
+    import { StateGraph, START } from "@langchain/langgraph";
+    import { z } from "zod";
+
+    // Define subgraph
+    const SubgraphState = z.object({
+      foo: z.string(),  // (1)! 
+      bar: z.string(),  // (2)!
+    });
+    
+    const subgraphBuilder = new StateGraph(SubgraphState)
+      .addNode("subgraphNode1", (state) => {
+        return { bar: "bar" };
+      })
+      .addNode("subgraphNode2", (state) => {
+        // note that this node is using a state key ('bar') that is only available in the subgraph
+        // and is sending update on the shared state key ('foo')
+        return { foo: state.foo + state.bar };
+      })
+      .addEdge(START, "subgraphNode1")
+      .addEdge("subgraphNode1", "subgraphNode2");
+    
+    const subgraph = subgraphBuilder.compile();
+    
+    // Define parent graph
+    const ParentState = z.object({
+      foo: z.string(),
+    });
+    
+    const builder = new StateGraph(ParentState)
+      .addNode("node1", (state) => {
+        return { foo: "hi! " + state.foo };
+      })
+      .addNode("node2", subgraph)
+      .addEdge(START, "node1")
+      .addEdge("node1", "node2");
+    
+    const graph = builder.compile();
+    
+    for await (const chunk of await graph.stream({ foo: "foo" })) {
+      console.log(chunk);
+    }
+    ```
+
+    3. This key is shared with the parent graph state
+    4. This key is private to the `SubgraphState` and is not visible to the parent graph
+    
+    ```
+    { node1: { foo: 'hi! foo' } }
+    { node2: { foo: 'hi! foobar' } }
+    ```
+    :::

 ## Different state schemas

@@ -108,6 +205,7 @@ For more complex systems you might want to define subgraphs that have a **comple

 If that's the case for your application, you need to define a node **function that invokes the subgraph**. This function needs to transform the input (parent) state to the subgraph state before invoking the subgraph, and transform the results back to the parent state before returning the state update from the node.

+:::python
 ```python
 from typing_extensions import TypedDict
 from langgraph.graph.state import StateGraph, START
@@ -142,9 +240,48 @@ graph = builder.compile()

 1. Transform the state to the subgraph state
 2. Transform response back to the parent state
+:::
+
+:::js
+```typescript
+import { StateGraph, START } from "@langchain/langgraph";
+import { z } from "zod";
+
+const SubgraphState = z.object({
+  bar: z.string(),
+});
+
+// Subgraph
+const subgraphBuilder = new StateGraph(SubgraphState)
+  .addNode("subgraphNode1", (state) => {
+    return { bar: "hi! " + state.bar };
+  })
+  .addEdge(START, "subgraphNode1");
+
+const subgraph = subgraphBuilder.compile();
+
+// Parent graph
+const State = z.object({
+  foo: z.string(),
+});
+
+const builder = new StateGraph(State)
+  .addNode("node1", async (state) => {
+    const subgraphOutput = await subgraph.invoke({ bar: state.foo }); // (1)!
+    return { foo: subgraphOutput.bar }; // (2)!
+  })
+  .addEdge(START, "node1");
+
+const graph = builder.compile();
+```
+
+1. Transform the state to the subgraph state
+2. Transform response back to the parent state
+:::

 ??? example "Full example: different state schemas"

+    :::python
    ```python
    from typing_extensions import TypedDict
    from langgraph.graph.state import StateGraph, START
@@ -200,11 +337,74 @@ graph = builder.compile()
    (('node_2:9c36dd0f-151a-cb42-cbad-fa2f851f9ab7',), {'grandchild_2': {'bar': 'hi! foobaz'}})
    ((), {'node_2': {'foo': 'hi! foobaz'}})
    ```
+    :::
+
+    :::js
+    ```typescript
+    import { StateGraph, START } from "@langchain/langgraph";
+    import { z } from "zod";
+
+    // Define subgraph
+    const SubgraphState = z.object({
+      // note that none of these keys are shared with the parent graph state
+      bar: z.string(),
+      baz: z.string(),
+    });
+    
+    const subgraphBuilder = new StateGraph(SubgraphState)
+      .addNode("subgraphNode1", (state) => {
+        return { baz: "baz" };
+      })
+      .addNode("subgraphNode2", (state) => {
+        return { bar: state.bar + state.baz };
+      })
+      .addEdge(START, "subgraphNode1")
+      .addEdge("subgraphNode1", "subgraphNode2");
+    
+    const subgraph = subgraphBuilder.compile();
+    
+    // Define parent graph
+    const ParentState = z.object({
+      foo: z.string(),
+    });
+    
+    const builder = new StateGraph(ParentState)
+      .addNode("node1", (state) => {
+        return { foo: "hi! " + state.foo };
+      })
+      .addNode("node2", async (state) => {
+        const response = await subgraph.invoke({ bar: state.foo }); // (1)!
+        return { foo: response.bar }; // (2)!
+      })
+      .addEdge(START, "node1")
+      .addEdge("node1", "node2");
+    
+    const graph = builder.compile();
+    
+    for await (const chunk of await graph.stream(
+      { foo: "foo" }, 
+      { subgraphs: true }
+    )) {
+      console.log(chunk);
+    }
+    ```
+
+    3. Transform the state to the subgraph state
+    4. Transform response back to the parent state
+
+    ```
+    [[], { node1: { foo: 'hi! foo' } }]
+    [['node2:9c36dd0f-151a-cb42-cbad-fa2f851f9ab7'], { subgraphNode1: { baz: 'baz' } }]
+    [['node2:9c36dd0f-151a-cb42-cbad-fa2f851f9ab7'], { subgraphNode2: { bar: 'hi! foobaz' } }]
+    [[], { node2: { foo: 'hi! foobaz' } }]
+    ```
+    :::

 ??? example "Full example: different state schemas (two levels of subgraphs)"

    This is an example with two levels of subgraphs: parent -> child -> grandchild.

+    :::python
    ```python
    # Grandchild graph
    from typing_extensions import TypedDict
@@ -288,14 +488,102 @@ graph = builder.compile()
    ((), {'child': {'my_key': 'hi Bob, how are you today?'}})
    ((), {'parent_2': {'my_key': 'hi Bob, how are you today? bye!'}})
    ```
+    :::
+
+    :::js
+    ```typescript
+    import { StateGraph, START, END } from "@langchain/langgraph";
+    import { z } from "zod";
+
+    // Grandchild graph
+    const GrandChildState = z.object({
+      myGrandchildKey: z.string(),
+    });
+    
+    const grandchild = new StateGraph(GrandChildState)
+      .addNode("grandchild1", (state) => {
+        // NOTE: child or parent keys will not be accessible here
+        return { myGrandchildKey: state.myGrandchildKey + ", how are you" };
+      })
+      .addEdge(START, "grandchild1")
+      .addEdge("grandchild1", END);
+    
+    const grandchildGraph = grandchild.compile();
+    
+    // Child graph
+    const ChildState = z.object({
+      myChildKey: z.string(),
+    });
+    
+    const child = new StateGraph(ChildState)
+      .addNode("child1", async (state) => {
+        // NOTE: parent or grandchild keys won't be accessible here
+        const grandchildGraphInput = { myGrandchildKey: state.myChildKey }; // (1)!
+        const grandchildGraphOutput = await grandchildGraph.invoke(grandchildGraphInput);
+        return { myChildKey: grandchildGraphOutput.myGrandchildKey + " today?" }; // (2)!
+      }) // (3)!
+      .addEdge(START, "child1")
+      .addEdge("child1", END);
+    
+    const childGraph = child.compile();
+    
+    // Parent graph
+    const ParentState = z.object({
+      myKey: z.string(),
+    });
+    
+    const parent = new StateGraph(ParentState)
+      .addNode("parent1", (state) => {
+        // NOTE: child or grandchild keys won't be accessible here
+        return { myKey: "hi " + state.myKey };
+      })
+      .addNode("child", async (state) => {
+        const childGraphInput = { myChildKey: state.myKey }; // (4)!
+        const childGraphOutput = await childGraph.invoke(childGraphInput);
+        return { myKey: childGraphOutput.myChildKey }; // (5)!
+      }) // (6)!
+      .addNode("parent2", (state) => {
+        return { myKey: state.myKey + " bye!" };
+      })
+      .addEdge(START, "parent1")
+      .addEdge("parent1", "child")
+      .addEdge("child", "parent2")
+      .addEdge("parent2", END);
+    
+    const parentGraph = parent.compile();
+    
+    for await (const chunk of await parentGraph.stream(
+      { myKey: "Bob" }, 
+      { subgraphs: true }
+    )) {
+      console.log(chunk);
+    }
+    ```
+
+    7. We're transforming the state from the child state channels (`myChildKey`) to the grandchild state channels (`myGrandchildKey`)
+    8. We're transforming the state from the grandchild state channels (`myGrandchildKey`) back to the child state channels (`myChildKey`)
+    9. We're passing a function here instead of just compiled graph (`grandchildGraph`)
+    10. We're transforming the state from the parent state channels (`myKey`) to the child state channels (`myChildKey`)
+    11. We're transforming the state from the child state channels (`myChildKey`) back to the parent state channels (`myKey`)
+    12. We're passing a function here instead of just a compiled graph (`childGraph`)
+
+    ```
+    [[], { parent1: { myKey: 'hi Bob' } }]
+    [['child:2e26e9ce-602f-862c-aa66-1ea5a4655e3b', 'child1:781bb3b1-3971-84ce-810b-acf819a03f9c'], { grandchild1: { myGrandchildKey: 'hi Bob, how are you' } }]
+    [['child:2e26e9ce-602f-862c-aa66-1ea5a4655e3b'], { child1: { myChildKey: 'hi Bob, how are you today?' } }]
+    [[], { child: { myKey: 'hi Bob, how are you today?' } }]
+    [[], { parent2: { myKey: 'hi Bob, how are you today? bye!' } }]
+    ```
+    :::

 ## Add persistence 

 You only need to **provide the checkpointer when compiling the parent graph**. LangGraph will automatically propagate the checkpointer to the child subgraphs.

+:::python
 ```python
 from langgraph.graph import START, StateGraph
-from langgraph.checkpoint.memory import InMemorySaver
+from langgraph.checkpoint.memory import MemorySaver
 from typing_extensions import TypedDict

 class State(TypedDict):
@@ -317,20 +605,66 @@ builder = StateGraph(State)
 builder.add_node("node_1", subgraph)
 builder.add_edge(START, "node_1")

-checkpointer = InMemorySaver()
+checkpointer = MemorySaver()
 graph = builder.compile(checkpointer=checkpointer)
 ```    
+:::

-If you want the subgraph to **have its own memory**, you can compile it `with checkpointer=True`. This is useful in [multi-agent](../concepts/multi_agent.md) systems, if you want agents to keep track of their internal message histories:
+:::js
+```typescript
+import { StateGraph, START, MemorySaver } from "@langchain/langgraph";
+import { z } from "zod";

+const State = z.object({
+  foo: z.string(),
+});
+
+// Subgraph
+const subgraphBuilder = new StateGraph(State)
+  .addNode("subgraphNode1", (state) => {
+    return { foo: state.foo + "bar" };
+  })
+  .addEdge(START, "subgraphNode1");
+
+const subgraph = subgraphBuilder.compile();
+
+// Parent graph
+const builder = new StateGraph(State)
+  .addNode("node1", subgraph)
+  .addEdge(START, "node1");
+
+const checkpointer = new MemorySaver();
+const graph = builder.compile({ checkpointer });
+```    
+:::
+
+If you want the subgraph to **have its own memory**, you can compile it with the appropriate checkpointer option. This is useful in [multi-agent](../concepts/multi_agent.md) systems, if you want agents to keep track of their internal message histories:
+
+:::python
 ```python
 subgraph_builder = StateGraph(...)
 subgraph = subgraph_builder.compile(checkpointer=True)
 ```
+:::
+
+:::js
+```typescript
+const subgraphBuilder = new StateGraph(...)
+const subgraph = subgraphBuilder.compile({ checkpointer: true });
+```
+:::

 ## View subgraph state

-When you enable [persistence](../concepts/persistence.md), you can [inspect the graph state](../concepts/persistence.md#checkpoints) (checkpoint) via `graph.get_state(config)`. To view the subgraph state, you can use `graph.get_state(config, subgraphs=True)`.
+When you enable [persistence](../concepts/persistence.md), you can [inspect the graph state](../concepts/persistence.md#checkpoints) (checkpoint) via the appropriate method. To view the subgraph state, you can use the subgraphs option.
+
+:::python
+You can inspect the graph state via `graph.get_state(config)`. To view the subgraph state, you can use `graph.get_state(config, subgraphs=True)`.
+:::
+
+:::js
+You can inspect the graph state via `graph.getState(config)`. To view the subgraph state, you can use `graph.getState(config, { subgraphs: true })`.
+:::

 !!! important "Available **only** when interrupted"

@@ -338,9 +672,10 @@ When you enable [persistence](../concepts/persistence.md), you can [inspect the

 ??? example "View interrupted subgraph state"

+    :::python
    ```python
    from langgraph.graph import START, StateGraph
-    from langgraph.checkpoint.memory import InMemorySaver
+    from langgraph.checkpoint.memory import MemorySaver
    from langgraph.types import interrupt, Command
    from typing_extensions import TypedDict
    
@@ -365,7 +700,7 @@ When you enable [persistence](../concepts/persistence.md), you can [inspect the
    builder.add_node("node_1", subgraph)
    builder.add_edge(START, "node_1")
    
-    checkpointer = InMemorySaver()
+    checkpointer = MemorySaver()
    graph = builder.compile(checkpointer=checkpointer)
    
    config = {"configurable": {"thread_id": "1"}}
@@ -379,11 +714,53 @@ When you enable [persistence](../concepts/persistence.md), you can [inspect the
    ```
    
    1. This will be available only when the subgraph is interrupted. Once you resume the graph, you won't be able to access the subgraph state.
+    :::
+
+    :::js
+    ```typescript
+    import { StateGraph, START, MemorySaver, interrupt, Command } from "@langchain/langgraph";
+    import { z } from "zod";
+    
+    const State = z.object({
+      foo: z.string(),
+    });
+    
+    // Subgraph
+    const subgraphBuilder = new StateGraph(State)
+      .addNode("subgraphNode1", (state) => {
+        const value = interrupt("Provide value:");
+        return { foo: state.foo + value };
+      })
+      .addEdge(START, "subgraphNode1");
+    
+    const subgraph = subgraphBuilder.compile();
+    
+    // Parent graph
+    const builder = new StateGraph(State)
+      .addNode("node1", subgraph)
+      .addEdge(START, "node1");
+    
+    const checkpointer = new MemorySaver();
+    const graph = builder.compile({ checkpointer });
+    
+    const config = { configurable: { thread_id: "1" } };
+    
+    await graph.invoke({ foo: "" }, config);
+    const parentState = await graph.getState(config);
+    const subgraphState = (await graph.getState(config, { subgraphs: true })).tasks[0].state; // (1)!
+    
+    // resume the subgraph
+    await graph.invoke(new Command({ resume: "bar" }), config);
+    ```
+    
+    2. This will be available only when the subgraph is interrupted. Once you resume the graph, you won't be able to access the subgraph state.
+    :::

 ## Stream subgraph outputs

-To include outputs from subgraphs in the streamed outputs, you can set `subgraphs=True` in the `.stream()` method of the parent graph. This will stream outputs from both the parent graph and any subgraphs.
+To include outputs from subgraphs in the streamed outputs, you can set the subgraphs option in the stream method of the parent graph. This will stream outputs from both the parent graph and any subgraphs.

+:::python
 ```python
 for chunk in graph.stream(
    {"foo": "foo"},
@@ -394,9 +771,27 @@ for chunk in graph.stream(
 ```

 1. Set `subgraphs=True` to stream outputs from subgraphs.
+:::
+
+:::js
+```typescript
+for await (const chunk of await graph.stream(
+  { foo: "foo" },
+  {
+    subgraphs: true, // (1)!
+    streamMode: "updates",
+  }
+)) {
+  console.log(chunk);
+}
+```
+
+1. Set `subgraphs: true` to stream outputs from subgraphs.
+:::

 ??? example "Stream from subgraphs"

+    :::python
    ```python
    from typing_extensions import TypedDict
    from langgraph.graph.state import StateGraph, START
@@ -450,4 +845,66 @@ for chunk in graph.stream(
    (('node_2:e58e5673-a661-ebb0-70d4-e298a7fc28b7',), {'subgraph_node_1': {'bar': 'bar'}})
    (('node_2:e58e5673-a661-ebb0-70d4-e298a7fc28b7',), {'subgraph_node_2': {'foo': 'hi! foobar'}})
    ((), {'node_2': {'foo': 'hi! foobar'}})
-    
+    ```
+    :::
+
+    :::js
+    ```typescript
+    import { StateGraph, START } from "@langchain/langgraph";
+    import { z } from "zod";
+
+    // Define subgraph
+    const SubgraphState = z.object({
+      foo: z.string(),
+      bar: z.string(),
+    });
+    
+    const subgraphBuilder = new StateGraph(SubgraphState)
+      .addNode("subgraphNode1", (state) => {
+        return { bar: "bar" };
+      })
+      .addNode("subgraphNode2", (state) => {
+        // note that this node is using a state key ('bar') that is only available in the subgraph
+        // and is sending update on the shared state key ('foo')
+        return { foo: state.foo + state.bar };
+      })
+      .addEdge(START, "subgraphNode1")
+      .addEdge("subgraphNode1", "subgraphNode2");
+    
+    const subgraph = subgraphBuilder.compile();
+    
+    // Define parent graph
+    const ParentState = z.object({
+      foo: z.string(),
+    });
+    
+    const builder = new StateGraph(ParentState)
+      .addNode("node1", (state) => {
+        return { foo: "hi! " + state.foo };
+      })
+      .addNode("node2", subgraph)
+      .addEdge(START, "node1")
+      .addEdge("node1", "node2");
+    
+    const graph = builder.compile();
+
+    for await (const chunk of await graph.stream(
+      { foo: "foo" },
+      {
+        streamMode: "updates",
+        subgraphs: true, // (1)!
+      }
+    )) {
+      console.log(chunk);
+    }
+    ```
+  
+    2. Set `subgraphs: true` to stream outputs from subgraphs.
+
+    ```
+    [[], { node1: { foo: 'hi! foo' } }]
+    [['node2:e58e5673-a661-ebb0-70d4-e298a7fc28b7'], { subgraphNode1: { bar: 'bar' } }]
+    [['node2:e58e5673-a661-ebb0-70d4-e298a7fc28b7'], { subgraphNode2: { foo: 'hi! foobar' } }]
+    [[], { node2: { foo: 'hi! foobar' } }]
+    ```
+    :::
@@ -172,6 +172,82 @@ await agent.invoke({

 :::

+:::python
+
+### Dynamically select tools
+
+Configure tool availability at runtime based on context:
+
+```python
+from dataclasses import dataclass
+from typing import Literal
+
+from langchain.chat_models import init_chat_model
+from langchain_core.tools import tool
+
+from langgraph.prebuilt import create_react_agent
+from langgraph.prebuilt.chat_agent_executor import AgentState
+from langgraph.runtime import Runtime
+
+
+@dataclass
+class CustomContext:
+    tools: list[Literal["weather", "compass"]]
+
+
+@tool
+def weather() -> str:
+    """Returns the current weather conditions."""
+    return "It's nice and sunny."
+
+
+@tool
+def compass() -> str:
+    """Returns the direction the user is facing."""
+    return "North"
+
+model = init_chat_model("anthropic:claude-sonnet-4-20250514")
+
+# highlight-next-line
+def configure_model(state: AgentState, runtime: Runtime[CustomContext]):
+    """Configure the model with tools based on runtime context."""
+    selected_tools = [
+        tool
+        for tool in [weather, compass]
+        if tool.name in runtime.context.tools
+    ]
+    return model.bind_tools(selected_tools)
+
+
+agent = create_react_agent(
+    # Dynamically configure the model with tools based on runtime context
+    # highlight-next-line
+    configure_model,
+    # Initialize with all tools available
+    # highlight-next-line
+    tools=[weather, compass]
+)
+
+output = agent.invoke(
+    {
+        "messages": [
+            {
+                "role": "user",
+                "content": "Who are you and what tools do you have access to?",
+            }
+        ]
+    },
+    # highlight-next-line
+    context=CustomContext(tools=["weather"]),  # Only enable the weather tool
+)
+
+print(output["messages"][-1].text())
+```
+
+!!! version-added "New in langgraph>=0.6"
+
+:::
+
 ## Use in a workflow

 If you are writing a custom workflow, you will need to:
@@ -1495,6 +1571,7 @@ const saveUserInfo = tool(

    from langchain_core.tools import tool
    from langgraph.config import get_store
+    from langchain_core.runnables import RunnableConfig
    from langgraph.prebuilt import create_react_agent
    from langgraph.store.memory import InMemoryStore

@@ -10,7 +10,7 @@
 - [Implementing Human-in-the-Loop Controls in LangGraph](https://langchain-ai.github.io/langgraph/tutorials/get-started/4-human-in-the-loop/): This page provides a comprehensive guide on adding human-in-the-loop controls to LangGraph workflows, enabling agents to pause execution for human input. It details the use of the `interrupt` function to facilitate user feedback and outlines the steps to integrate a `human_assistance` tool into a chatbot. Additionally, the tutorial covers graph compilation, visualization, and resuming execution with human input.
 - [Customizing State in LangGraph for Enhanced Chatbot Functionality](https://langchain-ai.github.io/langgraph/tutorials/get-started/5-customize-state/): This tutorial guides you through the process of adding custom fields to the state in LangGraph, enabling complex behaviors in your chatbot without relying solely on message lists. You will learn how to implement human-in-the-loop controls to verify information before it is stored in the state. By the end of this tutorial, you will have a deeper understanding of state management and how to enhance your chatbot's capabilities.
 - [Implementing Time Travel in LangGraph Chatbots](https://langchain-ai.github.io/langgraph/tutorials/get-started/6-time-travel/): This page provides a comprehensive guide on utilizing the time travel functionality in LangGraph to enhance chatbot interactions. It covers how to rewind, add steps, and replay the state history of a chatbot, allowing users to explore different outcomes and fix mistakes. Additionally, it includes code snippets and practical examples to help developers implement these features effectively.
- [LangGraph Deployment Options](https://langchain-ai.github.io/langgraph/tutorials/deployment/): This page outlines the various options available for deploying LangGraph applications, including local testing and different cloud-based solutions. It details free deployment methods such as Local and Standalone Container (Lite), as well as production options like Cloud SaaS and self-hosted solutions. Each deployment method is linked to further documentation for in-depth guidance.
+- [LangGraph Deployment Options](https://langchain-ai.github.io/langgraph/tutorials/deployment/): This page outlines the various options available for deploying LangGraph applications, including local testing and different cloud-based solutions. It details free deployment methods such as Local, as well as production options like Cloud SaaS and self-hosted solutions. Each deployment method is linked to further documentation for in-depth guidance.
 - [Agent Development with LangGraph](https://langchain-ai.github.io/langgraph/agents/overview/): This page provides an overview of agent development using LangGraph, highlighting its prebuilt components and capabilities for building agent-based applications. It explains the structure of an agent, key features such as memory integration and human-in-the-loop control, and outlines the package ecosystem available for developers. With LangGraph, users can focus on application logic while leveraging robust infrastructure for state management and feedback.
 - [Guide to Running Agents in LangGraph](https://langchain-ai.github.io/langgraph/agents/run_agents/): This page provides a comprehensive overview of how to execute agents in LangGraph, detailing both synchronous and asynchronous methods. It covers input and output formats, streaming capabilities, and how to manage execution limits to prevent infinite loops. Additionally, it includes code examples and links to further resources for deeper understanding.
 - [Streaming Data in LangGraph](https://langchain-ai.github.io/langgraph/agents/streaming/): This page provides an overview of streaming data types in LangGraph, including agent progress, LLM tokens, and custom updates. It includes code examples for both synchronous and asynchronous streaming methods. Additionally, it covers how to stream multiple modes and disable streaming when necessary.
@@ -73,7 +73,7 @@
 - [Integrating Semantic Search in LangGraph](https://langchain-ai.github.io/langgraph/cloud/deployment/semantic_search/): This guide provides step-by-step instructions on how to implement semantic search in your LangGraph deployment. It covers prerequisites, configuration of the store, and usage examples for searching memories and documents by semantic similarity. Additionally, it includes information on using custom embeddings and querying via the LangGraph SDK.
 - [Configuring Time-to-Live (TTL) in LangGraph Applications](https://langchain-ai.github.io/langgraph/how-tos/ttl/configure_ttl/): This guide provides detailed instructions on how to configure Time-to-Live (TTL) settings for checkpoints and store items in LangGraph applications. It covers the necessary configurations in the `langgraph.json` file, including strategies for managing data lifecycle and memory. Additionally, it explains how to combine TTL configurations and override them at runtime.
 - [LangGraph Authentication & Access Control Overview](https://langchain-ai.github.io/langgraph/concepts/auth/): This page provides a comprehensive guide to the authentication and authorization mechanisms within the LangGraph Platform. It explains the core concepts of authentication versus authorization, outlines default security models, and details the system architecture involved in user identity management. Additionally, it covers implementation examples for authentication and authorization handlers, along with common access patterns and supported resources.
- [Custom Authentication Setup for LangGraph Platform](https://langchain-ai.github.io/langgraph/how-tos/auth/custom_auth/): This guide provides step-by-step instructions on how to implement custom authentication in your LangGraph Platform application. It covers the necessary prerequisites, implementation details, configuration updates, and client connection methods. The guide is applicable to both managed and Enterprise self-hosted deployments, but not to Lite self-hosted plans.
+- [Custom Authentication Setup for LangGraph Platform](https://langchain-ai.github.io/langgraph/how-tos/auth/custom_auth/): This guide provides step-by-step instructions on how to implement custom authentication in your LangGraph Platform application. It covers the necessary prerequisites, implementation details, configuration updates, and client connection methods. The guide is applicable to both managed and Enterprise self-hosted deployments.
 - [Documenting API Authentication in OpenAPI for LangGraph](https://langchain-ai.github.io/langgraph/how-tos/auth/openapi_security/): This guide provides instructions on how to customize the security schema for your LangGraph Platform API documentation using OpenAPI. It covers default security schemes for both LangGraph Platform and self-hosted deployments, as well as how to implement custom authentication. Additionally, it includes examples for OAuth2 and API key authentication, along with testing procedures.
 - [Managing Assistants in LangGraph](https://langchain-ai.github.io/langgraph/concepts/assistants/): This page provides an overview of how to create and manage assistants within the LangGraph Platform, which allows for separate configuration of agents without altering the core graph logic. It covers the prerequisites, configuration options, and versioning of assistants, highlighting their role in optimizing agent performance for different tasks. Additionally, it includes links to relevant API references and how-to guides for further assistance.
 - [Managing Assistants in LangGraph](https://langchain-ai.github.io/langgraph/cloud/how-tos/configuration_cloud/): This documentation page provides a comprehensive guide on how to create, configure, and manage assistants using the LangGraph SDK and Platform UI. It includes code examples in Python and JavaScript, as well as instructions for creating new versions and using previous versions of assistants. Additionally, it covers the process of utilizing assistants in various environments.
@@ -112,7 +112,7 @@
 - [Deploying a Self-Hosted Data Plane](https://langchain-ai.github.io/langgraph/cloud/deployment/self_hosted_data_plane/): This page provides a comprehensive guide on deploying a Self-Hosted Data Plane using Kubernetes and Amazon ECS. It outlines the prerequisites, setup steps, and configuration details necessary for a successful deployment. Additionally, it highlights the current beta status of this deployment option.
 - [Self-Hosted Control Plane Deployment Guide](https://langchain-ai.github.io/langgraph/concepts/langgraph_self_hosted_control_plane/): This page provides an overview of the Self-Hosted Control Plane deployment option, currently in beta. It outlines the requirements, architecture, and compute platforms supported for deploying the control and data planes in your cloud environment. Additionally, it includes important links and resources for managing your self-hosted infrastructure.
 - [Deploying a Self-Hosted Control Plane](https://langchain-ai.github.io/langgraph/cloud/deployment/self_hosted_control_plane/): This page provides a comprehensive guide on deploying a Self-Hosted Control Plane using Kubernetes. It outlines the prerequisites, setup steps, and configuration details necessary for a successful deployment. Additionally, it highlights the beta status of this deployment option and includes links to relevant resources for further assistance.
- [Deploying LangGraph Server with Standalone Container](https://langchain-ai.github.io/langgraph/concepts/langgraph_standalone_container/): This page provides a comprehensive guide on deploying a LangGraph Server using the Standalone Container option. It outlines the architecture, supported compute platforms, and differences between Lite and Enterprise server versions. Users will find essential information on managing the data plane infrastructure without a control plane.
+- [Deploying LangGraph Server with Standalone Container](https://langchain-ai.github.io/langgraph/concepts/langgraph_standalone_container/): This page provides a comprehensive guide on deploying a LangGraph Server using the Standalone Container option. It outlines the architecture, supported compute platforms, and Enterprise server version features. Users will find essential information on managing the data plane infrastructure without a control plane.
 - [Deploying a Standalone Container with LangGraph](https://langchain-ai.github.io/langgraph/cloud/deployment/standalone_container/): This documentation provides a comprehensive guide on deploying a standalone container for the LangGraph application. It covers prerequisites, environment variable configurations, and deployment methods using Docker and Docker Compose. Additionally, it includes instructions for deploying on Kubernetes using Helm.
 - [Scalability and Resilience of LangGraph Platform](https://langchain-ai.github.io/langgraph/concepts/scalability_and_resilience/): This page provides an overview of the scalability and resilience features of the LangGraph Platform. It details how the platform handles server and queue scalability, as well as the mechanisms in place for ensuring resilience during both graceful and hard shutdowns. Additionally, it covers the resilience strategies employed for Postgres and Redis to maintain service availability.
 - [LangGraph Platform Plans Overview](https://langchain-ai.github.io/langgraph/concepts/plans/): This page provides an overview of the different plans available for the LangGraph Platform, including Developer, Plus, and Enterprise options. Each plan offers varying deployment options, usage limits, and features tailored to different user needs. For detailed pricing and related resources, links to additional documentation are also included.
@@ -49,9 +49,8 @@ Higher-level abstractions for common workflows, agents, and other patterns.

 Tools for deploying and connecting to the LangGraph Platform.

- [CLI](../cloud/reference/cli.md): Command-line interface for building and deploying LangGraph Platform applications.
- [Server API](../cloud/reference/api/api_ref.md): REST API for the LangGraph Server.
 - [SDK (Python)](../cloud/reference/sdk/python_sdk_ref.md): Python SDK for interacting with instances of the LangGraph Server.
 - [SDK (JS/TS)](../cloud/reference/sdk/js_ts_sdk_ref.md): JavaScript/TypeScript SDK for interacting with instances of the LangGraph Server.
 - [RemoteGraph](remote_graph.md): `Pregel` abstraction for connecting to LangGraph Server instances.
- [Environment variables](../cloud/reference/env_var.md): Supported configuration variables when deploying with the LangGraph Platform.
+
+See the [LangGraph Platform reference](https://docs.langchain.com/langgraph-platform/reference-overview) for more reference documentation.
@@ -21,15 +21,9 @@ See the [local server](../../tutorials/langgraph-platform/local-server.md) docs

 If you would like a fast managed environment, consider the [Cloud SaaS](../../concepts/langgraph_cloud.md) deployment option. This requires no additional license key.

-#### For Standalone Container (Lite)
+#### For Standalone Container

-If your deployment is unlikely to see more than 1 million node executions per year and don't need Crons and other enterprise features, consider the [Standalone Container](../../concepts/deployment_options.md) deployment option.
-
-You can deploy with Standalone Container by setting a valid `LANGSMITH_API_KEY` in your environment (e.g., in the `.env` file referenced by `langgraph.json`) and building a Docker image. The API key must be associated with an account on a **Plus** plan or greater.
-
-#### For Standalone Container (Enterprise)
-
-For full self-hosting, set the `LANGGRAPH_CLOUD_LICENSE_KEY` environment variable. If you are interested in an enterprise license key, please contact the LangChain support team.
+For self-hosting, set the `LANGGRAPH_CLOUD_LICENSE_KEY` environment variable. If you are interested in an enterprise license key, please contact the LangChain support team.

 For more information on deployment options and their features, see the [Deployment Options](../../concepts/deployment_options.md) documentation.

@@ -38,12 +32,7 @@ For more information on deployment options and their features, see the [Deployme

 If you have confirmed that you would like to self-host LangGraph Platform, please verify your credentials.

-#### For Standalone Container (Lite)
-
-1. Confirm that you have provided a working `LANGSMITH_API_KEY` environment variable in your deployment environment or `.env` file
-2. Confirm the provided API key is associated with an account on a **Plus** or **Enterprise** plan (or equivalent)
-
-#### For Standalone Container (Enterprise)
+#### For Standalone Container

 1. Confirm that you have provided a working `LANGGRAPH_CLOUD_LICENSE_KEY` environment variable in your deployment environment or `.env` file
 2. Confirm the key is still valid and has not surpassed its expiration date
@@ -11,11 +11,4 @@ Errors referenced below will have an `lc_error_code` property corresponding to o
 - [INVALID_CONCURRENT_GRAPH_UPDATE](./INVALID_CONCURRENT_GRAPH_UPDATE.md)
 - [INVALID_GRAPH_NODE_RETURN_VALUE](./INVALID_GRAPH_NODE_RETURN_VALUE.md)
 - [MULTIPLE_SUBGRAPHS](./MULTIPLE_SUBGRAPHS.md)
- [INVALID_CHAT_HISTORY](./INVALID_CHAT_HISTORY.md)
-
-## LangGraph Platform
-
-These guides provide troubleshooting information for errors that are specific to the LangGraph Platform.
-
- [INVALID_LICENSE](./INVALID_LICENSE.md)
- [Studio Errors](../studio.md)
+- [INVALID_CHAT_HISTORY](./INVALID_CHAT_HISTORY.md)
@@ -17,7 +17,7 @@ Create a `MemorySaver` checkpointer:
 :::python

 ```python
-from langgraph.checkpoint.memory import MemorySaver
+from langgraph.checkpoint.memory import InMemorySaver

 memory = InMemorySaver()
 ```
@@ -447,3 +447,4 @@ const graph = new StateGraph(State)
 ## Next steps

 In the next tutorial, you will [add human-in-the-loop to the chatbot](./4-human-in-the-loop.md) to handle situations where it may need guidance or verification before proceeding.
+
@@ -85,124 +85,80 @@ Let's [run the agent](../../agents/run_agents.md) to verify that it behaves as e

 !!! note "We'll use `pretty_print_messages` helper to render the streamed agent outputs nicely"

-    ```python
-    from langchain_core.messages import convert_to_messages
-    
-    
-    def pretty_print_message(message, indent=False):
-        pretty_message = message.pretty_repr(html=True)
-        if not indent:
-            print(pretty_message)
-            return
-    
-        indented = "\n".join("\t" + c for c in pretty_message.split("\n"))
-        print(indented)
-    
-    
-    def pretty_print_messages(update, last_message=False):
-        is_subgraph = False
-        if isinstance(update, tuple):
-            ns, update = update
-            # skip parent graph updates in the printouts
-            if len(ns) == 0:
-                return
-    
-            graph_id = ns[-1].split(":")[0]
-            print(f"Update from subgraph {graph_id}:")
-            print("\n")
-            is_subgraph = True
-    
-        for node_name, node_update in update.items():
-            update_label = f"Update from node {node_name}:"
-            if is_subgraph:
-                update_label = "\t" + update_label
-    
-            print(update_label)
-            print("\n")
-    
-            messages = convert_to_messages(node_update["messages"])
-            if last_message:
-                messages = messages[-1:]
-    
-            for m in messages:
-                pretty_print_message(m, indent=is_subgraph)
-            print("\n")
-    ```
-
-```python
-from langchain_core.messages import convert_to_messages
+  ```python
+  from langchain_core.messages import convert_to_messages


-def pretty_print_message(message, indent=False):
-    pretty_message = message.pretty_repr(html=True)
-    if not indent:
-        print(pretty_message)
-        return
+  def pretty_print_message(message, indent=False):
+      pretty_message = message.pretty_repr(html=True)
+      if not indent:
+          print(pretty_message)
+          return

-    indented = "\n".join("\t" + c for c in pretty_message.split("\n"))
-    print(indented)
+      indented = "\n".join("\t" + c for c in pretty_message.split("\n"))
+      print(indented)


-def pretty_print_messages(update, last_message=False):
-    is_subgraph = False
-    if isinstance(update, tuple):
-        ns, update = update
-        # skip parent graph updates in the printouts
-        if len(ns) == 0:
-            return
+  def pretty_print_messages(update, last_message=False):
+      is_subgraph = False
+      if isinstance(update, tuple):
+          ns, update = update
+          # skip parent graph updates in the printouts
+          if len(ns) == 0:
+              return

-        graph_id = ns[-1].split(":")[0]
-        print(f"Update from subgraph {graph_id}:")
-        print("\n")
-        is_subgraph = True
+          graph_id = ns[-1].split(":")[0]
+          print(f"Update from subgraph {graph_id}:")
+          print("\n")
+          is_subgraph = True

-    for node_name, node_update in update.items():
-        update_label = f"Update from node {node_name}:"
-        if is_subgraph:
-            update_label = "\t" + update_label
+      for node_name, node_update in update.items():
+          update_label = f"Update from node {node_name}:"
+          if is_subgraph:
+              update_label = "\t" + update_label

-        print(update_label)
-        print("\n")
+          print(update_label)
+          print("\n")

-        messages = convert_to_messages(node_update["messages"])
-        if last_message:
-            messages = messages[-1:]
+          messages = convert_to_messages(node_update["messages"])
+          if last_message:
+              messages = messages[-1:]

-        for m in messages:
-            pretty_print_message(m, indent=is_subgraph)
-        print("\n")
-```
+          for m in messages:
+              pretty_print_message(m, indent=is_subgraph)
+          print("\n")
+  ```

-```python
-for chunk in research_agent.stream(
-    {"messages": [{"role": "user", "content": "who is the mayor of NYC?"}]}
-):
-    pretty_print_messages(chunk)
-```
+  ```python
+  for chunk in research_agent.stream(
+      {"messages": [{"role": "user", "content": "who is the mayor of NYC?"}]}
+  ):
+      pretty_print_messages(chunk)
+  ```

-**Output:**
-```
-Update from node agent:
+  **Output:**
+  ```
+  Update from node agent:


-================================== Ai Message ==================================
-Name: research_agent
-Tool Calls:
-  tavily_search (call_U748rQhQXT36sjhbkYLSXQtJ)
- Call ID: call_U748rQhQXT36sjhbkYLSXQtJ
-  Args:
-    query: current mayor of New York City
-    search_depth: basic
+  ================================== Ai Message ==================================
+  Name: research_agent
+  Tool Calls:
+    tavily_search (call_U748rQhQXT36sjhbkYLSXQtJ)
+   Call ID: call_U748rQhQXT36sjhbkYLSXQtJ
+    Args:
+      query: current mayor of New York City
+      search_depth: basic


-Update from node tools:
+  Update from node tools:


-================================= Tool Message ==================================
-Name: tavily_search
+  ================================= Tool Message ==================================
+  Name: tavily_search

-{"query": "current mayor of New York City", "follow_up_questions": null, "answer": null, "images": [], "results": [{"title": "List of mayors of New York City - Wikipedia", "url": "https://en.wikipedia.org/wiki/List_of_mayors_of_New_York_City", "content": "The mayor of New York City is the chief executive of the Government of New York City, as stipulated by New York City's charter.The current officeholder, the 110th in the sequence of regular mayors, is Eric Adams, a member of the Democratic Party.. During the Dutch colonial period from 1624 to 1664, New Amsterdam was governed by the Director of Netherland.", "score": 0.9039154, "raw_content": null}, {"title": "Office of the Mayor | Mayor's Bio | City of New York - NYC.gov", "url": "https://www.nyc.gov/office-of-the-mayor/bio.page", "content": "Mayor Eric Adams has served the people of New York City as an NYPD officer, State Senator, Brooklyn Borough President, and now as the 110th Mayor of the City of New York. He gave voice to a diverse coalition of working families in all five boroughs and is leading the fight to bring back New York City's economy, reduce inequality, improve", "score": 0.8405867, "raw_content": null}, {"title": "Eric Adams - Wikipedia", "url": "https://en.wikipedia.org/wiki/Eric_Adams", "content": "Eric Leroy Adams (born September 1, 1960) is an American politician and former police officer who has served as the 110th mayor of New York City since 2022. Adams was an officer in the New York City Transit Police and then the New York City Police Department (```
-```
+  {"query": "current mayor of New York City", "follow_up_questions": null, "answer": null, "images": [], "results": [{"title": "List of mayors of New York City - Wikipedia", "url": "https://en.wikipedia.org/wiki/List_of_mayors_of_New_York_City", "content": "The mayor of New York City is the chief executive of the Government of New York City, as stipulated by New York City's charter.The current officeholder, the 110th in the sequence of regular mayors, is Eric Adams, a member of the Democratic Party.. During the Dutch colonial period from 1624 to 1664, New Amsterdam was governed by the Director of Netherland.", "score": 0.9039154, "raw_content": null}, {"title": "Office of the Mayor | Mayor's Bio | City of New York - NYC.gov", "url": "https://www.nyc.gov/office-of-the-mayor/bio.page", "content": "Mayor Eric Adams has served the people of New York City as an NYPD officer, State Senator, Brooklyn Borough President, and now as the 110th Mayor of the City of New York. He gave voice to a diverse coalition of working families in all five boroughs and is leading the fight to bring back New York City's economy, reduce inequality, improve", "score": 0.8405867, "raw_content": null}, {"title": "Eric Adams - Wikipedia", "url": "https://en.wikipedia.org/wiki/Eric_Adams", "content": "Eric Leroy Adams (born September 1, 1960) is an American politician and former police officer who has served as the 110th mayor of New York City since 2022. Adams was an officer in the New York City Transit Police and then the New York City Police Department (```
+  ```

 ### Math agent

@@ -809,4 +765,4 @@ Update from subgraph research_agent:
 	Name: tavily_search
 	
 	{"query": "2024 United States GDP value from a reputable source", "follow_up_questions": null, "answer": null, "images": [], "results": [{"url": "https://www.focus-economics.com/countries/united-states/", "title": "United States Economy Overview - Focus Economics", "content": "The United States' Macroeconomic Analysis:\n------------------------------------------\n\n**Nominal GDP of USD 29,185 billion in 2024.**\n\n**Nominal GDP of USD 29,179 billion in 2024.**\n\n**GDP per capita of USD 86,635 compared to the global average of USD 10,589.**\n\n**GDP per capita of USD 86,652 compared to the global average of USD 10,589.**\n\n**Average real GDP growth of 2.5% over the last decade.**\n\n**Average real GDP growth of ```
-``` 
+``` 
@@ -52,6 +52,103 @@ theme:
 plugins:
  - search:
      separator: '[\s\u200b\-,:!=\[\]()"`/]+|\.(?!\d)|&[lg]t;'
+  - exclude-search:
+      exclude:
+        - additional-resources/index.md
+        - agents/prebuilt.md
+        - cloud/concepts/cron_jobs.md
+        - cloud/concepts/data_storage_and_privacy.md
+        - cloud/concepts/webhooks.md
+        - cloud/deployment/cloud.md
+        - cloud/deployment/custom_docker.md
+        - cloud/deployment/egress.md
+        - cloud/deployment/graph_rebuild.md
+        - cloud/deployment/self_hosted_control_plane.md
+        - cloud/deployment/self_hosted_data_plane.md
+        - cloud/deployment/semantic_search.md
+        - cloud/deployment/setup_javascript.md
+        - cloud/deployment/setup_pyproject.md
+        - cloud/deployment/setup.md
+        - cloud/deployment/standalone_container.md
+        - cloud/how-tos/add-human-in-the-loop.md
+        - cloud/how-tos/background_run.md
+        - cloud/how-tos/clone_traces_studio.md
+        - cloud/how-tos/configurable_headers.md
+        - cloud/how-tos/configuration_cloud.md
+        - cloud/how-tos/cron_jobs.md
+        - cloud/how-tos/datasets_studio.md
+        - cloud/how-tos/enqueue_concurrent.md
+        - cloud/how-tos/generative_ui_react.md
+        - cloud/how-tos/human_in_the_loop_time_travel.md
+        - cloud/how-tos/interrupt_concurrent.md
+        - cloud/how-tos/invoke_studio.md
+        - cloud/how-tos/iterate_graph_studio.md
+        - cloud/how-tos/reject_concurrent.md
+        - cloud/how-tos/rollback_concurrent.md
+        - cloud/how-tos/same-thread.md
+        - cloud/how-tos/stateless_runs.md
+        - cloud/how-tos/streaming.md
+        - cloud/how-tos/studio/manage_assistants.md
+        - cloud/how-tos/studio/quick_start.md
+        - cloud/how-tos/studio/run_evals.md
+        - cloud/how-tos/threads_studio.md
+        - cloud/how-tos/use_stream_react.md
+        - cloud/how-tos/use_threads.md
+        - cloud/how-tos/webhooks.md
+        - cloud/quick_start.md
+        - cloud/reference/api/api_ref_control_plane.md
+        - cloud/reference/api/api_ref.md
+        - cloud/reference/cli.md
+        - cloud/reference/env_var.md
+        - cloud/reference/langgraph_server_changelog.md
+        - cloud/reference/sdk/js_ts_sdk_ref.md
+        - concepts/application_structure.md
+        - concepts/assistants.md
+        - concepts/auth.md
+        - concepts/deployment_options.md
+        - concepts/double_texting.md
+        - concepts/faq.md
+        - concepts/langgraph_cli.md
+        - concepts/langgraph_cloud.md
+        - concepts/langgraph_components.md
+        - concepts/langgraph_control_plane.md
+        - concepts/langgraph_data_plane.md
+        - concepts/langgraph_platform.md
+        - concepts/langgraph_self_hosted_control_plane.md
+        - concepts/langgraph_self_hosted_data_plane.md
+        - concepts/langgraph_server.md
+        - concepts/langgraph_standalone_container.md
+        - concepts/langgraph_studio.md
+        - concepts/plans.md
+        - concepts/scalability_and_resilience.md
+        - concepts/sdk.md
+        - concepts/server-mcp.md
+        - concepts/template_applications.md
+        - concepts/why-langgraph.md
+        - examples/index.md
+        - guides/index.md
+        - how-tos/auth/custom_auth.md
+        - how-tos/auth/openapi_security.md
+        - how-tos/autogen-integration.md
+        - how-tos/http/custom_lifespan.md
+        - how-tos/http/custom_middleware.md
+        - how-tos/http/custom_routes.md
+        - how-tos/ttl/configure_ttl.md
+        - how-tos/use-remote-graph.md
+        - index.md
+        - reference/index.md
+        - snippets/chat_model_tabs.md
+        - troubleshooting/errors/GRAPH_RECURSION_LIMIT.md
+        - troubleshooting/errors/index.md
+        - troubleshooting/errors/INVALID_CHAT_HISTORY.md
+        - troubleshooting/errors/INVALID_CONCURRENT_GRAPH_UPDATE.md
+        - troubleshooting/errors/INVALID_GRAPH_NODE_RETURN_VALUE.md
+        - troubleshooting/errors/INVALID_LICENSE.md
+        - troubleshooting/errors/MULTIPLE_SUBGRAPHS.md
+        - troubleshooting/studio.md
+        - tutorials/auth/add_auth_server.md
+        - tutorials/auth/getting_started.md
+        - tutorials/auth/resource_auth.md
  - tags
  - include-markdown
  - mkdocstrings:
@@ -123,7 +220,6 @@ nav:
      - Streaming:
          - Overview: concepts/streaming.md
          - Stream outputs: how-tos/streaming.md
-          - Use Server API: cloud/how-tos/streaming.md
      - Persistence:
          - Overview: concepts/persistence.md
      - Durable execution:
@@ -141,11 +237,9 @@ nav:
      - Human-in-the-loop:
          - Overview: concepts/human_in_the_loop.md
          - Add human intervention: how-tos/human_in_the_loop/add-human-in-the-loop.md
-          - Use Server API: cloud/how-tos/add-human-in-the-loop.md
      - Time travel:
          - Overview: concepts/time-travel.md
          - Use time travel: how-tos/human_in_the_loop/time-travel.md
-          - Use Server API: cloud/how-tos/human_in_the_loop_time_travel.md
      - Subgraphs:
          - Overview: concepts/subgraphs.md
          - Use subgraphs: how-tos/subgraph.md
@@ -156,88 +250,10 @@ nav:
      - MCP:
          - Overview: concepts/mcp.md
          - Use MCP: agents/mcp.md
-          - Server API: concepts/server-mcp.md
      - Tracing:
          - Overview: concepts/tracing.md
          - Enable tracing: how-tos/enable-tracing.md
          - Evaluate performance: agents/evals.md
-    - Platform-only capabilities:
-      - LangGraph Platform:
-          - Overview: concepts/langgraph_platform.md
-          - Components:
-            - Overview: concepts/langgraph_components.md
-            - LangGraph Server:
-              - Overview: concepts/langgraph_server.md
-              - Data plane: concepts/langgraph_data_plane.md
-              - Control plane: concepts/langgraph_control_plane.md
-            - LangGraph CLI: concepts/langgraph_cli.md
-            - LangGraph Studio: 
-              - Overview: concepts/langgraph_studio.md
-              - Quickstart: cloud/how-tos/studio/quick_start.md
-              - cloud/how-tos/invoke_studio.md
-              - cloud/how-tos/studio/manage_assistants.md
-              - cloud/how-tos/threads_studio.md
-              - cloud/how-tos/iterate_graph_studio.md
-              - cloud/how-tos/studio/run_evals.md
-              - cloud/how-tos/clone_traces_studio.md
-              - cloud/how-tos/datasets_studio.md
-            - LangGraph SDK: concepts/sdk.md
-          - Plans & pricing: concepts/plans.md
-          - Application structure: concepts/application_structure.md
-          - Scalability & resilience: concepts/scalability_and_resilience.md
-      - Authentication & access control:
-          - Overview: concepts/auth.md
-          - how-tos/auth/custom_auth.md
-          - how-tos/auth/openapi_security.md
-      - Assistants:
-          - Overview: concepts/assistants.md
-          - cloud/how-tos/configuration_cloud.md
-          - Threads: cloud/how-tos/use_threads.md
-          - Runs:
-            - cloud/how-tos/background_run.md
-            - cloud/how-tos/same-thread.md
-            - cloud/how-tos/cron_jobs.md
-            - cloud/how-tos/stateless_runs.md
-            - cloud/how-tos/configurable_headers.md
-      - Double-texting: 
-          - Overview: concepts/double_texting.md
-          - cloud/how-tos/interrupt_concurrent.md
-          - cloud/how-tos/rollback_concurrent.md
-          - cloud/how-tos/reject_concurrent.md
-          - cloud/how-tos/enqueue_concurrent.md
-      - Webhooks:
-          - Overview: cloud/concepts/webhooks.md
-          - Use webhooks: cloud/how-tos/webhooks.md
-      - Cron jobs:
-          - Overview: cloud/concepts/cron_jobs.md
-          - cloud/how-tos/cron_jobs.md
-      - Server customization:
-          - how-tos/http/custom_lifespan.md
-          - how-tos/http/custom_middleware.md
-          - how-tos/http/custom_routes.md
-      - Data management:
-        - cloud/concepts/data_storage_and_privacy.md
-        - Add semantic search: cloud/deployment/semantic_search.md
-        - Add TTLs: how-tos/ttl/configure_ttl.md
-      - Deployment:
-          - Overview: concepts/deployment_options.md
-          - Quickstart: cloud/quick_start.md
-          - Set up your application:
-            - Use requirements.txt: cloud/deployment/setup.md
-            - Use pyproject.toml: cloud/deployment/setup_pyproject.md
-            - Use JavaScript: cloud/deployment/setup_javascript.md
-            - Use custom Docker: cloud/deployment/custom_docker.md
-            - Rebuild graph at runtime: cloud/deployment/graph_rebuild.md
-          - Deployment options:
-            - Cloud SaaS: concepts/langgraph_cloud.md
-            - Self-Hosted Data Plane: concepts/langgraph_self_hosted_data_plane.md
-            - Self-Hosted Control Plane: concepts/langgraph_self_hosted_control_plane.md
-            - Standalone Container: concepts/langgraph_standalone_container.md
-          - Deploy to production:
-            - Cloud SaaS: cloud/deployment/cloud.md
-            - Self-Hosted Data Plane: cloud/deployment/self_hosted_data_plane.md
-            - Self-Hosted Control Plane: cloud/deployment/self_hosted_control_plane.md
-            - Standalone Container: cloud/deployment/standalone_container.md

  - Reference:
    - reference/index.md
@@ -260,14 +276,9 @@ nav:
      - Swarm: reference/swarm.md
      - MCP Adapters: reference/mcp.md
    - LangGraph Platform:
-      - Server API: cloud/reference/api/api_ref.md
-      - Server changelog: cloud/reference/langgraph_server_changelog.md
-      - Control Plane API: cloud/reference/api/api_ref_control_plane.md
-      - CLI: cloud/reference/cli.md
      - SDK (Python): cloud/reference/sdk/python_sdk_ref.md
      - SDK (JS/TS): https://langchain-ai.github.io/langgraphjs/reference/modules/sdk.html
      - RemoteGraph: reference/remote_graph.md
-      - Environment variables: cloud/reference/env_var.md

  - Examples:
    - examples/index.md
@@ -277,16 +288,6 @@ nav:
    - SQL agent: tutorials/sql/sql-agent.md
    - Prebuilt chat UI: agents/ui.md
    - Graph runs in LangSmith: how-tos/run-id-langsmith.md
-    - LangGraph Platform:
-      - Authentication:
-        - tutorials/auth/getting_started.md
-        - tutorials/auth/resource_auth.md
-        - tutorials/auth/add_auth_server.md
-      - Use RemoteGraph: how-tos/use-remote-graph.md
-      - Deploy CrewAI, AutoGen, and other frameworks: how-tos/autogen-integration.md
-      - Front-end and generative UI:
-        - Integrate LangGraph into a React app: cloud/how-tos/use_stream_react.md
-        - Implement generative UI with LangGraph: cloud/how-tos/generative_ui_react.md

  - Additional resources:
    - additional-resources/index.md
@@ -305,7 +306,6 @@ nav:
          - troubleshooting/errors/MULTIPLE_SUBGRAPHS.md
          - troubleshooting/errors/INVALID_CHAT_HISTORY.md
          - troubleshooting/errors/INVALID_LICENSE.md
-        - LangGraph Studio: troubleshooting/studio.md
    

 markdown_extensions:
@@ -360,5 +360,5 @@ j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src=
 {% endblock %}

 {% block announce %}
-LangGraph Platform docs are moving! Find the LangGraph Platform docs at the new <a href="https://docs.langchain.com/langgraph-platform" target="_blank">LangChain Docs</a> site!
+<strong>LangGraph Platform docs have moved!</strong> Find the LangGraph Platform docs at the new <a href="https://docs.langchain.com/langgraph-platform" target="_blank">LangChain Docs</a> site.
 {% endblock %}
@@ -39,6 +39,7 @@ docs = [
    "markdown-callouts",
    "markdown-include",
    "mkdocs-exclude",
+    "mkdocs-exclude-search",
    "psycopg[binary]",
    "psycopg-pool",
    "pygments-ansi-color",
@@ -2337,7 +2337,7 @@ wheels = [

 [[package]]
 name = "langgraph"
-version = "0.6.1"
+version = "0.6.2"
 source = { editable = "../libs/langgraph" }
 dependencies = [
    { name = "langchain-core" },
@@ -2524,6 +2524,7 @@ docs = [
    { name = "markdown-include" },
    { name = "mkdocs" },
    { name = "mkdocs-exclude" },
+    { name = "mkdocs-exclude-search" },
    { name = "mkdocs-git-committers-plugin-2" },
    { name = "mkdocs-include-markdown-plugin" },
    { name = "mkdocs-material", extra = ["imaging"] },
@@ -2595,6 +2596,7 @@ docs = [
    { name = "markdown-include" },
    { name = "mkdocs" },
    { name = "mkdocs-exclude" },
+    { name = "mkdocs-exclude-search" },
    { name = "mkdocs-git-committers-plugin-2" },
    { name = "mkdocs-include-markdown-plugin", specifier = ">=7.1.6" },
    { name = "mkdocs-material", extras = ["imaging"] },
@@ -2641,7 +2643,7 @@ test = [

 [[package]]
 name = "langgraph-prebuilt"
-version = "0.6.1"
+version = "0.6.2"
 source = { editable = "../libs/prebuilt" }
 dependencies = [
    { name = "langchain-core" },
@@ -3030,6 +3032,18 @@ dependencies = [
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/54/b5/3a8e289282c9e8d7003f8a2f53d673d4fdaa81d493dc6966092d9985b6fc/mkdocs-exclude-1.0.2.tar.gz", hash = "sha256:ba6fab3c80ddbe3fd31d3e579861fd3124513708271180a5f81846da8c7e2a51", size = 6751, upload-time = "2019-02-20T23:34:12.81Z" }

+[[package]]
+name = "mkdocs-exclude-search"
+version = "0.6.6"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "mkdocs" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/1d/52/8243589d294cf6091c1145896915fe50feea0e91d64d843942d0175770c2/mkdocs-exclude-search-0.6.6.tar.gz", hash = "sha256:3cdff1b9afdc1b227019cd1e124f401453235b92153d60c0e5e651a76be4f044", size = 9501, upload-time = "2023-12-03T22:58:21.259Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/3b/ef/9af45ffb1bdba684a0694922abae0bb771e9777aba005933f838b7f1bcea/mkdocs_exclude_search-0.6.6-py3-none-any.whl", hash = "sha256:2b4b941d1689808db533fe4a6afba75ce76c9bab8b21d4e31efc05fd8c4e0a4f", size = 7821, upload-time = "2023-12-03T22:58:19.355Z" },
+]
+
 [[package]]
 name = "mkdocs-get-deps"
 version = "0.2.0"
@@ -329,6 +329,7 @@ dev = [
    { name = "pytest-asyncio" },
    { name = "pytest-mock" },
    { name = "pytest-watcher" },
+    { name = "redis" },
    { name = "ruff" },
 ]

@@ -341,6 +341,7 @@ dev = [
    { name = "pytest-asyncio" },
    { name = "pytest-mock" },
    { name = "pytest-watcher" },
+    { name = "redis" },
    { name = "ruff" },
 ]

@@ -0,0 +1,144 @@
+from __future__ import annotations
+
+from collections.abc import Mapping, Sequence
+from typing import Any
+
+from langgraph.cache.base import BaseCache, FullKey, Namespace, ValueT
+from langgraph.checkpoint.serde.base import SerializerProtocol
+
+
+class RedisCache(BaseCache[ValueT]):
+    """Redis-based cache implementation with TTL support."""
+
+    def __init__(
+        self,
+        redis: Any,
+        *,
+        serde: SerializerProtocol | None = None,
+        prefix: str = "langgraph:cache:",
+    ) -> None:
+        """Initialize the cache with a Redis client.
+
+        Args:
+            redis: Redis client instance (sync or async)
+            serde: Serializer to use for values
+            prefix: Key prefix for all cached values
+        """
+        super().__init__(serde=serde)
+        self.redis = redis
+        self.prefix = prefix
+
+    def _make_key(self, ns: Namespace, key: str) -> str:
+        """Create a Redis key from namespace and key."""
+        ns_str = ":".join(ns) if ns else ""
+        return f"{self.prefix}{ns_str}:{key}" if ns_str else f"{self.prefix}{key}"
+
+    def _parse_key(self, redis_key: str) -> tuple[Namespace, str]:
+        """Parse a Redis key back to namespace and key."""
+        if not redis_key.startswith(self.prefix):
+            raise ValueError(
+                f"Key {redis_key} does not start with prefix {self.prefix}"
+            )
+
+        remaining = redis_key[len(self.prefix) :]
+        if ":" in remaining:
+            parts = remaining.split(":")
+            key = parts[-1]
+            ns_parts = parts[:-1]
+            return (tuple(ns_parts), key)
+        else:
+            return (tuple(), remaining)
+
+    def get(self, keys: Sequence[FullKey]) -> dict[FullKey, ValueT]:
+        """Get the cached values for the given keys."""
+        if not keys:
+            return {}
+
+        # Build Redis keys
+        redis_keys = [self._make_key(ns, key) for ns, key in keys]
+
+        # Get values from Redis using MGET
+        try:
+            raw_values = self.redis.mget(redis_keys)
+        except Exception:
+            # If Redis is unavailable, return empty dict
+            return {}
+
+        values: dict[FullKey, ValueT] = {}
+        for i, raw_value in enumerate(raw_values):
+            if raw_value is not None:
+                try:
+                    # Deserialize the value
+                    encoding, data = raw_value.split(b":", 1)
+                    values[keys[i]] = self.serde.loads_typed((encoding.decode(), data))
+                except Exception:
+                    # Skip corrupted entries
+                    continue
+
+        return values
+
+    async def aget(self, keys: Sequence[FullKey]) -> dict[FullKey, ValueT]:
+        """Asynchronously get the cached values for the given keys."""
+        return self.get(keys)
+
+    def set(self, mapping: Mapping[FullKey, tuple[ValueT, int | None]]) -> None:
+        """Set the cached values for the given keys and TTLs."""
+        if not mapping:
+            return
+
+        # Use pipeline for efficient batch operations
+        pipe = self.redis.pipeline()
+
+        for (ns, key), (value, ttl) in mapping.items():
+            redis_key = self._make_key(ns, key)
+            encoding, data = self.serde.dumps_typed(value)
+
+            # Store as "encoding:data" format
+            serialized_value = f"{encoding}:".encode() + data
+
+            if ttl is not None:
+                pipe.setex(redis_key, ttl, serialized_value)
+            else:
+                pipe.set(redis_key, serialized_value)
+
+        try:
+            pipe.execute()
+        except Exception:
+            # Silently fail if Redis is unavailable
+            pass
+
+    async def aset(self, mapping: Mapping[FullKey, tuple[ValueT, int | None]]) -> None:
+        """Asynchronously set the cached values for the given keys and TTLs."""
+        self.set(mapping)
+
+    def clear(self, namespaces: Sequence[Namespace] | None = None) -> None:
+        """Delete the cached values for the given namespaces.
+        If no namespaces are provided, clear all cached values."""
+        try:
+            if namespaces is None:
+                # Clear all keys with our prefix
+                pattern = f"{self.prefix}*"
+                keys = self.redis.keys(pattern)
+                if keys:
+                    self.redis.delete(*keys)
+            else:
+                # Clear specific namespaces
+                keys_to_delete = []
+                for ns in namespaces:
+                    ns_str = ":".join(ns) if ns else ""
+                    pattern = (
+                        f"{self.prefix}{ns_str}:*" if ns_str else f"{self.prefix}*"
+                    )
+                    keys = self.redis.keys(pattern)
+                    keys_to_delete.extend(keys)
+
+                if keys_to_delete:
+                    self.redis.delete(*keys_to_delete)
+        except Exception:
+            # Silently fail if Redis is unavailable
+            pass
+
+    async def aclear(self, namespaces: Sequence[Namespace] | None = None) -> None:
+        """Asynchronously delete the cached values for the given namespaces.
+        If no namespaces are provided, clear all cached values."""
+        self.clear(namespaces)
@@ -81,6 +81,9 @@ class Checkpoint(TypedDict):
    This keeps track of the versions of the channels that each node has seen.
    Used to determine which nodes to execute next.
    """
+    updated_channels: list[str] | None
+    """The channels that were updated in this checkpoint.
+    """


 def copy_checkpoint(checkpoint: Checkpoint) -> Checkpoint:
@@ -92,6 +95,7 @@ def copy_checkpoint(checkpoint: Checkpoint) -> Checkpoint:
        channel_versions=checkpoint["channel_versions"].copy(),
        versions_seen={k: v.copy() for k, v in checkpoint["versions_seen"].items()},
        pending_sends=checkpoint.get("pending_sends", []).copy(),
+        updated_channels=checkpoint.get("updated_channels", None),
    )


@@ -437,6 +441,7 @@ def empty_checkpoint() -> Checkpoint:
        channel_versions={},
        versions_seen={},
        pending_sends=[],
+        updated_channels=None,
    )


@@ -470,4 +475,5 @@ def create_checkpoint(
        channel_versions=checkpoint["channel_versions"],
        versions_seen=checkpoint["versions_seen"],
        pending_sends=checkpoint.get("pending_sends", []),
+        updated_channels=None,
    )
@@ -64,14 +64,21 @@ class AsyncBatchedBaseStore(BaseStore):
        super().__init__()
        self._loop = asyncio.get_running_loop()
        self._aqueue: asyncio.Queue[tuple[asyncio.Future, Op]] = asyncio.Queue()
-        self._task = self._loop.create_task(_run(self._aqueue, weakref.ref(self)))
+        self._task: asyncio.Task | None = None
+        self._ensure_task()

    def __del__(self) -> None:
        try:
-            self._task.cancel()
+            if self._task:
+                self._task.cancel()
        except RuntimeError:
            pass

+    def _ensure_task(self) -> None:
+        """Ensure the background processing loop is running."""
+        if self._task is None or self._task.done():
+            self._task = self._loop.create_task(_run(self._aqueue, weakref.ref(self)))
+
    async def aget(
        self,
        namespace: tuple[str, ...],
@@ -79,7 +86,7 @@ class AsyncBatchedBaseStore(BaseStore):
        *,
        refresh_ttl: bool | None = None,
    ) -> Item | None:
-        assert not self._task.done()
+        self._ensure_task()
        fut = self._loop.create_future()
        self._aqueue.put_nowait(
            (
@@ -104,7 +111,7 @@ class AsyncBatchedBaseStore(BaseStore):
        offset: int = 0,
        refresh_ttl: bool | None = None,
    ) -> list[SearchItem]:
-        assert not self._task.done()
+        self._ensure_task()
        fut = self._loop.create_future()
        self._aqueue.put_nowait(
            (
@@ -130,7 +137,7 @@ class AsyncBatchedBaseStore(BaseStore):
        *,
        ttl: float | None | NotProvided = NOT_PROVIDED,
    ) -> None:
-        assert not self._task.done()
+        self._ensure_task()
        _validate_namespace(namespace)
        fut = self._loop.create_future()
        self._aqueue.put_nowait(
@@ -148,7 +155,7 @@ class AsyncBatchedBaseStore(BaseStore):
        namespace: tuple[str, ...],
        key: str,
    ) -> None:
-        assert not self._task.done()
+        self._ensure_task()
        fut = self._loop.create_future()
        self._aqueue.put_nowait((fut, PutOp(namespace, key, None)))
        return await fut
@@ -162,7 +169,7 @@ class AsyncBatchedBaseStore(BaseStore):
        limit: int = 100,
        offset: int = 0,
    ) -> list[tuple[str, ...]]:
-        assert not self._task.done()
+        self._ensure_task()
        fut = self._loop.create_future()
        match_conditions = []
        if prefix:
@@ -32,6 +32,7 @@ dev = [
  "numpy",
  "pandas",
  "pandas-stubs>=2.2.2.240807",
+  "redis",
 ]

 [tool.hatch.build.targets.wheel]
@@ -0,0 +1,313 @@
+"""Unit tests for Redis cache implementation."""
+
+import time
+
+import pytest
+import redis
+
+from langgraph.cache.redis import RedisCache
+
+
+class TestRedisCache:
+    @pytest.fixture(autouse=True)
+    def setup(self):
+        """Set up test Redis client and cache."""
+        self.client = redis.Redis(
+            host="localhost", port=6379, db=0, decode_responses=False
+        )
+        try:
+            self.client.ping()
+        except redis.ConnectionError:
+            pytest.skip("Redis server not available")
+
+        self.cache = RedisCache(self.client, prefix="test:cache:")
+
+        # Clean up before each test
+        self.client.flushdb()
+
+    def teardown_method(self):
+        """Clean up after each test."""
+        try:
+            self.client.flushdb()
+        except Exception:
+            pass
+
+    def test_basic_set_and_get(self):
+        """Test basic set and get operations."""
+        keys = [(("graph", "node"), "key1")]
+        values = {keys[0]: ({"result": 42}, None)}
+
+        # Set value
+        self.cache.set(values)
+
+        # Get value
+        result = self.cache.get(keys)
+        assert len(result) == 1
+        assert result[keys[0]] == {"result": 42}
+
+    def test_batch_operations(self):
+        """Test batch set and get operations."""
+        keys = [
+            (("graph", "node1"), "key1"),
+            (("graph", "node2"), "key2"),
+            (("other", "node"), "key3"),
+        ]
+        values = {
+            keys[0]: ({"result": 1}, None),
+            keys[1]: ({"result": 2}, 60),  # With TTL
+            keys[2]: ({"result": 3}, None),
+        }
+
+        # Set values
+        self.cache.set(values)
+
+        # Get all values
+        result = self.cache.get(keys)
+        assert len(result) == 3
+        assert result[keys[0]] == {"result": 1}
+        assert result[keys[1]] == {"result": 2}
+        assert result[keys[2]] == {"result": 3}
+
+    def test_ttl_behavior(self):
+        """Test TTL (time-to-live) functionality."""
+        key = (("graph", "node"), "ttl_key")
+        values = {key: ({"data": "expires_soon"}, 1)}  # 1 second TTL
+
+        # Set with TTL
+        self.cache.set(values)
+
+        # Should be available immediately
+        result = self.cache.get([key])
+        assert len(result) == 1
+        assert result[key] == {"data": "expires_soon"}
+
+        # Wait for expiration
+        time.sleep(1.1)
+
+        # Should be expired
+        result = self.cache.get([key])
+        assert len(result) == 0
+
+    def test_namespace_isolation(self):
+        """Test that different namespaces are isolated."""
+        key1 = (("graph1", "node"), "same_key")
+        key2 = (("graph2", "node"), "same_key")
+
+        values = {key1: ({"graph": 1}, None), key2: ({"graph": 2}, None)}
+
+        self.cache.set(values)
+
+        result = self.cache.get([key1, key2])
+        assert result[key1] == {"graph": 1}
+        assert result[key2] == {"graph": 2}
+
+    def test_clear_all(self):
+        """Test clearing all cached values."""
+        keys = [(("graph", "node1"), "key1"), (("graph", "node2"), "key2")]
+        values = {keys[0]: ({"result": 1}, None), keys[1]: ({"result": 2}, None)}
+
+        self.cache.set(values)
+
+        # Verify data exists
+        result = self.cache.get(keys)
+        assert len(result) == 2
+
+        # Clear all
+        self.cache.clear()
+
+        # Verify data is gone
+        result = self.cache.get(keys)
+        assert len(result) == 0
+
+    def test_clear_by_namespace(self):
+        """Test clearing cached values by namespace."""
+        keys = [
+            (("graph1", "node"), "key1"),
+            (("graph2", "node"), "key2"),
+            (("graph1", "other"), "key3"),
+        ]
+        values = {
+            keys[0]: ({"result": 1}, None),
+            keys[1]: ({"result": 2}, None),
+            keys[2]: ({"result": 3}, None),
+        }
+
+        self.cache.set(values)
+
+        # Clear only graph1 namespace
+        self.cache.clear([("graph1", "node"), ("graph1", "other")])
+
+        # graph1 should be cleared, graph2 should remain
+        result = self.cache.get(keys)
+        assert len(result) == 1
+        assert result[keys[1]] == {"result": 2}
+
+    def test_empty_operations(self):
+        """Test behavior with empty keys/values."""
+        # Empty get
+        result = self.cache.get([])
+        assert result == {}
+
+        # Empty set
+        self.cache.set({})  # Should not raise error
+
+    def test_nonexistent_keys(self):
+        """Test getting keys that don't exist."""
+        keys = [(("graph", "node"), "nonexistent")]
+        result = self.cache.get(keys)
+        assert len(result) == 0
+
+    @pytest.mark.asyncio
+    async def test_async_operations(self):
+        """Test async set and get operations with sync Redis client."""
+        # Create sync Redis client and cache (like main integration tests)
+        client = redis.Redis(
+            host="localhost", port=6379, db=1, decode_responses=False
+        )
+        try:
+            client.ping()
+        except Exception:
+            pytest.skip("Redis not available")
+
+        cache = RedisCache(client, prefix="test:async:")
+
+        keys = [(("graph", "node"), "async_key")]
+        values = {keys[0]: ({"async": True}, None)}
+
+        # Async set (delegates to sync)
+        await cache.aset(values)
+
+        # Async get (delegates to sync)
+        result = await cache.aget(keys)
+        assert len(result) == 1
+        assert result[keys[0]] == {"async": True}
+
+        # Cleanup
+        client.flushdb()
+
+    @pytest.mark.asyncio
+    async def test_async_clear(self):
+        """Test async clear operations with sync Redis client."""
+        # Create sync Redis client and cache (like main integration tests)
+        client = redis.Redis(
+            host="localhost", port=6379, db=1, decode_responses=False
+        )
+        try:
+            client.ping()
+        except Exception:
+            pytest.skip("Redis not available")
+
+        cache = RedisCache(client, prefix="test:async:")
+
+        keys = [(("graph", "node"), "key")]
+        values = {keys[0]: ({"data": "test"}, None)}
+
+        await cache.aset(values)
+
+        # Verify data exists
+        result = await cache.aget(keys)
+        assert len(result) == 1
+
+        # Clear all (delegates to sync)
+        await cache.aclear()
+
+        # Verify data is gone
+        result = await cache.aget(keys)
+        assert len(result) == 0
+
+        # Cleanup
+        client.flushdb()
+
+    def test_redis_unavailable_get(self):
+        """Test behavior when Redis is unavailable during get operations."""
+        # Create cache with non-existent Redis server
+        bad_client = redis.Redis(
+            host="nonexistent", port=9999, socket_connect_timeout=0.1
+        )
+        cache = RedisCache(bad_client, prefix="test:cache:")
+
+        keys = [(("graph", "node"), "key")]
+        result = cache.get(keys)
+
+        # Should return empty dict when Redis unavailable
+        assert result == {}
+
+    def test_redis_unavailable_set(self):
+        """Test behavior when Redis is unavailable during set operations."""
+        # Create cache with non-existent Redis server
+        bad_client = redis.Redis(
+            host="nonexistent", port=9999, socket_connect_timeout=0.1
+        )
+        cache = RedisCache(bad_client, prefix="test:cache:")
+
+        keys = [(("graph", "node"), "key")]
+        values = {keys[0]: ({"data": "test"}, None)}
+
+        # Should not raise exception when Redis unavailable
+        cache.set(values)  # Should silently fail
+
+    @pytest.mark.asyncio
+    async def test_redis_unavailable_async(self):
+        """Test async behavior when Redis is unavailable."""
+        # Create sync cache with non-existent Redis server (like main integration tests)
+        bad_client = redis.Redis(
+            host="nonexistent", port=9999, socket_connect_timeout=0.1
+        )
+        cache = RedisCache(bad_client, prefix="test:cache:")
+
+        keys = [(("graph", "node"), "key")]
+        values = {keys[0]: ({"data": "test"}, None)}
+
+        # Should return empty dict for get (delegates to sync)
+        result = await cache.aget(keys)
+        assert result == {}
+
+        # Should not raise exception for set (delegates to sync)
+        await cache.aset(values)  # Should silently fail
+
+    def test_corrupted_data_handling(self):
+        """Test handling of corrupted data in Redis."""
+        # Set some valid data first
+        keys = [(("graph", "node"), "valid_key")]
+        values = {keys[0]: ({"data": "valid"}, None)}
+        self.cache.set(values)
+
+        # Manually insert corrupted data
+        corrupted_key = self.cache._make_key(("graph", "node"), "corrupted_key")
+        self.client.set(corrupted_key, b"invalid:data:format:too:many:colons")
+
+        # Should skip corrupted entry and return only valid ones
+        all_keys = [keys[0], (("graph", "node"), "corrupted_key")]
+        result = self.cache.get(all_keys)
+
+        assert len(result) == 1
+        assert result[keys[0]] == {"data": "valid"}
+
+    def test_key_parsing_edge_cases(self):
+        """Test key parsing with edge cases."""
+        # Test empty namespace
+        key1 = ((), "empty_ns")
+        values = {key1: ({"data": "empty_ns"}, None)}
+        self.cache.set(values)
+        result = self.cache.get([key1])
+        assert result[key1] == {"data": "empty_ns"}
+
+        # Test namespace with special characters
+        key2 = (("graph:with:colons", "node-with-dashes"), "key_with_underscores")
+        values = {key2: ({"data": "special_chars"}, None)}
+        self.cache.set(values)
+        result = self.cache.get([key2])
+        assert result[key2] == {"data": "special_chars"}
+
+    def test_large_data_serialization(self):
+        """Test handling of large data objects."""
+        # Create a large data structure
+        large_data = {"large_list": list(range(1000)), "nested": {"data": "x" * 1000}}
+        key = (("graph", "node"), "large_key")
+        values = {key: (large_data, None)}
+
+        self.cache.set(values)
+        result = self.cache.get([key])
+
+        assert len(result) == 1
+        assert result[key] == large_data
@@ -34,6 +34,42 @@ class MockAsyncBatchedStore(AsyncBatchedBaseStore):
        return self._store.batch(ops)


+async def test_async_batch_store_resilience() -> None:
+    """Test that AsyncBatchedBaseStore recovers gracefully from task cancellation."""
+    doc = {"foo": "bar"}
+    async_store = MockAsyncBatchedStore()
+
+    await async_store.aput(("foo", "langgraph", "foo"), "bar", doc)
+
+    # Store the original task reference
+    original_task = async_store._task
+    assert original_task is not None
+    assert not original_task.done()
+
+    # Cancel the background task
+    original_task.cancel()
+    await asyncio.sleep(0.01)
+    assert original_task.cancelled()
+
+    # Perform a new operation - this should trigger _ensure_task() to create a new task
+    result = await async_store.asearch(("foo", "langgraph", "foo"))
+    assert len(result) > 0
+    assert result[0].value == doc
+
+    # Verify a new task was created
+    new_task = async_store._task
+    assert new_task is not None
+    assert new_task is not original_task
+    assert not new_task.done()
+
+    # Test that operations continue to work with the new task
+    doc2 = {"baz": "qux"}
+    await async_store.aput(("test", "namespace"), "key", doc2)
+    result2 = await async_store.aget(("test", "namespace"), "key")
+    assert result2 is not None
+    assert result2.value == doc2
+
+
 def test_get_text_at_path() -> None:
    nested_data = {
        "name": "test",
@@ -32,6 +32,15 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/a1/ee/48ca1a7c89ffec8b6a0c5d02b89c305671d5ffd8d3c94acf8b8c408575bb/anyio-4.9.0-py3-none-any.whl", hash = "sha256:9f76d541cad6e36af7beb62e978876f3b41e3e04f2c1fbf0884604c0a9c4d93c", size = 100916, upload-time = "2025-03-17T00:02:52.713Z" },
 ]

+[[package]]
+name = "async-timeout"
+version = "5.0.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/a5/ae/136395dfbfe00dfc94da3f3e136d0b13f394cba8f4841120e34226265780/async_timeout-5.0.1.tar.gz", hash = "sha256:d9321a7a3d5a6a5e187e824d2fa0793ce379a202935782d555d6e9d2735677d3", size = 9274, upload-time = "2024-11-06T16:41:39.6Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/fe/ba/e2081de779ca30d473f21f5b30e0e737c438205440784c7dfc81efc2b029/async_timeout-5.0.1-py3-none-any.whl", hash = "sha256:39e3809566ff85354557ec2398b55e096c8364bacac9405a7a1fa429e77fe76c", size = 6233, upload-time = "2024-11-06T16:41:37.9Z" },
+]
+
 [[package]]
 name = "certifi"
 version = "2025.7.9"
@@ -345,6 +354,7 @@ dev = [
    { name = "pytest-asyncio" },
    { name = "pytest-mock" },
    { name = "pytest-watcher" },
+    { name = "redis" },
    { name = "ruff" },
 ]

@@ -366,6 +376,7 @@ dev = [
    { name = "pytest-asyncio" },
    { name = "pytest-mock" },
    { name = "pytest-watcher" },
+    { name = "redis" },
    { name = "ruff" },
 ]

@@ -1153,6 +1164,18 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/19/87/5124b1c1f2412bb95c59ec481eaf936cd32f0fe2a7b16b97b81c4c017a6a/PyYAML-6.0.2-cp39-cp39-win_amd64.whl", hash = "sha256:39693e1f8320ae4f43943590b49779ffb98acb81f788220ea932a6b6c51004d8", size = 162312, upload-time = "2024-08-06T20:33:49.073Z" },
 ]

+[[package]]
+name = "redis"
+version = "6.3.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "async-timeout", marker = "python_full_version < '3.11.3'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/21/cd/030274634a1a052b708756016283ea3d84e91ae45f74d7f5dcf55d753a0f/redis-6.3.0.tar.gz", hash = "sha256:3000dbe532babfb0999cdab7b3e5744bcb23e51923febcfaeb52c8cfb29632ef", size = 4647275, upload-time = "2025-08-05T08:12:31.648Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/df/a7/2fe45801534a187543fc45d28b3844d84559c1589255bc2ece30d92dc205/redis-6.3.0-py3-none-any.whl", hash = "sha256:92f079d656ded871535e099080f70fab8e75273c0236797126ac60242d638e9b", size = 280018, upload-time = "2025-08-05T08:12:30.093Z" },
+]
+
 [[package]]
 name = "requests"
 version = "2.32.4"
@@ -37,11 +37,11 @@ coverage:
 		--cov-report xml \
 		--cov-report term-missing:skip-covered

-start-postgres:
-	docker compose -f tests/compose-postgres.yml up -V --force-recreate --wait --remove-orphans
+start-services:
+	docker compose -f tests/compose-postgres.yml -f tests/compose-redis.yml up -V --force-recreate --wait --remove-orphans

-stop-postgres:
-	docker compose -f tests/compose-postgres.yml down -v
+stop-services:
+	docker compose -f tests/compose-postgres.yml -f tests/compose-redis.yml down -v

 start-dev-server:
 	LOG_LEVEL=warning uv run langgraph dev --config tests/example_app/langgraph.json --no-browser & echo "$$!" > .devserver.pid
@@ -60,11 +60,11 @@ NO_DOCKER ?= $(sh command -v docker >/dev/null 2>&1 && echo "false" || echo "tru

 test:
 	if [ "$(NO_DOCKER)" = "false" ]; then \
-		make start-postgres &&\
+		make start-services &&\
 		make start-dev-server &&\
 		uv run pytest $(TEST); \
 		EXIT_CODE=$$?; \
-		make stop-postgres; \
+		make stop-services; \
 		make stop-dev-server; \
 		exit $$EXIT_CODE; \
 	else \
@@ -74,11 +74,11 @@ test:
 	fi

 test_parallel:
-	make start-postgres &&\
+	make start-services &&\
 	make start-dev-server &&\
 	uv run pytest -n auto --dist worksteal $(TEST); \
 	EXIT_CODE=$$?; \
-	make stop-postgres; \
+	make stop-services; \
 	make stop-dev-server; \
 	exit $$EXIT_CODE

@@ -93,11 +93,11 @@ MAXFAIL_ARGS := $(if $(MAXFAIL),--maxfail $(MAXFAIL),)
 XDIST_ARGS := $(if $(WORKERS),-x $(XDIST_ARGS),)

 test_watch:
-	make start-postgres &&\
+	make start-services &&\
 	make start-dev-server &&\
 	uv run ptw . -- --ff -vv $(XDIST_ARGS) $(MAXFAIL_ARGS) $(TEST); \
 	EXIT_CODE=$$?; \
-	make stop-postgres; \
+	make stop-services; \
 	make stop-dev-server; \
 	exit $$EXIT_CODE

@@ -4,6 +4,7 @@ import asyncio
 import enum
 import inspect
 import sys
+import warnings
 from collections.abc import (
    AsyncIterator,
    Awaitable,
@@ -303,6 +304,16 @@ class RunnableCallable(Runnable):
            if typ != (ANY_TYPE,) and p.annotation not in typ:
                # A specific type is required, but the function annotation does
                # not match the expected type.
+
+                # If this is a config parameter with incorrect typing, emit a warning
+                # because we used to support any type but are moving towards more correct typing
+                if kw == "config" and p.annotation != inspect.Parameter.empty:
+                    warnings.warn(
+                        f"The 'config' parameter should be typed as 'RunnableConfig' or "
+                        f"'RunnableConfig | None', not '{p.annotation}'. ",
+                        UserWarning,
+                        stacklevel=4,
+                    )
                continue

            # If the kwarg is accepted by the function, store the key / runtime attribute to inject
@@ -91,7 +91,7 @@ class GraphInterrupt(GraphBubbleUp):

@deprecated(
    "NodeInterrupt is deprecated. Please use `langgraph.types.interrupt` instead.",
-    stacklevel=2,
+    category=None,
 )
 class NodeInterrupt(GraphInterrupt):
    """Raised by a node to interrupt execution.
@@ -335,7 +335,10 @@ class entrypoint(Generic[ContextT]):
        of the previous invocation on the same thread id.

        ```python
-        from langgraph.checkpoint.memory import InMemorySaver
+        from typing import Optional
+
+        from langgraph.checkpoint.memory import MemorySaver
+
        from langgraph.func import entrypoint

        @entrypoint(checkpointer=InMemorySaver())
@@ -347,7 +350,7 @@ class entrypoint(Generic[ContextT]):
                "thread_id": "some_thread"
            }
        }
-        my_workflow.invoke("hello")
+        my_workflow.invoke("hello", config)
        ```

    Example: Using entrypoint.final to save a value
@@ -357,7 +360,10 @@ class entrypoint(Generic[ContextT]):
        long as the same thread id is used.

        ```python
-        from langgraph.checkpoint.memory import InMemorySaver
+        from typing import Any
+
+        from langgraph.checkpoint.memory import MemorySaver
+
        from langgraph.func import entrypoint

        @entrypoint(checkpointer=InMemorySaver())
@@ -41,16 +41,16 @@ _Writer = Callable[


 def _get_branch_path_input_schema(
-    path: Callable[..., Hashable | list[Hashable]]
-    | Callable[..., Awaitable[Hashable | list[Hashable]]]
-    | Runnable[Any, Hashable | list[Hashable]],
+    path: Callable[..., Hashable | Sequence[Hashable]]
+    | Callable[..., Awaitable[Hashable | Sequence[Hashable]]]
+    | Runnable[Any, Hashable | Sequence[Hashable]],
 ) -> type[Any] | None:
    input = None
    # detect input schema annotation in the branch callable
    try:
        callable_: (
-            Callable[..., Hashable | list[Hashable]]
-            | Callable[..., Awaitable[Hashable | list[Hashable]]]
+            Callable[..., Hashable | Sequence[Hashable]]
+            | Callable[..., Awaitable[Hashable | Sequence[Hashable]]]
            | None
        ) = None
        if isinstance(path, (RunnableCallable, RunnableLambda)):
@@ -22,10 +22,11 @@ from langchain_core.messages import (
    convert_to_messages,
    message_chunk_to_message,
 )
-from typing_extensions import TypedDict
+from typing_extensions import TypedDict, deprecated

 from langgraph._internal._constants import CONF, CONFIG_KEY_SEND, NS_SEP
 from langgraph.graph.state import StateGraph
+from langgraph.warnings import LangGraphDeprecatedSinceV10

 __all__ = (
    "add_messages",
@@ -233,9 +234,16 @@ def add_messages(
    return merged


+@deprecated(
+    "MessageGraph is deprecated in LangGraph v1.0.0, to be removed in v2.0.0. Please use StateGraph with a `messages` key instead.",
+    category=None,
+)
 class MessageGraph(StateGraph):
    """A StateGraph where every node receives a list of messages as input and returns one or more messages as output.

+    !!! warning "Deprecation"
+        MessageGraph is deprecated in LangGraph v1.0.0, to be removed in v2.0.0. Please use StateGraph with a `messages` key instead.
+
    MessageGraph is a subclass of StateGraph whose entire state is a single, append-only* list of messages.
    Each node in a MessageGraph takes a list of messages as input and returns zero or more
    messages as output. The `add_messages` function is used to merge the output messages from each node
@@ -281,6 +289,11 @@ class MessageGraph(StateGraph):
    """

    def __init__(self) -> None:
+        warnings.warn(
+            "MessageGraph is deprecated in LangGraph v1.0.0, to be removed in v2.0.0. Please use StateGraph with a `messages` key instead.",
+            category=LangGraphDeprecatedSinceV10,
+            stacklevel=2,
+        )
        super().__init__(Annotated[list[AnyMessage], add_messages])  # type: ignore[arg-type]


@@ -607,9 +607,9 @@ class StateGraph(Generic[StateT, ContextT, InputT, OutputT]):
    def add_conditional_edges(
        self,
        source: str,
-        path: Callable[..., Hashable | list[Hashable]]
-        | Callable[..., Awaitable[Hashable | list[Hashable]]]
-        | Runnable[Any, Hashable | list[Hashable]],
+        path: Callable[..., Hashable | Sequence[Hashable]]
+        | Callable[..., Awaitable[Hashable | Sequence[Hashable]]]
+        | Runnable[Any, Hashable | Sequence[Hashable]],
        path_map: dict[Hashable, str] | list[str] | None = None,
    ) -> Self:
        """Add a conditional edge from the starting node to any number of destination nodes.
@@ -710,9 +710,9 @@ class StateGraph(Generic[StateT, ContextT, InputT, OutputT]):

    def set_conditional_entry_point(
        self,
-        path: Callable[..., Hashable | list[Hashable]]
-        | Callable[..., Awaitable[Hashable | list[Hashable]]]
-        | Runnable[Any, Hashable | list[Hashable]],
+        path: Callable[..., Hashable | Sequence[Hashable]]
+        | Callable[..., Awaitable[Hashable | Sequence[Hashable]]]
+        | Runnable[Any, Hashable | Sequence[Hashable]],
        path_map: dict[Hashable, str] | list[str] | None = None,
    ) -> Self:
        """Sets a conditional entry point in the graph.
@@ -1390,6 +1390,14 @@ def _is_field_managed_value(name: str, typ: type[Any]) -> ManagedValueSpec | Non
            if is_managed_value(decoration):
                return decoration

+    # Handle Required, NotRequired, etc wrapped types by extracting the inner type
+    if (
+        get_origin(typ) is not None
+        and (args := get_args(typ))
+        and (inner_type := args[0])
+    ):
+        return _is_field_managed_value(name, inner_type)
+
    return None


@@ -8,7 +8,7 @@ from typing import (

 from typing_extensions import TypeGuard

-from langgraph.pregel._scratchpad import PregelScratchpad
+from langgraph._internal._scratchpad import PregelScratchpad

 V = TypeVar("V")
 U = TypeVar("U")
@@ -1,7 +1,7 @@
 from typing import Annotated

+from langgraph._internal._scratchpad import PregelScratchpad
 from langgraph.managed.base import ManagedValue
-from langgraph.pregel._scratchpad import PregelScratchpad

 __all__ = ("IsLastStep", "RemainingStepsManager")

@@ -53,6 +53,7 @@ from langgraph._internal._constants import (
    RETURN,
    TASKS,
 )
+from langgraph._internal._scratchpad import PregelScratchpad
 from langgraph._internal._typing import EMPTY_SEQ, MISSING
 from langgraph.channels.base import BaseChannel
 from langgraph.channels.topic import Topic
@@ -69,7 +70,6 @@ from langgraph.pregel._call import get_runnable_for_task, identifier
 from langgraph.pregel._io import read_channels
 from langgraph.pregel._log import logger
 from langgraph.pregel._read import INPUT_CACHE_KEY_TYPE, PregelNode
-from langgraph.pregel._scratchpad import PregelScratchpad
 from langgraph.runtime import DEFAULT_RUNTIME, Runtime
 from langgraph.store.base import BaseStore
 from langgraph.types import (
@@ -29,6 +29,7 @@ def create_checkpoint(
    step: int,
    *,
    id: str | None = None,
+    updated_channels: set[str] | None = None,
 ) -> Checkpoint:
    """Create a checkpoint for the given channels."""
    ts = datetime.now(timezone.utc).isoformat()
@@ -49,6 +50,7 @@ def create_checkpoint(
        channel_values=values,
        channel_versions=checkpoint["channel_versions"],
        versions_seen=checkpoint["versions_seen"],
+        updated_channels=None if updated_channels is None else sorted(updated_channels),
    )


@@ -81,4 +83,5 @@ def copy_checkpoint(checkpoint: Checkpoint) -> Checkpoint:
        channel_values=checkpoint["channel_values"].copy(),
        channel_versions=checkpoint["channel_versions"].copy(),
        versions_seen={k: v.copy() for k, v in checkpoint["versions_seen"].items()},
+        updated_channels=checkpoint.get("updated_channels", None),
    )
@@ -48,6 +48,7 @@ from langgraph._internal._constants import (
    PUSH,
    RESUME,
 )
+from langgraph._internal._scratchpad import PregelScratchpad
 from langgraph._internal._typing import EMPTY_SEQ, MISSING
 from langgraph.cache.base import BaseCache
 from langgraph.channels.base import BaseChannel
@@ -100,7 +101,6 @@ from langgraph.pregel._io import (
    read_channels,
 )
 from langgraph.pregel._read import PregelNode
-from langgraph.pregel._scratchpad import PregelScratchpad
 from langgraph.pregel._utils import get_new_channel_versions, is_xxh3_128_hexdigest
 from langgraph.pregel.debug import (
    map_debug_checkpoint,
@@ -568,7 +568,9 @@ class PregelLoop:
            if task := tasks.get(tid):
                task.writes.append((k, v))

-    def _first(self, *, input_keys: str | Sequence[str]) -> set[str] | None:
+    def _first(
+        self, *, input_keys: str | Sequence[str], updated_channels: set[str] | None
+    ) -> set[str] | None:
        # resuming from previous checkpoint requires
        # - finding a previous checkpoint
        # - receiving None input (outer graph) or RESUMING flag (subgraph)
@@ -585,8 +587,6 @@ class PregelLoop:
                ),
            )
        )
-        # this can be set only when there are input_writes
-        updated_channels: set[str] | None = None

        # map command to writes
        if isinstance(self.input, Command):
@@ -614,13 +614,15 @@ class PregelLoop:
        if null_writes := [
            w[1:] for w in self.checkpoint_pending_writes if w[0] == NULL_TASK_ID
        ]:
-            apply_writes(
+            null_updated_channels = apply_writes(
                self.checkpoint,
                self.channels,
                [PregelTaskWrites((), INPUT, null_writes, [])],
                self.checkpointer_get_next_version,
                self.trigger_to_nodes,
            )
+            if updated_channels is not None:
+                updated_channels.update(null_updated_channels)
        # proceed past previous checkpoint
        if is_resuming:
            self.checkpoint["versions_seen"].setdefault(INTERRUPT, {})
@@ -648,6 +650,7 @@ class PregelLoop:
                store=None,
                checkpointer=None,
                manager=None,
+                updated_channels=updated_channels,
            )
            # apply input writes
            updated_channels = apply_writes(
@@ -661,6 +664,7 @@ class PregelLoop:
                self.trigger_to_nodes,
            )
            # save input checkpoint
+            self.updated_channels = updated_channels
            self._put_checkpoint({"source": "input"})
        elif CONFIG_KEY_RESUMING not in configurable:
            raise EmptyInputError(f"Received no input for {input_keys}")
@@ -693,6 +697,7 @@ class PregelLoop:
            self.channels if do_checkpoint else None,
            self.step,
            id=self.checkpoint["id"] if exiting else None,
+            updated_channels=self.updated_channels,
        )
        # bail if no checkpointer
        if do_checkpoint and self._checkpointer_put_after_previous is not None:
@@ -1036,7 +1041,12 @@ class SyncPregelLoop(PregelLoop, AbstractContextManager):
        self.step = self.checkpoint_metadata["step"] + 1
        self.stop = self.step + self.config["recursion_limit"] + 1
        self.checkpoint_previous_versions = self.checkpoint["channel_versions"].copy()
-        self.updated_channels = self._first(input_keys=self.input_keys)
+        self.updated_channels = self._first(
+            input_keys=self.input_keys,
+            updated_channels=set(self.checkpoint.get("updated_channels"))  # type: ignore[arg-type]
+            if self.checkpoint.get("updated_channels")
+            else None,
+        )

        return self

@@ -1212,7 +1222,12 @@ class AsyncPregelLoop(PregelLoop, AbstractAsyncContextManager):
        self.step = self.checkpoint_metadata["step"] + 1
        self.stop = self.step + self.config["recursion_limit"] + 1
        self.checkpoint_previous_versions = self.checkpoint["channel_versions"].copy()
-        self.updated_channels = self._first(input_keys=self.input_keys)
+        self.updated_channels = self._first(
+            input_keys=self.input_keys,
+            updated_channels=set(self.checkpoint.get("updated_channels"))  # type: ignore[arg-type]
+            if self.checkpoint.get("updated_channels")
+            else None,
+        )

        return self

@@ -29,16 +29,51 @@ Meta = tuple[tuple[str, ...], dict[str, Any]]

 class StreamMessagesHandler(BaseCallbackHandler, _StreamingCallbackHandler):
    """A callback handler that implements stream_mode=messages.
-    Collects messages from (1) chat model stream events and (2) node outputs."""
+
+    Collects messages from:
+    (1) chat model stream events; and
+    (2) node outputs.
+    """

    run_inline = True
-    """We want this callback to run in the main thread, to avoid order/locking issues."""
+    """We want this callback to run in the main thread to avoid order/locking issues."""

-    def __init__(self, stream: Callable[[StreamChunk], None], subgraphs: bool):
+    def __init__(
+        self,
+        stream: Callable[[StreamChunk], None],
+        subgraphs: bool,
+        *,
+        parent_ns: tuple[str, ...] | None = None,
+    ) -> None:
+        """Configure the handler to stream messages from LLMs and nodes.
+
+        Args:
+            stream: A callable that takes a StreamChunk and emits it.
+            subgraphs: Whether to emit messages from subgraphs.
+            parent_ns: The namespace where the handler was created.
+                We keep track of this namespace to allow calls to subgraphs that
+                were explicitly requested as a stream with `messages` mode
+                configured.
+
+        Example:
+            parent_ns is used to handle scenarios where the subgraph is explicitly
+            streamed with `stream_mode="messages"`.
+
+            ```python
+            def parent_graph_node():
+                # This node is in the parent graph.
+                async for event in some_subgraph(..., stream_mode="messages"):
+                    do something with event # <-- these events will be emitted
+                return ...
+
+            parent_graph.invoke(subgraphs=False)
+            ```
+        """
        self.stream = stream
        self.subgraphs = subgraphs
        self.metadata: dict[UUID, Meta] = {}
        self.seen: set[int | str] = set()
+        self.parent_ns = parent_ns

    def _emit(self, meta: Meta, message: BaseMessage, *, dedupe: bool = False) -> None:
        if dedupe and message.id in self.seen:
@@ -100,7 +135,7 @@ class StreamMessagesHandler(BaseCallbackHandler, _StreamingCallbackHandler):
            ns = tuple(cast(str, metadata["langgraph_checkpoint_ns"]).split(NS_SEP))[
                :-1
            ]
-            if not self.subgraphs and len(ns) > 0:
+            if not self.subgraphs and len(ns) > 0 and ns != self.parent_ns:
                return
            if tags:
                if filtered_tags := [t for t in tags if not t.startswith("seq:step")]:
@@ -30,13 +30,13 @@ from langgraph._internal._constants import (
    RETURN,
 )
 from langgraph._internal._future import chain_future, run_coroutine_threadsafe
+from langgraph._internal._scratchpad import PregelScratchpad
 from langgraph._internal._typing import MISSING
 from langgraph.constants import TAG_HIDDEN
 from langgraph.errors import GraphBubbleUp, GraphInterrupt
 from langgraph.pregel._algo import Call
 from langgraph.pregel._executor import Submit
 from langgraph.pregel._retry import arun_with_retry, run_with_retry
-from langgraph.pregel._scratchpad import PregelScratchpad
 from langgraph.types import (
    CachePolicy,
    PregelExecutableTask,
@@ -637,8 +637,7 @@ class Pregel(
        **deprecated_kwargs: Unpack[DeprecatedKwargs],
    ) -> None:
        if (
-            config_type := deprecated_kwargs.get("config_type"),
-            MISSING,
+            config_type := deprecated_kwargs.get("config_type", MISSING)
        ) is not MISSING:
            warnings.warn(
                "`config_type` is deprecated and will be removed. Please use `context_schema` instead.",
@@ -785,7 +784,8 @@ class Pregel(
        return self

    @deprecated(
-        "`config_schema` is deprecated. Use `get_context_jsonschema` for the relevant schema instead."
+        "`config_schema` is deprecated. Use `get_context_jsonschema` for the relevant schema instead.",
+        category=None,
    )
    def config_schema(self, *, include: Sequence[str] | None = None) -> type[BaseModel]:
        warnings.warn(
@@ -810,7 +810,8 @@ class Pregel(
        return create_model(self.get_name("Config"), field_definitions=fields)

    @deprecated(
-        "`get_config_jsonschema` is deprecated. Use `get_context_jsonschema` instead."
+        "`get_config_jsonschema` is deprecated. Use `get_context_jsonschema` instead.",
+        category=None,
    )
    def get_config_jsonschema(
        self, *, include: Sequence[str] | None = None
@@ -1305,7 +1306,7 @@ class Pregel(
    ) -> Iterator[StateSnapshot]:
        """Get the history of the state of the graph."""
        config = ensure_config(config)
-        checkpointer: BaseCheckpointSaver | None = ensure_config(config)[CONF].get(
+        checkpointer: BaseCheckpointSaver | None = config[CONF].get(
            CONFIG_KEY_CHECKPOINTER, self.checkpointer
        )
        if not checkpointer:
@@ -2351,7 +2352,6 @@ class Pregel(
        interrupt_before: All | Sequence[str] | None,
        interrupt_after: All | Sequence[str] | None,
        durability: Durability | None = None,
-        checkpoint_during: bool | None = None,
    ) -> tuple[
        set[StreamMode],
        str | Sequence[str],
@@ -2399,15 +2399,6 @@ class Pregel(
            cache: BaseCache | None = config[CONF][CONFIG_KEY_CACHE]
        else:
            cache = self.cache
-        if checkpoint_during is not None:
-            if durability is not None:
-                raise ValueError(
-                    "Cannot use both `checkpoint_during` and `durability` parameters."
-                )
-            elif checkpoint_during:
-                durability = "async"
-            else:
-                durability = "exit"
        if durability is None:
            durability = config.get(CONF, {}).get(CONFIG_KEY_DURABILITY, "async")
        return (
@@ -2480,6 +2471,17 @@ class Pregel(
        Yields:
            The output of each step in the graph. The output shape depends on the stream_mode.
        """
+        if (checkpoint_during := kwargs.get("checkpoint_during")) is not None:
+            warnings.warn(
+                "`checkpoint_during` is deprecated and will be removed. Please use `durability` instead.",
+                category=LangGraphDeprecatedSinceV10,
+                stacklevel=2,
+            )
+            if durability is not None:
+                raise ValueError(
+                    "Cannot use both `checkpoint_during` and `durability` parameters. Please use `durability` instead."
+                )
+            durability = "async" if checkpoint_during else "exit"

        if stream_mode is None:
            # if being called as a node in another graph, default to values mode
@@ -2503,14 +2505,6 @@ class Pregel(
            run_id=config.get("run_id"),
        )
        try:
-            deprecated_checkpoint_during = cast(
-                Optional[bool], kwargs.get("checkpoint_during")
-            )
-            if deprecated_checkpoint_during is not None:
-                warnings.warn(
-                    "`checkpoint_during` is deprecated and will be removed. Please use `durability` instead.",
-                    category=LangGraphDeprecatedSinceV10,
-                )
            # assign defaults
            (
                stream_modes,
@@ -2529,11 +2523,8 @@ class Pregel(
                interrupt_before=interrupt_before,
                interrupt_after=interrupt_after,
                durability=durability,
-                checkpoint_during=deprecated_checkpoint_during,
            )
-            if checkpointer is None and (
-                durability is not None or deprecated_checkpoint_during is not None
-            ):
+            if checkpointer is None and durability is not None:
                warnings.warn(
                    "`durability` has no effect when no checkpointer is present.",
                )
@@ -2543,8 +2534,13 @@ class Pregel(
                config[CONF][CONFIG_KEY_CHECKPOINT_NS] = recast_checkpoint_ns(ns)
            # set up messages stream mode
            if "messages" in stream_modes:
+                ns_ = cast(Optional[str], config[CONF].get(CONFIG_KEY_CHECKPOINT_NS))
                run_manager.inheritable_handlers.append(
-                    StreamMessagesHandler(stream.put, subgraphs)
+                    StreamMessagesHandler(
+                        stream.put,
+                        subgraphs,
+                        parent_ns=tuple(ns_.split(NS_SEP)) if ns_ else None,
+                    )
                )

            # set up custom stream mode
@@ -2570,7 +2566,7 @@ class Pregel(
                    pass

            # set durability mode for subgraphs
-            if durability is not None or deprecated_checkpoint_during is not None:
+            if durability is not None:
                config[CONF][CONFIG_KEY_DURABILITY] = durability_

            runtime = Runtime(
@@ -2741,6 +2737,17 @@ class Pregel(
        Yields:
            The output of each step in the graph. The output shape depends on the stream_mode.
        """
+        if (checkpoint_during := kwargs.get("checkpoint_during")) is not None:
+            warnings.warn(
+                "`checkpoint_during` is deprecated and will be removed. Please use `durability` instead.",
+                category=LangGraphDeprecatedSinceV10,
+                stacklevel=2,
+            )
+            if durability is not None:
+                raise ValueError(
+                    "Cannot use both `checkpoint_during` and `durability` parameters. Please use `durability` instead."
+                )
+            durability = "async" if checkpoint_during else "exit"

        if stream_mode is None:
            # if being called as a node in another graph, default to values mode
@@ -2783,14 +2790,6 @@ class Pregel(
            else False
        )
        try:
-            deprecated_checkpoint_during = cast(
-                Optional[bool], kwargs.get("checkpoint_during")
-            )
-            if deprecated_checkpoint_during is not None:
-                warnings.warn(
-                    "`checkpoint_during` is deprecated and will be removed. Please use `durability` instead.",
-                    category=LangGraphDeprecatedSinceV10,
-                )
            # assign defaults
            (
                stream_modes,
@@ -2809,11 +2808,8 @@ class Pregel(
                interrupt_before=interrupt_before,
                interrupt_after=interrupt_after,
                durability=durability,
-                checkpoint_during=deprecated_checkpoint_during,
            )
-            if checkpointer is None and (
-                durability is not None or deprecated_checkpoint_during is not None
-            ):
+            if checkpointer is None and durability is not None:
                warnings.warn(
                    "`durability` has no effect when no checkpointer is present.",
                )
@@ -2823,8 +2819,14 @@ class Pregel(
                config[CONF][CONFIG_KEY_CHECKPOINT_NS] = recast_checkpoint_ns(ns)
            # set up messages stream mode
            if "messages" in stream_modes:
+                # namespace can be None in a root level graph?
+                ns_ = cast(Optional[str], config[CONF].get(CONFIG_KEY_CHECKPOINT_NS))
                run_manager.inheritable_handlers.append(
-                    StreamMessagesHandler(stream_put, subgraphs)
+                    StreamMessagesHandler(
+                        stream_put,
+                        subgraphs,
+                        parent_ns=tuple(ns_.split(NS_SEP)) if ns_ else None,
+                    )
                )

            # set up custom stream mode
@@ -2865,7 +2867,7 @@ class Pregel(
                    pass

            # set durability mode for subgraphs
-            if durability is not None or deprecated_checkpoint_during is not None:
+            if durability is not None:
                config[CONF][CONFIG_KEY_DURABILITY] = durability_

            runtime = Runtime(
@@ -2990,6 +2992,7 @@ class Pregel(
        output_keys: str | Sequence[str] | None = None,
        interrupt_before: All | Sequence[str] | None = None,
        interrupt_after: All | Sequence[str] | None = None,
+        durability: Durability | None = None,
        **kwargs: Any,
    ) -> dict[str, Any] | Any:
        """Run the graph with a single input and config.
@@ -3004,6 +3007,10 @@ class Pregel(
            output_keys: Optional. The output keys to retrieve from the graph run.
            interrupt_before: Optional. The nodes to interrupt the graph run before.
            interrupt_after: Optional. The nodes to interrupt the graph run after.
+            durability: The durability mode for the graph execution, defaults to "async". Options are:
+                - `"sync"`: Changes are persisted synchronously before the next step starts.
+                - `"async"`: Changes are persisted asynchronously while the next step executes.
+                - `"exit"`: Changes are persisted only when the graph exits.
            **kwargs: Additional keyword arguments to pass to the graph run.

        Returns:
@@ -3027,6 +3034,7 @@ class Pregel(
            output_keys=output_keys,
            interrupt_before=interrupt_before,
            interrupt_after=interrupt_after,
+            durability=durability,
            **kwargs,
        ):
            if stream_mode == "values":
@@ -3069,6 +3077,7 @@ class Pregel(
        output_keys: str | Sequence[str] | None = None,
        interrupt_before: All | Sequence[str] | None = None,
        interrupt_after: All | Sequence[str] | None = None,
+        durability: Durability | None = None,
        **kwargs: Any,
    ) -> dict[str, Any] | Any:
        """Asynchronously invoke the graph on a single input.
@@ -3083,6 +3092,10 @@ class Pregel(
            output_keys: Optional. The output keys to include in the result. Default is None.
            interrupt_before: Optional. The nodes to interrupt before. Default is None.
            interrupt_after: Optional. The nodes to interrupt after. Default is None.
+            durability: The durability mode for the graph execution, defaults to "async". Options are:
+                - `"sync"`: Changes are persisted synchronously before the next step starts.
+                - `"async"`: Changes are persisted asynchronously while the next step executes.
+                - `"exit"`: Changes are persisted only when the graph exits.
            **kwargs: Additional keyword arguments.

        Returns:
@@ -3107,6 +3120,7 @@ class Pregel(
            output_keys=output_keys,
            interrupt_before=interrupt_before,
            interrupt_after=interrupt_after,
+            durability=durability,
            **kwargs,
        ):
            if stream_mode == "values":
@@ -191,10 +191,7 @@ class Interrupt:
        return cls(value=value, id=xxh3_128_hexdigest(ns.encode()))

    @property
-    @deprecated(
-        "`interrupt_id` is deprecated. Use `id` instead.",
-        stacklevel=2,
-    )
+    @deprecated("`interrupt_id` is deprecated. Use `id` instead.", category=None)
    def interrupt_id(self) -> str:
        warn(
            "`interrupt_id` is deprecated. Use `id` instead.",
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"

 [project]
 name = "langgraph"
-version = "0.6.2"
+version = "0.6.4"
 description = "Building stateful, multi-actor applications with LLMs"
 authors = []
 requires-python = ">=3.9"
@@ -49,6 +49,7 @@ dev = [
    "types-requests",
    "pycryptodome",
    "langgraph-cli[inmem]",
+    "redis",
 ]

 [tool.uv]
@@ -175,10 +175,10 @@
  '''
 # ---
 # name: test_prebuilt_tool_chat
-  '{"$defs": {"BaseMessage": {"additionalProperties": true, "description": "Base abstract message class.\\n\\nMessages are the inputs and outputs of ChatModels.", "properties": {"content": {"anyOf": [{"type": "string"}, {"items": {"anyOf": [{"type": "string"}, {"additionalProperties": true, "type": "object"}]}, "type": "array"}], "title": "Content"}, "additional_kwargs": {"additionalProperties": true, "title": "Additional Kwargs", "type": "object"}, "response_metadata": {"additionalProperties": true, "title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "type": "string"}, "name": {"anyOf": [{"type": "string"}, {"type": "null"}], "default": null, "title": "Name"}, "id": {"anyOf": [{"type": "string"}, {"type": "null"}], "default": null, "title": "Id"}}, "required": ["content", "type"], "title": "BaseMessage", "type": "object"}}, "description": "The state of the agent.", "properties": {"messages": {"items": {"$ref": "#/$defs/BaseMessage"}, "title": "Messages", "type": "array"}, "is_last_step": {"title": "Is Last Step", "type": "boolean"}, "remaining_steps": {"title": "Remaining Steps", "type": "integer"}}, "required": ["messages", "is_last_step", "remaining_steps"], "title": "AgentState", "type": "object"}'
+  '{"$defs": {"BaseMessage": {"additionalProperties": true, "description": "Base abstract message class.\\n\\nMessages are the inputs and outputs of ChatModels.", "properties": {"content": {"anyOf": [{"type": "string"}, {"items": {"anyOf": [{"type": "string"}, {"additionalProperties": true, "type": "object"}]}, "type": "array"}], "title": "Content"}, "additional_kwargs": {"additionalProperties": true, "title": "Additional Kwargs", "type": "object"}, "response_metadata": {"additionalProperties": true, "title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "type": "string"}, "name": {"anyOf": [{"type": "string"}, {"type": "null"}], "default": null, "title": "Name"}, "id": {"anyOf": [{"type": "string"}, {"type": "null"}], "default": null, "title": "Id"}}, "required": ["content", "type"], "title": "BaseMessage", "type": "object"}}, "description": "The state of the agent.", "properties": {"messages": {"items": {"$ref": "#/$defs/BaseMessage"}, "title": "Messages", "type": "array"}, "remaining_steps": {"title": "Remaining Steps", "type": "integer"}}, "required": ["messages"], "title": "AgentState", "type": "object"}'
 # ---
 # name: test_prebuilt_tool_chat.1
-  '{"$defs": {"BaseMessage": {"additionalProperties": true, "description": "Base abstract message class.\\n\\nMessages are the inputs and outputs of ChatModels.", "properties": {"content": {"anyOf": [{"type": "string"}, {"items": {"anyOf": [{"type": "string"}, {"additionalProperties": true, "type": "object"}]}, "type": "array"}], "title": "Content"}, "additional_kwargs": {"additionalProperties": true, "title": "Additional Kwargs", "type": "object"}, "response_metadata": {"additionalProperties": true, "title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "type": "string"}, "name": {"anyOf": [{"type": "string"}, {"type": "null"}], "default": null, "title": "Name"}, "id": {"anyOf": [{"type": "string"}, {"type": "null"}], "default": null, "title": "Id"}}, "required": ["content", "type"], "title": "BaseMessage", "type": "object"}}, "description": "The state of the agent.", "properties": {"messages": {"items": {"$ref": "#/$defs/BaseMessage"}, "title": "Messages", "type": "array"}, "is_last_step": {"title": "Is Last Step", "type": "boolean"}, "remaining_steps": {"title": "Remaining Steps", "type": "integer"}}, "required": ["messages", "is_last_step", "remaining_steps"], "title": "AgentState", "type": "object"}'
+  '{"$defs": {"BaseMessage": {"additionalProperties": true, "description": "Base abstract message class.\\n\\nMessages are the inputs and outputs of ChatModels.", "properties": {"content": {"anyOf": [{"type": "string"}, {"items": {"anyOf": [{"type": "string"}, {"additionalProperties": true, "type": "object"}]}, "type": "array"}], "title": "Content"}, "additional_kwargs": {"additionalProperties": true, "title": "Additional Kwargs", "type": "object"}, "response_metadata": {"additionalProperties": true, "title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "type": "string"}, "name": {"anyOf": [{"type": "string"}, {"type": "null"}], "default": null, "title": "Name"}, "id": {"anyOf": [{"type": "string"}, {"type": "null"}], "default": null, "title": "Id"}}, "required": ["content", "type"], "title": "BaseMessage", "type": "object"}}, "description": "The state of the agent.", "properties": {"messages": {"items": {"$ref": "#/$defs/BaseMessage"}, "title": "Messages", "type": "array"}, "remaining_steps": {"title": "Remaining Steps", "type": "integer"}}, "required": ["messages"], "title": "AgentState", "type": "object"}'
 # ---
 # name: test_prebuilt_tool_chat.2
  '''
@@ -0,0 +1,16 @@
+name: langgraph-tests
+services:
+  redis-test:
+    image: redis:7-alpine
+    ports:
+      - "6379:6379"
+    command: redis-server --maxmemory 256mb --maxmemory-policy allkeys-lru
+    healthcheck:
+      test: redis-cli ping
+      start_period: 10s
+      timeout: 1s
+      retries: 5
+      interval: 5s
+      start_interval: 1s
+    tmpfs:
+      - /data  # Use tmpfs for faster testing
@@ -3,10 +3,12 @@ from collections.abc import AsyncIterator, Iterator
 from uuid import UUID

 import pytest
+import redis
 from pytest_mock import MockerFixture

 from langgraph.cache.base import BaseCache
 from langgraph.cache.memory import InMemoryCache
+from langgraph.cache.redis import RedisCache
 from langgraph.cache.sqlite import SqliteCache
 from langgraph.checkpoint.base import BaseCheckpointSaver
 from langgraph.store.base import BaseStore
@@ -55,12 +57,34 @@ def durability(request: pytest.FixtureRequest) -> Durability:
    return request.param


-@pytest.fixture(scope="function", params=["sqlite", "memory"])
+@pytest.fixture(
+    scope="function",
+    params=["sqlite", "memory"] if NO_DOCKER else ["sqlite", "memory", "redis"],
+)
 def cache(request: pytest.FixtureRequest) -> Iterator[BaseCache]:
    if request.param == "sqlite":
        yield SqliteCache(path=":memory:")
    elif request.param == "memory":
        yield InMemoryCache()
+    elif request.param == "redis":
+        # Get worker ID for parallel test isolation
+        worker_id = getattr(request.config, "workerinput", {}).get("workerid", "master")
+        
+        redis_client = redis.Redis(
+            host="localhost", port=6379, db=0, decode_responses=False
+        )
+        # Use worker-specific prefix to avoid cache pollution between parallel tests
+        cache = RedisCache(redis_client, prefix=f"test:cache:{worker_id}:")
+        yield cache
+
+        try:
+            # Only clear keys with our specific prefix
+            pattern = f"test:cache:{worker_id}:*"
+            keys = redis_client.keys(pattern)
+            if keys:
+                redis_client.delete(*keys)
+        except Exception:
+            pass
    else:
        raise ValueError(f"Unknown cache type: {request.param}")

@@ -330,6 +330,7 @@ SAVED_CHECKPOINTS = {
                    "docs": ["doc1", "doc2", "doc3", "doc4"],
                    "answer": "doc1,doc2,doc3,doc4",
                },
+                "updated_channels": None,
            },
            metadata={
                "source": "loop",
@@ -390,6 +391,7 @@ SAVED_CHECKPOINTS = {
                    "docs": ["doc1", "doc2", "doc3", "doc4"],
                    "branch:to:qa": None,
                },
+                "updated_channels": None,
            },
            metadata={
                "source": "loop",
@@ -465,6 +467,7 @@ SAVED_CHECKPOINTS = {
                    "branch:to:retriever_one": None,
                    "docs": ["doc3", "doc4"],
                },
+                "updated_channels": None,
            },
            metadata={
                "source": "loop",
@@ -516,6 +519,7 @@ SAVED_CHECKPOINTS = {
                    "branch:to:analyzer_one": None,
                    "branch:to:retriever_two": None,
                },
+                "updated_channels": None,
            },
            metadata={
                "source": "loop",
@@ -570,6 +574,7 @@ SAVED_CHECKPOINTS = {
                    "query": "what is weather in sf",
                    "branch:to:rewrite_query": None,
                },
+                "updated_channels": None,
            },
            metadata={
                "source": "loop",
@@ -618,6 +623,7 @@ SAVED_CHECKPOINTS = {
                },
                "versions_seen": {"__input__": {}},
                "channel_values": {"__start__": {"query": "what is weather in sf"}},
+                "updated_channels": None,
            },
            metadata={
                "source": "input",
@@ -1,11 +1,18 @@
+from __future__ import annotations
+
+import warnings
+from typing import Any, Optional
+
 import pytest
+from langchain_core.runnables import RunnableConfig
 from pytest_mock import MockerFixture
-from typing_extensions import TypedDict
+from typing_extensions import NotRequired, TypedDict

 from langgraph.channels.last_value import LastValue
 from langgraph.errors import NodeInterrupt
 from langgraph.func import entrypoint, task
 from langgraph.graph import StateGraph
+from langgraph.graph.message import MessageGraph
 from langgraph.pregel import NodeBuilder, Pregel
 from langgraph.types import Interrupt, RetryPolicy
 from langgraph.warnings import LangGraphDeprecatedSinceV05, LangGraphDeprecatedSinceV10
@@ -94,8 +101,6 @@ def test_pregel_types_deprecation() -> None:
        from langgraph.pregel.types import StateSnapshot  # noqa: F401


-@pytest.mark.filterwarnings("ignore:`config_schema` is deprecated")
-@pytest.mark.filterwarnings("ignore:`get_config_jsonschema` is deprecated")
 def test_config_schema_deprecation() -> None:
    with pytest.warns(
        LangGraphDeprecatedSinceV10,
@@ -121,7 +126,6 @@ def test_config_schema_deprecation() -> None:
        graph.get_config_jsonschema()


-@pytest.mark.filterwarnings("ignore:`config_schema` is deprecated")
 def test_config_schema_deprecation_on_entrypoint() -> None:
    with pytest.warns(
        LangGraphDeprecatedSinceV10,
@@ -132,10 +136,15 @@ def test_config_schema_deprecation_on_entrypoint() -> None:
        def my_entrypoint(state: PlainState) -> PlainState:
            return state

+    with pytest.warns(
+        LangGraphDeprecatedSinceV10,
+        match="`config_schema` is deprecated. Use `get_context_jsonschema` for the relevant schema instead.",
+    ):
        assert my_entrypoint.context_schema == PlainState
        assert my_entrypoint.config_schema() is not None


+@pytest.mark.filterwarnings("ignore:`config_type` is deprecated")
 def test_config_type_deprecation_pregel(mocker: MockerFixture) -> None:
    add_one = mocker.Mock(side_effect=lambda x: x + 1)
    chain = NodeBuilder().subscribe_only("input").do(add_one).write_to("output")
@@ -159,7 +168,6 @@ def test_config_type_deprecation_pregel(mocker: MockerFixture) -> None:
        assert instance.context_schema == PlainState


-@pytest.mark.filterwarnings("ignore:`interrupt_id` is deprecated. Use `id` instead.")
 def test_interrupt_attributes_deprecation() -> None:
    interrupt = Interrupt(value="question", id="abc")

@@ -170,7 +178,6 @@ def test_interrupt_attributes_deprecation() -> None:
        interrupt.interrupt_id


-@pytest.mark.filterwarnings("ignore:NodeInterrupt is deprecated.")
 def test_node_interrupt_deprecation() -> None:
    with pytest.warns(
        LangGraphDeprecatedSinceV10,
@@ -185,3 +192,152 @@ def test_deprecated_import() -> None:
        match="Importing PREVIOUS from langgraph.constants is deprecated. This constant is now private and should not be used directly.",
    ):
        from langgraph.constants import PREVIOUS  # noqa: F401
+
+
+@pytest.mark.filterwarnings(
+    "ignore:`durability` has no effect when no checkpointer is present"
+)
+def test_checkpoint_during_deprecation_state_graph() -> None:
+    class CheckDurability(TypedDict):
+        durability: NotRequired[str]
+
+    def plain_node(state: CheckDurability, config: RunnableConfig) -> CheckDurability:
+        return {"durability": config["configurable"]["__pregel_durability"]}
+
+    builder = StateGraph(CheckDurability)
+    builder.add_node("plain_node", plain_node)
+    builder.set_entry_point("plain_node")
+    graph = builder.compile()
+
+    with pytest.warns(
+        LangGraphDeprecatedSinceV10,
+        match="`checkpoint_during` is deprecated and will be removed. Please use `durability` instead.",
+    ):
+        result = graph.invoke({}, checkpoint_during=True)
+        assert result["durability"] == "async"
+
+    with pytest.warns(
+        LangGraphDeprecatedSinceV10,
+        match="`checkpoint_during` is deprecated and will be removed. Please use `durability` instead.",
+    ):
+        result = graph.invoke({}, checkpoint_during=False)
+        assert result["durability"] == "exit"
+
+    with pytest.warns(
+        LangGraphDeprecatedSinceV10,
+        match="`checkpoint_during` is deprecated and will be removed. Please use `durability` instead.",
+    ):
+        for chunk in graph.stream({}, checkpoint_during=True):  # type: ignore[arg-type]
+            assert chunk["plain_node"]["durability"] == "async"
+
+    with pytest.warns(
+        LangGraphDeprecatedSinceV10,
+        match="`checkpoint_during` is deprecated and will be removed. Please use `durability` instead.",
+    ):
+        for chunk in graph.stream({}, checkpoint_during=False):  # type: ignore[arg-type]
+            assert chunk["plain_node"]["durability"] == "exit"
+
+
+def test_config_parameter_incorrect_typing() -> None:
+    """Test that a warning is raised when config parameter is typed incorrectly."""
+    builder = StateGraph(PlainState)
+
+    # Test sync function with config: dict
+    with pytest.warns(
+        UserWarning,
+        match="The 'config' parameter should be typed as 'RunnableConfig' or 'RunnableConfig | None', not '.*dict.*'. ",
+    ):
+
+        def sync_node_with_dict_config(state: PlainState, config: dict) -> PlainState:
+            return state
+
+        builder.add_node(sync_node_with_dict_config)
+
+    # Test async function with config: dict
+    with pytest.warns(
+        UserWarning,
+        match="The 'config' parameter should be typed as 'RunnableConfig' or 'RunnableConfig | None', not '.*dict.*'. ",
+    ):
+
+        async def async_node_with_dict_config(
+            state: PlainState, config: dict
+        ) -> PlainState:
+            return state
+
+        builder.add_node(async_node_with_dict_config)
+
+    # Test with other incorrect types
+    with pytest.warns(
+        UserWarning,
+        match="The 'config' parameter should be typed as 'RunnableConfig' or 'RunnableConfig | None', not '.*Any.*'. ",
+    ):
+
+        def sync_node_with_any_config(state: PlainState, config: Any) -> PlainState:
+            return state
+
+        builder.add_node(sync_node_with_any_config)
+
+    with pytest.warns(
+        UserWarning,
+        match="The 'config' parameter should be typed as 'RunnableConfig' or 'RunnableConfig | None', not '.*Any.*'. ",
+    ):
+
+        async def async_node_with_any_config(
+            state: PlainState, config: Any
+        ) -> PlainState:
+            return state
+
+        builder.add_node(async_node_with_any_config)
+
+    with warnings.catch_warnings(record=True) as w:
+
+        def node_with_correct_config(
+            state: PlainState, config: RunnableConfig
+        ) -> PlainState:
+            return state
+
+        builder.add_node(node_with_correct_config)
+
+        def node_with_optional_config(
+            state: PlainState,
+            config: Optional[RunnableConfig],  # noqa: UP045
+        ) -> PlainState:
+            return state
+
+        builder.add_node(node_with_optional_config)
+
+        def node_with_untyped_config(state: PlainState, config) -> PlainState:
+            return state
+
+        builder.add_node(node_with_untyped_config)
+
+        async def async_node_with_correct_config(
+            state: PlainState, config: RunnableConfig
+        ) -> PlainState:
+            return state
+
+        builder.add_node(async_node_with_correct_config)
+
+        async def async_node_with_optional_config(
+            state: PlainState,
+            config: Optional[RunnableConfig],  # noqa: UP045
+        ) -> PlainState:
+            return state
+
+        builder.add_node(async_node_with_optional_config)
+
+        async def async_node_with_untyped_config(
+            state: PlainState, config
+        ) -> PlainState:
+            return state
+
+        builder.add_node(async_node_with_untyped_config)
+        assert len(w) == 0
+
+
+def test_message_graph_deprecation() -> None:
+    with pytest.warns(
+        LangGraphDeprecatedSinceV10,
+        match="MessageGraph is deprecated in LangGraph v1.0.0, to be removed in v2.0.0. Please use StateGraph with a `messages` key instead.",
+    ):
+        MessageGraph()
@@ -6,7 +6,9 @@ from dataclasses import replace
 from typing import Annotated, Any, Literal, Optional, Union, cast

 import pytest
+from langchain_core.messages import AIMessage, AnyMessage, ToolCall
 from langchain_core.runnables import RunnableConfig, RunnableMap, RunnablePick
+from langchain_core.tools import tool
 from pytest_mock import MockerFixture
 from syrupy import SnapshotAssertion
 from typing_extensions import TypedDict
@@ -18,7 +20,7 @@ from langgraph.checkpoint.base import BaseCheckpointSaver
 from langgraph.checkpoint.memory import InMemorySaver
 from langgraph.constants import END, START
 from langgraph.graph import StateGraph
-from langgraph.graph.message import MessageGraph, MessagesState, add_messages
+from langgraph.graph.message import MessagesState, add_messages
 from langgraph.prebuilt.chat_agent_executor import create_react_agent
 from langgraph.prebuilt.tool_node import ToolNode
 from langgraph.pregel import NodeBuilder, Pregel
@@ -2441,7 +2443,7 @@ def test_message_graph(
            return "continue"

    # Define a new graph
-    workflow = MessageGraph()
+    workflow = StateGraph(state_schema=Annotated[list[AnyMessage], add_messages])  # type: ignore[arg-type]

    # Define the two nodes we will cycle between
    workflow.add_node("agent", model)
@@ -2487,7 +2489,7 @@ def test_message_graph(
        assert json.dumps(app.get_graph().to_json(), indent=2) == snapshot
        assert app.get_graph().draw_mermaid(with_styles=False) == snapshot

-    assert app.invoke(HumanMessage(content="what is weather in sf")) == [
+    assert app.invoke([HumanMessage(content="what is weather in sf")]) == [
        _AnyIdHumanMessage(
            content="what is weather in sf",
        ),
@@ -6435,10 +6437,6 @@ def test_weather_subgraph(
    from langchain_core.language_models.fake_chat_models import (
        FakeMessagesListChatModel,
    )
-    from langchain_core.messages import AIMessage, ToolCall
-    from langchain_core.tools import tool
-
-    from langgraph.graph import MessagesState

    # setup subgraph

@@ -11,7 +11,7 @@ from typing import (
 )

 import pytest
-from langchain_core.messages import ToolCall
+from langchain_core.messages import AnyMessage, ToolCall
 from langchain_core.runnables import RunnableConfig, RunnablePick
 from pytest_mock import MockerFixture
 from typing_extensions import TypedDict
@@ -21,7 +21,7 @@ from langgraph.channels.last_value import LastValue
 from langgraph.channels.untracked_value import UntrackedValue
 from langgraph.checkpoint.base import BaseCheckpointSaver
 from langgraph.constants import END, START
-from langgraph.graph.message import MessageGraph, add_messages
+from langgraph.graph.message import add_messages
 from langgraph.graph.state import StateGraph
 from langgraph.prebuilt.chat_agent_executor import create_react_agent
 from langgraph.prebuilt.tool_node import ToolNode
@@ -2117,7 +2117,7 @@ async def test_message_graph(async_checkpointer: BaseCheckpointSaver) -> None:
            return "continue"

    # Define a new graph
-    workflow = MessageGraph()
+    workflow = StateGraph(state_schema=Annotated[list[AnyMessage], add_messages])  # type: ignore[arg-type]

    # Define the two nodes we will cycle between
    workflow.add_node("agent", model)
@@ -2157,7 +2157,7 @@ async def test_message_graph(async_checkpointer: BaseCheckpointSaver) -> None:
    # meaning you can use it as you would any other runnable
    app = workflow.compile()

-    assert await app.ainvoke(HumanMessage(content="what is weather in sf")) == [
+    assert await app.ainvoke([HumanMessage(content="what is weather in sf")]) == [
        _AnyIdHumanMessage(
            content="what is weather in sf",
        ),
@@ -0,0 +1,27 @@
+from typing_extensions import NotRequired, Required, TypedDict
+
+from langgraph.graph import StateGraph
+from langgraph.managed import RemainingSteps
+
+
+class StatePlain(TypedDict):
+    remaining_steps: RemainingSteps
+
+
+class StateNotRequired(TypedDict):
+    remaining_steps: NotRequired[RemainingSteps]
+
+
+class StateRequired(TypedDict):
+    remaining_steps: Required[RemainingSteps]
+
+
+def test_managed_values_recognized() -> None:
+    graph = StateGraph(StatePlain)
+    assert "remaining_steps" in graph.managed
+
+    graph = StateGraph(StateNotRequired)
+    assert "remaining_steps" in graph.managed
+
+    graph = StateGraph(StateRequired)
+    assert "remaining_steps" in graph.managed
@@ -16,6 +16,7 @@ from typing import Annotated, Any, Literal, Optional, Union, get_type_hints

 import pytest
 from langchain_core.language_models import GenericFakeChatModel
+from langchain_core.messages import AnyMessage
 from langchain_core.runnables import (
    RunnableConfig,
    RunnableLambda,
@@ -26,7 +27,7 @@ from langsmith import traceable
 from pydantic import BaseModel, ConfigDict, Field, ValidationError
 from pytest_mock import MockerFixture
 from syrupy import SnapshotAssertion
-from typing_extensions import TypedDict
+from typing_extensions import NotRequired, TypedDict

 from langgraph._internal._constants import CONFIG_KEY_NODE_FINISHED, ERROR, PULL
 from langgraph.cache.base import BaseCache
@@ -45,7 +46,7 @@ from langgraph.config import get_stream_writer
 from langgraph.errors import GraphRecursionError, InvalidUpdateError, ParentCommand
 from langgraph.func import entrypoint, task
 from langgraph.graph import END, START, StateGraph
-from langgraph.graph.message import MessageGraph, MessagesState, add_messages
+from langgraph.graph.message import MessagesState, add_messages
 from langgraph.prebuilt.tool_node import ToolNode
 from langgraph.pregel import (
    NodeBuilder,
@@ -967,6 +968,7 @@ def test_pending_writes_resume(
                "branch:to:two": AnyVersion(),
            },
            "channel_values": {"value": 6},
+            "updated_channels": ["value"],
        },
        metadata={
            "parents": {},
@@ -1014,6 +1016,7 @@ def test_pending_writes_resume(
                "branch:to:one": None,
                "branch:to:two": None,
            },
+            "updated_channels": ["branch:to:one", "branch:to:two", "value"],
        },
        metadata={
            "parents": {},
@@ -1065,6 +1068,7 @@ def test_pending_writes_resume(
                "__start__": AnyVersion(),
            },
            "channel_values": {"__start__": {"value": 1}},
+            "updated_channels": ["__start__"],
        },
        metadata={
            "parents": {},
@@ -3907,7 +3911,7 @@ def test_remove_message_via_state_update(
 ) -> None:
    from langchain_core.messages import AIMessage, HumanMessage, RemoveMessage

-    workflow = MessageGraph()
+    workflow = StateGraph(state_schema=Annotated[list[AnyMessage], add_messages])  # type: ignore[arg-type]
    workflow.add_node(
        "chatbot",
        lambda state: [
@@ -3940,7 +3944,7 @@ def test_remove_message_via_state_update(
 def test_remove_message_from_node():
    from langchain_core.messages import AIMessage, HumanMessage, RemoveMessage

-    workflow = MessageGraph()
+    workflow = StateGraph(state_schema=Annotated[list[AnyMessage], add_messages])  # type: ignore[arg-type]
    workflow.add_node(
        "chatbot",
        lambda state: [
@@ -8262,3 +8266,53 @@ def test_fork_and_update_task_results(sync_checkpointer: BaseCheckpointSaver) ->
            ],
        ],
    ]
+
+
+def test_subgraph_streaming_sync() -> None:
+    """Test subgraph streaming when used as a node in sync version"""
+
+    # Create a fake chat model that returns a simple response
+    model = GenericFakeChatModel(messages=iter(["The weather is sunny today."]))
+
+    # Create a subgraph that uses the fake chat model
+    def call_model_node(state: MessagesState, config: RunnableConfig) -> MessagesState:
+        """Node that calls the model with the last message."""
+        messages = state["messages"]
+        last_message = messages[-1].content if messages else ""
+        response = model.invoke([("user", last_message)], config)
+        return {"messages": [response]}
+
+    # Build the subgraph
+    subgraph = StateGraph(MessagesState)
+    subgraph.add_node("call_model", call_model_node)
+    subgraph.add_edge(START, "call_model")
+    compiled_subgraph = subgraph.compile()
+
+    class SomeCustomState(TypedDict):
+        last_chunk: NotRequired[str]
+        num_chunks: NotRequired[int]
+
+    # Will invoke a subgraph as a function
+    def parent_node(state: SomeCustomState, config: RunnableConfig) -> dict:
+        """Node that runs the subgraph."""
+        msgs = {"messages": [("user", "What is the weather in Tokyo?")]}
+        events = []
+        for event in compiled_subgraph.stream(msgs, config, stream_mode="messages"):
+            events.append(event)
+        ai_msg_chunks = [ai_msg_chunk for ai_msg_chunk, _ in events]
+        return {
+            "last_chunk": ai_msg_chunks[-1],
+            "num_chunks": len(ai_msg_chunks),
+        }
+
+    # Build the main workflow
+    workflow = StateGraph(SomeCustomState)
+    workflow.add_node("subgraph", parent_node)
+    workflow.add_edge(START, "subgraph")
+    compiled_workflow = workflow.compile()
+
+    # Test the basic functionality
+    result = compiled_workflow.invoke({})
+
+    assert result["last_chunk"].content == "today."
+    assert result["num_chunks"] == 9
@@ -26,7 +26,7 @@ from langchain_core.utils.aiter import aclosing
 from pydantic import BaseModel, ConfigDict, Field, ValidationError
 from pytest_mock import MockerFixture
 from syrupy import SnapshotAssertion
-from typing_extensions import TypedDict
+from typing_extensions import NotRequired, TypedDict

 from langgraph._internal._constants import CONFIG_KEY_NODE_FINISHED, ERROR, PULL
 from langgraph.cache.base import BaseCache
@@ -1908,6 +1908,7 @@ async def test_pending_writes_resume(
                "branch:to:two": AnyVersion(),
            },
            "channel_values": {"value": 6},
+            "updated_channels": ["value"],
        },
        metadata={
            "parents": {},
@@ -1955,6 +1956,7 @@ async def test_pending_writes_resume(
                "branch:to:one": None,
                "branch:to:two": None,
            },
+            "updated_channels": ["branch:to:one", "branch:to:two", "value"],
        },
        metadata={
            "parents": {},
@@ -2002,6 +2004,7 @@ async def test_pending_writes_resume(
                "__start__": AnyVersion(),
            },
            "channel_values": {"__start__": {"value": 1}},
+            "updated_channels": ["__start__"],
        },
        metadata={
            "parents": {},
@@ -9050,3 +9053,57 @@ async def test_fork_and_update_task_results(
            ],
        ],
    ]
+
+
+async def test_subgraph_streaming_async() -> None:
+    """Test subgraph streaming when used as a node in async version"""
+
+    # Create a fake chat model that returns a simple response
+    model = GenericFakeChatModel(messages=iter(["The weather is sunny today."]))
+
+    # Create a subgraph that uses the fake chat model
+    async def call_model_node(
+        state: MessagesState, config: RunnableConfig
+    ) -> MessagesState:
+        """Node that calls the model with the last message."""
+        messages = state["messages"]
+        last_message = messages[-1].content if messages else ""
+        response = await model.ainvoke([("user", last_message)], config)
+        return {"messages": [response]}
+
+    # Build the subgraph
+    subgraph = StateGraph(MessagesState)
+    subgraph.add_node("call_model", call_model_node)
+    subgraph.add_edge(START, "call_model")
+    compiled_subgraph = subgraph.compile()
+
+    class SomeCustomState(TypedDict):
+        last_chunk: NotRequired[str]
+        num_chunks: NotRequired[int]
+
+    # Will invoke a subgraph as a function
+    async def parent_node(state: SomeCustomState, config: RunnableConfig) -> dict:
+        """Node that runs the subgraph."""
+        msgs = {"messages": [("user", "What is the weather in Tokyo?")]}
+        events = []
+        async for event in compiled_subgraph.astream(
+            msgs, config, stream_mode="messages"
+        ):
+            events.append(event)
+        ai_msg_chunks = [ai_msg_chunk for ai_msg_chunk, _ in events]
+        return {
+            "last_chunk": ai_msg_chunks[-1],
+            "num_chunks": len(ai_msg_chunks),
+        }
+
+    # Build the main workflow
+    workflow = StateGraph(SomeCustomState)
+    workflow.add_node("subgraph", parent_node)
+    workflow.add_edge(START, "subgraph")
+    compiled_workflow = workflow.compile()
+
+    # Test the basic functionality
+    result = await compiled_workflow.ainvoke({})
+
+    assert result["last_chunk"].content == "today."
+    assert result["num_chunks"] == 9
@@ -119,6 +119,15 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/03/49/d10027df9fce941cb8184e78a02857af36360d33e1721df81c5ed2179a1a/async_lru-2.0.5-py3-none-any.whl", hash = "sha256:ab95404d8d2605310d345932697371a5f40def0487c03d6d0ad9138de52c9943", size = 6069, upload-time = "2025-03-16T17:25:35.422Z" },
 ]

+[[package]]
+name = "async-timeout"
+version = "5.0.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/a5/ae/136395dfbfe00dfc94da3f3e136d0b13f394cba8f4841120e34226265780/async_timeout-5.0.1.tar.gz", hash = "sha256:d9321a7a3d5a6a5e187e824d2fa0793ce379a202935782d555d6e9d2735677d3", size = 9274, upload-time = "2024-11-06T16:41:39.6Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/fe/ba/e2081de779ca30d473f21f5b30e0e737c438205440784c7dfc81efc2b029/async_timeout-5.0.1-py3-none-any.whl", hash = "sha256:39e3809566ff85354557ec2398b55e096c8364bacac9405a7a1fa429e77fe76c", size = 6233, upload-time = "2024-11-06T16:41:37.9Z" },
+]
+
 [[package]]
 name = "attrs"
 version = "25.3.0"
@@ -1192,7 +1201,7 @@ wheels = [

 [[package]]
 name = "langgraph"
-version = "0.6.2"
+version = "0.6.4"
 source = { editable = "." }
 dependencies = [
    { name = "langchain-core" },
@@ -1225,6 +1234,7 @@ dev = [
    { name = "pytest-repeat" },
    { name = "pytest-watcher" },
    { name = "pytest-xdist", extra = ["psutil"] },
+    { name = "redis" },
    { name = "ruff" },
    { name = "syrupy" },
    { name = "types-requests" },
@@ -1263,6 +1273,7 @@ dev = [
    { name = "pytest-repeat" },
    { name = "pytest-watcher" },
    { name = "pytest-xdist", extras = ["psutil"] },
+    { name = "redis" },
    { name = "ruff" },
    { name = "syrupy" },
    { name = "types-requests" },
@@ -1326,6 +1337,7 @@ dev = [
    { name = "pytest-asyncio" },
    { name = "pytest-mock" },
    { name = "pytest-watcher" },
+    { name = "redis" },
    { name = "ruff" },
 ]

@@ -1433,7 +1445,7 @@ dev = [

 [[package]]
 name = "langgraph-prebuilt"
-version = "0.6.2"
+version = "0.6.4"
 source = { editable = "../prebuilt" }
 dependencies = [
    { name = "langchain-core" },
@@ -2628,6 +2640,18 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/51/8b/619a9ee2fa4d3c724fbadde946427735ade64da03894b071bbdc3b789d83/pyzmq-27.0.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:096af9e133fec3a72108ddefba1e42985cb3639e9de52cfd336b6fc23aa083e9", size = 544715, upload-time = "2025-06-13T14:09:05.579Z" },
 ]

+[[package]]
+name = "redis"
+version = "6.3.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "async-timeout", marker = "python_full_version < '3.11.3'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/21/cd/030274634a1a052b708756016283ea3d84e91ae45f74d7f5dcf55d753a0f/redis-6.3.0.tar.gz", hash = "sha256:3000dbe532babfb0999cdab7b3e5744bcb23e51923febcfaeb52c8cfb29632ef", size = 4647275, upload-time = "2025-08-05T08:12:31.648Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/df/a7/2fe45801534a187543fc45d28b3844d84559c1589255bc2ece30d92dc205/redis-6.3.0-py3-none-any.whl", hash = "sha256:92f079d656ded871535e099080f70fab8e75273c0236797126ac60242d638e9b", size = 280018, upload-time = "2025-08-05T08:12:30.093Z" },
+]
+
 [[package]]
 name = "referencing"
 version = "0.36.2"
@@ -7,11 +7,11 @@ all: help
 # TESTING AND COVERAGE
 ######################

-start-postgres:
-	docker compose -f tests/compose-postgres.yml up -V --force-recreate --wait --remove-orphans
+start-services:
+	docker compose -f tests/compose-postgres.yml -f tests/compose-redis.yml up -V --force-recreate --wait --remove-orphans

-stop-postgres:
-	docker compose -f tests/compose-postgres.yml down -v
+stop-services:
+	docker compose -f tests/compose-postgres.yml -f tests/compose-redis.yml down -v

 TEST ?= .

@@ -19,17 +19,20 @@ test-fast:
 	LANGGRAPH_TEST_FAST=1 uv run pytest $(TEST)

 test:
-	make start-postgres && LANGGRAPH_TEST_FAST=0 uv run pytest $(TEST); \
+	make start-services && LANGGRAPH_TEST_FAST=0 uv run pytest $(TEST); \
 	EXIT_CODE=$$?; \
-	make stop-postgres; \
+	make stop-services; \
 	exit $$EXIT_CODE

 test_watch:
-	make start-postgres && LANGGRAPH_TEST_FAST=0 uv run ptw $(TEST); \
+	make start-services && LANGGRAPH_TEST_FAST=0 uv run ptw $(TEST); \
 	EXIT_CODE=$$?; \
-	make stop-postgres; \
+	make stop-services; \
 	exit $$EXIT_CODE

+snapshot_upate:
+	LANGGRAPH_TEST_FAST=1 uv run pytest --snapshot-update $(TEST)
+
 ######################
 # LINTING AND FORMATTING
 ######################
@@ -1,26 +0,0 @@
-from typing import Any, Literal, TypedDict
-
-from langchain_core.messages import ToolCall
-
-
-class ToolCallWithContext(TypedDict):
-    """ToolCall with additional context for graph state.
-
-    This is an internal data-structure meant to help the ToolNode accept
-    tools calls with additional context (e.g. state) when dispatched using the
-    `Send` API.
-
-    The Send API is used in create_react_agent to be able to distribute the tool
-    calls in parallel and support human-in-the-loop workflows where graph execution
-    may be paused for an indefinite time.
-    """
-
-    tool_call: ToolCall
-    __type: Literal["tool_call_with_context"]
-    """Type to parameterize the payload.
-    
-    Using "__" as a prefix to be defensive against potential name collisions with
-    regular user state.
-    """
-    state: Any
-    """The state is provided as additional context."""
@@ -0,0 +1,160 @@
+from __future__ import annotations
+
+import inspect
+from dataclasses import dataclass
+from typing import Any, Optional, Callable
+
+from langchain_core.runnables import RunnableConfig
+
+from langgraph.store.base import BaseStore
+from langgraph.types import StreamWriter
+
+
+# Special type to denote any type is accepted
+ANY_TYPE = object()
+
+VALID_KINDS = (inspect.Parameter.POSITIONAL_OR_KEYWORD, inspect.Parameter.KEYWORD_ONLY)
+
+
+
+# List of keyword arguments that can be injected into nodes / tasks / tools at runtime.
+# A named argument may appear multiple times if it appears with distinct types.
+KWARGS_CONFIG_KEYS: tuple[tuple[str, tuple[Any, ...], str, Any], ...] = (
+    (
+        "config",
+        (
+            RunnableConfig,
+            "RunnableConfig",
+            Optional[RunnableConfig],
+            "Optional[RunnableConfig]",
+            inspect.Parameter.empty,
+        ),
+        # for now, use config directly, eventually, will pop off of Runtime
+        "N/A",
+        inspect.Parameter.empty,
+    ),
+    (
+        "writer",
+        (StreamWriter, "StreamWriter", inspect.Parameter.empty),
+        "stream_writer",
+        lambda _: None,
+    ),
+    (
+        "store",
+        (
+            BaseStore,
+            "BaseStore",
+            inspect.Parameter.empty,
+        ),
+        "store",
+        inspect.Parameter.empty,
+    ),
+    (
+        "store",
+        (
+            Optional[BaseStore],
+            "Optional[BaseStore]",
+        ),
+        "store",
+        None,
+    ),
+    (
+        "previous",
+        (ANY_TYPE,),
+        "previous",
+        inspect.Parameter.empty,
+    ),
+    (
+        "runtime",
+        (ANY_TYPE,),
+        # we never hit this block, we just inject runtime directly
+        "N/A",
+        inspect.Parameter.empty,
+    ),
+)
+
+
+@dataclass
+class InjectionInfo:
+    """Information about which injected arguments a function supports.
+
+    Attributes:
+        func_accepts: Dictionary mapping argument names to tuples of (runtime_key, default_value)
+        supported_args: Set of argument names that the function accepts for injection
+        has_config: Whether the function accepts a 'config' argument
+        has_writer: Whether the function accepts a 'writer' argument
+        has_store: Whether the function accepts a 'store' argument
+        has_previous: Whether the function accepts a 'previous' argument
+        has_runtime: Whether the function accepts a 'runtime' argument
+    """
+
+    func_accepts: dict[str, tuple[str, Any]]
+    supported_args: set[str]
+    has_config: bool
+    has_writer: bool
+    has_store: bool
+    has_previous: bool
+    has_runtime: bool
+
+
+def get_function_injection_info(func: Callable) -> InjectionInfo:
+    """Determine which injected arguments are supported by a function.
+
+    This function analyzes a function's signature to determine which runtime arguments
+    it can accept for injection. It uses the same logic as RunnableCallable to check
+    parameter names, types, and annotations against the supported injection types.
+
+    Args:
+        func: The function to analyze for injection support
+
+    Returns:
+        InjectionInfo containing details about which arguments the function supports
+
+    Example:
+        ```python
+        def my_tool(x: int, config: RunnableConfig, store: BaseStore) -> str:
+            return f"x={x}, config={config is not None}, store={store is not None}"
+
+        info = get_function_injection_info(my_tool)
+        print(info.has_config)  # True
+        print(info.has_store)   # True
+        print(info.has_writer)  # False
+        print(info.supported_args)  # {'config', 'store'}
+        ```
+    """
+    func_accepts: dict[str, tuple[str, Any]] = {}
+    params = inspect.signature(func).parameters
+
+    for kw, typ, runtime_key, default in KWARGS_CONFIG_KEYS:
+        p = params.get(kw)
+
+        if p is None or p.kind not in VALID_KINDS:
+            # If parameter is not found or is not a valid kind, skip
+            continue
+
+        if typ != (ANY_TYPE,) and p.annotation not in typ:
+            # A specific type is required, but the function annotation does
+            # not match the expected type.
+
+            # If this is a config parameter with incorrect typing, we still accept it
+            # but could emit a warning (following RunnableCallable behavior)
+            if kw == "config" and p.annotation != inspect.Parameter.empty:
+                # Could add warning here if needed
+                pass
+            else:
+                continue
+
+        # If the kwarg is accepted by the function, store the key / runtime attribute to inject
+        func_accepts[kw] = (runtime_key, default)
+
+    supported_args = set(func_accepts.keys())
+
+    return InjectionInfo(
+        func_accepts=func_accepts,
+        supported_args=supported_args,
+        has_config="config" in supported_args,
+        has_writer="writer" in supported_args,
+        has_store="store" in supported_args,
+        has_previous="previous" in supported_args,
+        has_runtime="runtime" in supported_args,
+    )
@@ -31,6 +31,8 @@ Typical Usage:
    ```
 """

+from __future__ import annotations
+
 import asyncio
 import inspect
 import json
@@ -74,7 +76,6 @@ from typing_extensions import Annotated, get_args, get_origin
 from langgraph._internal._runnable import RunnableCallable
 from langgraph.errors import GraphBubbleUp
 from langgraph.graph.message import REMOVE_ALL_MESSAGES
-from langgraph.prebuilt._internal import ToolCallWithContext
 from langgraph.store.base import BaseStore
 from langgraph.types import Command, Send

@@ -238,17 +239,50 @@ def _infer_handled_types(handler: Callable[..., str]) -> tuple[type[Exception],


 class ToolNode(RunnableCallable):
-    """A node that runs the tools called in the last AIMessage.
+    """A node for executing tools in LangGraph workflows.

-    It can be used either in StateGraph with a "messages" state key (or a custom key passed via ToolNode's 'messages_key').
-    If multiple tool calls are requested, they will be run in parallel. The output will be
-    a list of ToolMessages, one for each tool call.
+    Handles tool execution patterns including function calls, state injection,
+    persistent storage, and control flow. Manages parallel execution,
+    error handling.

-    Tool calls can also be passed directly as a list of `ToolCall` dicts.
+    Input Formats:
+        1. Graph state with `messages` key that has a list of messages:
+           - Common representation for agentic workflows
+           - Supports custom messages key via ``messages_key`` parameter
+
+        2. **Message List**: ``[AIMessage(..., tool_calls=[...])]``
+           - List of messages with tool calls in the last AIMessage
+
+        3. **Direct Tool Calls**: ``[{"name": "tool", "args": {...}, "id": "1", "type": "tool_call"}]``
+           - Bypasses message parsing for direct tool execution
+           - For programmatic tool invocation and testing
+
+    Tool Types:
+        1. **Regular tools**: Functions or BaseTool instances that return values or
+            Commands.
+        2. **Structured output tools**: Pydantic model classes for schema-validated
+           responses
+
+    Output Formats:
+        Output format depends on input type and tool behavior:
+
+        **For Regular tools**:
+        - Dict input → ``{"messages": [ToolMessage(...)]}``
+        - List input → ``[ToolMessage(...)]``
+
+        **For Command tools**:
+        - Returns ``[Command(...)]`` or mixed list with regular tool outputs
+        - Commands can update state, trigger navigation, or send messages
+
+        **For Structured output tools**:
+        - Returns ``[Command(update={"messages": [...], "structured_response": schema_instance})]``
+        - Includes both message and structured data in the graph state

    Args:
-        tools: A sequence of tools that can be invoked by this node. Tools can be
-            BaseTool instances or plain functions that will be converted to tools.
+        tools: A sequence of tools that can be invoked by this node. Supports:
+            - **BaseTool instances**: Tools with schemas and metadata
+            - **Plain functions**: Automatically converted to tools with inferred schemas
+            - **Pydantic model classes**: Treated as structured output tools
        name: The name identifier for this node in the graph. Used for debugging
            and visualization. Defaults to "tools".
        tags: Optional metadata tags to associate with the node for filtering
@@ -256,21 +290,24 @@ class ToolNode(RunnableCallable):
        handle_tool_errors: Configuration for error handling during tool execution.
            Defaults to True. Supports multiple strategies:

-            - True: Catch all errors and return a ToolMessage with the default
+            - **True**: Catch all errors and return a ToolMessage with the default
              error template containing the exception details.
-            - str: Catch all errors and return a ToolMessage with this custom
+            - **str**: Catch all errors and return a ToolMessage with this custom
              error message string.
-            - tuple[type[Exception], ...]: Only catch exceptions of the specified
+            - **tuple[type[Exception], ...]**: Only catch exceptions with the specified
              types and return default error messages for them.
-            - Callable[..., str]: Catch exceptions matching the callable's signature
+            - **Callable[..., str]**: Catch exceptions matching the callable's signature
              and return the string result of calling it with the exception.
-            - False: Disable error handling entirely, allowing exceptions to propagate.
+            - **False**: Disable error handling entirely, allowing exceptions to
+              propagate.

        messages_key: The key in the state dictionary that contains the message list.
-            This same key will be used for the output ToolMessages. Defaults to "messages".
+            This same key will be used for the output ToolMessages.
+            Defaults to "messages".
+            Allows custom state schemas with different message field names.

-    Example:
-        Basic usage with simple tools:
+    Examples:
+        Basic usage:

        ```python
        from langgraph.prebuilt import ToolNode
@@ -284,42 +321,35 @@ class ToolNode(RunnableCallable):
        tool_node = ToolNode([calculator])
        ```

-        Custom error handling:
+        State injection:

        ```python
-        def handle_math_errors(e: ZeroDivisionError) -> str:
-            return "Cannot divide by zero!"
+        from typing_extensions import Annotated
+        from langgraph.prebuilt import InjectedState

-        tool_node = ToolNode([calculator], handle_tool_errors=handle_math_errors)
+        @tool
+        def context_tool(query: str, state: Annotated[dict, InjectedState]) -> str:
+            \"\"\"Some tool that uses state.\"\"\"
+            return f"Query: {query}, Messages: {len(state['messages'])}"
+
+        tool_node = ToolNode([context_tool])
        ```

-        Direct tool call execution:
+        Error handling:

        ```python
-        tool_calls = [{"name": "calculator", "args": {"a": 5, "b": 3}, "id": "1", "type": "tool_call"}]
-        result = tool_node.invoke(tool_calls)
+        def handle_errors(e: ValueError) -> str:
+            return "Invalid input provided"
+
+        tool_node = ToolNode([my_tool], handle_tool_errors=handle_errors)
        ```
-
-    Note:
-        The ToolNode expects input in one of three formats:
-        1. A dictionary with a messages key containing a list of messages
-        2. A list of messages directly
-        3. A list of tool call dictionaries
-
-        When using message formats, the last message must be an AIMessage with
-        tool_calls populated. The node automatically extracts and processes these
-        tool calls concurrently.
-
-        For advanced use cases involving state injection or store access, tools
-        can be annotated with InjectedState or InjectedStore to receive graph
-        context automatically.
    """

-    name: str = "ToolNode"
+    name: str = "tools"

    def __init__(
        self,
-        tools: Sequence[Union[BaseTool, Callable]],
+        tools: Sequence[Union[BaseTool, BaseModel, Callable]],
        *,
        name: str = "tools",
        tags: Optional[list[str]] = None,
@@ -338,17 +368,36 @@ class ToolNode(RunnableCallable):
            messages_key: State key containing messages.
        """
        super().__init__(self._func, self._afunc, name=name, tags=tags, trace=False)
-        self.tools_by_name: dict[str, BaseTool] = {}
-        self.tool_to_state_args: dict[str, dict[str, Optional[str]]] = {}
-        self.tool_to_store_arg: dict[str, Optional[str]] = {}
-        self.handle_tool_errors = handle_tool_errors
-        self.messages_key = messages_key
-        for tool_ in tools:
-            if not isinstance(tool_, BaseTool):
-                tool_ = create_tool(tool_)
-            self.tools_by_name[tool_.name] = tool_
-            self.tool_to_state_args[tool_.name] = _get_state_args(tool_)
-            self.tool_to_store_arg[tool_.name] = _get_store_arg(tool_)
+        self._tools_by_name: dict[str, BaseTool] = {}
+        self._structured_output_tools_by_name: dict[str, type[BaseModel]] = {}
+        self._tool_to_state_args: dict[str, dict[str, Optional[str]]] = {}
+        self._tool_to_store_arg: dict[str, Optional[str]] = {}
+        self._handle_tool_errors = handle_tool_errors
+        self._messages_key = messages_key
+        for tool in tools:
+            if inspect.isclass(tool) and issubclass(tool, BaseModel):
+                # Handle Pydantic model classes as structured output tools
+                self._structured_output_tools_by_name[tool.__name__] = tool
+                self._tool_to_state_args[tool.__name__] = {}
+                self._tool_to_store_arg[tool.__name__] = None
+            else:
+                if not isinstance(tool, BaseTool):
+                    tool_ = create_tool(cast(Type[BaseTool], tool))
+                else:
+                    tool_ = tool
+                self._tools_by_name[tool_.name] = tool_
+                self._tool_to_state_args[tool_.name] = _get_state_args(tool_)
+                self._tool_to_store_arg[tool_.name] = _get_store_arg(tool_)
+
+    @property
+    def tools_by_name(self) -> dict[str, BaseTool]:
+        """Mapping from tool name to BaseTool instance."""
+        return self._tools_by_name
+
+    @property
+    def structured_output_tools(self) -> dict[str, type[BaseModel]]:
+        """Mapping from structured output tool name to Pydantic model class."""
+        return self._structured_output_tools_by_name

    def _func(
        self,
@@ -361,8 +410,7 @@ class ToolNode(RunnableCallable):
        *,
        store: Optional[BaseStore],
    ) -> Any:
-        tool_calls, input_type = self._parse_input(input)
-        tool_calls = [self.inject_tool_args(call, input, store) for call in tool_calls]
+        tool_calls, input_type = self._parse_input(input, store)
        config_list = get_config_list(config, len(tool_calls))
        input_types = [input_type] * len(tool_calls)
        with get_executor_for_config(config) as executor:
@@ -383,8 +431,7 @@ class ToolNode(RunnableCallable):
        *,
        store: Optional[BaseStore],
    ) -> Any:
-        tool_calls, input_type = self._parse_input(input)
-        tool_calls = [self.inject_tool_args(call, input, store) for call in tool_calls]
+        tool_calls, input_type = self._parse_input(input, store)
        outputs = await asyncio.gather(
            *(self._arun_one(call, input_type, config) for call in tool_calls)
        )
@@ -393,14 +440,14 @@ class ToolNode(RunnableCallable):

    def _combine_tool_outputs(
        self,
-        outputs: list[ToolMessage],
+        outputs: list[Union[ToolMessage, Command]],
        input_type: Literal["list", "dict", "tool_calls"],
    ) -> list[Union[Command, list[ToolMessage], dict[str, list[ToolMessage]]]]:
        # preserve existing behavior for non-command tool outputs for backwards
        # compatibility
        if not any(isinstance(output, Command) for output in outputs):
            # TypedDict, pydantic, dataclass, etc. should all be able to load from dict
-            return outputs if input_type == "list" else {self.messages_key: outputs}
+            return outputs if input_type == "list" else {self._messages_key: outputs}

        # LangGraph will automatically handle list of Command and non-command node
        # updates
@@ -428,7 +475,7 @@ class ToolNode(RunnableCallable):
                    combined_outputs.append(output)
            else:
                combined_outputs.append(
-                    [output] if input_type == "list" else {self.messages_key: [output]}
+                    [output] if input_type == "list" else {self._messages_key: [output]}
                )

        if parent_command:
@@ -440,13 +487,31 @@ class ToolNode(RunnableCallable):
        call: ToolCall,
        input_type: Literal["list", "dict", "tool_calls"],
        config: RunnableConfig,
-    ) -> ToolMessage:
+    ) -> Union[ToolMessage, Command]:
        """Run a single tool call synchronously."""
        if invalid_tool_message := self._validate_tool_call(call):
            return invalid_tool_message
+
+        # Handle structured output tools
+        if call["name"] in self.structured_output_tools:
+            response_schema = self._structured_output_tools_by_name[call["name"]]
+            return Command(
+                update={
+                    "messages": [
+                        ToolMessage(
+                            content="ok!",
+                            name=call["name"],
+                            tool_call_id=call["id"],
+                        )
+                    ],
+                    "structured_response": response_schema(**call["args"]),
+                }
+            )
+
        try:
            call_args = {**call, **{"type": "tool_call"}}
-            response = self.tools_by_name[call["name"]].invoke(call_args, config)
+            tool = self.tools_by_name[call["name"]]
+            response = tool.invoke(call_args, config)

        # GraphInterrupt is a special exception that will always be raised.
        # It can be triggered in the following scenarios,
@@ -458,20 +523,20 @@ class ToolNode(RunnableCallable):
        except GraphBubbleUp as e:
            raise e
        except Exception as e:
-            if isinstance(self.handle_tool_errors, tuple):
-                handled_types: tuple = self.handle_tool_errors
-            elif callable(self.handle_tool_errors):
-                handled_types = _infer_handled_types(self.handle_tool_errors)
+            if isinstance(self._handle_tool_errors, tuple):
+                handled_types: tuple = self._handle_tool_errors
+            elif callable(self._handle_tool_errors):
+                handled_types = _infer_handled_types(self._handle_tool_errors)
            else:
                # default behavior is catching all exceptions
                handled_types = (Exception,)

            # Unhandled
-            if not self.handle_tool_errors or not isinstance(e, handled_types):
+            if not self._handle_tool_errors or not isinstance(e, handled_types):
                raise e
            # Handled
            else:
-                content = _handle_tool_error(e, flag=self.handle_tool_errors)
+                content = _handle_tool_error(e, flag=self._handle_tool_errors)
            return ToolMessage(
                content=content,
                name=call["name"],
@@ -496,38 +561,55 @@ class ToolNode(RunnableCallable):
        call: ToolCall,
        input_type: Literal["list", "dict", "tool_calls"],
        config: RunnableConfig,
-    ) -> ToolMessage:
+    ) -> Union[ToolMessage, Command]:
        """Run a single tool call asynchronously."""
        if invalid_tool_message := self._validate_tool_call(call):
            return invalid_tool_message

-        try:
-            input = {**call, **{"type": "tool_call"}}
-            response = await self.tools_by_name[call["name"]].ainvoke(input, config)
+        # Handle structured output tools
+        if call["name"] in self.structured_output_tools:
+            response_schema = self._structured_output_tools_by_name[call["name"]]
+            return Command(
+                update={
+                    "messages": [
+                        ToolMessage(
+                            content="ok!",
+                            name=call["name"],
+                            tool_call_id=call["id"],
+                        )
+                    ],
+                    "structured_response": response_schema(**call["args"]),
+                }
+            )

+        try:
+            call_args = {**call, **{"type": "tool_call"}}
+            tool = self.tools_by_name[call["name"]]
+            response = await tool.ainvoke(call_args, config)
        # GraphInterrupt is a special exception that will always be raised.
-        # It can be triggered in the following scenarios:
-        # (1) a NodeInterrupt is raised inside a tool
-        # (2) a NodeInterrupt is raised inside a graph node for a graph called as a tool
+        # It can be triggered in the following scenarios,
+        # Where GraphInterrupt(GraphBubbleUp) is raised from an `interrupt` invocation most commonly:
+        # (1) a GraphInterrupt is raised inside a tool
+        # (2) a GraphInterrupt is raised inside a graph node for a graph called as a tool
        # (3) a GraphInterrupt is raised when a subgraph is interrupted inside a graph called as a tool
        # (2 and 3 can happen in a "supervisor w/ tools" multi-agent architecture)
        except GraphBubbleUp as e:
            raise e
        except Exception as e:
-            if isinstance(self.handle_tool_errors, tuple):
-                handled_types: tuple = self.handle_tool_errors
-            elif callable(self.handle_tool_errors):
-                handled_types = _infer_handled_types(self.handle_tool_errors)
+            if isinstance(self._handle_tool_errors, tuple):
+                handled_types: tuple = self._handle_tool_errors
+            elif callable(self._handle_tool_errors):
+                handled_types = _infer_handled_types(self._handle_tool_errors)
            else:
                # default behavior is catching all exceptions
                handled_types = (Exception,)

            # Unhandled
-            if not self.handle_tool_errors or not isinstance(e, handled_types):
+            if not self._handle_tool_errors or not isinstance(e, handled_types):
                raise e
            # Handled
            else:
-                content = _handle_tool_error(e, flag=self.handle_tool_errors)
+                content = _handle_tool_error(e, flag=self._handle_tool_errors)

            return ToolMessage(
                content=content,
@@ -555,6 +637,7 @@ class ToolNode(RunnableCallable):
            dict[str, Any],
            BaseModel,
        ],
+        store: Optional[BaseStore],
    ) -> Tuple[list[ToolCall], Literal["list", "dict", "tool_calls"]]:
        input_type: Literal["list", "dict", "tool_calls"]
        if isinstance(input, list):
@@ -565,18 +648,11 @@ class ToolNode(RunnableCallable):
            else:
                input_type = "list"
                messages = input
-        elif (
-            isinstance(input, dict) and input.get("__type") == "tool_call_with_context"
+        elif isinstance(input, dict) and (
+            messages := input.get(self._messages_key, [])
        ):
-            # mypy will not be able to type narrow correctly since the signature
-            # for input contains dict[str, Any]. We'd need to type dict[str, Any]
-            # before we can apply correct typing.
-            input = cast(ToolCallWithContext, input)  # type: ignore[assignment]
-            input_type = "tool_calls"
-            return [input["tool_call"]], input_type
-        elif isinstance(input, dict) and (messages := input.get(self.messages_key, [])):
            input_type = "dict"
-        elif messages := getattr(input, self.messages_key, []):
+        elif messages := getattr(input, self._messages_key, []):
            # Assume dataclass-like state that can coerce from dict
            input_type = "dict"
        else:
@@ -589,14 +665,24 @@ class ToolNode(RunnableCallable):
        except StopIteration:
            raise ValueError("No AIMessage found in input")

-        tool_calls = [call for call in latest_ai_message.tool_calls]
+        tool_calls = [
+            self.inject_tool_args(call, input, store)
+            for call in latest_ai_message.tool_calls
+        ]
        return tool_calls, input_type

    def _validate_tool_call(self, call: ToolCall) -> Optional[ToolMessage]:
-        if (requested_tool := call["name"]) not in self.tools_by_name:
+        requested_tool = call["name"]
+        if (
+            requested_tool not in self.tools_by_name
+            and requested_tool not in self._structured_output_tools_by_name
+        ):
+            all_tool_names = list(self.tools_by_name.keys()) + list(
+                self._structured_output_tools_by_name.keys()
+            )
            content = INVALID_TOOL_NAME_ERROR_TEMPLATE.format(
                requested_tool=requested_tool,
-                available_tools=", ".join(self.tools_by_name.keys()),
+                available_tools=", ".join(all_tool_names),
            )
            return ToolMessage(
                content, name=requested_tool, tool_call_id=call["id"], status="error"
@@ -613,15 +699,15 @@ class ToolNode(RunnableCallable):
            BaseModel,
        ],
    ) -> ToolCall:
-        state_args = self.tool_to_state_args[tool_call["name"]]
+        state_args = self._tool_to_state_args[tool_call["name"]]
        if state_args and isinstance(input, list):
            required_fields = list(state_args.values())
            if (
                len(required_fields) == 1
-                and required_fields[0] == self.messages_key
+                and required_fields[0] == self._messages_key
                or required_fields[0] is None
            ):
-                input = {self.messages_key: input}
+                input = {self._messages_key: input}
            else:
                err_msg = (
                    f"Invalid input to ToolNode. Tool {tool_call['name']} requires "
@@ -632,19 +718,14 @@ class ToolNode(RunnableCallable):
                    err_msg += f" State should contain fields {required_fields_str}."
                raise ValueError(err_msg)

-        if isinstance(input, dict) and input.get("__type") == "tool_call_with_context":
-            state = input["state"]
-        else:
-            state = input
-
-        if isinstance(state, dict):
+        if isinstance(input, dict):
            tool_state_args = {
-                tool_arg: state[state_field] if state_field else state
+                tool_arg: input[state_field] if state_field else input
                for tool_arg, state_field in state_args.items()
            }
        else:
            tool_state_args = {
-                tool_arg: getattr(state, state_field) if state_field else state
+                tool_arg: getattr(input, state_field) if state_field else input
                for tool_arg, state_field in state_args.items()
            }

@@ -657,7 +738,7 @@ class ToolNode(RunnableCallable):
    def _inject_store(
        self, tool_call: ToolCall, store: Optional[BaseStore]
    ) -> ToolCall:
-        store_arg = self.tool_to_store_arg[tool_call["name"]]
+        store_arg = self._tool_to_store_arg[tool_call["name"]]
        if not store_arg:
            return tool_call

@@ -716,7 +797,10 @@ class ToolNode(RunnableCallable):
            The injection is performed on a copy of the tool call to avoid mutating
            the original.
        """
-        if tool_call["name"] not in self.tools_by_name:
+        if (
+            tool_call["name"] not in self.tools_by_name
+            and tool_call["name"] not in self._structured_output_tools_by_name
+        ):
            return tool_call

        tool_call_copy: ToolCall = copy(tool_call)
@@ -734,15 +818,15 @@ class ToolNode(RunnableCallable):
            # input type is dict when ToolNode is invoked with a dict input (e.g. {"messages": [AIMessage(..., tool_calls=[...])]})
            if input_type not in ("dict", "tool_calls"):
                raise ValueError(
-                    f"Tools can provide a dict in Command.update only when using dict with '{self.messages_key}' key as ToolNode input, "
+                    f"Tools can provide a dict in Command.update only when using dict with '{self._messages_key}' key as ToolNode input, "
                    f"got: {command.update} for tool '{call['name']}'"
                )

            updated_command = deepcopy(command)
            state_update = cast(dict[str, Any], updated_command.update) or {}
-            messages_update = state_update.get(self.messages_key, [])
+            messages_update = state_update.get(self._messages_key, [])
        elif isinstance(command.update, list):
-            # input type is list when ToolNode is invoked with a list input (e.g. [AIMessage(..., tool_calls=[...])])
+            # Input type is list when ToolNode is invoked with a list input (e.g. [AIMessage(..., tool_calls=[...])])
            if input_type != "list":
                raise ValueError(
                    f"Tools can provide a list of messages in Command.update only when using list of messages as ToolNode input, "
@@ -802,7 +886,6 @@ def tools_condition(

    Args:
        state: The current graph state to examine for tool calls. Supported formats:
-            - List of messages (for MessageGraph)
            - Dictionary containing a messages key (for StateGraph)
            - BaseModel instance with a messages attribute
        messages_key: The key or attribute name containing the message list in the state.
@@ -2,8 +2,7 @@
 in a langchain graph. It applies a pydantic schema to tool_calls in the models' outputs,
 and returns a ToolMessage with the validated content. If the schema is not valid, it
 returns a ToolMessage with the error message. The ValidationNode can be used in a
-StateGraph with a "messages" key or in a MessageGraph. If multiple tool calls are
-requested, they will be run in parallel.
+StateGraph with a "messages" key. If multiple tool calls are requested, they will be run in parallel.
 """

 from typing import (
@@ -49,7 +48,7 @@ def _default_format_error(
 class ValidationNode(RunnableCallable):
    """A node that validates all tools requests from the last AIMessage.

-    It can be used either in StateGraph with a "messages" key or in MessageGraph.
+    It can be used either in StateGraph with a "messages" key.

    !!! note

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"

 [project]
 name = "langgraph-prebuilt"
-version = "0.6.2"
+version = "0.6.4"
 description = "Library with high-level APIs for creating and executing LangGraph agents and tools."
 authors = []
 requires-python = ">=3.9"
@@ -171,3 +171,191 @@
  
  '''
 # ---
+# name: test_react_agent_graph_structure_with_individual_nodes[no_response_format-no_post_hook-no_pre_hook-no_tools]
+  '''
+  graph TD;
+  	__start__ --> agent;
+  	agent --> __end__;
+  
+  '''
+# ---
+# name: test_react_agent_graph_structure_with_individual_nodes[no_response_format-no_post_hook-no_pre_hook-two_tools]
+  '''
+  graph TD;
+  	__start__ --> agent;
+  	agent -.-> __end__;
+  	agent -.-> tool;
+  	agent -.-> tool2;
+  	tool --> agent;
+  	tool2 --> agent;
+  
+  '''
+# ---
+# name: test_react_agent_graph_structure_with_individual_nodes[no_response_format-no_post_hook-with_pre_hook-no_tools]
+  '''
+  graph TD;
+  	__start__ --> pre_model_hook;
+  	pre_model_hook --> agent;
+  	agent --> __end__;
+  
+  '''
+# ---
+# name: test_react_agent_graph_structure_with_individual_nodes[no_response_format-no_post_hook-with_pre_hook-two_tools]
+  '''
+  graph TD;
+  	__start__ --> pre_model_hook;
+  	agent -.-> __end__;
+  	agent -.-> tool;
+  	agent -.-> tool2;
+  	pre_model_hook --> agent;
+  	tool --> pre_model_hook;
+  	tool2 --> pre_model_hook;
+  
+  '''
+# ---
+# name: test_react_agent_graph_structure_with_individual_nodes[no_response_format-with_post_hook-no_pre_hook-no_tools]
+  '''
+  graph TD;
+  	__start__ --> agent;
+  	agent --> post_model_hook;
+  	post_model_hook --> __end__;
+  
+  '''
+# ---
+# name: test_react_agent_graph_structure_with_individual_nodes[no_response_format-with_post_hook-no_pre_hook-two_tools]
+  '''
+  graph TD;
+  	__start__ --> agent;
+  	agent --> post_model_hook;
+  	post_model_hook -.-> __end__;
+  	post_model_hook -.-> agent;
+  	post_model_hook -.-> tool;
+  	post_model_hook -.-> tool2;
+  	tool --> agent;
+  	tool2 --> agent;
+  
+  '''
+# ---
+# name: test_react_agent_graph_structure_with_individual_nodes[no_response_format-with_post_hook-with_pre_hook-no_tools]
+  '''
+  graph TD;
+  	__start__ --> pre_model_hook;
+  	agent --> post_model_hook;
+  	pre_model_hook --> agent;
+  	post_model_hook --> __end__;
+  
+  '''
+# ---
+# name: test_react_agent_graph_structure_with_individual_nodes[no_response_format-with_post_hook-with_pre_hook-two_tools]
+  '''
+  graph TD;
+  	__start__ --> pre_model_hook;
+  	agent --> post_model_hook;
+  	post_model_hook -.-> __end__;
+  	post_model_hook -.-> pre_model_hook;
+  	post_model_hook -.-> tool;
+  	post_model_hook -.-> tool2;
+  	pre_model_hook --> agent;
+  	tool --> pre_model_hook;
+  	tool2 --> pre_model_hook;
+  
+  '''
+# ---
+# name: test_react_agent_graph_structure_with_individual_nodes[with_response_format-no_post_hook-no_pre_hook-no_tools]
+  '''
+  graph TD;
+  	__start__ --> agent;
+  	agent --> generate_structured_response;
+  	generate_structured_response --> __end__;
+  
+  '''
+# ---
+# name: test_react_agent_graph_structure_with_individual_nodes[with_response_format-no_post_hook-no_pre_hook-two_tools]
+  '''
+  graph TD;
+  	__start__ --> agent;
+  	agent -.-> generate_structured_response;
+  	agent -.-> tool;
+  	agent -.-> tool2;
+  	tool --> agent;
+  	tool2 --> agent;
+  	generate_structured_response --> __end__;
+  
+  '''
+# ---
+# name: test_react_agent_graph_structure_with_individual_nodes[with_response_format-no_post_hook-with_pre_hook-no_tools]
+  '''
+  graph TD;
+  	__start__ --> pre_model_hook;
+  	agent --> generate_structured_response;
+  	pre_model_hook --> agent;
+  	generate_structured_response --> __end__;
+  
+  '''
+# ---
+# name: test_react_agent_graph_structure_with_individual_nodes[with_response_format-no_post_hook-with_pre_hook-two_tools]
+  '''
+  graph TD;
+  	__start__ --> pre_model_hook;
+  	agent -.-> generate_structured_response;
+  	agent -.-> tool;
+  	agent -.-> tool2;
+  	pre_model_hook --> agent;
+  	tool --> pre_model_hook;
+  	tool2 --> pre_model_hook;
+  	generate_structured_response --> __end__;
+  
+  '''
+# ---
+# name: test_react_agent_graph_structure_with_individual_nodes[with_response_format-with_post_hook-no_pre_hook-no_tools]
+  '''
+  graph TD;
+  	__start__ --> agent;
+  	agent --> post_model_hook;
+  	post_model_hook --> generate_structured_response;
+  	generate_structured_response --> __end__;
+  
+  '''
+# ---
+# name: test_react_agent_graph_structure_with_individual_nodes[with_response_format-with_post_hook-no_pre_hook-two_tools]
+  '''
+  graph TD;
+  	__start__ --> agent;
+  	agent --> post_model_hook;
+  	post_model_hook -.-> agent;
+  	post_model_hook -.-> generate_structured_response;
+  	post_model_hook -.-> tool;
+  	post_model_hook -.-> tool2;
+  	tool --> agent;
+  	tool2 --> agent;
+  	generate_structured_response --> __end__;
+  
+  '''
+# ---
+# name: test_react_agent_graph_structure_with_individual_nodes[with_response_format-with_post_hook-with_pre_hook-no_tools]
+  '''
+  graph TD;
+  	__start__ --> pre_model_hook;
+  	agent --> post_model_hook;
+  	post_model_hook --> generate_structured_response;
+  	pre_model_hook --> agent;
+  	generate_structured_response --> __end__;
+  
+  '''
+# ---
+# name: test_react_agent_graph_structure_with_individual_nodes[with_response_format-with_post_hook-with_pre_hook-two_tools]
+  '''
+  graph TD;
+  	__start__ --> pre_model_hook;
+  	agent --> post_model_hook;
+  	post_model_hook -.-> generate_structured_response;
+  	post_model_hook -.-> pre_model_hook;
+  	post_model_hook -.-> tool;
+  	post_model_hook -.-> tool2;
+  	pre_model_hook --> agent;
+  	tool --> pre_model_hook;
+  	tool2 --> pre_model_hook;
+  	generate_structured_response --> __end__;
+  
+  '''
+# ---
@@ -0,0 +1,16 @@
+name: langgraph-tests-redis
+services:
+  redis-test:
+    image: redis:7-alpine
+    ports:
+      - "6379:6379"
+    command: redis-server --maxmemory 256mb --maxmemory-policy allkeys-lru
+    healthcheck:
+      test: redis-cli ping
+      start_period: 10s
+      timeout: 1s
+      retries: 5
+      interval: 5s
+      start_interval: 1s
+    tmpfs:
+      - /data  # Use tmpfs for faster testing
@@ -31,3 +31,11 @@ def test_config_schema_deprecation() -> None:
        match="`get_config_jsonschema` is deprecated. Use `get_context_jsonschema` instead.",
    ):
        assert agent.get_config_jsonschema() is not None
+
+
+def test_extra_kwargs_deprecation() -> None:
+    with pytest.raises(
+        TypeError,
+        match="create_react_agent\(\) got unexpected keyword arguments: \{'extra': 'extra'\}",
+    ):
+        create_react_agent(FakeToolCallingModel(), [], extra="extra")
@@ -1,14 +1,9 @@
 import dataclasses
 import inspect
-import json
-from functools import partial
 from typing import (
    Annotated,
-    List,
    Literal,
    Optional,
-    Type,
-    TypeVar,
    Union,
 )

@@ -16,7 +11,6 @@ import pytest
 from langchain_core.language_models import BaseChatModel
 from langchain_core.messages import (
    AIMessage,
-    AnyMessage,
    HumanMessage,
    MessageLikeRepresentation,
    RemoveMessage,
@@ -24,21 +18,18 @@ from langchain_core.messages import (
    ToolCall,
    ToolMessage,
 )
-from langchain_core.runnables import RunnableLambda
+from langchain_core.runnables import RunnableConfig, RunnableLambda
 from langchain_core.tools import InjectedToolCallId, ToolException
 from langchain_core.tools import tool as dec_tool
 from pydantic import BaseModel, Field
-from pydantic.v1 import BaseModel as BaseModelV1
 from typing_extensions import TypedDict

 from langgraph.checkpoint.base import BaseCheckpointSaver
-from langgraph.config import get_stream_writer
-from langgraph.graph import START, MessagesState, StateGraph, add_messages
+from langgraph.graph import START, MessagesState, StateGraph
 from langgraph.graph.message import REMOVE_ALL_MESSAGES
 from langgraph.prebuilt import (
    ToolNode,
    create_react_agent,
-    tools_condition,
 )
 from langgraph.prebuilt.chat_agent_executor import (
    AgentState,
@@ -184,7 +175,7 @@ def test_runnable_prompt():


@pytest.mark.parametrize("version", REACT_TOOL_CALL_VERSIONS)
-def test_prompt_with_store(version: str):
+def test_prompt_with_store(version: Literal["v1", "v2"]):
    def add(a: int, b: int):
        """Adds a and b"""
        return a + b
@@ -654,124 +645,6 @@ def test_react_agent_parallel_tool_calls(
        assert get_weather_execution_count == 1


-class _InjectStateSchema(TypedDict):
-    messages: list
-    foo: str
-
-
-class _InjectedStatePydanticSchema(BaseModelV1):
-    messages: list
-    foo: str
-
-
-class _InjectedStatePydanticV2Schema(BaseModel):
-    messages: list
-    foo: str
-
-
-@dataclasses.dataclass
-class _InjectedStateDataclassSchema:
-    messages: list
-    foo: str
-
-
-T = TypeVar("T")
-
-
-@pytest.mark.parametrize(
-    "schema_",
-    [
-        _InjectStateSchema,
-        _InjectedStatePydanticSchema,
-        _InjectedStatePydanticV2Schema,
-        _InjectedStateDataclassSchema,
-    ],
-)
-def test_tool_node_inject_state(schema_: Type[T]) -> None:
-    def tool1(some_val: int, state: Annotated[T, InjectedState]) -> str:
-        """Tool 1 docstring."""
-        if isinstance(state, dict):
-            return state["foo"]
-        else:
-            return getattr(state, "foo")
-
-    def tool2(some_val: int, state: Annotated[T, InjectedState()]) -> str:
-        """Tool 2 docstring."""
-        if isinstance(state, dict):
-            return state["foo"]
-        else:
-            return getattr(state, "foo")
-
-    def tool3(
-        some_val: int,
-        foo: Annotated[str, InjectedState("foo")],
-        msgs: Annotated[List[AnyMessage], InjectedState("messages")],
-    ) -> str:
-        """Tool 1 docstring."""
-        return foo
-
-    def tool4(
-        some_val: int, msgs: Annotated[List[AnyMessage], InjectedState("messages")]
-    ) -> str:
-        """Tool 1 docstring."""
-        return msgs[0].content
-
-    node = ToolNode([tool1, tool2, tool3, tool4])
-    for tool_name in ("tool1", "tool2", "tool3"):
-        tool_call = {
-            "name": tool_name,
-            "args": {"some_val": 1},
-            "id": "some 0",
-            "type": "tool_call",
-        }
-        msg = AIMessage("hi?", tool_calls=[tool_call])
-        result = node.invoke(schema_(**{"messages": [msg], "foo": "bar"}))
-        tool_message = result["messages"][-1]
-        assert tool_message.content == "bar", f"Failed for tool={tool_name}"
-
-        if tool_name == "tool3":
-            failure_input = None
-            try:
-                failure_input = schema_(**{"messages": [msg], "notfoo": "bar"})
-            except Exception:
-                pass
-            if failure_input is not None:
-                with pytest.raises(KeyError):
-                    node.invoke(failure_input)
-
-                with pytest.raises(ValueError):
-                    node.invoke([msg])
-        else:
-            failure_input = None
-            try:
-                failure_input = schema_(**{"messages": [msg], "notfoo": "bar"})
-            except Exception:
-                # We'd get a validation error from pydantic state and wouldn't make it to the node
-                # anyway
-                pass
-            if failure_input is not None:
-                messages_ = node.invoke(failure_input)
-                tool_message = messages_["messages"][-1]
-                assert "KeyError" in tool_message.content
-                tool_message = node.invoke([msg])[-1]
-                assert "KeyError" in tool_message.content
-
-    tool_call = {
-        "name": "tool4",
-        "args": {"some_val": 1},
-        "id": "some 0",
-        "type": "tool_call",
-    }
-    msg = AIMessage("hi?", tool_calls=[tool_call])
-    result = node.invoke(schema_(**{"messages": [msg], "foo": ""}))
-    tool_message = result["messages"][-1]
-    assert tool_message.content == "hi?"
-
-    result = node.invoke([msg])
-    tool_message = result[-1]
-    assert tool_message.content == "hi?"
-
-
 class AgentStateExtraKey(AgentState):
    foo: int

@@ -780,14 +653,24 @@ class AgentStateExtraKeyPydantic(AgentStatePydantic):
    foo: int


-@pytest.mark.parametrize("version", REACT_TOOL_CALL_VERSIONS)
+@pytest.mark.parametrize("version", ["v1", "v2"])
@pytest.mark.parametrize(
    "state_schema", [AgentStateExtraKey, AgentStateExtraKeyPydantic]
 )
+@pytest.mark.parametrize(
+    "use_individual_tool_nodes",
+    [False, True],
+    ids=["single_tool_node", "node_per_tool"],
+)
 def test_create_react_agent_inject_vars(
-    version: Literal["v1", "v2"], state_schema: StateSchemaType
+    version: Literal["v1", "v2"],
+    state_schema: StateSchemaType,
+    use_individual_tool_nodes: bool,
 ) -> None:
    """Test that the agent can inject state and store into tool functions."""
+    if version == "v1" and use_individual_tool_nodes:
+        pytest.skip("v1 does not support individual tool nodes")
+
    store = InMemoryStore()
    namespace = ("test",)
    store.put(namespace, "test_key", {"bar": 3})
@@ -826,6 +709,7 @@ def test_create_react_agent_inject_vars(
        state_schema=state_schema,
        store=store,
        version=version,
+        use_individual_tool_nodes=use_individual_tool_nodes,
    )
    result = agent.invoke({"messages": [{"role": "user", "content": "hi"}], "foo": 2})
    assert result["messages"] == [
@@ -837,137 +721,18 @@ def test_create_react_agent_inject_vars(
    assert result["foo"] == 2


-def test_tool_node_inject_store() -> None:
-    store = InMemoryStore()
-    namespace = ("test",)
-
-    def tool1(some_val: int, store: Annotated[BaseStore, InjectedStore()]) -> str:
-        """Tool 1 docstring."""
-        store_val = store.get(namespace, "test_key").value["foo"]
-        return f"Some val: {some_val}, store val: {store_val}"
-
-    def tool2(some_val: int, store: Annotated[BaseStore, InjectedStore()]) -> str:
-        """Tool 2 docstring."""
-        store_val = store.get(namespace, "test_key").value["foo"]
-        return f"Some val: {some_val}, store val: {store_val}"
-
-    def tool3(
-        some_val: int,
-        bar: Annotated[str, InjectedState("bar")],
-        store: Annotated[BaseStore, InjectedStore()],
-    ) -> str:
-        """Tool 3 docstring."""
-        store_val = store.get(namespace, "test_key").value["foo"]
-        return f"Some val: {some_val}, store val: {store_val}, state val: {bar}"
-
-    node = ToolNode([tool1, tool2, tool3], handle_tool_errors=True)
-    store.put(namespace, "test_key", {"foo": "bar"})
-
-    class State(MessagesState):
-        bar: str
-
-    builder = StateGraph(State)
-    builder.add_node("tools", node)
-    builder.add_edge(START, "tools")
-    graph = builder.compile(store=store)
-
-    for tool_name in ("tool1", "tool2"):
-        tool_call = {
-            "name": tool_name,
-            "args": {"some_val": 1},
-            "id": "some 0",
-            "type": "tool_call",
-        }
-        msg = AIMessage("hi?", tool_calls=[tool_call])
-        node_result = node.invoke({"messages": [msg]}, store=store)
-        graph_result = graph.invoke({"messages": [msg]})
-        for result in (node_result, graph_result):
-            result["messages"][-1]
-            tool_message = result["messages"][-1]
-            assert tool_message.content == "Some val: 1, store val: bar", (
-                f"Failed for tool={tool_name}"
-            )
-
-    tool_call = {
-        "name": "tool3",
-        "args": {"some_val": 1},
-        "id": "some 0",
-        "type": "tool_call",
-    }
-    msg = AIMessage("hi?", tool_calls=[tool_call])
-    node_result = node.invoke({"messages": [msg], "bar": "baz"}, store=store)
-    graph_result = graph.invoke({"messages": [msg], "bar": "baz"})
-    for result in (node_result, graph_result):
-        result["messages"][-1]
-        tool_message = result["messages"][-1]
-        assert tool_message.content == "Some val: 1, store val: bar, state val: baz", (
-            f"Failed for tool={tool_name}"
-        )
-
-    # test injected store without passing store to compiled graph
-    failing_graph = builder.compile()
-    with pytest.raises(ValueError):
-        failing_graph.invoke({"messages": [msg], "bar": "baz"})
-
-
-def test_tool_node_ensure_utf8() -> None:
-    @dec_tool
-    def get_day_list(days: list[str]) -> list[str]:
-        """choose days"""
-        return days
-
-    data = ["星期一", "水曜日", "목요일", "Friday"]
-    tools = [get_day_list]
-    tool_calls = [ToolCall(name=get_day_list.name, args={"days": data}, id="test_id")]
-    outputs: list[ToolMessage] = ToolNode(tools).invoke(
-        [AIMessage(content="", tool_calls=tool_calls)]
-    )
-    assert outputs[0].content == json.dumps(data, ensure_ascii=False)
-
-
-def test_tool_node_messages_key() -> None:
-    @dec_tool
-    def add(a: int, b: int):
-        """Adds a and b."""
-        return a + b
-
-    model = FakeToolCallingModel(
-        tool_calls=[[ToolCall(name=add.name, args={"a": 1, "b": 2}, id="test_id")]]
-    )
-
-    class State(TypedDict):
-        subgraph_messages: Annotated[list[AnyMessage], add_messages]
-
-    def call_model(state: State):
-        response = model.invoke(state["subgraph_messages"])
-        model.tool_calls = []
-        return {"subgraph_messages": response}
-
-    builder = StateGraph(State)
-    builder.add_node("agent", call_model)
-    builder.add_node("tools", ToolNode([add], messages_key="subgraph_messages"))
-    builder.add_conditional_edges(
-        "agent", partial(tools_condition, messages_key="subgraph_messages")
-    )
-    builder.add_edge(START, "agent")
-    builder.add_edge("tools", "agent")
-
-    graph = builder.compile()
-    result = graph.invoke({"subgraph_messages": [HumanMessage(content="hi")]})
-    assert result["subgraph_messages"] == [
-        _AnyIdHumanMessage(content="hi"),
-        AIMessage(
-            content="hi",
-            id="0",
-            tool_calls=[ToolCall(name=add.name, args={"a": 1, "b": 2}, id="test_id")],
-        ),
-        _AnyIdToolMessage(content="3", name=add.name, tool_call_id="test_id"),
-        AIMessage(content="hi-hi-3", id="1"),
-    ]
-
-
@pytest.mark.parametrize("version", REACT_TOOL_CALL_VERSIONS)
-async def test_return_direct(version: str) -> None:
+@pytest.mark.parametrize(
+    "use_individual_tool_nodes",
+    [False, True],
+    ids=["single_tool_node", "node_per_tool"],
+)
+async def test_return_direct(
+    version: Literal["v1", "v2"], use_individual_tool_nodes: bool
+) -> None:
+    if version == "v1" and use_individual_tool_nodes:
+        pytest.skip("v1 does not support individual tool nodes")
+
    @dec_tool(return_direct=True)
    def tool_return_direct(input: str) -> str:
        """A tool that returns directly."""
@@ -995,6 +760,7 @@ async def test_return_direct(version: str) -> None:
        model,
        [tool_return_direct, tool_normal],
        version=version,
+        use_individual_tool_nodes=use_individual_tool_nodes,
    )

    # Test direct return for tool_return_direct
@@ -1088,15 +854,27 @@ def test__get_state_args() -> None:


 def test_inspect_react() -> None:
+    """Test that we can inspect the agent and its nodes."""
    model = FakeToolCallingModel(tool_calls=[])
    agent = create_react_agent(model, [])
    inspect.getclosurevars(agent.nodes["agent"].bound.func)


@pytest.mark.parametrize("version", REACT_TOOL_CALL_VERSIONS)
+@pytest.mark.parametrize(
+    "use_individual_tool_nodes",
+    [False, True],
+    ids=["single_tool_node", "node_per_tool"],
+)
 def test_react_with_subgraph_tools(
-    sync_checkpointer: BaseCheckpointSaver, version: Literal["v1", "v2"]
+    sync_checkpointer: BaseCheckpointSaver,
+    version: Literal["v1", "v2"],
+    use_individual_tool_nodes: bool,
 ) -> None:
+    """Test React agent with subgraph tools."""
+    if version == "v1" and use_individual_tool_nodes:
+        pytest.skip("v1 does not support individual tool nodes")
+
    class State(TypedDict):
        a: int
        b: int
@@ -1152,6 +930,7 @@ def test_react_with_subgraph_tools(
        tool_node,
        checkpointer=sync_checkpointer,
        version=version,
+        use_individual_tool_nodes=use_individual_tool_nodes,
    )
    result = agent.invoke(
        {"messages": [HumanMessage(content="What's 2 + 3 and 2 * 3?")]},
@@ -1182,58 +961,198 @@ def test_react_with_subgraph_tools(
    ]


-def test_tool_node_stream_writer() -> None:
+@pytest.mark.parametrize("version", REACT_TOOL_CALL_VERSIONS)
+@pytest.mark.parametrize(
+    "use_individual_tool_nodes",
+    [False, True],
+    ids=["single_tool_node", "node_per_tool"],
+)
+def test_react_agent_subgraph_streaming_sync(
+    version: Literal["v1", "v2"], use_individual_tool_nodes: bool
+) -> None:
+    """Test React agent streaming when used as a subgraph node sync version"""
+    if version == "v1" and use_individual_tool_nodes:
+        pytest.skip("v1 does not support individual tool nodes")
+
    @dec_tool
-    def streaming_tool(x: int) -> str:
-        """Do something with writer."""
-        my_writer = get_stream_writer()
-        for value in ["foo", "bar", "baz"]:
-            my_writer({"custom_tool_value": value})
+    def get_weather(city: str) -> str:
+        """Get the weather of a city."""
+        return f"The weather of {city} is sunny."

-        return x
-
-    tool_node = ToolNode([streaming_tool])
-    graph = (
-        StateGraph(MessagesState)
-        .add_node("tools", tool_node)
-        .add_edge(START, "tools")
-        .compile()
+    # Create a React agent
+    model = FakeToolCallingModel(
+        tool_calls=[
+            [{"args": {"city": "Tokyo"}, "id": "1", "name": "get_weather"}],
+            [],
+        ]
    )

-    tool_call = {
-        "name": "streaming_tool",
-        "args": {"x": 1},
-        "id": "1",
-        "type": "tool_call",
-    }
-    inputs = {
-        "messages": [AIMessage("", tool_calls=[tool_call])],
-    }
+    agent = create_react_agent(
+        model,
+        tools=[get_weather],
+        prompt="You are a helpful travel assistant.",
+        version=version,
+        use_individual_tool_nodes=use_individual_tool_nodes,
+    )

-    assert list(graph.stream(inputs, stream_mode="custom")) == [
-        {"custom_tool_value": "foo"},
-        {"custom_tool_value": "bar"},
-        {"custom_tool_value": "baz"},
-    ]
-    assert list(graph.stream(inputs, stream_mode=["custom", "updates"])) == [
-        ("custom", {"custom_tool_value": "foo"}),
-        ("custom", {"custom_tool_value": "bar"}),
-        ("custom", {"custom_tool_value": "baz"}),
-        (
-            "updates",
-            {
-                "tools": {
-                    "messages": [
-                        _AnyIdToolMessage(
-                            content="1",
-                            name="streaming_tool",
-                            tool_call_id="1",
-                        ),
-                    ],
-                },
-            },
-        ),
-    ]
+    # Create a subgraph that uses the React agent as a node
+    def react_agent_node(state: MessagesState, config: RunnableConfig) -> MessagesState:
+        """Node that runs the React agent and collects streaming output."""
+        collected_content = ""
+
+        # Stream the agent output and collect content
+        for msg_chunk, msg_metadata in agent.stream(
+            {"messages": [("user", state["messages"][-1].content)]},
+            config,
+            stream_mode="messages",
+        ):
+            if hasattr(msg_chunk, "content") and msg_chunk.content:
+                collected_content += msg_chunk.content
+
+        return {"messages": [("assistant", collected_content)]}
+
+    # Create the main workflow with the React agent as a subgraph node
+    workflow = StateGraph(MessagesState)
+    workflow.add_node("react_agent", react_agent_node)
+    workflow.add_edge(START, "react_agent")
+    workflow.add_edge("react_agent", "__end__")
+    compiled_workflow = workflow.compile()
+
+    # Test the streaming functionality
+    result = compiled_workflow.invoke(
+        {"messages": [("user", "What is the weather in Tokyo?")]}
+    )
+
+    # Verify the result contains expected structure
+    assert len(result["messages"]) == 2
+    assert result["messages"][0].content == "What is the weather in Tokyo?"
+    assert "assistant" in str(result["messages"][1])
+
+    # Test streaming with subgraphs = True
+    result = compiled_workflow.invoke(
+        {"messages": [("user", "What is the weather in Tokyo?")]},
+        subgraphs=True,
+    )
+    assert len(result["messages"]) == 2
+
+    events = []
+    for event in compiled_workflow.stream(
+        {"messages": [("user", "What is the weather in Tokyo?")]},
+        stream_mode="messages",
+        subgraphs=False,
+    ):
+        events.append(event)
+
+    assert len(events) == 0
+
+    events = []
+    for event in compiled_workflow.stream(
+        {"messages": [("user", "What is the weather in Tokyo?")]},
+        stream_mode="messages",
+        subgraphs=True,
+    ):
+        events.append(event)
+
+    assert len(events) == 3
+    namespace, (msg, metadata) = events[0]
+    # FakeToolCallingModel returns a single AIMessage with tool calls
+    # The content of the AIMessage reflects the input message
+    assert msg.content.startswith("You are a helpful travel assistant")
+    namespace, (msg, metadata) = events[1]  # ToolMessage
+    assert msg.content.startswith("The weather of Tokyo is sunny.")
+
+
+@pytest.mark.parametrize("version", REACT_TOOL_CALL_VERSIONS)
+async def test_react_agent_subgraph_streaming(version: Literal["v1", "v2"]) -> None:
+    """Test React agent streaming when used as a subgraph node."""
+
+    @dec_tool
+    def get_weather(city: str) -> str:
+        """Get the weather of a city."""
+        return f"The weather of {city} is sunny."
+
+    # Create a React agent
+    model = FakeToolCallingModel(
+        tool_calls=[
+            [{"args": {"city": "Tokyo"}, "id": "1", "name": "get_weather"}],
+            [],
+        ]
+    )
+
+    agent = create_react_agent(
+        model,
+        tools=[get_weather],
+        prompt="You are a helpful travel assistant.",
+        version=version,
+    )
+
+    # Create a subgraph that uses the React agent as a node
+    async def react_agent_node(
+        state: MessagesState, config: RunnableConfig
+    ) -> MessagesState:
+        """Node that runs the React agent and collects streaming output."""
+        collected_content = ""
+
+        # Stream the agent output and collect content
+        async for msg_chunk, msg_metadata in agent.astream(
+            {"messages": [("user", state["messages"][-1].content)]},
+            config,
+            stream_mode="messages",
+        ):
+            if hasattr(msg_chunk, "content") and msg_chunk.content:
+                collected_content += msg_chunk.content
+
+        return {"messages": [("assistant", collected_content)]}
+
+    # Create the main workflow with the React agent as a subgraph node
+    workflow = StateGraph(MessagesState)
+    workflow.add_node("react_agent", react_agent_node)
+    workflow.add_edge(START, "react_agent")
+    workflow.add_edge("react_agent", "__end__")
+    compiled_workflow = workflow.compile()
+
+    # Test the streaming functionality
+    result = await compiled_workflow.ainvoke(
+        {"messages": [("user", "What is the weather in Tokyo?")]}
+    )
+
+    # Verify the result contains expected structure
+    assert len(result["messages"]) == 2
+    assert result["messages"][0].content == "What is the weather in Tokyo?"
+    assert "assistant" in str(result["messages"][1])
+
+    # Test streaming with subgraphs = True
+    result = await compiled_workflow.ainvoke(
+        {"messages": [("user", "What is the weather in Tokyo?")]},
+        subgraphs=True,
+    )
+    assert len(result["messages"]) == 2
+
+    events = []
+    async for event in compiled_workflow.astream(
+        {"messages": [("user", "What is the weather in Tokyo?")]},
+        stream_mode="messages",
+        subgraphs=False,
+    ):
+        events.append(event)
+
+    assert len(events) == 0
+
+    events = []
+    async for event in compiled_workflow.astream(
+        {"messages": [("user", "What is the weather in Tokyo?")]},
+        stream_mode="messages",
+        subgraphs=True,
+    ):
+        events.append(event)
+
+    assert len(events) == 3
+    namespace, (msg, metadata) = events[0]
+    # FakeToolCallingModel returns a single AIMessage with tool calls
+    # The content of the AIMessage reflects the input message
+    assert msg.content.startswith("You are a helpful travel assistant")
+    namespace, (msg, metadata) = events[1]  # ToolMessage
+    assert msg.content.startswith("The weather of Tokyo is sunny.")


@pytest.mark.parametrize("version", REACT_TOOL_CALL_VERSIONS)
@@ -15,6 +15,11 @@ def tool() -> None:
    ...


+def tool2() -> None:
+    """Another testing tool."""
+    ...
+
+
 def pre_model_hook() -> None:
    """Pre-model hook."""
    ...
@@ -49,4 +54,44 @@ def test_react_agent_graph_structure(
        post_model_hook=post_model_hook,
        response_format=response_format,
    )
+    try:
+        assert agent.get_graph().draw_mermaid(with_styles=False) == snapshot
+    except Exception as e:
+        raise ValueError(
+            "The graph structure has changed. Please update the snapshot."
+            "Configuration used:\n"
+            f"tools: {tools}, "
+            f"pre_model_hook: {pre_model_hook}, "
+            f"post_model_hook: {post_model_hook}, "
+            f"response_format: {response_format}"
+        ) from e
+
+
+@pytest.mark.parametrize("tools", [[], [tool, tool2]], ids=["no_tools", "two_tools"])
+@pytest.mark.parametrize(
+    "pre_model_hook", [None, pre_model_hook], ids=["no_pre_hook", "with_pre_hook"]
+)
+@pytest.mark.parametrize(
+    "post_model_hook", [None, post_model_hook], ids=["no_post_hook", "with_post_hook"]
+)
+@pytest.mark.parametrize(
+    "response_format",
+    [None, ResponseFormat],
+    ids=["no_response_format", "with_response_format"],
+)
+def test_react_agent_graph_structure_with_individual_nodes(
+    snapshot: SnapshotAssertion,
+    tools: list[Callable],
+    pre_model_hook: Union[Callable, None],
+    post_model_hook: Union[Callable, None],
+    response_format: Union[type[BaseModel], None],
+) -> None:
+    agent = create_react_agent(
+        model,
+        tools=tools,
+        pre_model_hook=pre_model_hook,
+        post_model_hook=post_model_hook,
+        response_format=response_format,
+        use_individual_tool_nodes=True,
+    )
    assert agent.get_graph().draw_mermaid(with_styles=False) == snapshot
@@ -1,25 +1,49 @@
+import dataclasses
+import json
+from functools import partial
 from typing import (
    Annotated,
    Any,
+    List,
+    Type,
+    TypeVar,
    Union,
 )

 import pytest
 from langchain_core.messages import (
    AIMessage,
+    AnyMessage,
+    HumanMessage,
    RemoveMessage,
+    ToolCall,
    ToolMessage,
 )
 from langchain_core.tools import BaseTool, ToolException
 from langchain_core.tools import tool as dec_tool
 from pydantic import BaseModel, ValidationError
+from pydantic.v1 import BaseModel as BaseModelV1
 from pydantic.v1 import ValidationError as ValidationErrorV1
+from typing_extensions import TypedDict

+from langgraph.config import get_stream_writer
 from langgraph.errors import GraphBubbleUp, GraphInterrupt
-from langgraph.graph.message import REMOVE_ALL_MESSAGES
-from langgraph.prebuilt import ToolNode
-from langgraph.prebuilt.tool_node import TOOL_CALL_ERROR_TEMPLATE
+from langgraph.graph import START, MessagesState, StateGraph
+from langgraph.graph.message import REMOVE_ALL_MESSAGES, add_messages
+from langgraph.prebuilt import (
+    ToolNode,
+)
+from langgraph.prebuilt.tool_node import (
+    TOOL_CALL_ERROR_TEMPLATE,
+    InjectedState,
+    InjectedStore,
+    tools_condition,
+)
+from langgraph.store.base import BaseStore
+from langgraph.store.memory import InMemoryStore
 from langgraph.types import Command, Send
+from tests.messages import _AnyIdHumanMessage, _AnyIdToolMessage
+from tests.model import FakeToolCallingModel

 pytestmark = pytest.mark.anyio

@@ -62,7 +86,8 @@ def tool5(some_val: int):
 tool5.handle_tool_error = "foo"


-async def test_tool_node():
+async def test_tool_node() -> None:
+    """Test tool node."""
    result = ToolNode([tool1]).invoke(
        {
            "messages": [
@@ -154,7 +179,7 @@ async def test_tool_node():
    assert tool_message.tool_call_id == "some 3"


-async def test_tool_node_tool_call_input():
+async def test_tool_node_tool_call_input() -> None:
    # Single tool call
    tool_call_1 = {
        "name": "tool1",
@@ -195,7 +220,7 @@ async def test_tool_node_tool_call_input():
    ]


-async def test_tool_node_error_handling():
+async def test_tool_node_error_handling() -> None:
    def handle_all(e: Union[ValueError, ToolException, ValidationError]):
        return TOOL_CALL_ERROR_TEMPLATE.format(error=repr(e))

@@ -257,7 +282,7 @@ async def test_tool_node_error_handling():
        assert result_error["messages"][2].tool_call_id == "another id"


-async def test_tool_node_error_handling_callable():
+async def test_tool_node_error_handling_callable() -> None:
    def handle_value_error(e: ValueError):
        return "Value error"

@@ -1156,3 +1181,395 @@ async def test_tool_node_command_remove_all_messages():
    command = result[0]
    assert isinstance(command, Command)
    assert command.update == {"messages": [RemoveMessage(id=REMOVE_ALL_MESSAGES)]}
+
+
+class _InjectStateSchema(TypedDict):
+    messages: list
+    foo: str
+
+
+class _InjectedStatePydanticSchema(BaseModelV1):
+    messages: list
+    foo: str
+
+
+class _InjectedStatePydanticV2Schema(BaseModel):
+    messages: list
+    foo: str
+
+
+@dataclasses.dataclass
+class _InjectedStateDataclassSchema:
+    messages: list
+    foo: str
+
+
+T = TypeVar("T")
+
+
+@pytest.mark.parametrize(
+    "schema_",
+    [
+        _InjectStateSchema,
+        _InjectedStatePydanticSchema,
+        _InjectedStatePydanticV2Schema,
+        _InjectedStateDataclassSchema,
+    ],
+)
+def test_tool_node_inject_state(schema_: Type[T]) -> None:
+    def tool1(some_val: int, state: Annotated[T, InjectedState]) -> str:
+        """Tool 1 docstring."""
+        if isinstance(state, dict):
+            return state["foo"]
+        else:
+            return getattr(state, "foo")
+
+    def tool2(some_val: int, state: Annotated[T, InjectedState()]) -> str:
+        """Tool 2 docstring."""
+        if isinstance(state, dict):
+            return state["foo"]
+        else:
+            return getattr(state, "foo")
+
+    def tool3(
+        some_val: int,
+        foo: Annotated[str, InjectedState("foo")],
+        msgs: Annotated[List[AnyMessage], InjectedState("messages")],
+    ) -> str:
+        """Tool 1 docstring."""
+        return foo
+
+    def tool4(
+        some_val: int, msgs: Annotated[List[AnyMessage], InjectedState("messages")]
+    ) -> str:
+        """Tool 1 docstring."""
+        return msgs[0].content
+
+    node = ToolNode([tool1, tool2, tool3, tool4])
+    for tool_name in ("tool1", "tool2", "tool3"):
+        tool_call = {
+            "name": tool_name,
+            "args": {"some_val": 1},
+            "id": "some 0",
+            "type": "tool_call",
+        }
+        msg = AIMessage("hi?", tool_calls=[tool_call])
+        result = node.invoke(schema_(**{"messages": [msg], "foo": "bar"}))
+        tool_message = result["messages"][-1]
+        assert tool_message.content == "bar", f"Failed for tool={tool_name}"
+
+        if tool_name == "tool3":
+            failure_input = None
+            try:
+                failure_input = schema_(**{"messages": [msg], "notfoo": "bar"})
+            except Exception:
+                pass
+            if failure_input is not None:
+                with pytest.raises(KeyError):
+                    node.invoke(failure_input)
+
+                with pytest.raises(ValueError):
+                    node.invoke([msg])
+        else:
+            failure_input = None
+            try:
+                failure_input = schema_(**{"messages": [msg], "notfoo": "bar"})
+            except Exception:
+                # We'd get a validation error from pydantic state and wouldn't make it to the node
+                # anyway
+                pass
+            if failure_input is not None:
+                messages_ = node.invoke(failure_input)
+                tool_message = messages_["messages"][-1]
+                assert "KeyError" in tool_message.content
+                tool_message = node.invoke([msg])[-1]
+                assert "KeyError" in tool_message.content
+
+    tool_call = {
+        "name": "tool4",
+        "args": {"some_val": 1},
+        "id": "some 0",
+        "type": "tool_call",
+    }
+    msg = AIMessage("hi?", tool_calls=[tool_call])
+    result = node.invoke(schema_(**{"messages": [msg], "foo": ""}))
+    tool_message = result["messages"][-1]
+    assert tool_message.content == "hi?"
+
+    result = node.invoke([msg])
+    tool_message = result[-1]
+    assert tool_message.content == "hi?"
+
+
+def test_tool_node_inject_store() -> None:
+    store = InMemoryStore()
+    namespace = ("test",)
+
+    def tool1(some_val: int, store: Annotated[BaseStore, InjectedStore()]) -> str:
+        """Tool 1 docstring."""
+        store_val = store.get(namespace, "test_key").value["foo"]
+        return f"Some val: {some_val}, store val: {store_val}"
+
+    def tool2(some_val: int, store: Annotated[BaseStore, InjectedStore()]) -> str:
+        """Tool 2 docstring."""
+        store_val = store.get(namespace, "test_key").value["foo"]
+        return f"Some val: {some_val}, store val: {store_val}"
+
+    def tool3(
+        some_val: int,
+        bar: Annotated[str, InjectedState("bar")],
+        store: Annotated[BaseStore, InjectedStore()],
+    ) -> str:
+        """Tool 3 docstring."""
+        store_val = store.get(namespace, "test_key").value["foo"]
+        return f"Some val: {some_val}, store val: {store_val}, state val: {bar}"
+
+    node = ToolNode([tool1, tool2, tool3], handle_tool_errors=True)
+    store.put(namespace, "test_key", {"foo": "bar"})
+
+    class State(MessagesState):
+        bar: str
+
+    builder = StateGraph(State)
+    builder.add_node("tools", node)
+    builder.add_edge(START, "tools")
+    graph = builder.compile(store=store)
+
+    for tool_name in ("tool1", "tool2"):
+        tool_call = {
+            "name": tool_name,
+            "args": {"some_val": 1},
+            "id": "some 0",
+            "type": "tool_call",
+        }
+        msg = AIMessage("hi?", tool_calls=[tool_call])
+        node_result = node.invoke({"messages": [msg]}, store=store)
+        graph_result = graph.invoke({"messages": [msg]})
+        for result in (node_result, graph_result):
+            result["messages"][-1]
+            tool_message = result["messages"][-1]
+            assert tool_message.content == "Some val: 1, store val: bar", (
+                f"Failed for tool={tool_name}"
+            )
+
+    tool_call = {
+        "name": "tool3",
+        "args": {"some_val": 1},
+        "id": "some 0",
+        "type": "tool_call",
+    }
+    msg = AIMessage("hi?", tool_calls=[tool_call])
+    node_result = node.invoke({"messages": [msg], "bar": "baz"}, store=store)
+    graph_result = graph.invoke({"messages": [msg], "bar": "baz"})
+    for result in (node_result, graph_result):
+        result["messages"][-1]
+        tool_message = result["messages"][-1]
+        assert tool_message.content == "Some val: 1, store val: bar, state val: baz", (
+            f"Failed for tool={tool_name}"
+        )
+
+    # test injected store without passing store to compiled graph
+    failing_graph = builder.compile()
+    with pytest.raises(ValueError):
+        failing_graph.invoke({"messages": [msg], "bar": "baz"})
+
+
+def test_tool_node_ensure_utf8() -> None:
+    @dec_tool
+    def get_day_list(days: list[str]) -> list[str]:
+        """choose days"""
+        return days
+
+    data = ["星期一", "水曜日", "목요일", "Friday"]
+    tools = [get_day_list]
+    tool_calls = [ToolCall(name=get_day_list.name, args={"days": data}, id="test_id")]
+    outputs: list[ToolMessage] = ToolNode(tools).invoke(
+        [AIMessage(content="", tool_calls=tool_calls)]
+    )
+    assert outputs[0].content == json.dumps(data, ensure_ascii=False)
+
+
+def test_tool_node_messages_key() -> None:
+    @dec_tool
+    def add(a: int, b: int):
+        """Adds a and b."""
+        return a + b
+
+    model = FakeToolCallingModel(
+        tool_calls=[[ToolCall(name=add.name, args={"a": 1, "b": 2}, id="test_id")]]
+    )
+
+    class State(TypedDict):
+        subgraph_messages: Annotated[list[AnyMessage], add_messages]
+
+    def call_model(state: State):
+        response = model.invoke(state["subgraph_messages"])
+        model.tool_calls = []
+        return {"subgraph_messages": response}
+
+    builder = StateGraph(State)
+    builder.add_node("agent", call_model)
+    builder.add_node("tools", ToolNode([add], messages_key="subgraph_messages"))
+    builder.add_conditional_edges(
+        "agent", partial(tools_condition, messages_key="subgraph_messages")
+    )
+    builder.add_edge(START, "agent")
+    builder.add_edge("tools", "agent")
+
+    graph = builder.compile()
+    result = graph.invoke({"subgraph_messages": [HumanMessage(content="hi")]})
+    assert result["subgraph_messages"] == [
+        _AnyIdHumanMessage(content="hi"),
+        AIMessage(
+            content="hi",
+            id="0",
+            tool_calls=[ToolCall(name=add.name, args={"a": 1, "b": 2}, id="test_id")],
+        ),
+        _AnyIdToolMessage(content="3", name=add.name, tool_call_id="test_id"),
+        AIMessage(content="hi-hi-3", id="1"),
+    ]
+
+
+def test_tool_node_stream_writer() -> None:
+    @dec_tool
+    def streaming_tool(x: int) -> str:
+        """Do something with writer."""
+        my_writer = get_stream_writer()
+        for value in ["foo", "bar", "baz"]:
+            my_writer({"custom_tool_value": value})
+
+        return x
+
+    tool_node = ToolNode([streaming_tool])
+    graph = (
+        StateGraph(MessagesState)
+        .add_node("tools", tool_node)
+        .add_edge(START, "tools")
+        .compile()
+    )
+
+    tool_call = {
+        "name": "streaming_tool",
+        "args": {"x": 1},
+        "id": "1",
+        "type": "tool_call",
+    }
+    inputs = {
+        "messages": [AIMessage("", tool_calls=[tool_call])],
+    }
+
+    assert list(graph.stream(inputs, stream_mode="custom")) == [
+        {"custom_tool_value": "foo"},
+        {"custom_tool_value": "bar"},
+        {"custom_tool_value": "baz"},
+    ]
+    assert list(graph.stream(inputs, stream_mode=["custom", "updates"])) == [
+        ("custom", {"custom_tool_value": "foo"}),
+        ("custom", {"custom_tool_value": "bar"}),
+        ("custom", {"custom_tool_value": "baz"}),
+        (
+            "updates",
+            {
+                "tools": {
+                    "messages": [
+                        _AnyIdToolMessage(
+                            content="1",
+                            name="streaming_tool",
+                            tool_call_id="1",
+                        ),
+                    ],
+                },
+            },
+        ),
+    ]
+
+
+def test_structured_output_tools_sync() -> None:
+    """Test that ToolNode handles Pydantic model classes as structured output tools."""
+
+    class OutputSchema(BaseModel):
+        name: str
+        age: int
+        location: str
+
+    tool_node = ToolNode([OutputSchema])
+
+    # Test that the structured output tool is registered correctly
+    assert "OutputSchema" in tool_node.structured_output_tools
+
+    # Create a tool call that matches the schema
+    tool_call = {
+        "name": "OutputSchema",
+        "args": {"name": "Alice", "age": 30, "location": "NYC"},
+        "id": "call_123",
+        "type": "tool_call",
+    }
+
+    # Test sync execution
+    result = tool_node.invoke(
+        {"messages": [AIMessage(content="", tool_calls=[tool_call])]}
+    )
+
+    # Should return a Command with structured response
+    assert isinstance(result, list)
+    assert len(result) == 1
+    command = result[0]
+    assert isinstance(command, Command)
+
+    # Check the update structure
+    assert "messages" in command.update
+    assert "structured_response" in command.update
+
+    # Check the tool message
+    tool_message = command.update["messages"][0]
+    assert isinstance(tool_message, ToolMessage)
+    assert tool_message.name == "OutputSchema"
+    assert tool_message.tool_call_id == "call_123"
+
+    # Check the structured response
+    structured_response = command.update["structured_response"]
+    assert isinstance(structured_response, OutputSchema)
+    assert structured_response.name == "Alice"
+    assert structured_response.age == 30
+    assert structured_response.location == "NYC"
+
+
+async def test_structured_output_tools_async() -> None:
+    """Test that ToolNode handles Pydantic model classes as structured output tools."""
+
+    class OutputSchema(BaseModel):
+        name: str
+        age: int
+        location: str
+
+    tool_node = ToolNode([OutputSchema])
+
+    # Test that the structured output tool is registered correctly
+    assert "OutputSchema" not in tool_node.tools_by_name
+    assert "OutputSchema" in tool_node.structured_output_tools
+
+    # Create a tool call that matches the schema
+    tool_call = {
+        "name": "OutputSchema",
+        "args": {"name": "Alice", "age": 30, "location": "NYC"},
+        "id": "call_123",
+        "type": "tool_call",
+    }
+
+    # Test async execution
+    result_async = await tool_node.ainvoke(
+        {"messages": [AIMessage(content="", tool_calls=[tool_call])]}
+    )
+
+    # Should produce the same result
+    assert isinstance(result_async, list)
+    assert len(result_async) == 1
+    command_async = result_async[0]
+    assert isinstance(command_async, Command)
+    assert "structured_response" in command_async.update
+
+    structured_response_async = command_async.update["structured_response"]
+    assert isinstance(structured_response_async, OutputSchema)
+    assert structured_response_async.name == "Alice"
+    assert structured_response_async.age == 30
+    assert structured_response_async.location == "NYC"
@@ -316,7 +316,7 @@ wheels = [

 [[package]]
 name = "langgraph"
-version = "0.6.2"
+version = "0.6.4"
 source = { editable = "../langgraph" }
 dependencies = [
    { name = "langchain-core" },
@@ -359,6 +359,7 @@ dev = [
    { name = "pytest-repeat" },
    { name = "pytest-watcher" },
    { name = "pytest-xdist", extras = ["psutil"] },
+    { name = "redis" },
    { name = "ruff" },
    { name = "syrupy" },
    { name = "types-requests" },
@@ -392,6 +393,7 @@ dev = [
    { name = "pytest-asyncio" },
    { name = "pytest-mock" },
    { name = "pytest-watcher" },
+    { name = "redis" },
    { name = "ruff" },
 ]

@@ -460,7 +462,7 @@ dev = [

 [[package]]
 name = "langgraph-prebuilt"
-version = "0.6.2"
+version = "0.6.4"
 source = { editable = "." }
 dependencies = [
    { name = "langchain-core" },
Author	SHA1	Message	Date
Eugene Yurtsev	8656e16346	x	2025-08-13 15:43:00 -04:00
Eugene YurtsevandGitHub	50601dc02c	feat(prebuilt): Add structured output tools to ToolNode (#5899 ) * Add structured output tools to ToolNode * Fix default tool node name to match the actual default ('tools') * Update doc-strings to explain what inputs/outputs are for the ToolNode. * Mark internal attributes as private (potentially breaking -- although hopefully users aren't accessing these) ## Decisions points * OK with two properties? Done since users may be relying on `tools_by_name` and expanding the return type will break user code. ## Changes in public/private interface ### Marked as public * Make `tools_by_name` an official public property * Make `structured_output_tools` a public property ### Marked as private There should be no reason why users are accessing these attributes ```python _tool_to_state_args _tool_to_store_arg _handle_tool_errors _messages_key ``` ### Usage ```python class OutputSchema(BaseModel): name: str age: int location: str tool_node = ToolNode([OutputSchema]) # Test that the structured output tool is registered correctly assert "OutputSchema" in tool_node.structured_output_tools # Create a tool call that matches the schema tool_call = { "name": "OutputSchema", "args": {"name": "Alice", "age": 30, "location": "NYC"}, "id": "call_123", "type": "tool_call", } # Test sync execution result = tool_node.invoke( {"messages": [AIMessage(content="", tool_calls=[tool_call])]} ) # Should return a Command with structured response assert isinstance(result, list) assert len(result) == 1 command = result[0] assert isinstance(command, Command) # Check the update structure assert "messages" in command.update assert "structured_response" in command.update # Check the tool message tool_message = command.update["messages"][0] assert isinstance(tool_message, ToolMessage) assert tool_message.name == "OutputSchema" assert tool_message.tool_call_id == "call_123" # Check the structured response structured_response = command.update["structured_response"] assert isinstance(structured_response, OutputSchema) assert structured_response.name == "Alice" assert structured_response.age == 30 assert structured_response.location == "NYC" ```	2025-08-13 15:16:53 -04:00
Eugene YurtsevandGitHub	9e174e7e8b	chore(prebuilt): move unit tests for ToolNode into the tool node testing code (#5893 ) Move unit tests for ToolNode into the tool node testing code	2025-08-13 11:15:10 -04:00
Eugene YurtsevandGitHub	9e9a5d2498	feat(prebuilt): Split tool node to individual tool nodes (#5888 ) Add option to split tool node to individual nodes. Summary: * User code (specifically streaming) may break if it's relying on the name of the `tools` node * The boolean flag in the interface is likely temporary (especially if there are no major breaking changes) * We'll need to decide if we can get rid of the version in create react agent. "v1" is not consistent conceptually with a node per tool.	2025-08-13 09:49:27 -04:00
Eugene Yurtsev	7e257dadd6	x	2025-08-12 21:52:21 -04:00
Eugene Yurtsev	2fed0e4852	Internal refactor of create react-agent	2025-08-12 21:50:19 -04:00
Hunter Lovell GitHub Brody Klapko	d43eaf1f42	chore(docs): add remaining js translations (#5825 ) Related Linear ticket: https://linear.app/langchain/issue/DOC-51/add-js-translations-for-remaining-pages --------- Co-authored-by: Brody Klapko <brody@langchain.dev>	2025-08-12 09:47:11 -04:00
Sam CrowderandGitHub	16b363fbb0	feat(langgraph): implement redis node level cache (#5834 ) ### Description Adds Redis as a supported cache backend for LangGraph node-level caching, enabling distributed caching across multiple processes/servers. This implementation follows the same patterns as existing InMemoryCache and SqliteCache. ### Key changes - New RedisCache class implementing the BaseCache interface - Support for TTL-based expiration and batch operations - Worker-specific cache prefixes for parallel test isolation ### Dependencies - redis package (already included in dev dependencies) ### Test Plan - Unit tests: Added Redis cache tests covering basic operations, TTL, batch operations, and error handling - Integration tests: Redis cache integrated into existing LangGraph test suite, tested with all checkpointer combinations	2025-08-11 09:19:34 -07:00
Sydney RunkleandGitHub	68a75135b0	release: langgraph + prebuilt 0.6.4 (#5854 )	2025-08-07 18:12:26 +00:00
Isaac FranciscoandGitHub	5c0c0fb186	fix: mypy issue with conditional edges (#5851 ) Send should inherit from hashable, and need to use Sequence since List is invariant. https://github.com/langchain-ai/langgraph/issues/5850	2025-08-07 08:46:44 -07:00
Eugene Yurtsev GitHub Sydney Runkle	4571b708d9	fix(langgraph): support emitting messages from subgraphs when messages mode explicitly requested (#5836 ) Reproduces: https://github.com/langchain-ai/langgraph/issues/5249#issuecomment-3156519635 Caused after this change: https://github.com/langchain-ai/langgraph/pull/4843 Fix to allow emitting messages from subgraphs if the subgraphs explicitly used a stream mode "messages". ```python def node_in_parent(...): # subgraph was called as a function. # messages are explicitly requested. for event in subgraph.stream(..., stream_mode="messages"): # something is done with `event` return ... # subgraphs = False! parent_graph.invoke(..., subgraphs=False) ``` The code above should continue to work correctly regardless of the value of subgraphs as streaming messages was requested explicitly in the parent node! --------- Co-authored-by: Sydney Runkle <54324534+sydney-runkle@users.noreply.github.com>	2025-08-07 10:10:52 -04:00
Sydney RunkleandGitHub	e365b2b8bd	fix(prebuilt): raise on additional deprecated kwargs (#5848 )	2025-08-06 21:08:42 +00:00
Isaac FranciscoandGitHub	b5504506a7	fix: add resiliency for task cancellation (#5846 )	2025-08-06 13:31:52 -07:00
Nuno CamposandGitHub	c6ae8d25b9	perf: Save updated_channels to checkpoint (#5828 ) - This makes prepare_next_tasks constant on number of nodes in all cases, whereas before we were falling back to node iteration when resuming from an existing checkpoint	2025-08-06 19:09:33 +01:00
Sydney RunkleandGitHub	0bd7dd2c52	chore(langgraph): deprecate `MessageGraph` (#5843 ) `MessageGraph` is deprecated, to be removed in v2. A `StateGraph` with a `messages` key should be used instead. Alternatively, folks can use `Annotated[list[AnyMessage], add_messages]` as their state schema.	2025-08-06 14:17:50 +00:00
Sydney RunkleandGitHub	82978a8dd8	chore(prebuilt): revert tool arg injection refactor (#5842 ) Reverts https://github.com/langchain-ai/langgraph/pull/5562 I anticipate that we want to do another pass at a refactor here in the short term, but this makes it easier to adapt to new langchain core message types for v0.4 support in the short term.	2025-08-06 10:12:08 -04:00
Kathryn MayandGitHub	925150a35d	docs: Update redirects for deployment option renaming (#5823 ) Updates the URLs for the new site deployment options after a rename.	2025-08-04 15:32:11 -04:00
Sydney RunkleandGitHub	2920a9dd19	fix(langgraph): Tidy up `AgentState` (#5801 ) Fixes https://github.com/langchain-ai/langgraph/issues/5784 * Removes usage of `is_last_step`, no longer needed with `remaining_steps` * Make `remaining_steps` `NotRequired` so that json schema doesn't suggest need for user input * Move `PregelScratchpad` to shared utils file to prevent circular import issue (it's used from `channels/managed` and other pregel files). * Ensures that managed values wrapped in `NotRequired` or `Required` are still recognized!	2025-08-03 07:12:53 -04:00
Eugene YurtsevandGitHub	db8ed4e9e4	fix(docs): update agents.md (#5800 ) fix comment in tip	2025-08-02 06:09:09 -04:00
Lauren Hirata SinghandGitHub	b16fcc8468	docs: remove broken links (#5803 )	2025-08-01 15:41:21 -04:00
Sydney RunkleandGitHub	a2fe4df89b	release: langgraph + prebuilt 0.6.3 (#5799 )	2025-08-01 14:52:38 -04:00
open-swe[bot]GitHubopen-swe[bot] <open-swe@users.noreply.github.com>Sydney Runkle	69dd20e523	fix(langgraph): Add warning for incorrect node signature with mistyped `config` param (#5798 ) Fixes: #5787 Ensures that if `config` is not typed as one of `RunanbleConfig` or `Optional[RunnableConfig]` a warning is raised to help developers avoid unexpected results at invocation time. --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> Co-authored-by: Sydney Runkle <sydneymarierunkle@gmail.com>	2025-08-01 17:25:14 +00:00
open-swe[bot]GitHubopen-swe[bot] <open-swe@users.noreply.github.com>	5152a96fce	fix(docs): Correct import statement for `InMemorySaver` in conceptual docs (#5797 ) Fixes #5781 Fixes the incorrect import statement in the Python documentation tutorial. - Changed import from `MemorySaver` to `InMemorySaver` - Ensures consistency between import statement and class instantiation - Verified through formatting and linting checks The documentation now correctly reflects the proper import for the InMemorySaver class. --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>	2025-08-01 14:54:30 +00:00
Sydney RunkleandGitHub	220314b53a	fix(langgraph): fix up deprecation warnings (#5796 ) Fixes https://github.com/langchain-ai/langgraph/issues/5795 * Must use `category=None` on decorator so that we get type checking support but no dupe warning * Fixed tuple on `confix_type` warning causing false warning	2025-08-01 14:33:46 +00:00
Sydney Runkle GitHub Eugene Yurtsev Lauren Hirata Singh	38bbd92e01	feat(langgraph): add durability mode for `invoke` and `ainvoke` (#5771 ) Fixes https://github.com/langchain-ai/langgraph/issues/5741 Follow up to https://github.com/langchain-ai/langgraph/pull/5432 Plus clean up deprecation logic for `checkpoint_during` and add tests. --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com> Co-authored-by: Lauren Hirata Singh <lauren@langchain.dev>	2025-08-01 10:30:24 -04:00
Eugene YurtsevandGitHub	e3cb2dd23b	chore(docs): fix more admonitions (#5792 ) Fix more admonitions	2025-07-31 22:57:44 -04:00
Eugene YurtsevandGitHub	2f23d1a30d	chore(docs): fix js build (#5793 ) Fix js build	2025-07-31 22:57:32 -04:00
Eugene YurtsevandGitHub	88e195bb78	chore(docs): fix admonitions in graph api page (#5791 ) fix many admonitions in the graph API page	2025-07-31 21:50:27 -04:00
Lauren Hirata Singh GitHub Hunter Lovell	41a4f993b1	docs: Update link maps for reference docs (#5745 ) Update link maps --------- Co-authored-by: Hunter Lovell <hunter@hntrl.io>	2025-07-31 18:06:35 -04:00
Kai-Wendel GitHub Eugene Yurtsev Lauren Hirata Singh	b8f3f48da9	fix(docs): Add missing imports to make examples runnable (#5477 ) I suppose that the code snippets are intended to run each on its own. To guarantee this the snippet for the example: "Write long-temr memory from tools" needs to include `RunnableConfig` Same also for the second commit of this pull request. The other commits are about similar issues, where imports are missing to make a snippet executable on its own. --------- Signed-off-by: Kai Wendel <kai.wendel@iws.uni-stuttgart.de> Co-authored-by: Eugene Yurtsev <eugene@langchain.dev> Co-authored-by: Lauren Hirata Singh <lauren@langchain.dev>	2025-07-31 20:04:52 +00:00
Michael GitHub Lauren Hirata Singh	94f7f0632d	docs(docs): fix image in "Run graph nodes in parallel" section of N Graph API how-to (#5527 ) Description: Replaced the outdated image in the "Run graph nodes in parallel" section of the N Graph API how-to guide to correctly show parallel node execution. Twitter handle: @MichaelLoukeris Co-authored-by: Lauren Hirata Singh <lauren@langchain.dev>	2025-07-31 20:02:33 +00:00
Xin JinandGitHub	b3e0582255	docs: clarify draw_mermaid_png only works in jupyter (#5609 ) Nit, without comments I thought image would somehow show in terminal, but that's not true you'd only get image to show if in jupyter notebook. Don't have to merge, i'm just seeing this particular as not a pleasure DevX. <img width="848" height="440" alt="Screenshot 2025-07-21 at 12 26 04 PM" src="https://github.com/user-attachments/assets/50261b35-f09d-4516-86f4-14e8bf53f8e2" />	2025-07-31 15:54:45 -04:00
Srikanto Rajbongshi GitHub Lauren Hirata Singh	24c7a8db3f	Remove duplicated pretty_print_messages helper in Multi‑agent supervisor tutorial (#5617 ) Description: Closes #___ Removed the redundant `pretty_print_message`/`pretty_print_messages` helper snippet from `docs/docs/tutorials/multi_agent/agent_supervisor.md`. Now there is a single, authoritative definition of these functions, which: - Simplifies the tutorial - Avoids reader confusion over which helper to use - Prevents future drift between duplicate code blocks Issue: Closes #___ Dependencies: None Co-authored-by: Lauren Hirata Singh <lauren@langchain.dev>	2025-07-31 19:54:22 +00:00
Sakshi Gupta GitHub Eugene Yurtsev	f8eb4244e0	docs(graphapi): update the graph image for the "Combine control flow and state updates with Command" example (#5626 ) The example had the node names as - node_a, node_b & node_c. But the graph shows the image of generate_topics. This change includes the addition of complete & accurate graph. --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	2025-07-31 19:52:55 +00:00
Syed Baqar AbbasandGitHub	62c3bbc9fe	docs: Removed repetition of block pretty_print_messages (#5636 ) ## docs: Removed repetition of block pretty_print_messages - Description: The documentation had the same cell duplicated, I fixed it by deleting one example - Issue: #5616	2025-07-31 19:49:48 +00:00
Kathryn MayandGitHub	76bbb761b4	docs: Add studio troubleshooting to redirects (#5783 ) Add a redirect from https://langchain-ai.github.io/langgraph/troubleshooting/studio/ to https://docs.langchain.com/langgraph-platform/troubleshooting-studio	2025-07-31 15:31:35 -04:00
Sydney RunkleandGitHub	80cd91344f	chore: no ci on v1 branch (#5782 )	2025-07-31 19:08:10 +00:00
Lauren Hirata SinghandGitHub	9e4c41cbed	docs: remove LGP mentions (#5780 )	2025-07-31 14:13:56 -04:00
ShehabandGitHub	1fda568df9	fix(docs): extended examples in graph API docs (#5774 ) Fixes #5770	2025-07-31 18:00:54 +00:00
Mohammad Mohtashim GitHub Eugene Yurtsev	08295ecadb	chore(prebuilt): add supported input types for model in create_react_agent (#5748 ) - Description: Update the type annotations in create_react_agent to allow one to provide a callable for the model that uses bind_tools and returns a Runnable[LanguageModelInput, BaseMessage] - Issue: #5739 --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	2025-07-31 14:00:12 -04:00
Lauren Hirata SinghandGitHub	4ecbabafe8	docs: redirects for LGP mintlify (#5767 ) - Added redirects for all of the LGP docs we're moving to Mintlify - Exclude files not listed in nav from search - Update banner	2025-07-31 13:10:45 -04:00
Sam CrowderandGitHub	246efe71f4	fix: change from developer to enterprise (#5778 )	2025-07-31 09:42:19 -07:00
Eugene YurtsevandGitHub	116121eb3a	feat(docs): dynamic model and tool selection in create react agent (#5777 ) Document dynamic models and dynamic tools	2025-07-31 11:22:30 -04:00
William FHandGitHub	18887e9f86	fix(langgraph): Remove duplicate call to ensure_config (#5768 )	2025-07-31 09:15:03 -04:00
Sam CrowderandGitHub	bec28226d0	fix: removing standalone container lite from old docs (#5759 )	2025-07-30 18:21:37 -07:00
Sam CrowderandGitHub	967e368e14	fix: add link that points to where changelog now lives (#5758 )	2025-07-30 17:49:51 -07:00