v bump

* Bump version of langgraph to v1.0.0a1
* Bump version of prebuilt to v0.7.0a1
* Fix tests w/ new langchain-core alpha version
* Bump min supported python version

Deprecating prebuilts tools w/ helpful IDE hinting + deprecation
messages.

---------

Co-authored-by: ccurme <chester.curme@gmail.com>

.github/scripts/check_sdk_methods.py

@@ -1,10 +1,15 @@
 import ast
 import os
 from itertools import filterfalse
-from typing import List, Tuple
+from typing import Dict, List, Tuple
 
 ROOT_PATH = os.path.abspath(os.path.join(__file__, "..", "..", ".."))
 CLIENT_PATH = os.path.join(ROOT_PATH, "libs", "sdk-py", "langgraph_sdk", "client.py")
+ASYNC_TO_SYNC_METHOD_MAP: Dict[str, str] = {
+    "aclose": "close",
+    "__aenter__": "__enter__",
+    "__aexit__": "__exit__",
+}
 
 
 def get_class_methods(node: ast.ClassDef) -> List[str]:
@@ -22,7 +27,7 @@ def find_classes(tree: ast.AST) -> List[Tuple[str, List[str]]]:
 
 def compare_sync_async_methods(sync_methods: List[str], async_methods: List[str]) -> List[str]:
     sync_set = set(sync_methods)
-    async_set = set(async_methods)
+    async_set = {ASYNC_TO_SYNC_METHOD_MAP.get(async_method, async_method) for async_method in async_methods}
     missing_in_sync = list(async_set - sync_set)
     missing_in_async = list(sync_set - async_set)
     return missing_in_sync + missing_in_async

.github/scripts/run_langgraph_cli_test.py

@@ -1,107 +1,145 @@
-import asyncio
-import json
-import os
 import pathlib
 import sys
-import langgraph_cli
-import langgraph_cli.docker
-import langgraph_cli.config
+import time
+from urllib import request, error
 
+import langgraph_cli
+import langgraph_cli.config
+import langgraph_cli.docker
+from langgraph_cli.cli import prepare_args_and_stdin
+from langgraph_cli.constants import DEFAULT_PORT
 from langgraph_cli.exec import Runner, subp_exec
 from langgraph_cli.progress import Progress
-from langgraph_cli.constants import DEFAULT_PORT
 
 
-def test(
-    config: pathlib.Path,
-    port: int,
-    tag: str,
-    verbose: bool,
-):
+def test(config: pathlib.Path, port: int, tag: str, verbose: bool):
+    """Spin up API with Postgres/Redis via docker compose and wait until ready."""
     with Runner() as runner, Progress(message="Pulling...") as set:
-        # check docker available
+        # Detect docker/compose capabilities
         capabilities = langgraph_cli.docker.check_capabilities(runner)
-        # open config
+
+        # Validate config and prepare compose stdin/args using built image
         config_json = langgraph_cli.config.validate_config_file(config)
+        args, stdin = prepare_args_and_stdin(
+            capabilities=capabilities,
+            config_path=config,
+            config=config_json,
+            docker_compose=None,
+            port=port,
+            watch=False,
+            debugger_port=None,
+            debugger_base_url=f"http://127.0.0.1:{port}",
+            postgres_uri=None,
+            api_version=None,
+            image=tag,
+            base_image=None,
+        )
 
-        set("Running...")
-        args = [
-            "run",
-            "--rm",
-            "-p",
-            f"{port}:8000",
-        ]
-        if isinstance(config_json["env"], str):
-            args.extend(
-                [
-                    "--env-file",
-                    str(config.parent / config_json["env"]),
-                ]
-            )
-        else:
-            for k, v in config_json["env"].items():
-                args.extend(
-                    [
-                        "-e",
-                        f"{k}={v}",
-                    ]
-                )
-        if capabilities.healthcheck_start_interval:
-            args.extend(
-                [
-                    "--health-interval",
-                    "5s",
-                    "--health-retries",
-                    "1",
-                    "--health-start-period",
-                    "10s",
-                    "--health-start-interval",
-                    "1s",
-                ]
-            )
-        else:
-            args.extend(
-                [
-                    "--health-interval",
-                    "5s",
-                    "--health-retries",
-                    "2",
-                ]
-            )
+        # Compose up with wait (implies detach), similar to `langgraph up --wait`
+        args_up = [*args, "up", "--remove-orphans", "--wait"]
 
-        _task = None
-
-        def on_stdout(line: str):
-            nonlocal _task
-            if "GET /ok" in line or "Uvicorn running on" in line:
-                set("")
-                sys.stdout.write(
-                    f"""Ready!
-- API: http://localhost:{port}
-"""
-                )
-                sys.stdout.flush()
-                _task.cancel()
-                return True
-            return False
-
-        async def subp_exec_task(*args, **kwargs):
-            nonlocal _task
-            _task = asyncio.create_task(subp_exec(*args, **kwargs))
-            await _task
+        compose_cmd = ["docker", "compose"]
+        if capabilities.compose_type == "standalone":
+            compose_cmd = ["docker-compose"]
 
+        set("Starting...")
         try:
             runner.run(
-                subp_exec_task(
-                    "docker",
-                    *args,
-                    tag,
+                subp_exec(
+                    *compose_cmd,
+                    *args_up,
+                    input=stdin,
                     verbose=verbose,
-                    on_stdout=on_stdout,
                 )
             )
-        except asyncio.CancelledError:
-            pass
+        except Exception as e:  # noqa: BLE001
+            # On failure, show diagnostics then ensure clean teardown
+            sys.stderr.write(f"docker compose up failed: {e}\n")
+            try:
+                sys.stderr.write("\n== docker compose ps ==\n")
+                runner.run(subp_exec(*compose_cmd, *args, "ps", input=stdin, verbose=False))
+            except Exception:
+                pass
+            try:
+                sys.stderr.write("\n== docker compose logs (api) ==\n")
+                runner.run(
+                    subp_exec(
+                        *compose_cmd,
+                        *args,
+                        "logs",
+                        "langgraph-api",
+                        input=stdin,
+                        verbose=False,
+                    )
+                )
+            except Exception:
+                pass
+            finally:
+                try:
+                    runner.run(
+                        subp_exec(
+                            *compose_cmd,
+                            *args,
+                            "down",
+                            "-v",
+                            "--remove-orphans",
+                            input=stdin,
+                            verbose=False,
+                        )
+                    )
+                finally:
+                    raise
+
+        set("")
+        base_url = f"http://localhost:{port}"
+        ok_url = f"{base_url}/ok"
+        print(f"Waiting for {ok_url} to respond with 200...")
+        deadline = time.time() + 30
+        last_err: Exception | None = None
+        while time.time() < deadline:
+            try:
+                with request.urlopen(ok_url, timeout=2) as resp:
+                    if resp.status == 200:
+                        sys.stdout.write(
+                            f"""Ready!\n- API: {base_url}\n- /ok: 200 OK\n"""
+                        )
+                        sys.stdout.flush()
+                        break
+                    else:
+                        last_err = RuntimeError(f"Unexpected status: {resp.status}")
+                        print(f"Unexpected status: {resp.status}")
+            except error.URLError as e:
+                last_err = e
+            except Exception as e:  # noqa: BLE001
+                last_err = e
+            time.sleep(0.5)
+        else:
+            # Bring stack down before raising
+            args_down = [*args, "down", "-v", "--remove-orphans"]
+            try:
+                runner.run(
+                    subp_exec(
+                        *compose_cmd,
+                        *args_down,
+                        input=stdin,
+                        verbose=verbose,
+                    )
+                )
+            finally:
+                raise SystemExit(
+                    f"/ok did not return 202 within timeout. Last error: {last_err}"
+                )
+
+        # Clean up: bring compose stack down to free ports for next test
+        args_down = [*args, "down", "-v", "--remove-orphans"]
+        runner.run(
+            subp_exec(
+                *compose_cmd,
+                *args_down,
+                input=stdin,
+                verbose=verbose,
+            )
+        )
 
 
 if __name__ == "__main__":
@@ -110,6 +148,6 @@ if __name__ == "__main__":
     parser = argparse.ArgumentParser()
     parser.add_argument("-t", "--tag", type=str)
     parser.add_argument("-c", "--config", type=str, default="./langgraph.json")
-    parser.add_argument("-p", "--port", default=DEFAULT_PORT)
+    parser.add_argument("-p", "--port", type=int, default=DEFAULT_PORT)
     args = parser.parse_args()
     test(pathlib.Path(args.config), args.port, args.tag, verbose=True)

.github/workflows/_integration_test.yml

@@ -43,28 +43,43 @@ jobs:
       - name: Build and test service A
         if: steps.changed-files.outputs.all
         working-directory: libs/cli/examples
+        env:
+          LANGSMITH_API_KEY: ${{ secrets.LANGSMITH_API_KEY }}
         run: |
           # The build-arg isn't used; just testing that we accept other args
-          langgraph build -t langgraph-test-a  --base-image "langchain/langgraph-trial"
-          cp .env.example .envg
+          langgraph build -t langgraph-test-a
+          cp .env.example .env
+          if [ -n "${{ secrets.LANGSMITH_API_KEY }}" ]; then echo "LANGSMITH_API_KEY=${{ secrets.LANGSMITH_API_KEY }}" >> .env; fi
           timeout 60 python ../../../.github/scripts/run_langgraph_cli_test.py -c langgraph.json -t langgraph-test-a
       - name: Build and test service B
         if: steps.changed-files.outputs.all
         working-directory: libs/cli/examples/graphs
+        env:
+          LANGSMITH_API_KEY: ${{ secrets.LANGSMITH_API_KEY }}
         run: |
-          langgraph build -t langgraph-test-b  --base-image "langchain/langgraph-trial"
+          langgraph build -t langgraph-test-b
+          cp ../.env.example .env
+          if [ -n "${{ secrets.LANGSMITH_API_KEY }}" ]; then echo "LANGSMITH_API_KEY=${{ secrets.LANGSMITH_API_KEY }}" >> .env; fi
           timeout 60 python ../../../../.github/scripts/run_langgraph_cli_test.py -t langgraph-test-b
       - name: Build and test service C
         if: steps.changed-files.outputs.all
         working-directory: libs/cli/examples/graphs_reqs_a
+        env:
+          LANGSMITH_API_KEY: ${{ secrets.LANGSMITH_API_KEY }}
         run: |
-          langgraph build -t langgraph-test-c  --base-image "langchain/langgraph-trial"
+          langgraph build -t langgraph-test-c
+          cp ../.env.example .env
+          if [ -n "${{ secrets.LANGSMITH_API_KEY }}" ]; then echo "LANGSMITH_API_KEY=${{ secrets.LANGSMITH_API_KEY }}" >> .env; fi
           timeout 60 python ../../../../.github/scripts/run_langgraph_cli_test.py -t langgraph-test-c
       - name: Build and test service D
         if: steps.changed-files.outputs.all
         working-directory: libs/cli/examples/graphs_reqs_b
+        env:
+          LANGSMITH_API_KEY: ${{ secrets.LANGSMITH_API_KEY }}
         run: |
-          langgraph build -t langgraph-test-d  --base-image "langchain/langgraph-trial"
+          langgraph build -t langgraph-test-d
+          cp ../.env.example .env
+          if [ -n "${{ secrets.LANGSMITH_API_KEY }}" ]; then echo "LANGSMITH_API_KEY=${{ secrets.LANGSMITH_API_KEY }}" >> .env; fi
           timeout 60 python ../../../../.github/scripts/run_langgraph_cli_test.py -t langgraph-test-d
 
       - name: Build JS service

.github/workflows/_test.yml

@@ -17,7 +17,6 @@ jobs:
     strategy:
       matrix:
         python-version:
-          - "3.9"
           - "3.10"
           - "3.11"
           - "3.12"

.github/workflows/_test_langgraph.yml

@@ -12,7 +12,6 @@ jobs:
     strategy:
       matrix:
         python-version:
-          - "3.9"
           - "3.10"
           - "3.11"
           - "3.12"

.github/workflows/_test_release.yml

@@ -16,7 +16,6 @@ permissions:
 
 jobs:
   build:
-    if: github.ref == 'refs/heads/main'
     runs-on: ubuntu-latest
 
     outputs:

.github/workflows/ci.yml

@@ -3,7 +3,8 @@ name: CI
 
 on:
   push:
-    branches: [main, v1]
+    branches:
+      - main
   pull_request:
 
 permissions:
@@ -77,6 +78,7 @@ jobs:
             "libs/checkpoint-sqlite",
             "libs/checkpoint-postgres",
             "libs/prebuilt",
+            "libs/sdk-py",
           ]
     if: needs.changes.outputs.python == 'true' || needs.changes.outputs.deps == 'true'
     uses: ./.github/workflows/_test.yml

.github/workflows/release.yml

@@ -16,7 +16,6 @@ env:
 
 jobs:
   build:
-    if: github.ref == 'refs/heads/main'
     runs-on: ubuntu-latest
 
     outputs:
@@ -62,7 +61,13 @@ jobs:
         working-directory: ${{ inputs.working-directory }}
         run: |
           PKG_NAME=$(grep -m 1 "^name = " pyproject.toml | cut -d '"' -f 2)
-          VERSION=$(grep -m 1 "^version = " pyproject.toml | cut -d '"' -f 2)
+          if grep -q 'dynamic.*=.*\[.*"version".*\]' pyproject.toml; then
+            # handle dynamic versioning
+            DIR_NAME=$(echo "$PKG_NAME" | tr '-' '_')
+            VERSION=$(grep -m 1 '^__version__' "${DIR_NAME}/__init__.py" | cut -d '"' -f 2)
+          else
+            VERSION=$(grep -m 1 "^version = " pyproject.toml | cut -d '"' -f 2)
+          fi
           SHORT_PKG_NAME="$(echo "$PKG_NAME" | sed -e 's/langgraph//g' -e 's/-//g')"
           if [ -z $SHORT_PKG_NAME ]; then
             TAG="$VERSION"

.github/workflows/uv_lock_ugprade.yml

@@ -22,7 +22,7 @@ jobs:
         uses: astral-sh/setup-uv@v6
         with:
           # use minimum supported Python version
-          python-version: "3.9"
+          python-version: "3.10"
           enable-cache: true
           cache-suffix: "uv-lock-upgrade"
           

docs/Makefile

@@ -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
 

docs/_scripts/link_map.py

@@ -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

docs/_scripts/notebook_hooks.py

@@ -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
@@ -127,30 +127,85 @@ REDIRECT_MAP = {
     "how-tos/human_in_the_loop/breakpoints.md": "how-tos/human_in_the_loop/add-human-in-the-loop.md",
     "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",
-    # LGP migration-related redirects - once LG is also migrated, we can add a redirect for the whole site
-    "concepts/langgraph_platform.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_studio.md": "https://docs.langchain.com/langgraph-platform/langgraph-studio",
-    "cloud/how-tos/invoke_studio.md": "https://docs.langchain.com/langgraph-platform/invoke-studio",
+    "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",
-    "concepts/langgraph_self_hosted_data_plane.md": "https://docs.langchain.com/langgraph-platform/self-hosted-data-plane",
-    "concepts/langgraph_self_hosted_control_plane.md": "https://docs.langchain.com/langgraph-platform/self-hosted-control-plane",
-    "concepts/langgraph_standalone_container.md": "https://docs.langchain.com/langgraph-platform/standalone-container",
-    "cloud/deployment/self_hosted_data_plane.md": "https://docs.langchain.com/langgraph-platform/deploy-self-hosted-data-plane",
-    "cloud/deployment/self_hosted_control_plane.md": "https://docs.langchain.com/langgraph-platform/deploy-self-hosted-control-plane",
-    "cloud/deployment/standalone_container.md": "https://docs.langchain.com/langgraph-platform/deploy-standalone-container",
+    "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#standalone-server",
+    "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-standalone-server",
     "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/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",
+    "cloud/reference/env_var.md": "https://docs.langchain.com/langgraph-platform/env-var",
+    "troubleshooting/studio.md": "https://docs.langchain.com/langgraph-platform/troubleshooting-studio",
 }
 
 
@@ -506,16 +561,51 @@ def on_post_page(html: str, page: Page, config: MkDocsConfig) -> str:
 def on_post_build(config):
     use_directory_urls = config.get("use_directory_urls")
     for page_old, page_new in REDIRECT_MAP.items():
+        # Convert .ipynb to .md for path calculation
         page_old = page_old.replace(".ipynb", ".md")
-        page_new = page_new.replace(".ipynb", ".md")
-        page_new_before_hash, hash, suffix = page_new.partition("#")
-        old_html_path = File(page_old, "", "", use_directory_urls).dest_path.replace(
-            os.sep, "/"
-        )
-        new_html_path = File(page_new_before_hash, "", "", True).url
-        new_html_path = (
-            posixpath.relpath(new_html_path, start=posixpath.dirname(old_html_path))
-            + hash
-            + suffix
-        )
-        _write_html(config["site_dir"], old_html_path, new_html_path)
+        
+        # Calculate the HTML path for the old page (whether it exists or not)
+        if use_directory_urls:
+            # With directory URLs: /path/to/page/ becomes /path/to/page/index.html
+            if page_old.endswith(".md"):
+                old_html_path = page_old[:-3] + "/index.html"
+            else:
+                old_html_path = page_old + "/index.html"
+        else:
+            # Without directory URLs: /path/to/page.md becomes /path/to/page.html
+            if page_old.endswith(".md"):
+                old_html_path = page_old[:-3] + ".html"
+            else:
+                old_html_path = page_old + ".html"
+        
+        if isinstance(page_new, str) and page_new.startswith("http"):
+            # Handle external redirects
+            _write_html(config["site_dir"], old_html_path, page_new)
+        else:
+            # Handle internal redirects
+            page_new = page_new.replace(".ipynb", ".md")
+            page_new_before_hash, hash, suffix = page_new.partition("#")
+            
+            # Try to get the new path using File class, but fallback to manual calculation
+            try:
+                new_html_path = File(page_new_before_hash, "", "", True).url
+                new_html_path = (
+                    posixpath.relpath(new_html_path, start=posixpath.dirname(old_html_path))
+                    + hash
+                    + suffix
+                )
+            except:
+                # Fallback: calculate relative path manually
+                if use_directory_urls:
+                    if page_new_before_hash.endswith(".md"):
+                        new_html_path = page_new_before_hash[:-3] + "/"
+                    else:
+                        new_html_path = page_new_before_hash + "/"
+                else:
+                    if page_new_before_hash.endswith(".md"):
+                        new_html_path = page_new_before_hash[:-3] + ".html"
+                    else:
+                        new_html_path = page_new_before_hash + ".html"
+                new_html_path += hash + suffix
+            
+            _write_html(config["site_dir"], old_html_path, new_html_path)

docs/docs/agents/agents.md

@@ -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/).
 
 :::
 

docs/docs/agents/context.md

@@ -3,11 +3,11 @@
 **Context engineering** is the practice of building dynamic systems that provide the right information and tools, in the right format, so that an AI application can accomplish a task. Context can be characterized along two key dimensions:
 
 1. By **mutability**:
-   - **Static context**: Immutable data that doesn't change during execution (e.g., user metadata, database connections, tools)
-   - **Dynamic context**: Mutable data that evolves as the application runs (e.g., conversation history, intermediate results, tool call observations)
+    - **Static context**: Immutable data that doesn't change during execution (e.g., user metadata, database connections, tools)
+    - **Dynamic context**: Mutable data that evolves as the application runs (e.g., conversation history, intermediate results, tool call observations)
 2. By **lifetime**:
-   - **Runtime context**: Data scoped to a single run or invocation
-   - **Cross-conversation context**: Data that persists across multiple conversations or sessions
+    - **Runtime context**: Data scoped to a single run or invocation
+    - **Cross-conversation context**: Data that persists across multiple conversations or sessions
 
 !!! tip "Runtime context vs LLM context"
 

docs/docs/agents/models.md

@@ -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

docs/docs/agents/multi-agent.md

@@ -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
 

docs/docs/agents/overview.md

@@ -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");
 }

docs/docs/cloud/concepts/cron_jobs.md

@@ -0,0 +1,15 @@
+## Cron jobs
+
+There are many situations in which it is useful to run an assistant on a schedule. 
+
+For example, say that you're building an assistant that runs daily and sends an email summary
+of the day's news. You could use a cron job to run the assistant every day at 8:00 PM.
+
+LangGraph Platform supports cron jobs, which run on a user-defined schedule. The user specifies a schedule, an assistant, and some input. After that, on the specified schedule, the server will:
+
+- Create a new thread with the specified assistant
+- Send the specified input to that thread
+
+Note that this sends the same input to the thread every time. See the [how-to guide](../../cloud/how-tos/cron_jobs.md) for creating cron jobs.
+
+The LangGraph Platform API provides several endpoints for creating and managing cron jobs. See the [API reference](../../cloud/reference/api/api_ref.html#tag/runscreate/POST/threads/{thread_id}/runs/crons) for more details.

docs/docs/cloud/concepts/data_storage_and_privacy.md

@@ -0,0 +1,54 @@
+# Data Storage and Privacy
+
+This document describes how data is processed in the LangGraph CLI and the LangGraph Server for both the in-memory server (`langgraph dev`) and the local Docker server (`langgraph up`). It also describes what data is tracked when interacting with the hosted LangGraph Studio frontend.
+
+## CLI
+
+LangGraph **CLI** is the command-line interface for building and running LangGraph applications; see the [CLI guide](../../concepts/langgraph_cli.md) to learn more.
+
+By default, calls to most CLI commands log a single analytics event upon invocation. This helps us better prioritize improvements to the CLI experience. Each telemetry event contains the calling process's OS, OS version, Python version, the CLI version, the command name (`dev`, `up`, `run`, etc.), and booleans representing whether a flag was passed to the command. You can see the full analytics logic [here](https://github.com/langchain-ai/langgraph/blob/main/libs/cli/langgraph_cli/analytics.py). 
+
+You can disable all CLI telemetry by setting `LANGGRAPH_CLI_NO_ANALYTICS=1`.
+
+## LangGraph Server (in-memory & docker)
+
+The [LangGraph Server](../../concepts/langgraph_server.md) provides a durable execution runtime that relies on persisting checkpoints of your application state, long-term memories, thread metadata, assistants, and similar resources to the local file system or a database. Unless you have deliberately customized the storage location, this information is either written to local disk (for `langgraph dev`) or a PostgreSQL database (for `langgraph up` and in all deployments).
+
+### LangSmith Tracing
+
+When running the LangGraph server (either in-memory or in Docker), LangSmith tracing may be enabled to facilitate faster debugging and offer observability of graph state and LLM prompts in production. You can always disable tracing by setting `LANGSMITH_TRACING=false` in your server's runtime environment.
+
+### In-memory development server (`langgraph dev`)
+
+`langgraph dev` runs an [in-memory development server](../../tutorials/langgraph-platform/local-server.md) as a single Python process, designed for quick development and testing. It saves all checkpointing and memory data to disk within a `.langgraph_api` directory in the current working directory. Apart from the telemetry data described in the [CLI](#cli) section, no data leaves the machine unless you have enabled tracing or your graph code explicitly contacts an external service.
+
+### Standalone Container (`langgraph up`)
+
+`langgraph up` builds your local package into a Docker image and runs the server as a [standalone container](../../concepts/deployment_options.md#standalone-container) consisting of three containers: the API server, a PostgreSQL container, and a Redis container. All persistent data (checkpoints, assistants, etc.) are stored in the PostgreSQL database. Redis is used as a pubsub connection for real-time streaming of events. You can encrypt all checkpoints before saving to the database by setting a valid `LANGGRAPH_AES_KEY` environment variable. You can also specify [TTLs](../../how-tos/ttl/configure_ttl.md) for checkpoints and cross-thread memories in `langgraph.json` to control how long data is stored. All persisted threads, memories, and other data can be deleted via the relevant API endpoints.
+
+Additional API calls are made to confirm that the server has a valid license and to track the number of executed runs and tasks. Periodically, the API server validates the provided license key (or API key).
+
+If you've disabled [tracing](#langsmith-tracing), no user data is persisted externally unless your graph code explicitly contacts an external service.
+
+## Studio
+
+[LangGraph Studio](../../concepts/langgraph_studio.md) is a graphical interface for interacting with your LangGraph server. It does not persist any private data (the data you send to your server is not sent to LangSmith). Though the studio interface is served at [smith.langchain.com](https://smith.langchain.com), it is run in your browser and connects directly to your local LangGraph server so that no data needs to be sent to LangSmith.
+
+If you are logged in, LangSmith does collect some usage analytics to help improve studio's user experience. This includes:
+
+- Page visits and navigation patterns
+- User actions (button clicks)
+- Browser type and version
+- Screen resolution and viewport size
+
+Importantly, no application data or code (or other sensitive configuration details) are collected. All of that is stored in the persistence layer of your LangGraph server. When using Studio anonymously, no account creation is required and usage analytics are not collected.
+
+## Quick reference
+
+In summary, you can opt-out of server-side telemetry by turning off CLI analytics and disabling tracing.
+
+| Variable                       | Purpose                   | Default                          |
+| ------------------------------ | ------------------------- | -------------------------------- |
+| `LANGGRAPH_CLI_NO_ANALYTICS=1` | Disable CLI analytics     | Analytics enabled                |
+| `LANGSMITH_API_KEY`            | Enable LangSmith tracing  | Tracing disabled                 |
+| `LANGSMITH_TRACING=false`      | Disable LangSmith tracing | Depends on environment           |

docs/docs/cloud/concepts/webhooks.md

@@ -0,0 +1,7 @@
+# Webhooks
+
+Webhooks enable event-driven communication from your LangGraph Platform application to external services. For example, you may want to issue an update to a separate service once an API call to LangGraph Platform has finished running.
+
+Many LangGraph Platform endpoints accept a `webhook` parameter. If this parameter is specified by an endpoint that can accept POST requests, LangGraph Platform will send a request at the completion of a run.
+
+See the corresponding [how-to guide](../../cloud/how-tos/webhooks.md) for more detail.

docs/docs/cloud/deployment/cloud.md

@@ -0,0 +1,128 @@
+# How to Deploy to Cloud SaaS
+
+Before deploying, review the [conceptual guide for the Cloud SaaS](../../concepts/langgraph_cloud.md) deployment option.
+
+## Prerequisites
+
+1. LangGraph Platform applications are deployed from GitHub repositories. Configure and upload a LangGraph Platform application to a GitHub repository in order to deploy it to LangGraph Platform.
+1. [Verify that the LangGraph API runs locally](../../tutorials/langgraph-platform/local-server.md). If the API does not run successfully (i.e. `langgraph dev`), deploying to LangGraph Platform will fail as well.
+
+## Create New Deployment
+
+Starting from the <a href="https://smith.langchain.com/" target="_blank">LangSmith UI</a>...
+
+1. In the left-hand navigation panel, select `LangGraph Platform`. The `LangGraph Platform` view contains a list of existing LangGraph Platform deployments.
+1. In the top-right corner, select `+ New Deployment` to create a new deployment.
+1. In the `Create New Deployment` panel, fill out the required fields.
+    1. `Deployment details`
+        1. Select `Import from GitHub` and follow the GitHub OAuth workflow to install and authorize LangChain's `hosted-langserve` GitHub app to access the selected repositories. After installation is complete, return to the `Create New Deployment` panel and select the GitHub repository to deploy from the dropdown menu. **Note**: The GitHub user installing LangChain's `hosted-langserve` GitHub app must be an [owner](https://docs.github.com/en/organizations/managing-peoples-access-to-your-organization-with-roles/roles-in-an-organization#organization-owners) of the organization or account.
+        1. Specify a name for the deployment.
+        1. Specify the desired `Git Branch`. A deployment is linked to a branch. When a new revision is created, code for the linked branch will be deployed. The branch can be updated later in the [Deployment Settings](#deployment-settings).
+        1. Specify the full path to the [LangGraph API config file](../reference/cli.md#configuration-file) including the file name. For example, if the file `langgraph.json` is in the root of the repository, simply specify `langgraph.json`.
+        1. Check/uncheck checkbox to `Automatically update deployment on push to branch`. If checked, the deployment will automatically be updated when changes are pushed to the specified `Git Branch`. This setting can be enabled/disabled later in the [Deployment Settings](#deployment-settings).
+    1. Select the desired `Deployment Type`.
+        1. `Development` deployments are meant for non-production use cases and are provisioned with minimal resources.
+        1. `Production` deployments can serve up to 500 requests/second and are provisioned with highly available storage with automatic backups.
+    1. Determine if the deployment should be `Shareable through LangGraph Studio`.
+        1. If unchecked, the deployment will only be accessible with a valid LangSmith API key for the workspace.
+        1. If checked, the deployment will be accessible through LangGraph Studio to any LangSmith user. A direct URL to LangGraph Studio for the deployment will be provided to share with other LangSmith users.
+    1. Specify `Environment Variables` and secrets. See the [Environment Variables reference](../reference/env_var.md) to configure additional variables for the deployment.
+        1. Sensitive values such as API keys (e.g. `OPENAI_API_KEY`) should be specified as secrets.
+        1. Additional non-secret environment variables can be specified as well.
+    1. A new LangSmith `Tracing Project` is automatically created with the same name as the deployment.
+1. In the top-right corner, select `Submit`. After a few seconds, the `Deployment` view appears and the new deployment will be queued for provisioning.
+
+## Create New Revision
+
+When [creating a new deployment](#create-new-deployment), a new revision is created by default. Subsequent revisions can be created to deploy new code changes.
+
+Starting from the <a href="https://smith.langchain.com/" target="_blank">LangSmith UI</a>...
+
+1. In the left-hand navigation panel, select `LangGraph Platform`. The `LangGraph Platform` view contains a list of existing LangGraph Platform deployments.
+1. Select an existing deployment to create a new revision for.
+1. In the `Deployment` view, in the top-right corner, select `+ New Revision`.
+1. In the `New Revision` modal, fill out the required fields.
+    1. Specify the full path to the [LangGraph API config file](../reference/cli.md#configuration-file) including the file name. For example, if the file `langgraph.json` is in the root of the repository, simply specify `langgraph.json`.
+    1. Determine if the deployment should be `Shareable through LangGraph Studio`.
+        1. If unchecked, the deployment will only be accessible with a valid LangSmith API key for the workspace.
+        1. If checked, the deployment will be accessible through LangGraph Studio to any LangSmith user. A direct URL to LangGraph Studio for the deployment will be provided to share with other LangSmith users.
+    1. Specify `Environment Variables` and secrets. Existing secrets and environment variables are prepopulated. See the [Environment Variables reference](../reference/env_var.md) to configure additional variables for the revision.
+        1. Add new secrets or environment variables.
+        1. Remove existing secrets or environment variables.
+        1. Update the value of existing secrets or environment variables.
+1. Select `Submit`. After a few seconds, the `New Revision` modal will close and the new revision will be queued for deployment.
+
+## View Build and Server Logs
+
+Build and server logs are available for each revision.
+
+Starting from the `LangGraph Platform` view...
+
+1. Select the desired revision from the `Revisions` table. A panel slides open from the right-hand side and the `Build` tab is selected by default, which displays build logs for the revision.
+1. In the panel, select the `Server` tab to view server logs for the revision. Server logs are only available after a revision has been deployed.
+1. Within the `Server` tab, adjust the date/time range picker as needed. By default, the date/time range picker is set to the `Last 7 days`.
+
+## View Deployment Metrics
+
+Starting from the <a href="https://smith.langchain.com/" target="_blank">LangSmith UI</a>...
+
+1. In the left-hand navigation panel, select `LangGraph Platform`. The `LangGraph Platform` view contains a list of existing LangGraph Platform deployments.
+1. Select an existing deployment to monitor.
+1. Select the `Monitoring` tab to view the deployment metrics. See a list of [all available metrics](../../concepts/langgraph_control_plane.md#monitoring).
+1. Within the `Monitoring` tab, use the date/time range picker as needed. By default, the date/time range picker is set to the `Last 15 minutes`.
+
+## Interrupt Revision
+
+Interrupting a revision will stop deployment of the revision.
+
+!!! warning "Undefined Behavior"
+    Interrupted revisions have undefined behavior. This is only useful if you need to deploy a new revision and you already have a revision "stuck" in progress. In the future, this feature may be removed.
+
+Starting from the `LangGraph Platform` view...
+
+1. Select the menu icon (three dots) on the right-hand side of the row for the desired revision from the `Revisions` table.
+1. Select `Interrupt` from the menu.
+1. A modal will appear. Review the confirmation message. Select `Interrupt revision`.
+
+## Delete Deployment
+
+Starting from the <a href="https://smith.langchain.com/" target="_blank">LangSmith UI</a>...
+
+1. In the left-hand navigation panel, select `LangGraph Platform`. The `LangGraph Platform` view contains a list of existing LangGraph Platform deployments.
+1. Select the menu icon (three dots) on the right-hand side of the row for the desired deployment and select `Delete`.
+1. A `Confirmation` modal will appear. Select `Delete`.
+
+## Deployment Settings
+
+Starting from the `LangGraph Platform` view...
+
+1. In the top-right corner, select the gear icon (`Deployment Settings`).
+1. Update the `Git Branch` to the desired branch.
+1. Check/uncheck checkbox to `Automatically update deployment on push to branch`.
+1. Branch creation/deletion and tag creation/deletion events will not trigger an update. Only pushes to an existing branch will trigger an update.
+1. Pushes in quick succession to a branch will queue subsequent updates. Once a build completes, the most recent commit will begin building and the other queued builds will be skipped.
+
+## Add or Remove GitHub Repositories
+
+After installing and authorizing LangChain's `hosted-langserve` GitHub app, repository access for the app can be modified to add new repositories or remove existing repositories. If a new repository is created, it may need to be added explicitly.
+
+1. From the GitHub profile, navigate to `Settings` > `Applications` > `hosted-langserve` > click `Configure`.
+1. Under `Repository access`, select `All repositories` or `Only select repositories`. If `Only select repositories` is selected, new repositories must be explicitly added.
+1. Click `Save`.
+1. When creating a new deployment, the list of GitHub repositories in the dropdown menu will be updated to reflect the repository access changes.
+
+## Whitelisting IP Addresses
+
+All traffic from `LangGraph Platform` deployments created after January 6th 2025 will come through a NAT gateway.
+This NAT gateway will have several static ip addresses depending on the region you are deploying in. Refer to the table below for the list of IP addresses to whitelist:
+
+| US             | EU              |
+|----------------|-----------------|
+| 35.197.29.146  | 34.90.213.236   |
+| 34.145.102.123 | 34.13.244.114   |
+| 34.169.45.153  | 34.32.180.189   |
+| 34.82.222.17   | 34.34.69.108    |
+| 35.227.171.135 | 34.32.145.240   | 
+| 34.169.88.30   | 34.90.157.44    |
+| 34.19.93.202   | 34.141.242.180  |
+| 34.19.34.50    | 34.32.141.108   |

docs/docs/cloud/deployment/custom_docker.md

@@ -0,0 +1,19 @@
+# How to customize Dockerfile
+
+Users can add an array of additional lines to add to the Dockerfile following the import from the parent LangGraph image. In order to do this, you simply need to modify your `langgraph.json` file by passing in the commands you want run to the `dockerfile_lines` key. For example, if we wanted to use `Pillow` in our graph you would need to add the following dependencies:
+
+```
+{
+    "dependencies": ["."],
+    "graphs": {
+        "openai_agent": "./openai_agent.py:agent",
+    },
+    "env": "./.env",
+    "dockerfile_lines": [
+        "RUN apt-get update && apt-get install -y libjpeg-dev zlib1g-dev libpng-dev",
+        "RUN pip install Pillow"
+    ]
+}
+```
+
+This would install the system packages required to use Pillow if we were working with `jpeg` or `png` image formats. 

docs/docs/cloud/deployment/egress.md

@@ -0,0 +1,119 @@
+# Egress for Subscription Metrics and Operational Metadata
+
+> **Important: Self Hosted Only** 
+> This section only applies to customers who are not running in offline mode and assumes you are using a self-hosted LangGraph Platform instance.
+> This does not apply to SaaS or Hybrid deployments.
+
+Self-Hosted LangGraph Platform instances store all information locally and will never send sensitive information outside of your network. We currently only track platform usage for billing purposes according to the entitlements in your order. In order to better remotely support our customers, we do require egress to `https://beacon.langchain.com`.
+
+In the future, we will be introducing support diagnostics to help us ensure that the LangGraph Platform is running at an optimal level within your environment.
+
+> **Warning**  
+> **This will require egress to `https://beacon.langchain.com` from your network.**
+> **If using an API key, you will also need to allow egress to `https://api.smith.langchain.com` or `https://eu.api.smith.langchain.com` for API key verification.**
+
+Generally, data that we send to Beacon can be categorized as follows:
+
+- **Subscription Metrics**
+  - Subscription metrics are used to determine level of access and utilization of LangSmith. This includes, but are not limited to:
+    - Nodes Executed
+    - Runs Executed
+    - License Key Verification
+- **Operational Metadata**
+  - This metadata will contain and collect the above subscription metrics to assist with remote support, allowing the LangChain team to diagnose and troubleshoot performance issues more effectively and proactively.
+
+## Example Payloads
+
+In an effort to maximize transparency, we provide sample payloads here:
+
+### License Verification (If using an Enterprise License)
+
+**Endpoint:**
+
+`POST beacon.langchain.com/v1/beacon/verify`
+
+**Request:**
+
+```json
+{
+  "license": "<YOUR_LICENSE_KEY>"
+}
+```
+
+**Response:**
+
+```json
+{
+  "token": "Valid JWT" // Short-lived JWT token to avoid repeated license checks
+}
+```
+
+### Api Key Verification (If using a LangSmith API Key)
+
+**Endpoint:**
+`POST api.smith.langchain.com/auth`
+
+**Request:**
+
+```json
+"Headers": {
+  X-Api-Key: <YOUR_API_KEY>
+}
+```
+
+**Response:**
+
+```json
+{
+  "org_config": {
+    "org_id": "3a1c2b6f-4430-4b92-8a5b-79b8b567bbc1",
+    ... // Additional organization details
+  }
+}
+```
+
+### Usage Reporting
+
+**Endpoint:**
+
+`POST beacon.langchain.com/v1/metadata/submit`
+
+**Request:**
+
+```json
+{
+  "license": "<YOUR_LICENSE_KEY>",
+  "from_timestamp": "2025-01-06T09:00:00Z",
+  "to_timestamp": "2025-01-06T10:00:00Z",
+  "tags": {
+    "langgraph.python.version": "0.1.0",
+    "langgraph_api.version": "0.2.0",
+    "langgraph.platform.revision": "abc123",
+    "langgraph.platform.variant": "standard",
+    "langgraph.platform.host": "host-1",
+    "langgraph.platform.tenant_id": "3a1c2b6f-4430-4b92-8a5b-79b8b567bbc1",
+    "langgraph.platform.project_id": "c5b5f53a-4716-4326-8967-d4f7f7799735",
+    "langgraph.platform.plan": "enterprise",
+    "user_app.uses_indexing": "true",
+    "user_app.uses_custom_app": "false",
+    "user_app.uses_custom_auth": "true",
+    "user_app.uses_thread_ttl": "true",
+    "user_app.uses_store_ttl": "false"
+  },
+  "measures": {
+    "langgraph.platform.runs": 150,
+    "langgraph.platform.nodes": 450
+  },
+  "logs": []
+}
+```
+
+**Response:**
+
+```json
+"204 No Content"
+```
+
+## Our Commitment
+
+LangChain will not store any sensitive information in the Subscription Metrics or Operational Metadata. Any data collected will not be shared with a third party. If you have any concerns about the data being sent, please reach out to your account team.

docs/docs/cloud/deployment/graph_rebuild.md

@@ -0,0 +1,147 @@
+# Rebuild Graph at Runtime
+
+You might need to rebuild your graph with a different configuration for a new run. For example, you might need to use a different graph state or graph structure depending on the config. This guide shows how you can do this.
+
+!!! note "Note"
+    In most cases, customizing behavior based on the config should be handled by a single graph where each node can read a config and change its behavior based on it
+
+## Prerequisites
+
+Make sure to check out [this how-to guide](./setup.md) on setting up your app for deployment first.
+
+## Define graphs
+
+Let's say you have an app with a simple graph that calls an LLM and returns the response to the user. The app file directory looks like the following:
+
+```
+my-app/
+|-- requirements.txt
+|-- .env
+|-- openai_agent.py     # code for your graph
+```
+
+where the graph is defined in `openai_agent.py`. 
+
+### No rebuild
+
+In the standard LangGraph API configuration, the server uses the compiled graph instance that's defined at the top level of `openai_agent.py`, which looks like the following:
+
+```python
+from langchain_openai import ChatOpenAI
+from langgraph.graph import END, START, MessageGraph
+
+model = ChatOpenAI(temperature=0)
+
+graph_workflow = MessageGraph()
+
+graph_workflow.add_node("agent", model)
+graph_workflow.add_edge("agent", END)
+graph_workflow.add_edge(START, "agent")
+
+agent = graph_workflow.compile()
+```
+
+To make the server aware of your graph, you need to specify a path to the variable that contains the `CompiledStateGraph` instance in your LangGraph API configuration (`langgraph.json`), e.g.:
+
+```
+{
+    "dependencies": ["."],
+    "graphs": {
+        "openai_agent": "./openai_agent.py:agent",
+    },
+    "env": "./.env"
+}
+```
+
+### Rebuild
+
+To make your graph rebuild on each new run with custom configuration, you need to rewrite `openai_agent.py` to instead provide a _function_ that takes a config and returns a graph (or compiled graph) instance. Let's say we want to return our existing graph for user ID '1', and a tool-calling agent for other users. We can modify `openai_agent.py` as follows:
+
+```python
+from typing import Annotated
+from typing_extensions import TypedDict
+from langchain_openai import ChatOpenAI
+from langgraph.graph import END, START, MessageGraph
+from langgraph.graph.state import StateGraph
+from langgraph.graph.message import add_messages
+from langgraph.prebuilt import ToolNode
+from langchain_core.tools import tool
+from langchain_core.messages import BaseMessage
+from langchain_core.runnables import RunnableConfig
+
+
+class State(TypedDict):
+    messages: Annotated[list[BaseMessage], add_messages]
+
+
+model = ChatOpenAI(temperature=0)
+
+def make_default_graph():
+    """Make a simple LLM agent"""
+    graph_workflow = StateGraph(State)
+    def call_model(state):
+        return {"messages": [model.invoke(state["messages"])]}
+
+    graph_workflow.add_node("agent", call_model)
+    graph_workflow.add_edge("agent", END)
+    graph_workflow.add_edge(START, "agent")
+
+    agent = graph_workflow.compile()
+    return agent
+
+
+def make_alternative_graph():
+    """Make a tool-calling agent"""
+
+    @tool
+    def add(a: float, b: float):
+        """Adds two numbers."""
+        return a + b
+
+    tool_node = ToolNode([add])
+    model_with_tools = model.bind_tools([add])
+    def call_model(state):
+        return {"messages": [model_with_tools.invoke(state["messages"])]}
+
+    def should_continue(state: State):
+        if state["messages"][-1].tool_calls:
+            return "tools"
+        else:
+            return END
+
+    graph_workflow = StateGraph(State)
+
+    graph_workflow.add_node("agent", call_model)
+    graph_workflow.add_node("tools", tool_node)
+    graph_workflow.add_edge("tools", "agent")
+    graph_workflow.add_edge(START, "agent")
+    graph_workflow.add_conditional_edges("agent", should_continue)
+
+    agent = graph_workflow.compile()
+    return agent
+
+
+# this is the graph making function that will decide which graph to
+# build based on the provided config
+def make_graph(config: RunnableConfig):
+    user_id = config.get("configurable", {}).get("user_id")
+    # route to different graph state / structure based on the user ID
+    if user_id == "1":
+        return make_default_graph()
+    else:
+        return make_alternative_graph()
+```
+
+Finally, you need to specify the path to your graph-making function (`make_graph`) in `langgraph.json`:
+
+```
+{
+    "dependencies": ["."],
+    "graphs": {
+        "openai_agent": "./openai_agent.py:make_graph",
+    },
+    "env": "./.env"
+}
+```
+
+See more info on LangGraph API configuration file [here](../reference/cli.md#configuration-file)

docs/docs/cloud/deployment/self_hosted_control_plane.md

@@ -0,0 +1,53 @@
+# How to Deploy Self-Hosted Control Plane
+
+Before deploying, review the [conceptual guide for the Self-Hosted Control Plane](../../concepts/langgraph_self_hosted_control_plane.md) deployment option.
+
+!!! info "Important"
+    The Self-Hosted Control Plane deployment option requires an [Enterprise](../../concepts/plans.md) plan.
+
+## Prerequisites
+
+1. You are using Kubernetes.
+1. You have self-hosted LangSmith deployed.
+1. Use the [LangGraph CLI](../../concepts/langgraph_cli.md) to [test your application locally](../../tutorials/langgraph-platform/local-server.md).
+1. Use the [LangGraph CLI](../../concepts/langgraph_cli.md) to build a Docker image (i.e. `langgraph build`) and push it to a registry your Kubernetes cluster has access to.
+1. `KEDA` is installed on your cluster.
+
+         helm repo add kedacore https://kedacore.github.io/charts 
+         helm install keda kedacore/keda --namespace keda --create-namespace
+1. Ingress Configuration
+    1. You must set up an ingress for your LangSmith instance. All agents will be deployed as Kubernetes services behind this ingress.
+    1. You can use this guide to [set up an ingress](https://docs.smith.langchain.com/self_hosting/configuration/ingress) for your instance.
+1. You have slack space in your cluster for multiple deployments. `Cluster-Autoscaler` is recommended to automatically provision new nodes.
+1. A valid Dynamic PV provisioner or PVs available on your cluster. You can verify this by running:
+
+        kubectl get storageclass
+
+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.
+
+## Setup
+
+1. As part of configuring your Self-Hosted LangSmith instance, you enable the `langgraphPlatform` option. This will provision a few key resources.
+    1. `listener`: This is a service that listens to the [control plane](../../concepts/langgraph_control_plane.md) for changes to your deployments and creates/updates downstream CRDs.
+    1. `LangGraphPlatform CRD`: A CRD for LangGraph Platform deployments. This contains the spec for managing an instance of a LangGraph platform deployment.
+    1. `operator`: This operator handles changes to your LangGraph Platform CRDs.
+    1. `host-backend`: This is the [control plane](../../concepts/langgraph_control_plane.md).
+1. Two additional images will be used by the chart. Use the images that are specified in the latest release.
+
+        hostBackendImage:
+          repository: "docker.io/langchain/hosted-langserve-backend"
+          pullPolicy: IfNotPresent
+        operatorImage:
+          repository: "docker.io/langchain/langgraph-operator"
+          pullPolicy: IfNotPresent
+
+1. In your config file for langsmith (usually `langsmith_config.yaml`, enable the `langgraphPlatform` option. Note that you must also have a valid ingress setup:
+
+        config:
+          langgraphPlatform:
+            enabled: true
+            langgraphPlatformLicenseKey: "YOUR_LANGGRAPH_PLATFORM_LICENSE_KEY"
+1. In your `values.yaml` file, configure the `hostBackendImage` and `operatorImage` options (if you need to mirror images)
+
+1. You can also configure base templates for your agents by overriding the base templates [here](https://github.com/langchain-ai/helm/blob/main/charts/langsmith/values.yaml#L898).
+1. You create a deployment from the [control plane UI](../../concepts/langgraph_control_plane.md#control-plane-ui).

docs/docs/cloud/deployment/self_hosted_data_plane.md

@@ -0,0 +1,59 @@
+# How to Deploy Self-Hosted Data Plane
+
+Before deploying, review the [conceptual guide for the Self-Hosted Data Plane](../../concepts/langgraph_self_hosted_data_plane.md) deployment option.
+
+!!! info "Important"
+    The Self-Hosted Data Plane deployment option requires an [Enterprise](../../concepts/plans.md) plan.
+
+## Prerequisites
+
+1. Use the [LangGraph CLI](../../concepts/langgraph_cli.md) to [test your application locally](../../tutorials/langgraph-platform/local-server.md).
+1. Use the [LangGraph CLI](../../concepts/langgraph_cli.md) to build a Docker image (i.e. `langgraph build`) and push it to a registry your Kubernetes cluster or Amazon ECS cluster has access to.
+
+## Kubernetes
+
+### Prerequisites
+1. `KEDA` is installed on your cluster.
+
+        helm repo add kedacore https://kedacore.github.io/charts
+        helm install keda kedacore/keda --namespace keda --create-namespace
+
+1. A valid `Ingress` controller is installed on your cluster.
+1. You have slack space in your cluster for multiple deployments. `Cluster-Autoscaler` is recommended to automatically provision new nodes.
+1. You will need to enable egress to two control plane URLs. The listener polls these endpoints for deployments:
+
+        https://api.host.langchain.com
+        https://api.smith.langchain.com
+
+### Setup
+
+1. You give us your LangSmith organization ID. We will enable the Self-Hosted Data Plane for your organization.
+1. We provide you a [Helm chart](https://github.com/langchain-ai/helm/tree/main/charts/langgraph-dataplane) which you run to setup your Kubernetes cluster. This chart contains a few important components.
+    1. `langgraph-listener`: This is a service that listens to LangChain's [control plane](../../concepts/langgraph_control_plane.md) for changes to your deployments and creates/updates downstream CRDs.
+    1. `LangGraphPlatform CRD`: A CRD for LangGraph Platform deployments. This contains the spec for managing an instance of a LangGraph Platform deployment.
+    1. `langgraph-platform-operator`: This operator handles changes to your LangGraph Platform CRDs.
+1. Configure your `langgraph-dataplane-values.yaml` file.
+
+        config:
+          langsmithApiKey: "" # API Key of your Workspace
+          langsmithWorkspaceId: "" # Workspace ID
+          hostBackendUrl: "https://api.host.langchain.com" # Only override this if on EU
+          smithBackendUrl: "https://api.smith.langchain.com" # Only override this if on EU
+
+1. Deploy `langgraph-dataplane` Helm chart.
+
+        helm repo add langchain https://langchain-ai.github.io/helm/
+        helm repo update
+        helm upgrade -i langgraph-dataplane langchain/langgraph-dataplane --values langgraph-dataplane-values.yaml
+
+1. If successful, you will see two services start up in your namespace.
+
+        NAME                                          READY   STATUS              RESTARTS   AGE
+        langgraph-dataplane-listener-7fccd788-wn2dx   0/1     Running             0          9s
+        langgraph-dataplane-redis-0                   0/1     ContainerCreating   0          9s
+
+1. You create a deployment from the [control plane UI](../../concepts/langgraph_control_plane.md#control-plane-ui).
+
+## Amazon ECS
+
+Coming soon!

docs/docs/cloud/deployment/semantic_search.md

@@ -0,0 +1,123 @@
+# How to add semantic search to your LangGraph deployment
+
+This guide explains how to add semantic search to your LangGraph deployment's cross-thread [store](../../concepts/persistence.md#memory-store), so that your agent can search for memories and other documents by semantic similarity.
+
+## Prerequisites
+
+- A LangGraph deployment (see [how to deploy](setup_pyproject.md))
+- API keys for your embedding provider (in this case, OpenAI)
+- `langchain >= 0.3.8` (if you specify using the string format below)
+
+## Steps
+
+1. Update your `langgraph.json` configuration file to include the store configuration:
+
+```json
+{
+    ...
+    "store": {
+        "index": {
+            "embed": "openai:text-embedding-3-small",
+            "dims": 1536,
+            "fields": ["$"]
+        }
+    }
+}
+```
+
+This configuration:
+
+- Uses OpenAI's text-embedding-3-small model for generating embeddings
+- Sets the embedding dimension to 1536 (matching the model's output)
+- Indexes all fields in your stored data (`["$"]` means index everything, or specify specific fields like `["text", "metadata.title"]`)
+
+2. To use the string embedding format above, make sure your dependencies include `langchain >= 0.3.8`:
+
+```toml
+# In pyproject.toml
+[project]
+dependencies = [
+    "langchain>=0.3.8"
+]
+```
+
+Or if using requirements.txt:
+
+```
+langchain>=0.3.8
+```
+
+## Usage
+
+Once configured, you can use semantic search in your LangGraph nodes. The store requires a namespace tuple to organize memories:
+
+```python
+def search_memory(state: State, *, store: BaseStore):
+    # Search the store using semantic similarity
+    # The namespace tuple helps organize different types of memories
+    # e.g., ("user_facts", "preferences") or ("conversation", "summaries")
+    results = store.search(
+        namespace=("memory", "facts"),  # Organize memories by type
+        query="your search query",
+        limit=3  # number of results to return
+    )
+    return results
+```
+
+## Custom Embeddings
+
+If you want to use custom embeddings, you can pass a path to a custom embedding function:
+
+```json
+{
+    ...
+    "store": {
+        "index": {
+            "embed": "path/to/embedding_function.py:embed",
+            "dims": 1536,
+            "fields": ["$"]
+        }
+    }
+}
+```
+
+The deployment will look for the function in the specified path. The function must be async and accept a list of strings:
+
+```python
+# path/to/embedding_function.py
+from openai import AsyncOpenAI
+
+client = AsyncOpenAI()
+
+async def aembed_texts(texts: list[str]) -> list[list[float]]:
+    """Custom embedding function that must:
+    1. Be async
+    2. Accept a list of strings
+    3. Return a list of float arrays (embeddings)
+    """
+    response = await client.embeddings.create(
+        model="text-embedding-3-small",
+        input=texts
+    )
+    return [e.embedding for e in response.data]
+```
+
+## Querying via the API
+
+You can also query the store using the LangGraph SDK. Since the SDK uses async operations:
+
+```python
+from langgraph_sdk import get_client
+
+async def search_store():
+    client = get_client()
+    results = await client.store.search_items(
+        ("memory", "facts"),
+        query="your search query",
+        limit=3  # number of results to return
+    )
+    return results
+
+# Use in an async context
+results = await search_store()
+```

docs/docs/cloud/deployment/setup.md

@@ -0,0 +1,188 @@
+# How to Set Up a LangGraph Application with requirements.txt
+
+A LangGraph application must be configured with a [LangGraph configuration file](../reference/cli.md#configuration-file) in order to be deployed to LangGraph Platform (or to be self-hosted). This how-to guide discusses the basic steps to setup a LangGraph application for deployment using `requirements.txt` to specify project dependencies.
+
+This walkthrough is based on [this repository](https://github.com/langchain-ai/langgraph-example), which you can play around with to learn more about how to setup your LangGraph application for deployment.
+
+!!! tip "Setup with pyproject.toml"
+    If you prefer using poetry for dependency management, check out [this how-to guide](./setup_pyproject.md) on using `pyproject.toml` for LangGraph Platform.
+
+!!! tip "Setup with a Monorepo"
+    If you are interested in deploying a graph located inside a monorepo, take a look at [this repository](https://github.com/langchain-ai/langgraph-example-monorepo) for an example of how to do so.
+
+The final repository structure will look something like this:
+
+```bash
+my-app/
+├── my_agent # all project code lies within here
+│   ├── utils # utilities for your graph
+│   │   ├── __init__.py
+│   │   ├── tools.py # tools for your graph
+│   │   ├── nodes.py # node functions for you graph
+│   │   └── state.py # state definition of your graph
+│   ├── requirements.txt # package dependencies
+│   ├── __init__.py
+│   └── agent.py # code for constructing your graph
+├── .env # environment variables
+└── langgraph.json # configuration file for LangGraph
+```
+
+After each step, an example file directory is provided to demonstrate how code can be organized.
+
+## Specify Dependencies
+
+Dependencies can optionally be specified in one of the following files: `pyproject.toml`, `setup.py`, or `requirements.txt`. If none of these files is created, then dependencies can be specified later in the [LangGraph configuration file](#create-langgraph-configuration-file).
+
+The dependencies below will be included in the image, you can also use them in your code, as long as with a compatible version range:
+
+```
+langgraph>=0.3.27
+langgraph-sdk>=0.1.66
+langgraph-checkpoint>=2.0.23
+langchain-core>=0.2.38
+langsmith>=0.1.63
+orjson>=3.9.7,<3.10.17
+httpx>=0.25.0
+tenacity>=8.0.0
+uvicorn>=0.26.0
+sse-starlette>=2.1.0,<2.2.0
+uvloop>=0.18.0
+httptools>=0.5.0
+jsonschema-rs>=0.20.0
+structlog>=24.1.0
+cloudpickle>=3.0.0
+```
+
+Example `requirements.txt` file:
+
+```
+langgraph
+langchain_anthropic
+tavily-python
+langchain_community
+langchain_openai
+
+```
+
+Example file directory:
+
+```bash
+my-app/
+├── my_agent # all project code lies within here
+│   └── requirements.txt # package dependencies
+```
+
+## Specify Environment Variables
+
+Environment variables can optionally be specified in a file (e.g. `.env`). See the [Environment Variables reference](../reference/env_var.md) to configure additional variables for a deployment.
+
+Example `.env` file:
+
+```
+MY_ENV_VAR_1=foo
+MY_ENV_VAR_2=bar
+OPENAI_API_KEY=key
+```
+
+Example file directory:
+
+```bash
+my-app/
+├── my_agent # all project code lies within here
+│   └── requirements.txt # package dependencies
+└── .env # environment variables
+```
+
+## Define Graphs
+
+Implement your graphs! Graphs can be defined in a single file or multiple files. Make note of the variable names of each @[CompiledStateGraph][CompiledStateGraph] to be included in the LangGraph application. The variable names will be used later when creating the [LangGraph configuration file](../reference/cli.md#configuration-file).
+
+Example `agent.py` file, which shows how to import from other modules you define (code for the modules is not shown here, please see [this repository](https://github.com/langchain-ai/langgraph-example) to see their implementation):
+
+```python
+# my_agent/agent.py
+from typing import Literal
+from typing_extensions import TypedDict
+
+from langgraph.graph import StateGraph, END, START
+from my_agent.utils.nodes import call_model, should_continue, tool_node # import nodes
+from my_agent.utils.state import AgentState # import state
+
+# Define the runtime context
+class GraphContext(TypedDict):
+    model_name: Literal["anthropic", "openai"]
+
+workflow = StateGraph(AgentState, context_schema=GraphContext)
+workflow.add_node("agent", call_model)
+workflow.add_node("action", tool_node)
+workflow.add_edge(START, "agent")
+workflow.add_conditional_edges(
+    "agent",
+    should_continue,
+    {
+        "continue": "action",
+        "end": END,
+    },
+)
+workflow.add_edge("action", "agent")
+
+graph = workflow.compile()
+```
+
+Example file directory:
+
+```bash
+my-app/
+├── my_agent # all project code lies within here
+│   ├── utils # utilities for your graph
+│   │   ├── __init__.py
+│   │   ├── tools.py # tools for your graph
+│   │   ├── nodes.py # node functions for you graph
+│   │   └── state.py # state definition of your graph
+│   ├── requirements.txt # package dependencies
+│   ├── __init__.py
+│   └── agent.py # code for constructing your graph
+└── .env # environment variables
+```
+
+## Create LangGraph Configuration File
+
+Create a [LangGraph configuration file](../reference/cli.md#configuration-file) called `langgraph.json`. See the [LangGraph configuration file reference](../reference/cli.md#configuration-file) for detailed explanations of each key in the JSON object of the configuration file.
+
+Example `langgraph.json` file:
+
+```json
+{
+  "dependencies": ["./my_agent"],
+  "graphs": {
+    "agent": "./my_agent/agent.py:graph"
+  },
+  "env": ".env"
+}
+```
+
+Note that the variable name of the `CompiledGraph` appears at the end of the value of each subkey in the top-level `graphs` key (i.e. `:<variable_name>`).
+
+!!! warning "Configuration File Location"
+    The LangGraph configuration file must be placed in a directory that is at the same level or higher than the Python files that contain compiled graphs and associated dependencies.
+
+Example file directory:
+
+```bash
+my-app/
+├── my_agent # all project code lies within here
+│   ├── utils # utilities for your graph
+│   │   ├── __init__.py
+│   │   ├── tools.py # tools for your graph
+│   │   ├── nodes.py # node functions for you graph
+│   │   └── state.py # state definition of your graph
+│   ├── requirements.txt # package dependencies
+│   ├── __init__.py
+│   └── agent.py # code for constructing your graph
+├── .env # environment variables
+└── langgraph.json # configuration file for LangGraph
+```
+
+## Next
+
+After you setup your project and place it in a GitHub repository, it's time to [deploy your app](./cloud.md).

docs/docs/cloud/deployment/setup_javascript.md

@@ -0,0 +1,199 @@
+# How to Set Up a LangGraph.js Application
+
+A [LangGraph.js](https://langchain-ai.github.io/langgraphjs/) application must be configured with a [LangGraph configuration file](../reference/cli.md#configuration-file) in order to be deployed to LangGraph Platform (or to be self-hosted). This how-to guide discusses the basic steps to setup a LangGraph.js application for deployment using `package.json` to specify project dependencies.
+
+This walkthrough is based on [this repository](https://github.com/langchain-ai/langgraphjs-studio-starter), which you can play around with to learn more about how to setup your LangGraph application for deployment.
+
+The final repository structure will look something like this:
+
+```bash
+my-app/
+├── src # all project code lies within here
+│   ├── utils # optional utilities for your graph
+│   │   ├── tools.ts # tools for your graph
+│   │   ├── nodes.ts # node functions for you graph
+│   │   └── state.ts # state definition of your graph
+│   └── agent.ts # code for constructing your graph
+├── package.json # package dependencies
+├── .env # environment variables
+└── langgraph.json # configuration file for LangGraph
+```
+
+After each step, an example file directory is provided to demonstrate how code can be organized.
+
+## Specify Dependencies
+
+Dependencies can be specified in a `package.json`. If none of these files is created, then dependencies can be specified later in the [LangGraph configuration file](#create-langgraph-api-config).
+
+Example `package.json` file:
+
+```json
+{
+  "name": "langgraphjs-studio-starter",
+  "packageManager": "yarn@1.22.22",
+  "dependencies": {
+    "@langchain/community": "^0.2.31",
+    "@langchain/core": "^0.2.31",
+    "@langchain/langgraph": "^0.2.0",
+    "@langchain/openai": "^0.2.8"
+  }
+}
+```
+
+When deploying your app, the dependencies will be installed using the package manager of your choice, provided they adhere to the compatible version ranges listed below:
+
+```
+"@langchain/core": "^0.3.42",
+"@langchain/langgraph": "^0.2.57",
+"@langchain/langgraph-checkpoint": "~0.0.16",
+```
+
+Example file directory:
+
+```bash
+my-app/
+└── package.json # package dependencies
+```
+
+## Specify Environment Variables
+
+Environment variables can optionally be specified in a file (e.g. `.env`). See the [Environment Variables reference](../reference/env_var.md) to configure additional variables for a deployment.
+
+Example `.env` file:
+
+```
+MY_ENV_VAR_1=foo
+MY_ENV_VAR_2=bar
+OPENAI_API_KEY=key
+TAVILY_API_KEY=key_2
+```
+
+Example file directory:
+
+```bash
+my-app/
+├── package.json
+└── .env # environment variables
+```
+
+## Define Graphs
+
+Implement your graphs! Graphs can be defined in a single file or multiple files. Make note of the variable names of each compiled graph to be included in the LangGraph application. The variable names will be used later when creating the [LangGraph configuration file](../reference/cli.md#configuration-file).
+
+Here is an example `agent.ts`:
+
+```ts
+import type { AIMessage } from "@langchain/core/messages";
+import { TavilySearchResults } from "@langchain/community/tools/tavily_search";
+import { ChatOpenAI } from "@langchain/openai";
+
+import { MessagesAnnotation, StateGraph } from "@langchain/langgraph";
+import { ToolNode } from "@langchain/langgraph/prebuilt";
+
+const tools = [new TavilySearchResults({ maxResults: 3 })];
+
+// Define the function that calls the model
+async function callModel(state: typeof MessagesAnnotation.State) {
+  /**
+   * Call the LLM powering our agent.
+   * Feel free to customize the prompt, model, and other logic!
+   */
+  const model = new ChatOpenAI({
+    model: "gpt-4o",
+  }).bindTools(tools);
+
+  const response = await model.invoke([
+    {
+      role: "system",
+      content: `You are a helpful assistant. The current date is ${new Date().getTime()}.`,
+    },
+    ...state.messages,
+  ]);
+
+  // MessagesAnnotation supports returning a single message or array of messages
+  return { messages: response };
+}
+
+// Define the function that determines whether to continue or not
+function routeModelOutput(state: typeof MessagesAnnotation.State) {
+  const messages = state.messages;
+  const lastMessage: AIMessage = messages[messages.length - 1];
+  // If the LLM is invoking tools, route there.
+  if ((lastMessage?.tool_calls?.length ?? 0) > 0) {
+    return "tools";
+  }
+  // Otherwise end the graph.
+  return "__end__";
+}
+
+// Define a new graph.
+// See https://langchain-ai.github.io/langgraphjs/how-tos/define-state/#getting-started for
+// more on defining custom graph states.
+const workflow = new StateGraph(MessagesAnnotation)
+  // Define the two nodes we will cycle between
+  .addNode("callModel", callModel)
+  .addNode("tools", new ToolNode(tools))
+  // Set the entrypoint as `callModel`
+  // This means that this node is the first one called
+  .addEdge("__start__", "callModel")
+  .addConditionalEdges(
+    // First, we define the edges' source node. We use `callModel`.
+    // This means these are the edges taken after the `callModel` node is called.
+    "callModel",
+    // Next, we pass in the function that will determine the sink node(s), which
+    // will be called after the source node is called.
+    routeModelOutput,
+    // List of the possible destinations the conditional edge can route to.
+    // Required for conditional edges to properly render the graph in Studio
+    ["tools", "__end__"]
+  )
+  // This means that after `tools` is called, `callModel` node is called next.
+  .addEdge("tools", "callModel");
+
+// Finally, we compile it!
+// This compiles it into a graph you can invoke and deploy.
+export const graph = workflow.compile();
+```
+
+Example file directory:
+
+```bash
+my-app/
+├── src # all project code lies within here
+│   ├── utils # optional utilities for your graph
+│   │   ├── tools.ts # tools for your graph
+│   │   ├── nodes.ts # node functions for you graph
+│   │   └── state.ts # state definition of your graph
+│   └── agent.ts # code for constructing your graph
+├── package.json # package dependencies
+├── .env # environment variables
+└── langgraph.json # configuration file for LangGraph
+```
+
+## Create LangGraph API Config
+
+Create a [LangGraph configuration file](../reference/cli.md#configuration-file) called `langgraph.json`. See the [LangGraph configuration file reference](../reference/cli.md#configuration-file) for detailed explanations of each key in the JSON object of the configuration file.
+
+Example `langgraph.json` file:
+
+```json
+{
+  "node_version": "20",
+  "dockerfile_lines": [],
+  "dependencies": ["."],
+  "graphs": {
+    "agent": "./src/agent.ts:graph"
+  },
+  "env": ".env"
+}
+```
+
+Note that the variable name of the `CompiledGraph` appears at the end of the value of each subkey in the top-level `graphs` key (i.e. `:<variable_name>`).
+
+!!! info "Configuration Location"
+
+    The LangGraph configuration file must be placed in a directory that is at the same level or higher than the TypeScript files that contain compiled graphs and associated dependencies.
+
+## Next
+
+After you setup your project and place it in a GitHub repository, it's time to [deploy your app](./cloud.md).

docs/docs/cloud/deployment/setup_pyproject.md

@@ -0,0 +1,201 @@
+# How to Set Up a LangGraph Application with pyproject.toml
+
+A LangGraph application must be configured with a [LangGraph configuration file](../reference/cli.md#configuration-file) in order to be deployed to LangGraph Platform (or to be self-hosted). This how-to guide discusses the basic steps to setup a LangGraph application for deployment using `pyproject.toml` to define your package's dependencies.
+
+This walkthrough is based on [this repository](https://github.com/langchain-ai/langgraph-example-pyproject), which you can play around with to learn more about how to setup your LangGraph application for deployment.
+
+!!! tip "Setup with requirements.txt"
+    If you prefer using `requirements.txt` for dependency management, check out [this how-to guide](./setup.md).
+
+!!! tip "Setup with a Monorepo"
+    If you are interested in deploying a graph located inside a monorepo, take a look at [this](https://github.com/langchain-ai/langgraph-example-monorepo) repository for an example of how to do so.
+
+The final repository structure will look something like this:
+
+```bash
+my-app/
+├── my_agent # all project code lies within here
+│   ├── utils # utilities for your graph
+│   │   ├── __init__.py
+│   │   ├── tools.py # tools for your graph
+│   │   ├── nodes.py # node functions for you graph
+│   │   └── state.py # state definition of your graph
+│   ├── __init__.py
+│   └── agent.py # code for constructing your graph
+├── .env # environment variables
+├── langgraph.json  # configuration file for LangGraph
+└── pyproject.toml # dependencies for your project
+```
+
+After each step, an example file directory is provided to demonstrate how code can be organized.
+
+## Specify Dependencies
+
+Dependencies can optionally be specified in one of the following files: `pyproject.toml`, `setup.py`, or `requirements.txt`. If none of these files is created, then dependencies can be specified later in the [LangGraph configuration file](#create-langgraph-configuration-file).
+
+The dependencies below will be included in the image, you can also use them in your code, as long as with a compatible version range:
+
+```
+langgraph>=0.3.27
+langgraph-sdk>=0.1.66
+langgraph-checkpoint>=2.0.23
+langchain-core>=0.2.38
+langsmith>=0.1.63
+orjson>=3.9.7,<3.10.17
+httpx>=0.25.0
+tenacity>=8.0.0
+uvicorn>=0.26.0
+sse-starlette>=2.1.0,<2.2.0
+uvloop>=0.18.0
+httptools>=0.5.0
+jsonschema-rs>=0.20.0
+structlog>=24.1.0
+cloudpickle>=3.0.0
+```
+
+Example `pyproject.toml` file:
+
+```toml
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "my-agent"
+version = "0.0.1"
+description = "An excellent agent build for LangGraph Platform."
+authors = [
+    {name = "Polly the parrot", email = "1223+polly@users.noreply.github.com"}
+]
+license = {text = "MIT"}
+readme = "README.md"
+requires-python = ">=3.9"
+dependencies = [
+    "langgraph>=0.2.0",
+    "langchain-fireworks>=0.1.3"
+]
+
+[tool.hatch.build.targets.wheel]
+packages = ["my_agent"]
+```
+
+Example file directory:
+
+```bash
+my-app/
+└── pyproject.toml   # Python packages required for your graph
+```
+
+## Specify Environment Variables
+
+Environment variables can optionally be specified in a file (e.g. `.env`). See the [Environment Variables reference](../reference/env_var.md) to configure additional variables for a deployment.
+
+Example `.env` file:
+
+```
+MY_ENV_VAR_1=foo
+MY_ENV_VAR_2=bar
+FIREWORKS_API_KEY=key
+```
+
+Example file directory:
+
+```bash
+my-app/
+├── .env # file with environment variables
+└── pyproject.toml
+```
+
+## Define Graphs
+
+Implement your graphs! Graphs can be defined in a single file or multiple files. Make note of the variable names of each @[CompiledStateGraph][CompiledStateGraph] to be included in the LangGraph application. The variable names will be used later when creating the [LangGraph configuration file](../reference/cli.md#configuration-file).
+
+Example `agent.py` file, which shows how to import from other modules you define (code for the modules is not shown here, please see [this repository](https://github.com/langchain-ai/langgraph-example-pyproject) to see their implementation):
+
+```python
+# my_agent/agent.py
+from typing import Literal
+from typing_extensions import TypedDict
+
+from langgraph.graph import StateGraph, END, START
+from my_agent.utils.nodes import call_model, should_continue, tool_node # import nodes
+from my_agent.utils.state import AgentState # import state
+
+# Define the runtime context
+class GraphContext(TypedDict):
+    model_name: Literal["anthropic", "openai"]
+
+workflow = StateGraph(AgentState, context_schema=GraphContext)
+workflow.add_node("agent", call_model)
+workflow.add_node("action", tool_node)
+workflow.add_edge(START, "agent")
+workflow.add_conditional_edges(
+    "agent",
+    should_continue,
+    {
+        "continue": "action",
+        "end": END,
+    },
+)
+workflow.add_edge("action", "agent")
+
+graph = workflow.compile()
+```
+
+Example file directory:
+
+```bash
+my-app/
+├── my_agent # all project code lies within here
+│   ├── utils # utilities for your graph
+│   │   ├── __init__.py
+│   │   ├── tools.py # tools for your graph
+│   │   ├── nodes.py # node functions for you graph
+│   │   └── state.py # state definition of your graph
+│   ├── __init__.py
+│   └── agent.py # code for constructing your graph
+├── .env
+└── pyproject.toml
+```
+
+## Create LangGraph Configuration File
+
+Create a [LangGraph configuration file](../reference/cli.md#configuration-file) called `langgraph.json`. See the [LangGraph configuration file reference](../reference/cli.md#configuration-file) for detailed explanations of each key in the JSON object of the configuration file.
+
+Example `langgraph.json` file:
+
+```json
+{
+  "dependencies": ["."],
+  "graphs": {
+    "agent": "./my_agent/agent.py:graph"
+  },
+  "env": ".env"
+}
+```
+
+Note that the variable name of the `CompiledGraph` appears at the end of the value of each subkey in the top-level `graphs` key (i.e. `:<variable_name>`).
+
+!!! warning "Configuration File Location"
+    The LangGraph configuration file must be placed in a directory that is at the same level or higher than the Python files that contain compiled graphs and associated dependencies.
+
+Example file directory:
+
+```bash
+my-app/
+├── my_agent # all project code lies within here
+│   ├── utils # utilities for your graph
+│   │   ├── __init__.py
+│   │   ├── tools.py # tools for your graph
+│   │   ├── nodes.py # node functions for you graph
+│   │   └── state.py # state definition of your graph
+│   ├── __init__.py
+│   └── agent.py # code for constructing your graph
+├── .env # environment variables
+├── langgraph.json  # configuration file for LangGraph
+└── pyproject.toml # dependencies for your project
+```
+
+## Next
+
+After you setup your project and place it in a GitHub repository, it's time to [deploy your app](./cloud.md).

docs/docs/cloud/deployment/standalone_container.md

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

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

@@ -0,0 +1,486 @@
+# Human-in-the-loop using Server API
+
+To review, edit, and approve tool calls in an agent or workflow, use LangGraph's [human-in-the-loop](../../concepts/human_in_the_loop.md) features.
+
+## Dynamic interrupts
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+    # highlight-next-line
+    from langgraph_sdk.schema import Command
+    client = get_client(url=<DEPLOYMENT_URL>)
+
+    # Using the graph deployed with the name "agent"
+    assistant_id = "agent"
+
+    # create a thread
+    thread = await client.threads.create()
+    thread_id = thread["thread_id"]
+
+    # Run the graph until the interrupt is hit.
+    result = await client.runs.wait(
+        thread_id,
+        assistant_id,
+        input={"some_text": "original text"}   # (1)!
+    )
+
+    print(result['__interrupt__']) # (2)!
+    # > [
+    # >     {
+    # >         'value': {'text_to_revise': 'original text'},
+    # >         'id': '...',
+    # >     }
+    # > ]
+
+
+    # Resume the graph
+    print(await client.runs.wait(
+        thread_id,
+        assistant_id,
+        # highlight-next-line
+        command=Command(resume="Edited text")   # (3)!
+    ))
+    # > {'some_text': 'Edited text'}
+    ```
+
+    1. The graph is invoked with some initial state.
+    2. When the graph hits the interrupt, it returns an interrupt object with the payload and metadata.
+    3. The graph is resumed with a `Command(resume=...)`, injecting the human's input and continuing execution.
+
+=== "JavaScript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
+
+    // Using the graph deployed with the name "agent"
+    const assistantID = "agent";
+
+    // create a thread
+    const thread = await client.threads.create();
+    const threadID = thread["thread_id"];
+
+    // Run the graph until the interrupt is hit.
+    const result = await client.runs.wait(
+      threadID,
+      assistantID,
+      { input: { "some_text": "original text" } }   // (1)!
+    );
+
+    console.log(result['__interrupt__']); // (2)!
+    // > [
+    // >     {
+    // >         'value': {'text_to_revise': 'original text'},
+    // >         'resumable': True,
+    // >         'ns': ['human_node:fc722478-2f21-0578-c572-d9fc4dd07c3b'],
+    // >         'when': 'during'
+    // >     }
+    // > ]
+
+    // Resume the graph
+    console.log(await client.runs.wait(
+        threadID,
+        assistantID,
+        // highlight-next-line
+        { command: { resume: "Edited text" }}   // (3)!
+    ));
+    // > {'some_text': 'Edited text'}
+    ```
+
+    1. The graph is invoked with some initial state.
+    2. When the graph hits the interrupt, it returns an interrupt object with the payload and metadata.
+    3. The graph is resumed with a `{ resume: ... }` command object, injecting the human's input and continuing execution.
+
+=== "cURL"
+
+    Create a thread:
+
+    ```bash
+    curl --request POST \
+    --url <DEPLOYMENT_URL>/threads \
+    --header 'Content-Type: application/json' \
+    --data '{}'
+    ```
+
+    Run the graph until the interrupt is hit.:
+
+    ```bash
+    curl --request POST \
+    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/wait \
+    --header 'Content-Type: application/json' \
+    --data "{
+      \"assistant_id\": \"agent\",
+      \"input\": {\"some_text\": \"original text\"}
+    }"
+    ```
+
+    Resume the graph:
+
+    ```bash
+    curl --request POST \
+     --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/wait \
+     --header 'Content-Type: application/json' \
+     --data "{
+       \"assistant_id\": \"agent\",
+       \"command\": {
+         \"resume\": \"Edited text\"
+       }
+     }"
+    ```
+
+??? example "Extended example: using `interrupt`"
+
+    This is an example graph you can run in the LangGraph API server.
+    See [LangGraph Platform quickstart](../quick_start.md) for more details.
+
+    ```python
+    from typing import TypedDict
+    import uuid
+
+    from langgraph.checkpoint.memory import InMemorySaver
+    from langgraph.constants import START
+    from langgraph.graph import StateGraph
+    # highlight-next-line
+    from langgraph.types import interrupt, Command
+
+    class State(TypedDict):
+        some_text: str
+
+    def human_node(state: State):
+        # highlight-next-line
+        value = interrupt( # (1)!
+            {
+                "text_to_revise": state["some_text"] # (2)!
+            }
+        )
+        return {
+            "some_text": value # (3)!
+        }
+
+
+    # Build the graph
+    graph_builder = StateGraph(State)
+    graph_builder.add_node("human_node", human_node)
+    graph_builder.add_edge(START, "human_node")
+
+    graph = graph_builder.compile()
+    ```
+
+    1. `interrupt(...)` pauses execution at `human_node`, surfacing the given payload to a human.
+    2. Any JSON serializable value can be passed to the `interrupt` function. Here, a dict containing the text to revise.
+    3. Once resumed, the return value of `interrupt(...)` is the human-provided input, which is used to update the state.
+
+    Once you have a running LangGraph API server, you can interact with it using
+    [LangGraph SDK](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/python_sdk_ref/)
+
+    === "Python"
+
+        ```python
+        from langgraph_sdk import get_client
+        # highlight-next-line
+        from langgraph_sdk.schema import Command
+        client = get_client(url=<DEPLOYMENT_URL>)
+
+        # Using the graph deployed with the name "agent"
+        assistant_id = "agent"
+
+        # create a thread
+        thread = await client.threads.create()
+        thread_id = thread["thread_id"]
+
+        # Run the graph until the interrupt is hit.
+        result = await client.runs.wait(
+            thread_id,
+            assistant_id,
+            input={"some_text": "original text"}   # (1)!
+        )
+
+        print(result['__interrupt__']) # (2)!
+        # > [
+        # >     {
+        # >         'value': {'text_to_revise': 'original text'},
+        # >         'id': '...',
+        # >     }
+        # > ]
+
+
+        # Resume the graph
+        print(await client.runs.wait(
+            thread_id,
+            assistant_id,
+            # highlight-next-line
+            command=Command(resume="Edited text")   # (3)!
+        ))
+        # > {'some_text': 'Edited text'}
+        ```
+
+        1. The graph is invoked with some initial state.
+        2. When the graph hits the interrupt, it returns an interrupt object with the payload and metadata.
+        3. The graph is resumed with a `Command(resume=...)`, injecting the human's input and continuing execution.
+
+    === "JavaScript"
+
+        ```js
+        import { Client } from "@langchain/langgraph-sdk";
+        const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
+
+        // Using the graph deployed with the name "agent"
+        const assistantID = "agent";
+
+        // create a thread
+        const thread = await client.threads.create();
+        const threadID = thread["thread_id"];
+
+        // Run the graph until the interrupt is hit.
+        const result = await client.runs.wait(
+          threadID,
+          assistantID,
+          { input: { "some_text": "original text" } }   // (1)!
+        );
+
+        console.log(result['__interrupt__']); // (2)!
+        // > [
+        // >     {
+        // >         'value': {'text_to_revise': 'original text'},
+        // >         'resumable': True,
+        // >         'ns': ['human_node:fc722478-2f21-0578-c572-d9fc4dd07c3b'],
+        // >         'when': 'during'
+        // >     }
+        // > ]
+
+        // Resume the graph
+        console.log(await client.runs.wait(
+            threadID,
+            assistantID,
+            // highlight-next-line
+            { command: { resume: "Edited text" }}   // (3)!
+        ));
+        // > {'some_text': 'Edited text'}
+        ```
+
+        1. The graph is invoked with some initial state.
+        2. When the graph hits the interrupt, it returns an interrupt object with the payload and metadata.
+        3. The graph is resumed with a `{ resume: ... }` command object, injecting the human's input and continuing execution.
+
+    === "cURL"
+
+        Create a thread:
+
+        ```bash
+        curl --request POST \
+        --url <DEPLOYMENT_URL>/threads \
+        --header 'Content-Type: application/json' \
+        --data '{}'
+        ```
+
+        Run the graph until the interrupt is hit:
+
+        ```bash
+        curl --request POST \
+        --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/wait \
+        --header 'Content-Type: application/json' \
+        --data "{
+          \"assistant_id\": \"agent\",
+          \"input\": {\"some_text\": \"original text\"}
+        }"
+        ```
+
+        Resume the graph:
+
+        ```bash
+        curl --request POST \
+        --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/wait \
+        --header 'Content-Type: application/json' \
+        --data "{
+          \"assistant_id\": \"agent\",
+          \"command\": {
+            \"resume\": \"Edited text\"
+          }
+        }"
+        ```
+
+## Static interrupts
+
+Static interrupts (also known as static breakpoints) are triggered either before or after a node executes. 
+
+!!! warning
+
+    Static interrupts are **not** recommended for human-in-the-loop workflows. They are best used for debugging and testing.
+
+You can set static interrupts by specifying `interrupt_before` and `interrupt_after` at compile time:
+
+```python
+# highlight-next-line
+graph = graph_builder.compile( # (1)!
+    # highlight-next-line
+    interrupt_before=["node_a"], # (2)!
+    # highlight-next-line
+    interrupt_after=["node_b", "node_c"], # (3)!
+)
+```
+
+1. The breakpoints are set during `compile` time.
+2. `interrupt_before` specifies the nodes where execution should pause before the node is executed.
+3. `interrupt_after` specifies the nodes where execution should pause after the node is executed.
+
+Alternatively, you can set static interrupts at run time:
+
+=== "Python"
+
+    ```python
+    # highlight-next-line
+    await client.runs.wait( # (1)!
+        thread_id,
+        assistant_id,
+        inputs=inputs,
+        # highlight-next-line
+        interrupt_before=["node_a"], # (2)!
+        # highlight-next-line
+        interrupt_after=["node_b", "node_c"] # (3)!
+    )
+    ```
+
+    1. `client.runs.wait` is called with the `interrupt_before` and `interrupt_after` parameters. This is a run-time configuration and can be changed for every invocation.
+    2. `interrupt_before` specifies the nodes where execution should pause before the node is executed.
+    3. `interrupt_after` specifies the nodes where execution should pause after the node is executed.
+
+=== "JavaScript"
+
+    ```js
+    // highlight-next-line
+    await client.runs.wait( // (1)!
+        threadID,
+        assistantID,
+        {
+        input: input,
+        // highlight-next-line
+        interruptBefore: ["node_a"], // (2)!
+        // highlight-next-line
+        interruptAfter: ["node_b", "node_c"] // (3)!
+        }
+    )
+    ```
+
+    1. `client.runs.wait` is called with the `interruptBefore` and `interruptAfter` parameters. This is a run-time configuration and can be changed for every invocation.
+    2. `interruptBefore` specifies the nodes where execution should pause before the node is executed.
+    3. `interruptAfter` specifies the nodes where execution should pause after the node is executed.
+
+=== "cURL"
+
+    ```bash
+    curl --request POST \
+    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/wait \
+    --header 'Content-Type: application/json' \
+    --data "{
+        \"assistant_id\": \"agent\",
+        \"interrupt_before\": [\"node_a\"],
+        \"interrupt_after\": [\"node_b\", \"node_c\"],
+        \"input\": <INPUT>
+    }"
+    ```
+
+The following example shows how to add static interrupts:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+    client = get_client(url=<DEPLOYMENT_URL>)
+
+    # Using the graph deployed with the name "agent"
+    assistant_id = "agent"
+
+    # create a thread
+    thread = await client.threads.create()
+    thread_id = thread["thread_id"]
+
+    # Run the graph until the breakpoint
+    result = await client.runs.wait(
+        thread_id,
+        assistant_id,
+        input=inputs   # (1)!
+    )
+
+    # Resume the graph
+    await client.runs.wait(
+        thread_id,
+        assistant_id,
+        input=None   # (2)!
+    )
+    ```
+
+    1. The graph is run until the first breakpoint is hit.
+    2. The graph is resumed by passing in `None` for the input. This will run the graph until the next breakpoint is hit.
+
+=== "JavaScript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
+
+    // Using the graph deployed with the name "agent"
+    const assistantID = "agent";
+
+    // create a thread
+    const thread = await client.threads.create();
+    const threadID = thread["thread_id"];
+
+    // Run the graph until the breakpoint
+    const result = await client.runs.wait(
+      threadID,
+      assistantID,
+      { input: input }   // (1)!
+    );
+
+    // Resume the graph
+    await client.runs.wait(
+      threadID,
+      assistantID,
+      { input: null }   // (2)!
+    );
+    ```
+
+    1. The graph is run until the first breakpoint is hit.
+    2. The graph is resumed by passing in `null` for the input. This will run the graph until the next breakpoint is hit.
+
+=== "cURL"
+
+    Create a thread:
+
+    ```bash
+    curl --request POST \
+    --url <DEPLOYMENT_URL>/threads \
+    --header 'Content-Type: application/json' \
+    --data '{}'
+    ```
+
+    Run the graph until the breakpoint:
+
+    ```bash
+    curl --request POST \
+    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/wait \
+    --header 'Content-Type: application/json' \
+    --data "{
+      \"assistant_id\": \"agent\",
+      \"input\": <INPUT>
+    }"
+    ```
+
+    Resume the graph:
+
+    ```bash
+    curl --request POST \
+    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/wait \
+    --header 'Content-Type: application/json' \
+    --data "{
+      \"assistant_id\": \"agent\"
+    }"
+    ```
+
+
+## Learn more
+
+- [Human-in-the-loop conceptual guide](../../concepts/human_in_the_loop.md): learn more about LangGraph human-in-the-loop features. 
+- [Common patterns](../../how-tos/human_in_the_loop/add-human-in-the-loop.md#common-patterns): learn how to implement patterns like approving/rejecting actions, requesting user input, tool call review, and validating human input.

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

@@ -0,0 +1,451 @@
+# How to kick off background runs
+ 
+
+This guide covers how to kick off background runs for your agent.
+This can be useful for long running jobs.
+
+## Setup
+
+First let's set up our client and thread:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url=<DEPLOYMENT_URL>)
+    # Using the graph deployed with the name "agent"
+    assistant_id = "agent"
+    # create thread
+    thread = await client.threads.create()
+    print(thread)
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
+    // Using the graph deployed with the name "agent"
+    const assistantID = "agent";
+    // create thread
+    const thread = await client.threads.create();
+    console.log(thread);
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+      --url <DEPLOYMENT_URL>/threads \
+      --header 'Content-Type: application/json' \
+      --data '{}'
+    ```
+
+Output:
+
+    {
+        'thread_id': '5cb1e8a1-34b3-4a61-a34e-71a9799bd00d',
+        'created_at': '2024-08-30T20:35:52.062934+00:00',
+        'updated_at': '2024-08-30T20:35:52.062934+00:00',
+        'metadata': {},
+        'status': 'idle',
+        'config': {},
+        'values': None
+    }
+
+## Check runs on thread
+
+If we list the current runs on this thread, we will see that it's empty:
+
+=== "Python"
+
+    ```python
+    runs = await client.runs.list(thread["thread_id"])
+    print(runs)
+    ```
+
+=== "Javascript"
+
+    ```js
+    let runs = await client.runs.list(thread['thread_id']);
+    console.log(runs);
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request GET \
+        --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs
+    ```
+
+Output:
+
+    []
+
+## Start runs on thread
+
+Now let's kick off a run:
+
+=== "Python"
+
+    ```python
+    input = {"messages": [{"role": "user", "content": "what's the weather in sf"}]}
+    run = await client.runs.create(thread["thread_id"], assistant_id, input=input)
+    ```
+
+=== "Javascript"
+
+    ```js
+    let input = {"messages": [{"role": "user", "content": "what's the weather in sf"}]};
+    let run = await client.runs.create(thread["thread_id"], assistantID, { input });
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+        --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs \
+        --header 'Content-Type: application/json' \
+        --data '{
+            "assistant_id": <ASSISTANT_ID>
+        }'
+    ```
+
+The first time we poll it, we can see `status=pending`:
+
+=== "Python"
+
+    ```python
+    print(await client.runs.get(thread["thread_id"], run["run_id"]))
+    ```
+
+=== "Javascript"
+
+    ```js
+    console.log(await client.runs.get(thread["thread_id"], run["run_id"]));
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request GET \
+        --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/<RUN_ID>
+    ```
+
+Output:
+
+        {
+            "run_id": "1ef6a5f8-bd86-6763-bbd6-bff042db7b1b",
+            "thread_id": "7885f0cf-94ad-4040-91d7-73f7ba007c8a",
+            "assistant_id": "fe096781-5601-53d2-b2f6-0d3403f7e9ca",
+            "created_at": "2024-09-04T01:46:47.244887+00:00",
+            "updated_at": "2024-09-04T01:46:47.244887+00:00",
+            "metadata": {},
+            "status": "pending",
+            "kwargs": {
+                "input": {
+                    "messages": [
+                        {
+                            "role": "user",
+                            "content": "what's the weather in sf"
+                        }
+                    ]
+                },
+                "config": {
+                    "metadata": {
+                        "created_by": "system"
+                    },
+                    "configurable": {
+                        "run_id": "1ef6a5f8-bd86-6763-bbd6-bff042db7b1b",
+                        "user_id": "",
+                        "graph_id": "agent",
+                        "thread_id": "7885f0cf-94ad-4040-91d7-73f7ba007c8a",
+                        "assistant_id": "fe096781-5601-53d2-b2f6-0d3403f7e9ca",
+                        "checkpoint_id": null
+                    }
+                },
+                "webhook": null,
+                "temporary": false,
+                "stream_mode": [
+                    "values"
+                ],
+                "feedback_keys": null,
+                "interrupt_after": null,
+                "interrupt_before": null
+            },
+            "multitask_strategy": "reject"
+        }
+
+
+
+Now we can join the run, wait for it to finish and check that status again:
+
+=== "Python"
+
+    ```python
+    await client.runs.join(thread["thread_id"], run["run_id"])
+    print(await client.runs.get(thread["thread_id"], run["run_id"]))
+    ```
+
+=== "Javascript"
+
+    ```js
+    await client.runs.join(thread["thread_id"], run["run_id"]);
+    console.log(await client.runs.get(thread["thread_id"], run["run_id"]));
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request GET \
+        --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/<RUN_ID>/join &&
+    curl --request GET \
+        --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/<RUN_ID>
+    ```
+
+Output:
+
+    {
+        "run_id": "1ef6a5f8-bd86-6763-bbd6-bff042db7b1b",
+        "thread_id": "7885f0cf-94ad-4040-91d7-73f7ba007c8a",
+        "assistant_id": "fe096781-5601-53d2-b2f6-0d3403f7e9ca",
+        "created_at": "2024-09-04T01:46:47.244887+00:00",
+        "updated_at": "2024-09-04T01:46:47.244887+00:00",
+        "metadata": {},
+        "status": "success",
+        "kwargs": {
+            "input": {
+                "messages": [
+                    {
+                        "role": "user",
+                        "content": "what's the weather in sf"
+                    }
+                ]
+            },
+            "config": {
+                "metadata": {
+                    "created_by": "system"
+                },
+                "configurable": {
+                    "run_id": "1ef6a5f8-bd86-6763-bbd6-bff042db7b1b",
+                    "user_id": "",
+                    "graph_id": "agent",
+                    "thread_id": "7885f0cf-94ad-4040-91d7-73f7ba007c8a",
+                    "assistant_id": "fe096781-5601-53d2-b2f6-0d3403f7e9ca",
+                    "checkpoint_id": null
+                }
+            },
+            "webhook": null,
+            "temporary": false,
+            "stream_mode": [
+                "values"
+            ],
+            "feedback_keys": null,
+            "interrupt_after": null,
+            "interrupt_before": null
+        },
+        "multitask_strategy": "reject"
+    }
+
+
+Perfect! The run succeeded as we would expect. We can double check that the run worked as expected by printing out the final state:
+
+=== "Python"
+
+    ```python
+    final_result = await client.threads.get_state(thread["thread_id"])
+    print(final_result)
+    ```
+
+=== "Javascript"
+
+    ```js
+    let finalResult = await client.threads.getState(thread["thread_id"]);
+    console.log(finalResult);
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request GET \
+        --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/state
+    ```
+
+Output:
+
+    {
+        "values": {
+            "messages": [
+                {
+                    "content": "what's the weather in sf",
+                    "additional_kwargs": {},
+                    "response_metadata": {},
+                    "type": "human",
+                    "name": null,
+                    "id": "beba31bf-320d-4125-9c37-cadf526ac47a",
+                    "example": false
+                },
+                {
+                    "content": [
+                        {
+                            "id": "toolu_01AaNPSPzqia21v7aAKwbKYm",
+                            "input": {},
+                            "name": "tavily_search_results_json",
+                            "type": "tool_use",
+                            "index": 0,
+                            "partial_json": "{\"query\": \"weather in san francisco\"}"
+                        }
+                    ],
+                    "additional_kwargs": {},
+                    "response_metadata": {
+                        "stop_reason": "tool_use",
+                        "stop_sequence": null
+                    },
+                    "type": "ai",
+                    "name": null,
+                    "id": "run-f220faf8-1d27-4f73-ad91-6bb3f47e8639",
+                    "example": false,
+                    "tool_calls": [
+                        {
+                            "name": "tavily_search_results_json",
+                            "args": {
+                                "query": "weather in san francisco"
+                            },
+                            "id": "toolu_01AaNPSPzqia21v7aAKwbKYm",
+                            "type": "tool_call"
+                        }
+                    ],
+                    "invalid_tool_calls": [],
+                    "usage_metadata": {
+                        "input_tokens": 273,
+                        "output_tokens": 61,
+                        "total_tokens": 334
+                    }
+                },
+                {
+                    "content": "[{\"url\": \"https://www.weatherapi.com/\", \"content\": \"{'location': {'name': 'San Francisco', 'region': 'California', 'country': 'United States of America', 'lat': 37.78, 'lon': -122.42, 'tz_id': 'America/Los_Angeles', 'localtime_epoch': 1725052131, 'localtime': '2024-08-30 14:08'}, 'current': {'last_updated_epoch': 1725051600, 'last_updated': '2024-08-30 14:00', 'temp_c': 21.1, 'temp_f': 70.0, 'is_day': 1, 'condition': {'text': 'Partly cloudy', 'icon': '//cdn.weatherapi.com/weather/64x64/day/116.png', 'code': 1003}, 'wind_mph': 11.9, 'wind_kph': 19.1, 'wind_degree': 290, 'wind_dir': 'WNW', 'pressure_mb': 1018.0, 'pressure_in': 30.07, 'precip_mm': 0.0, 'precip_in': 0.0, 'humidity': 59, 'cloud': 25, 'feelslike_c': 21.1, 'feelslike_f': 70.0, 'windchill_c': 18.6, 'windchill_f': 65.5, 'heatindex_c': 18.6, 'heatindex_f': 65.5, 'dewpoint_c': 12.2, 'dewpoint_f': 54.0, 'vis_km': 16.0, 'vis_miles': 9.0, 'uv': 5.0, 'gust_mph': 15.0, 'gust_kph': 24.2}}\"}]",
+                    "additional_kwargs": {},
+                    "response_metadata": {},
+                    "type": "tool",
+                    "name": "tavily_search_results_json",
+                    "id": "686b2487-f332-4e58-9508-89b3a814cd81",
+                    "tool_call_id": "toolu_01AaNPSPzqia21v7aAKwbKYm",
+                    "artifact": {
+                        "query": "weather in san francisco",
+                        "follow_up_questions": null,
+                        "answer": null,
+                        "images": [],
+                        "results": [
+                            {
+                                "title": "Weather in San Francisco",
+                                "url": "https://www.weatherapi.com/",
+                                "content": "{'location': {'name': 'San Francisco', 'region': 'California', 'country': 'United States of America', 'lat': 37.78, 'lon': -122.42, 'tz_id': 'America/Los_Angeles', 'localtime_epoch': 1725052131, 'localtime': '2024-08-30 14:08'}, 'current': {'last_updated_epoch': 1725051600, 'last_updated': '2024-08-30 14:00', 'temp_c': 21.1, 'temp_f': 70.0, 'is_day': 1, 'condition': {'text': 'Partly cloudy', 'icon': '//cdn.weatherapi.com/weather/64x64/day/116.png', 'code': 1003}, 'wind_mph': 11.9, 'wind_kph': 19.1, 'wind_degree': 290, 'wind_dir': 'WNW', 'pressure_mb': 1018.0, 'pressure_in': 30.07, 'precip_mm': 0.0, 'precip_in': 0.0, 'humidity': 59, 'cloud': 25, 'feelslike_c': 21.1, 'feelslike_f': 70.0, 'windchill_c': 18.6, 'windchill_f': 65.5, 'heatindex_c': 18.6, 'heatindex_f': 65.5, 'dewpoint_c': 12.2, 'dewpoint_f': 54.0, 'vis_km': 16.0, 'vis_miles': 9.0, 'uv': 5.0, 'gust_mph': 15.0, 'gust_kph': 24.2}}",
+                                "score": 0.976148,
+                                "raw_content": null
+                            }
+                        ],
+                        "response_time": 3.07
+                    },
+                    "status": "success"
+                },
+                {
+                    "content": [
+                        {
+                            "text": "\n\nThe search results provide the current weather conditions in San Francisco. According to the data, as of 2:00 PM on August 30, 2024, the temperature in San Francisco is 70\u00b0F (21.1\u00b0C) with partly cloudy skies. The wind is blowing from the west-northwest at around 12 mph (19 km/h). The humidity is 59% and visibility is 9 miles (16 km). Overall, it looks like a nice late summer day in San Francisco with comfortable temperatures and partly sunny conditions.",
+                            "type": "text",
+                            "index": 0
+                        }
+                    ],
+                    "additional_kwargs": {},
+                    "response_metadata": {
+                        "stop_reason": "end_turn",
+                        "stop_sequence": null
+                    },
+                    "type": "ai",
+                    "name": null,
+                    "id": "run-8fecc61d-3d9f-4e16-8e8a-92f702be498a",
+                    "example": false,
+                    "tool_calls": [],
+                    "invalid_tool_calls": [],
+                    "usage_metadata": {
+                        "input_tokens": 837,
+                        "output_tokens": 124,
+                        "total_tokens": 961
+                    }
+                }
+            ]
+        },
+        "next": [],
+        "tasks": [],
+        "metadata": {
+            "step": 3,
+            "run_id": "1ef67140-eb23-684b-8253-91d4c90bb05e",
+            "source": "loop",
+            "writes": {
+                "agent": {
+                    "messages": [
+                        {
+                            "id": "run-8fecc61d-3d9f-4e16-8e8a-92f702be498a",
+                            "name": null,
+                            "type": "ai",
+                            "content": [
+                                {
+                                    "text": "\n\nThe search results provide the current weather conditions in San Francisco. According to the data, as of 2:00 PM on August 30, 2024, the temperature in San Francisco is 70\u00b0F (21.1\u00b0C) with partly cloudy skies. The wind is blowing from the west-northwest at around 12 mph (19 km/h). The humidity is 59% and visibility is 9 miles (16 km). Overall, it looks like a nice late summer day in San Francisco with comfortable temperatures and partly sunny conditions.",
+                                    "type": "text",
+                                    "index": 0
+                                }
+                            ],
+                            "example": false,
+                            "tool_calls": [],
+                            "usage_metadata": {
+                                "input_tokens": 837,
+                                "total_tokens": 961,
+                                "output_tokens": 124
+                            },
+                            "additional_kwargs": {},
+                            "response_metadata": {
+                                "stop_reason": "end_turn",
+                                "stop_sequence": null
+                            },
+                            "invalid_tool_calls": []
+                        }
+                    ]
+                }
+            },
+            "user_id": "",
+            "graph_id": "agent",
+            "thread_id": "5cb1e8a1-34b3-4a61-a34e-71a9799bd00d",
+            "created_by": "system",
+            "assistant_id": "fe096781-5601-53d2-b2f6-0d3403f7e9ca"
+        },
+        "created_at": "2024-08-30T21:09:00.079909+00:00",
+        "checkpoint_id": "1ef67141-3ca2-6fae-8003-fe96832e57d6",
+        "parent_checkpoint_id": "1ef67141-2129-6b37-8002-61fc3bf69cb5"
+    }
+
+We can also just print the content of the last AIMessage:
+
+=== "Python"
+
+    ```python
+    print(final_result['values']['messages'][-1]['content'][0]['text'])
+    ```
+
+=== "Javascript"
+
+    ```js
+    console.log(finalResult['values']['messages'][finalResult['values']['messages'].length-1]['content'][0]['text']);
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request GET \
+        --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/state | jq -r '.values.messages[-1].content.[0].text'
+    ```
+
+Output:
+
+    The search results provide the current weather conditions in San Francisco. According to the data, as of 2:00 PM on August 30, 2024, the temperature in San Francisco is 70°F (21.1°C) with partly cloudy skies. The wind is blowing from the west-northwest at around 12 mph (19 km/h). The humidity is 59% and visibility is 9 miles (16 km). Overall, it looks like a nice late summer day in San Francisco with comfortable temperatures and partly sunny conditions.

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

@@ -0,0 +1,36 @@
+# Debug LangSmith traces
+
+This guide explains how to open LangSmith traces in LangGraph Studio for interactive investigation and debugging.
+
+## Open deployed threads
+
+1. Open the LangSmith trace, selecting the root run.
+2. Click "Run in Studio".
+
+This will open LangGraph Studio connected to the associated LangGraph Platform deployment with the trace's parent thread selected.
+
+## Testing local agents with remote traces
+
+This section explains how to test a local agent against remote traces from LangSmith. This enables you to use production traces as input for local testing, allowing you to debug and verify agent modifications in your development environment.
+
+### Requirements
+
+- A LangSmith traced thread
+- A locally running agent. See [here](../how-tos/studio/quick_start.md#local-development-server) for setup
+  instructions.
+
+!!! info "Local agent requirements"
+
+    - langgraph>=0.3.18
+    - langgraph-api>=0.0.32
+    - Contains the same set of nodes present in the remote trace
+
+### Cloning Thread
+
+1. Open the LangSmith trace, selecting the root run.
+2. Click the dropdown next to "Run in Studio".
+3. Enter your local agent's URL.
+4. Select "Clone thread locally".
+5. If multiple graphs exist, select the target graph.
+
+A new thread will be created in your local agent with the thread history inferred and copied from the remote thread, and you will be navigated to LangGraph Studio for your locally running application.

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

@@ -0,0 +1,84 @@
+# Configurable Headers
+
+LangGraph allows runtime configuration to modify agent behavior and permissions dynamically. When using the [LangGraph Platform](../quick_start.md), you can pass this configuration in the request body (`config`) or specific request headers. This enables adjustments based on user identity or other request data.
+
+For privacy, control which headers are passed to the runtime configuration via the `http.configurable_headers` section in your `langgraph.json` file.
+
+Here's how to customize the included and excluded headers:
+
+```json
+{
+  "http": {
+    "configurable_headers": {
+      "include": ["x-user-id", "x-organization-id", "my-prefix-*"],
+      "exclude": ["authorization", "x-api-key"]
+    }
+  }
+}
+```
+
+
+The `include` and `exclude` lists accept exact header names or patterns using `*` to match any number of characters. For your security, no other regex patterns are supported.
+
+## Using within your graph
+
+You can access the included headers in your graph using the `config` argument of any node.
+
+```python
+def my_node(state, config):
+  organization_id = config["configurable"].get("x-organization-id")
+  ...
+```
+
+Or by fetching from context (useful in tools and or within other nested functions).
+
+```python
+from langgraph.config import get_config
+
+def search_everything(query: str):
+  organization_id = get_config()["configurable"].get("x-organization-id")
+  ...
+```
+
+
+You can even use this to dynamically compile the graph.
+
+```python
+# my_graph.py.
+import contextlib
+
+@contextlib.asynccontextmanager
+async def generate_agent(config):
+  organization_id = config["configurable"].get("x-organization-id")
+  if organization_id == "org1":
+    graph = ...
+    yield graph
+  else:
+    graph = ...
+    yield graph
+
+```
+
+```json
+{
+  "graphs": {"agent": "my_grph.py:generate_agent"}
+}
+```
+
+### Opt-out of configurable headers
+
+If you'd like to opt-out of configurable headers, you can simply set a wildcard pattern in the `exclude` list:
+
+```json
+{
+  "http": {
+    "configurable_headers": {
+      "exclude": ["*"]
+    }
+  }
+}
+```
+
+This will exclude all headers from being added to your run's configuration.
+
+Note that exclusions take precedence over inclusions.

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

@@ -0,0 +1,332 @@
+# Manage assistants
+
+In this guide we will show how to create, configure, and manage an [assistant](../../concepts/assistants.md).
+
+First, as a brief refresher on the concept of runtime context, consider the following simple `call_model` node and context schema. Observe that this node tries to read and use the `model_provider` as defined by the `Runtime` object's `context` property.
+
+=== "Python"
+
+    ```python
+    @dataclass
+    class ContextSchema:
+        llm_provider: str = "anthropic"
+
+    builder = StateGraph(AgentState, context_schema=ContextSchema)
+
+    def call_model(state, runtime: Runtime[ContextSchema]):
+        messages = state["messages"]
+        model = _get_model(runtime.context.llm_provider)
+        response = model.invoke(messages)
+        # We return a list, because this will get added to the existing list
+        return {"messages": [response]}
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Annotation } from "@langchain/langgraph";
+
+    const ConfigSchema = Annotation.Root({
+        model_name: Annotation<string>,
+        system_prompt:
+    });
+
+    const builder = new StateGraph(AgentState, ConfigSchema)
+
+    function callModel(state: State, config: RunnableConfig) {
+      const messages = state.messages;
+      const modelName = config.configurable?.model_name ?? "anthropic";
+      const model = _getModel(modelName);
+      const response = model.invoke(messages);
+      // We return a list, because this will get added to the existing list
+      return { messages: [response] };
+    }
+    ```
+
+:::python
+For more information on runtime context, [see here](../../concepts/low_level.md#runtime-context).
+:::
+
+## Create an assistant
+
+### LangGraph SDK
+
+To create an assistant, use the [LangGraph SDK](../../concepts/sdk.md) `create` method. See the [Python](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/python_sdk_ref/#langgraph_sdk.client.AssistantsClient.create) and [JS](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#create) SDK reference docs for more information.
+
+This example uses the same configuration schema as above, and creates an assistant with `model_name` set to `openai`.
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url=<DEPLOYMENT_URL>)
+    openai_assistant = await client.assistants.create(
+        # "agent" is the name of a graph we deployed
+        "agent", config={"configurable": {"model_name": "openai"}}, name="Open AI Assistant"
+    )
+
+    print(openai_assistant)
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
+    const openAIAssistant = await client.assistants.create({
+        graphId: 'agent',
+        name: "Open AI Assistant",
+        config: { "configurable": { "model_name": "openai" } },
+    });
+
+    console.log(openAIAssistant);
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+        --url <DEPLOYMENT_URL>/assistants \
+        --header 'Content-Type: application/json' \
+        --data '{"graph_id":"agent", "config":{"configurable":{"model_name":"openai"}}, "name": "Open AI Assistant"}'
+    ```
+
+Output:
+
+    {
+        "assistant_id": "62e209ca-9154-432a-b9e9-2d75c7a9219b",
+        "graph_id": "agent",
+        "name": "Open AI Assistant"
+        "config": {
+            "configurable": {
+                "model_name": "openai"
+            }
+        },
+        "metadata": {}
+        "created_at": "2024-08-31T03:09:10.230718+00:00",
+        "updated_at": "2024-08-31T03:09:10.230718+00:00",
+    }
+
+### LangGraph Platform UI
+
+You can also create assistants from the LangGraph Platform UI.
+
+Inside your deployment, select the "Assistants" tab. This will load a table of all of the assistants in your deployment, across all graphs.
+
+To create a new assistant, select the "+ New assistant" button. This will open a form where you can specify the graph this assistant is for, as well as provide a name, description, and the desired configuration for the assistant based on the configuration schema for that graph.
+
+To confirm, click "Create assistant". This will take you to [LangGraph Studio](../../concepts/langgraph_studio.md) where you can test the assistant. If you go back to the "Assistants" tab in the deployment, you will see the newly created assistant in the table.
+
+## Use an assistant
+
+### LangGraph SDK
+
+We have now created an assistant called "Open AI Assistant" that has `model_name` defined as `openai`. We can now use this assistant with this configuration:
+
+=== "Python"
+
+    ```python
+    thread = await client.threads.create()
+    input = {"messages": [{"role": "user", "content": "who made you?"}]}
+    async for event in client.runs.stream(
+        thread["thread_id"],
+        # this is where we specify the assistant id to use
+        openai_assistant["assistant_id"],
+        input=input,
+        stream_mode="updates",
+    ):
+        print(f"Receiving event of type: {event.event}")
+        print(event.data)
+        print("\n\n")
+    ```
+
+=== "Javascript"
+
+    ```js
+    const thread = await client.threads.create();
+    const input = { "messages": [{ "role": "user", "content": "who made you?" }] };
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      // this is where we specify the assistant id to use
+      openAIAssistant["assistant_id"],
+      {
+        input,
+        streamMode: "updates"
+      }
+    );
+
+    for await (const event of streamResponse) {
+      console.log(`Receiving event of type: ${event.event}`);
+      console.log(event.data);
+      console.log("\n\n");
+    }
+    ```
+
+=== "CURL"
+
+    ```bash
+    thread_id=$(curl --request POST \
+        --url <DEPLOYMENT_URL>/threads \
+        --header 'Content-Type: application/json' \
+        --data '{}' | jq -r '.thread_id') && \
+    curl --request POST \
+        --url "<DEPLOYMENT_URL>/threads/${thread_id}/runs/stream" \
+        --header 'Content-Type: application/json' \
+        --data '{
+            "assistant_id": <OPENAI_ASSISTANT_ID>,
+            "input": {
+                "messages": [
+                    {
+                        "role": "user",
+                        "content": "who made you?"
+                    }
+                ]
+            },
+            "stream_mode": [
+                "updates"
+            ]
+        }' | \
+        sed 's/\r$//' | \
+        awk '
+        /^event:/ {
+            if (data_content != "") {
+                print data_content "\n"
+            }
+            sub(/^event: /, "Receiving event of type: ", $0)
+            printf "%s...\n", $0
+            data_content = ""
+        }
+        /^data:/ {
+            sub(/^data: /, "", $0)
+            data_content = $0
+        }
+        END {
+            if (data_content != "") {
+                print data_content "\n\n"
+            }
+        }
+    '
+    ```
+
+Output:
+
+    ```
+    Receiving event of type: metadata
+    {'run_id': '1ef6746e-5893-67b1-978a-0f1cd4060e16'}
+
+
+
+    Receiving event of type: updates
+    {'agent': {'messages': [{'content': 'I was created by OpenAI, a research organization focused on developing and advancing artificial intelligence technology.', 'additional_kwargs': {}, 'response_metadata': {'finish_reason': 'stop', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_157b3831f5'}, 'type': 'ai', 'name': None, 'id': 'run-e1a6b25c-8416-41f2-9981-f9cfe043f414', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+    ```
+
+### LangGraph Platform UI
+
+Inside your deployment, select the "Assistants" tab. For the assistant you would like to use, click the "Studio" button. This will open LangGraph Studio with the selected assistant. When you submit an input (either in Graph or Chat mode), the selected assistant and its configuration will be used.
+
+## Create a new version for your assistant
+
+### LangGraph SDK
+
+To edit the assistant, use the `update` method. This will create a new version of the assistant with the provided edits. See the [Python](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/python_sdk_ref/#langgraph_sdk.client.AssistantsClient.update) and [JS](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#update) SDK reference docs for more information.
+
+!!! note "Note"
+
+    You must pass in the ENTIRE config (and metadata if you are using it). The update endpoint creates new versions completely from scratch and does not rely on previous versions.
+
+For example, to update your assistant's system prompt:
+
+=== "Python"
+
+    ```python
+    openai_assistant_v2 = await client.assistants.update(
+        openai_assistant["assistant_id"],
+        config={
+            "configurable": {
+                "model_name": "openai",
+                "system_prompt": "You are an unhelpful assistant!",
+            }
+        },
+    )
+    ```
+
+=== "Javascript"
+
+    ```js
+    const openaiAssistantV2 = await client.assistants.update(
+        openai_assistant["assistant_id"],
+        {
+            config: {
+                configurable: {
+                    model_name: 'openai',
+                    system_prompt: 'You are an unhelpful assistant!',
+                },
+        },
+    });
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request PATCH \
+    --url <DEPOLYMENT_URL>/assistants/<ASSISTANT_ID> \
+    --header 'Content-Type: application/json' \
+    --data '{
+    "config": {"model_name": "openai", "system_prompt": "You are an unhelpful assistant!"}
+    }'
+    ```
+
+This will create a new version of the assistant with the updated parameters and set this as the active version of your assistant. If you now run your graph and pass in this assistant id, it will use this latest version.
+
+### LangGraph Platform UI
+
+You can also edit assistants from the LangGraph Platform UI.
+
+Inside your deployment, select the "Assistants" tab. This will load a table of all of the assistants in your deployment, across all graphs.
+
+To edit an existing assistant, select the "Edit" button for the specified assistant. This will open a form where you can edit the assistant's name, description, and configuration.
+
+Additionally, if using LangGraph Studio, you can edit the assistants and create new versions via the "Manage Assistants" button.
+
+## Use a previous assistant version
+
+### LangGraph SDK
+
+You can also change the active version of your assistant. To do so, use the `setLatest` method.
+
+In the example above, to rollback to the first version of the assistant:
+
+=== "Python"
+
+    ```python
+    await client.assistants.set_latest(openai_assistant['assistant_id'], 1)
+    ```
+
+=== "Javascript"
+
+    ```js
+    await client.assistants.setLatest(openaiAssistant['assistant_id'], 1);
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+    --url <DEPLOYMENT_URL>/assistants/<ASSISTANT_ID>/latest \
+    --header 'Content-Type: application/json' \
+    --data '{
+    "version": 1
+    }'
+    ```
+
+If you now run your graph and pass in this assistant id, it will use the first version of the assistant.
+
+### LangGraph Platform UI
+
+If using LangGraph Studio, to set the active version of your assistant, click the "Manage Assistants" button and locate the assistant you would like to use. Select the assistant and the version, and then click the "Active" toggle. This will update the assistant to make the selected version active.
+
+!!! warning "Deleting Assistants"
+Deleting as assistant will delete ALL of its versions. There is currently no way to delete a single version, but by pointing your assistant to the correct version you can skip any versions that you don't wish to use.

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

@@ -0,0 +1,184 @@
+# Use cron jobs
+
+Sometimes you don't want to run your graph based on user interaction, but rather you would like to schedule your graph to run on a schedule - for example if you wish for your graph to compose and send out a weekly email of to-dos for your team. LangGraph Platform allows you to do this without having to write your own script by using the `Crons` client. To schedule a graph job, you need to pass a [cron expression](https://crontab.cronhub.io/) to inform the client when you want to run the graph. `Cron` jobs are run in the background and do not interfere with normal invocations of the graph.
+
+## Setup
+
+First, let's set up our SDK client, assistant, and thread:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url=<DEPLOYMENT_URL>)
+    # Using the graph deployed with the name "agent"
+    assistant_id = "agent"
+    # create thread
+    thread = await client.threads.create()
+    print(thread)
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
+    // Using the graph deployed with the name "agent"
+    const assistantId = "agent";
+    // create thread
+    const thread = await client.threads.create();
+    console.log(thread);
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+        --url <DEPLOYMENT_URL>/assistants/search \
+        --header 'Content-Type: application/json' \
+        --data '{
+            "limit": 10,
+            "offset": 0
+        }' | jq -c 'map(select(.config == null or .config == {})) | .[0].graph_id' && \
+    curl --request POST \
+        --url <DEPLOYMENT_URL>/threads \
+        --header 'Content-Type: application/json' \
+        --data '{}'
+    ```
+
+Output:
+
+    {
+        'thread_id': '9dde5490-2b67-47c8-aa14-4bfec88af217', 
+        'created_at': '2024-08-30T23:07:38.242730+00:00', 
+        'updated_at': '2024-08-30T23:07:38.242730+00:00', 
+        'metadata': {}, 
+        'status': 'idle', 
+        'config': {}, 
+        'values': None
+    }
+
+## Cron job on a thread 
+
+To create a cron job associated with a specific thread, you can write:
+
+
+=== "Python"
+
+    ```python
+    # This schedules a job to run at 15:27 (3:27PM) every day
+    cron_job = await client.crons.create_for_thread(
+        thread["thread_id"],
+        assistant_id,
+        schedule="27 15 * * *",
+        input={"messages": [{"role": "user", "content": "What time is it?"}]},
+    )
+    ```
+
+=== "Javascript"
+
+    ```js
+    // This schedules a job to run at 15:27 (3:27PM) every day
+    const cronJob = await client.crons.create_for_thread(
+      thread["thread_id"],
+      assistantId,
+      {
+        schedule: "27 15 * * *",
+        input: { messages: [{ role: "user", content: "What time is it?" }] }
+      }
+    );
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+        --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/crons \
+        --header 'Content-Type: application/json' \
+        --data '{
+            "assistant_id": <ASSISTANT_ID>,
+        }'
+    ```
+
+Note that it is **very** important to delete `Cron` jobs that are no longer useful. Otherwise you could rack up unwanted API charges to the LLM! You can delete a `Cron` job using the following code:
+
+=== "Python"
+
+    ```python
+    await client.crons.delete(cron_job["cron_id"])
+    ```
+
+=== "Javascript"
+
+    ```js
+    await client.crons.delete(cronJob["cron_id"]);
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request DELETE \
+        --url <DEPLOYMENT_URL>/runs/crons/<CRON_ID>
+    ```
+
+## Cron job stateless
+
+You can also create stateless cron jobs by using the following code:
+
+=== "Python"
+
+    ```python
+    # This schedules a job to run at 15:27 (3:27PM) every day
+    cron_job_stateless = await client.crons.create(
+        assistant_id,
+        schedule="27 15 * * *",
+        input={"messages": [{"role": "user", "content": "What time is it?"}]},
+    )
+    ```
+
+=== "Javascript"
+
+    ```js
+    // This schedules a job to run at 15:27 (3:27PM) every day
+    const cronJobStateless = await client.crons.create(
+      assistantId,
+      {
+        schedule: "27 15 * * *",
+        input: { messages: [{ role: "user", content: "What time is it?" }] }
+      }
+    );
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+        --url <DEPLOYMENT_URL>/runs/crons \
+        --header 'Content-Type: application/json' \
+        --data '{
+            "assistant_id": <ASSISTANT_ID>,
+        }'
+    ```
+
+Again, remember to delete your job once you are done with it!
+
+=== "Python"
+
+    ```python
+    await client.crons.delete(cron_job_stateless["cron_id"])
+    ```
+
+=== "Javascript"
+
+    ```js
+    await client.crons.delete(cronJobStateless["cron_id"]);
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request DELETE \
+        --url <DEPLOYMENT_URL>/runs/crons/<CRON_ID>
+    ```

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

@@ -0,0 +1,12 @@
+# Add node to dataset
+
+This guide shows how to add examples to [LangSmith datasets](https://docs.smith.langchain.com/evaluation/how_to_guides#dataset-management) from nodes in the thread log. This is useful to evaluate individual steps of the agent.
+
+1. Select a thread.
+2. Click on the `Add to Dataset` button.
+3. Select nodes whose input/output you want to add to a dataset.
+4. For each selected node, select the target dataset to create the example in. By default a dataset for the specific assistant and node will be selected. If this dataset does not yet exist, it will be created.
+5. Edit the example's input/output as needed before adding it to the dataset.
+6. Select "Add to dataset" at the bottom of the page to add all selected nodes to their respective datasets.
+
+See [Evaluating intermediate steps](https://docs.smith.langchain.com/evaluation/how_to_guides/langgraph#evaluating-intermediate-steps) for more details on how to evaluate intermediate steps.

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

@@ -0,0 +1,255 @@
+# Enqueue
+
+This guide assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide](../../concepts/double_texting.md).
+
+The guide covers the `enqueue` option for double texting, which adds the interruptions to a queue and executes them in the order they are received by the client. Below is a quick example of using the `enqueue` option.
+
+## Setup
+
+First, we will define a quick helper function for printing out JS and CURL model outputs (you can skip this if using Python):
+
+=== "Javascript"
+
+    ```js
+    function prettyPrint(m) {
+      const padded = " " + m['type'] + " ";
+      const sepLen = Math.floor((80 - padded.length) / 2);
+      const sep = "=".repeat(sepLen);
+      const secondSep = sep + (padded.length % 2 ? "=" : "");
+      
+      console.log(`${sep}${padded}${secondSep}`);
+      console.log("\n\n");
+      console.log(m.content);
+    }
+    ```
+
+=== "CURL"
+
+    ```bash
+    # PLACE THIS IN A FILE CALLED pretty_print.sh
+    pretty_print() {
+      local type="$1"
+      local content="$2"
+      local padded=" $type "
+      local total_width=80
+      local sep_len=$(( (total_width - ${#padded}) / 2 ))
+      local sep=$(printf '=%.0s' $(eval "echo {1.."${sep_len}"}"))
+      local second_sep=$sep
+      if (( (total_width - ${#padded}) % 2 )); then
+        second_sep="${second_sep}="
+      fi
+
+      echo "${sep}${padded}${second_sep}"
+      echo
+      echo "$content"
+    }
+    ```
+
+Then, let's import our required packages and instantiate our client, assistant, and thread.
+
+=== "Python"
+
+    ```python
+    import asyncio
+
+    import httpx
+    from langchain_core.messages import convert_to_messages
+    from langgraph_sdk import get_client
+
+    client = get_client(url=<DEPLOYMENT_URL>)
+    # Using the graph deployed with the name "agent"
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+    
+
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
+    // Using the graph deployed with the name "agent"
+    const assistantId = "agent";
+    const thread = await client.threads.create();
+    ```
+  
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+      --url <DEPLOYMENT_URL>/threads \
+      --header 'Content-Type: application/json' \
+      --data '{}'
+    ```
+
+## Create runs
+
+Now let's start two runs, with the second interrupting the first one with a multitask strategy of "enqueue":
+
+=== "Python"
+
+    ```python
+    first_run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "user", "content": "what's the weather in sf?"}]},
+    )
+    second_run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "user", "content": "what's the weather in nyc?"}]},
+        multitask_strategy="enqueue",
+    )
+    ```
+
+=== "Javascript"
+
+    ```js
+    const firstRun = await client.runs.create(
+      thread["thread_id"],
+      assistantId,
+      input={"messages": [{"role": "user", "content": "what's the weather in sf?"}]},
+    )
+
+    const secondRun = await client.runs.create(
+      thread["thread_id"],
+      assistantId,
+      input={"messages": [{"role": "user", "content": "what's the weather in nyc?"}]},
+      multitask_strategy="enqueue",
+    )
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+    --url <DEPLOY<ENT_URL>>/threads/<THREAD_ID>/runs \
+    --header 'Content-Type: application/json' \
+    --data "{
+      \"assistant_id\": \"agent\",
+      \"input\": {\"messages\": [{\"role\": \"human\", \"content\": \"what\'s the weather in sf?\"}]},
+    }" && curl --request POST \
+    --url <DEPLOY<ENT_URL>>/threads/<THREAD_ID>/runs \
+    --header 'Content-Type: application/json' \
+    --data "{
+      \"assistant_id\": \"agent\",
+      \"input\": {\"messages\": [{\"role\": \"human\", \"content\": \"what\'s the weather in nyc?\"}]},
+      \"multitask_strategy\": \"enqueue\"
+    }"
+    ```
+
+## View run results
+
+Verify that the thread has data from both runs:
+
+=== "Python"
+
+    ```python
+    # wait until the second run completes
+    await client.runs.join(thread["thread_id"], second_run["run_id"])
+
+    state = await client.threads.get_state(thread["thread_id"])
+
+    for m in convert_to_messages(state["values"]["messages"]):
+        m.pretty_print()
+    ```
+
+=== "Javascript"
+
+    ```js
+    await client.runs.join(thread["thread_id"], secondRun["run_id"]);
+
+    const state = await client.threads.getState(thread["thread_id"]);
+
+    for (const m of state["values"]["messages"]) {
+      prettyPrint(m);
+    }
+    ```
+
+=== "CURL"
+
+    ```bash
+    source pretty_print.sh && curl --request GET \
+    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/<RUN_ID>/join && \
+    curl --request GET --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/state | \
+    jq -c '.values.messages[]' | while read -r element; do
+        type=$(echo "$element" | jq -r '.type')
+        content=$(echo "$element" | jq -r '.content | if type == "array" then tostring else . end')
+        pretty_print "$type" "$content"
+    done
+    ```
+
+Output:
+
+    ================================ Human Message =================================
+    
+    what's the weather in sf?
+    ================================== Ai Message ==================================
+    
+    [{'id': 'toolu_01Dez1sJre4oA2Y7NsKJV6VT', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
+    Tool Calls:
+      tavily_search_results_json (toolu_01Dez1sJre4oA2Y7NsKJV6VT)
+     Call ID: toolu_01Dez1sJre4oA2Y7NsKJV6VT
+      Args:
+        query: weather in san francisco
+    ================================= Tool Message =================================
+    Name: tavily_search_results_json
+    
+    [{"url": "https://www.accuweather.com/en/us/san-francisco/94103/weather-forecast/347629", "content": "Get the current and future weather conditions for San Francisco, CA, including temperature, precipitation, wind, air quality and more. See the hourly and 10-day outlook, radar maps, alerts and allergy information."}]
+    ================================== Ai Message ==================================
+    
+    According to AccuWeather, the current weather conditions in San Francisco are:
+    
+    Temperature: 57°F (14°C)
+    Conditions: Mostly Sunny
+    Wind: WSW 10 mph
+    Humidity: 72%
+    
+    The forecast for the next few days shows partly sunny skies with highs in the upper 50s to mid 60s F (14-18°C) and lows in the upper 40s to low 50s F (9-11°C). Typical mild, dry weather for San Francisco this time of year.
+    
+    Some key details from the AccuWeather forecast:
+    
+    Today: Mostly sunny, high of 62°F (17°C)
+    Tonight: Partly cloudy, low of 49°F (9°C) 
+    Tomorrow: Partly sunny, high of 59°F (15°C)
+    Saturday: Mostly sunny, high of 64°F (18°C)
+    Sunday: Partly sunny, high of 61°F (16°C)
+    
+    So in summary, expect seasonable spring weather in San Francisco over the next several days, with a mix of sun and clouds and temperatures ranging from the upper 40s at night to the low 60s during the days. Typical dry conditions with no rain in the forecast.
+    ================================ Human Message =================================
+    
+    what's the weather in nyc?
+    ================================== Ai Message ==================================
+    
+    [{'text': 'Here are the current weather conditions and forecast for New York City:', 'type': 'text'}, {'id': 'toolu_01FFft5Sx9oS6AdVJuRWWcGp', 'input': {'query': 'weather in new york city'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
+    Tool Calls:
+      tavily_search_results_json (toolu_01FFft5Sx9oS6AdVJuRWWcGp)
+     Call ID: toolu_01FFft5Sx9oS6AdVJuRWWcGp
+      Args:
+        query: weather in new york city
+    ================================= Tool Message =================================
+    Name: tavily_search_results_json
+    
+    [{"url": "https://www.weatherapi.com/", "content": "{'location': {'name': 'New York', 'region': 'New York', 'country': 'United States of America', 'lat': 40.71, 'lon': -74.01, 'tz_id': 'America/New_York', 'localtime_epoch': 1718734479, 'localtime': '2024-06-18 14:14'}, 'current': {'last_updated_epoch': 1718733600, 'last_updated': '2024-06-18 14:00', 'temp_c': 29.4, 'temp_f': 84.9, 'is_day': 1, 'condition': {'text': 'Sunny', 'icon': '//cdn.weatherapi.com/weather/64x64/day/113.png', 'code': 1000}, 'wind_mph': 2.2, 'wind_kph': 3.6, 'wind_degree': 158, 'wind_dir': 'SSE', 'pressure_mb': 1025.0, 'pressure_in': 30.26, 'precip_mm': 0.0, 'precip_in': 0.0, 'humidity': 63, 'cloud': 0, 'feelslike_c': 31.3, 'feelslike_f': 88.3, 'windchill_c': 28.3, 'windchill_f': 82.9, 'heatindex_c': 29.6, 'heatindex_f': 85.3, 'dewpoint_c': 18.4, 'dewpoint_f': 65.2, 'vis_km': 16.0, 'vis_miles': 9.0, 'uv': 7.0, 'gust_mph': 16.5, 'gust_kph': 26.5}}"}]
+    ================================== Ai Message ==================================
+    
+    According to the weather data from WeatherAPI:
+    
+    Current Conditions in New York City (as of 2:00 PM local time):
+    - Temperature: 85°F (29°C)
+    - Conditions: Sunny
+    - Wind: 2 mph (4 km/h) from the SSE
+    - Humidity: 63%
+    - Heat Index: 85°F (30°C)
+    
+    The forecast shows sunny and warm conditions persisting over the next few days:
+    
+    Today: Sunny, high of 85°F (29°C)
+    Tonight: Clear, low of 68°F (20°C)
+    Tomorrow: Sunny, high of 88°F (31°C) 
+    Thursday: Mostly sunny, high of 90°F (32°C)
+    Friday: Partly cloudy, high of 87°F (31°C)
+    
+    So New York City is experiencing beautiful sunny weather with seasonably warm temperatures in the mid-to-upper 80s Fahrenheit (around 30°C). Humidity is moderate in the 60% range. Overall, ideal late spring/early summer conditions for being outdoors in the city over the next several days.
+

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

@@ -0,0 +1,538 @@
+# How to implement Generative User Interfaces with LangGraph
+
+!!! info "Prerequisites"
+
+    - [LangGraph Platform](../../concepts/langgraph_platform.md)
+    - [LangGraph Server](../../concepts/langgraph_server.md)
+    - [`useStream()` React Hook](./use_stream_react.md)
+
+Generative user interfaces (Generative UI) allows agents to go beyond text and generate rich user interfaces. This enables creating more interactive and context-aware applications where the UI adapts based on the conversation flow and AI responses.
+
+![Generative UI Sample](./img/generative_ui_sample.jpg)
+
+LangGraph Platform supports colocating your React components with your graph code. This allows you to focus on building specific UI components for your graph while easily plugging into existing chat interfaces such as [Agent Chat](https://agentchat.vercel.app) and loading the code only when actually needed.
+
+## Tutorial
+
+### 1. Define and configure UI components
+
+First, create your first UI component. For each component you need to provide an unique identifier that will be used to reference the component in your graph code.
+
+```tsx title="src/agent/ui.tsx"
+const WeatherComponent = (props: { city: string }) => {
+  return <div>Weather for {props.city}</div>;
+};
+
+export default {
+  weather: WeatherComponent,
+};
+```
+
+Next, define your UI components in your `langgraph.json` configuration:
+
+=== "Python agent"
+
+    ```json title="langgraph.json"
+    {
+      "node_version": "20",
+      "graphs": {
+        "agent": "./src/agent.py:graph"
+      },
+      "ui": {
+        "agent": "./src/agent/ui.tsx"
+      }
+    }
+    ```
+
+=== "JS agent"
+
+    ```json title="langgraph.json"
+    {
+      "node_version": "20",
+      "graphs": {
+        "agent": "./src/agent/index.ts:graph"
+      },
+      "ui": {
+        "agent": "./src/agent/ui.tsx"
+      }
+    }
+    ```
+
+The `ui` section points to the UI components that will be used by graphs. By default, we recommend using the same key as the graph name, but you can split out the components however you like, see [Customise the namespace of UI components](#customise-the-namespace-of-ui-components) for more details.
+
+LangGraph Platform will automatically bundle your UI components code and styles and serve them as external assets that can be loaded by the `LoadExternalComponent` component. Some dependencies such as `react` and `react-dom` will be automatically excluded from the bundle.
+
+CSS and Tailwind 4.x is also supported out of the box, so you can freely use Tailwind classes as well as `shadcn/ui` in your UI components.
+
+=== "`src/agent/ui.tsx`"
+
+    ```tsx
+    import "./styles.css";
+
+    const WeatherComponent = (props: { city: string }) => {
+      return <div className="bg-red-500">Weather for {props.city}</div>;
+    };
+
+    export default {
+      weather: WeatherComponent,
+    };
+    ```
+
+=== "`src/agent/styles.css`"
+
+    ```css
+    @import "tailwindcss";
+    ```
+
+### 2. Send the UI components in your graph
+
+=== "Python"
+
+    ```python title="src/agent.py"
+    import uuid
+    from typing import Annotated, Sequence, TypedDict
+
+    from langchain_core.messages import AIMessage, BaseMessage
+    from langchain_openai import ChatOpenAI
+    from langgraph.graph import StateGraph
+    from langgraph.graph.message import add_messages
+    from langgraph.graph.ui import AnyUIMessage, ui_message_reducer, push_ui_message
+
+
+    class AgentState(TypedDict):  # noqa: D101
+        messages: Annotated[Sequence[BaseMessage], add_messages]
+        ui: Annotated[Sequence[AnyUIMessage], ui_message_reducer]
+
+
+    async def weather(state: AgentState):
+        class WeatherOutput(TypedDict):
+            city: str
+
+        weather: WeatherOutput = (
+            await ChatOpenAI(model="gpt-4o-mini")
+            .with_structured_output(WeatherOutput)
+            .with_config({"tags": ["nostream"]})
+            .ainvoke(state["messages"])
+        )
+
+        message = AIMessage(
+            id=str(uuid.uuid4()),
+            content=f"Here's the weather for {weather['city']}",
+        )
+
+        # Emit UI elements associated with the message
+        push_ui_message("weather", weather, message=message)
+        return {"messages": [message]}
+
+
+    workflow = StateGraph(AgentState)
+    workflow.add_node(weather)
+    workflow.add_edge("__start__", "weather")
+    graph = workflow.compile()
+    ```
+
+=== "JS"
+
+    Use the `typedUi` utility to emit UI elements from your agent nodes:
+
+    ```typescript title="src/agent/index.ts"
+    import {
+      typedUi,
+      uiMessageReducer,
+    } from "@langchain/langgraph-sdk/react-ui/server";
+
+    import { ChatOpenAI } from "@langchain/openai";
+    import { v4 as uuidv4 } from "uuid";
+    import { z } from "zod";
+
+    import type ComponentMap from "./ui.js";
+
+    import {
+      Annotation,
+      MessagesAnnotation,
+      StateGraph,
+      type LangGraphRunnableConfig,
+    } from "@langchain/langgraph";
+
+    const AgentState = Annotation.Root({
+      ...MessagesAnnotation.spec,
+      ui: Annotation({ reducer: uiMessageReducer, default: () => [] }),
+    });
+
+    export const graph = new StateGraph(AgentState)
+      .addNode("weather", async (state, config) => {
+        // Provide the type of the component map to ensure
+        // type safety of `ui.push()` calls as well as
+        // pushing the messages to the `ui` and sending a custom event as well.
+        const ui = typedUi<typeof ComponentMap>(config);
+
+        const weather = await new ChatOpenAI({ model: "gpt-4o-mini" })
+          .withStructuredOutput(z.object({ city: z.string() }))
+          .withConfig({ tags: ["nostream"] })
+          .invoke(state.messages);
+
+        const response = {
+          id: uuidv4(),
+          type: "ai",
+          content: `Here's the weather for ${weather.city}`,
+        };
+
+        // Emit UI elements associated with the AI message
+        ui.push({ name: "weather", props: weather }, { message: response });
+
+        return { messages: [response] };
+      })
+      .addEdge("__start__", "weather")
+      .compile();
+    ```
+
+### 3. Handle UI elements in your React application
+
+On the client side, you can use `useStream()` and `LoadExternalComponent` to display the UI elements.
+
+```tsx title="src/app/page.tsx"
+"use client";
+
+import { useStream } from "@langchain/langgraph-sdk/react";
+import { LoadExternalComponent } from "@langchain/langgraph-sdk/react-ui";
+
+export default function Page() {
+  const { thread, values } = useStream({
+    apiUrl: "http://localhost:2024",
+    assistantId: "agent",
+  });
+
+  return (
+    <div>
+      {thread.messages.map((message) => (
+        <div key={message.id}>
+          {message.content}
+          {values.ui
+            ?.filter((ui) => ui.metadata?.message_id === message.id)
+            .map((ui) => (
+              <LoadExternalComponent key={ui.id} stream={thread} message={ui} />
+            ))}
+        </div>
+      ))}
+    </div>
+  );
+}
+```
+
+Behind the scenes, `LoadExternalComponent` will fetch the JS and CSS for the UI components from LangGraph Platform and render them in a shadow DOM, thus ensuring style isolation from the rest of your application.
+
+## How-to guides
+
+### Provide custom components on the client side
+
+If you already have the components loaded in your client application, you can provide a map of such components to be rendered directly without fetching the UI code from LangGraph Platform.
+
+```tsx
+const clientComponents = {
+  weather: WeatherComponent,
+};
+
+<LoadExternalComponent
+  stream={thread}
+  message={ui}
+  components={clientComponents}
+/>;
+```
+
+### Show loading UI when components are loading
+
+You can provide a fallback UI to be rendered when the components are loading.
+
+```tsx
+<LoadExternalComponent
+  stream={thread}
+  message={ui}
+  fallback={<div>Loading...</div>}
+/>
+```
+
+### Customise the namespace of UI components.
+
+By default `LoadExternalComponent` will use the `assistantId` from `useStream()` hook to fetch the code for UI components. You can customise this by providing a `namespace` prop to the `LoadExternalComponent` component.
+
+=== "`src/app/page.tsx`"
+
+    ```tsx
+    <LoadExternalComponent
+      stream={thread}
+      message={ui}
+      namespace="custom-namespace"
+    />
+    ```
+
+=== "`langgraph.json`"
+
+    ```json
+    {
+      "ui": {
+        "custom-namespace": "./src/agent/ui.tsx"
+      }
+    }
+    ```
+
+### Access and interact with the thread state from the UI component
+
+You can access the thread state inside the UI component by using the `useStreamContext` hook.
+
+```tsx
+import { useStreamContext } from "@langchain/langgraph-sdk/react-ui";
+
+const WeatherComponent = (props: { city: string }) => {
+  const { thread, submit } = useStreamContext();
+  return (
+    <>
+      <div>Weather for {props.city}</div>
+
+      <button
+        onClick={() => {
+          const newMessage = {
+            type: "human",
+            content: `What's the weather in ${props.city}?`,
+          };
+
+          submit({ messages: [newMessage] });
+        }}
+      >
+        Retry
+      </button>
+    </>
+  );
+};
+```
+
+### Pass additional context to the client components
+
+You can pass additional context to the client components by providing a `meta` prop to the `LoadExternalComponent` component.
+
+```tsx
+<LoadExternalComponent stream={thread} message={ui} meta={{ userId: "123" }} />
+```
+
+Then, you can access the `meta` prop in the UI component by using the `useStreamContext` hook.
+
+```tsx
+import { useStreamContext } from "@langchain/langgraph-sdk/react-ui";
+
+const WeatherComponent = (props: { city: string }) => {
+  const { meta } = useStreamContext<
+    { city: string },
+    { MetaType: { userId?: string } }
+  >();
+
+  return (
+    <div>
+      Weather for {props.city} (user: {meta?.userId})
+    </div>
+  );
+};
+```
+
+### Streaming UI messages from the server
+
+You can stream UI messages before the node execution is finished by using the `onCustomEvent` callback of the `useStream()` hook. This is especially useful when updating the UI component as the LLM is generating the response.
+
+```tsx
+import { uiMessageReducer } from "@langchain/langgraph-sdk/react-ui";
+
+const { thread, submit } = useStream({
+  apiUrl: "http://localhost:2024",
+  assistantId: "agent",
+  onCustomEvent: (event, options) => {
+    options.mutate((prev) => {
+      const ui = uiMessageReducer(prev.ui ?? [], event);
+      return { ...prev, ui };
+    });
+  },
+});
+```
+
+Then you can push updates to the UI component by calling `ui.push()` / `push_ui_message()` with the same ID as the UI message you wish to update.
+
+=== "Python"
+
+    ```python
+    from typing import Annotated, Sequence, TypedDict
+
+    from langchain_anthropic import ChatAnthropic
+    from langchain_core.messages import AIMessage, AIMessageChunk, BaseMessage
+    from langgraph.graph import StateGraph
+    from langgraph.graph.message import add_messages
+    from langgraph.graph.ui import AnyUIMessage, push_ui_message, ui_message_reducer
+
+
+    class AgentState(TypedDict):  # noqa: D101
+        messages: Annotated[Sequence[BaseMessage], add_messages]
+        ui: Annotated[Sequence[AnyUIMessage], ui_message_reducer]
+
+
+    class CreateTextDocument(TypedDict):
+        """Prepare a document heading for the user."""
+
+        title: str
+
+
+    async def writer_node(state: AgentState):
+        model = ChatAnthropic(model="claude-3-5-sonnet-latest")
+        message: AIMessage = await model.bind_tools(
+            tools=[CreateTextDocument],
+            tool_choice={"type": "tool", "name": "CreateTextDocument"},
+        ).ainvoke(state["messages"])
+
+        tool_call = next(
+            (x["args"] for x in message.tool_calls if x["name"] == "CreateTextDocument"),
+            None,
+        )
+
+        if tool_call:
+            ui_message = push_ui_message("writer", tool_call, message=message)
+            ui_message_id = ui_message["id"]
+
+            # We're already streaming the LLM response to the client through UI messages
+            # so we don't need to stream it again to the `messages` stream mode.
+            content_stream = model.with_config({"tags": ["nostream"]}).astream(
+                f"Create a document with the title: {tool_call['title']}"
+            )
+
+            content: AIMessageChunk | None = None
+            async for chunk in content_stream:
+                content = content + chunk if content else chunk
+
+                push_ui_message(
+                    "writer",
+                    {"content": content.text()},
+                    id=ui_message_id,
+                    message=message,
+                    # Use `merge=rue` to merge props with the existing UI message
+                    merge=True,
+                )
+
+        return {"messages": [message]}
+    ```
+
+=== "JS"
+
+    ```tsx
+    import {
+      Annotation,
+      MessagesAnnotation,
+      type LangGraphRunnableConfig,
+    } from "@langchain/langgraph";
+    import { z } from "zod";
+    import { ChatAnthropic } from "@langchain/anthropic";
+    import {
+      typedUi,
+      uiMessageReducer,
+    } from "@langchain/langgraph-sdk/react-ui/server";
+    import type { AIMessageChunk } from "@langchain/core/messages";
+
+    import type ComponentMap from "./ui";
+
+    const AgentState = Annotation.Root({
+      ...MessagesAnnotation.spec,
+      ui: Annotation({ reducer: uiMessageReducer, default: () => [] }),
+    });
+
+    async function writerNode(
+      state: typeof AgentState.State,
+      config: LangGraphRunnableConfig
+    ): Promise<typeof AgentState.Update> {
+      const ui = typedUi<typeof ComponentMap>(config);
+
+      const model = new ChatAnthropic({ model: "claude-3-5-sonnet-latest" });
+      const message = await model
+        .bindTools(
+          [
+            {
+              name: "create_text_document",
+              description: "Prepare a document heading for the user.",
+              schema: z.object({ title: z.string() }),
+            },
+          ],
+          { tool_choice: { type: "tool", name: "create_text_document" } }
+        )
+        .invoke(state.messages);
+
+      type ToolCall = { name: "create_text_document"; args: { title: string } };
+      const toolCall = message.tool_calls?.find(
+        (tool): tool is ToolCall => tool.name === "create_text_document"
+      );
+
+      if (toolCall) {
+        const { id, name } = ui.push(
+          { name: "writer", props: { title: toolCall.args.title } },
+          { message }
+        );
+
+        const contentStream = await model
+          // We're already streaming the LLM response to the client through UI messages
+          // so we don't need to stream it again to the `messages` stream mode.
+          .withConfig({ tags: ["nostream"] })
+          .stream(`Create a short poem with the topic: ${message.text}`);
+
+        let content: AIMessageChunk | undefined;
+        for await (const chunk of contentStream) {
+          content = content?.concat(chunk) ?? chunk;
+
+          ui.push(
+            { id, name, props: { content: content?.text } },
+            // Use `merge: true` to merge props with the existing UI message
+            { message, merge: true }
+          );
+        }
+      }
+
+      return { messages: [message] };
+    }
+    ```
+
+=== "`ui.tsx`"
+
+    ```tsx
+    function WriterComponent(props: { title: string; content?: string }) {
+      return (
+        <article>
+          <h2>{props.title}</h2>
+          <p style={{ whiteSpace: "pre-wrap" }}>{props.content}</p>
+        </article>
+      );
+    }
+
+    export default {
+      weather: WriterComponent,
+    };
+    ```
+
+### Remove UI messages from state
+
+Similar to how messages can be removed from the state by appending a RemoveMessage you can remove an UI message from the state by calling `remove_ui_message` / `ui.delete` with the ID of the UI message.
+
+=== "Python"
+
+    ```python
+    from langgraph.graph.ui import push_ui_message, delete_ui_message
+
+    # push message
+    message = push_ui_message("weather", {"city": "London"})
+
+    # remove said message
+    delete_ui_message(message["id"])
+    ```
+
+=== "JS"
+
+    ```tsx
+    // push message
+    const message = ui.push({ name: "weather", props: { city: "London" } });
+
+    // remove said message
+    ui.delete(message.id);
+    ```
+
+## Learn more
+
+- [JS/TS SDK Reference](../reference/sdk/js_ts_sdk_ref.md)

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

@@ -0,0 +1,238 @@
+# Time travel using Server API
+
+LangGraph provides the [**time travel**](../../concepts/time-travel.md) functionality to resume execution from a prior checkpoint, either replaying the same state or modifying it to explore alternatives. In all cases, resuming past execution produces a new fork in the history.
+
+To time travel using the LangGraph Server API (via the LangGraph SDK):
+
+1. **Run the graph** with initial inputs using [LangGraph SDK](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/python_sdk_ref/)'s @[`client.runs.wait`][client.runs.wait] or @[`client.runs.stream`][client.runs.stream] APIs.
+2. **Identify a checkpoint in an existing thread**: Use @[`client.threads.get_history`][client.threads.get_history] method to retrieve the execution history for a specific `thread_id` and locate the desired `checkpoint_id`.
+   Alternatively, set a [breakpoint](./human_in_the_loop_breakpoint.md) before the node(s) where you want execution to pause. You can then find the most recent checkpoint recorded up to that breakpoint.
+3. **(Optional) modify the graph state**: Use the @[`client.threads.update_state`][client.threads.update_state] method to modify the graph’s state at the checkpoint and resume execution from alternative state.
+4. **Resume execution from the checkpoint**: Use the @[`client.runs.wait`][client.runs.wait] or @[`client.runs.stream`][client.runs.stream] APIs with an input of `None` and the appropriate `thread_id` and `checkpoint_id`.
+
+## Use time travel in a workflow
+
+??? example "Example graph"
+
+    ```python
+    from typing_extensions import TypedDict, NotRequired
+    from langgraph.graph import StateGraph, START, END
+    from langchain.chat_models import init_chat_model
+    from langgraph.checkpoint.memory import InMemorySaver
+
+    class State(TypedDict):
+        topic: NotRequired[str]
+        joke: NotRequired[str]
+
+    llm = init_chat_model(
+        "anthropic:claude-3-7-sonnet-latest",
+        temperature=0,
+    )
+
+    def generate_topic(state: State):
+        """LLM call to generate a topic for the joke"""
+        msg = llm.invoke("Give me a funny topic for a joke")
+        return {"topic": msg.content}
+
+    def write_joke(state: State):
+        """LLM call to write a joke based on the topic"""
+        msg = llm.invoke(f"Write a short joke about {state['topic']}")
+        return {"joke": msg.content}
+
+    # Build workflow
+    builder = StateGraph(State)
+
+    # Add nodes
+    builder.add_node("generate_topic", generate_topic)
+    builder.add_node("write_joke", write_joke)
+
+    # Add edges to connect nodes
+    builder.add_edge(START, "generate_topic")
+    builder.add_edge("generate_topic", "write_joke")
+
+    # Compile
+    graph = builder.compile()
+    ```
+
+### 1. Run the graph
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+    client = get_client(url=<DEPLOYMENT_URL>)
+
+    # Using the graph deployed with the name "agent"
+    assistant_id = "agent"
+
+    # create a thread
+    thread = await client.threads.create()
+    thread_id = thread["thread_id"]
+
+    # Run the graph
+    result = await client.runs.wait(
+        thread_id,
+        assistant_id,
+        input={}
+    )
+    ```
+
+=== "JavaScript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
+
+    // Using the graph deployed with the name "agent"
+    const assistantID = "agent";
+
+    // create a thread
+    const thread = await client.threads.create();
+    const threadID = thread["thread_id"];
+
+    // Run the graph
+    const result = await client.runs.wait(
+      threadID,
+      assistantID,
+      { input: {}}
+    );
+    ```
+
+=== "cURL"
+
+    Create a thread:
+
+    ```bash
+    curl --request POST \
+    --url <DEPLOYMENT_URL>/threads \
+    --header 'Content-Type: application/json' \
+    --data '{}'
+    ```
+
+    Run the graph:
+
+    ```bash
+    curl --request POST \
+    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/wait \
+    --header 'Content-Type: application/json' \
+    --data "{
+      \"assistant_id\": \"agent\",
+      \"input\": {}
+    }"
+    ```
+
+### 2. Identify a checkpoint
+
+=== "Python"
+
+    ```python
+    # The states are returned in reverse chronological order.
+    states = await client.threads.get_history(thread_id)
+    selected_state = states[1]
+    print(selected_state)
+    ```
+
+=== "JavaScript"
+
+    ```js
+    // The states are returned in reverse chronological order.
+    const states = await client.threads.getHistory(threadID);
+    const selectedState = states[1];
+    console.log(selectedState);
+    ```
+
+=== "cURL"
+
+    ```bash
+    curl --request GET \
+    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/history \
+    --header 'Content-Type: application/json'
+    ```
+
+### 3. Update the state (optional)
+
+`update_state` will create a new checkpoint. The new checkpoint will be associated with the same thread, but a new checkpoint ID.
+
+=== "Python"
+
+    ```python
+    new_config = await client.threads.update_state(
+        thread_id,
+        {"topic": "chickens"},
+        # highlight-next-line
+        checkpoint_id=selected_state["checkpoint_id"]
+    )
+    print(new_config)
+    ```
+
+=== "JavaScript"
+
+    ```js
+    const newConfig = await client.threads.updateState(
+      threadID,
+      {
+        values: { "topic": "chickens" },
+        checkpointId: selectedState["checkpoint_id"]
+      }
+    );
+    console.log(newConfig);
+    ```
+
+=== "cURL"
+
+    ```bash
+    curl --request POST \
+    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/state \
+    --header 'Content-Type: application/json' \
+    --data "{
+      \"assistant_id\": \"agent\",
+      \"checkpoint_id\": <CHECKPOINT_ID>,
+      \"values\": {\"topic\": \"chickens\"}
+    }"
+    ```
+
+### 4. Resume execution from the checkpoint
+
+=== "Python"
+
+    ```python
+    await client.runs.wait(
+        thread_id,
+        assistant_id,
+        # highlight-next-line
+        input=None,
+        # highlight-next-line
+        checkpoint_id=new_config["checkpoint_id"]
+    )
+    ```
+
+=== "JavaScript"
+
+    ```js
+    await client.runs.wait(
+      threadID,
+      assistantID,
+      {
+        // highlight-next-line
+        input: null,
+        // highlight-next-line
+        checkpointId: newConfig["checkpoint_id"]
+      }
+    );
+    ```
+
+=== "cURL"
+
+    ```bash
+    curl --request POST \
+    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/wait \
+    --header 'Content-Type: application/json' \
+    --data "{
+      \"assistant_id\": \"agent\",
+      \"checkpoint_id\": <CHECKPOINT_ID>
+    }"
+    ```
+
+## Learn more
+
+- [**LangGraph time travel guide**](../../how-tos/human_in_the_loop/time-travel.md): learn more about using time travel in LangGraph.

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

@@ -0,0 +1,253 @@
+# How to use the interrupt option
+
+This guide assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide](../../concepts/double_texting.md).
+
+The guide covers the `interrupt` option for double texting, which interrupts the prior run of the graph and starts a new one with the double-text. This option does not delete the first run, but rather keeps it in the database but sets its status to `interrupted`. Below is a quick example of using the `interrupt` option.
+
+## Setup
+
+First, we will define a quick helper function for printing out JS and CURL model outputs (you can skip this if using Python):
+
+=== "Javascript"
+
+    ```js
+    function prettyPrint(m) {
+      const padded = " " + m['type'] + " ";
+      const sepLen = Math.floor((80 - padded.length) / 2);
+      const sep = "=".repeat(sepLen);
+      const secondSep = sep + (padded.length % 2 ? "=" : "");
+      
+      console.log(`${sep}${padded}${secondSep}`);
+      console.log("\n\n");
+      console.log(m.content);
+    }
+    ```
+
+=== "CURL"
+
+    ```bash
+    # PLACE THIS IN A FILE CALLED pretty_print.sh
+    pretty_print() {
+      local type="$1"
+      local content="$2"
+      local padded=" $type "
+      local total_width=80
+      local sep_len=$(( (total_width - ${#padded}) / 2 ))
+      local sep=$(printf '=%.0s' $(eval "echo {1.."${sep_len}"}"))
+      local second_sep=$sep
+      if (( (total_width - ${#padded}) % 2 )); then
+        second_sep="${second_sep}="
+      fi
+
+      echo "${sep}${padded}${second_sep}"
+      echo
+      echo "$content"
+    }
+    ```
+
+Now, let's import our required packages and instantiate our client, assistant, and thread.
+
+=== "Python"
+
+    ```python
+    import asyncio
+
+    from langchain_core.messages import convert_to_messages
+    from langgraph_sdk import get_client
+
+    client = get_client(url=<DEPLOYMENT_URL>)
+    # Using the graph deployed with the name "agent"
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
+    // Using the graph deployed with the name "agent"
+    const assistantId = "agent";
+    const thread = await client.threads.create();
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+      --url <DEPLOYMENT_URL>/threads \
+      --header 'Content-Type: application/json' \
+      --data '{}'
+    ```
+
+## Create runs
+
+Now we can start our two runs and join the second one until it has completed:
+
+=== "Python"
+
+    ```python
+    # the first run will be interrupted
+    interrupted_run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "user", "content": "what's the weather in sf?"}]},
+    )
+    # sleep a bit to get partial outputs from the first run
+    await asyncio.sleep(2)
+    run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "user", "content": "what's the weather in nyc?"}]},
+        multitask_strategy="interrupt",
+    )
+    # wait until the second run completes
+    await client.runs.join(thread["thread_id"], run["run_id"])
+    ```
+
+=== "Javascript"
+
+    ```js
+    // the first run will be interrupted
+    let interruptedRun = await client.runs.create(
+      thread["thread_id"],
+      assistantId,
+      { input: { messages: [{ role: "human", content: "what's the weather in sf?" }] } }
+    );
+    // sleep a bit to get partial outputs from the first run
+    await new Promise(resolve => setTimeout(resolve, 2000)); 
+
+    let run = await client.runs.create(
+      thread["thread_id"],
+      assistantId,
+      { 
+        input: { messages: [{ role: "human", content: "what's the weather in nyc?" }] },
+        multitaskStrategy: "interrupt" 
+      }
+    );
+
+    // wait until the second run completes
+    await client.runs.join(thread["thread_id"], run["run_id"]);
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+    --url <DEPLOY<ENT_URL>>/threads/<THREAD_ID>/runs \
+    --header 'Content-Type: application/json' \
+    --data "{
+      \"assistant_id\": \"agent\",
+      \"input\": {\"messages\": [{\"role\": \"human\", \"content\": \"what\'s the weather in sf?\"}]},
+    }" && sleep 2 && curl --request POST \
+    --url <DEPLOY<ENT_URL>>/threads/<THREAD_ID>/runs \
+    --header 'Content-Type: application/json' \
+    --data "{
+      \"assistant_id\": \"agent\",
+      \"input\": {\"messages\": [{\"role\": \"human\", \"content\": \"what\'s the weather in nyc?\"}]},
+      \"multitask_strategy\": \"interrupt\"
+    }" && curl --request GET \
+    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/<RUN_ID>/join
+    ```
+
+## View run results
+
+We can see that the thread has partial data from the first run + data from the second run
+
+
+=== "Python"
+
+    ```python
+    state = await client.threads.get_state(thread["thread_id"])
+
+    for m in convert_to_messages(state["values"]["messages"]):
+        m.pretty_print()
+    ```
+
+=== "Javascript"
+
+    ```js
+    const state = await client.threads.getState(thread["thread_id"]);
+
+    for (const m of state['values']['messages']) {
+      prettyPrint(m);
+    }
+    ```
+
+=== "CURL"
+
+    ```bash
+    source pretty_print.sh && curl --request GET \
+    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/state | \
+    jq -c '.values.messages[]' | while read -r element; do
+        type=$(echo "$element" | jq -r '.type')
+        content=$(echo "$element" | jq -r '.content | if type == "array" then tostring else . end')
+        pretty_print "$type" "$content"
+    done
+    ```
+
+Output:
+
+    ================================ Human Message =================================
+    
+    what's the weather in sf?
+    ================================== Ai Message ==================================
+    
+    [{'id': 'toolu_01MjNtVJwEcpujRGrf3x6Pih', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
+    Tool Calls:
+      tavily_search_results_json (toolu_01MjNtVJwEcpujRGrf3x6Pih)
+     Call ID: toolu_01MjNtVJwEcpujRGrf3x6Pih
+      Args:
+        query: weather in san francisco
+    ================================= Tool Message =================================
+    Name: tavily_search_results_json
+    
+    [{"url": "https://www.wunderground.com/hourly/us/ca/san-francisco/KCASANFR2002/date/2024-6-18", "content": "High 64F. Winds W at 10 to 20 mph. A few clouds from time to time. Low 49F. Winds W at 10 to 20 mph. Temp. San Francisco Weather Forecasts. Weather Underground provides local & long-range weather ..."}]
+    ================================ Human Message =================================
+    
+    what's the weather in nyc?
+    ================================== Ai Message ==================================
+    
+    [{'id': 'toolu_01KtE1m1ifPLQAx4fQLyZL9Q', 'input': {'query': 'weather in new york city'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
+    Tool Calls:
+      tavily_search_results_json (toolu_01KtE1m1ifPLQAx4fQLyZL9Q)
+     Call ID: toolu_01KtE1m1ifPLQAx4fQLyZL9Q
+      Args:
+        query: weather in new york city
+    ================================= Tool Message =================================
+    Name: tavily_search_results_json
+    
+    [{"url": "https://www.accuweather.com/en/us/new-york/10021/june-weather/349727", "content": "Get the monthly weather forecast for New York, NY, including daily high/low, historical averages, to help you plan ahead."}]
+    ================================== Ai Message ==================================
+    
+    The search results provide weather forecasts and information for New York City. Based on the top result from AccuWeather, here are some key details about the weather in NYC:
+    
+    - This is a monthly weather forecast for New York City for the month of June.
+    - It includes daily high and low temperatures to help plan ahead.
+    - Historical averages for June in NYC are also provided as a reference point.
+    - More detailed daily or hourly forecasts with precipitation chances, humidity, wind, etc. can be found by visiting the AccuWeather page.
+    
+    So in summary, the search provides a convenient overview of the expected weather conditions in New York City over the next month to give you an idea of what to prepare for if traveling or making plans there. Let me know if you need any other details!
+
+
+Verify that the original, interrupted run was interrupted
+
+=== "Python"
+
+    ```python
+    print((await client.runs.get(thread["thread_id"], interrupted_run["run_id"]))["status"])
+    ```
+
+=== "Javascript"
+
+    ```js
+    console.log((await client.runs.get(thread['thread_id'], interruptedRun["run_id"]))["status"])
+    ```
+
+Output:
+
+    ```
+    'interrupted'
+    ```
+

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

@@ -0,0 +1,48 @@
+# Run application
+
+!!!info  "Prerequisites"
+    - [Running agents](../../agents/run_agents.md#running-agents)
+
+This guide shows how to submit a [run](../../concepts/assistants.md#execution) to your application.
+
+## Graph mode
+
+### Specify input
+First define the input to your graph with in the "Input" section on the left side of the page, below the graph interface.
+
+Studio will attempt to render a form for your input based on the graph's defined [state schema](../../concepts/low_level.md/#schema). To disable this, click the "View Raw" button, which will present you with a JSON editor.
+
+Click the up/down arrows at the top of the "Input" section to toggle through and use previously submitted inputs.
+
+### Run settings
+
+#### Assistant
+
+To specify the [assistant](../../concepts/assistants.md) that is used for the run click the settings button in the bottom left corner. If an assistant is currently selected the button will also list the assistant name. If no assistant is selected it will say "Manage Assistants".
+
+Select the assistant to run and click the "Active" toggle at the top of the modal to activate it. [See here](./studio/manage_assistants.md) for more information on managing assistants.
+
+#### Streaming
+Click the dropdown next to "Submit" and click the toggle to enable/disable streaming.
+
+#### Breakpoints
+To run your graph with breakpoints, click the "Interrupt" button. Select a node and whether to pause before and/or after that node has executed. Click "Continue" in the thread log to resume execution.
+
+
+For more information on breakpoints see [here](../../concepts/human_in_the_loop.md).
+
+### Submit run
+
+To submit the run with the specified input and run settings, click the "Submit" button. This will add a [run](../../concepts/assistants.md#execution) to the existing selected [thread](../../concepts/persistence.md#threads). If no thread is currently selected, a new one will be created.
+
+To cancel the ongoing run, click the "Cancel" button.
+
+
+## Chat mode
+Specify the input to your chat application in the bottom of the conversation panel. Click the "Send message" button to submit the input as a Human message and have the response streamed back.
+
+To cancel the ongoing run, click the "Cancel" button. Click the "Show tool calls" toggle to hide/show tool calls in the conversation.
+
+## Learn more
+
+To run your application from a specific checkpoint in an existing thread, see [this guide](./threads_studio.md#edit-thread-history).

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

@@ -0,0 +1,134 @@
+# Iterate on prompts
+
+## Overview
+
+LangGraph Studio supports two methods for modifying prompts in your graph: direct node editing and the LangSmith Playground interface.
+
+## Direct Node Editing
+
+Studio allows you to edit prompts used inside individual nodes, directly from the graph interface.
+
+!!! info "Prerequisites"
+
+    - [Assistants overview](../../concepts/assistants.md)
+
+### Graph Configuration
+
+Define your [configuration](https://langchain-ai.github.io/langgraph/how-tos/configuration/) to specify prompt fields and their associated nodes using `langgraph_nodes` and `langgraph_type` keys.
+
+#### Configuration Reference
+
+##### `langgraph_nodes`
+
+- **Description**: Specifies which nodes of the graph a configuration field is associated with.
+- **Value Type**: Array of strings, where each string is the name of a node in your graph.
+- **Usage Context**: Include in the `json_schema_extra` dictionary for Pydantic models or the `metadata["json_schema_extra"]` dictionary for dataclasses.
+- **Example**:
+  ```python
+  system_prompt: str = Field(
+      default="You are a helpful AI assistant.",
+      json_schema_extra={"langgraph_nodes": ["call_model", "other_node"]},
+  )
+  ```
+
+##### `langgraph_type`
+
+- **Description**: Specifies the type of configuration field, which determines how it's handled in the UI.
+- **Value Type**: String
+- **Supported Values**:
+  - `"prompt"`: Indicates the field contains prompt text that should be treated specially in the UI.
+- **Usage Context**: Include in the `json_schema_extra` dictionary for Pydantic models or the `metadata["json_schema_extra"]` dictionary for dataclasses.
+- **Example**:
+  ```python
+  system_prompt: str = Field(
+      default="You are a helpful AI assistant.",
+      json_schema_extra={
+          "langgraph_nodes": ["call_model"],
+          "langgraph_type": "prompt",
+      },
+  )
+  ```
+
+#### Example Configuration
+
+```python
+## Using Pydantic
+from pydantic import BaseModel, Field
+from typing import Annotated, Literal
+
+class Configuration(BaseModel):
+    """The configuration for the agent."""
+
+    system_prompt: str = Field(
+        default="You are a helpful AI assistant.",
+        description="The system prompt to use for the agent's interactions. "
+        "This prompt sets the context and behavior for the agent.",
+        json_schema_extra={
+            "langgraph_nodes": ["call_model"],
+            "langgraph_type": "prompt",
+        },
+    )
+
+    model: Annotated[
+        Literal[
+            "anthropic/claude-3-7-sonnet-latest",
+            "anthropic/claude-3-5-haiku-latest",
+            "openai/o1",
+            "openai/gpt-4o-mini",
+            "openai/o1-mini",
+            "openai/o3-mini",
+        ],
+        {"__template_metadata__": {"kind": "llm"}},
+    ] = Field(
+        default="openai/gpt-4o-mini",
+        description="The name of the language model to use for the agent's main interactions. "
+        "Should be in the form: provider/model-name.",
+        json_schema_extra={"langgraph_nodes": ["call_model"]},
+    )
+
+## Using Dataclasses
+from dataclasses import dataclass, field
+
+@dataclass(kw_only=True)
+class Configuration:
+    """The configuration for the agent."""
+
+    system_prompt: str = field(
+        default="You are a helpful AI assistant.",
+        metadata={
+            "description": "The system prompt to use for the agent's interactions. "
+            "This prompt sets the context and behavior for the agent.",
+            "json_schema_extra": {"langgraph_nodes": ["call_model"]},
+        },
+    )
+
+    model: Annotated[str, {"__template_metadata__": {"kind": "llm"}}] = field(
+        default="anthropic/claude-3-5-sonnet-20240620",
+        metadata={
+            "description": "The name of the language model to use for the agent's main interactions. "
+            "Should be in the form: provider/model-name.",
+            "json_schema_extra": {"langgraph_nodes": ["call_model"]},
+        },
+    )
+
+```
+
+### Editing prompts in UI
+
+1. Locate the gear icon on nodes with associated configuration fields
+2. Click to open the configuration modal
+3. Edit the values
+4. Save to update the current assistant version or create a new one
+
+## LangSmith Playground
+
+The [LangSmith Playground](https://
+docs.smith.langchain.com/prompt_engineering/how_to_guides#playground) interface allows testing individual LLM calls without running the full graph:
+
+1. Select a thread
+2. Click "View LLM Runs" on a node. This lists all the LLM calls (if any) made inside the node.
+3. Select an LLM run to open in Playground
+4. Modify prompts and test different model and tool settings
+5. Copy updated prompts back to your graph
+
+For advanced Playground features, click the expand button in the top right corner.

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

@@ -0,0 +1,229 @@
+# Reject
+
+This guide assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide](../../concepts/double_texting.md).
+
+The guide covers the `reject` option for double texting, which rejects the new run of the graph by throwing an error and continues with the original run until completion. Below is a quick example of using the `reject` option.
+
+## Setup
+
+First, we will define a quick helper function for printing out JS and CURL model outputs (you can skip this if using Python):
+
+=== "Javascript"
+
+    ```js
+    function prettyPrint(m) {
+      const padded = " " + m['type'] + " ";
+      const sepLen = Math.floor((80 - padded.length) / 2);
+      const sep = "=".repeat(sepLen);
+      const secondSep = sep + (padded.length % 2 ? "=" : "");
+      
+      console.log(`${sep}${padded}${secondSep}`);
+      console.log("\n\n");
+      console.log(m.content);
+    }
+    ```
+
+=== "CURL"
+
+    ```bash
+    # PLACE THIS IN A FILE CALLED pretty_print.sh
+    pretty_print() {
+      local type="$1"
+      local content="$2"
+      local padded=" $type "
+      local total_width=80
+      local sep_len=$(( (total_width - ${#padded}) / 2 ))
+      local sep=$(printf '=%.0s' $(eval "echo {1.."${sep_len}"}"))
+      local second_sep=$sep
+      if (( (total_width - ${#padded}) % 2 )); then
+        second_sep="${second_sep}="
+      fi
+
+      echo "${sep}${padded}${second_sep}"
+      echo
+      echo "$content"
+    }
+    ```
+
+Now, let's import our required packages and instantiate our client, assistant, and thread.
+
+=== "Python"
+
+    ```python
+    import httpx
+    from langchain_core.messages import convert_to_messages
+    from langgraph_sdk import get_client
+
+    client = get_client(url=<DEPLOYMENT_URL>)
+    # Using the graph deployed with the name "agent"
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
+    // Using the graph deployed with the name "agent"
+    const assistantId = "agent";
+    const thread = await client.threads.create();
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+      --url <DEPLOYMENT_URL>/threads \
+      --header 'Content-Type: application/json' \
+      --data '{}'
+    ```
+
+## Create runs
+
+Now we can run a thread and try to run a second one with the "reject" option, which should fail since we have already started a run:
+
+
+=== "Python"
+
+    ```python
+    run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "user", "content": "what's the weather in sf?"}]},
+    )
+    try:
+        await client.runs.create(
+            thread["thread_id"],
+            assistant_id,
+            input={
+                "messages": [{"role": "user", "content": "what's the weather in nyc?"}]
+            },
+            multitask_strategy="reject",
+        )
+    except httpx.HTTPStatusError as e:
+        print("Failed to start concurrent run", e)
+    ```
+
+=== "Javascript"
+
+    ```js
+    const run = await client.runs.create(
+      thread["thread_id"],
+      assistantId,
+      input={"messages": [{"role": "user", "content": "what's the weather in sf?"}]},
+    );
+    
+    try {
+      await client.runs.create(
+        thread["thread_id"],
+        assistantId,
+        { 
+          input: {"messages": [{"role": "user", "content": "what's the weather in nyc?"}]},
+          multitask_strategy:"reject"
+        },
+      );
+    } catch (e) {
+      console.error("Failed to start concurrent run", e);
+    }
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+    --url <DEPLOY<ENT_URL>>/threads/<THREAD_ID>/runs \
+    --header 'Content-Type: application/json' \
+    --data "{
+      \"assistant_id\": \"agent\",
+      \"input\": {\"messages\": [{\"role\": \"human\", \"content\": \"what\'s the weather in sf?\"}]},
+    }" && curl --request POST \
+    --url <DEPLOY<ENT_URL>>/threads/<THREAD_ID>/runs \
+    --header 'Content-Type: application/json' \
+    --data "{
+      \"assistant_id\": \"agent\",
+      \"input\": {\"messages\": [{\"role\": \"human\", \"content\": \"what\'s the weather in nyc?\"}]},
+      \"multitask_strategy\": \"reject\"
+    }" || { echo "Failed to start concurrent run"; echo "Error: $?" >&2; }
+    ```
+
+Output:
+
+    Failed to start concurrent run Client error '409 Conflict' for url 'http://localhost:8123/threads/f9e7088b-8028-4e5c-88d2-9cc9a2870e50/runs'
+    For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/409
+
+## View run results
+
+We can verify that the original thread finished executing:
+
+=== "Python"
+
+    ```python
+    # wait until the original run completes
+    await client.runs.join(thread["thread_id"], run["run_id"])
+
+    state = await client.threads.get_state(thread["thread_id"])
+
+    for m in convert_to_messages(state["values"]["messages"]):
+        m.pretty_print()
+    ```
+
+=== "Javascript"
+
+    ```js
+    await client.runs.join(thread["thread_id"], run["run_id"]);
+
+    const state = await client.threads.getState(thread["thread_id"]);
+
+    for (const m of state["values"]["messages"]) {
+      prettyPrint(m);
+    }
+    ```
+
+=== "CURL"
+
+    ```bash
+    source pretty_print.sh && curl --request GET \
+    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/<RUN_ID>/join && \
+    curl --request GET --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/state | \
+    jq -c '.values.messages[]' | while read -r element; do
+        type=$(echo "$element" | jq -r '.type')
+        content=$(echo "$element" | jq -r '.content | if type == "array" then tostring else . end')
+        pretty_print "$type" "$content"
+    done
+    ```
+
+Output:
+
+    ================================ Human Message =================================
+    
+    what's the weather in sf?
+    ================================== Ai Message ==================================
+    
+    [{'id': 'toolu_01CyewEifV2Kmi7EFKHbMDr1', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
+    Tool Calls:
+      tavily_search_results_json (toolu_01CyewEifV2Kmi7EFKHbMDr1)
+     Call ID: toolu_01CyewEifV2Kmi7EFKHbMDr1
+      Args:
+        query: weather in san francisco
+    ================================= Tool Message =================================
+    Name: tavily_search_results_json
+    
+    [{"url": "https://www.accuweather.com/en/us/san-francisco/94103/june-weather/347629", "content": "Get the monthly weather forecast for San Francisco, CA, including daily high/low, historical averages, to help you plan ahead."}]
+    ================================== Ai Message ==================================
+    
+    According to the search results from Tavily, the current weather in San Francisco is:
+    
+    The average high temperature in San Francisco in June is around 65°F (18°C), with average lows around 54°F (12°C). June tends to be one of the cooler and foggier months in San Francisco due to the marine layer of fog that often blankets the city during the summer months.
+    
+    Some key points about the typical June weather in San Francisco:
+    
+    - Mild temperatures with highs in the 60s F and lows in the 50s F
+    - Foggy mornings that often burn off to sunny afternoons
+    - Little to no rainfall, as June falls in the dry season
+    - Breezy conditions, with winds off the Pacific Ocean
+    - Layers are recommended for changing weather conditions
+    
+    So in summary, you can expect mild, foggy mornings giving way to sunny but cool afternoons in San Francisco this time of year. The marine layer keeps temperatures moderate compared to other parts of California in June.
+

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

@@ -0,0 +1,233 @@
+# How to use the Rollback option
+
+
+This guide assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide](../../concepts/double_texting.md).
+
+The guide covers the `rollback` option for double texting, which interrupts the prior run of the graph and starts a new one with the double-text. This option is very similar to the `interrupt` option, but in this case the first run is completely deleted from the database and cannot be restarted. Below is a quick example of using the `rollback` option.
+
+## Setup
+
+First, we will define a quick helper function for printing out JS and CURL model outputs (you can skip this if using Python):
+
+=== "Javascript"
+
+    ```js
+    function prettyPrint(m) {
+      const padded = " " + m['type'] + " ";
+      const sepLen = Math.floor((80 - padded.length) / 2);
+      const sep = "=".repeat(sepLen);
+      const secondSep = sep + (padded.length % 2 ? "=" : "");
+      
+      console.log(`${sep}${padded}${secondSep}`);
+      console.log("\n\n");
+      console.log(m.content);
+    }
+    ```
+
+=== "CURL"
+
+    ```bash
+    # PLACE THIS IN A FILE CALLED pretty_print.sh
+    pretty_print() {
+      local type="$1"
+      local content="$2"
+      local padded=" $type "
+      local total_width=80
+      local sep_len=$(( (total_width - ${#padded}) / 2 ))
+      local sep=$(printf '=%.0s' $(eval "echo {1.."${sep_len}"}"))
+      local second_sep=$sep
+      if (( (total_width - ${#padded}) % 2 )); then
+        second_sep="${second_sep}="
+      fi
+
+      echo "${sep}${padded}${second_sep}"
+      echo
+      echo "$content"
+    }
+    ```
+
+Now, let's import our required packages and instantiate our client, assistant, and thread.
+
+=== "Python"
+
+    ```python
+    import asyncio
+
+    import httpx
+    from langchain_core.messages import convert_to_messages
+    from langgraph_sdk import get_client
+
+    client = get_client(url=<DEPLOYMENT_URL>)
+    # Using the graph deployed with the name "agent"
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
+    // Using the graph deployed with the name "agent"
+    const assistantId = "agent";
+    const thread = await client.threads.create();
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+      --url <DEPLOYMENT_URL>/threads \
+      --header 'Content-Type: application/json' \
+      --data '{}'
+    ```
+
+## Create runs
+
+Now let's run a thread with the multitask parameter set to "rollback":
+
+=== "Python"
+
+    ```python
+    # the first run will be rolled back
+    rolled_back_run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "user", "content": "what's the weather in sf?"}]},
+    )
+    run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "user", "content": "what's the weather in nyc?"}]},
+        multitask_strategy="rollback",
+    )
+    # wait until the second run completes
+    await client.runs.join(thread["thread_id"], run["run_id"])
+    ```
+
+=== "Javascript"
+
+    ```js
+    // the first run will be interrupted
+    let rolledBackRun = await client.runs.create(
+      thread["thread_id"],
+      assistantId,
+      { input: { messages: [{ role: "human", content: "what's the weather in sf?" }] } }
+    );
+
+    let run = await client.runs.create(
+      thread["thread_id"],
+      assistant_id,
+      { 
+        input: { messages: [{ role: "human", content: "what's the weather in nyc?" }] },
+        multitaskStrategy: "rollback" 
+      }
+    );
+
+    // wait until the second run completes
+    await client.runs.join(thread["thread_id"], run["run_id"]);
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+    --url <DEPLOY<ENT_URL>>/threads/<THREAD_ID>/runs \
+    --header 'Content-Type: application/json' \
+    --data "{
+      \"assistant_id\": \"agent\",
+      \"input\": {\"messages\": [{\"role\": \"human\", \"content\": \"what\'s the weather in sf?\"}]},
+    }" && curl --request POST \
+    --url <DEPLOY<ENT_URL>>/threads/<THREAD_ID>/runs \
+    --header 'Content-Type: application/json' \
+    --data "{
+      \"assistant_id\": \"agent\",
+      \"input\": {\"messages\": [{\"role\": \"human\", \"content\": \"what\'s the weather in nyc?\"}]},
+      \"multitask_strategy\": \"rollback\"
+    }" && curl --request GET \
+    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/<RUN_ID>/join
+    ```
+
+## View run results
+
+We can see that the thread has data only from the second run
+
+=== "Python"
+
+    ```python
+    state = await client.threads.get_state(thread["thread_id"])
+
+    for m in convert_to_messages(state["values"]["messages"]):
+        m.pretty_print()
+    ```
+
+=== "Javascript"
+
+    ```js
+    const state = await client.threads.getState(thread["thread_id"]);
+
+    for (const m of state['values']['messages']) {
+      prettyPrint(m);
+    }
+    ```
+
+=== "CURL"
+
+    ```bash
+    source pretty_print.sh && curl --request GET \
+    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/state | \
+    jq -c '.values.messages[]' | while read -r element; do
+        type=$(echo "$element" | jq -r '.type')
+        content=$(echo "$element" | jq -r '.content | if type == "array" then tostring else . end')
+        pretty_print "$type" "$content"
+    done
+    ```
+
+Output:
+
+    ================================ Human Message =================================
+    
+    what's the weather in nyc?
+    ================================== Ai Message ==================================
+    
+    [{'id': 'toolu_01JzPqefao1gxwajHQ3Yh3JD', 'input': {'query': 'weather in nyc'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
+    Tool Calls:
+      tavily_search_results_json (toolu_01JzPqefao1gxwajHQ3Yh3JD)
+     Call ID: toolu_01JzPqefao1gxwajHQ3Yh3JD
+      Args:
+        query: weather in nyc
+    ================================= Tool Message =================================
+    Name: tavily_search_results_json
+    
+    [{"url": "https://www.weatherapi.com/", "content": "{'location': {'name': 'New York', 'region': 'New York', 'country': 'United States of America', 'lat': 40.71, 'lon': -74.01, 'tz_id': 'America/New_York', 'localtime_epoch': 1718734479, 'localtime': '2024-06-18 14:14'}, 'current': {'last_updated_epoch': 1718733600, 'last_updated': '2024-06-18 14:00', 'temp_c': 29.4, 'temp_f': 84.9, 'is_day': 1, 'condition': {'text': 'Sunny', 'icon': '//cdn.weatherapi.com/weather/64x64/day/113.png', 'code': 1000}, 'wind_mph': 2.2, 'wind_kph': 3.6, 'wind_degree': 158, 'wind_dir': 'SSE', 'pressure_mb': 1025.0, 'pressure_in': 30.26, 'precip_mm': 0.0, 'precip_in': 0.0, 'humidity': 63, 'cloud': 0, 'feelslike_c': 31.3, 'feelslike_f': 88.3, 'windchill_c': 28.3, 'windchill_f': 82.9, 'heatindex_c': 29.6, 'heatindex_f': 85.3, 'dewpoint_c': 18.4, 'dewpoint_f': 65.2, 'vis_km': 16.0, 'vis_miles': 9.0, 'uv': 7.0, 'gust_mph': 16.5, 'gust_kph': 26.5}}"}]
+    ================================== Ai Message ==================================
+    
+    The weather API results show that the current weather in New York City is sunny with a temperature of around 85°F (29°C). The wind is light at around 2-3 mph from the south-southeast. Overall it looks like a nice sunny summer day in NYC.
+
+
+Verify that the original, rolled back run was deleted
+
+=== "Python"
+
+    ```python
+    try:
+        await client.runs.get(thread["thread_id"], rolled_back_run["run_id"])
+    except httpx.HTTPStatusError as _:
+        print("Original run was correctly deleted")
+    ```
+
+=== "Javascript"
+
+    ```js
+    try {
+      await client.runs.get(thread["thread_id"], rolledBackRun["run_id"]);
+    } catch (e) {
+      console.log("Original run was correctly deleted");
+    }
+    ```
+
+Output:
+
+    Original run was correctly deleted
+

docs/docs/cloud/how-tos/same-thread.md

@@ -0,0 +1,318 @@
+# How to run multiple agents on the same thread
+
+In LangGraph Platform, a thread is not explicitly associated with a particular agent.
+This means that you can run multiple agents on the same thread, which allows a different agent to continue from an initial agent's progress.
+
+In this example, we will create two agents and then call them both on the same thread.
+You'll see that the second agent will respond using information from the [checkpoint](https://langchain-ai.github.io/langgraph/concepts/low_level/#checkpointer-state) generated in the thread by the first agent as context.
+
+## Setup
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url=<DEPLOYMENT_URL>)
+
+    openai_assistant = await client.assistants.create(
+        graph_id="agent", config={"configurable": {"model_name": "openai"}}
+    )
+
+    # There should always be a default assistant with no configuration
+    assistants = await client.assistants.search()
+    default_assistant = [a for a in assistants if not a["config"]][0]
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
+    
+    const openAIAssistant = await client.assistants.create(
+      { graphId: "agent", config: {"configurable": {"model_name": "openai"}}}
+    );
+
+    const assistants = await client.assistants.search();
+    const defaultAssistant = assistants.find(a => !a.config);
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+        --url <DEPLOYMENT_URL>/assistants \
+        --header 'Content-Type: application/json' \
+        --data '{
+            "graph_id": "agent",
+            "config": { "configurable": { "model_name": "openai" } }
+        }' && \
+    curl --request POST \
+        --url <DEPLOYMENT_URL>/assistants/search \
+        --header 'Content-Type: application/json' \
+        --data '{
+            "limit": 10,
+            "offset": 0
+        }' | jq -c 'map(select(.config == null or .config == {})) | .[0]'
+    ```
+
+We can see that these agents are different:
+
+=== "Python"
+
+    ```python
+    print(openai_assistant)
+    ```
+
+=== "Javascript"
+
+    ```js
+    console.log(openAIAssistant);
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request GET \
+        --url <DEPLOYMENT_URL>/assistants/<OPENAI_ASSISTANT_ID>
+    ```
+
+Output:
+
+    {
+        "assistant_id": "db87f39d-b2b1-4da8-ac65-cf81beb3c766",
+        "graph_id": "agent",
+        "created_at": "2024-08-30T21:18:51.850581+00:00",
+        "updated_at": "2024-08-30T21:18:51.850581+00:00",
+        "config": {
+            "configurable": {
+                "model_name": "openai"
+            }
+        },
+        "metadata": {}
+    }
+
+=== "Python"
+
+    ```python
+    print(default_assistant)
+    ```
+
+=== "Javascript"
+
+    ```js
+    console.log(defaultAssistant);
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request GET \
+        --url <DEPLOYMENT_URL>/assistants/<DEFAULT_ASSISTANT_ID>
+    ```
+
+Output:
+
+    {
+        "assistant_id": "fe096781-5601-53d2-b2f6-0d3403f7e9ca",
+        "graph_id": "agent",
+        "created_at": "2024-08-08T22:45:24.562906+00:00",
+        "updated_at": "2024-08-08T22:45:24.562906+00:00",
+        "config": {},
+        "metadata": {
+            "created_by": "system"
+        }
+    }
+
+## Run assistants on thread
+
+### Run OpenAI assistant
+
+We can now run the OpenAI assistant on the thread first.
+
+=== "Python"
+
+    ```python
+    thread = await client.threads.create()
+    input = {"messages": [{"role": "user", "content": "who made you?"}]}
+    async for event in client.runs.stream(
+        thread["thread_id"],
+        openai_assistant["assistant_id"],
+        input=input,
+        stream_mode="updates",
+    ):
+        print(f"Receiving event of type: {event.event}")
+        print(event.data)
+        print("\n\n")
+    ```
+
+=== "Javascript"
+
+    ```js
+    const thread = await client.threads.create();
+    let input =  {"messages": [{"role": "user", "content": "who made you?"}]}
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      openAIAssistant["assistant_id"],
+      {
+        input,
+        streamMode: "updates"
+      }
+    );
+    for await (const event of streamResponse) {
+      console.log(`Receiving event of type: ${event.event}`);
+      console.log(event.data);
+      console.log("\n\n");
+    }
+    ```
+
+=== "CURL"
+
+    ```bash
+    thread_id=$(curl --request POST \
+        --url <DEPLOYMENT_URL>/threads \
+        --header 'Content-Type: application/json' \
+        --data '{}' | jq -r '.thread_id') && \
+    curl --request POST \
+        --url "<DEPLOYMENT_URL>/threads/${thread_id}/runs/stream" \
+        --header 'Content-Type: application/json' \
+        --data '{
+            "assistant_id": <OPENAI_ASSISTANT_ID>,
+            "input": {
+                "messages": [
+                    {
+                        "role": "user",
+                        "content": "who made you?"
+                    }
+                ]
+            },
+            "stream_mode": [
+                "updates"
+            ]
+        }' | \
+        sed 's/\r$//' | \
+        awk '
+        /^event:/ {
+            if (data_content != "") {
+                print data_content "\n"
+            }
+            sub(/^event: /, "Receiving event of type: ", $0)
+            printf "%s...\n", $0
+            data_content = ""
+        }
+        /^data:/ {
+            sub(/^data: /, "", $0)
+            data_content = $0
+        }
+        END {
+            if (data_content != "") {
+                print data_content "\n\n"
+            }
+        }
+    '
+    ```
+
+Output:
+
+    Receiving event of type: metadata
+    {'run_id': '1ef671c5-fb83-6e70-b698-44dba2d9213e'}
+
+
+    Receiving event of type: updates
+    {'agent': {'messages': [{'content': 'I was created by OpenAI, a research organization focused on developing and advancing artificial intelligence technology.', 'additional_kwargs': {}, 'response_metadata': {'finish_reason': 'stop', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_157b3831f5'}, 'type': 'ai', 'name': None, 'id': 'run-f5735b86-b80d-4c71-8dc3-4782b5a9c7c8', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+
+### Run default assistant
+
+Now, we can run it on the default assistant and see that this second assistant is aware of the initial question, and can answer the question, "and you?":
+
+=== "Python"
+
+    ```python
+    input = {"messages": [{"role": "user", "content": "and you?"}]}
+    async for event in client.runs.stream(
+        thread["thread_id"],
+        default_assistant["assistant_id"],
+        input=input,
+        stream_mode="updates",
+    ):
+        print(f"Receiving event of type: {event.event}")
+        print(event.data)
+        print("\n\n")
+    ```
+
+=== "Javascript"
+
+    ```js
+    let input =  {"messages": [{"role": "user", "content": "and you?"}]}
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      defaultAssistant["assistant_id"],
+      {
+        input,
+        streamMode: "updates"
+      }
+    );
+    for await (const event of streamResponse) {
+      console.log(`Receiving event of type: ${event.event}`);
+      console.log(event.data);
+      console.log("\n\n");
+    }
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+        --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/stream \
+        --header 'Content-Type: application/json' \
+        --data '{
+            "assistant_id": <DEFAULT_ASSISTANT_ID>,
+            "input": {
+                "messages": [
+                    {
+                        "role": "user",
+                        "content": "and you?"
+                    }
+                ]
+            },
+            "stream_mode": [
+                "updates"
+            ]
+        }' | \
+        sed 's/\r$//' | \
+        awk '
+        /^event:/ {
+            if (data_content != "") {
+                print data_content "\n"
+            }
+            sub(/^event: /, "Receiving event of type: ", $0)
+            printf "%s...\n", $0
+            data_content = ""
+        }
+        /^data:/ {
+            sub(/^data: /, "", $0)
+            data_content = $0
+        }
+        END {
+            if (data_content != "") {
+                print data_content "\n\n"
+            }
+        }
+    '
+    ```
+
+Output:
+
+    Receiving event of type: metadata
+    {'run_id': '1ef6722d-80b3-6fbb-9324-253796b1cd13'}
+
+
+    Receiving event of type: updates
+    {'agent': {'messages': [{'content': [{'text': 'I am an artificial intelligence created by Anthropic, not by OpenAI. I should not have stated that OpenAI created me, as that is incorrect. Anthropic is the company that developed and trained me using advanced language models and AI technology. I will be more careful about providing accurate information regarding my origins in the future.', 'type': 'text', 'index': 0}], 'additional_kwargs': {}, 'response_metadata': {'stop_reason': 'end_turn', 'stop_sequence': None}, 'type': 'ai', 'name': None, 'id': 'run-ebaacf62-9dd9-4165-9535-db432e4793ec', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': {'input_tokens': 302, 'output_tokens': 72, 'total_tokens': 374}}]}}
+
+
+

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

@@ -0,0 +1,180 @@
+# Stateless Runs
+
+Most of the time, you provide a `thread_id` to your client when you run your graph in order to keep track of prior runs through the persistent state implemented in LangGraph Platform. However, if you don't need to persist the runs you don't need to use the built in persistent state and can create stateless runs.
+
+## Setup
+
+First, let's setup our client:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url=<DEPLOYMENT_URL>)
+    # Using the graph deployed with the name "agent"
+    assistant_id = "agent"
+    # create thread
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
+    // Using the graph deployed with the name "agent"
+    const assistantId = "agent";
+    // create thread
+    const thread = await client.threads.create();
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+        --url <DEPLOYMENT_URL>/assistants/search \
+        --header 'Content-Type: application/json' \
+        --data '{
+            "limit": 10,
+            "offset": 0
+        }' | jq -c 'map(select(.config == null or .config == {})) | .[0].graph_id' && \
+    curl --request POST \
+        --url <DEPLOYMENT_URL>/threads \
+        --header 'Content-Type: application/json' \
+        --data '{}'
+    ```
+
+## Stateless streaming
+
+We can stream the results of a stateless run in an almost identical fashion to how we stream from a run with the state attribute, but instead of passing a value to the `thread_id` parameter, we pass `None`:
+
+=== "Python"
+
+    ```python
+    input = {
+        "messages": [
+            {"role": "user", "content": "Hello! My name is Bagatur and I am 26 years old."}
+        ]
+    }
+
+    async for chunk in client.runs.stream(
+        # Don't pass in a thread_id and the stream will be stateless
+        None,
+        assistant_id,
+        input=input,
+        stream_mode="updates",
+    ):
+        if chunk.data and "run_id" not in chunk.data:
+            print(chunk.data)
+    ```
+
+=== "Javascript"
+
+    ```js
+    let input = {
+      messages: [
+        { role: "user", content: "Hello! My name is Bagatur and I am 26 years old." }
+      ]
+    };
+
+    const streamResponse = client.runs.stream(
+      // Don't pass in a thread_id and the stream will be stateless
+      null,
+      assistantId,
+      {
+        input,
+        streamMode: "updates"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.data && !("run_id" in chunk.data)) {
+        console.log(chunk.data);
+      }
+    }
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+        --url <DEPLOYMENT_URL>/runs/stream \
+        --header 'Content-Type: application/json' \
+        --data "{
+            \"assistant_id\": \"agent\",
+            \"input\": {\"messages\": [{\"role\": \"human\", \"content\": \"Hello! My name is Bagatur and I am 26 years old.\"}]},
+            \"stream_mode\": [
+                \"updates\"
+            ]
+        }" | jq -c 'select(.data and (.data | has("run_id") | not)) | .data'
+    ```
+
+Output:
+
+    {'agent': {'messages': [{'content': "Hello Bagatur! It's nice to meet you. Thank you for introducing yourself and sharing your age. Is there anything specific you'd like to know or discuss? I'm here to help with any questions or topics you're interested in.", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-489ec573-1645-4ce2-a3b8-91b391d50a71', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+
+## Waiting for stateless results
+
+In addition to streaming, you can also wait for a stateless result by using the `.wait` function like follows:
+
+=== "Python"
+
+    ```python
+    stateless_run_result = await client.runs.wait(
+        None,
+        assistant_id,
+        input=input,
+    )
+    print(stateless_run_result)
+    ```
+
+=== "Javascript"
+
+    ```js
+    let statelessRunResult = await client.runs.wait(
+      null,
+      assistantId,
+      { input: input }
+    );
+    console.log(statelessRunResult);
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+        --url <DEPLOYMENT_URL>/runs/wait \
+        --header 'Content-Type: application/json' \
+        --data '{
+            "assistant_id": <ASSISTANT_IDD>,
+        }'
+    ```
+
+Output:
+
+    {
+        'messages': [
+            {
+                'content': 'Hello! My name is Bagatur and I am 26 years old.',
+                'additional_kwargs': {},
+                'response_metadata': {},
+                'type': 'human',
+                'name': None,
+                'id': '5e088543-62c2-43de-9d95-6086ad7f8b48',
+                'example': False}
+            ,
+            {
+                'content': "Hello Bagatur! It's nice to meet you. Thank you for introducing yourself and sharing your age. Is there anything specific you'd like to know or discuss? I'm here to help with any questions or topics you'd like to explore.",
+                'additional_kwargs': {},
+                'response_metadata': {},
+                'type': 'ai',
+                'name': None,
+                'id': 'run-d6361e8d-4d4c-45bd-ba47-39520257f773',
+                'example': False,
+                'tool_calls': [],
+                'invalid_tool_calls': [],
+                'usage_metadata': None
+            }
+        ]
+    }

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

@@ -0,0 +1,957 @@
+# Streaming API
+
+[LangGraph SDK](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/python_sdk_ref/) allows you to [stream outputs](../../concepts/streaming.md) from the LangGraph API server.
+
+!!! note
+
+    LangGraph SDK and LangGraph Server are a part of [LangGraph Platform](../../concepts/langgraph_platform.md).
+
+## Basic usage
+
+Basic usage example:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+    client = get_client(url=<DEPLOYMENT_URL>, api_key=<API_KEY>)
+
+    # Using the graph deployed with the name "agent"
+    assistant_id = "agent"
+
+    # create a thread
+    thread = await client.threads.create()
+    thread_id = thread["thread_id"]
+
+    # create a streaming run
+    # highlight-next-line
+    async for chunk in client.runs.stream(
+        thread_id,
+        assistant_id,
+        input=inputs,
+        stream_mode="updates"
+    ):
+        print(chunk.data)
+    ```
+
+=== "JavaScript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL>, apiKey: <API_KEY> });
+
+    // Using the graph deployed with the name "agent"
+    const assistantID = "agent";
+
+    // create a thread
+    const thread = await client.threads.create();
+    const threadID = thread["thread_id"];
+
+    // create a streaming run
+    // highlight-next-line
+    const streamResponse = client.runs.stream(
+      threadID,
+      assistantID,
+      {
+        input,
+        streamMode: "updates"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(chunk.data);
+    }
+    ```
+
+=== "cURL"
+
+    Create a thread:
+
+    ```bash
+    curl --request POST \
+    --url <DEPLOYMENT_URL>/threads \
+    --header 'Content-Type: application/json' \
+    --data '{}'
+    ```
+
+    Create a streaming run:
+
+    ```bash
+    curl --request POST \
+    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/stream \
+    --header 'Content-Type: application/json' \
+    --header 'x-api-key: <API_KEY>'
+    --data "{
+      \"assistant_id\": \"agent\",
+      \"input\": <inputs>,
+      \"stream_mode\": \"updates\"
+    }"
+    ```
+
+??? example "Extended example: streaming updates"
+
+    This is an example graph you can run in the LangGraph API server.
+    See [LangGraph Platform quickstart](../quick_start.md) for more details.
+
+    ```python
+    # graph.py
+    from typing import TypedDict
+    from langgraph.graph import StateGraph, START, END
+
+    class State(TypedDict):
+        topic: str
+        joke: str
+
+    def refine_topic(state: State):
+        return {"topic": state["topic"] + " and cats"}
+
+    def generate_joke(state: State):
+        return {"joke": f"This is a joke about {state['topic']}"}
+
+    graph = (
+        StateGraph(State)
+        .add_node(refine_topic)
+        .add_node(generate_joke)
+        .add_edge(START, "refine_topic")
+        .add_edge("refine_topic", "generate_joke")
+        .add_edge("generate_joke", END)
+        .compile()
+    )
+    ```
+
+    Once you have a running LangGraph API server, you can interact with it using
+    [LangGraph SDK](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/python_sdk_ref/)
+
+    === "Python"
+
+        ```python
+        from langgraph_sdk import get_client
+        client = get_client(url=<DEPLOYMENT_URL>)
+
+        # Using the graph deployed with the name "agent"
+        assistant_id = "agent"
+
+        # create a thread
+        thread = await client.threads.create()
+        thread_id = thread["thread_id"]
+
+        # create a streaming run
+        # highlight-next-line
+        async for chunk in client.runs.stream(  # (1)!
+            thread_id,
+            assistant_id,
+            input={"topic": "ice cream"},
+            # highlight-next-line
+            stream_mode="updates"  # (2)!
+        ):
+            print(chunk.data)
+        ```
+
+        1. The `client.runs.stream()` method returns an iterator that yields streamed outputs.
+        2. Set `stream_mode="updates"` to stream only the updates to the graph state after each node. Other stream modes are also available. See [supported stream modes](#supported-stream-modes) for details.
+
+    === "JavaScript"
+
+        ```js
+        import { Client } from "@langchain/langgraph-sdk";
+        const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
+
+        // Using the graph deployed with the name "agent"
+        const assistantID = "agent";
+
+        // create a thread
+        const thread = await client.threads.create();
+        const threadID = thread["thread_id"];
+
+        // create a streaming run
+        // highlight-next-line
+        const streamResponse = client.runs.stream(  // (1)!
+          threadID,
+          assistantID,
+          {
+            input: { topic: "ice cream" },
+            // highlight-next-line
+            streamMode: "updates"  // (2)!
+          }
+        );
+        for await (const chunk of streamResponse) {
+          console.log(chunk.data);
+        }
+        ```
+
+        1. The `client.runs.stream()` method returns an iterator that yields streamed outputs.
+        2. Set `streamMode: "updates"` to stream only the updates to the graph state after each node. Other stream modes are also available. See [supported stream modes](#supported-stream-modes) for details.
+
+    === "cURL"
+
+        Create a thread:
+
+        ```bash
+        curl --request POST \
+        --url <DEPLOYMENT_URL>/threads \
+        --header 'Content-Type: application/json' \
+        --data '{}'
+        ```
+
+        Create a streaming run:
+
+        ```bash
+        curl --request POST \
+        --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/stream \
+        --header 'Content-Type: application/json' \
+        --data "{
+          \"assistant_id\": \"agent\",
+          \"input\": {\"topic\": \"ice cream\"},
+          \"stream_mode\": \"updates\"
+        }"
+        ```
+
+    ```output
+    {'run_id': '1f02c2b3-3cef-68de-b720-eec2a4a8e920', 'attempt': 1}
+    {'refine_topic': {'topic': 'ice cream and cats'}}
+    {'generate_joke': {'joke': 'This is a joke about ice cream and cats'}}
+    ```
+
+
+### Supported stream modes
+
+| Mode                             | Description                                                                                                                                                                         | LangGraph Library Method                                                                                 |
+|----------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------|
+| [`values`](#stream-graph-state)  | Stream the full graph state after each [super-step](../../concepts/low_level.md#graphs).                                                                                            | `.stream()` / `.astream()` with [`stream_mode="values"`](../../how-tos/streaming.md#stream-graph-state)  |
+| [`updates`](#stream-graph-state) | Streams the updates to the state after each step of the graph. If multiple updates are made in the same step (e.g., multiple nodes are run), those updates are streamed separately. | `.stream()` / `.astream()` with [`stream_mode="updates"`](../../how-tos/streaming.md#stream-graph-state) |
+| [`messages-tuple`](#messages)    | Streams LLM tokens and metadata for the graph node where the LLM is invoked (useful for chat apps).                                                                                 | `.stream()` / `.astream()` with [`stream_mode="messages"`](../../how-tos/streaming.md#messages)          |
+| [`debug`](#debug)                | Streams as much information as possible throughout the execution of the graph.                                                                                                      | `.stream()` / `.astream()` with [`stream_mode="debug"`](../../how-tos/streaming.md#stream-graph-state)   |
+| [`custom`](#stream-custom-data)  | Streams custom data from inside your graph                                                                                                                                          | `.stream()` / `.astream()` with [`stream_mode="custom"`](../../how-tos/streaming.md#stream-custom-data)  |
+| [`events`](#stream-events)       | Stream all events (including the state of the graph); mainly useful when migrating large LCEL apps.                                                                                 | `.astream_events()`                                                                                      |
+
+### Stream multiple modes
+
+You can pass a list as the `stream_mode` parameter to stream multiple modes at once.
+
+The streamed outputs will be tuples of `(mode, chunk)` where `mode` is the name of the stream mode and `chunk` is the data streamed by that mode.
+
+=== "Python"
+
+    ```python
+    async for chunk in client.runs.stream(
+        thread_id,
+        assistant_id,
+        input=inputs,
+        stream_mode=["updates", "custom"]
+    ):
+        print(chunk)
+    ```
+
+=== "JavaScript"
+
+    ```js
+    const streamResponse = client.runs.stream(
+      threadID,
+      assistantID,
+      {
+        input,
+        streamMode: ["updates", "custom"]
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(chunk);
+    }
+    ```
+
+=== "cURL"
+
+    ```bash
+    curl --request POST \
+     --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/stream \
+     --header 'Content-Type: application/json' \
+     --data "{
+       \"assistant_id\": \"agent\",
+       \"input\": <inputs>,
+       \"stream_mode\": [
+         \"updates\"
+         \"custom\"
+       ]
+     }"
+    ```
+
+## Stream graph state
+
+Use the stream modes `updates` and `values` to stream the state of the graph as it executes.
+
+* `updates` streams the **updates** to the state after each step of the graph.
+* `values` streams the **full value** of the state after each step of the graph.
+
+??? example "Example graph"
+
+    ```python
+    from typing import TypedDict
+    from langgraph.graph import StateGraph, START, END
+
+    class State(TypedDict):
+      topic: str
+      joke: str
+
+    def refine_topic(state: State):
+        return {"topic": state["topic"] + " and cats"}
+
+    def generate_joke(state: State):
+        return {"joke": f"This is a joke about {state['topic']}"}
+
+    graph = (
+      StateGraph(State)
+      .add_node(refine_topic)
+      .add_node(generate_joke)
+      .add_edge(START, "refine_topic")
+      .add_edge("refine_topic", "generate_joke")
+      .add_edge("generate_joke", END)
+      .compile()
+    )
+    ```
+
+!!! note "Stateful runs"
+
+    Examples below assume that you want to **persist the outputs** of a streaming run in the [checkpointer](../../concepts/persistence.md) DB and have created a thread. To create a thread:
+
+    === "Python"
+
+        ```python
+        from langgraph_sdk import get_client
+        client = get_client(url=<DEPLOYMENT_URL>)
+
+        # Using the graph deployed with the name "agent"
+        assistant_id = "agent"
+        # create a thread
+        thread = await client.threads.create()
+        thread_id = thread["thread_id"]
+        ```
+
+    === "JavaScript"
+
+        ```js
+        import { Client } from "@langchain/langgraph-sdk";
+        const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
+
+        // Using the graph deployed with the name "agent"
+        const assistantID = "agent";
+        // create a thread
+        const thread = await client.threads.create();
+        const threadID = thread["thread_id"]
+        ```
+
+    === "cURL"
+
+        ```bash
+        curl --request POST \
+        --url <DEPLOYMENT_URL>/threads \
+        --header 'Content-Type: application/json' \
+        --data '{}'
+        ```
+
+    If you don't need to persist the outputs of a run, you can pass `None` instead of `thread_id` when streaming.
+
+=== "updates"
+
+    Use this to stream only the **state updates** returned by the nodes after each step. The streamed outputs include the name of the node as well as the update.
+
+    === "Python"
+
+        ```python
+        async for chunk in client.runs.stream(
+            thread_id,
+            assistant_id,
+            input={"topic": "ice cream"},
+            # highlight-next-line
+            stream_mode="updates"
+        ):
+            print(chunk.data)
+        ```
+
+    === "JavaScript"
+
+        ```js
+        const streamResponse = client.runs.stream(
+          threadID,
+          assistantID,
+          {
+            input: { topic: "ice cream" },
+            // highlight-next-line
+            streamMode: "updates"
+          }
+        );
+        for await (const chunk of streamResponse) {
+          console.log(chunk.data);
+        }
+        ```
+
+    === "cURL"
+
+        ```bash
+        curl --request POST \
+        --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/stream \
+        --header 'Content-Type: application/json' \
+        --data "{
+          \"assistant_id\": \"agent\",
+          \"input\": {\"topic\": \"ice cream\"},
+          \"stream_mode\": \"updates\"
+        }"
+        ```
+
+===  "values"
+
+    Use this to stream the **full state** of the graph after each step.
+
+    === "Python"
+
+        ```python
+        async for chunk in client.runs.stream(
+            thread_id,
+            assistant_id,
+            input={"topic": "ice cream"},
+            # highlight-next-line
+            stream_mode="values"
+        ):
+            print(chunk.data)
+        ```
+
+    === "JavaScript"
+
+        ```js
+        const streamResponse = client.runs.stream(
+          threadID,
+          assistantID,
+          {
+            input: { topic: "ice cream" },
+            // highlight-next-line
+            streamMode: "values"
+          }
+        );
+        for await (const chunk of streamResponse) {
+          console.log(chunk.data);
+        }
+        ```
+
+    === "cURL"
+
+        ```bash
+        curl --request POST \
+        --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/stream \
+        --header 'Content-Type: application/json' \
+        --data "{
+          \"assistant_id\": \"agent\",
+          \"input\": {\"topic\": \"ice cream\"},
+          \"stream_mode\": \"values\"
+        }"
+        ```
+
+
+## Subgraphs
+
+To include outputs from [subgraphs](../../concepts/subgraphs.md) 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.
+
+```python
+for chunk in client.runs.stream(
+    thread_id,
+    assistant_id,
+    input={"foo": "foo"},
+    # highlight-next-line
+    stream_subgraphs=True, # (1)!
+    stream_mode="updates",
+):
+    print(chunk)
+```
+
+1. Set `stream_subgraphs=True` to stream outputs from subgraphs.
+
+??? example "Extended example: streaming from subgraphs"
+
+    This is an example graph you can run in the LangGraph API server.
+    See [LangGraph Platform quickstart](../quick_start.md) for more details.
+
+    ```python
+    # graph.py
+    from langgraph.graph import START, StateGraph
+    from typing import TypedDict
+
+    # Define subgraph
+    class SubgraphState(TypedDict):
+        foo: str  # note that this key is shared with the parent graph state
+        bar: str
+
+    def subgraph_node_1(state: SubgraphState):
+        return {"bar": "bar"}
+
+    def subgraph_node_2(state: SubgraphState):
+        return {"foo": state["foo"] + state["bar"]}
+
+    subgraph_builder = StateGraph(SubgraphState)
+    subgraph_builder.add_node(subgraph_node_1)
+    subgraph_builder.add_node(subgraph_node_2)
+    subgraph_builder.add_edge(START, "subgraph_node_1")
+    subgraph_builder.add_edge("subgraph_node_1", "subgraph_node_2")
+    subgraph = subgraph_builder.compile()
+
+    # Define parent graph
+    class ParentState(TypedDict):
+        foo: str
+
+    def node_1(state: ParentState):
+        return {"foo": "hi! " + state["foo"]}
+
+    builder = StateGraph(ParentState)
+    builder.add_node("node_1", node_1)
+    builder.add_node("node_2", subgraph)
+    builder.add_edge(START, "node_1")
+    builder.add_edge("node_1", "node_2")
+    graph = builder.compile()
+    ```
+
+    Once you have a running LangGraph API server, you can interact with it using
+    [LangGraph SDK](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/python_sdk_ref/)
+
+    === "Python"
+
+        ```python
+        from langgraph_sdk import get_client
+        client = get_client(url=<DEPLOYMENT_URL>)
+
+        # Using the graph deployed with the name "agent"
+        assistant_id = "agent"
+
+        # create a thread
+        thread = await client.threads.create()
+        thread_id = thread["thread_id"]
+    
+        async for chunk in client.runs.stream(
+            thread_id,
+            assistant_id,
+            input={"foo": "foo"},
+            # highlight-next-line
+            stream_subgraphs=True, # (1)!
+            stream_mode="updates",
+        ):
+            print(chunk)
+        ```
+        
+        1. Set `stream_subgraphs=True` to stream outputs from subgraphs.
+
+    === "JavaScript"
+
+        ```js
+        import { Client } from "@langchain/langgraph-sdk";
+        const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
+
+        // Using the graph deployed with the name "agent"
+        const assistantID = "agent";
+
+        // create a thread
+        const thread = await client.threads.create();
+        const threadID = thread["thread_id"];
+
+        // create a streaming run
+        const streamResponse = client.runs.stream(
+          threadID,
+          assistantID,
+          {
+            input: { foo: "foo" },
+            // highlight-next-line
+            streamSubgraphs: true,  // (1)!
+            streamMode: "updates"
+          }
+        );
+        for await (const chunk of streamResponse) {
+          console.log(chunk);
+        }
+        ```
+
+        1. Set `streamSubgraphs: true` to stream outputs from subgraphs.
+
+    === "cURL"
+
+        Create a thread:
+
+        ```bash
+        curl --request POST \
+        --url <DEPLOYMENT_URL>/threads \
+        --header 'Content-Type: application/json' \
+        --data '{}'
+        ```
+
+        Create a streaming run:
+
+        ```bash
+        curl --request POST \
+        --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/stream \
+        --header 'Content-Type: application/json' \
+        --data "{
+          \"assistant_id\": \"agent\",
+          \"input\": {\"foo\": \"foo\"},
+          \"stream_subgraphs\": true,
+          \"stream_mode\": [
+            \"updates\"
+          ]
+        }"
+        ```
+
+    **Note** that we are receiving not just the node updates, but we also the namespaces which tell us what graph (or subgraph) we are streaming from.
+
+## Debugging {#debug}
+
+Use the `debug` streaming mode to stream as much information as possible throughout the execution of the graph. The streamed outputs include the name of the node as well as the full state.
+
+=== "Python"
+
+    ```python
+    async for chunk in client.runs.stream(
+        thread_id,
+        assistant_id,
+        input={"topic": "ice cream"},
+        # highlight-next-line
+        stream_mode="debug"
+    ):
+        print(chunk.data)
+    ```
+
+=== "JavaScript"
+
+    ```js
+    const streamResponse = client.runs.stream(
+      threadID,
+      assistantID,
+      {
+        input: { topic: "ice cream" },
+        // highlight-next-line
+        streamMode: "debug"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(chunk.data);
+    }
+    ```
+
+=== "cURL"
+
+    ```bash
+    curl --request POST \
+    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/stream \
+    --header 'Content-Type: application/json' \
+    --data "{
+      \"assistant_id\": \"agent\",
+      \"input\": {\"topic\": \"ice cream\"},
+      \"stream_mode\": \"debug\"
+    }"
+    ```
+
+## LLM tokens {#messages}
+
+Use the `messages-tuple` streaming mode to stream Large Language Model (LLM) outputs **token by token** from any part of your graph, including nodes, tools, subgraphs, or tasks.
+
+The streamed output from [`messages-tuple` mode](#supported-stream-modes) is a tuple `(message_chunk, metadata)` where:
+
+- `message_chunk`: the token or message segment from the LLM.
+- `metadata`: a dictionary containing details about the graph node and LLM invocation.
+ 
+??? example "Example graph"
+
+    ```python
+    from dataclasses import dataclass
+
+    from langchain.chat_models import init_chat_model
+    from langgraph.graph import StateGraph, START
+
+    @dataclass
+    class MyState:
+        topic: str
+        joke: str = ""
+
+    llm = init_chat_model(model="openai:gpt-4o-mini")
+
+    def call_model(state: MyState):
+        """Call the LLM to generate a joke about a topic"""
+        # highlight-next-line
+        llm_response = llm.invoke( # (1)!
+            [
+                {"role": "user", "content": f"Generate a joke about {state.topic}"}
+            ]
+        )
+        return {"joke": llm_response.content}
+
+    graph = (
+        StateGraph(MyState)
+        .add_node(call_model)
+        .add_edge(START, "call_model")
+        .compile()
+    )
+    ```
+
+    1. Note that the message events are emitted even when the LLM is run using `.invoke` rather than `.stream`.
+
+=== "Python"
+
+    ```python
+    async for chunk in client.runs.stream(
+        thread_id,
+        assistant_id,
+        input={"topic": "ice cream"},
+        # highlight-next-line
+        stream_mode="messages-tuple",
+    ):
+        if chunk.event != "messages":
+            continue
+
+        message_chunk, metadata = chunk.data  # (1)!
+        if message_chunk["content"]:
+            print(message_chunk["content"], end="|", flush=True)
+    ```
+
+    1. The "messages-tuple" stream mode returns an iterator of tuples `(message_chunk, metadata)` where `message_chunk` is the token streamed by the LLM and `metadata` is a dictionary with information about the graph node where the LLM was called and other information.
+
+=== "JavaScript"
+
+    ```js
+    const streamResponse = client.runs.stream(
+      threadID,
+      assistantID,
+      {
+        input: { topic: "ice cream" },
+        // highlight-next-line
+        streamMode: "messages-tuple"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.event !== "messages") {
+        continue;
+      }
+      console.log(chunk.data[0]["content"]);  // (1)!
+    }
+    ```
+
+    1. The "messages-tuple" stream mode returns an iterator of tuples `(message_chunk, metadata)` where `message_chunk` is the token streamed by the LLM and `metadata` is a dictionary with information about the graph node where the LLM was called and other information.
+
+=== "cURL"
+
+    ```bash
+    curl --request POST \
+    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/stream \
+    --header 'Content-Type: application/json' \
+    --data "{
+      \"assistant_id\": \"agent\",
+      \"input\": {\"topic\": \"ice cream\"},
+      \"stream_mode\": \"messages-tuple\"
+    }"
+    ```
+
+### Filter LLM tokens
+
+* To filter the streamed tokens by LLM invocation, you can [associate `tags` with LLM invocations](../../how-tos/streaming.md#filter-by-llm-invocation).
+* To stream tokens only from specific nodes, use `stream_mode="messages"` and [filter the outputs by the `langgraph_node` field](../../how-tos/streaming.md#filter-by-node) in the streamed metadata.
+
+## Stream custom data
+
+To send **custom user-defined data**:
+
+=== "Python"
+
+    ```python
+    async for chunk in client.runs.stream(
+        thread_id,
+        assistant_id,
+        input={"query": "example"},
+        # highlight-next-line
+        stream_mode="custom"
+    ):
+        print(chunk.data)
+    ```
+
+=== "JavaScript"
+
+    ```js
+    const streamResponse = client.runs.stream(
+      threadID,
+      assistantID,
+      {
+        input: { query: "example" },
+        // highlight-next-line
+        streamMode: "custom"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(chunk.data);
+    }
+    ```
+
+=== "cURL"
+
+    ```bash
+    curl --request POST \
+    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/stream \
+    --header 'Content-Type: application/json' \
+    --data "{
+      \"assistant_id\": \"agent\",
+      \"input\": {\"query\": \"example\"},
+      \"stream_mode\": \"custom\"
+    }"
+    ```
+
+## Stream events
+
+To stream all events, including the state of the graph:
+
+=== "Python"
+
+    ```python
+    async for chunk in client.runs.stream(
+        thread_id,
+        assistant_id,
+        input={"topic": "ice cream"},
+        # highlight-next-line
+        stream_mode="events"
+    ):
+        print(chunk.data)
+    ```
+
+=== "JavaScript"
+
+    ```js
+    const streamResponse = client.runs.stream(
+      threadID,
+      assistantID,
+      {
+        input: { topic: "ice cream" },
+        // highlight-next-line
+        streamMode: "events"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(chunk.data);
+    }
+    ```
+
+=== "cURL"
+
+    ```bash
+    curl --request POST \
+    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/stream \
+    --header 'Content-Type: application/json' \
+    --data "{
+      \"assistant_id\": \"agent\",
+      \"input\": {\"topic\": \"ice cream\"},
+      \"stream_mode\": \"events\"
+    }"
+    ```
+
+## Stateless runs
+
+If you don't want to **persist the outputs** of a streaming run in the [checkpointer](../../concepts/persistence.md) DB, you can create a stateless run without creating a thread:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+    client = get_client(url=<DEPLOYMENT_URL>, api_key=<API_KEY>)
+
+    async for chunk in client.runs.stream(
+        # highlight-next-line
+        None,  # (1)!
+        assistant_id,
+        input=inputs,
+        stream_mode="updates"
+    ):
+        print(chunk.data)
+    ```
+
+    1. We are passing `None` instead of a `thread_id` UUID.
+
+=== "JavaScript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL>, apiKey: <API_KEY> });
+
+    // create a streaming run
+    // highlight-next-line
+    const streamResponse = client.runs.stream(
+      // highlight-next-line
+      null,  // (1)!
+      assistantID,
+      {
+        input,
+        streamMode: "updates"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(chunk.data);
+    }
+    ```
+
+    1. We are passing `None` instead of a `thread_id` UUID.
+
+=== "cURL"
+
+    ```bash
+    curl --request POST \
+    --url <DEPLOYMENT_URL>/runs/stream \
+    --header 'Content-Type: application/json' \
+    --header 'x-api-key: <API_KEY>'
+    --data "{
+      \"assistant_id\": \"agent\",
+      \"input\": <inputs>,
+      \"stream_mode\": \"updates\"
+    }"
+    ```
+
+## Join and stream
+
+LangGraph Platform allows you to join an active [background run](../how-tos/background_run.md) and stream outputs from it. To do so, you can use [LangGraph SDK's](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/python_sdk_ref/) `client.runs.join_stream` method:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+    client = get_client(url=<DEPLOYMENT_URL>, api_key=<API_KEY>)
+
+    # highlight-next-line
+    async for chunk in client.runs.join_stream(
+        thread_id,
+        # highlight-next-line
+        run_id,  # (1)!
+    ):
+        print(chunk)
+    ```
+
+    1. This is the `run_id` of an existing run you want to join.
+
+
+=== "JavaScript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL>, apiKey: <API_KEY> });
+
+    // highlight-next-line
+    const streamResponse = client.runs.joinStream(
+      threadID,
+      // highlight-next-line
+      runId  // (1)!
+    );
+    for await (const chunk of streamResponse) {
+      console.log(chunk);
+    }
+    ```
+
+    1. This is the `run_id` of an existing run you want to join.
+
+=== "cURL"
+
+    ```bash
+    curl --request GET \
+    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/<RUN_ID>/stream \
+    --header 'Content-Type: application/json' \
+    --header 'x-api-key: <API_KEY>'
+    ```
+
+!!! warning "Outputs not buffered"
+
+    When you use `.join_stream`, output is not buffered, so any output produced before joining will not be received.
+
+## API Reference
+
+For API usage and implementation, refer to the [API reference](../reference/api/api_ref.html#tag/thread-runs/POST/threads/{thread_id}/runs/stream). 

docs/docs/cloud/how-tos/studio/manage_assistants.md

@@ -0,0 +1,19 @@
+# Manage assistants
+
+!!! info "Prerequisites"
+
+    - [Assistants Overview](../../../concepts/assistants.md)
+
+LangGraph Studio lets you view, edit, and update your assistants, and allows you to run your graph using these assistant configurations.
+
+## Graph mode
+
+To view your assistants, click the "Manage Assistants" button in the bottom left corner.
+
+This opens a modal for you to view all the assistants for the selected graph. Specify the assistant and its version you would like to mark as "Active", and this assistant will be used when submitting runs.
+
+By default, the "Default configuration" option will be active. This option reflects the default configuration defined in your graph. Edits made to this configuration will be used to update the run-time configuration, but will not update or create a new assistant unless you click "Create new assistant".
+
+## Chat mode
+
+Chat mode enables you to switch through the different assistants in your graph via the dropdown selector at the top of the page. To create, edit, or delete assistants, use Graph mode.

docs/docs/cloud/how-tos/studio/quick_start.md

@@ -0,0 +1,112 @@
+!!! info "Prerequisites"
+
+    - [LangGraph Studio Overview](../../../concepts/langgraph_studio.md)
+
+LangGraph Studio supports connecting to two types of graphs:
+
+- Graphs deployed on [LangGraph Platform](../../../cloud/quick_start.md)
+- Graphs running locally via the [LangGraph Server](../../../tutorials/langgraph-platform/local-server.md).
+
+LangGraph Studio is accessed from the LangSmith UI, within the LangGraph Platform Deployments tab.
+
+## Deployed application
+
+For applications that are [deployed](../../quick_start.md) on LangGraph Platform, you can access Studio as part of that deployment. To do so, navigate to the deployment in LangGraph Platform within the LangSmith UI and click the "LangGraph Studio" button.
+
+This will load the Studio UI connected to your live deployment, allowing you to create, read, and update the [threads](../../../concepts/persistence.md#threads), [assistants](../../../concepts/assistants.md), and [memory](../../../concepts//memory.md) in that deployment.
+
+## Local development server
+
+To test your locally running application using LangGraph Studio, ensure your application is set up following [this guide](https://langchain-ai.github.io/langgraph/cloud/deployment/setup/).
+
+!!! info "LangSmith Tracing"
+    For local development, if you do not wish to have data traced to LangSmith, set `LANGSMITH_TRACING=false` in your application's `.env` file. With tracing disabled, no data will leave your local server.
+
+Next, install the [LangGraph CLI](../../../concepts/langgraph_cli.md):
+
+```
+pip install -U "langgraph-cli[inmem]"
+```
+
+and run:
+
+```
+langgraph dev
+```
+
+!!! warning "Browser Compatibility"
+    Safari blocks `localhost` connections to Studio. To work around this, run the above command with `--tunnel` to access Studio via a secure tunnel.
+
+This will start the LangGraph Server locally, running in-memory. The server will run in watch mode, listening for and automatically restarting on code changes. Read this [reference](https://langchain-ai.github.io/langgraph/cloud/reference/cli/#dev) to learn about all the options for starting the API server.
+
+If successful, you will see the following logs:
+
+> Ready!
+>
+> - API: [http://localhost:2024](http://localhost:2024/)
+>
+> - Docs: http://localhost:2024/docs
+>
+> - LangGraph Studio Web UI: https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024
+
+Once running, you will automatically be directed to LangGraph Studio.
+
+For an already running server, access Studio by either:
+
+1.  Directly navigate to the following URL: `https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024`.
+2.  Within LangSmith, navigate to the LangGraph Platform Deployments tab, click the "LangGraph Studio" button, enter `http://127.0.0.1:2024` and click "Connect".
+
+If running your server at a different host or port, simply update the `baseUrl` to match.
+
+### (Optional) Attach a debugger
+
+For step-by-step debugging with breakpoints and variable inspection:
+
+```bash
+# Install debugpy package
+pip install debugpy
+
+# Start server with debugging enabled
+langgraph dev --debug-port 5678
+```
+
+Then attach your preferred debugger:
+
+=== "VS Code"
+
+    Add this configuration to `launch.json`:
+
+    ```json
+    {
+        "name": "Attach to LangGraph",
+        "type": "debugpy",
+        "request": "attach",
+        "connect": {
+          "host": "0.0.0.0",
+          "port": 5678
+        }
+    }
+    ```
+
+=== "PyCharm" 
+
+    1. Go to Run → Edit Configurations 
+    2. Click + and select "Python Debug Server" 
+    3. Set IDE host name: `localhost` 
+    4. Set port: `5678` (or the port number you chose in the previous step) 
+    5. Click "OK" and start debugging
+
+## Troubleshooting
+
+For issues getting started, please see this [troubleshooting guide](../../../troubleshooting/studio.md).
+
+## Next steps
+
+See the following guides for more information on how to use Studio:
+
+- [Run application](../invoke_studio.md)
+- [Manage assistants](./manage_assistants.md)
+- [Manage threads](../threads_studio.md)
+- [Iterate on prompts](../iterate_graph_studio.md)
+- [Debug LangSmith traces](../clone_traces_studio.md)
+- [Add node to dataset](../datasets_studio.md)

docs/docs/cloud/how-tos/studio/run_evals.md

@@ -0,0 +1,57 @@
+# Run experiments over a dataset
+
+LangGraph Studio supports evaluations by allowing you to run your assistant over a pre-defined LangSmith dataset. This enables you to understand how your application performs over a variety of inputs, compare the results to reference outputs, and score the results using [evaluators](../../../agents/evals.md).
+
+This guide shows you how to run an experiment end-to-end from Studio.
+
+---
+
+## Prerequisites
+
+Before running an experiment, ensure you have the following:
+
+1.  **A LangSmith dataset**: Your dataset should contain the inputs you want to test and optionally, reference outputs for comparison.
+
+    - The schema for the inputs must match the required input schema for the assistant. For more information on schemas, see [here](../../../concepts/low_level.md#schema).
+    - For more on creating datasets, see [How to Manage Datasets](https://docs.smith.langchain.com/evaluation/how_to_guides/manage_datasets_in_application#set-up-your-dataset).
+
+2.  **(Optional) Evaluators**: You can attach evaluators (e.g., LLM-as-a-Judge, heuristics, or custom functions) to your dataset in LangSmith. These will run automatically after the graph has processed all inputs.
+
+    - To learn more, read about [Evaluation Concepts](https://docs.smith.langchain.com/evaluation/concepts#evaluators).
+
+3.  **A running application**: The experiment can be run against:
+    - An application deployed on [LangGraph Platform](../../quick_start.md).
+    - A locally running application started via the [langgraph-cli](../../../tutorials/langgraph-platform/local-server.md).
+
+---
+
+## Step-by-step guide
+
+### 1. Launch the experiment
+
+Click the **Run experiment** button in the top right corner of the Studio page.
+
+### 2. Select your dataset
+
+In the modal that appears, select the dataset (or a specific dataset split) to use for the experiment and click **Start**.
+
+### 3. Monitor the progress
+
+All of the inputs in the dataset will now be run against the active assistant. Monitor the experiment's progress via the badge in the top right corner.
+
+You can continue to work in Studio while the experiment runs in the background. Click the arrow icon button at any time to navigate to LangSmith and view the detailed experiment results.
+
+---
+
+## Troubleshooting
+
+### "Run experiment" button is disabled
+
+If the "Run experiment" button is disabled, check the following:
+
+- **Deployed application**: If your application is deployed on LangGraph Platform, you may need to create a new revision to enable this feature.
+- **Local development server**: If you are running your application locally, make sure you have upgraded to the latest version of the `langgraph-cli` (`pip install -U langgraph-cli`). Additionally, ensure you have tracing enabled by setting the `LANGSMITH_API_KEY` in your project's `.env` file.
+
+### Evaluator results are missing
+
+When you run an experiment, any attached evaluators are scheduled for execution in a queue. If you don't see results immediately, it likely means they are still pending.

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

@@ -0,0 +1,37 @@
+# Manage threads
+
+Studio allows you to view [threads](../../concepts/persistence.md#threads) from the server and edit their state.
+
+## View threads
+
+### Graph mode
+
+1. In the top of the right-hand pane, select the dropdown menu to view existing threads.
+1. Select the desired thread, and the thread history will populate in the right-hand side of the page.
+1. To create a new thread, click `+ New Thread` and [submit a run](../how-tos/invoke_studio.md#graph-mode).
+
+To view more granular information in the thread, drag the slider at the top of the page to the right. To view less information, drag the slider to the left. Additionally, collapse or expand individual turns, nodes, and keys of the state.
+
+Switch between `Pretty` and `JSON` mode for different rendering formats.
+
+### Chat mode
+
+1. View all threads in the right-hand pane of the page.
+2. Select the desired thread and the thread history will populate in the center panel.
+3. To create a new thread, click the plus button and [submit a run](../how-tos/invoke_studio.md#chat-mode).
+
+## Edit thread history
+
+### Graph mode
+
+To edit the state of the thread, select "edit node state" next to the desired node. Edit the node's output as desired and click "fork" to confirm. This will create a new forked run from the checkpoint of the selected node.
+
+If you instead want to re-run the thread from a given checkpoint without editing the state, click the "Re-run from here". This will again create a new forked run from the selected checkpoint. This is useful for re-running with changes that are not specific to the state, such as the selected assistant.
+
+### Chat mode
+
+To edit a human message in the thread, click the edit button below the human message. Edit the message as desired and submit. This will create a new fork of the conversation history. To re-generate an AI message, click the retry icon below the AI message.
+
+## Learn more
+
+For more information about time travel, [see here](../../concepts/time-travel.md).

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

@@ -0,0 +1,661 @@
+# How to integrate LangGraph into your React application
+
+!!! info "Prerequisites"
+
+    - [LangGraph Platform](../../concepts/langgraph_platform.md)
+    - [LangGraph Server](../../concepts/langgraph_server.md)
+
+The `useStream()` React hook provides a seamless way to integrate LangGraph into your React applications. It handles all the complexities of streaming, state management, and branching logic, letting you focus on building great chat experiences.
+
+Key features:
+
+- Messages streaming: Handle a stream of message chunks to form a complete message
+- Automatic state management for messages, interrupts, loading states, and errors
+- Conversation branching: Create alternate conversation paths from any point in the chat history
+- UI-agnostic design: bring your own components and styling
+
+Let's explore how to use `useStream()` in your React application.
+
+The `useStream()` provides a solid foundation for creating bespoke chat experiences. For pre-built chat components and interfaces, we also recommend checking out [CopilotKit](https://docs.copilotkit.ai/coagents/quickstart/langgraph) and [assistant-ui](https://www.assistant-ui.com/docs/runtimes/langgraph).
+
+## Installation
+
+```bash
+npm install @langchain/langgraph-sdk @langchain/core
+```
+
+## Example
+
+```tsx
+"use client";
+
+import { useStream } from "@langchain/langgraph-sdk/react";
+import type { Message } from "@langchain/langgraph-sdk";
+
+export default function App() {
+  const thread = useStream<{ messages: Message[] }>({
+    apiUrl: "http://localhost:2024",
+    assistantId: "agent",
+    messagesKey: "messages",
+  });
+
+  return (
+    <div>
+      <div>
+        {thread.messages.map((message) => (
+          <div key={message.id}>{message.content as string}</div>
+        ))}
+      </div>
+
+      <form
+        onSubmit={(e) => {
+          e.preventDefault();
+
+          const form = e.target as HTMLFormElement;
+          const message = new FormData(form).get("message") as string;
+
+          form.reset();
+          thread.submit({ messages: [{ type: "human", content: message }] });
+        }}
+      >
+        <input type="text" name="message" />
+
+        {thread.isLoading ? (
+          <button key="stop" type="button" onClick={() => thread.stop()}>
+            Stop
+          </button>
+        ) : (
+          <button keytype="submit">Send</button>
+        )}
+      </form>
+    </div>
+  );
+}
+```
+
+## Customizing Your UI
+
+The `useStream()` hook takes care of all the complex state management behind the scenes, providing you with simple interfaces to build your UI. Here's what you get out of the box:
+
+- Thread state management
+- Loading and error states
+- Interrupts
+- Message handling and updates
+- Branching support
+
+Here are some examples on how to use these features effectively:
+
+### Loading States
+
+The `isLoading` property tells you when a stream is active, enabling you to:
+
+- Show a loading indicator
+- Disable input fields during processing
+- Display a cancel button
+
+```tsx
+export default function App() {
+  const { isLoading, stop } = useStream<{ messages: Message[] }>({
+    apiUrl: "http://localhost:2024",
+    assistantId: "agent",
+    messagesKey: "messages",
+  });
+
+  return (
+    <form>
+      {isLoading && (
+        <button key="stop" type="button" onClick={() => stop()}>
+          Stop
+        </button>
+      )}
+    </form>
+  );
+}
+```
+
+### Resume a stream after page refresh
+
+The `useStream()` hook can automatically resume an ongoing run upon mounting by setting `reconnectOnMount: true`. This is useful for continuing a stream after a page refresh, ensuring no messages and events generated during the downtime are lost.
+
+```tsx
+const thread = useStream<{ messages: Message[] }>({
+  apiUrl: "http://localhost:2024",
+  assistantId: "agent",
+  reconnectOnMount: true,
+});
+```
+
+By default the ID of the created run is stored in `window.sessionStorage`, which can be swapped by passing a custom storage in `reconnectOnMount` instead. The storage is used to persist the in-flight run ID for a thread (under `lg:stream:${threadId}` key).
+
+```tsx
+const thread = useStream<{ messages: Message[] }>({
+  apiUrl: "http://localhost:2024",
+  assistantId: "agent",
+  reconnectOnMount: () => window.localStorage,
+});
+```
+
+You can also manually manage the resuming process by using the run callbacks to persist the run metadata and the `joinStream` function to resume the stream. Make sure to pass `streamResumable: true` when creating the run; otherwise some events might be lost.
+
+```tsx
+import type { Message } from "@langchain/langgraph-sdk";
+import { useStream } from "@langchain/langgraph-sdk/react";
+import { useCallback, useState, useEffect, useRef } from "react";
+
+export default function App() {
+  const [threadId, onThreadId] = useSearchParam("threadId");
+
+  const thread = useStream<{ messages: Message[] }>({
+    apiUrl: "http://localhost:2024",
+    assistantId: "agent",
+
+    threadId,
+    onThreadId,
+
+    onCreated: (run) => {
+      window.sessionStorage.setItem(`resume:${run.thread_id}`, run.run_id);
+    },
+    onFinish: (_, run) => {
+      window.sessionStorage.removeItem(`resume:${run?.thread_id}`);
+    },
+  });
+
+  // Ensure that we only join the stream once per thread.
+  const joinedThreadId = useRef<string | null>(null);
+  useEffect(() => {
+    if (!threadId) return;
+
+    const resume = window.sessionStorage.getItem(`resume:${threadId}`);
+    if (resume && joinedThreadId.current !== threadId) {
+      thread.joinStream(resume);
+      joinedThreadId.current = threadId;
+    }
+  }, [threadId]);
+
+  return (
+    <form
+      onSubmit={(e) => {
+        e.preventDefault();
+        const form = e.target as HTMLFormElement;
+        const message = new FormData(form).get("message") as string;
+        thread.submit(
+          { messages: [{ type: "human", content: message }] },
+          { streamResumable: true }
+        );
+      }}
+    >
+      <div>
+        {thread.messages.map((message) => (
+          <div key={message.id}>{message.content as string}</div>
+        ))}
+      </div>
+      <input type="text" name="message" />
+      <button type="submit">Send</button>
+    </form>
+  );
+}
+
+// Utility method to retrieve and persist data in URL as search param
+function useSearchParam(key: string) {
+  const [value, setValue] = useState<string | null>(() => {
+    const params = new URLSearchParams(window.location.search);
+    return params.get(key) ?? null;
+  });
+
+  const update = useCallback(
+    (value: string | null) => {
+      setValue(value);
+
+      const url = new URL(window.location.href);
+      if (value == null) {
+        url.searchParams.delete(key);
+      } else {
+        url.searchParams.set(key, value);
+      }
+
+      window.history.pushState({}, "", url.toString());
+    },
+    [key]
+  );
+
+  return [value, update] as const;
+}
+```
+
+### Thread Management
+
+Keep track of conversations with built-in thread management. You can access the current thread ID and get notified when new threads are created:
+
+```tsx
+const [threadId, setThreadId] = useState<string | null>(null);
+
+const thread = useStream<{ messages: Message[] }>({
+  apiUrl: "http://localhost:2024",
+  assistantId: "agent",
+
+  threadId: threadId,
+  onThreadId: setThreadId,
+});
+```
+
+We recommend storing the `threadId` in your URL's query parameters to let users resume conversations after page refreshes.
+
+### Messages Handling
+
+The `useStream()` hook will keep track of the message chunks received from the server and concatenate them together to form a complete message. The completed message chunks can be retrieved via the `messages` property.
+
+By default, the `messagesKey` is set to `messages`, where it will append the new messages chunks to `values["messages"]`. If you store messages in a different key, you can change the value of `messagesKey`.
+
+```tsx
+import type { Message } from "@langchain/langgraph-sdk";
+import { useStream } from "@langchain/langgraph-sdk/react";
+
+export default function HomePage() {
+  const thread = useStream<{ messages: Message[] }>({
+    apiUrl: "http://localhost:2024",
+    assistantId: "agent",
+    messagesKey: "messages",
+  });
+
+  return (
+    <div>
+      {thread.messages.map((message) => (
+        <div key={message.id}>{message.content as string}</div>
+      ))}
+    </div>
+  );
+}
+```
+
+Under the hood, the `useStream()` hook will use the `streamMode: "messages-tuple"` to receive a stream of messages (i.e. individual LLM tokens) from any LangChain chat model invocations inside your graph nodes. Learn more about messages streaming in the [streaming](../how-tos/streaming.md#messages) guide.
+
+### Interrupts
+
+The `useStream()` hook exposes the `interrupt` property, which will be filled with the last interrupt from the thread. You can use interrupts to:
+
+- Render a confirmation UI before executing a node
+- Wait for human input, allowing agent to ask the user with clarifying questions
+
+Learn more about interrupts in the [How to handle interrupts](../../how-tos/human_in_the_loop/wait-user-input.ipynb) guide.
+
+```tsx
+const thread = useStream<{ messages: Message[] }, { InterruptType: string }>({
+  apiUrl: "http://localhost:2024",
+  assistantId: "agent",
+  messagesKey: "messages",
+});
+
+if (thread.interrupt) {
+  return (
+    <div>
+      Interrupted! {thread.interrupt.value}
+      <button
+        type="button"
+        onClick={() => {
+          // `resume` can be any value that the agent accepts
+          thread.submit(undefined, { command: { resume: true } });
+        }}
+      >
+        Resume
+      </button>
+    </div>
+  );
+}
+```
+
+### Branching
+
+For each message, you can use `getMessagesMetadata()` to get the first checkpoint from which the message has been first seen. You can then create a new run from the checkpoint preceding the first seen checkpoint to create a new branch in a thread.
+
+A branch can be created in following ways:
+
+1. Edit a previous user message.
+2. Request a regeneration of a previous assistant message.
+
+```tsx
+"use client";
+
+import type { Message } from "@langchain/langgraph-sdk";
+import { useStream } from "@langchain/langgraph-sdk/react";
+import { useState } from "react";
+
+function BranchSwitcher({
+  branch,
+  branchOptions,
+  onSelect,
+}: {
+  branch: string | undefined;
+  branchOptions: string[] | undefined;
+  onSelect: (branch: string) => void;
+}) {
+  if (!branchOptions || !branch) return null;
+  const index = branchOptions.indexOf(branch);
+
+  return (
+    <div className="flex items-center gap-2">
+      <button
+        type="button"
+        onClick={() => {
+          const prevBranch = branchOptions[index - 1];
+          if (!prevBranch) return;
+          onSelect(prevBranch);
+        }}
+      >
+        Prev
+      </button>
+      <span>
+        {index + 1} / {branchOptions.length}
+      </span>
+      <button
+        type="button"
+        onClick={() => {
+          const nextBranch = branchOptions[index + 1];
+          if (!nextBranch) return;
+          onSelect(nextBranch);
+        }}
+      >
+        Next
+      </button>
+    </div>
+  );
+}
+
+function EditMessage({
+  message,
+  onEdit,
+}: {
+  message: Message;
+  onEdit: (message: Message) => void;
+}) {
+  const [editing, setEditing] = useState(false);
+
+  if (!editing) {
+    return (
+      <button type="button" onClick={() => setEditing(true)}>
+        Edit
+      </button>
+    );
+  }
+
+  return (
+    <form
+      onSubmit={(e) => {
+        e.preventDefault();
+        const form = e.target as HTMLFormElement;
+        const content = new FormData(form).get("content") as string;
+
+        form.reset();
+        onEdit({ type: "human", content });
+        setEditing(false);
+      }}
+    >
+      <input name="content" defaultValue={message.content as string} />
+      <button type="submit">Save</button>
+    </form>
+  );
+}
+
+export default function App() {
+  const thread = useStream({
+    apiUrl: "http://localhost:2024",
+    assistantId: "agent",
+    messagesKey: "messages",
+  });
+
+  return (
+    <div>
+      <div>
+        {thread.messages.map((message) => {
+          const meta = thread.getMessagesMetadata(message);
+          const parentCheckpoint = meta?.firstSeenState?.parent_checkpoint;
+
+          return (
+            <div key={message.id}>
+              <div>{message.content as string}</div>
+
+              {message.type === "human" && (
+                <EditMessage
+                  message={message}
+                  onEdit={(message) =>
+                    thread.submit(
+                      { messages: [message] },
+                      { checkpoint: parentCheckpoint }
+                    )
+                  }
+                />
+              )}
+
+              {message.type === "ai" && (
+                <button
+                  type="button"
+                  onClick={() =>
+                    thread.submit(undefined, { checkpoint: parentCheckpoint })
+                  }
+                >
+                  <span>Regenerate</span>
+                </button>
+              )}
+
+              <BranchSwitcher
+                branch={meta?.branch}
+                branchOptions={meta?.branchOptions}
+                onSelect={(branch) => thread.setBranch(branch)}
+              />
+            </div>
+          );
+        })}
+      </div>
+
+      <form
+        onSubmit={(e) => {
+          e.preventDefault();
+
+          const form = e.target as HTMLFormElement;
+          const message = new FormData(form).get("message") as string;
+
+          form.reset();
+          thread.submit({ messages: [message] });
+        }}
+      >
+        <input type="text" name="message" />
+
+        {thread.isLoading ? (
+          <button key="stop" type="button" onClick={() => thread.stop()}>
+            Stop
+          </button>
+        ) : (
+          <button key="submit" type="submit">
+            Send
+          </button>
+        )}
+      </form>
+    </div>
+  );
+}
+```
+
+For advanced use cases you can use the `experimental_branchTree` property to get the tree representation of the thread, which can be used to render branching controls for non-message based graphs.
+
+### Optimistic Updates
+
+You can optimistically update the client state before performing a network request to the agent, allowing you to provide immediate feedback to the user, such as showing the user message immediately before the agent has seen the request.
+
+```tsx
+const stream = useStream({
+  apiUrl: "http://localhost:2024",
+  assistantId: "agent",
+  messagesKey: "messages",
+});
+
+const handleSubmit = (text: string) => {
+  const newMessage = { type: "human" as const, content: text };
+
+  stream.submit(
+    { messages: [newMessage] },
+    {
+      optimisticValues(prev) {
+        const prevMessages = prev.messages ?? [];
+        const newMessages = [...prevMessages, newMessage];
+        return { ...prev, messages: newMessages };
+      },
+    }
+  );
+};
+```
+
+### Cached Thread Display
+
+Use the `initialValues` option to display cached thread data immediately while the history is being loaded from the server. This improves user experience by showing cached data instantly when navigating to existing threads.
+
+```tsx
+import { useStream } from "@langchain/langgraph-sdk/react";
+
+const CachedThreadExample = ({ threadId, cachedThreadData }) => {
+  const stream = useStream({
+    apiUrl: "http://localhost:2024",
+    assistantId: "agent",
+    threadId,
+    // Show cached data immediately while history loads
+    initialValues: cachedThreadData?.values,
+    messagesKey: "messages",
+  });
+
+  return (
+    <div>
+      {stream.messages.map((message) => (
+        <div key={message.id}>{message.content as string}</div>
+      ))}
+    </div>
+  );
+};
+```
+
+### Optimistic Thread Creation
+
+Use the `threadId` option in `submit` function to enable optimistic UI patterns where you need to know the thread ID before the thread is actually created.
+
+```tsx
+import { useState } from "react";
+import { useStream } from "@langchain/langgraph-sdk/react";
+
+const OptimisticThreadExample = () => {
+  const [threadId, setThreadId] = useState<string | null>(null);
+  const [optimisticThreadId] = useState(() => crypto.randomUUID());
+
+  const stream = useStream({
+    apiUrl: "http://localhost:2024",
+    assistantId: "agent",
+    threadId,
+    onThreadId: setThreadId, // (3) Updated after thread has been created.
+    messagesKey: "messages",
+  });
+
+  const handleSubmit = (text: string) => {
+    // (1) Perform a soft navigation to /threads/${optimisticThreadId}
+    // without waiting for thread creation.
+    window.history.pushState({}, "", `/threads/${optimisticThreadId}`);
+
+    // (2) Submit message to create thread with the predetermined ID.
+    stream.submit(
+      { messages: [{ type: "human", content: text }] },
+      { threadId: optimisticThreadId }
+    );
+  };
+
+  return (
+    <div>
+      <p>Thread ID: {threadId ?? optimisticThreadId}</p>
+      {/* Rest of component */}
+    </div>
+  );
+};
+```
+
+### TypeScript
+
+The `useStream()` hook is friendly for apps written in TypeScript and you can specify types for the state to get better type safety and IDE support.
+
+```tsx
+// Define your types
+type State = {
+  messages: Message[];
+  context?: Record<string, unknown>;
+};
+
+// Use them with the hook
+const thread = useStream<State>({
+  apiUrl: "http://localhost:2024",
+  assistantId: "agent",
+  messagesKey: "messages",
+});
+```
+
+You can also optionally specify types for different scenarios, such as:
+
+- `ConfigurableType`: Type for the `config.configurable` property (default: `Record<string, unknown>`)
+- `InterruptType`: Type for the interrupt value - i.e. contents of `interrupt(...)` function (default: `unknown`)
+- `CustomEventType`: Type for the custom events (default: `unknown`)
+- `UpdateType`: Type for the submit function (default: `Partial<State>`)
+
+```tsx
+const thread = useStream<
+  State,
+  {
+    UpdateType: {
+      messages: Message[] | Message;
+      context?: Record<string, unknown>;
+    };
+    InterruptType: string;
+    CustomEventType: {
+      type: "progress" | "debug";
+      payload: unknown;
+    };
+    ConfigurableType: {
+      model: string;
+    };
+  }
+>({
+  apiUrl: "http://localhost:2024",
+  assistantId: "agent",
+  messagesKey: "messages",
+});
+```
+
+If you're using LangGraph.js, you can also reuse your graph's annotation types. However, make sure to only import the types of the annotation schema in order to avoid importing the entire LangGraph.js runtime (i.e. via `import type { ... }` directive).
+
+```tsx
+import {
+  Annotation,
+  MessagesAnnotation,
+  type StateType,
+  type UpdateType,
+} from "@langchain/langgraph/web";
+
+const AgentState = Annotation.Root({
+  ...MessagesAnnotation.spec,
+  context: Annotation<string>(),
+});
+
+const thread = useStream<
+  StateType<typeof AgentState.spec>,
+  { UpdateType: UpdateType<typeof AgentState.spec> }
+>({
+  apiUrl: "http://localhost:2024",
+  assistantId: "agent",
+  messagesKey: "messages",
+});
+```
+
+## Event Handling
+
+The `useStream()` hook provides several callback options to help you respond to different events:
+
+- `onError`: Called when an error occurs.
+- `onFinish`: Called when the stream is finished.
+- `onUpdateEvent`: Called when an update event is received.
+- `onCustomEvent`: Called when a custom event is received. See the [streaming](../../how-tos/streaming.md#stream-custom-data) guide to learn how to stream custom events.
+- `onMetadataEvent`: Called when a metadata event is received, which contains the Run ID and Thread ID.
+
+## Learn More
+
+- [JS/TS SDK Reference](../reference/sdk/js_ts_sdk_ref.md)

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

@@ -0,0 +1,487 @@
+# Use threads
+
+In this guide, we will show how to create, view, and inspect [threads](../../concepts/persistence.md#threads).
+
+## Create a thread
+
+To run your graph and the state persisted, you must first create a thread.
+
+### Empty thread
+
+To create a new thread, use the [LangGraph SDK](../../concepts/sdk.md) `create` method. See the [Python](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/python_sdk_ref/#langgraph_sdk.client.ThreadsClient.create) and [JS](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#create_3) SDK reference docs for more information.
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url=<DEPLOYMENT_URL>)
+    thread = await client.threads.create()
+
+    print(thread)
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
+    const thread = await client.threads.create();
+
+    console.log(thread);
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+        --url <DEPLOYMENT_URL>/threads \
+        --header 'Content-Type: application/json' \
+        --data '{}'
+    ```
+
+Output:
+
+    {
+      "thread_id": "123e4567-e89b-12d3-a456-426614174000",
+      "created_at": "2025-05-12T14:04:08.268Z",
+      "updated_at": "2025-05-12T14:04:08.268Z",
+      "metadata": {},
+      "status": "idle",
+      "values": {}
+    }
+
+### Copy thread
+
+Alternatively, if you already have a thread in your application whose state you wish to copy, you can use the `copy` method. This will create an independent thread whose history is identical to the original thread at the time of the operation. See the [Python](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/python_sdk_ref/#langgraph_sdk.client.ThreadsClient.copy) and [JS](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#copy) SDK reference docs for more information.
+
+=== "Python"
+
+    ```python
+    copied_thread = await client.threads.copy(<THREAD_ID>)
+    ```
+
+=== "Javascript"
+
+    ```js
+    const copiedThread = await client.threads.copy(<THREAD_ID>);
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/copy \
+    --header 'Content-Type: application/json'
+    ```
+
+### Prepopulated State
+
+Finally, you can create a thread with an arbitrary pre-defined state by providing a list of `supersteps` into the `create` method. The `supersteps` describe a list of a sequence of state updates. For example:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url=<DEPLOYMENT_URL>)
+    thread = await client.threads.create(
+      graph_id="agent",
+      supersteps=[
+        {
+          updates: [
+            {
+              values: {},
+              as_node: '__input__',
+            },
+          ],
+        },
+        {
+          updates: [
+            {
+              values: {
+                messages: [
+                  {
+                    type: 'human',
+                    content: 'hello',
+                  },
+                ],
+              },
+              as_node: '__start__',
+            },
+          ],
+        },
+        {
+          updates: [
+            {
+              values: {
+                messages: [
+                  {
+                    content: 'Hello! How can I assist you today?',
+                    type: 'ai',
+                  },
+                ],
+              },
+              as_node: 'call_model',
+            },
+          ],
+        },
+      ])
+
+    print(thread)
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
+    const thread = await client.threads.create({
+        graphId: 'agent',
+        supersteps: [
+        {
+          updates: [
+            {
+              values: {},
+              asNode: '__input__',
+            },
+          ],
+        },
+        {
+          updates: [
+            {
+              values: {
+                messages: [
+                  {
+                    type: 'human',
+                    content: 'hello',
+                  },
+                ],
+              },
+              asNode: '__start__',
+            },
+          ],
+        },
+        {
+          updates: [
+            {
+              values: {
+                messages: [
+                  {
+                    content: 'Hello! How can I assist you today?',
+                    type: 'ai',
+                  },
+                ],
+              },
+              asNode: 'call_model',
+            },
+          ],
+        },
+      ],
+    });
+
+    console.log(thread);
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+        --url <DEPLOYMENT_URL>/threads \
+        --header 'Content-Type: application/json' \
+        --data '{"metadata":{"graph_id":"agent"},"supersteps":[{"updates":[{"values":{},"as_node":"__input__"}]},{"updates":[{"values":{"messages":[{"type":"human","content":"hello"}]},"as_node":"__start__"}]},{"updates":[{"values":{"messages":[{"content":"Hello\u0021 How can I assist you today?","type":"ai"}]},"as_node":"call_model"}]}]}'
+    ```
+
+Output:
+
+    {
+        "thread_id": "f15d70a1-27d4-4793-a897-de5609920b7d",
+        "created_at": "2025-05-12T15:37:08.935038+00:00",
+        "updated_at": "2025-05-12T15:37:08.935046+00:00",
+        "metadata": {"graph_id": "agent"},
+        "status": "idle",
+        "config": {},
+        "values": {
+            "messages": [
+                {
+                    "content": "hello",
+                    "additional_kwargs": {},
+                    "response_metadata": {},
+                    "type": "human",
+                    "name": null,
+                    "id": "8701f3be-959c-4b7c-852f-c2160699b4ab",
+                    "example": false
+                },
+                {
+                    "content": "Hello! How can I assist you today?",
+                    "additional_kwargs": {},
+                    "response_metadata": {},
+                    "type": "ai",
+                    "name": null,
+                    "id": "4d8ea561-7ca1-409a-99f7-6b67af3e1aa3",
+                    "example": false,
+                    "tool_calls": [],
+                    "invalid_tool_calls": [],
+                    "usage_metadata": null
+                }
+            ]
+        }
+    }
+
+## List threads
+
+### LangGraph SDK
+
+To list threads, use the [LangGraph SDK](../../concepts/sdk.md) `search` method. This will list the threads in the application that match the provided filters. See the [Python](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/python_sdk_ref/#langgraph_sdk.client.ThreadsClient.search) and [JS](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#search_2) SDK reference docs for more information.
+
+#### Filter by thread status
+
+Use the `status` field to filter threads based on their status. Supported values are `idle`, `busy`, `interrupted`, and `error`. See [here](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/python_sdk_ref/?h=thread+status#langgraph_sdk.auth.types.ThreadStatus) for information on each status. For example, to view `idle` threads:
+
+=== "Python"
+
+    ```python
+    print(await client.threads.search(status="idle",limit=1))
+    ```
+
+=== "Javascript"
+
+    ```js
+    console.log(await client.threads.search({ status: "idle", limit: 1 }));
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+    --url <DEPLOYMENT_URL>/threads/search \
+    --header 'Content-Type: application/json' \
+    --data '{"status": "idle", "limit": 1}'
+    ```
+
+Output:
+
+    [
+      {
+        'thread_id': 'cacf79bb-4248-4d01-aabc-938dbd60ed2c',
+        'created_at': '2024-08-14T17:36:38.921660+00:00',
+        'updated_at': '2024-08-14T17:36:38.921660+00:00',
+        'metadata': {'graph_id': 'agent'},
+        'status': 'idle',
+        'config': {'configurable': {}}
+      }
+    ]
+
+#### Filter by metadata
+
+The `search` method allows you to filter on metadata:
+
+=== "Python"
+
+    ```python
+    print((await client.threads.search(metadata={"graph_id":"agent"},limit=1)))
+    ```
+
+=== "Javascript"
+
+    ```js
+    console.log((await client.threads.search({ metadata: { "graph_id": "agent" }, limit: 1 })));
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+    --url <DEPLOYMENT_URL>/threads/search \
+    --header 'Content-Type: application/json' \
+    --data '{"metadata": {"graph_id":"agent"}, "limit": 1}'
+    ```
+
+Output:
+
+    [
+      {
+        'thread_id': 'cacf79bb-4248-4d01-aabc-938dbd60ed2c',
+        'created_at': '2024-08-14T17:36:38.921660+00:00',
+        'updated_at': '2024-08-14T17:36:38.921660+00:00',
+        'metadata': {'graph_id': 'agent'},
+        'status': 'idle',
+        'config': {'configurable': {}}
+      }
+    ]
+
+#### Sorting
+
+The SDK also supports sorting threads by `thread_id`, `status`, `created_at`, and `updated_at` using the `sort_by` and `sort_order` params.
+
+### LangGraph Platform UI
+
+You can also view threads in a deployment via the LangGraph Platform UI.
+
+Inside your deployment, select the "Threads" tab. This will load a table of all of the threads in your deployment.
+
+To filter by thread status, select a status in the top bar. To sort by a supported property, click on the arrow icon for the desired column.
+
+## Inspect threads
+
+### LangGraph SDK
+
+#### Get Thread
+
+To view a specific thread given its `thread_id`, use the `get` method:
+
+=== "Python"
+
+    ```python
+    print((await client.threads.get(<THREAD_ID>)))
+    ```
+
+=== "Javascript"
+
+    ```js
+    console.log((await client.threads.get(<THREAD_ID>)));
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request GET \
+    --url <DEPLOYMENT_URL>/threads/<THREAD_ID> \
+    --header 'Content-Type: application/json'
+    ```
+
+Output:
+
+    {
+      'thread_id': 'cacf79bb-4248-4d01-aabc-938dbd60ed2c',
+      'created_at': '2024-08-14T17:36:38.921660+00:00',
+      'updated_at': '2024-08-14T17:36:38.921660+00:00',
+      'metadata': {'graph_id': 'agent'},
+      'status': 'idle',
+      'config': {'configurable': {}}
+    }
+
+#### Inspect Thread State
+
+To view the current state of a given thread, use the `get_state` method:
+
+=== "Python"
+
+    ```python
+    print((await client.threads.get_state(<THREAD_ID>)))
+    ```
+
+=== "Javascript"
+
+    ```js
+    console.log((await client.threads.getState(<THREAD_ID>)));
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request GET \
+    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/state \
+    --header 'Content-Type: application/json'
+    ```
+
+Output:
+
+    {
+        "values": {
+            "messages": [
+                {
+                    "content": "hello",
+                    "additional_kwargs": {},
+                    "response_metadata": {},
+                    "type": "human",
+                    "name": null,
+                    "id": "8701f3be-959c-4b7c-852f-c2160699b4ab",
+                    "example": false
+                },
+                {
+                    "content": "Hello! How can I assist you today?",
+                    "additional_kwargs": {},
+                    "response_metadata": {},
+                    "type": "ai",
+                    "name": null,
+                    "id": "4d8ea561-7ca1-409a-99f7-6b67af3e1aa3",
+                    "example": false,
+                    "tool_calls": [],
+                    "invalid_tool_calls": [],
+                    "usage_metadata": null
+                }
+            ]
+        },
+        "next": [],
+        "tasks": [],
+        "metadata": {
+            "thread_id": "f15d70a1-27d4-4793-a897-de5609920b7d",
+            "checkpoint_id": "1f02f46f-7308-616c-8000-1b158a9a6955",
+            "graph_id": "agent_with_quite_a_long_name",
+            "source": "update",
+            "step": 1,
+            "writes": {
+                "call_model": {
+                    "messages": [
+                        {
+                            "content": "Hello! How can I assist you today?",
+                            "type": "ai"
+                        }
+                    ]
+                }
+            },
+            "parents": {}
+        },
+        "created_at": "2025-05-12T15:37:09.008055+00:00",
+        "checkpoint": {
+            "checkpoint_id": "1f02f46f-733f-6b58-8001-ea90dcabb1bd",
+            "thread_id": "f15d70a1-27d4-4793-a897-de5609920b7d",
+            "checkpoint_ns": ""
+        },
+        "parent_checkpoint": {
+            "checkpoint_id": "1f02f46f-7308-616c-8000-1b158a9a6955",
+            "thread_id": "f15d70a1-27d4-4793-a897-de5609920b7d",
+            "checkpoint_ns": ""
+        },
+        "checkpoint_id": "1f02f46f-733f-6b58-8001-ea90dcabb1bd",
+        "parent_checkpoint_id": "1f02f46f-7308-616c-8000-1b158a9a6955"
+    }
+
+Optionally, to view the state of a thread at a given checkpoint, simply pass in the checkpoint id (or the entire checkpoint object):
+
+=== "Python"
+
+    ```python
+    thread_state = await client.threads.get_state(
+      thread_id=<THREAD_ID>
+      checkpoint_id=<CHECKPOINT_ID>
+    )
+    ```
+
+=== "Javascript"
+
+    ```js
+    const threadState = await client.threads.getState(<THREAD_ID>, <CHECKPOINT_ID>);
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request GET \
+    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/state/<CHECKPOINT_ID> \
+    --header 'Content-Type: application/json'
+    ```
+
+#### Inspect Full Thread History
+
+To view a thread's history, use the `get_history` method. This returns a list of every state the thread experienced. For more information see the [Python](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/python_sdk_ref/?h=thread+status#langgraph_sdk.client.ThreadsClient.get_history) and [JS](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#gethistory) reference docs.
+
+### LangGraph Platform UI
+
+You can also view threads in a deployment via the LangGraph Platform UI.
+
+Inside your deployment, select the "Threads" tab. This will load a table of all of the threads in your deployment.
+
+Select a thread to inspect its current state. To view its full history and for further debugging, open the thread in [LangGraph Studio](../../concepts//langgraph_studio.md).

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

@@ -0,0 +1,166 @@
+# Use webhooks
+
+When working with LangGraph Platform, you may want to use webhooks to receive updates after an API call completes. Webhooks are useful for triggering actions in your service once a run has finished processing. To implement this, you need to expose an endpoint that can accept `POST` requests and pass this endpoint as a `webhook` parameter in your API request.
+
+Currently, the SDK does not provide built-in support for defining webhook endpoints, but you can specify them manually using API requests.
+
+## Supported endpoints
+
+The following API endpoints accept a `webhook` parameter:
+
+| Operation            | HTTP Method | Endpoint                          |
+|----------------------|-------------|-----------------------------------|
+| Create Run           | `POST`      | `/thread/{thread_id}/runs`        |
+| Create Thread Cron   | `POST`      | `/thread/{thread_id}/runs/crons`  |
+| Stream Run           | `POST`      | `/thread/{thread_id}/runs/stream` |
+| Wait Run             | `POST`      | `/thread/{thread_id}/runs/wait`   |
+| Create Cron          | `POST`      | `/runs/crons`                     |
+| Stream Run Stateless | `POST`      | `/runs/stream`                    |
+| Wait Run Stateless   | `POST`      | `/runs/wait`                      |
+
+In this guide, we’ll show how to trigger a webhook after streaming a run.
+
+## Set up your assistant and thread
+
+Before making API calls, set up your assistant and thread.
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url=<DEPLOYMENT_URL>)
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    print(thread)
+    ```
+
+=== "JavaScript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
+    const assistantID = "agent";
+    const thread = await client.threads.create();
+    console.log(thread);
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+        --url <DEPLOYMENT_URL>/assistants/search \
+        --header 'Content-Type: application/json' \
+        --data '{ "limit": 10, "offset": 0 }' | jq -c 'map(select(.config == null or .config == {})) | .[0]' && \
+    curl --request POST \
+        --url <DEPLOYMENT_URL>/threads \
+        --header 'Content-Type: application/json' \
+        --data '{}'
+    ```
+
+Example response:
+
+```json
+{
+    "thread_id": "9dde5490-2b67-47c8-aa14-4bfec88af217",
+    "created_at": "2024-08-30T23:07:38.242730+00:00",
+    "updated_at": "2024-08-30T23:07:38.242730+00:00",
+    "metadata": {},
+    "status": "idle",
+    "config": {},
+    "values": null
+}
+```
+
+## Use a webhook with a graph run
+
+To use a webhook, specify the `webhook` parameter in your API request. When the run completes, LangGraph Platform sends a `POST` request to the specified webhook URL.
+
+For example, if your server listens for webhook events at `https://my-server.app/my-webhook-endpoint`, include this in your request:
+
+=== "Python"
+
+    ```python
+    input = { "messages": [{ "role": "user", "content": "Hello!" }] }
+
+    async for chunk in client.runs.stream(
+        thread_id=thread["thread_id"],
+        assistant_id=assistant_id,
+        input=input,
+        stream_mode="events",
+        webhook="https://my-server.app/my-webhook-endpoint"
+    ):
+        pass
+    ```
+
+=== "JavaScript"
+
+    ```js
+    const input = { messages: [{ role: "human", content: "Hello!" }] };
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantID,
+      {
+        input: input,
+        webhook: "https://my-server.app/my-webhook-endpoint"
+      }
+    );
+
+    for await (const chunk of streamResponse) {
+      // Handle stream output
+    }
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+        --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/stream \
+        --header 'Content-Type: application/json' \
+        --data '{
+            "assistant_id": <ASSISTANT_ID>,
+            "input": {"messages": [{"role": "user", "content": "Hello!"}]},
+            "webhook": "https://my-server.app/my-webhook-endpoint"
+        }'
+    ```
+
+## Webhook payload
+
+LangGraph Platform sends webhook notifications in the format of a [Run](../../concepts/assistants.md#execution). See the [API Reference](https://langchain-ai.github.io/langgraph/cloud/reference/api/api_ref.html#model/run) for details. The request payload includes run input, configuration, and other metadata in the `kwargs` field.
+
+## Secure webhooks
+
+To ensure only authorized requests hit your webhook endpoint, consider adding a security token as a query parameter:
+
+```
+https://my-server.app/my-webhook-endpoint?token=YOUR_SECRET_TOKEN
+```
+
+Your server should extract and validate this token before processing requests.
+
+## Disable webhooks
+
+As of `langgraph-api>=0.2.78`, developers can disable webhooks in the `langgraph.json` file:
+
+```json
+{
+  "http": {
+    "disable_webhooks": true
+  }
+}
+```
+
+This feature is primarily intended for self-hosted deployments, where platform administrators or developers may prefer to disable webhooks to simplify their security posture—especially if they are not configuring firewall rules or other network controls. Disabling webhooks helps prevent untrusted payloads from being sent to internal endpoints.
+
+For full configuration details, refer to the [configuration file reference](https://langchain-ai.github.io/langgraph/cloud/reference/cli/?h=disable_webhooks#configuration-file).
+
+## Test webhooks
+
+You can test your webhook using online services like:
+
+- **[Beeceptor](https://beeceptor.com/)** – Quickly create a test endpoint and inspect incoming webhook payloads.
+- **[Webhook.site](https://webhook.site/)** – View, debug, and log incoming webhook requests in real time.
+
+These tools help you verify that LangGraph Platform is correctly triggering and sending webhooks to your service.

docs/docs/cloud/quick_start.md

@@ -0,0 +1,184 @@
+# Deployment quickstart
+
+This guide shows you how to set up and use LangGraph Platform for a cloud deployment.
+
+## Prerequisites
+
+Before you begin, ensure you have the following:
+
+- A [GitHub account](https://github.com/)
+- A [LangSmith account](https://smith.langchain.com/) – free to sign up
+
+## 1. Create a repository on GitHub
+
+To deploy an application to **LangGraph Platform**, your application code must reside in a GitHub repository. Both public and private repositories are supported. For this quickstart, use the [`new-langgraph-project` template](https://github.com/langchain-ai/react-agent) for your application:
+
+1. Go to the [`new-langgraph-project` repository](https://github.com/langchain-ai/new-langgraph-project) or [`new-langgraphjs-project` template](https://github.com/langchain-ai/new-langgraphjs-project).
+1. Click the `Fork` button in the top right corner to fork the repository to your GitHub account.
+1. Click **Create fork**. 
+
+## 2. Deploy to LangGraph Platform
+
+1. Log in to [LangSmith](https://smith.langchain.com/).
+1. In the left sidebar, select **Deployments**.
+1. Click the **+ New Deployment** button. A pane will open where you can fill in the required fields.
+1. If you are a first time user or adding a private repository that has not been previously connected, click the **Import from GitHub** button and follow the instructions to connect your GitHub account.
+1. Select your New LangGraph Project repository.
+1. Click **Submit** to deploy.
+
+    This may take about 15 minutes to complete. You can check the status in the **Deployment details** view.
+
+## 3. Test your application in LangGraph Studio
+
+Once your application is deployed:
+
+1. Select the deployment you just created to view more details.
+1. Click the **LangGraph Studio** button in the top right corner.
+
+    LangGraph Studio will open to display your graph.
+
+    <figure markdown="1">
+    [![image](deployment/img/langgraph_studio.png){: style="max-height:400px"}](deployment/img/langgraph_studio.png)
+    <figcaption>
+        Sample graph run in LangGraph Studio.
+    </figcaption>
+    </figure>
+
+## 4. Get the API URL for your deployment
+
+1. In the **Deployment details** view in LangGraph, click the **API URL** to copy it to your clipboard.
+1. Click the `URL` to copy it to the clipboard.
+
+## 5. Test the API
+
+You can now test the API:
+
+=== "Python SDK (Async)"
+
+    1. Install the LangGraph Python SDK:
+
+        ```shell
+        pip install langgraph-sdk
+        ```
+
+    1. Send a message to the assistant (threadless run):
+
+        ```python
+        from langgraph_sdk import get_client
+
+        client = get_client(url="your-deployment-url", api_key="your-langsmith-api-key")
+
+        async for chunk in client.runs.stream(
+            None,  # Threadless run
+            "agent", # Name of assistant. Defined in langgraph.json.
+            input={
+                "messages": [{
+                    "role": "human",
+                    "content": "What is LangGraph?",
+                }],
+            },
+            stream_mode="updates",
+        ):
+            print(f"Receiving new event of type: {chunk.event}...")
+            print(chunk.data)
+            print("\n\n")
+        ```
+
+=== "Python SDK (Sync)"
+
+    1. Install the LangGraph Python SDK:
+
+        ```shell
+        pip install langgraph-sdk
+        ```
+
+    1. Send a message to the assistant (threadless run):
+
+        ```python
+        from langgraph_sdk import get_sync_client
+
+        client = get_sync_client(url="your-deployment-url", api_key="your-langsmith-api-key")
+
+        for chunk in client.runs.stream(
+            None,  # Threadless run
+            "agent", # Name of assistant. Defined in langgraph.json.
+            input={
+                "messages": [{
+                    "role": "human",
+                    "content": "What is LangGraph?",
+                }],
+            },
+            stream_mode="updates",
+        ):
+            print(f"Receiving new event of type: {chunk.event}...")
+            print(chunk.data)
+            print("\n\n")
+        ```
+
+=== "JavaScript SDK"
+
+    1. Install the LangGraph JS SDK
+
+        ```shell
+        npm install @langchain/langgraph-sdk
+        ```
+
+    1. Send a message to the assistant (threadless run):
+
+        ```js
+        const { Client } = await import("@langchain/langgraph-sdk");
+
+        const client = new Client({ apiUrl: "your-deployment-url", apiKey: "your-langsmith-api-key" });
+
+        const streamResponse = client.runs.stream(
+            null, // Threadless run
+            "agent", // Assistant ID
+            {
+                input: {
+                    "messages": [
+                        { "role": "user", "content": "What is LangGraph?"}
+                    ]
+                },
+                streamMode: "messages",
+            }
+        );
+
+        for await (const chunk of streamResponse) {
+            console.log(`Receiving new event of type: ${chunk.event}...`);
+            console.log(JSON.stringify(chunk.data));
+            console.log("\n\n");
+        }
+        ```
+
+=== "Rest API"
+
+    ```bash
+    curl -s --request POST \
+        --url <DEPLOYMENT_URL>/runs/stream \
+        --header 'Content-Type: application/json' \
+        --header "X-Api-Key: <LANGSMITH API KEY> \
+        --data "{
+            \"assistant_id\": \"agent\",
+            \"input\": {
+                \"messages\": [
+                    {
+                        \"role\": \"human\",
+                        \"content\": \"What is LangGraph?\"
+                    }
+                ]
+            },
+            \"stream_mode\": \"updates\"
+        }" 
+    ```
+
+
+## Next steps
+
+Congratulations! You have deployed an application using LangGraph Platform.
+
+Here are some other resources to check out:
+
+- [LangGraph Platform overview](../concepts/langgraph_platform.md)
+- [Deployment options](../concepts/deployment_options.md)
+
+

docs/docs/cloud/reference/api/api_ref.md

@@ -0,0 +1,22 @@
+# LangGraph Server API Reference
+
+The LangGraph Server API reference is available within each deployment at the `/docs` endpoint (e.g. `http://localhost:8124/docs`).
+
+Click <a href="/langgraph/cloud/reference/api/api_ref.html" target="_blank">here</a> to view the API reference.
+
+## Authentication
+
+For deployments to LangGraph Platform, authentication is required. Pass the `X-Api-Key` header with each request to the LangGraph Server. The value of the header should be set to a valid LangSmith API key for the organization where the LangGraph Server is deployed.
+
+Example `curl` command:
+```shell
+curl --request POST \
+  --url http://localhost:8124/assistants/search \
+  --header 'Content-Type: application/json' \
+  --header 'X-Api-Key: LANGSMITH_API_KEY' \
+  --data '{
+  "metadata": {},
+  "limit": 10,
+  "offset": 0
+}'
+```

docs/docs/cloud/reference/api/api_ref_control_plane.md

@@ -0,0 +1,247 @@
+# LangGraph Control Plane API Reference
+
+The LangGraph Control Plane API is used to programmatically create and manage LangGraph Server deployments. For example, the APIs can be orchestrated to create custom CI/CD workflows.
+
+Click <a href="https://api.host.langchain.com/docs" target="_blank">here</a> to view the API reference.
+
+## Host
+
+LangGraph Control Plane hosts for Cloud SaaS data regions:
+
+| US | EU |
+|----|----|
+| `https://api.host.langchain.com` | `https://eu.api.host.langchain.com` |
+
+**Note**: Self-hosted deployments of LangGraph Platform will have a custom host for the LangGraph Control Plane.
+
+## Authentication
+
+To authenticate with the LangGraph Control Plane API, set the `X-Api-Key` header to a valid LangSmith API key.
+
+Example `curl` command:
+```shell
+curl --request GET \
+  --url http://localhost:8124/v2/deployments \
+  --header 'X-Api-Key: LANGSMITH_API_KEY'
+```
+
+## Versioning
+
+Each endpoint path is prefixed with a version (e.g. `v1`, `v2`).
+
+## Quick Start
+
+1. Call `POST /v2/deployments` to create a new Deployment. The response body contains the Deployment ID (`id`) and the ID of the latest (and first) revision (`latest_revision_id`).
+1. Call `GET /v2/deployments/{deployment_id}` to retrieve the Deployment. Set `deployment_id` in the URL to the value of Deployment ID (`id`).
+1. Poll for revision `status` until `status` is `DEPLOYED` by calling `GET /v2/deployments/{deployment_id}/revisions/{latest_revision_id}`.
+1. Call `PATCH /v2/deployments/{deployment_id}` to update the deployment.
+
+## Example Code
+Below is example Python code that demonstrates how to orchestrate the LangGraph Control Plane APIs to create a deployment, update the deployment, and delete the deployment.
+```python
+import os
+import time
+
+import requests
+from dotenv import load_dotenv
+
+
+load_dotenv()
+
+# required environment variables
+CONTROL_PLANE_HOST = os.getenv("CONTROL_PLANE_HOST")
+LANGSMITH_API_KEY = os.getenv("LANGSMITH_API_KEY")
+INTEGRATION_ID = os.getenv("INTEGRATION_ID")
+MAX_WAIT_TIME = 1800  # 30 mins
+
+
+def get_headers() -> dict:
+    """Return common headers for requests to LangGraph Control Plane API."""
+    return {
+        "X-Api-Key": LANGSMITH_API_KEY,
+    }
+
+
+def create_deployment() -> str:
+    """Create deployment. Return deployment ID."""
+    headers = get_headers()
+    headers["Content-Type"] = "application/json"
+
+    deployment_name = "my_deployment"
+
+    request_body = {
+        "name": deployment_name,
+        "source": "github",
+        "source_config": {
+            "integration_id": INTEGRATION_ID,
+            "repo_url": "https://github.com/langchain-ai/langgraph-example",
+            "deployment_type": "dev",
+            "build_on_push": False,
+            "custom_url": None,
+            "resource_spec": None,
+        },
+        "source_revision_config": {
+            "repo_ref": "main",
+            "langgraph_config_path": "langgraph.json",
+            "image_uri": None,
+        },
+        "secrets": [
+            {
+                "name": "OPENAI_API_KEY",
+                "value": "test_openai_api_key",
+            },
+            {
+                "name": "ANTHROPIC_API_KEY",
+                "value": "test_anthropic_api_key",
+            },
+            {
+                "name": "TAVILY_API_KEY",
+                "value": "test_tavily_api_key",
+            },
+        ],
+    }
+
+    response = requests.post(
+        url=f"{CONTROL_PLANE_HOST}/v2/deployments",
+        headers=headers,
+        json=request_body,
+    )
+
+    if response.status_code != 201:
+        raise Exception(f"Failed to create deployment: {response.text}")
+
+    deployment_id = response.json()["id"]
+    print(f"Created deployment {deployment_name} ({deployment_id})")
+    return deployment_id
+
+
+def get_deployment(deployment_id: str) -> dict:
+    """Get deployment."""
+    response = requests.get(
+        url=f"{CONTROL_PLANE_HOST}/v2/deployments/{deployment_id}",
+        headers=get_headers(),
+    )
+
+    if response.status_code != 200:
+        raise Exception(f"Failed to get deployment ID {deployment_id}: {response.text}")
+
+    return response.json()
+
+
+def list_revisions(deployment_id: str) -> list[dict]:
+    """List revisions.
+
+    Return list is sorted by created_at in descending order (latest first).
+    """
+    response = requests.get(
+        url=f"{CONTROL_PLANE_HOST}/v2/deployments/{deployment_id}/revisions",
+        headers=get_headers(),
+    )
+
+    if response.status_code != 200:
+        raise Exception(
+            f"Failed to list revisions for deployment ID {deployment_id}: {response.text}"
+        )
+
+    return response.json()
+
+
+def get_revision(
+    deployment_id: str,
+    revision_id: str,
+) -> dict:
+    """Get revision."""
+    response = requests.get(
+        url=f"{CONTROL_PLANE_HOST}/v2/deployments/{deployment_id}/revisions/{revision_id}",
+        headers=get_headers(),
+    )
+
+    if response.status_code != 200:
+        raise Exception(f"Failed to get revision ID {revision_id}: {response.text}")
+
+    return response.json()
+
+
+def patch_deployment(deployment_id: str) -> None:
+    """Patch deployment."""
+    headers = get_headers()
+    headers["Content-Type"] = "application/json"
+
+    response = requests.patch(
+        url=f"{CONTROL_PLANE_HOST}/v2/deployments/{deployment_id}",
+        headers=headers,
+        json={
+            "source_config": {
+                "build_on_push": True,
+            },
+            "source_revision_config": {
+                "repo_ref": "main",
+                "langgraph_config_path": "langgraph.json",
+            },
+        },
+    )
+
+    if response.status_code != 200:
+        raise Exception(f"Failed to patch deployment: {response.text}")
+
+    print(f"Patched deployment ID {deployment_id}")
+
+
+def wait_for_deployment(deployment_id: str, revision_id: str) -> None:
+    """Wait for revision status to be DEPLOYED."""
+    start_time = time.time()
+    revision, status = None, None
+    while time.time() - start_time < MAX_WAIT_TIME:
+        revision = get_revision(deployment_id, revision_id)
+        status = revision["status"]
+        if status == "DEPLOYED":
+            break
+        elif "FAILED" in status:
+            raise Exception(f"Revision ID {revision_id} failed: {revision}")
+
+        print(f"Waiting for revision ID {revision_id} to be DEPLOYED...")
+        time.sleep(60)
+
+    if status != "DEPLOYED":
+        raise Exception(
+            f"Timeout waiting for revision ID {revision_id} to be DEPLOYED: {revision}"
+        )
+
+
+def delete_deployment(deployment_id: str) -> None:
+    """Delete deployment."""
+    response = requests.delete(
+        url=f"{CONTROL_PLANE_HOST}/v2/deployments/{deployment_id}",
+        headers=get_headers(),
+    )
+
+    if response.status_code != 204:
+        raise Exception(
+            f"Failed to delete deployment ID {deployment_id}: {response.text}"
+        )
+
+    print(f"Deployment ID {deployment_id} deleted")
+
+
+if __name__ == "__main__":
+    # create deployment and get the latest revision
+    deployment_id = create_deployment()
+    revisions = list_revisions(deployment_id)
+    latest_revision = revisions["resources"][0]
+    latest_revision_id = latest_revision["id"]
+
+    # wait for latest revision to be DEPLOYED
+    wait_for_deployment(deployment_id, latest_revision_id)
+
+    # patch the deployment and get the latest revision
+    patch_deployment(deployment_id)
+    revisions = list_revisions(deployment_id)
+    latest_revision = revisions["resources"][0]
+    latest_revision_id = latest_revision["id"]
+
+    # wait for latest revision to be DEPLOYED
+    wait_for_deployment(deployment_id, latest_revision_id)
+
+    # delete the deployment
+    delete_deployment(deployment_id)
+```

docs/docs/cloud/reference/api/openapi.json

@@ -28,6 +28,14 @@
     {
       "name": "Store",
       "description": "Store is an API for managing persistent key-value store (long-term memory) that is available from any thread."
+    },
+    {
+      "name": "MCP",
+      "description": "Model Context Protocol related endpoints for exposing an agent as an MCP server."
+    },
+    {
+      "name": "System",
+      "description": "System endpoints for health checks, metrics, and server information."
     }
   ],
   "paths": {
@@ -149,6 +157,59 @@
         }
       }
     },
+    "/assistants/count": {
+      "post": {
+        "tags": [
+          "Assistants"
+        ],
+        "summary": "Count Assistants",
+        "description": "Get the count of assistants matching the specified criteria.",
+        "operationId": "count_assistants_assistants_count_post",
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/AssistantCountRequest"
+              }
+            }
+          },
+          "required": true
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "type": "integer",
+                  "title": "Count"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "Not Found",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            }
+          },
+          "422": {
+            "description": "Validation Error",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
     "/assistants/{assistant_id}": {
       "get": {
         "tags": [
@@ -805,6 +866,59 @@
         }
       }
     },
+    "/threads/count": {
+      "post": {
+        "tags": [
+          "Threads"
+        ],
+        "summary": "Count Threads",
+        "description": "Get the count of threads matching the specified criteria.",
+        "operationId": "count_threads_threads_count_post",
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ThreadCountRequest"
+              }
+            }
+          },
+          "required": true
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "type": "integer",
+                  "title": "Count"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "Not Found",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            }
+          },
+          "422": {
+            "description": "Validation Error",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
     "/threads/{thread_id}/state": {
       "get": {
         "tags": [
@@ -1406,6 +1520,73 @@
         }
       }
     },
+    "/threads/{thread_id}/stream": {
+      "get": {
+        "tags": [
+          "Threads"
+        ],
+        "summary": "Join Thread Stream",
+        "description": "This endpoint streams output in real-time from a thread. The stream will include the output of each run executed sequentially on the thread and will remain open indefinitely. It is the responsibility of the calling client to close the connection.",
+        "operationId": "join_thread_stream_threads__thread_id__stream_get",
+        "parameters": [
+          {
+            "description": "The ID of the thread.",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "format": "uuid",
+              "title": "Thread Id",
+              "description": "The ID of the thread."
+            },
+            "name": "thread_id",
+            "in": "path"
+          },
+          {
+            "required": false,
+            "schema": {
+              "type": "string",
+              "title": "Last Event ID",
+              "description": "The ID of the last event received. Used to resume streaming from a specific point. Pass '-' to resume from the beginning."
+            },
+            "name": "Last-Event-ID",
+            "in": "header"
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "text/event-stream": {
+                "schema": {
+                  "type": "string",
+                  "description": "The server will send a stream of events in SSE format.\n\n**Example event**:\n\nid: 1\n\nevent: message\n\ndata: {}"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "Not Found",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            }
+          },
+          "422": {
+            "description": "Validation Error",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
     "/threads/{thread_id}/runs": {
       "get": {
         "tags": [
@@ -1461,6 +1642,30 @@
             },
             "name": "status",
             "in": "query"
+          },
+          {
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "run_id",
+                  "thread_id",
+                  "assistant_id",
+                  "created_at",
+                  "updated_at",
+                  "status",
+                  "metadata",
+                  "kwargs",
+                  "multitask_strategy"
+                ]
+              },
+              "title": "Select",
+              "description": "Specify which fields to return. If not provided, all fields are returned."
+            },
+            "name": "select",
+            "in": "query"
           }
         ],
         "responses": {
@@ -2312,6 +2517,59 @@
         }
       }
     },
+    "/runs/crons/count": {
+      "post": {
+        "tags": [
+          "Crons (Plus tier)"
+        ],
+        "summary": "Count Crons",
+        "description": "Get the count of crons matching the specified criteria.",
+        "operationId": "count_crons_runs_crons_count_post",
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CronCountRequest"
+              }
+            }
+          },
+          "required": true
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "type": "integer",
+                  "title": "Count"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "Not Found",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            }
+          },
+          "422": {
+            "description": "Validation Error",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
     "/runs/stream": {
       "post": {
         "tags": [
@@ -2996,6 +3254,153 @@
           "MCP"
         ]
       }
+    },
+    "/info": {
+      "get": {
+        "tags": [
+          "System"
+        ],
+        "summary": "Server Information",
+        "description": "Get server version information, feature flags, and metadata.",
+        "operationId": "server_info_info_get",
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "type": "object",
+                  "properties": {
+                    "version": {
+                      "type": "string",
+                      "title": "Version",
+                      "description": "LangGraph API version"
+                    },
+                    "langgraph_py_version": {
+                      "type": "string",
+                      "title": "LangGraph Python Version",
+                      "description": "LangGraph Python library version"
+                    },
+                    "flags": {
+                      "type": "object",
+                      "title": "Feature Flags",
+                      "description": "Enabled features and capabilities"
+                    },
+                    "metadata": {
+                      "type": "object",
+                      "title": "Metadata",
+                      "description": "Server deployment metadata"
+                    }
+                  },
+                  "required": ["version", "langgraph_py_version", "flags", "metadata"],
+                  "title": "ServerInfo"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
+    "/metrics": {
+      "get": {
+        "tags": [
+          "System"
+        ],
+        "summary": "System Metrics",
+        "description": "Get system metrics in Prometheus or JSON format for monitoring and observability.",
+        "operationId": "system_metrics_metrics_get",
+        "parameters": [
+          {
+            "name": "format",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": ["prometheus", "json"],
+              "default": "prometheus",
+              "title": "Output Format",
+              "description": "Response format: prometheus (default) or json"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "text/plain": {
+                "schema": {
+                  "type": "string",
+                  "title": "Prometheus Metrics",
+                  "description": "Metrics in Prometheus exposition format"
+                }
+              },
+              "application/json": {
+                "schema": {
+                  "type": "object",
+                  "title": "JSON Metrics",
+                  "description": "Metrics in JSON format including queue stats, worker stats, and HTTP metrics"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
+    "/ok": {
+      "get": {
+        "tags": [
+          "System"
+        ],
+        "summary": "Health Check",
+        "description": "Check the health status of the server. Optionally check database connectivity.",
+        "operationId": "health_check_ok_get",
+        "parameters": [
+          {
+            "name": "check_db",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "enum": [0, 1],
+              "default": 0,
+              "title": "Check Database",
+              "description": "Whether to check database connectivity (0=false, 1=true)"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "type": "object",
+                  "properties": {
+                    "ok": {
+                      "type": "boolean",
+                      "const": true,
+                      "title": "OK",
+                      "description": "Indicates the server is healthy"
+                    }
+                  },
+                  "required": ["ok"],
+                  "title": "HealthResponse"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "Internal Server Error",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            }
+          }
+        }
+      }
     }
   },
   "components": {
@@ -3035,6 +3440,11 @@
             "title": "Config",
             "description": "The assistant config."
           },
+          "context": {
+            "type": "object",
+            "title": "Context",
+            "description": "Static context added to the assistant."
+          },
           "created_at": {
             "type": "string",
             "format": "date-time",
@@ -3100,6 +3510,11 @@
             "title": "Config",
             "description": "Configuration to use for the graph. Useful when graph is configurable and you want to create different assistants based on different configurations."
           },
+          "context": {
+            "type": "object",
+            "title": "Context",
+            "description": "Static context added to the assistant."
+          },
           "metadata": {
             "type": "object",
             "title": "Metadata",
@@ -3148,6 +3563,11 @@
             "title": "Config",
             "description": "Configuration to use for the graph. Useful when graph is configurable and you want to update the assistant's configuration."
           },
+          "context": {
+            "type": "object",
+            "title": "Context",
+            "description": "Static context added to the assistant."
+          },
           "metadata": {
             "type": "object",
             "title": "Metadata",
@@ -3209,6 +3629,12 @@
             "title": "Cron Id",
             "description": "The ID of the cron."
           },
+          "assistant_id": {
+            "type": ["string", "null"],
+            "format": "uuid",
+            "title": "Assistant Id",
+            "description": "The ID of the assistant."
+          },
           "thread_id": {
             "type": "string",
             "format": "uuid",
@@ -3238,10 +3664,26 @@
             "title": "Updated At",
             "description": "The last time the cron was updated."
           },
+          "user_id": {
+            "type": ["string", "null"],
+            "title": "User Id",
+            "description": "The ID of the user."
+          },
           "payload": {
             "type": "object",
             "title": "Payload",
             "description": "The run payload to use for creating new run."
+          },
+          "next_run_date": {
+            "type": ["string", "null"],
+            "format": "date-time",
+            "title": "Next Run Date",
+            "description": "The next run date of the cron."
+          },
+          "metadata": {
+            "type": "object",
+            "title": "Metadata",
+            "description": "The cron metadata."
           }
         },
         "type": "object",
@@ -3326,6 +3768,11 @@
             "title": "Config",
             "description": "The configuration for the assistant."
           },
+          "context": {
+            "type": "object",
+            "title": "Context",
+            "description": "Static context added to the assistant."
+          },
           "webhook": {
             "type": "string",
             "maxLength": 65536,
@@ -3380,7 +3827,7 @@
             ],
             "title": "Multitask Strategy",
             "description": "Multitask strategy to use. Must be one of 'reject', 'interrupt', 'rollback', or 'enqueue'.",
-            "default": "reject"
+            "default": "enqueue"
           }
         },
         "type": "object",
@@ -3397,7 +3844,7 @@
             "type": "string",
             "format": "uuid",
             "title": "Assistant Id",
-            "description": "The assistant ID or graph name to search for."
+            "description": "The assistant ID or graph name to filter by using exact match."
           },
           "thread_id": {
             "type": "string",
@@ -3433,6 +3880,28 @@
             "description": "The order to sort by.",
             "default": "desc",
             "enum": ["asc", "desc"]
+          },
+          "select": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "enum": [
+                "cron_id",
+                "assistant_id",
+                "thread_id",
+                "end_time",
+                "schedule",
+                "created_at",
+                "updated_at",
+                "user_id",
+                "payload",
+                "next_run_date",
+                "metadata",
+                "now"
+              ]
+            },
+            "title": "Select",
+            "description": "Specify which fields to return. If not provided, all fields are returned."
           }
         },
         "type": "object",
@@ -3440,6 +3909,25 @@
         "title": "CronSearch",
         "description": "Payload for listing crons"
       },
+      "CronCountRequest": {
+        "properties": {
+          "assistant_id": {
+            "type": "string",
+            "format": "uuid",
+            "title": "Assistant Id",
+            "description": "The assistant ID or graph name to search for."
+          },
+          "thread_id": {
+            "type": "string",
+            "format": "uuid",
+            "title": "Thread Id",
+            "description": "The thread ID to search for."
+          }
+        },
+        "type": "object",
+        "title": "CronCountRequest",
+        "description": "Payload for counting crons"
+      },
       "GraphSchema": {
         "properties": {
           "graph_id": {
@@ -3466,13 +3954,17 @@
             "type": "object",
             "title": "Config Schema",
             "description": "The schema for the graph config. Missing if unable to generate JSON schema from graph."
+          },
+          "context_schema": {
+            "type": "object",
+            "title": "Context Schema",
+            "description": "The schema for the graph context. Missing if unable to generate JSON schema from graph."
           }
         },
         "type": "object",
         "required": [
           "graph_id",
-          "state_schema",
-          "config_schema"
+          "state_schema"
         ],
         "title": "GraphSchema",
         "description": "Defines the structure and properties of a graph."
@@ -3498,14 +3990,18 @@
             "type": "object",
             "title": "Config Schema",
             "description": "The schema for the graph config. Missing if unable to generate JSON schema from graph."
+          },
+          "context_schema": {
+            "type": "object",
+            "title": "Context Schema",
+            "description": "The schema for the graph context. Missing if unable to generate JSON schema from graph."
           }
         },
         "type": "object",
         "required": [
           "input_schema",
           "output_schema",
-          "state_schema",
-          "config_schema"
+          "state_schema"
         ],
         "title": "GraphSchemaNoId",
         "description": "Defines the structure and properties of a graph without an ID."
@@ -3516,7 +4012,7 @@
           "$ref": "#/components/schemas/GraphSchemaNoId"
         },
         "title": "Subgraphs",
-        "description": "Map of graph name to graph schema metadata (`input_schema`, `output_schema`, `state_schema`, `config_schema`)."
+        "description": "Map of graph name to graph schema metadata (`input_schema`, `output_schema`, `state_schema`, `config_schema`, `context_schema`)."
       },
       "Run": {
         "properties": {
@@ -3766,6 +4262,11 @@
             "title": "Config",
             "description": "The configuration for the assistant."
           },
+          "context": {
+            "type": "object",
+            "title": "Context",
+            "description": "Static context added to the assistant."
+          },
           "webhook": {
             "type": "string",
             "maxLength": 65536,
@@ -3819,6 +4320,8 @@
                     "values",
                     "messages",
                     "messages-tuple",
+                    "tasks",
+                    "checkpoints",
                     "updates",
                     "events",
                     "debug",
@@ -3833,6 +4336,8 @@
                   "values",
                   "messages",
                   "messages-tuple",
+                  "tasks",
+                  "checkpoints",
                   "updates",
                   "events",
                   "debug",
@@ -3886,7 +4391,7 @@
             ],
             "title": "Multitask Strategy",
             "description": "Multitask strategy to use. Must be one of 'reject', 'interrupt', 'rollback', or 'enqueue'.",
-            "default": "reject"
+            "default": "enqueue"
           },
           "if_not_exists": {
             "type": "string",
@@ -4005,6 +4510,11 @@
             "title": "Config",
             "description": "The configuration for the assistant."
           },
+          "context": {
+            "type": "object",
+            "title": "Context",
+            "description": "Static context added to the assistant."
+          },
           "webhook": {
             "type": "string",
             "maxLength": 65536,
@@ -4058,6 +4568,8 @@
                     "values",
                     "messages",
                     "messages-tuple",
+                    "tasks",
+                    "checkpoints",
                     "updates",
                     "events",
                     "debug",
@@ -4072,6 +4584,8 @@
                   "values",
                   "messages",
                   "messages-tuple",
+                  "tasks",
+                  "checkpoints",
                   "updates",
                   "events",
                   "debug",
@@ -4191,12 +4705,49 @@
             ],
             "title": "Sort Order",
             "description": "The order to sort by."
+          },
+          "select": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "enum": [
+                "assistant_id",
+                "graph_id", 
+                "name",
+                "description",
+                "config",
+                "context",
+                "created_at",
+                "updated_at",
+                "metadata",
+                "version"
+              ]
+            },
+            "title": "Select",
+            "description": "Specify which fields to return. If not provided, all fields are returned."
           }
         },
         "type": "object",
         "title": "AssistantSearchRequest",
         "description": "Payload for listing assistants."
       },
+      "AssistantCountRequest": {
+        "properties": {
+          "metadata": {
+            "type": "object",
+            "title": "Metadata",
+            "description": "Metadata to filter by. Exact match filter for each KV pair."
+          },
+          "graph_id": {
+            "type": "string",
+            "title": "Graph Id",
+            "description": "The ID of the graph to filter by. The graph ID is normally set in your langgraph.json configuration."
+          }
+        },
+        "type": "object",
+        "title": "AssistantCountRequest",
+        "description": "Payload for counting assistants."
+      },
       "AssistantVersionsSearchRequest": {
         "properties": {
           "metadata": {
@@ -4281,12 +4832,59 @@
             ],
             "title": "Sort Order",
             "description": "Sort order."
+          },
+          "select": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "enum": [
+                "thread_id",
+                "created_at",
+                "updated_at",
+                "metadata",
+                "config",
+                "context",
+                "status",
+                "values",
+                "interrupts"
+              ]
+            },
+            "title": "Select",
+            "description": "Specify which fields to return. If not provided, all fields are returned."
           }
         },
         "type": "object",
         "title": "ThreadSearchRequest",
         "description": "Payload for listing threads."
       },
+      "ThreadCountRequest": {
+        "properties": {
+          "metadata": {
+            "type": "object",
+            "title": "Metadata",
+            "description": "Thread metadata to filter on."
+          },
+          "values": {
+            "type": "object",
+            "title": "Values",
+            "description": "State values to filter on."
+          },
+          "status": {
+            "type": "string",
+            "enum": [
+              "idle",
+              "busy",
+              "interrupted",
+              "error"
+            ],
+            "title": "Status",
+            "description": "Thread status to filter on."
+          }
+        },
+        "type": "object",
+        "title": "ThreadCountRequest",
+        "description": "Payload for counting threads."
+      },
       "Thread": {
         "properties": {
           "thread_id": {
@@ -4312,6 +4910,11 @@
             "title": "Metadata",
             "description": "The thread metadata."
           },
+          "config": {
+            "type": "object",
+            "title": "Config",
+            "description": "The thread config."
+          },
           "status": {
             "type": "string",
             "enum": [
@@ -4327,6 +4930,11 @@
             "type": "object",
             "title": "Values",
             "description": "The current state of the thread."
+          },
+          "interrupts": {
+            "type": "object",
+            "title": "Interrupts",
+            "description": "The current interrupts of the thread."
           }
         },
         "type": "object",
@@ -4476,7 +5084,9 @@
                 },
                 "interrupts": {
                   "type": "array",
-                  "items": {}
+                  "items": {
+                    "$ref": "#/components/schemas/Interrupt"
+                  }
                 },
                 "checkpoint": {
                   "$ref": "#/components/schemas/CheckpointConfig",
@@ -4509,6 +5119,12 @@
           "parent_checkpoint": {
             "type": "object",
             "title": "Parent Checkpoint"
+          },
+          "interrupts": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/Interrupt"
+            }
           }
         },
         "type": "object",
@@ -4527,7 +5143,7 @@
             "type": "integer",
             "title": "Limit",
             "description": "The maximum number of states to return.",
-            "default": 10,
+            "default": 1,
             "maximum": 1000,
             "minimum": 1
           },
@@ -4954,6 +5570,24 @@
             }
           }
         }
+      },
+      "Interrupt": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "value": {
+            "type": "object"
+          }
+        },
+        "title": "Interrupt",
+        "required": [
+          "value"
+        ]
       }
     }
   }

docs/docs/cloud/reference/cli.md

@@ -0,0 +1,544 @@
+# LangGraph CLI
+
+The LangGraph command line interface includes commands to build and run a LangGraph Platform API server locally in [Docker](https://www.docker.com/). For development and testing, you can use the CLI to deploy a local API server.
+
+## Installation
+
+1.  Ensure that Docker is installed (e.g. `docker --version`).
+2.  Install the CLI package:
+
+    === "Python"
+        ```bash
+        pip install langgraph-cli
+        ```
+
+    === "JS"
+        ```bash
+        npx @langchain/langgraph-cli
+
+        # Install globally, will be available as `langgraphjs`
+        npm install -g @langchain/langgraph-cli
+        ```
+
+3.  Run the command `langgraph --help` or `npx @langchain/langgraph-cli --help` to confirm that the CLI is working correctly.
+
+[](){#langgraph.json}
+
+## Configuration File {#configuration-file}
+
+The LangGraph CLI requires a JSON configuration file that follows this [schema](https://raw.githubusercontent.com/langchain-ai/langgraph/refs/heads/main/libs/cli/schemas/schema.json). It contains the following properties:
+
+<div class="admonition tip">
+    <p class="admonition-title">Note</p>
+    <p>
+        The LangGraph CLI defaults to using the configuration file <strong>langgraph.json</strong> in the current directory.
+    </p>
+</div>
+
+=== "Python"
+
+    | Key                                                          | Description                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
+    | ------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+    | <span style="white-space: nowrap;">`dependencies`</span>     | **Required**. Array of dependencies for LangGraph Platform API server. Dependencies can be one of the following: <ul><li>A single period (`"."`), which will look for local Python packages.</li><li>The directory path where `pyproject.toml`, `setup.py` or `requirements.txt` is located.</br></br>For example, if `requirements.txt` is located in the root of the project directory, specify `"./"`. If it's located in a subdirectory called `local_package`, specify `"./local_package"`. Do not specify the string `"requirements.txt"` itself.</li><li>A Python package name.</li></ul> |
+    | <span style="white-space: nowrap;">`graphs`</span>           | **Required**. Mapping from graph ID to path where the compiled graph or a function that makes a graph is defined. Example: <ul><li>`./your_package/your_file.py:variable`, where `variable` is an instance of `langgraph.graph.state.CompiledStateGraph`</li><li>`./your_package/your_file.py:make_graph`, where `make_graph` is a function that takes a config dictionary (`langchain_core.runnables.RunnableConfig`) and returns an instance of `langgraph.graph.state.StateGraph` or `langgraph.graph.state.CompiledStateGraph`. See [how to rebuild a graph at runtime](../../cloud/deployment/graph_rebuild.md) for more details.</li></ul>                                    |
+    | <span style="white-space: nowrap;">`auth`</span>             | _(Added in v0.0.11)_ Auth configuration containing the path to your authentication handler. Example: `./your_package/auth.py:auth`, where `auth` is an instance of `langgraph_sdk.Auth`. See [authentication guide](../../concepts/auth.md) for details.                                                                                                                                                                                                                                                                                                                        |
+    | <span style="white-space: nowrap;">`base_image`</span>       | Optional. Base image to use for the LangGraph API server. Defaults to `langchain/langgraph-api` or `langchain/langgraphjs-api`. Use this to pin your builds to a particular version of the langgraph API, such as `"langchain/langgraph-server:0.2"`. See https://hub.docker.com/r/langchain/langgraph-server/tags for more details. (added in `langgraph-cli==0.2.8`) |
+    | <span style="white-space: nowrap;">`image_distro`</span>     | Optional. Linux distribution for the base image. Must be either `"debian"` or `"wolfi"`. If omitted, defaults to `"debian"`. Available in `langgraph-cli>=0.2.11`.|
+    | <span style="white-space: nowrap;">`env`</span>              | Path to `.env` file or a mapping from environment variable to its value.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+    | <span style="white-space: nowrap;">`store`</span>            | Configuration for adding semantic search and/or time-to-live (TTL) to the BaseStore. Contains the following fields: <ul><li>`index` (optional): Configuration for semantic search indexing with fields `embed`, `dims`, and optional `fields`.</li><li>`ttl` (optional): Configuration for item expiration. An object with optional fields: `refresh_on_read` (boolean, defaults to `true`), `default_ttl` (float, lifespan in **minutes**, defaults to no expiration), and `sweep_interval_minutes` (integer, how often to check for expired items, defaults to no sweeping).</li></ul> |
+    | <span style="white-space: nowrap;">`ui`</span>               | Optional. Named definitions of UI components emitted by the agent, each pointing to a JS/TS file. (added in `langgraph-cli==0.1.84`)                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
+    | <span style="white-space: nowrap;">`python_version`</span>   | `3.11`, `3.12`, or `3.13`. Defaults to `3.11`.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
+    | <span style="white-space: nowrap;">`node_version`</span>     | Specify `node_version: 20` to use LangGraph.js.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+    | <span style="white-space: nowrap;">`pip_config_file`</span>  | Path to `pip` config file.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
+    | <span style="white-space: nowrap;">`pip_installer`</span> | _(Added in v0.3)_ Optional. Python package installer selector. It can be set to `"auto"`, `"pip"`, or `"uv"`. From version&nbsp;0.3 onward the default strategy is to run `uv pip`, which typically delivers faster builds while remaining a drop-in replacement. In the uncommon situation where `uv` cannot handle your dependency graph or the structure of your `pyproject.toml`, specify `"pip"` here to revert to the earlier behaviour. |
+    | <span style="white-space: nowrap;">`keep_pkg_tools`</span> | _(Added in v0.3.4)_ Optional. Control whether to retain Python packaging tools (`pip`, `setuptools`, `wheel`) in the final image. Accepted values: <ul><li><code>true</code> : Keep all three tools (skip uninstall).</li><li><code>false</code> / omitted : Uninstall all three tools (default behaviour).</li><li><code>list[str]</code> : Names of tools <strong>to retain</strong>. Each value must be one of "pip", "setuptools", "wheel".</li></ul>. By default, all three tools are uninstalled. |
+    | <span style="white-space: nowrap;">`dockerfile_lines`</span> | Array of additional lines to add to Dockerfile following the import from parent image.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+    | <span style="white-space: nowrap;">`checkpointer`</span>   | Configuration for the checkpointer. Contains a `ttl` field which is an object with the following keys: <ul><li>`strategy`: How to handle expired checkpoints (e.g., `"delete"`).</li><li>`sweep_interval_minutes`: How often to check for expired checkpoints (integer).</li><li>`default_ttl`: Default time-to-live for checkpoints in **minutes** (integer). Defines how long checkpoints are kept before the specified strategy is applied.</li></ul> |
+    | <span style="white-space: nowrap;">`http`</span>            | HTTP server configuration with the following fields: <ul><li>`app`: Path to custom Starlette/FastAPI app (e.g., `"./src/agent/webapp.py:app"`). See [custom routes guide](../../how-tos/http/custom_routes.md).</li><li>`cors`: CORS configuration with fields for `allow_origins`, `allow_methods`, `allow_headers`, etc.</li><li>`configurable_headers`: Define which request headers to exclude or include as a run's configurable values.</li><li>`disable_assistants`: Disable `/assistants` routes</li><li>`disable_mcp`: Disable `/mcp` routes</li><li>`disable_meta`: Disable `/ok`, `/info`, `/metrics`, and `/docs` routes</li><li>`disable_runs`: Disable `/runs` routes</li><li>`disable_store`: Disable `/store` routes</li><li>`disable_threads`: Disable `/threads` routes</li><li>`disable_ui`: Disable `/ui` routes</li><li>`disable_webhooks`: Disable webhooks calls on run completion in all routes</li><li>`mount_prefix`: Prefix for mounted routes (e.g., "/my-deployment/api")</li></ul> |
+
+=== "JS"
+
+    | Key                                                          | Description                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
+    | ------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+    | <span style="white-space: nowrap;">`graphs`</span>           | **Required**. Mapping from graph ID to path where the compiled graph or a function that makes a graph is defined. Example: <ul><li>`./src/graph.ts:variable`, where `variable` is an instance of `CompiledStateGraph`</li><li>`./src/graph.ts:makeGraph`, where `makeGraph` is a function that takes a config dictionary (`LangGraphRunnableConfig`) and returns an instance of `StateGraph` or `CompiledStateGraph`. See [how to rebuild a graph at runtime](../../cloud/deployment/graph_rebuild.md) for more details.</li></ul>                                    |
+    | <span style="white-space: nowrap;">`env`</span>              | Path to `.env` file or a mapping from environment variable to its value.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+    | <span style="white-space: nowrap;">`store`</span>            | Configuration for adding semantic search and/or time-to-live (TTL) to the BaseStore. Contains the following fields: <ul><li>`index` (optional): Configuration for semantic search indexing with fields `embed`, `dims`, and optional `fields`.</li><li>`ttl` (optional): Configuration for item expiration. An object with optional fields: `refresh_on_read` (boolean, defaults to `true`), `default_ttl` (float, lifespan in **minutes**, defaults to no expiration), and `sweep_interval_minutes` (integer, how often to check for expired items, defaults to no sweeping).</li></ul> |
+    | <span style="white-space: nowrap;">`node_version`</span>     | Specify `node_version: 20` to use LangGraph.js.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+    | <span style="white-space: nowrap;">`dockerfile_lines`</span> | Array of additional lines to add to Dockerfile following the import from parent image.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+    | <span style="white-space: nowrap;">`checkpointer`</span>   | Configuration for the checkpointer. Contains a `ttl` field which is an object with the following keys: <ul><li>`strategy`: How to handle expired checkpoints (e.g., `"delete"`).</li><li>`sweep_interval_minutes`: How often to check for expired checkpoints (integer).</li><li>`default_ttl`: Default time-to-live for checkpoints in **minutes** (integer). Defines how long checkpoints are kept before the specified strategy is applied.</li></ul> |
+
+### Examples
+
+=== "Python"
+    
+    #### Basic Configuration
+
+    ```json
+    {
+      "dependencies": ["."],
+      "graphs": {
+        "chat": "./chat/graph.py:graph"
+      }
+    }
+    ```
+
+    #### Using Wolfi Base Images
+
+    You can specify the Linux distribution for your base image using the `image_distro` field. Valid options are `debian` or `wolfi`. Wolfi is the recommended option as it provides smaller and more secure images. This is available in `langgraph-cli>=0.2.11`.
+
+    ```json
+    {
+      "dependencies": ["."],
+      "graphs": {
+        "chat": "./chat/graph.py:graph"
+      },
+      "image_distro": "wolfi"
+    }
+    ```
+
+    #### Adding semantic search to the store
+
+    All deployments come with a DB-backed BaseStore. Adding an "index" configuration to your `langgraph.json` will enable [semantic search](../deployment/semantic_search.md) within the BaseStore of your deployment.
+
+    The `index.fields` configuration determines which parts of your documents to embed:
+
+    - If omitted or set to `["$"]`, the entire document will be embedded
+    - To embed specific fields, use JSON path notation: `["metadata.title", "content.text"]`
+    - Documents missing specified fields will still be stored but won't have embeddings for those fields
+    - You can still override which fields to embed on a specific item at `put` time using the `index` parameter
+
+    ```json
+    {
+      "dependencies": ["."],
+      "graphs": {
+        "memory_agent": "./agent/graph.py:graph"
+      },
+      "store": {
+        "index": {
+          "embed": "openai:text-embedding-3-small",
+          "dims": 1536,
+          "fields": ["$"]
+        }
+      }
+    }
+    ```
+
+    !!! note "Common model dimensions" 
+        - `openai:text-embedding-3-large`: 3072 
+        - `openai:text-embedding-3-small`: 1536 
+        - `openai:text-embedding-ada-002`: 1536 
+        - `cohere:embed-english-v3.0`: 1024 
+        - `cohere:embed-english-light-v3.0`: 384 
+        - `cohere:embed-multilingual-v3.0`: 1024 
+        - `cohere:embed-multilingual-light-v3.0`: 384 
+
+    #### Semantic search with a custom embedding function
+
+    If you want to use semantic search with a custom embedding function, you can pass a path to a custom embedding function:
+
+    ```json
+    {
+      "dependencies": ["."],
+      "graphs": {
+        "memory_agent": "./agent/graph.py:graph"
+      },
+      "store": {
+        "index": {
+          "embed": "./embeddings.py:embed_texts",
+          "dims": 768,
+          "fields": ["text", "summary"]
+        }
+      }
+    }
+    ```
+
+    The `embed` field in store configuration can reference a custom function that takes a list of strings and returns a list of embeddings. Example implementation:
+
+    ```python
+    # embeddings.py
+    def embed_texts(texts: list[str]) -> list[list[float]]:
+        """Custom embedding function for semantic search."""
+        # Implementation using your preferred embedding model
+        return [[0.1, 0.2, ...] for _ in texts]  # dims-dimensional vectors
+    ```
+
+    #### Adding custom authentication
+
+    ```json
+    {
+      "dependencies": ["."],
+      "graphs": {
+        "chat": "./chat/graph.py:graph"
+      },
+      "auth": {
+        "path": "./auth.py:auth",
+        "openapi": {
+          "securitySchemes": {
+            "apiKeyAuth": {
+              "type": "apiKey",
+              "in": "header",
+              "name": "X-API-Key"
+            }
+          },
+          "security": [{ "apiKeyAuth": [] }]
+        },
+        "disable_studio_auth": false
+      }
+    }
+    ```
+
+    See the [authentication conceptual guide](../../concepts/auth.md) for details, and the [setting up custom authentication](../../tutorials/auth/getting_started.md) guide for a practical walk through of the process.
+
+    #### Configuring Store Item Time-to-Live (TTL)
+
+    You can configure default data expiration for items/memories in the BaseStore using the `store.ttl` key. This determines how long items are retained after they are last accessed (with reads potentially refreshing the timer based on `refresh_on_read`). Note that these defaults can be overwritten on a per-call basis by modifying the corresponding arguments in `get`, `search`, etc.
+    
+    The `ttl` configuration is an object containing optional fields:
+
+    - `refresh_on_read`: If `true` (the default), accessing an item via `get` or `search` resets its expiration timer. Set to `false` to only refresh TTL on writes (`put`).
+    - `default_ttl`: The default lifespan of an item in **minutes**. If not set, items do not expire by default.
+    - `sweep_interval_minutes`: How frequently (in minutes) the system should run a background process to delete expired items. If not set, sweeping does not occur automatically.
+
+    Here is an example enabling a 7-day TTL (10080 minutes), refreshing on reads, and sweeping every hour:
+
+    ```json
+    {
+      "dependencies": ["."],
+      "graphs": {
+        "memory_agent": "./agent/graph.py:graph"
+      },
+      "store": {
+        "ttl": {
+          "refresh_on_read": true,
+          "sweep_interval_minutes": 60,
+          "default_ttl": 10080 
+        }
+      }
+    }
+    ```
+
+    #### Configuring Checkpoint Time-to-Live (TTL)
+
+    You can configure the time-to-live (TTL) for checkpoints using the `checkpointer` key. This determines how long checkpoint data is retained before being automatically handled according to the specified strategy (e.g., deletion). The `ttl` configuration is an object containing:
+
+    - `strategy`: The action to take on expired checkpoints (currently `"delete"` is the only accepted option).
+    - `sweep_interval_minutes`: How frequently (in minutes) the system checks for expired checkpoints.
+    - `default_ttl`: The default lifespan of a checkpoint in **minutes**.
+
+    Here's an example setting a default TTL of 30 days (43200 minutes):
+
+    ```json
+    {
+      "dependencies": ["."],
+      "graphs": {
+        "chat": "./chat/graph.py:graph"
+      },
+      "checkpointer": {
+        "ttl": {
+          "strategy": "delete",
+          "sweep_interval_minutes": 10,
+          "default_ttl": 43200
+        }
+      }
+    }
+    ```
+
+    In this example, checkpoints older than 30 days will be deleted, and the check runs every 10 minutes.
+
+
+=== "JS"
+    
+    #### Basic Configuration
+
+    ```json
+    {
+      "graphs": {
+        "chat": "./src/graph.ts:graph"
+      }
+    }
+    ```
+
+
+## Commands
+
+**Usage**
+
+=== "Python"
+
+    The base command for the LangGraph CLI is `langgraph`.
+
+    ```
+    langgraph [OPTIONS] COMMAND [ARGS]
+    ```
+=== "JS"
+
+    The base command for the LangGraph.js CLI is `langgraphjs`. 
+
+    ```
+    npx @langchain/langgraph-cli [OPTIONS] COMMAND [ARGS]
+    ```
+
+    We recommend using `npx` to always use the latest version of the CLI.
+
+### `dev`
+
+=== "Python"
+
+    Run LangGraph API server in development mode with hot reloading and debugging capabilities. This lightweight server requires no Docker installation and is suitable for development and testing. State is persisted to a local directory.
+
+    !!! note
+
+        Currently, the CLI only supports Python >= 3.11.
+
+    **Installation**
+
+    This command requires the "inmem" extra to be installed:
+
+    ```bash
+    pip install -U "langgraph-cli[inmem]"
+    ```
+
+    **Usage**
+
+    ```
+    langgraph dev [OPTIONS]
+    ```
+
+    **Options**
+
+    | Option                        | Default          | Description                                                                         |
+    | ----------------------------- | ---------------- | ----------------------------------------------------------------------------------- |
+    | `-c, --config FILE`           | `langgraph.json` | Path to configuration file declaring dependencies, graphs and environment variables |
+    | `--host TEXT`                 | `127.0.0.1`      | Host to bind the server to                                                          |
+    | `--port INTEGER`              | `2024`           | Port to bind the server to                                                          |
+    | `--no-reload`                 |                  | Disable auto-reload                                                                 |
+    | `--n-jobs-per-worker INTEGER` |                  | Number of jobs per worker. Default is 10                                            |
+    | `--debug-port INTEGER`        |                  | Port for debugger to listen on                                                      |
+    | `--wait-for-client`           | `False`          | Wait for a debugger client to connect to the debug port before starting the server   |
+    | `--no-browser`                |                  | Skip automatically opening the browser when the server starts                       |
+    | `--studio-url TEXT`           |                  | URL of the LangGraph Studio instance to connect to. Defaults to https://smith.langchain.com |
+    | `--allow-blocking`            | `False`          | Do not raise errors for synchronous I/O blocking operations in your code (added in `0.2.6`)           |
+    | `--tunnel`                    | `False`          | Expose the local server via a public tunnel (Cloudflare) for remote frontend access. This avoids issues with browsers like Safari or networks blocking localhost connections        |
+    | `--help`                      |                  | Display command documentation                                                       |
+
+
+=== "JS"
+
+    Run LangGraph API server in development mode with hot reloading capabilities. This lightweight server requires no Docker installation and is suitable for development and testing. State is persisted to a local directory.
+
+    **Usage**
+
+    ```
+    npx @langchain/langgraph-cli dev [OPTIONS]
+    ```
+
+    **Options**
+
+    | Option                        | Default          | Description                                                                         |
+    | ----------------------------- | ---------------- | ----------------------------------------------------------------------------------- |
+    | `-c, --config FILE`           | `langgraph.json` | Path to configuration file declaring dependencies, graphs and environment variables |
+    | `--host TEXT`                 | `127.0.0.1`      | Host to bind the server to                                                          |
+    | `--port INTEGER`              | `2024`           | Port to bind the server to                                                          |
+    | `--no-reload`                 |                  | Disable auto-reload                                                                 |
+    | `--n-jobs-per-worker INTEGER` |                  | Number of jobs per worker. Default is 10                                            |
+    | `--debug-port INTEGER`        |                  | Port for debugger to listen on                                                      |
+    | `--wait-for-client`           | `False`          | Wait for a debugger client to connect to the debug port before starting the server   |
+    | `--no-browser`                |                  | Skip automatically opening the browser when the server starts                       |
+    | `--studio-url TEXT`           |                  | URL of the LangGraph Studio instance to connect to. Defaults to https://smith.langchain.com |
+    | `--allow-blocking`            | `False`          | Do not raise errors for synchronous I/O blocking operations in your code            |
+    | `--tunnel`                    | `False`          | Expose the local server via a public tunnel (Cloudflare) for remote frontend access. This avoids issues with browsers or networks blocking localhost connections        |
+    | `--help`                      |                  | Display command documentation                                                       |
+
+### `build`
+
+=== "Python"
+
+    Build LangGraph Platform API server Docker image.
+
+    **Usage**
+
+    ```
+    langgraph build [OPTIONS]
+    ```
+
+    **Options**
+
+    | Option               | Default          | Description                                                                                                     |
+    | -------------------- | ---------------- | --------------------------------------------------------------------------------------------------------------- |
+    | `--platform TEXT`    |                  | Target platform(s) to build the Docker image for. Example: `langgraph build --platform linux/amd64,linux/arm64`              |
+    | `-t, --tag TEXT`     |                  | **Required**. Tag for the Docker image. Example: `langgraph build -t my-image`                                               |
+    | `--pull / --no-pull` | `--pull`         | Build with latest remote Docker image. Use `--no-pull` for running the LangGraph Platform API server with locally built images. |
+    | `-c, --config FILE`  | `langgraph.json` | Path to configuration file declaring dependencies, graphs and environment variables.                                         |
+    | `--help`             |                  | Display command documentation.                                                                                               |
+
+=== "JS"
+
+    Build LangGraph Platform API server Docker image.
+
+    **Usage**
+
+    ```
+    npx @langchain/langgraph-cli build [OPTIONS]
+    ```
+
+    **Options**
+
+    | Option               | Default          | Description                                                                                                     |
+    | -------------------- | ---------------- | --------------------------------------------------------------------------------------------------------------- |
+    | `--platform TEXT`    |                  | Target platform(s) to build the Docker image for. Example: `langgraph build --platform linux/amd64,linux/arm64`              |
+    | `-t, --tag TEXT`     |                  | **Required**. Tag for the Docker image. Example: `langgraph build -t my-image`                                               |
+    | `--no-pull`          |                  | Use locally built images. Defaults to `false` to build with latest remote Docker image.                                      |
+    | `-c, --config FILE`  | `langgraph.json` | Path to configuration file declaring dependencies, graphs and environment variables.                                         |
+    | `--help`             |                  | Display command documentation.                                                                                               |
+
+
+### `up`
+
+=== "Python"
+
+    Start LangGraph API server. For local testing, requires a LangSmith API key with access to LangGraph Platform. Requires a license key for production use.
+
+    **Usage**
+
+    ```
+    langgraph up [OPTIONS]
+    ```
+
+    **Options**
+
+    | Option                       | Default                   | Description                                                                                                             |
+    | ---------------------------- | ------------------------- | ----------------------------------------------------------------------------------------------------------------------- |
+    | `--wait`                     |                           | Wait for services to start before returning. Implies --detach                                                           |
+    | `--base-image TEXT`          | `langchain/langgraph-api`  | Base image to use for the LangGraph API server. Pin to specific versions using version tags.                            |
+    | `--image TEXT`               |                           | Docker image to use for the langgraph-api service. If specified, skips building and uses this image directly.           |
+    | `--postgres-uri TEXT`        | Local database            | Postgres URI to use for the database.                                                                                   |
+    | `--watch`                    |                           | Restart on file changes                                                                                                 |
+    | `--debugger-base-url TEXT`   | `http://127.0.0.1:[PORT]` | URL used by the debugger to access LangGraph API.                                                                       |
+    | `--debugger-port INTEGER`    |                           | Pull the debugger image locally and serve the UI on specified port                                                      |
+    | `--verbose`                  |                           | Show more output from the server logs.                                                                                  |
+    | `-c, --config FILE`          | `langgraph.json`          | Path to configuration file declaring dependencies, graphs and environment variables.                                    |
+    | `-d, --docker-compose FILE`  |                           | Path to docker-compose.yml file with additional services to launch.                                                     |
+    | `-p, --port INTEGER`         | `8123`                    | Port to expose. Example: `langgraph up --port 8000`                                                                     |
+    | `--pull / --no-pull`         | `pull`                    | Pull latest images. Use `--no-pull` for running the server with locally-built images. Example: `langgraph up --no-pull` |
+    | `--recreate / --no-recreate` | `no-recreate`             | Recreate containers even if their configuration and image haven't changed                                               |
+    | `--help`                     |                           | Display command documentation.                                                                                          |
+
+=== "JS"
+
+    Start LangGraph API server. For local testing, requires a LangSmith API key with access to LangGraph Platform. Requires a license key for production use.
+
+    **Usage**
+
+    ```
+    npx @langchain/langgraph-cli up [OPTIONS]
+    ```
+
+    **Options**
+
+    | Option                                                                 | Default                   | Description                                                                                                             |
+    | ---------------------------------------------------------------------- | ------------------------- | ----------------------------------------------------------------------------------------------------------------------- |
+    | <span style="white-space: nowrap;">`--wait`</span>                     |                           | Wait for services to start before returning. Implies --detach                                                           |
+    | <span style="white-space: nowrap;">`--base-image TEXT`</span>          | <span style="white-space: nowrap;">`langchain/langgraph-api`</span> | Base image to use for the LangGraph API server. Pin to specific versions using version tags. |
+    | <span style="white-space: nowrap;">`--image TEXT`</span>               |                           | Docker image to use for the langgraph-api service. If specified, skips building and uses this image directly. |
+    | <span style="white-space: nowrap;">`--postgres-uri TEXT`</span>        | Local database            | Postgres URI to use for the database.                                                                                   |
+    | <span style="white-space: nowrap;">`--watch`</span>                    |                           | Restart on file changes                                                                                                 |
+    | <span style="white-space: nowrap;">`-c, --config FILE`</span>          | `langgraph.json`          | Path to configuration file declaring dependencies, graphs and environment variables.                                    |
+    | <span style="white-space: nowrap;">`-d, --docker-compose FILE`</span>  |                           | Path to docker-compose.yml file with additional services to launch.                                                     |
+    | <span style="white-space: nowrap;">`-p, --port INTEGER`</span>         | `8123`                    | Port to expose. Example: `langgraph up --port 8000`                                                                     |
+    | <span style="white-space: nowrap;">`--no-pull`</span>                  |                           | Use locally built images. Defaults to `false` to build with latest remote Docker image.                                 |
+    | <span style="white-space: nowrap;">`--recreate`</span>                 |                           | Recreate containers even if their configuration and image haven't changed                                               |
+    | <span style="white-space: nowrap;">`--help`</span>                     |                           | Display command documentation.                                                                                          |
+
+### `dockerfile`
+
+=== "Python"
+
+    Generate a Dockerfile for building a LangGraph Platform API server Docker image.
+
+    **Usage**
+
+    ```
+    langgraph dockerfile [OPTIONS] SAVE_PATH
+    ```
+
+    **Options**
+
+    | Option              | Default          | Description                                                                                                     |
+    | ------------------- | ---------------- | --------------------------------------------------------------------------------------------------------------- |
+    | `-c, --config FILE` | `langgraph.json` | Path to the [configuration file](#configuration-file) declaring dependencies, graphs and environment variables. |
+    | `--help`            |                  | Show this message and exit.                                                                                     |
+
+    Example:
+
+    ```bash
+    langgraph dockerfile -c langgraph.json Dockerfile
+    ```
+
+    This generates a Dockerfile that looks similar to:
+
+    ```dockerfile
+    FROM langchain/langgraph-api:3.11
+
+    ADD ./pipconf.txt /pipconfig.txt
+
+    RUN PIP_CONFIG_FILE=/pipconfig.txt PYTHONDONTWRITEBYTECODE=1 pip install --no-cache-dir -c /api/constraints.txt langchain_community langchain_anthropic langchain_openai wikipedia scikit-learn
+
+    ADD ./graphs /deps/__outer_graphs/src
+    RUN set -ex && \
+        for line in '[project]' \
+                    'name = "graphs"' \
+                    'version = "0.1"' \
+                    '[tool.setuptools.package-data]' \
+                    '"*" = ["**/*"]'; do \
+            echo "$line" >> /deps/__outer_graphs/pyproject.toml; \
+        done
+
+    RUN PIP_CONFIG_FILE=/pipconfig.txt PYTHONDONTWRITEBYTECODE=1 pip install --no-cache-dir -c /api/constraints.txt -e /deps/*
+
+    ENV LANGSERVE_GRAPHS='{"agent": "/deps/__outer_graphs/src/agent.py:graph", "storm": "/deps/__outer_graphs/src/storm.py:graph"}'
+    ```
+
+    ???+ note "Updating your langgraph.json file"
+         The `langgraph dockerfile` command translates all the configuration in your `langgraph.json` file into Dockerfile commands. When using this command, you will have to re-run it whenever you update your `langgraph.json` file. Otherwise, your changes will not be reflected when you build or run the dockerfile.
+
+=== "JS"
+
+    Generate a Dockerfile for building a LangGraph Platform API server Docker image.
+
+    **Usage**
+
+    ```
+    npx @langchain/langgraph-cli dockerfile [OPTIONS] SAVE_PATH
+    ```
+
+    **Options**
+
+    | Option              | Default          | Description                                                                                                     |
+    | ------------------- | ---------------- | --------------------------------------------------------------------------------------------------------------- |
+    | `-c, --config FILE` | `langgraph.json` | Path to the [configuration file](#configuration-file) declaring dependencies, graphs and environment variables. |
+    | `--help`            |                  | Show this message and exit.                                                                                     |
+
+    Example:
+
+    ```bash
+    npx @langchain/langgraph-cli dockerfile -c langgraph.json Dockerfile
+    ```
+
+    This generates a Dockerfile that looks similar to:
+
+    ```dockerfile
+    FROM langchain/langgraphjs-api:20
+    
+    ADD . /deps/agent
+    
+    RUN cd /deps/agent && yarn install
+    
+    ENV LANGSERVE_GRAPHS='{"agent":"./src/react_agent/graph.ts:graph"}'
+    
+    WORKDIR /deps/agent
+    
+    RUN (test ! -f /api/langgraph_api/js/build.mts && echo "Prebuild script not found, skipping") || tsx /api/langgraph_api/js/build.mts
+    ```
+
+    ???+ note "Updating your langgraph.json file"
+         The `npx @langchain/langgraph-cli dockerfile` command translates all the configuration in your `langgraph.json` file into Dockerfile commands. When using this command, you will have to re-run it whenever you update your `langgraph.json` file. Otherwise, your changes will not be reflected when you build or run the dockerfile.

docs/docs/cloud/reference/env_var.md

@@ -0,0 +1,150 @@
+# Environment Variables
+
+The LangGraph Server supports specific environment variables for configuring a deployment.
+
+## `BG_JOB_ISOLATED_LOOPS`
+
+Set `BG_JOB_ISOLATED_LOOPS` to `True` to execute background runs in an isolated event loop separate from the serving API event loop.
+
+This environment variable should be set to `True` if the implementation of a graph/node contains synchronous code. In this situation, the synchronous code will block the serving API event loop, which may cause the API to be unavailable. A symptom of an unavailable API is continuous application restarts due to failing health checks.
+
+Defaults to `False`.
+
+## `BG_JOB_SHUTDOWN_GRACE_PERIOD_SECS`
+
+Specifies, in seconds, how long the server will wait for background jobs to finish after the queue receives a shutdown signal. After this period, the server will force termination. Defaults to `180` seconds. Set this to ensure jobs have enough time to complete cleanly during shutdown. Added in `langgraph-api==0.2.16`.
+
+## `BG_JOB_TIMEOUT_SECS`
+
+The timeout of a background run can be increased. However, the infrastructure for a Cloud SaaS deployment enforces a 1 hour timeout limit for API requests. This means the connection between client and server will timeout after 1 hour. This is not configurable.
+
+A background run can execute for longer than 1 hour, but a client must reconnect to the server (e.g. join stream via `POST /threads/{thread_id}/runs/{run_id}/stream`) to retrieve output from the run if the run is taking longer than 1 hour.
+
+Defaults to `3600`.
+
+## `DD_API_KEY`
+
+Specify `DD_API_KEY` (your [Datadog API Key](https://docs.datadoghq.com/account_management/api-app-keys/)) to automatically enable Datadog tracing for the deployment. Specify other [`DD_*` environment variables](https://ddtrace.readthedocs.io/en/stable/configuration.html) to configure the tracing instrumentation.
+
+If `DD_API_KEY` is specified, the application process is wrapped in the [`ddtrace-run` command](https://ddtrace.readthedocs.io/en/stable/installation_quickstart.html). Other `DD_*` environment variables (e.g. `DD_SITE`, `DD_ENV`, `DD_SERVICE`, `DD_TRACE_ENABLED`) are typically needed to properly configure the tracing instrumentation. See [`DD_*` environment variables](https://ddtrace.readthedocs.io/en/stable/configuration.html) for more details.
+
+!!! note 
+    Enabling `DD_API_KEY` (and thus `ddtrace-run`) can override or interfere with other auto-instrumentation solutions (such as OpenTelemetry) that you may have instrumented into your application code.
+
+## `LANGCHAIN_TRACING_SAMPLING_RATE`
+
+Sampling rate for traces sent to LangSmith. Valid values: Any float between `0` and `1`.
+
+See <a href="https://docs.smith.langchain.com/how_to_guides/tracing/sample_traces" target="_blank">LangSmith documentation</a> for more details.
+
+## `LANGGRAPH_AUTH_TYPE`
+
+Type of authentication for the LangGraph Server deployment. Valid values: `langsmith`, `noop`.
+
+For deployments to LangGraph Platform, this environment variable is set automatically. For local development or deployments where authentication is handled externally (e.g. self-hosted), set this environment variable to `noop`.
+
+## `LANGGRAPH_POSTGRES_POOL_MAX_SIZE`
+
+Beginning with langgraph-api version `0.2.12`, the maximum size of the Postgres connection pool (per replica) can be controlled using the `LANGGRAPH_POSTGRES_POOL_MAX_SIZE` environment variable. By setting this variable, you can determine the upper bound on the number of simultaneous connections the server will establish with the Postgres database.
+
+For example, if a deployment is scaled up to 10 replicas and `LANGGRAPH_POSTGRES_POOL_MAX_SIZE` is configured to `150`, then up to `1500` connections to Postgres can be established. This is particularly useful for deployments where database resources are limited (or more available) or where you need to tune connection behavior for performance or scaling reasons.
+
+Defaults to `150` connections.
+
+## `LANGSMITH_RUNS_ENDPOINTS`
+
+For deployments with [self-hosted LangSmith](https://docs.smith.langchain.com/self_hosting) only.
+
+Set this environment variable to have a deployment send traces to a self-hosted LangSmith instance. The value of `LANGSMITH_RUNS_ENDPOINTS` is a JSON string: `{"<SELF_HOSTED_LANGSMITH_HOSTNAME>":"<LANGSMITH_API_KEY>"}`.
+
+`SELF_HOSTED_LANGSMITH_HOSTNAME` is the hostname of the self-hosted LangSmith instance. It must be accessible to the deployment. `LANGSMITH_API_KEY` is a LangSmith API generated from the self-hosted LangSmith instance.
+
+## `LANGSMITH_TRACING`
+
+Set `LANGSMITH_TRACING` to `false` to disable tracing to LangSmith.
+
+Defaults to `true`.
+
+## `LOG_COLOR`
+
+This is mainly relevant in the context of using the dev server via the `langgraph dev` command. Set `LOG_COLOR` to `true` to enable ANSI-colored console output when using the default console renderer. Disabling color output by setting this variable to `false` produces monochrome logs. Defaults to `true`.
+
+## `LOG_LEVEL`
+
+Configure [log level](https://docs.python.org/3/library/logging.html#logging-levels). Defaults to `INFO`.
+
+## `LOG_JSON`
+
+Set `LOG_JSON` to `true` to render all log messages as JSON objects using the configured `JSONRenderer`. This produces structured logs that can be easily parsed or ingested by log management systems. Defaults to `false`.
+
+## `MOUNT_PREFIX`
+
+!!! info "Only Allowed in Self-Hosted Deployments"
+    The `MOUNT_PREFIX` environment variable is only allowed in Self-Hosted Deployment models, LangGraph Platform SaaS will not allow this environment variable.
+
+Set `MOUNT_PREFIX` to serve the LangGraph Server under a specific path prefix. This is useful for deployments where the server is behind a reverse proxy or load balancer that requires a specific path prefix.
+
+For example, if the server is to be served under `https://example.com/langgraph`, set `MOUNT_PREFIX` to `/langgraph`.
+
+## `N_JOBS_PER_WORKER`
+
+Number of jobs per worker for the LangGraph Server task queue. Defaults to `10`.
+
+## `POSTGRES_URI_CUSTOM`
+
+!!! info "Only for Self-Hosted Data Plane and Self-Hosted Control Plane"
+    Custom Postgres instances are only available for [Self-Hosted Data Plane](../../concepts/langgraph_self_hosted_data_plane.md) and [Self-Hosted Control Plane](../../concepts/langgraph_self_hosted_control_plane.md) deployments.
+
+Specify `POSTGRES_URI_CUSTOM` to use a custom Postgres instance. The value of `POSTGRES_URI_CUSTOM` must be a valid [Postgres connection URI](https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNSTRING-URIS).
+
+Postgres:
+
+- Version 15.8 or higher.
+- An initial database must be present and the connection URI must reference the database.
+
+Control Plane Functionality:
+
+- If `POSTGRES_URI_CUSTOM` is specified, the LangGraph Control Plane will not provision a database for the server.
+- If `POSTGRES_URI_CUSTOM` is removed, the LangGraph Control Plane will not provision a database for the server and will not delete the externally managed Postgres instance.
+- If `POSTGRES_URI_CUSTOM` is removed, deployment of the revision will not succeed. Once `POSTGRES_URI_CUSTOM` is specified, it must always be set for the lifecycle of the deployment.
+- If the deployment is deleted, the LangGraph Control Plane will not delete the externally managed Postgres instance.
+- The value of `POSTGRES_URI_CUSTOM` can be updated. For example, a password in the URI can be updated.
+
+Database Connectivity:
+
+- The custom Postgres instance must be accessible by the LangGraph Server. The user is responsible for ensuring connectivity.
+
+## `REDIS_CLUSTER`
+
+!!! info "Only Allowed in Self-Hosted Deployments"
+    Redis Cluster mode is only available in Self-Hosted Deployment models, LangGraph Platform SaaS will provision a redis instance for you by default.
+
+Set `REDIS_CLUSTER` to `True` to enable Redis Cluster mode. When enabled, the system will connect to Redis using cluster mode. This is useful when connecting to a Redis Cluster deployment.
+
+Defaults to `False`.
+
+## `REDIS_KEY_PREFIX`
+
+!!! info "Available in API Server version 0.1.9+"
+    This environment variable is supported in API Server version 0.1.9 and above.
+
+Specify a prefix for Redis keys. This allows multiple LangGraph Server instances to share the same Redis instance by using different key prefixes. 
+
+Defaults to `''`.
+
+## `REDIS_URI_CUSTOM`
+
+!!! info "Only for Self-Hosted Data Plane and Self-Hosted Control Plane"
+    Custom Redis instances are only available for [Self-Hosted Data Plane](../../concepts/langgraph_self_hosted_data_plane.md) and [Self-Hosted Control Plane](../../concepts/langgraph_self_hosted_control_plane.md) deployments.
+
+Specify `REDIS_URI_CUSTOM` to use a custom Redis instance. The value of `REDIS_URI_CUSTOM` must be a valid [Redis connection URI](https://redis-py.readthedocs.io/en/stable/connections.html#redis.Redis.from_url).
+
+## `RESUMABLE_STREAM_TTL_SECONDS`
+
+Time-to-live in seconds for resumable stream data in Redis.
+
+When a run is created and the output is streamed, the stream can be configured to be resumable (e.g. `stream_resumable=True`). If a stream is resumable, output from the stream is temporarily stored in Redis. The TTL for this data can be configured by setting `RESUMABLE_STREAM_TTL_SECONDS`.
+
+See the [Python](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/python_sdk_ref/#langgraph_sdk.client.RunsClient.stream) and [JS/TS](https://langchain-ai.github.io/langgraphjs/reference/classes/sdk_client.RunsClient.html#stream) SDKs for more details on how to implement resumable streams.
+
+Defaults to `120` seconds.

docs/docs/cloud/reference/langgraph_server_changelog.md

@@ -0,0 +1,233 @@
+# 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.
+
+---
+
+## v0.2.111 (2025-07-29)
+- Started the heartbeat immediately upon connection to prevent JS graph streaming errors during long startups.
+
+## v0.2.110 (2025-07-29)
+- Added interrupts as default values for all operations except streams to maintain consistent behavior.
+
+## v0.2.109 (2025-07-28)
+- Fixed an issue where missing config schema occurred when `config_type` was not set.
+
+## v0.2.108 (2025-07-28)
+- Added compatibility for langgraph v0.6, including new context API support and a migration to enhance context handling in assistant operations.
+
+## v0.2.107 (2025-07-27)
+- Implemented caching for authentication processes to improve performance.
+- Merged count and select queries to improve database query efficiency.
+
+## v0.2.106 (2025-07-27)
+- Log whether run uses resumable streams.
+
+## v0.2.105 (2025-07-27)
+- Added a `/heapdump` endpoint to capture and save JS process heap data.
+
+## v0.2.103 (2025-07-25)
+- Corrected the metadata endpoint to ensure accurate data retrieval.
+
+## v0.2.102 (2025-07-24)
+- Captured interrupt events in the wait method to preserve legacy behavior and stream updates by default.
+- Added support for SDK structlog in the JavaScript environment, enhancing logging capabilities.
+
+## v0.2.101 (2025-07-24)
+- Used the correct metadata endpoint for self-hosted environments, resolving an access issue.
+
+## v0.2.99 (2025-07-22)
+- Improved license validation by adding an in-memory cache and handling Redis connection errors more effectively.
+- Automatically remove agents from memory that are removed from `langgraph.json` to prevent persistence issues.
+- Ensured the UI namespace for generated UI is a valid JavaScript property name to prevent errors.
+- Raised a 422 error for improved request validation feedback.
+
+## v0.2.98 (2025-07-19)
+- Added langgraph node context for improved log filtering and trace visibility.
+
+## v0.2.97 (2025-07-19)
+- Fixed scheduling issue with ckpt ingestion worker that occurred on isolated background loops.
+- Ensured queue worker starts only after all migrations have completed.
+- Added more detailed error messages for thread state issues and improved response handling when state updates fail.
+- Exposed interrupt ID while retrieving thread state for enhanced API response details.
+
+## v0.2.96 (2025-07-17)
+- Added a fallback mechanism for configurable header patterns to handle exclude/include settings more effectively.
+
+## v0.2.95 (2025-07-17)
+- Avoided setting the future if it is already done to prevent redundant operations.
+- Resolved compatibility errors in CI by switching from `typing.TypedDict` to `typing_extensions.TypedDict` for Python versions below 3.12.
+
+## v0.2.94 (2025-07-16)
+- Improved performance by omitting pending sends for langgraph versions 0.5 and above.
+- Improved server startup logs to provide clearer warnings when the DD_API_KEY environment variable is set.
+
+## v0.2.93 (2025-07-16)
+- Removed the GIN index for run metadata to improve performance.
+
+## v0.2.92 (2025-07-16)
+- Enabled copying functionality for blobs and checkpoints, improving data management flexibility.
+
+## v0.2.91 (2025-07-16)
+- Reduced writes to the `checkpoint_blobs` table by inlining small values (null, numeric, str, etc.). This means we don't need to store extra values for channels that haven't been updated.
+
+## v0.2.90 (2025-07-16)
+- Improve checkpoint writes via node-local background queueing.
+
+
+## v0.2.89 (2025-07-15)
+- Decoupled checkpoint writing from thread/run state by removing foreign keys and updated logger to prevent timeout-related failures.
+
+## v0.2.88 (2025-07-14)
+- Removed the foreign key constraint for `thread` in the `run` table to simplify database schema.
+
+## v0.2.87 (2025-07-14)
+- Added more detailed logs for Redis worker signaling to improve debugging.
+
+## v0.2.86 (2025-07-11)
+- Honored tool descriptions in the `/mcp` endpoint to align with expected functionality.
+
+## v0.2.85 (2025-07-10)
+- Added support for the `on_disconnect` field to `runs/wait` and included disconnect logs for better debugging.
+
+## v0.2.84 (2025-07-09)
+- Removed unnecessary status updates to streamline thread handling and updated version to 0.2.84.
+
+## v0.2.83 (2025-07-09)
+- Reduced the default time-to-live for resumable streams to 2 minutes.
+- Enhanced data submission logic to send data to both Beacon and LangSmith instance based on license configuration.
+- Enabled submission of self-hosted data to a Langsmith instance when the endpoint is configured.
+
+## v0.2.82 (2025-07-03)
+- Addressed a race condition in background runs by implementing a lock using join, ensuring reliable execution across CTEs.
+
+## v0.2.81 (2025-07-03)
+- Optimized run streams by reducing initial wait time to improve responsiveness for older or non-existent runs.
+
+## v0.2.80 (2025-07-03)
+- Corrected parameter passing in the `logger.ainfo()` API call to resolve a TypeError.
+
+## v0.2.79 (2025-07-02)
+- Fixed a JsonDecodeError in checkpointing with remote graph by correcting JSON serialization to handle trailing slashes properly.
+- Introduced a configuration flag to disable webhooks globally across all routes.
+
+## v0.2.78 (2025-07-02)
+- Added timeout retries to webhook calls to improve reliability.
+- Added HTTP request metrics, including a request count and latency histogram, for enhanced monitoring capabilities.
+
+## v0.2.77 (2025-07-02)
+- Added HTTP metrics to improve performance monitoring.
+- Changed the Redis cache delimiter to reduce conflicts with subgraph message names and updated caching behavior.
+
+## v0.2.76 (2025-07-01)
+- Updated Redis cache delimiter to prevent conflicts with subgraph messages.
+
+## v0.2.74 (2025-06-30)
+- Scheduled webhooks in an isolated loop to ensure thread-safe operations and prevent errors with PYTHONASYNCIODEBUG=1.
+
+## v0.2.73 (2025-06-27)
+- Fixed an infinite frame loop issue and removed the dict_parser due to structlog's unexpected behavior.
+- Throw a 409 error on deadlock occurrence during run cancellations to handle lock conflicts gracefully.
+
+## v0.2.72 (2025-06-27)
+- Ensured compatibility with future langgraph versions.
+- Implemented a 409 response status to handle deadlock issues during cancellation.
+
+## v0.2.71 (2025-06-26)
+- Improved logging for better clarity and detail regarding log types.
+
+## v0.2.70 (2025-06-26)
+- Improved error handling to better distinguish and log TimeoutErrors caused by users from internal run timeouts.
+
+## v0.2.69 (2025-06-26)
+- Added sorting and pagination to the crons API and updated schema definitions for improved accuracy.
+
+## v0.2.66 (2025-06-26)
+- Fixed a 404 error when creating multiple runs with the same thread_id using `on_not_exist="create"`.
+
+## v0.2.65 (2025-06-25)
+- Ensured that only fields from `assistant_versions` are returned when necessary.
+- Ensured consistent data types for in-memory and PostgreSQL users, improving internal authentication handling.
+
+## v0.2.64 (2025-06-24)
+- Added descriptions to version entries for better clarity.
+
+## v0.2.62 (2025-06-23)
+- Improved user handling for custom authentication in the JS Studio.
+- Added Prometheus-format run statistics to the metrics endpoint for better monitoring.
+- Added run statistics in Prometheus format to the metrics endpoint.
+
+## v0.2.61 (2025-06-20)
+- Set a maximum idle time for Redis connections to prevent unnecessary open connections.
+
+## v0.2.60 (2025-06-20)
+- Enhanced error logging to include traceback details for dictionary operations.
+- Added a `/metrics` endpoint to expose queue worker metrics for monitoring.
+
+## v0.2.57 (2025-06-18)
+- Removed CancelledError from retriable exceptions to allow local interrupts while maintaining retriability for workers.
+- Introduced middleware to gracefully shut down the server after completing in-flight requests upon receiving a SIGINT.
+- Reduced metadata stored in checkpoint to only include necessary information.
+- Improved error handling in join runs to return error details when present.
+
+## v0.2.56 (2025-06-17)
+- Improved application stability by adding a handler for SIGTERM signals.
+
+## v0.2.55 (2025-06-17)
+- Improved the handling of cancellations in the queue entrypoint.
+- Improved cancellation handling in the queue entry point.
+
+## v0.2.54 (2025-06-16)
+- Enhanced error message for LuaLock timeout during license validation.
+- Fixed the $contains filter in custom auth by requiring an explicit ::text cast and updated tests accordingly.
+- Ensured project and tenant IDs are formatted as UUIDs for consistency.
+
+## v0.2.53 (2025-06-13)
+- Resolved a timing issue to ensure the queue starts only after the graph is registered.
+- Improved performance by setting thread and run status in a single query and enhanced error handling during checkpoint writes.
+- Reduced the default background grace period to 3 minutes.
+
+## v0.2.52 (2025-06-12)
+- Now logging expected graphs when one is omitted to improve traceability.
+- Implemented a time-to-live (TTL) feature for resumable streams.
+- Improved query efficiency and consistency by adding a unique index and optimizing row locking.
+
+## v0.2.51 (2025-06-12)
+- Handled `CancelledError` by marking tasks as ready to retry, improving error management in worker processes.
+- Added LG API version and request ID to metadata and logs for better tracking.
+- Added LG API version and request ID to metadata and logs to improve traceability.
+- Improved database performance by creating indexes concurrently.
+- Ensured postgres write is committed only after the Redis running marker is set to prevent race conditions.
+- Enhanced query efficiency and reliability by adding a unique index on thread_id/running, optimizing row locks, and ensuring deterministic run selection.
+- Resolved a race condition by ensuring Postgres updates only occur after the Redis running marker is set.
+
+## v0.2.46 (2025-06-07)
+- Introduced a new connection for each operation while preserving transaction characteristics in Threads state `update()` and `bulk()` commands.
+
+## v0.2.45 (2025-06-05)
+- Enhanced streaming feature by incorporating tracing contexts.
+- Removed an unnecessary query from the Crons.search function.
+- Resolved connection reuse issue when scheduling next run for multiple cron jobs.
+- Removed an unnecessary query in the Crons.search function to improve efficiency.
+- Resolved an issue with scheduling the next cron run by improving connection reuse.
+
+## v0.2.44 (2025-06-04)
+- Enhanced the worker logic to exit the pipeline before continuing when the Redis message limit is reached.
+- Introduced a ceiling for Redis message size with an option to skip messages larger than 128 MB for improved performance.
+- Ensured the pipeline always closes properly to prevent resource leaks.
+
+## v0.2.43 (2025-06-04)
+- Improved performance by omitting logs in metadata calls and ensuring output schema compliance in value streaming.
+- Ensured the connection is properly closed after use.
+- Aligned output format to strictly adhere to the specified schema.
+- Stopped sending internal logs in metadata requests to improve privacy.
+
+## v0.2.42 (2025-06-04)
+- Added timestamps to track the start and end of a request's run.
+- Added tracer information to the configuration settings.
+- Added support for streaming with tracing contexts.
+
+## v0.2.41 (2025-06-03)
+- Added locking mechanism to prevent errors in pipelined executions.

docs/docs/cloud/reference/sdk/python_sdk_ref.md

@@ -0,0 +1,17 @@
+# Python SDK Reference
+
+::: langgraph_sdk.client
+    handler: python
+
+
+::: langgraph_sdk.schema
+    handler: python
+
+::: langgraph_sdk.auth
+    handler: python
+
+::: langgraph_sdk.auth.types
+    handler: python
+
+::: langgraph_sdk.auth.exceptions
+    handler: python

docs/docs/concepts/application_structure.md

@@ -0,0 +1,170 @@
+---
+search:
+  boost: 2
+---
+
+# Application Structure
+
+## Overview
+
+A LangGraph application consists of one or more graphs, a configuration file (`langgraph.json`), a file that specifies dependencies, and an optional `.env` file that specifies environment variables.
+
+This guide shows a typical structure of an application and shows how the required information to deploy an application using the LangGraph Platform is specified.
+
+## Key Concepts
+
+To deploy using the LangGraph Platform, the following information should be provided:
+
+1. A [LangGraph configuration file](#configuration-file-concepts) (`langgraph.json`) that specifies the dependencies, graphs, and environment variables to use for the application.
+2. The [graphs](#graphs) that implement the logic of the application.
+3. A file that specifies [dependencies](#dependencies) required to run the application.
+4. [Environment variables](#environment-variables) that are required for the application to run.
+
+## File Structure
+
+Below are examples of directory structures for applications:
+
+:::python
+=== "Python (requirements.txt)"
+
+    ```plaintext
+    my-app/
+    ├── my_agent # all project code lies within here
+    │   ├── utils # utilities for your graph
+    │   │   ├── __init__.py
+    │   │   ├── tools.py # tools for your graph
+    │   │   ├── nodes.py # node functions for your graph
+    │   │   └── state.py # state definition of your graph
+    │   ├── __init__.py
+    │   └── agent.py # code for constructing your graph
+    ├── .env # environment variables
+    ├── requirements.txt # package dependencies
+    └── langgraph.json # configuration file for LangGraph
+    ```
+
+=== "Python (pyproject.toml)"
+
+    ```plaintext
+    my-app/
+    ├── my_agent # all project code lies within here
+    │   ├── utils # utilities for your graph
+    │   │   ├── __init__.py
+    │   │   ├── tools.py # tools for your graph
+    │   │   ├── nodes.py # node functions for your graph
+    │   │   └── state.py # state definition of your graph
+    │   ├── __init__.py
+    │   └── agent.py # code for constructing your graph
+    ├── .env # environment variables
+    ├── langgraph.json  # configuration file for LangGraph
+    └── pyproject.toml # dependencies for your project
+    ```
+
+:::
+
+:::js
+
+```plaintext
+my-app/
+├── src # all project code lies within here
+│   ├── utils # optional utilities for your graph
+│   │   ├── tools.ts # tools for your graph
+│   │   ├── nodes.ts # node functions for your graph
+│   │   └── state.ts # state definition of your graph
+│   └── agent.ts # code for constructing your graph
+├── package.json # package dependencies
+├── .env # environment variables
+└── langgraph.json # configuration file for LangGraph
+```
+
+:::
+
+!!! note
+
+    The directory structure of a LangGraph application can vary depending on the programming language and the package manager used.
+
+## Configuration File {#configuration-file-concepts}
+
+The `langgraph.json` file is a JSON file that specifies the dependencies, graphs, environment variables, and other settings required to deploy a LangGraph application.
+
+See the [LangGraph configuration file reference](../cloud/reference/cli.md#configuration-file) for details on all supported keys in the JSON file.
+
+!!! tip
+
+    The [LangGraph CLI](./langgraph_cli.md) defaults to using the configuration file `langgraph.json` in the current directory.
+
+### Examples
+
+:::python
+
+- The dependencies involve a custom local package and the `langchain_openai` package.
+- A single graph will be loaded from the file `./your_package/your_file.py` with the variable `variable`.
+- The environment variables are loaded from the `.env` file.
+
+```json
+{
+  "dependencies": ["langchain_openai", "./your_package"],
+  "graphs": {
+    "my_agent": "./your_package/your_file.py:agent"
+  },
+  "env": "./.env"
+}
+```
+
+:::
+
+:::js
+
+- The dependencies will be loaded from a dependency file in the local directory (e.g., `package.json`).
+- A single graph will be loaded from the file `./your_package/your_file.js` with the function `agent`.
+- The environment variable `OPENAI_API_KEY` is set inline.
+
+```json
+{
+  "dependencies": ["."],
+  "graphs": {
+    "my_agent": "./your_package/your_file.js:agent"
+  },
+  "env": {
+    "OPENAI_API_KEY": "secret-key"
+  }
+}
+```
+
+:::
+
+## Dependencies
+
+:::python
+A LangGraph application may depend on other Python packages.
+:::
+
+:::js
+A LangGraph application may depend on other TypeScript/JavaScript libraries.
+:::
+
+You will generally need to specify the following information for dependencies to be set up correctly:
+
+:::python
+
+1. A file in the directory that specifies the dependencies (e.g. `requirements.txt`, `pyproject.toml`, or `package.json`).
+   :::
+
+:::js
+
+1. A file in the directory that specifies the dependencies (e.g. `package.json`).
+   :::
+
+2. A `dependencies` key in the [LangGraph configuration file](#configuration-file-concepts) that specifies the dependencies required to run the LangGraph application.
+3. Any additional binaries or system libraries can be specified using `dockerfile_lines` key in the [LangGraph configuration file](#configuration-file-concepts).
+
+## Graphs
+
+Use the `graphs` key in the [LangGraph configuration file](#configuration-file-concepts) to specify which graphs will be available in the deployed LangGraph application.
+
+You can specify one or more graphs in the configuration file. Each graph is identified by a name (which should be unique) and a path for either: (1) the compiled graph or (2) a function that makes a graph is defined.
+
+## Environment Variables
+
+If you're working with a deployed LangGraph application locally, you can configure environment variables in the `env` key of the [LangGraph configuration file](#configuration-file-concepts).
+
+For a production deployment, you will typically want to configure the environment variables in the deployment environment.

docs/docs/concepts/assistants.md

@@ -0,0 +1,34 @@
+# Assistants
+
+**Assistants** allow you to manage configurations (like prompts, LLM selection, tools) separately from your graph's core logic, enabling rapid changes that don't alter the graph architecture. It is a way to create multiple specialized versions of the same graph architecture, each optimized for different use cases through context/configuration variations rather than structural changes.
+
+For example, imagine a general-purpose writing agent built on a common graph architecture. While the structure remains the same, different writing styles—such as blog posts and tweets—require tailored configurations to optimize performance. To support these variations, you can create multiple assistants (e.g., one for blogs and another for tweets) that share the underlying graph but differ in model selection and system prompt.
+
+![assistant versions](img/assistants.png)
+
+The LangGraph Cloud API provides several endpoints for creating and managing assistants and their versions. See the [API reference](../cloud/reference/api/api_ref.html#tag/assistants) for more details.
+
+!!! info
+
+    Assistants are a [LangGraph Platform](langgraph_platform.md) concept. They are not available in the open source LangGraph library.
+
+## Configuration
+
+:::python
+Assistants build on the LangGraph open source concepts of configuration and [runtime context](low_level.md#runtime-context).
+:::
+
+While these features are available in the open source LangGraph library, assistants are only present in [LangGraph Platform](langgraph_platform.md). This is due to the fact that assistants are tightly coupled to your deployed graph. Upon deployment, LangGraph Server will automatically create a default assistant for each graph using the graph's default context and configuration settings.
+
+In practice, an assistant is just an _instance_ of a graph with a specific configuration. Therefore, multiple assistants can reference the same graph but can contain different configurations (e.g. prompts, models, tools). The LangGraph Server API provides several endpoints for creating and managing assistants. See the [API reference](../cloud/reference/api/api_ref.html) and [this how-to](../cloud/how-tos/configuration_cloud.md) for more details on how to create assistants.
+
+## Versioning
+
+Assistants support versioning to track changes over time.
+Once you've created an assistant, subsequent edits to that assistant will create new versions. See [this how-to](../cloud/how-tos/configuration_cloud.md#create-a-new-version-for-your-assistant) for more details on how to manage assistant versions.
+
+## Execution
+
+A **run** is an invocation of an assistant. Each run may have its own input, configuration, context, and metadata, which may affect execution and output of the underlying graph. A run can optionally be executed on a [thread](./persistence.md#threads).
+
+The LangGraph Platform API provides several endpoints for creating and managing runs. See the [API reference](../cloud/reference/api/api_ref.html#tag/thread-runs/) for more details.

docs/docs/concepts/auth.md

@@ -0,0 +1,809 @@
+---
+search:
+  boost: 2
+---
+
+# Authentication & Access Control
+
+LangGraph Platform provides a flexible authentication and authorization system that can integrate with most authentication schemes.
+
+## Core Concepts
+
+### Authentication vs Authorization
+
+While often used interchangeably, these terms represent distinct security concepts:
+
+- [**Authentication**](#authentication) ("AuthN") verifies _who_ you are. This runs as middleware for every request.
+- [**Authorization**](#authorization) ("AuthZ") determines _what you can do_. This validates the user's privileges and roles on a per-resource basis.
+
+:::python
+In LangGraph Platform, authentication is handled by your [`@auth.authenticate`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.Auth.authenticate) handler, and authorization is handled by your [`@auth.on`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.Auth.on) handlers.
+:::
+
+:::js
+In LangGraph Platform, authentication is handled by your [`@auth.authenticate`](../cloud/reference/sdk/typescript_sdk_ref.md#auth.authenticate) handler, and authorization is handled by your [`@auth.on`](../cloud/reference/sdk/typescript_sdk_ref.md#auth.on) handlers.
+:::
+
+## Default Security Models
+
+LangGraph Platform provides different security defaults:
+
+### LangGraph Platform
+
+- Uses LangSmith API keys by default
+- Requires valid API key in `x-api-key` header
+- Can be customized with your auth handler
+
+!!! note "Custom auth"
+
+   Custom auth **is supported** for all plans in LangGraph Platform.
+
+### Self-Hosted
+
+- No default authentication
+- Complete flexibility to implement your security model
+- You control all aspects of authentication and authorization
+
+## System Architecture
+
+A typical authentication setup involves three main components:
+
+1. **Authentication Provider** (Identity Provider/IdP)
+
+   - A dedicated service that manages user identities and credentials
+   - Handles user registration, login, password resets, etc.
+   - Issues tokens (JWT, session tokens, etc.) after successful authentication
+   - Examples: Auth0, Supabase Auth, Okta, or your own auth server
+
+2. **LangGraph Backend** (Resource Server)
+
+   - Your LangGraph application that contains business logic and protected resources
+   - Validates tokens with the auth provider
+   - Enforces access control based on user identity and permissions
+   - Doesn't store user credentials directly
+
+3. **Client Application** (Frontend)
+
+   - Web app, mobile app, or API client
+   - Collects time-sensitive user credentials and sends to auth provider
+   - Receives tokens from auth provider
+   - Includes these tokens in requests to LangGraph backend
+
+Here's how these components typically interact:
+
+```mermaid
+sequenceDiagram
+    participant Client as Client App
+    participant Auth as Auth Provider
+    participant LG as LangGraph Backend
+
+    Client->>Auth: 1. Login (username/password)
+    Auth-->>Client: 2. Return token
+    Client->>LG: 3. Request with token
+    Note over LG: 4. Validate token (@auth.authenticate)
+    LG-->>Auth:  5. Fetch user info
+    Auth-->>LG: 6. Confirm validity
+    Note over LG: 7. Apply access control (@auth.on.*)
+    LG-->>Client: 8. Return resources
+```
+
+:::python
+Your [`@auth.authenticate`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.Auth.authenticate) handler in LangGraph handles steps 4-6, while your [`@auth.on`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.Auth.on) handlers implement step 7.
+:::
+
+:::js
+Your [`auth.authenticate`](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#authenticate) handler in LangGraph handles steps 4-6, while your [`auth.on`](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#on>) handlers implement step 7.
+:::
+
+## Authentication
+
+:::python
+Authentication in LangGraph runs as middleware on every request. Your [`@auth.authenticate`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.Auth.authenticate) handler receives request information and should:
+
+1. Validate the credentials
+2. Return [user info](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.types.MinimalUserDict) containing the user's identity and user information if valid
+3. Raise an [HTTPException](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.exceptions.HTTPException) or AssertionError if invalid
+
+```python
+from langgraph_sdk import Auth
+
+auth = Auth()
+
+@auth.authenticate
+async def authenticate(headers: dict) -> Auth.types.MinimalUserDict:
+    # Validate credentials (e.g., API key, JWT token)
+    api_key = headers.get("x-api-key")
+    if not api_key or not is_valid_key(api_key):
+        raise Auth.exceptions.HTTPException(
+            status_code=401,
+            detail="Invalid API key"
+        )
+
+    # Return user info - only identity and is_authenticated are required
+    # Add any additional fields you need for authorization
+    return {
+        "identity": "user-123",        # Required: unique user identifier
+        "is_authenticated": True,      # Optional: assumed True by default
+        "permissions": ["read", "write"] # Optional: for permission-based auth
+        # You can add more custom fields if you want to implement other auth patterns
+        "role": "admin",
+        "org_id": "org-456"
+
+    }
+```
+
+The returned user information is available:
+
+- To your authorization handlers via [`ctx.user`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.types.AuthContext)
+- In your application via `config["configuration"]["langgraph_auth_user"]`
+  :::
+
+:::js
+Authentication in LangGraph runs as middleware on every request. Your [`authenticate`](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#authenticate>) handler receives request information and should:
+
+1. Validate the credentials
+2. Return user information containing the user's identity and user information if valid
+3. Raise an [HTTPException](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#class-httpexception>) if invalid
+
+```typescript
+import { Auth, HTTPException } from "@langchain/langgraph-sdk";
+
+export const auth = new Auth();
+
+auth.authenticate(async (request) => {
+  // Validate credentials (e.g., API key, JWT token)
+  const apiKey = request.headers.get("x-api-key");
+  if (!apiKey || !isValidKey(apiKey)) {
+    throw new HTTPException(401, "Invalid API key");
+  }
+
+  // Return user info - only identity and isAuthenticated are required
+  // Add any additional fields you need for authorization
+  return {
+    identity: "user-123", // Required: unique user identifier
+    isAuthenticated: true, // Optional: assumed true by default
+    permissions: ["read", "write"], // Optional: for permission-based auth
+    // You can add more custom fields if you want to implement other auth patterns
+    role: "admin",
+    orgId: "org-456",
+  };
+});
+```
+
+The returned user information is available:
+
+- To your authorization handlers via the `user` property in a [callback handler](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#on)
+- In your application via `config.configurable.langgraph_auth_user`
+  :::
+
+??? tip "Supported Parameters"
+
+    :::python
+    The [`@auth.authenticate`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.Auth.authenticate) handler can accept any of the following parameters by name:
+
+    * request (Request): The raw ASGI request object
+    * body (dict): The parsed request body
+    * path (str): The request path, e.g., "/threads/abcd-1234-abcd-1234/runs/abcd-1234-abcd-1234/stream"
+    * method (str): The HTTP method, e.g., "GET"
+    * path_params (dict[str, str]): URL path parameters, e.g., {"thread_id": "abcd-1234-abcd-1234", "run_id": "abcd-1234-abcd-1234"}
+    * query_params (dict[str, str]): URL query parameters, e.g., {"stream": "true"}
+    * headers (dict[bytes, bytes]): Request headers
+    * authorization (str | None): The Authorization header value (e.g., "Bearer <token>")
+    :::
+
+    :::js
+    The [`authenticate`](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#authenticate) handler can accept any of the following parameters:
+
+    * request (Request): The raw request object
+    * body (object): The parsed request body
+    * path (string): The request path, e.g., "/threads/abcd-1234-abcd-1234/runs/abcd-1234-abcd-1234/stream"
+    * method (string): The HTTP method, e.g., "GET"
+    * pathParams (Record<string, string>): URL path parameters, e.g., {"threadId": "abcd-1234-abcd-1234", "runId": "abcd-1234-abcd-1234"}
+    * queryParams (Record<string, string>): URL query parameters, e.g., {"stream": "true"}
+    * headers (Record<string, string>): Request headers
+    * authorization (string | null): The Authorization header value (e.g., "Bearer <token>")
+    :::
+
+    In many of our tutorials, we will just show the "authorization" parameter to be concise, but you can opt to accept more information as needed
+    to implement your custom authentication scheme.
+
+### Agent authentication
+
+Custom authentication permits delegated access. The values you return in `@auth.authenticate` are added to the run context, giving agents user-scoped credentials lets them access resources on the user’s behalf.
+
+```mermaid
+sequenceDiagram
+  %% Actors
+  participant ClientApp as Client
+  participant AuthProv  as Auth Provider
+  participant LangGraph as LangGraph Backend
+  participant SecretStore as Secret Store
+  participant ExternalService as External Service
+
+  %% 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.*)
+
+  %% External Service round-trip
+  LangGraph  ->> ExternalService: 8. Call external service (with header)
+  Note over ExternalService: 9. External service validates header and executes action
+  ExternalService  -->> LangGraph: 10. Service response
+
+  %% Return to caller
+  LangGraph  -->> ClientApp: 11. Return resources
+```
+
+After authentication, the platform creates a special configuration object that is passed to your graph and all nodes via the configurable context.
+This object contains information about the current user, including any custom fields you return from your [`@auth.authenticate`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.Auth.authenticate) handler.
+
+To enable an agent to act on behalf of the user, use [custom authentication middleware](../how-tos/auth/custom_auth.md). This will allow the agent to interact with external systems like MCP servers, external databases, and even other agents on behalf of the user.
+
+For more information, see the [Use custom auth](../how-tos/auth/custom_auth.md#enable-agent-authentication) guide.
+
+### Agent authentication with MCP
+
+For information on how to authenticate an agent to an MCP server, see the [MCP conceptual guide](../concepts/mcp.md).
+
+## Authorization
+
+After authentication, LangGraph calls your authorization handlers to control access to specific resources (e.g., threads, assistants, crons). These handlers can:
+
+1. Add metadata to be saved during resource creation by mutating the metadata. See the [supported actions table](#supported-actions) for the list of types the value can take for each action.
+2. Filter resources by metadata during search/list or read operations by returning a [filter](#filter-operations).
+3. Raise an HTTP exception if access is denied.
+
+If you want to just implement simple user-scoped access control, you can use a single authorization handler for all resources and actions. If you want to have different control depending on the resource and action, you can use [resource-specific handlers](#resource-specific-handlers). See the [Supported Resources](#supported-resources) section for a full list of the resources that support access control.
+
+:::python
+Your [`@auth.on`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.Auth.on) handlers control access by mutating the `value["metadata"]` dictionary directly and returning a [filter dictionary](#filter-operations).
+
+```python
+@auth.on
+async def add_owner(
+    ctx: Auth.types.AuthContext,
+    value: dict  # The payload being sent to this access method
+) -> dict:  # Returns a filter dict that restricts access to resources
+    """Authorize all access to threads, runs, crons, and assistants.
+
+    This handler does two things:
+        - Adds a value to resource metadata (to persist with the resource so it can be filtered later)
+        - Returns a filter (to restrict access to existing resources)
+
+    Args:
+        ctx: Authentication context containing user info, permissions, the path, and
+        value: The request payload sent to the endpoint. For creation
+              operations, this contains the resource parameters. For read
+              operations, this contains the resource being accessed.
+
+    Returns:
+        A filter dictionary that LangGraph uses to restrict access to resources.
+        See [Filter Operations](#filter-operations) for supported operators.
+    """
+    # Create filter to restrict access to just this user's resources
+    filters = {"owner": ctx.user.identity}
+
+    # Get or create the metadata dictionary in the payload
+    # This is where we store persistent info about the resource
+    metadata = value.setdefault("metadata", {})
+
+    # Add owner to metadata - if this is a create or update operation,
+    # this information will be saved with the resource
+    # So we can filter by it later in read operations
+    metadata.update(filters)
+
+    # Return filters to restrict access
+    # These filters are applied to ALL operations (create, read, update, search, etc.)
+    # to ensure users can only access their own resources
+    return filters
+```
+
+:::
+
+:::js
+You can granularly control access by mutating the `value.metadata` object directly and returning a [filter object](#filter-operations) when registering an [`on()`](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#on) handler.
+
+```typescript
+import { Auth, HTTPException } from "@langchain/langgraph-sdk/auth";
+
+export const auth = new Auth()
+  .authenticate(async (request: Request) => ({
+    identity: "user-123",
+    permissions: [],
+  }))
+  .on("*", ({ value, user }) => {
+    // Create filter to restrict access to just this user's resources
+    const filters = { owner: user.identity };
+
+    // If the operation supports metadata, add the user identity
+    // as metadata to the resource.
+    if ("metadata" in value) {
+      value.metadata ??= {};
+      value.metadata.owner = user.identity;
+    }
+
+    // Return filters to restrict access
+    // These filters are applied to ALL operations (create, read, update, search, etc.)
+    // to ensure users can only access their own resources
+    return filters;
+  });
+```
+
+:::
+
+### Resource-Specific Handlers {#resource-specific-handlers}
+
+You can register handlers for specific resources and actions by chaining the resource and action names together with the authorization decorator.
+When a request is made, the most specific handler that matches that resource and action is called. Below is an example of how to register handlers for specific resources and actions. For the following setup:
+
+1. Authenticated users are able to create threads, read threads, and create runs on threads
+2. Only users with the "assistants:create" permission are allowed to create new assistants
+3. All other endpoints (e.g., e.g., delete assistant, crons, store) are disabled for all users.
+
+!!! tip "Supported Handlers"
+
+    For a full list of supported resources and actions, see the [Supported Resources](#supported-resources) section below.
+
+:::python
+
+```python
+# Generic / global handler catches calls that aren't handled by more specific handlers
+@auth.on
+async def reject_unhandled_requests(ctx: Auth.types.AuthContext, value: Any) -> False:
+    print(f"Request to {ctx.path} by {ctx.user.identity}")
+    raise Auth.exceptions.HTTPException(
+        status_code=403,
+        detail="Forbidden"
+    )
+
+# Matches the "thread" resource and all actions - create, read, update, delete, search
+# Since this is **more specific** than the generic @auth.on handler, it will take precedence
+# over the generic handler for all actions on the "threads" resource
+@auth.on.threads
+async def on_thread_create(
+    ctx: Auth.types.AuthContext,
+    value: Auth.types.threads.create.value
+):
+    if "write" not in ctx.permissions:
+        raise Auth.exceptions.HTTPException(
+            status_code=403,
+            detail="User lacks the required permissions."
+        )
+    # Setting metadata on the thread being created
+    # will ensure that the resource contains an "owner" field
+    # Then any time a user tries to access this thread or runs within the thread,
+    # we can filter by owner
+    metadata = value.setdefault("metadata", {})
+    metadata["owner"] = ctx.user.identity
+    return {"owner": ctx.user.identity}
+
+# Thread creation. This will match only on thread create actions
+# Since this is **more specific** than both the generic @auth.on handler and the @auth.on.threads handler,
+# it will take precedence for any "create" actions on the "threads" resources
+@auth.on.threads.create
+async def on_thread_create(
+    ctx: Auth.types.AuthContext,
+    value: Auth.types.threads.create.value
+):
+    # Setting metadata on the thread being created
+    # will ensure that the resource contains an "owner" field
+    # Then any time a user tries to access this thread or runs within the thread,
+    # we can filter by owner
+    metadata = value.setdefault("metadata", {})
+    metadata["owner"] = ctx.user.identity
+    return {"owner": ctx.user.identity}
+
+# Reading a thread. Since this is also more specific than the generic @auth.on handler, and the @auth.on.threads handler,
+# it will take precedence for any "read" actions on the "threads" resource
+@auth.on.threads.read
+async def on_thread_read(
+    ctx: Auth.types.AuthContext,
+    value: Auth.types.threads.read.value
+):
+    # Since we are reading (and not creating) a thread,
+    # we don't need to set metadata. We just need to
+    # return a filter to ensure users can only see their own threads
+    return {"owner": ctx.user.identity}
+
+# Run creation, streaming, updates, etc.
+# This takes precedenceover the generic @auth.on handler and the @auth.on.threads handler
+@auth.on.threads.create_run
+async def on_run_create(
+    ctx: Auth.types.AuthContext,
+    value: Auth.types.threads.create_run.value
+):
+    metadata = value.setdefault("metadata", {})
+    metadata["owner"] = ctx.user.identity
+    # Inherit thread's access control
+    return {"owner": ctx.user.identity}
+
+# Assistant creation
+@auth.on.assistants.create
+async def on_assistant_create(
+    ctx: Auth.types.AuthContext,
+    value: Auth.types.assistants.create.value
+):
+    if "assistants:create" not in ctx.permissions:
+        raise Auth.exceptions.HTTPException(
+            status_code=403,
+            detail="User lacks the required permissions."
+        )
+```
+
+:::
+
+:::js
+
+```typescript
+import { Auth, HTTPException } from "@langchain/langgraph-sdk/auth";
+
+export const auth = new Auth()
+  .authenticate(async (request: Request) => ({
+    identity: "user-123",
+    permissions: ["threads:write", "threads:read"],
+  }))
+  .on("*", ({ event, user }) => {
+    console.log(`Request for ${event} by ${user.identity}`);
+    throw new HTTPException(403, { message: "Forbidden" });
+  })
+
+  // Matches the "threads" resource and all actions - create, read, update, delete, search
+  // Since this is **more specific** than the generic `on("*")` handler, it will take precedence over the generic handler for all actions on the "threads" resource
+  .on("threads", ({ permissions, value, user }) => {
+    if (!permissions.includes("write")) {
+      throw new HTTPException(403, {
+        message: "User lacks the required permissions.",
+      });
+    }
+
+    // Not all events do include `metadata` property in `value`.
+    // So we need to add this type guard.
+    if ("metadata" in value) {
+      value.metadata ??= {};
+      value.metadata.owner = user.identity;
+    }
+
+    return { owner: user.identity };
+  })
+
+  // Thread creation. This will match only on thread create actions.
+  // Since this is **more specific** than both the generic `on("*")` handler and the `on("threads")` handler, it will take precedence for any "create" actions on the "threads" resources
+  .on("threads:create", ({ value, user, permissions }) => {
+    if (!permissions.includes("write")) {
+      throw new HTTPException(403, {
+        message: "User lacks the required permissions.",
+      });
+    }
+
+    // Setting metadata on the thread being created will ensure that the resource contains an "owner" field
+    // Then any time a user tries to access this thread or runs within the thread,
+    // we can filter by owner
+    value.metadata ??= {};
+    value.metadata.owner = user.identity;
+
+    return { owner: user.identity };
+  })
+
+  // Reading a thread. Since this is also more specific than the generic `on("*")` handler, and the `on("threads")` handler,
+  .on("threads:read", ({ user }) => {
+    // Since we are reading (and not creating) a thread,
+    // we don't need to set metadata. We just need to
+    // return a filter to ensure users can only see their own threads.
+    return { owner: user.identity };
+  })
+
+  // Run creation, streaming, updates, etc.
+  // This takes precedence over the generic `on("*")` handler and the `on("threads")` handler
+  .on("threads:create_run", ({ value, user }) => {
+    value.metadata ??= {};
+    value.metadata.owner = user.identity;
+
+    return { owner: user.identity };
+  })
+
+  // Assistant creation. This will match only on assistant create actions.
+  // Since this is **more specific** than both the generic `on("*")` handler and the `on("assistants")` handler, it will take precedence for any "create" actions on the "assistants" resources
+  .on("assistants:create", ({ value, user, permissions }) => {
+    if (!permissions.includes("assistants:create")) {
+      throw new HTTPException(403, {
+        message: "User lacks the required permissions.",
+      });
+    }
+
+    // Setting metadata on the assistant being created will ensure that the resource contains an "owner" field.
+    // Then any time a user tries to access this assistant, we can filter by owner
+    value.metadata ??= {};
+    value.metadata.owner = user.identity;
+
+    return { owner: user.identity };
+  });
+```
+
+:::
+
+Notice that we are mixing global and resource-specific handlers in the above example. Since each request is handled by the most specific handler, a request to create a `thread` would match the `on_thread_create` handler but NOT the `reject_unhandled_requests` handler. A request to `update` a thread, however would be handled by the global handler, since we don't have a more specific handler for that resource and action.
+
+### Filter Operations {#filter-operations}
+
+:::python
+Authorization handlers can return different types of values:
+
+- `None` and `True` mean "authorize access to all underling resources"
+- `False` means "deny access to all underling resources (raises a 403 exception)"
+- A metadata filter dictionary will restrict access to resources
+
+A filter dictionary is a dictionary with keys that match the resource metadata. It supports three operators:
+
+- The default value is a shorthand for exact match, or "$eq", below. For example, `{"owner": user_id}` will include only resources with metadata containing `{"owner": user_id}`
+- `$eq`: Exact match (e.g., `{"owner": {"$eq": user_id}}`) - this is equivalent to the shorthand above, `{"owner": user_id}`
+- `$contains`: List membership (e.g., `{"allowed_users": {"$contains": user_id}}`) The value here must be an element of the list. The metadata in the stored resource must be a list/container type.
+
+A dictionary with multiple keys is treated using a logical `AND` filter. For example, `{"owner": org_id, "allowed_users": {"$contains": user_id}}` will only match resources with metadata whose "owner" is `org_id` and whose "allowed_users" list contains `user_id`.
+See the reference [here](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.types.FilterType) for more information.
+:::
+
+:::js
+Authorization handlers can return different types of values:
+
+- `null` and `true` mean "authorize access to all underling resources"
+- `false` means "deny access to all underling resources (raises a 403 exception)"
+- A metadata filter object will restrict access to resources
+
+A filter object is an object with keys that match the resource metadata. It supports three operators:
+
+- The default value is a shorthand for exact match, or "$eq", below. For example, `{ owner: userId}` will include only resources with metadata containing `{ owner: userId }`
+- `$eq`: Exact match (e.g., `{ owner: { $eq: userId } }`) - this is equivalent to the shorthand above, `{ owner: userId }`
+- `$contains`: List membership (e.g., `{ allowedUsers: { $contains: userId} }`) The value here must be an element of the list. The metadata in the stored resource must be a list/container type.
+
+An object with multiple keys is treated using a logical `AND` filter. For example, `{ owner: orgId, allowedUsers: { $contains: userId} }` will only match resources with metadata whose "owner" is `orgId` and whose "allowedUsers" list contains `userId`.
+See the reference [here](../cloud/reference/sdk/typescript_sdk_ref.md#auth.types.FilterType) for more information.
+:::
+
+## Common Access Patterns
+
+Here are some typical authorization patterns:
+
+### Single-Owner Resources
+
+This common pattern lets you scope all threads, assistants, crons, and runs to a single user. It's useful for common single-user use cases like regular chatbot-style apps.
+
+:::python
+
+```python
+@auth.on
+async def owner_only(ctx: Auth.types.AuthContext, value: dict):
+    metadata = value.setdefault("metadata", {})
+    metadata["owner"] = ctx.user.identity
+    return {"owner": ctx.user.identity}
+```
+
+:::
+
+:::js
+
+```typescript
+export const auth = new Auth()
+  .authenticate(async (request: Request) => ({
+    identity: "user-123",
+    permissions: ["threads:write", "threads:read"],
+  }))
+  .on("*", ({ value, user }) => {
+    if ("metadata" in value) {
+      value.metadata ??= {};
+      value.metadata.owner = user.identity;
+    }
+    return { owner: user.identity };
+  });
+```
+
+:::
+
+### Permission-based Access
+
+This pattern lets you control access based on **permissions**. It's useful if you want certain roles to have broader or more restricted access to resources.
+
+:::python
+
+```python
+# In your auth handler:
+@auth.authenticate
+async def authenticate(headers: dict) -> Auth.types.MinimalUserDict:
+    ...
+    return {
+        "identity": "user-123",
+        "is_authenticated": True,
+        "permissions": ["threads:write", "threads:read"]  # Define permissions in auth
+    }
+
+def _default(ctx: Auth.types.AuthContext, value: dict):
+    metadata = value.setdefault("metadata", {})
+    metadata["owner"] = ctx.user.identity
+    return {"owner": ctx.user.identity}
+
+@auth.on.threads.create
+async def create_thread(ctx: Auth.types.AuthContext, value: dict):
+    if "threads:write" not in ctx.permissions:
+        raise Auth.exceptions.HTTPException(
+            status_code=403,
+            detail="Unauthorized"
+        )
+    return _default(ctx, value)
+
+
+@auth.on.threads.read
+async def rbac_create(ctx: Auth.types.AuthContext, value: dict):
+    if "threads:read" not in ctx.permissions and "threads:write" not in ctx.permissions:
+        raise Auth.exceptions.HTTPException(
+            status_code=403,
+            detail="Unauthorized"
+        )
+    return _default(ctx, value)
+```
+
+:::
+
+:::js
+
+```typescript
+import { Auth, HTTPException } from "@langchain/langgraph-sdk/auth";
+
+export const auth = new Auth()
+  .authenticate(async (request: Request) => ({
+    identity: "user-123",
+    // Define permissions in auth
+    permissions: ["threads:write", "threads:read"],
+  }))
+  .on("threads:create", ({ value, user, permissions }) => {
+    if (!permissions.includes("threads:write")) {
+      throw new HTTPException(403, { message: "Unauthorized" });
+    }
+
+    if ("metadata" in value) {
+      value.metadata ??= {};
+      value.metadata.owner = user.identity;
+    }
+    return { owner: user.identity };
+  })
+  .on("threads:read", ({ user, permissions }) => {
+    if (
+      !permissions.includes("threads:read") &&
+      !permissions.includes("threads:write")
+    ) {
+      throw new HTTPException(403, { message: "Unauthorized" });
+    }
+
+    return { owner: user.identity };
+  });
+```
+
+:::
+
+## Supported Resources
+
+LangGraph provides three levels of authorization handlers, from most general to most specific:
+
+:::python
+
+1. **Global Handler** (`@auth.on`): Matches all resources and actions
+2. **Resource Handler** (e.g., `@auth.on.threads`, `@auth.on.assistants`, `@auth.on.crons`): Matches all actions for a specific resource
+3. **Action Handler** (e.g., `@auth.on.threads.create`, `@auth.on.threads.read`): Matches a specific action on a specific resource
+
+The most specific matching handler will be used. For example, `@auth.on.threads.create` takes precedence over `@auth.on.threads` for thread creation.
+If a more specific handler is registered, the more general handler will not be called for that resource and action.
+:::
+
+:::js
+
+1. **Global Handler** (`on("*")`): Matches all resources and actions
+2. **Resource Handler** (e.g., `on("threads")`, `on("assistants")`, `on("crons")`): Matches all actions for a specific resource
+3. **Action Handler** (e.g., `on("threads:create")`, `on("threads:read")`): Matches a specific action on a specific resource
+
+The most specific matching handler will be used. For example, `on("threads:create")` takes precedence over `on("threads")` for thread creation.
+If a more specific handler is registered, the more general handler will not be called for that resource and action.
+:::
+
+:::python
+???+ tip "Type Safety"
+Each handler has type hints available for its `value` parameter. For example:
+
+    ```python
+    @auth.on.threads.create
+    async def on_thread_create(
+        ctx: Auth.types.AuthContext,
+        value: Auth.types.on.threads.create.value  # Specific type for thread creation
+    ):
+        ...
+
+    @auth.on.threads
+    async def on_threads(
+        ctx: Auth.types.AuthContext,
+        value: Auth.types.on.threads.value  # Union type of all thread actions
+    ):
+        ...
+
+    @auth.on
+    async def on_all(
+        ctx: Auth.types.AuthContext,
+        value: dict  # Union type of all possible actions
+    ):
+        ...
+    ```
+
+    More specific handlers provide better type hints since they handle fewer action types.
+
+:::
+
+#### Supported actions and types {#supported-actions}
+
+Here are all the supported action handlers:
+
+:::python
+| Resource | Handler | Description | Value Type |
+|----------|---------|-------------|------------|
+| **Threads** | `@auth.on.threads.create` | Thread creation | [`ThreadsCreate`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.types.ThreadsCreate) |
+| | `@auth.on.threads.read` | Thread retrieval | [`ThreadsRead`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.types.ThreadsRead) |
+| | `@auth.on.threads.update` | Thread updates | [`ThreadsUpdate`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.types.ThreadsUpdate) |
+| | `@auth.on.threads.delete` | Thread deletion | [`ThreadsDelete`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.types.ThreadsDelete) |
+| | `@auth.on.threads.search` | Listing threads | [`ThreadsSearch`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.types.ThreadsSearch) |
+| | `@auth.on.threads.create_run` | Creating or updating a run | [`RunsCreate`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.types.RunsCreate) |
+| **Assistants** | `@auth.on.assistants.create` | Assistant creation | [`AssistantsCreate`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.types.AssistantsCreate) |
+| | `@auth.on.assistants.read` | Assistant retrieval | [`AssistantsRead`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.types.AssistantsRead) |
+| | `@auth.on.assistants.update` | Assistant updates | [`AssistantsUpdate`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.types.AssistantsUpdate) |
+| | `@auth.on.assistants.delete` | Assistant deletion | [`AssistantsDelete`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.types.AssistantsDelete) |
+| | `@auth.on.assistants.search` | Listing assistants | [`AssistantsSearch`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.types.AssistantsSearch) |
+| **Crons** | `@auth.on.crons.create` | Cron job creation | [`CronsCreate`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.types.CronsCreate) |
+| | `@auth.on.crons.read` | Cron job retrieval | [`CronsRead`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.types.CronsRead) |
+| | `@auth.on.crons.update` | Cron job updates | [`CronsUpdate`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.types.CronsUpdate) |
+| | `@auth.on.crons.delete` | Cron job deletion | [`CronsDelete`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.types.CronsDelete) |
+| | `@auth.on.crons.search` | Listing cron jobs | [`CronsSearch`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.types.CronsSearch) |
+:::
+
+:::js
+| Resource | Event | Description | Value Type |
+| -------------- | -------------------- | -------------------------- | ------------------------------------------------------------------------------------------------------------------ |
+| **Threads** | `threads:create` | Thread creation | [`ThreadsCreate`](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#threadscreate) |
+| | `threads:read` | Thread retrieval | [`ThreadsRead`](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#threadsread) |
+| | `threads:update` | Thread updates | [`ThreadsUpdate`](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#threadsupdate) |
+| | `threads:delete` | Thread deletion | [`ThreadsDelete`](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#threadsdelete) |
+| | `threads:search` | Listing threads | [`ThreadsSearch`](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#threadssearch) |
+| | `threads:create_run` | Creating or updating a run | [`RunsCreate`](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#threadscreate_run) |
+| **Assistants** | `assistants:create` | Assistant creation | [`AssistantsCreate`](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#assistantscreate) |
+| | `assistants:read` | Assistant retrieval | [`AssistantsRead`](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#assistantsread) |
+| | `assistants:update` | Assistant updates | [`AssistantsUpdate`](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#assistantsupdate) |
+| | `assistants:delete` | Assistant deletion | [`AssistantsDelete`](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#assistantsdelete) |
+| | `assistants:search` | Listing assistants | [`AssistantsSearch`](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#assistantssearch) |
+| **Crons** | `crons:create` | Cron job creation | [`CronsCreate`](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#cronscreate) |
+| | `crons:read` | Cron job retrieval | [`CronsRead`](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#cronsread) |
+| | `crons:update` | Cron job updates | [`CronsUpdate`](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#cronsupdate) |
+| | `crons:delete` | Cron job deletion | [`CronsDelete`](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#cronsdelete) |
+| | `crons:search` | Listing cron jobs | [`CronsSearch`](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#cronssearch) |
+:::
+
+???+ note "About Runs"
+
+    Runs are scoped to their parent thread for access control. This means permissions are typically inherited from the thread, reflecting the conversational nature of the data model. All run operations (reading, listing) except creation are controlled by the thread's handlers.
+
+    :::python
+    There is a specific `create_run` handler for creating new runs because it had more arguments that you can view in the handler.
+    :::
+
+    :::js
+    There is a specific `threads:create_run` handler for creating new runs because it had more arguments that you can view in the handler.
+    :::
+
+## Next Steps
+
+For implementation details:
+
+- Check out the introductory tutorial on [setting up authentication](../tutorials/auth/getting_started.md)
+- See the how-to guide on implementing a [custom auth handlers](../how-tos/auth/custom_auth.md)

docs/docs/concepts/deployment_options.md

@@ -0,0 +1,94 @@
+---
+search:
+  boost: 2
+---
+
+# Deployment Options
+
+## Free deployment
+
+[Local](../tutorials/langgraph-platform/local-server.md): Deploy for local testing and development.
+
+## Production deployment
+
+There are 4 main options for deploying with the [LangGraph Platform](langgraph_platform.md):
+
+1. [Cloud SaaS](#cloud-saas)
+
+1. [Self-Hosted Data Plane](#self-hosted-data-plane)
+
+1. [Self-Hosted Control Plane](#self-hosted-control-plane)
+
+1. [Standalone Container](#standalone-container)
+
+
+A quick comparison:
+
+|                      | **Cloud SaaS** | **Self-Hosted Data Plane** | **Self-Hosted Control Plane** | **Standalone Container** |
+|----------------------|----------------|----------------------------|-------------------------------|--------------------------|
+| **[Control plane UI/API](../concepts/langgraph_control_plane.md)** | Yes | Yes | Yes | No |
+| **CI/CD** | Managed internally by platform | Managed externally by you | Managed externally by you | Managed externally by you |
+| **Data/compute residency** | LangChain's cloud | Your cloud | Your cloud | Your cloud |
+| **LangSmith compatibility** | Trace to LangSmith SaaS | Trace to LangSmith SaaS | Trace to Self-Hosted LangSmith | Optional tracing |
+| **[Pricing](https://www.langchain.com/pricing-langgraph-platform)** | Plus | Enterprise | Enterprise | Enterprise |
+
+## Cloud SaaS
+
+The [Cloud SaaS](./langgraph_cloud.md) deployment option is a fully managed model for deployment where we manage the [control plane](./langgraph_control_plane.md) and [data plane](./langgraph_data_plane.md) in our cloud. This option provides a simple way to deploy and manage your LangGraph Servers.
+
+Connect your GitHub repositories to the platform and deploy your LangGraph Servers from the [control plane UI](./langgraph_control_plane.md#control-plane-ui). The build process (i.e. CI/CD) is managed internally by the platform.
+
+For more information, please see:
+
+* [Cloud SaaS Conceptual Guide](./langgraph_cloud.md)
+* [How to deploy to Cloud SaaS](../cloud/deployment/cloud.md)
+
+## Self-Hosted Data Plane
+
+!!! info "Important"
+    The Self-Hosted Data Plane deployment option requires an [Enterprise](../concepts/plans.md) plan.
+
+The [Self-Hosted Data Plane](./langgraph_self_hosted_data_plane.md) deployment option is a "hybrid" model for deployment where we manage the [control plane](./langgraph_control_plane.md) in our cloud and you manage the [data plane](./langgraph_data_plane.md) in your cloud. This option provides a way to securely manage your data plane infrastructure, while offloading control plane management to us.
+
+Build a Docker image using the [LangGraph CLI](./langgraph_cli.md) and deploy your LangGraph Server from the [control plane UI](./langgraph_control_plane.md#control-plane-ui).
+
+Supported Compute Platforms: [Kubernetes](https://kubernetes.io/), [Amazon ECS](https://aws.amazon.com/ecs/) (coming soon!)
+
+For more information, please see:
+
+* [Self-Hosted Data Plane Conceptual Guide](./langgraph_self_hosted_data_plane.md)
+* [How to deploy the Self-Hosted Data Plane](../cloud/deployment/self_hosted_data_plane.md)
+
+## Self-Hosted Control Plane
+
+!!! info "Important"
+    The Self-Hosted Control Plane deployment option requires an [Enterprise](../concepts/plans.md) plan.
+
+The [Self-Hosted Control Plane](./langgraph_self_hosted_control_plane.md) deployment option is a fully self-hosted model for deployment where you manage the [control plane](./langgraph_control_plane.md) and [data plane](./langgraph_data_plane.md) in your cloud. This option gives you full control and responsibility of the control plane and data plane infrastructure.
+
+Build a Docker image using the [LangGraph CLI](./langgraph_cli.md) and deploy your LangGraph Server from the [control plane UI](./langgraph_control_plane.md#control-plane-ui).
+
+Supported Compute Platforms: [Kubernetes](https://kubernetes.io/)
+
+For more information, please see:
+
+* [Self-Hosted Control Plane Conceptual Guide](./langgraph_self_hosted_control_plane.md)
+* [How to deploy the Self-Hosted Control Plane](../cloud/deployment/self_hosted_control_plane.md)
+
+## Standalone Container
+
+The [Standalone Container](./langgraph_standalone_container.md) deployment option is the least restrictive model for deployment. Deploy standalone instances of a LangGraph Server in your cloud, using any of the [available](./plans.md) license options.
+
+Build a Docker image using the [LangGraph CLI](./langgraph_cli.md) and deploy your LangGraph Server using the container deployment tooling of your choice. Images can be deployed to any compute platform.
+
+For more information, please see:
+
+* [Standalone Container Conceptual Guide](./langgraph_standalone_container.md)
+* [How to deploy a Standalone Container](../cloud/deployment/standalone_container.md)
+
+## Related
+
+For more information, please see:
+
+* [LangGraph Platform plans](./plans.md)
+* [LangGraph Platform pricing](https://www.langchain.com/langgraph-platform-pricing)

docs/docs/concepts/durable_execution.md

@@ -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.