Merge branch 'main' into update-openapi-spec-v0.5.25

**Description:** Updating `sdk-py` version for release.

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -1,21 +1,21 @@
 name: "\U0001F41B Bug Report"
 description: Report a bug in LangGraph. To report a security issue, please instead use the security option below. For questions, please use the LangChain Forum at forum.langchain.com.
-labels: [pending,bug]
+labels: [pending, bug]
 body:
   - type: markdown
     attributes:
       value: |
         Thank you for taking the time to file a bug report. 
-        
+
         Use this to report BUGS in LangGraph. For usage questions, feature requests and general design questions, please use the [LangChain Forum](https://forum.langchain.com/).
-        
+
         Relevant links to check before filing a bug report to see if your issue has already been reported, fixed or
         if there's another way to solve your problem:
-        
+
         * [LangChain Forum](https://forum.langchain.com/),
         * [LangGraph Github Issues](https://github.com/langchain-ai/langgraph/issues),
         * [LangGraph how-to guides](https://langchain-ai.github.io/langgraph/how-tos/).
-        * [LangChain documentation with the integrated search](https://python.langchain.com/docs/get_started/introduction),
+        * [LangChain documentation with the integrated search](https://docs.langchain.com/),
         * [GitHub search](https://github.com/langchain-ai/langgraph),
   - type: checkboxes
     id: checks

.github/ISSUE_TEMPLATE/config.yml

@@ -1,6 +1,9 @@
 blank_issues_enabled: false
 version: 2.1
 contact_links:
+  - name: Documentation
+    url: https://github.com/langchain-ai/docs/issues/new?template=langgraph.yml
+    about: Report an issue related to the LangGraph documentation
   - name: LangChain Forum
     url:  https://forum.langchain.com/
-    about: General community discussions, support, and feature requests
+    about: General community discussions and support

.github/ISSUE_TEMPLATE/documentation.yml

@@ -1,19 +0,0 @@
-name: Documentation
-description: Report an issue related to the LangGraph documentation.
-title: "DOC: <Please write a comprehensive title after the 'DOC: ' prefix>"
-labels: [documentation]
-
-body:
-- type: textarea
-  attributes: 
-    label: "Issue with current documentation:"
-    description: >
-      Please make sure to leave a reference to the document/code you're
-      referring to.
-
-- type: textarea
-  attributes:
-    label: "Idea or request for content:"
-    description: >
-      Please describe as clearly as possible what topics you think are missing
-      from the current documentation.

.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

@@ -1,108 +1,164 @@
-import asyncio
-import json
-import os
+import logging
 import pathlib
 import sys
-import langgraph_cli
-import langgraph_cli.docker
-import langgraph_cli.config
+import time
+from urllib import error, request
 
+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
+
+logger = logging.getLogger(__name__)
+logging.basicConfig(level=logging.INFO)
 
 
-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."""
+    logger.info("Starting test...")
     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:
+        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"
+        logger.info(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}")
+                        logger.error(f"Unexpected status: {resp.status}")
+            except error.URLError as e:
+                logger.error(f"URLError: {e}")
+                last_err = e
+            except Exception as e:  # noqa: BLE001
+                logger.error(f"Exception: {e}")
+                last_err = e
+            time.sleep(0.5)
+        else:
+            logger.error("Timeout waiting for /ok to return 200")
+            # 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
+        logger.info("Test succeeded. Bringing down compose stack...")
+        try:
+            args_down = [*args, "down", "-v", "--remove-orphans"]
+            runner.run(
+                subp_exec(
+                    *compose_cmd,
+                    *args_down,
+                    input=stdin,
+                    verbose=verbose,
+                )
+            )
+            logger.info("Compose stack down. Finishing...")
+        except Exception:
+            logger.exception("Failed to bring down compose stack")
             pass
 
+    logger.info("Test finished")
+
 
 if __name__ == "__main__":
     import argparse
@@ -110,6 +166,12 @@ 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)
+    try:
+        test(pathlib.Path(args.config), args.port, args.tag, verbose=True)
+    except BaseException:
+        logger.exception("Test failed")
+        raise
+    
+    logger.info("Test execution finished")

.github/workflows/_integration_test.yml

@@ -13,13 +13,26 @@ jobs:
       matrix:
         python-version:
           - "3.10"
-          - "3.11"
+          - "3.14"
+        example:
+          - name: A
+            workdir: libs/cli/examples
+            tag: langgraph-test-a
+          - name: B
+            workdir: libs/cli/examples/graphs
+            tag: langgraph-test-b
+          - name: C
+            workdir: libs/cli/examples/graphs_reqs_a
+            tag: langgraph-test-c
+          - name: D
+            workdir: libs/cli/examples/graphs_reqs_b
+            tag: langgraph-test-d
     name: "CLI integration test"
     defaults:
       run:
         working-directory: libs/cli
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
       - name: Get changed files
         id: changed-files
         uses: Ana06/get-changed-files@v2.3.0
@@ -27,48 +40,79 @@ jobs:
           filter: "libs/cli/**"
       - name: Set up Python ${{ matrix.python-version }}
         if: steps.changed-files.outputs.all
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@v7
         with:
           python-version: ${{ matrix.python-version }}
           enable-cache: true
           cache-suffix: "cli-integration-test"
           ignore-nothing-to-cache: true
-      - name: Setup env
-        if: steps.changed-files.outputs.all
-        working-directory: libs/cli/examples
-        run: cat .env.example > .env
       - name: Install cli globally
         if: steps.changed-files.outputs.all
         run: pip install -e .
-      - name: Build and test service A
+      - name: Build and test service ${{ matrix.example.name }}
         if: steps.changed-files.outputs.all
-        working-directory: libs/cli/examples
+        working-directory: ${{ matrix.example.workdir }}
+        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
-          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
-        run: |
-          langgraph build -t langgraph-test-b  --base-image "langchain/langgraph-trial"
-          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
-        run: |
-          langgraph build -t langgraph-test-c  --base-image "langchain/langgraph-trial"
-          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
-        run: |
-          langgraph build -t langgraph-test-d  --base-image "langchain/langgraph-trial"
-          timeout 60 python ../../../../.github/scripts/run_langgraph_cli_test.py -t langgraph-test-d
+          # Build the image for this example
+          langgraph build -t ${{ matrix.example.tag }}
+          # Prepare environment file from local or parent example directory
+          if [ -f .env.example ]; then cp .env.example .env; elif [ -f ../.env.example ]; then cp ../.env.example .env && cp ../.env.example ../.env; fi
+          if [ -n "${{ secrets.LANGSMITH_API_KEY }}" ]; then echo "LANGSMITH_API_KEY=${{ secrets.LANGSMITH_API_KEY }}" >> .env; if [ -f ../.env ]; then echo "LANGSMITH_API_KEY=${{ secrets.LANGSMITH_API_KEY }}" >> ../.env; fi; fi
+          # Run the integration test using the built tag
+          # Compute repo root to reference the shared script robustly
+          REPO_ROOT=$(git rev-parse --show-toplevel)
+          timeout 60 python "$REPO_ROOT/.github/scripts/run_langgraph_cli_test.py" -t ${{ matrix.example.tag }}
 
       - name: Build JS service
-        if: steps.changed-files.outputs.all
+        if: ${{ steps.changed-files.outputs.all && matrix.example.name == 'A' }}
         working-directory: libs/cli/js-examples
         run: |
           langgraph build -t langgraph-test-e
+
+      - name: Build JS monorepo service
+        if: ${{ steps.changed-files.outputs.all && matrix.example.name == 'A' }}
+        working-directory: libs/cli/js-monorepo-example
+        run: |
+          langgraph build -t langgraph-test-f -c apps/agent/langgraph.json --build-command "yarn run turbo build" --install-command "yarn install"
+
+      - name: Build Python monorepo service
+        if: ${{ steps.changed-files.outputs.all && matrix.example.name == 'A' }}
+        working-directory: libs/cli/python-monorepo-example
+        run: |
+          langgraph build -t langgraph-test-g -c apps/agent/langgraph.json
+          cp apps/agent/.env.example apps/agent/.env
+          if [ -n "${{ secrets.LANGSMITH_API_KEY }}" ]; then echo "LANGSMITH_API_KEY=${{ secrets.LANGSMITH_API_KEY }}" >> apps/agent/.env; fi
+          timeout 60 python ../../../.github/scripts/run_langgraph_cli_test.py -t langgraph-test-g -c apps/agent/langgraph.json
+
+      - name: Build and test prerelease reqs service
+        if: ${{ steps.changed-files.outputs.all && matrix.example.name == 'A' }}
+        working-directory: libs/cli/examples/graph_prerelease_reqs
+        run: |
+          langgraph build -t langgraph-test-h
+          cp ../.env.example .env
+          if [ -n "${{ secrets.LANGSMITH_API_KEY }}" ]; then echo "LANGSMITH_API_KEY=${{ secrets.LANGSMITH_API_KEY }}" >> .env; fi
+          timeout 60 python ../../../../.github/scripts/run_langgraph_cli_test.py -t langgraph-test-h
+          echo "Finished starting up langgraph-test-h"
+          LANGGRAPH_VERSION=$(docker run --rm --entrypoint "" langgraph-test-h python -c "import sys; from importlib.metadata import version; v = version('langgraph'); print(v);")
+          if [ "$LANGGRAPH_VERSION" != "1.0.2" ]; then
+            echo "LANGGRAPH_VERSION != 1.0.2; $LANGGRAPH_VERSION"
+            exit 1
+          fi
+          LANGCHAIN_OPENAI_VERSION=$(docker run --rm --entrypoint "" langgraph-test-h python -c "import sys; from importlib.metadata import version; v = version('langchain-openai'); print(v);")
+          if [ "$LANGCHAIN_OPENAI_VERSION" != "1.0.1" ]; then
+            echo "LANGCHAIN_OPENAI_VERSION != 1.0.1; $LANGCHAIN_OPENAI_VERSION"
+            exit 1
+          fi
+          LANGCHAIN_ANTHROPIC_VERSION=$(docker run --rm --entrypoint "" langgraph-test-h python -c "import sys; from importlib.metadata import version; v = version('langchain-anthropic'); print(v);")
+          if [ "$LANGCHAIN_ANTHROPIC_VERSION" != "1.0.0a5" ]; then
+            echo "LANGCHAIN_ANTHROPIC_VERSION != 1.0.0a5; $LANGCHAIN_ANTHROPIC_VERSION"
+            exit 1
+          fi
+
+      - name: Build and test prerelease reqs fail service
+        if: ${{ steps.changed-files.outputs.all && matrix.example.name == 'A' }}
+        working-directory: libs/cli/examples/graph_prerelease_reqs_fail
+        run: |
+          langgraph build -t langgraph-test-i || [ $? -eq 1 ]

.github/workflows/_lint.yml

@@ -31,7 +31,7 @@ jobs:
           - "3.12"
     name: "lint #${{ matrix.python-version }}"
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
       - name: Get changed files
         id: changed-files
         uses: Ana06/get-changed-files@v2.3.0
@@ -39,7 +39,7 @@ jobs:
           filter: "${{ inputs.working-directory }}/**"
       - name: Set up Python ${{ matrix.python-version }}
         if: steps.changed-files.outputs.all
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@v7
         with:
           python-version: ${{ matrix.python-version }}
           enable-cache: true
@@ -48,7 +48,7 @@ jobs:
       - name: Install dependencies
         if: steps.changed-files.outputs.all
         working-directory: ${{ inputs.working-directory }}
-        run: uv sync --frozen --group dev
+        run: uv sync --frozen --group lint
 
       - name: Get .mypy_cache to speed up mypy
         if: steps.changed-files.outputs.all
@@ -74,7 +74,7 @@ jobs:
       - name: Install test dependencies
         if: steps.changed-files.outputs.all
         working-directory: ${{ inputs.working-directory }}
-        run: uv sync --group dev
+        run: uv sync --group lint
 
       - name: Get .mypy_cache_test to speed up mypy
         if: steps.changed-files.outputs.all

.github/workflows/_test.yml

@@ -17,17 +17,17 @@ jobs:
     strategy:
       matrix:
         python-version:
-          - "3.9"
           - "3.10"
           - "3.11"
           - "3.12"
           - "3.13"
+          - "3.14"
 
     name: "test #${{ matrix.python-version }}"
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
       - name: Set up Python ${{ matrix.python-version }}
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@v7
         with:
           python-version: ${{ matrix.python-version }}
           enable-cache: true
@@ -42,7 +42,7 @@ jobs:
       - name: Install dependencies
         shell: bash
         working-directory: ${{ inputs.working-directory }}
-        run: uv sync --frozen --group dev
+        run: uv sync --frozen --group test --no-dev
 
       - name: Run tests
         shell: bash

.github/workflows/_test_langgraph.yml

@@ -12,20 +12,20 @@ jobs:
     strategy:
       matrix:
         python-version:
-          - "3.9"
           - "3.10"
           - "3.11"
           - "3.12"
           - "3.13"
+          - "3.14"
 
     defaults:
       run:
         working-directory: libs/langgraph
     name: "test #${{ matrix.python-version }}"
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
       - name: Set up Python ${{ matrix.python-version }}
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@v7
         with:
           python-version: ${{ matrix.python-version }}
           enable-cache: true
@@ -39,7 +39,7 @@ jobs:
 
       - name: Install dependencies
         shell: bash
-        run: uv sync --frozen --group dev
+        run: uv sync --frozen --group test --no-dev
 
       - name: Run tests
         shell: bash

.github/workflows/_test_release.yml

@@ -16,7 +16,6 @@ permissions:
 
 jobs:
   build:
-    if: github.ref == 'refs/heads/main'
     runs-on: ubuntu-latest
 
     outputs:
@@ -24,10 +23,10 @@ jobs:
       version: ${{ steps.check-version.outputs.version }}
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
 
       - name: Set up Python $${ env.PYTHON_VERSION }}
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@v7
         with:
           python-version: ${{ env.PYTHON_VERSION }}
           enable-cache: true
@@ -49,7 +48,7 @@ jobs:
         working-directory: ${{ inputs.working-directory }}
 
       - name: Upload build
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v5
         with:
           name: test-dist
           path: ${{ inputs.working-directory }}/dist/
@@ -75,9 +74,9 @@ jobs:
       id-token: write
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
 
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v6
         with:
           name: test-dist
           path: ${{ inputs.working-directory }}/dist/

.github/workflows/baseline.yml

@@ -17,16 +17,16 @@ jobs:
       run:
         working-directory: libs/langgraph
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
       - run: SHA=$(git rev-parse HEAD) && echo "SHA=$SHA" >> $GITHUB_ENV
       - name: Set up Python 3.11
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@v7
         with:
           python-version: "3.11"
           enable-cache: true
           cache-suffix: "bench"
       - name: Install dependencies
-        run: uv sync --group dev
+        run: uv sync --group test
       - name: Run benchmarks
         run: OUTPUT=out/benchmark-baseline.json make -s benchmark
       - name: Save outputs

.github/workflows/bench.yml

@@ -15,20 +15,20 @@ jobs:
       run:
         working-directory: libs/langgraph
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
       - id: files
         name: Get changed files
         uses: Ana06/get-changed-files@v2.3.0
         with:
           format: json
       - name: Set up Python 3.11
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@v7
         with:
           python-version: "3.11"
           enable-cache: true
           cache-suffix: "bench"
       - name: Install dependencies
-        run: uv sync --group dev
+        run: uv sync --group test
       - name: Download baseline
         uses: actions/cache/restore@v4
         with:
@@ -57,7 +57,7 @@ jobs:
             echo EOF
           } >> "$GITHUB_OUTPUT"
       - name: Annotation
-        uses: actions/github-script@v7
+        uses: actions/github-script@v8
         with:
           script: |
             const file = JSON.parse(`${{ steps.files.outputs.added_modified_renamed }}`)[0]

.github/workflows/ci.yml

@@ -3,7 +3,8 @@ name: CI
 
 on:
   push:
-    branches: [main, v1]
+    branches:
+      - main
   pull_request:
 
 permissions:
@@ -26,7 +27,7 @@ jobs:
       python: ${{ steps.filter.outputs.python }}
       deps: ${{ steps.filter.outputs.deps }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
       - uses: dorny/paths-filter@v3
         id: filter
         with:
@@ -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
@@ -98,9 +100,9 @@ jobs:
     name: "Check SDK methods matching"
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: "3.11"
       - name: Run check_sdk_methods script
@@ -116,9 +118,9 @@ jobs:
         python-version:
           - "3.11"
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
       - name: Set up Python ${{ matrix.python-version }}
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@v7
         with:
           python-version: "3.11"
           enable-cache: true

.github/workflows/codespell.yml

@@ -21,7 +21,7 @@
     
         steps:
           - name: Checkout
-            uses: actions/checkout@v4
+            uses: actions/checkout@v5
     
           - name: Install Dependencies
             run: |

.github/workflows/deploy_docs.yml

@@ -1,12 +1,9 @@
-name: Deploy Docs
+name: Deploy Docs Redirects
 
 on:
   push:
     branches:
       - main
-  pull_request:
-    branches:
-      - main
   workflow_dispatch:
 
 permissions:
@@ -23,30 +20,18 @@ defaults:
     working-directory: docs
 
 jobs:
-  get-changed-files:
-    runs-on: ubuntu-latest
-    outputs:
-      changed-files: ${{ steps.changed-files.outputs.added_modified }}
-    steps:
-      - uses: actions/checkout@v4
-      - name: Get changed files
-        id: changed-files
-        uses: Ana06/get-changed-files@v2.3.0
-        with:
-          filter: "docs/docs/**"
-
   deploy:
     runs-on: ubuntu-latest
     timeout-minutes: 10 # Job will be cancelled if it runs for more than 10 minutes
     env:
       GITHUB_TOKEN: ${{ secrets.MKDOCS_GITHUB_TOKEN }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
         with:
           fetch-depth: 0
 
       - name: Set up Python
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@v7
         with:
           python-version: "3.12"
           enable-cache: true
@@ -62,85 +47,22 @@ jobs:
             uv run pip install "git+https://${GITHUB_TOKEN}@github.com/langchain-ai/mkdocs-material-insiders.git"
           fi
 
-      - name: Run unit tests
-        # Run unit tests on the docs build pipeline
-        run: make tests
-      - name: Lint Docs
-        # This step lints the docs using the existing linting set up.
-        # It should be very fast and should not require any external services.
-        run: make lint-docs
       - name: Build llms-text
         run: make llms-text
-      - name: Build site
-        run: |
-          # If this is main branch, then we want to download stats. we do this 
-          # with the env variable DOWNLOAD_STATS=true
-          if [ "${{ github.ref }}" == "refs/heads/main" ]; then
-            DOWNLOAD_STATS=true make build-docs
-          else
-            make build-docs
-          fi
+
+      - name: Build site (redirects only)
+        run: make build-docs
         env:
-          MKDOCS_GIT_COMMITTERS_APIKEY: ${{ secrets.MKDOCS_GIT_COMMITTERS_APIKEY }}
           OPENAI_API_KEY: sf-proj-1234567890 # fake placeholder, shouldn't actually be used
           ANTHROPIC_API_KEY: sk-ant-api03-1234567890 # fake placeholder, shouldn't actually be used
-      - name: Check links in notebooks
-        env:
-          LANGCHAIN_API_KEY: test
-        if: github.event_name == 'schedule'
-        run: |
-          if [ "${{ github.event_name }}" == "schedule" ]; then
-            echo "Running link check on all HTML files matching notebooks in docs directory..."
-            uv run pytest -v \
-              --check-links-ignore "https://(api|web|docs)\.smith\.langchain\.com/.*" \
-              --check-links-ignore "https://academy\.langchain\.com/.*" \
-              --check-links-ignore "https://x.com/.*" \
-              --check-links-ignore "https://twitter.com/.*" \
-              --check-links-ignore "https://github\.com/.*" \
-              --check-links-ignore "http://localhost:8123/.*" \
-              --check-links-ignore "http://localhost:2024.*" \
-              --check-links-ignore "http://127.0.0.1:.*" \
-              --check-links-ignore "/.*\.(ipynb|html)$" \
-              --check-links-ignore "https://python\.langchain\.com/.*" \
-              --check-links-ignore "https://openai\.com/.*" \
-              --check-links-ignore "https://www\.uber\.com/.*" \
-              --check-links-ignore "https://pepy\.tech/.*" \
-              --check-links-ignore "docs/docs/static/wordmark_*" \
-              --check-links $(find site -name "index.html" | grep -v 'storm/index.html')
-              
-          else
-            echo "Fetching changes from origin/main..."
-            git fetch origin main
-            echo "Checking for changed notebook files..."
-            CHANGED_FILES=$(git diff --name-only --diff-filter=d origin/main | grep 'docs/docs/.*\.ipynb$' | grep -v 'storm.ipynb' | sed -E 's|^docs/docs/|site/|; s/\.ipynb$/\/index.html/' || true)
-            echo "Changed files: ${CHANGED_FILES}"
-            if [ -n "${CHANGED_FILES}" ]; then
-              echo "Running link check on HTML files matching changed notebook files..."
-              uv run pytest -v \
-                --check-links-ignore "https://(api|web|docs)\.smith\.langchain\.com/.*" \
-                --check-links-ignore "https://academy\.langchain\.com/.*" \
-                --check-links-ignore "http://localhost:8123/.*" \
-                --check-links-ignore "http://localhost:2024.*" \
-                --check-links-ignore "http://127.0.0.1:.*" \
-                --check-links-ignore "https://x.com/.*" \
-                --check-links-ignore "https://twitter.com/.*" \
-                --check-links-ignore "https://github\.com/.*" \
-                --check-links-ignore "/.*\.(ipynb|html)$" \
-                --check-links-ignore "docs/docs/static/wordmark_*" \
-                --check-links ${CHANGED_FILES} \
-                || ([ $? = 5 ] && exit 0 || exit $?)
-            else
-              echo "No notebook files changed."
-            fi
-          fi
 
       - name: Configure GitHub Pages
         if: github.ref == 'refs/heads/main'
         uses: actions/configure-pages@v5
 
       - name: Upload Pages Artifact
-        # if: github.ref == 'refs/heads/main'
-        uses: actions/upload-pages-artifact@v3
+        if: github.ref == 'refs/heads/main'
+        uses: actions/upload-pages-artifact@v4
         with:
           path: ./docs/site/
 

.github/workflows/link_check.yml

@@ -19,7 +19,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
         with:
           fetch-depth: 0
 
@@ -36,7 +36,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
         with:
           fetch-depth: 1
 

.github/workflows/pr_lint.yml

@@ -12,7 +12,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Validate PR Title
-        uses: amannn/action-semantic-pull-request@v5
+        uses: amannn/action-semantic-pull-request@v6
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         with:
@@ -40,6 +40,7 @@ jobs:
             sdk-py
             docs
             ci
+            deps
           requireScope: false
           ignoreLabels: |
             ignore-lint-pr-title

.github/workflows/release.yml

@@ -16,7 +16,6 @@ env:
 
 jobs:
   build:
-    if: github.ref == 'refs/heads/main'
     runs-on: ubuntu-latest
 
     outputs:
@@ -26,10 +25,10 @@ jobs:
       tag: ${{ steps.check-version.outputs.tag }}
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
 
       - name: Set up Python
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@v7
         with:
           python-version: ${{ env.PYTHON_VERSION }}
           enable-cache: true
@@ -51,7 +50,7 @@ jobs:
         working-directory: ${{ inputs.working-directory }}
 
       - name: Upload build
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v5
         with:
           name: dist
           path: ${{ inputs.working-directory }}/dist/
@@ -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"
@@ -81,7 +86,7 @@ jobs:
     outputs:
       release-body: ${{ steps.generate-release-body.outputs.release-body }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
         with:
           repository: langchain-ai/langgraph
           path: langgraph
@@ -152,7 +157,7 @@ jobs:
       - test-pypi-publish
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
 
       # We explicitly *don't* set up caching here. This ensures our tests are
       # maximally sensitive to catching breakage.
@@ -168,7 +173,7 @@ jobs:
       #   used in the real world.
 
       - name: Set up Python
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@v7
         with:
           python-version: ${{ env.PYTHON_VERSION }}
           enable-cache: true
@@ -216,7 +221,7 @@ jobs:
           uv run python -c "import $IMPORT_NAME; print(dir($IMPORT_NAME))"
 
       - name: Import test dependencies
-        run: uv sync --group dev
+        run: uv sync --group test
         working-directory: ${{ inputs.working-directory }}
 
       # Overwrite the local version of the package with the test PyPI version.
@@ -255,16 +260,16 @@ jobs:
         working-directory: ${{ inputs.working-directory }}
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
 
       - name: Set up Python
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@v7
         with:
           python-version: ${{ env.PYTHON_VERSION }}
           enable-cache: true
           cache-suffix: "release"
 
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v6
         with:
           name: dist
           path: ${{ inputs.working-directory }}/dist/
@@ -296,16 +301,16 @@ jobs:
         working-directory: ${{ inputs.working-directory }}
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
 
       - name: Set up Python
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@v7
         with:
           python-version: ${{ env.PYTHON_VERSION }}
           enable-cache: true
           cache-suffix: "release"
 
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v6
         with:
           name: dist
           path: ${{ inputs.working-directory }}/dist/

.github/workflows/run_notebooks.yml

@@ -28,9 +28,9 @@ jobs:
           - "latest"
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
       - name: Set up Python + Poetry
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@v7
         with:
           python-version: "3.11"
           enable-cache: true

.github/workflows/uv_lock_ugprade.yml

@@ -16,13 +16,13 @@ jobs:
     runs-on: ubuntu-latest
     
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
       
       - name: Set up uv
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@v7
         with:
           # use minimum supported Python version
-          python-version: "3.9"
+          python-version: "3.10"
           enable-cache: true
           cache-suffix: "uv-lock-upgrade"
           
@@ -33,8 +33,8 @@ jobs:
         uses: peter-evans/create-pull-request@v7
         with:
           token: ${{ secrets.GITHUB_TOKEN }}
-          commit-message: "chore[deps]: upgrade dependencies with `uv lock --upgrade`"
-          title: "chore[deps]: upgrade dependencies with `uv lock --upgrade`"
+          commit-message: "chore(deps): upgrade dependencies with `uv lock --upgrade`"
+          title: "chore(deps): upgrade dependencies with `uv lock --upgrade`"
           body: |
             This PR updates the dependencies in all Python packages using `uv lock --upgrade`.
             

AGENTS.md

@@ -28,7 +28,7 @@ Below is a high-level overview:
 - **langgraph** – core framework for building stateful, multi-actor agents.
 - **prebuilt** – high-level APIs for creating and running agents and tools.
 - **sdk-js** – JS/TS SDK for interacting with the LangGraph REST API.
-- **sdk-py** – Python SDK for the LangGraph Platform API.
+- **sdk-py** – Python SDK for the LangGraph Server API.
 
 ### Dependency map
 

CONTRIBUTING.md

@@ -277,9 +277,9 @@ def my_function(arg1: int, arg2: str) -> float:
     Examples:
         This is a section for examples of how to use the function.
 
-        .. code-block:: python
-
-            my_function(1, "hello")
+        ```python
+        my_function(1, "hello")
+        \```
 
     Args:
         arg1: This is a description of arg1. We do not need to specify the type since

README.md

@@ -63,15 +63,15 @@ LangGraph provides low-level supporting infrastructure for *any* long-running, s
 While LangGraph can be used standalone, it also integrates seamlessly with any LangChain product, giving developers a full suite of tools for building agents. To improve your LLM application development, pair LangGraph with:
 
 - [LangSmith](http://www.langchain.com/langsmith) — Helpful for agent evals and observability. Debug poor-performing LLM app runs, evaluate agent trajectories, gain visibility in production, and improve performance over time.
-- [LangGraph Platform](https://langchain-ai.github.io/langgraph/concepts/langgraph_platform/) — Deploy and scale agents effortlessly with a purpose-built deployment platform for long running, stateful workflows. Discover, reuse, configure, and share agents across teams — and iterate quickly with visual prototyping in [LangGraph Studio](https://langchain-ai.github.io/langgraph/concepts/langgraph_studio/).
-- [LangChain](https://python.langchain.com/docs/introduction/) – Provides integrations and composable components to streamline LLM application development.
+- [LangSmith Deployment](https://langchain-ai.github.io/langgraph/concepts/langgraph_platform/) — Deploy and scale agents effortlessly with a purpose-built deployment platform for long running, stateful workflows. Discover, reuse, configure, and share agents across teams — and iterate quickly with visual prototyping in [LangGraph Studio](https://langchain-ai.github.io/langgraph/concepts/langgraph_studio/).
+- [LangChain](https://docs.langchain.com/oss/python/langchain/overview) – Provides integrations and composable components to streamline LLM application development.
 
 > [!NOTE]
 > Looking for the JS version of LangGraph? See the [JS repo](https://github.com/langchain-ai/langgraphjs) and the [JS docs](https://langchain-ai.github.io/langgraphjs/).
 
 ## Additional resources
 
-- [Guides](https://langchain-ai.github.io/langgraph/how-tos/): Quick, actionable code snippets for topics such as streaming, adding memory & persistence, and design patterns (e.g. branching, subgraphs, etc.).
+- [Guides](https://langchain-ai.github.io/langgraph/guides/): Quick, actionable code snippets for topics such as streaming, adding memory & persistence, and design patterns (e.g. branching, subgraphs, etc.).
 - [Reference](https://langchain-ai.github.io/langgraph/reference/graphs/): Detailed reference on core classes, methods, how to use the graph and checkpointing APIs, and higher-level prebuilt components.
 - [Examples](https://langchain-ai.github.io/langgraph/examples/): Guided examples on getting started with LangGraph.
 - [LangChain Forum](https://forum.langchain.com/): Connect with the community and share all of your technical questions, ideas, and feedback.
@@ -81,4 +81,4 @@ While LangGraph can be used standalone, it also integrates seamlessly with any L
 
 ## Acknowledgements
 
-LangGraph is inspired by [Pregel](https://research.google/pubs/pub37252/) and [Apache Beam](https://beam.apache.org/). The public interface draws inspiration from [NetworkX](https://networkx.org/documentation/latest/). LangGraph is built by LangChain Inc, the creators of LangChain, but can be used without LangChain.
+LangGraph is inspired by [Pregel](https://research.google/pubs/pub37252/) and [Apache Beam](https://beam.apache.org/). The public interface draws inspiration from [NetworkX](https://networkx.org/documentation/latest/). LangGraph is built by LangChain Inc, the creators of LangChain, but can be used without LangChain.

docs/Makefile

@@ -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/README.md

@@ -1,24 +1,126 @@
-# Setup
+# LangGraph Documentation
 
-To setup requirements for building docs you can run:
+For more information on contributing to our documentation, see the [Contributing Guide](../CONTRIBUTING.md).
 
-```bash
-uv sync --group test
+## Structure
+
+The primary documentation is located in the `docs/` directory. This directory contains both the source files for the main documentation as well as the API reference doc build process.
+
+### Main Documentation
+
+Main documentation files are located in `docs/docs/` and are written in Markdown format. The site uses [**MkDocs**](https://www.mkdocs.org/) with the [Material theme](https://squidfunk.github.io/mkdocs-material/) and includes:
+
+- **Concepts**: Core LangGraph concepts and explanations
+- **Tutorials**: Step-by-step learning guides
+- **How-tos**: Task-focused guides for specific use cases
+- **Examples**: Real-world applications and use cases
+- **Jupyter Notebooks**: Interactive tutorials that are automatically converted to markdown
+
+### API Reference
+
+API reference documentation is defined in `docs/docs/reference/`. Each `.md` file outlines the "template" that each page is built from. Reference content is automatically generated from docstrings in the codebase using the **mkdocstrings** plugin. Once generated, the content is plugged into the corresponding markdown file where it is referenced by using manual directives to specify which classes and/or functions are documented:
+
+```markdown
+::: langgraph.graph.state.StateGraph
+    options:
+      show_if_no_docstring: true
+      show_root_heading: true
+      show_root_full_path: false
+      members:
+        - add_node
+        - add_edge
+        - add_conditional_edges
+        - add_sequence
+        - compile
 ```
 
-## Serving documentation locally
+## Build Process
 
-To run the documentation server locally you can run:
+Docs are built following these steps:
+
+1. **Content Processing:**
+   - `_scripts/notebook_hooks.py` - Main processing pipeline that:
+     - Converts how-tos/tutorial Jupyter notebooks to markdown using `notebook_convert.py`
+     - Adds automatic API reference links to code blocks using `generate_api_reference_links.py`
+     - Handles conditional rendering for Python/JS versions
+     - Processes highlight comments and custom syntax
+
+2. **API Reference Generation:**
+   - **mkdocstrings** plugin extracts docstrings from Python source code
+   - Manual `::: module.Class` directives in reference pages (`/docs/docs/*`) specify what to document
+   - Cross-references are automatically generated between docs and API
+
+3. **Site Generation:**
+   - **MkDocs** processes all markdown files and generates static HTML
+   - Custom hooks handle redirects and inject additional functionality
+
+4. **Deployment:**
+   - Site is deployed with Vercel
+   - `make build-docs` generates production build (also usable for local testing)
+   - Automatic redirects handle URL changes between versions
+
+### Local Development
+
+For local development, use the Makefile targets:
 
 ```bash
+# Serve docs locally with hot reloading
 make serve-docs
+
+# Clean build for production testing
+make build-docs
+
+# Serve with clean build
+make serve-clean-docs
 ```
 
-This will start the documentation server on [http://127.0.0.1:8000/langgraph/](http://127.0.0.1:8000/langgraph/).
+The `serve-docs` command:
+
+- Watches source files for changes
+- Includes dirty builds for faster iteration
+- Serves on [http://127.0.0.1:8000/langgraph/](http://127.0.0.1:8000/langgraph/)
+
+## Standards
+
+**Docstring Format:**
+The API reference uses **Google-style docstrings** with Markdown markup. The `mkdocstrings` plugin processes these to generate documentation.
+
+**Required format:**
+
+```python
+def example_function(param1: str, param2: int = 5) -> bool:
+    """Brief description of the function.
+
+    Longer description can go here. Use Markdown syntax for
+    rich formatting like **bold** and *italic*.
+
+    Args:
+        param1: Description of the first parameter.
+        param2: Description of the second parameter with default value.
+
+    Returns:
+        Description of the return value.
+
+    Raises:
+        ValueError: When param1 is empty.
+        TypeError: When param2 is not an integer.
+
+    !!! warning
+        This function is experimental and may change.
+
+    !!! version-added "Added in version 0.2.0"
+    """
+```
+
+**Special Markers:**
+
+- **MkDocs admonitions**: `!!! warning`, `!!! note`, `!!! version-added`
+- **Code blocks**: Standard markdown ``` syntax
+- **Cross-references**: Automatic linking via `generate_api_reference_links.py`
 
 ## Execute notebooks
 
-If you would like to automatically execute all of the notebooks, to mimic the "Run notebooks" GHA, you can run:
+If you would like to automatically execute all of the notebooks, to mimic the "Run notebooks" GitHub action, you can run:
 
 ```bash
 python _scripts/prepare_notebooks_for_ci.py
@@ -33,8 +135,9 @@ python _scripts/prepare_notebooks_for_ci.py --comment-install-cells
 ```
 
 `prepare_notebooks_for_ci.py` script will add VCR cassette context manager for each cell in the notebook, so that:
-* when the notebook is run for the first time, cells with network requests will be recorded to a VCR cassette file
-* when the notebook is run subsequently, the cells with network requests will be replayed from the cassettes
+
+- when the notebook is run for the first time, cells with network requests will be recorded to a VCR cassette file
+- when the notebook is run subsequently, the cells with network requests will be replayed from the cassettes
 
 ## Adding new notebooks
 

docs/_scripts/generate_api_reference_links.py

@@ -1,3 +1,5 @@
+"""Generate API reference links for imports in Python code blocks within markdown files."""
+
 import ast
 import importlib
 import logging
@@ -70,8 +72,18 @@ MANUAL_API_REFERENCES_LANGGRAPH = [
     ([], "langgraph.checkpoint.postgres.aio", "AsyncPostgresSaver", "checkpoints"),
     ([], "langgraph.checkpoint.postgres", "PostgresSaver", "checkpoints"),
     # other prebuilts
-    (["langgraph_supervisor"], "langgraph_supervisor.supervisor", "create_supervisor", "supervisor"),
-    (["langgraph_supervisor"], "langgraph_supervisor.handoff", "create_handoff_tool", "supervisor"),
+    (
+        ["langgraph_supervisor"],
+        "langgraph_supervisor.supervisor",
+        "create_supervisor",
+        "supervisor",
+    ),
+    (
+        ["langgraph_supervisor"],
+        "langgraph_supervisor.handoff",
+        "create_handoff_tool",
+        "supervisor",
+    ),
     ([], "langgraph_supervisor.handoff", "create_forward_message_tool", "supervisor"),
     (["langgraph_swarm"], "langgraph_swarm.swarm", "create_swarm", "swarm"),
     (["langgraph_swarm"], "langgraph_swarm.swarm", "add_active_agent_router", "swarm"),

docs/_scripts/handle_auto_links.py

@@ -29,7 +29,11 @@ logger = logging.getLogger(__name__)
 
 
 def _transform_link(
-    link_name: str, scope: str, file_path: str, line_number: int, custom_title: Optional[str] = None
+    link_name: str,
+    scope: str,
+    file_path: str,
+    line_number: int,
+    custom_title: Optional[str] = None,
 ) -> Optional[str]:
     """Transform a cross-reference link based on the current scope.
 
@@ -38,7 +42,7 @@ def _transform_link(
         scope: The current scope context ("global", "python", "js", etc.).
         file_path: The file path for error reporting.
         line_number: The line number for error reporting.
-        custom_title: Optional custom title for the link. If None, uses link_name.
+        custom_title: Optional custom title for the link. If `None`, uses link_name.
 
     Returns:
         A formatted markdown link if the link is found in the scope mapping,
@@ -117,7 +121,9 @@ CROSS_REFERENCE_PATTERN = re.compile(
 )
 
 
-def _replace_autolinks(markdown: str, file_path: str, *, default_scope: str = "python") -> str:
+def _replace_autolinks(
+    markdown: str, file_path: str, *, default_scope: str = "python"
+) -> str:
     """Preprocess markdown lines to handle @[links] with conditional fence scopes.
 
     This function processes markdown content to transform @[link_name] references
@@ -169,7 +175,7 @@ def _replace_autolinks(markdown: str, file_path: str, *, default_scope: str = "p
                 # This is @[ref] format
                 link_name = match.group("link_name")
                 custom_title = None
-            
+
             transformed = _transform_link(
                 link_name, current_scope, file_path, line_number, custom_title
             )

docs/_scripts/js_translation/codeblocks/yarn.lock

@@ -2108,9 +2108,9 @@ __metadata:
   linkType: hard
 
 "hono@npm:^4.5.4":
-  version: 4.8.9
-  resolution: "hono@npm:4.8.9"
-  checksum: 10c0/385539d1787fdc747bc869ef0e5ccc9f39cbe40289b94f23eecfc82c6ca440f059704647cd6381a5066d2cf7baa43ab25184c78d44af4c5c98a5c5b07670059e
+  version: 4.10.3
+  resolution: "hono@npm:4.10.3"
+  checksum: 10c0/bdcc4c7066c74ba7cfa63ed6550768a0f43a420286c8f8f74b7012ea4901b8b06778fa8e98264b46f1a86920f056b7ede1f07814da4934912f9945def4977c29
   languageName: node
   linkType: hard
 

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_convert.py

@@ -1,3 +1,5 @@
+"""Convert Jupyter notebooks to markdown with custom processing."""
+
 import ast
 import os
 import re

docs/_scripts/notebook_hooks.py

@@ -27,130 +27,430 @@ DISABLED = os.getenv("DISABLE_NOTEBOOK_CONVERT") in ("1", "true", "True")
 
 REDIRECT_MAP = {
     # lib redirects
-    "how-tos/stream-values.ipynb": "how-tos/streaming.md#stream-graph-state",
-    "how-tos/stream-updates.ipynb": "how-tos/streaming.md#stream-graph-state",
-    "how-tos/streaming-content.ipynb": "how-tos/streaming.md",
-    "how-tos/stream-multiple.ipynb": "how-tos/streaming.md#stream-multiple-nodes",
-    "how-tos/streaming-tokens-without-langchain.ipynb": "how-tos/streaming.md#use-with-any-llm",
-    "how-tos/streaming-from-final-node.ipynb": "how-tos/streaming-specific-nodes.ipynb",
-    "how-tos/streaming-events-from-within-tools-without-langchain.ipynb": "how-tos/streaming-events-from-within-tools.ipynb#example-without-langchain",
+    "how-tos/stream-values.ipynb": "https://docs.langchain.com/oss/python/langgraph/streaming",
+    "how-tos/stream-updates.ipynb": "https://docs.langchain.com/oss/python/langgraph/streaming",
+    "how-tos/streaming-content.ipynb": "https://docs.langchain.com/oss/python/langgraph/streaming",
+    "how-tos/stream-multiple.ipynb": "https://docs.langchain.com/oss/python/langgraph/streaming",
+    "how-tos/streaming-tokens-without-langchain.ipynb": "https://docs.langchain.com/oss/python/langgraph/streaming",
+    "how-tos/streaming-from-final-node.ipynb": "https://docs.langchain.com/oss/python/langgraph/streaming",
+    "how-tos/streaming-events-from-within-tools-without-langchain.ipynb": "https://docs.langchain.com/oss/python/langgraph/streaming",
     # graph-api
-    "how-tos/state-reducers.ipynb": "how-tos/graph-api.md#define-and-update-state",
-    "how-tos/sequence.ipynb": "how-tos/graph-api.md#create-a-sequence-of-steps",
-    "how-tos/branching.ipynb": "how-tos/graph-api.md#create-branches",
-    "how-tos/recursion-limit.ipynb": "how-tos/graph-api.md#create-and-control-loops",
-    "how-tos/visualization.ipynb": "how-tos/graph-api.md#visualize-your-graph",
-    "how-tos/input_output_schema.ipynb": "how-tos/graph-api.md#define-input-and-output-schemas",
-    "how-tos/pass_private_state.ipynb": "how-tos/graph-api.md#pass-private-state-between-nodes",
-    "how-tos/state-model.ipynb": "how-tos/graph-api.md#use-pydantic-models-for-graph-state",
-    "how-tos/map-reduce.ipynb": "how-tos/graph-api.md#map-reduce-and-the-send-api",
-    "how-tos/command.ipynb": "how-tos/graph-api.md#combine-control-flow-and-state-updates-with-command",
-    "how-tos/configuration.ipynb": "how-tos/graph-api.md#add-runtime-configuration",
-    "how-tos/node-retries.ipynb": "how-tos/graph-api.md#add-retry-policies",
-    "how-tos/return-when-recursion-limit-hits.ipynb": "how-tos/graph-api.md#impose-a-recursion-limit",
-    "how-tos/async.ipynb": "how-tos/graph-api.md#async",
+    "how-tos/state-reducers.ipynb": "https://docs.langchain.com/oss/python/langgraph/graph-api#define-and-update-state",
+    "how-tos/sequence.ipynb": "https://docs.langchain.com/oss/python/langgraph/graph-api#create-a-sequence-of-steps",
+    "how-tos/branching.ipynb": "https://docs.langchain.com/oss/python/langgraph/graph-api#create-branches",
+    "how-tos/recursion-limit.ipynb": "https://docs.langchain.com/oss/python/langgraph/graph-api#create-and-control-loops",
+    "how-tos/visualization.ipynb": "https://docs.langchain.com/oss/python/langgraph/graph-api#visualize-your-graph",
+    "how-tos/input_output_schema.ipynb": "https://docs.langchain.com/oss/python/langgraph/graph-api#define-input-and-output-schemas",
+    "how-tos/pass_private_state.ipynb": "https://docs.langchain.com/oss/python/langgraph/graph-api#pass-private-state-between-nodes",
+    "how-tos/state-model.ipynb": "https://docs.langchain.com/oss/python/langgraph/graph-api#use-pydantic-models-for-graph-state",
+    "how-tos/map-reduce.ipynb": "https://docs.langchain.com/oss/python/langgraph/graph-api#map-reduce-and-the-send-api",
+    "how-tos/command.ipynb": "https://docs.langchain.com/oss/python/langgraph/graph-api#combine-control-flow-and-state-updates-with-command",
+    "how-tos/configuration.ipynb": "https://docs.langchain.com/oss/python/langgraph/graph-api#add-runtime-configuration",
+    "how-tos/node-retries.ipynb": "https://docs.langchain.com/oss/python/langgraph/graph-api#add-retry-policies",
+    "how-tos/return-when-recursion-limit-hits.ipynb": "https://docs.langchain.com/oss/python/langgraph/graph-api#impose-a-recursion-limit",
+    "how-tos/async.ipynb": "https://docs.langchain.com/oss/python/langgraph/graph-api#async",
     # memory how-tos
-    "how-tos/memory/manage-conversation-history.ipynb": "how-tos/memory/add-memory.md",
-    "how-tos/memory/delete-messages.ipynb": "how-tos/memory/add-memory.md#delete-messages",
-    "how-tos/memory/add-summary-conversation-history.ipynb": "how-tos/memory/add-memory.md#summarize-messages",
-    "how-tos/memory.ipynb": "how-tos/memory/add-memory.md",
-    "agents/memory.ipynb": "how-tos/memory/add-memory.md",
+    "how-tos/memory/manage-conversation-history.ipynb": "https://docs.langchain.com/oss/python/langgraph/add-memory",
+    "how-tos/memory/delete-messages.ipynb": "https://docs.langchain.com/oss/python/langgraph/add-memory#delete-messages",
+    "how-tos/memory/add-summary-conversation-history.ipynb": "https://docs.langchain.com/oss/python/langgraph/add-memory#summarize-messages",
+    "how-tos/memory.ipynb": "https://docs.langchain.com/oss/python/langgraph/add-memory",
+    "agents/memory.ipynb": "https://docs.langchain.com/oss/python/langgraph/add-memory",
     # subgraph how-tos
-    "how-tos/subgraph-transform-state.ipynb": "how-tos/subgraph.md#different-state-schemas",
-    "how-tos/subgraphs-manage-state.ipynb": "how-tos/subgraph.md#add-persistence",
+    "how-tos/subgraph-transform-state.ipynb": "https://docs.langchain.com/oss/python/langgraph/use-subgraphs#different-state-schemas",
+    "how-tos/subgraphs-manage-state.ipynb": "https://docs.langchain.com/oss/python/langgraph/use-subgraphs#add-persistence",
     # persistence how-tos
-    "how-tos/persistence_postgres.ipynb": "how-tos/memory/add-memory.md#use-in-production",
-    "how-tos/persistence_mongodb.ipynb": "how-tos/memory/add-memory.md#use-in-production",
-    "how-tos/persistence_redis.ipynb": "how-tos/memory/add-memory.md#use-in-production",
-    "how-tos/subgraph-persistence.ipynb": "how-tos/memory/add-memory.md#use-with-subgraphs",
-    "how-tos/cross-thread-persistence.ipynb": "how-tos/memory/add-memory.md#add-long-term-memory",
-    "cloud/how-tos/copy_threads": "cloud/how-tos/use_threads",
-    "cloud/how-tos/check-thread-status": "cloud/how-tos/use_threads",
-    "cloud/concepts/threads.md": "concepts/persistence.md#threads",
-    "how-tos/persistence.ipynb": "how-tos/memory/add-memory.md",
+    "how-tos/persistence_postgres.ipynb": "https://docs.langchain.com/oss/python/langgraph/add-memory#use-in-production",
+    "how-tos/persistence_mongodb.ipynb": "https://docs.langchain.com/oss/python/langgraph/add-memory#use-in-production",
+    "how-tos/persistence_redis.ipynb": "https://docs.langchain.com/oss/python/langgraph/add-memory#use-in-production",
+    "how-tos/subgraph-persistence.ipynb": "https://docs.langchain.com/oss/python/langgraph/add-memory#use-with-subgraphs",
+    "how-tos/cross-thread-persistence.ipynb": "https://docs.langchain.com/oss/python/langgraph/add-memory#add-long-term-memory",
+    "cloud/how-tos/copy_threads": "https://docs.langchain.com/langsmith/use-threads",
+    "cloud/how-tos/check-thread-status": "https://docs.langchain.com/langsmith/use-threads",
+    "cloud/concepts/threads.md": "https://docs.langchain.com/oss/python/langgraph/persistence#threads",
+    "how-tos/persistence.ipynb": "https://docs.langchain.com/oss/python/langgraph/add-memory",
     # tool calling how-tos
-    "how-tos/tool-calling-errors.ipynb": "how-tos/tool-calling.ipynb#handle-errors",
-    "how-tos/pass-config-to-tools.ipynb": "how-tos/tool-calling.ipynb#access-config",
-    "how-tos/pass-run-time-values-to-tools.ipynb": "how-tos/tool-calling.ipynb#read-state",
-    "how-tos/update-state-from-tools.ipynb": "how-tos/tool-calling.ipynb#update-state",
-    "agents/tools.md": "how-tos/tool-calling.md",
+    "how-tos/tool-calling-errors.ipynb": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+    "how-tos/pass-config-to-tools.ipynb": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+    "how-tos/pass-run-time-values-to-tools.ipynb": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+    "how-tos/update-state-from-tools.ipynb": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+    "agents/tools.md": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
     # multi-agent how-tos
-    "how-tos/agent-handoffs.ipynb": "how-tos/multi_agent.md#handoffs",
-    "how-tos/multi-agent-network.ipynb": "how-tos/multi_agent.md#use-in-a-multi-agent-system",
-    "how-tos/multi-agent-multi-turn-convo.ipynb": "how-tos/multi_agent.md#multi-turn-conversation",
+    "how-tos/agent-handoffs.ipynb": "https://docs.langchain.com/oss/python/langgraph/graph-api",
+    "how-tos/multi-agent-network.ipynb": "https://docs.langchain.com/oss/python/langgraph/graph-api",
+    "how-tos/multi-agent-multi-turn-convo.ipynb": "https://docs.langchain.com/oss/python/langgraph/graph-api",
     # cloud redirects
-    "cloud/index.md": "index.md",
-    "cloud/how-tos/index.md": "concepts/langgraph_platform",
-    "cloud/concepts/api.md": "concepts/langgraph_server.md",
-    "cloud/concepts/cloud.md": "concepts/langgraph_cloud.md",
-    "cloud/faq/studio.md": "concepts/langgraph_studio.md#studio-faqs",
-    "cloud/how-tos/human_in_the_loop_edit_state.md": "cloud/how-tos/add-human-in-the-loop.md",
-    "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/index.md": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "cloud/how-tos/index.md": "https://docs.langchain.com/langsmith/home",
+    "cloud/concepts/api.md": "https://docs.langchain.com/langsmith/agent-server",
+    "cloud/concepts/cloud.md": "https://docs.langchain.com/langsmith/cloud",
+    "cloud/faq/studio.md": "https://docs.langchain.com/langsmith/studio",
+    "cloud/how-tos/human_in_the_loop_edit_state.md": "https://docs.langchain.com/langsmith/add-human-in-the-loop",
+    "cloud/how-tos/human_in_the_loop_user_input.md": "https://docs.langchain.com/langsmith/add-human-in-the-loop",
+    "concepts/platform_architecture.md": "https://docs.langchain.com/langsmith/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/concepts/streaming.md": "concepts/streaming.md",
-    "agents/streaming.md": "how-tos/streaming.md",
+    "cloud/how-tos/stream_values.md": "https://docs.langchain.com/langsmith/streaming",
+    "cloud/how-tos/stream_updates.md": "https://docs.langchain.com/langsmith/streaming",
+    "cloud/how-tos/stream_messages.md": "https://docs.langchain.com/langsmith/streaming",
+    "cloud/how-tos/stream_events.md": "https://docs.langchain.com/langsmith/streaming",
+    "cloud/how-tos/stream_debug.md": "https://docs.langchain.com/langsmith/streaming",
+    "cloud/how-tos/stream_multiple.md": "https://docs.langchain.com/langsmith/streaming",
+    "cloud/concepts/streaming.md": "https://docs.langchain.com/oss/python/langgraph/streaming",
+    "agents/streaming.md": "https://docs.langchain.com/oss/python/langgraph/streaming",
     # prebuilt redirects
-    "how-tos/create-react-agent.ipynb": "agents/agents.md#basic-configuration",
-    "how-tos/create-react-agent-memory.ipynb": "agents/memory.md",
-    "how-tos/create-react-agent-system-prompt.ipynb": "agents/context.md#prompts",
-    "how-tos/create-react-agent-structured-output.ipynb": "agents/agents.md#structured-output",
+    "how-tos/create-react-agent.ipynb": "https://docs.langchain.com/oss/python/langchain/agents#basic-configuration",
+    "how-tos/create-react-agent-memory.ipynb": "https://docs.langchain.com/oss/python/langgraph/add-memory",
+    "how-tos/create-react-agent-system-prompt.ipynb": "https://docs.langchain.com/oss/python/langgraph/add-memory",
+    "how-tos/create-react-agent-structured-output.ipynb": "https://docs.langchain.com/oss/python/langchain/agents#structured-output",
     # misc
-    "prebuilt.md": "agents/prebuilt.md",
-    "reference/prebuilt.md": "reference/agents.md",
-    "concepts/high_level.md": "index.md",
-    "concepts/index.md": "index.md",
-    "concepts/v0-human-in-the-loop.md": "concepts/human-in-the-loop.md",
-    "how-tos/index.md": "index.md",
-    "tutorials/introduction.ipynb": "concepts/why-langgraph.md",
-    "agents/deployment.md": "tutorials/langgraph-platform/local-server.md",
+    "prebuilt.md": "https://docs.langchain.com/oss/python/langchain/agents",
+    "reference/prebuilt.md": "https://reference.langchain.com/python/langgraph/agents/",
+    "concepts/high_level.md": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "concepts/index.md": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "concepts/v0-human-in-the-loop.md": "https://docs.langchain.com/oss/python/langgraph/interrupts",
+    "how-tos/index.md": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "tutorials/introduction.ipynb": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "agents/deployment.md": "https://docs.langchain.com/oss/python/langgraph/local-server",
     # deployment redirects
-    "how-tos/deploy-self-hosted.md": "cloud/deployment/self_hosted_data_plane.md",
-    "concepts/self_hosted.md": "concepts/langgraph_self_hosted_data_plane.md",
-    "tutorials/deployment.md": "concepts/deployment_options.md",
+    "how-tos/deploy-self-hosted.md": "https://docs.langchain.com/langsmith/platform-setup",
+    "concepts/self_hosted.md": "https://docs.langchain.com/langsmith/platform-setup",
+    "tutorials/deployment.md": "https://docs.langchain.com/langsmith/deployments",
     # assistant redirects
-    "cloud/how-tos/assistant_versioning.md": "cloud/how-tos/configuration_cloud.md",
-    "cloud/concepts/runs.md": "concepts/assistants.md#execution",
+    "cloud/how-tos/assistant_versioning.md": "https://docs.langchain.com/langsmith/configuration-cloud",
+    "cloud/concepts/runs.md": "https://docs.langchain.com/langsmith/assistants#execution",
     # hitl redirects
-    "how-tos/wait-user-input-functional.ipynb": "how-tos/use-functional-api.md",
-    "how-tos/review-tool-calls-functional.ipynb": "how-tos/use-functional-api.md",
-    "how-tos/create-react-agent-hitl.ipynb": "how-tos/human_in_the_loop/add-human-in-the-loop.md",
-    "agents/human-in-the-loop.md": "how-tos/human_in_the_loop/add-human-in-the-loop.md",
-    "how-tos/human_in_the_loop/dynamic_breakpoints.ipynb": "how-tos/human_in_the_loop/breakpoints.md",
-    "concepts/breakpoints.md": "concepts/human_in_the_loop.md",
-    "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",
-    "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_cli.md": "https://docs.langchain.com/langgraph-platform/langgraph-cli",
-    "cloud/how-tos/studio/quick_start.md": "https://docs.langchain.com/langgraph-platform/quick-start-studio",
-    "concepts/sdk.md": "https://docs.langchain.com/langgraph-platform/sdk",
-    "concepts/auth.md": "https://docs.langchain.com/langgraph-platform/auth",
-    "concepts/assistants.md": "https://docs.langchain.com/langgraph-platform/assistants",
-    "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",
-    "concepts/server-mcp.md": "https://docs.langchain.com/langgraph-platform/server-mcp",
-    "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",
+    "how-tos/wait-user-input-functional.ipynb": "https://docs.langchain.com/oss/python/langgraph/functional-api",
+    "how-tos/review-tool-calls-functional.ipynb": "https://docs.langchain.com/oss/python/langgraph/functional-api",
+    "how-tos/create-react-agent-hitl.ipynb": "https://docs.langchain.com/oss/python/langgraph/interrupts",
+    "agents/human-in-the-loop.md": "https://docs.langchain.com/oss/python/langgraph/interrupts",
+    "how-tos/human_in_the_loop/dynamic_breakpoints.ipynb": "https://docs.langchain.com/oss/python/langgraph/interrupts",
+    "concepts/breakpoints.md": "https://docs.langchain.com/oss/python/langgraph/interrupts",
+    "how-tos/human_in_the_loop/breakpoints.md": "https://docs.langchain.com/oss/python/langgraph/interrupts",
+    "cloud/how-tos/human_in_the_loop_breakpoint.md": "https://docs.langchain.com/langsmith/add-human-in-the-loop",
+    "how-tos/human_in_the_loop/edit-graph-state.ipynb": "https://docs.langchain.com/oss/python/langgraph/use-time-travel",
+
+    # LGP mintlify migration redirects
+    "examples/index.md": "https://docs.langchain.com/oss/python/learn",
+    "guides/index.md": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "concepts/index.md": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "tutorials/index.md": "https://docs.langchain.com/oss/python/learn",
+    "llms-txt-overview.md": "https://docs.langchain.com/llms.txt",
+    "tutorials/rag/langgraph_adaptive_rag.md": "https://docs.langchain.com/oss/python/langgraph/agentic-rag",
+    "tutorials/multi_agent/multi-agent-collaboration.ipynb": "https://docs.langchain.com/oss/python/langchain/multi-agent",
+    "how-tos/create-react-agent-manage-message-history.ipynb": "https://docs.langchain.com/oss/python/langgraph/add-memory",
+    "how-tos/many-tools.ipynb": "https://docs.langchain.com/oss/python/langchain/tools",
+    "tutorials/customer-support/customer-support.ipynb": "https://docs.langchain.com/oss/python/langgraph/agentic-rag",
+    "how-tos/react-agent-structured-output.ipynb": "https://docs.langchain.com/oss/python/langchain/agents#structured-output",
+    "tutorials/code_assistant/langgraph_code_assistant.ipynb": "https://docs.langchain.com/oss/python/langgraph/agentic-rag",
+    "tutorials/multi_agent/hierarchical_agent_teams.ipynb": "https://docs.langchain.com/oss/python/langchain/supervisor",
+    "tutorials/auth/getting_started.md": "https://docs.langchain.com/langsmith/auth",
+    "tutorials/auth/resource_auth.md": "https://docs.langchain.com/langsmith/resource-auth",
+    "tutorials/auth/add_auth_server.md": "https://docs.langchain.com/langsmith/add-auth-server",
+    "how-tos/use-remote-graph.md": "https://docs.langchain.com/langsmith/use-remote-graph",
+    "how-tos/autogen-integration.md": "https://docs.langchain.com/langsmith/autogen-integration",
+    "how-tos/human_in_the_loop/wait-user-input.ipynb": "https://docs.langchain.com/oss/python/langgraph/interrupts",
+    "cloud/how-tos/use_stream_react.md": "https://docs.langchain.com/langsmith/use-stream-react",
+    "cloud/how-tos/generative_ui_react.md": "https://docs.langchain.com/langsmith/generative-ui-react",
+    "concepts/langgraph_platform.md": "https://docs.langchain.com/langsmith/deployments",
+    "concepts/langgraph_components.md": "https://docs.langchain.com/langsmith/components",
+    "concepts/langgraph_server.md": "https://docs.langchain.com/langsmith/agent-server",
+    "concepts/langgraph_data_plane.md": "https://docs.langchain.com/langsmith/data-plane",
+    "concepts/langgraph_control_plane.md": "https://docs.langchain.com/langsmith/control-plane",
+    "concepts/langgraph_cli.md": "https://docs.langchain.com/langsmith/cli",
+    "concepts/langgraph_studio.md": "https://docs.langchain.com/langsmith/studio",
+    "cloud/how-tos/studio/quick_start.md": "https://docs.langchain.com/langsmith/quick-start-studio",
+    "cloud/how-tos/invoke_studio.md": "https://docs.langchain.com/langsmith/use-studio#run-application",
+    "cloud/how-tos/studio/manage_assistants.md": "https://docs.langchain.com/langsmith/use-studio#manage-assistants",
+    "cloud/how-tos/threads_studio.md": "https://docs.langchain.com/langsmith/use-studio#manage-threads",
+    "cloud/how-tos/iterate_graph_studio.md": "https://docs.langchain.com/langsmith/observability-studio#iterate-on-prompts",
+    "cloud/how-tos/studio/run_evals.md": "https://docs.langchain.com/langsmith/observability-studio#run-experiments-over-a-dataset",
+    "cloud/how-tos/clone_traces_studio.md": "https://docs.langchain.com/langsmith/observability-studio#debug-langsmith-traces",
+    "cloud/how-tos/datasets_studio.md": "https://docs.langchain.com/langsmith/observability-studio#add-node-to-dataset",
+    "concepts/sdk.md": "https://docs.langchain.com/langsmith/sdk",
+    "concepts/plans.md": "https://langchain.com/pricing",
+    "concepts/application_structure.md": "https://docs.langchain.com/langsmith/application-structure",
+    "concepts/scalability_and_resilience.md": "https://docs.langchain.com/langsmith/scalability-and-resilience",
+    "concepts/auth.md": "https://docs.langchain.com/langsmith/authentication-methods",
+    "how-tos/auth/custom_auth.md": "https://docs.langchain.com/langsmith/custom-auth",
+    "how-tos/auth/openapi_security.md": "https://docs.langchain.com/langsmith/openapi-security",
+    "concepts/assistants.md": "https://docs.langchain.com/langsmith/assistants",
+    "cloud/how-tos/configuration_cloud.md": "https://docs.langchain.com/langsmith/cloud",
+    "cloud/how-tos/use_threads.md": "https://docs.langchain.com/langsmith/use-threads",
+    "cloud/how-tos/background_run.md": "https://docs.langchain.com/langsmith/background-run",
+    "cloud/how-tos/same-thread.md": "https://docs.langchain.com/langsmith/same-thread",
+    "cloud/how-tos/stateless_runs.md": "https://docs.langchain.com/langsmith/stateless-runs",
+    "cloud/how-tos/configurable_headers.md": "https://docs.langchain.com/langsmith/configurable-headers",
+    "concepts/double_texting.md": "https://docs.langchain.com/langsmith/double-texting",
+    "cloud/how-tos/interrupt_concurrent.md": "https://docs.langchain.com/langsmith/interrupt-concurrent",
+    "cloud/how-tos/rollback_concurrent.md": "https://docs.langchain.com/langsmith/rollback-concurrent",
+    "cloud/how-tos/reject_concurrent.md": "https://docs.langchain.com/langsmith/reject-concurrent",
+    "cloud/how-tos/enqueue_concurrent.md": "https://docs.langchain.com/langsmith/enqueue-concurrent",
+    "cloud/concepts/webhooks.md": "https://docs.langchain.com/langsmith/use-webhooks",
+    "cloud/how-tos/webhooks.md": "https://docs.langchain.com/langsmith/use-webhooks",
+    "cloud/concepts/cron_jobs.md": "https://docs.langchain.com/langsmith/cron-jobs",
+    "cloud/how-tos/cron_jobs.md": "https://docs.langchain.com/langsmith/cron-jobs",
+    "how-tos/http/custom_lifespan.md": "https://docs.langchain.com/langsmith/custom-lifespan",
+    "how-tos/http/custom_middleware.md": "https://docs.langchain.com/langsmith/custom-middleware",
+    "how-tos/http/custom_routes.md": "https://docs.langchain.com/langsmith/custom-routes",
+    "cloud/concepts/data_storage_and_privacy.md": "https://docs.langchain.com/langsmith/data-storage-and-privacy",
+    "cloud/deployment/semantic_search.md": "https://docs.langchain.com/langsmith/semantic-search",
+    "how-tos/ttl/configure_ttl.md": "https://docs.langchain.com/langsmith/configure-ttl",
+    "concepts/deployment_options.md": "https://docs.langchain.com/langsmith/platform-setup",
+    "cloud/quick_start.md": "https://docs.langchain.com/langsmith/deployment-quickstart",
+    "cloud/deployment/setup.md": "https://docs.langchain.com/langsmith/setup-app-requirements-txt",
+    "cloud/deployment/setup_pyproject.md": "https://docs.langchain.com/langsmith/setup-pyproject",
+    "cloud/deployment/setup_javascript.md": "https://docs.langchain.com/langsmith/setup-javascript",
+    "cloud/deployment/custom_docker.md": "https://docs.langchain.com/langsmith/custom-docker",
+    "cloud/deployment/graph_rebuild.md": "https://docs.langchain.com/langsmith/graph-rebuild",
+    "concepts/langgraph_cloud.md": "https://docs.langchain.com/langsmith/cloud",
+    "concepts/langgraph_self_hosted_data_plane.md": "https://docs.langchain.com/langsmith/hybrid",
+    "concepts/langgraph_self_hosted_control_plane.md": "https://docs.langchain.com/langsmith/self-hosted",
+    "concepts/langgraph_standalone_container.md": "https://docs.langchain.com/langsmith/self-hosted#standalone-server",
+    "cloud/deployment/cloud.md": "https://docs.langchain.com/langsmith/cloud",
+    "cloud/deployment/self_hosted_data_plane.md": "https://docs.langchain.com/langsmith/deploy-hybrid",
+    "cloud/deployment/self_hosted_control_plane.md": "https://docs.langchain.com/langsmith/deploy-self-hosted-full-platform",
+    "cloud/deployment/standalone_container.md": "https://docs.langchain.com/langsmith/deploy-standalone-server",
+    "concepts/server-mcp.md": "https://docs.langchain.com/langsmith/server-mcp",
+    "cloud/how-tos/human_in_the_loop_time_travel.md": "https://docs.langchain.com/langsmith/human-in-the-loop-time-travel",
+    "cloud/how-tos/add-human-in-the-loop.md": "https://docs.langchain.com/langsmith/add-human-in-the-loop",
+    "cloud/deployment/egress.md": "https://docs.langchain.com/langsmith/env-var",
+    "cloud/how-tos/streaming.md": "https://docs.langchain.com/langsmith/streaming",
+    "cloud/reference/api/api_ref.md": "https://docs.langchain.com/langsmith/server-api-ref",
+    "cloud/reference/langgraph_server_changelog.md": "https://docs.langchain.com/langsmith/agent-server-changelog",
+    "cloud/reference/api/api_ref_control_plane.md": "https://docs.langchain.com/langsmith/api-ref-control-plane",
+    "cloud/reference/cli.md": "https://docs.langchain.com/langsmith/cli",
+    "cloud/reference/env_var.md": "https://docs.langchain.com/langsmith/env-var",
+    "troubleshooting/studio.md": "https://docs.langchain.com/langsmith/troubleshooting-studio",
+
+    # LangGraph mintlify migration redirects
+    "index.md": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "agents/agents.md": "https://docs.langchain.com/oss/python/langchain/agents",
+    "concepts/why-langgraph.md": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "tutorials/get-started/1-build-basic-chatbot.md": "https://docs.langchain.com/oss/python/langgraph/quickstart",
+    "tutorials/get-started/2-add-tools.md": "https://docs.langchain.com/oss/python/langgraph/quickstart",
+    "tutorials/get-started/3-add-memory.md": "https://docs.langchain.com/oss/python/langgraph/quickstart",
+    "tutorials/get-started/4-human-in-the-loop.md": "https://docs.langchain.com/oss/python/langgraph/quickstart",
+    "tutorials/get-started/5-customize-state.md": "https://docs.langchain.com/oss/python/langgraph/quickstart",
+    "tutorials/get-started/6-time-travel.md": "https://docs.langchain.com/oss/python/langgraph/quickstart",
+    "tutorials/langsmith/local-server.md": "https://docs.langchain.com/oss/python/langgraph/local-server",
+    "tutorials/workflows.md": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+    "tutorials/plan-and-execute/plan-and-execute.ipynb": "https://docs.langchain.com/oss/python/langchain/middleware/built-in#to-do-list",
+    "tutorials/langgraph-platform/local-server/local-server.md": "https://docs.langchain.com/langsmith/local-server",
+    "concepts/agentic_concepts.md": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+    "guides/index.md": "https://docs.langchain.com/oss/python/langchain/overview",
+    "agents/overview.md": "https://docs.langchain.com/oss/python/langchain/agents",
+    "agents/run_agents.md": "https://docs.langchain.com/oss/python/langgraph/quickstart",
+    "concepts/low_level.md": "https://docs.langchain.com/oss/python/langgraph/graph-api",
+    "how-tos/graph-api.md": "https://docs.langchain.com/oss/python/langgraph/graph-api",
+    "how-tos/react-agent-from-scratch.ipynb": "https://docs.langchain.com/oss/python/langchain/quickstart",
+    "concepts/functional_api.md": "https://docs.langchain.com/oss/python/langgraph/functional-api",
+    "how-tos/use-functional-api.md": "https://docs.langchain.com/oss/python/langgraph/functional-api",
+    "concepts/pregel.md": "https://docs.langchain.com/oss/python/langgraph/pregel",
+    "concepts/streaming.md": "https://docs.langchain.com/oss/python/langgraph/streaming",
+    "how-tos/streaming.md": "https://docs.langchain.com/oss/python/langgraph/streaming",
+    "concepts/persistence.md": "https://docs.langchain.com/oss/python/langgraph/persistence",
+    "concepts/durable_execution.md": "https://docs.langchain.com/oss/python/langgraph/durable-execution",
+    "concepts/memory.md": "https://docs.langchain.com/oss/python/langgraph/memory",
+    "how-tos/memory/add-memory.md": "https://docs.langchain.com/oss/python/langgraph/add-memory",
+    "agents/context.md": "https://docs.langchain.com/oss/python/langgraph/add-memory",
+    "agents/models.md": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "concepts/tools.md": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+    "how-tos/tool-calling.md": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+    "concepts/human_in_the_loop.md": "https://docs.langchain.com/oss/python/langgraph/interrupts",
+    "how-tos/human_in_the_loop/add-human-in-the-loop.md": "https://docs.langchain.com/oss/python/langgraph/interrupts",
+    "concepts/time-travel.md": "https://docs.langchain.com/oss/python/langgraph/persistence",
+    "how-tos/human_in_the_loop/time-travel.md": "https://docs.langchain.com/oss/python/langgraph/use-time-travel",
+    "concepts/subgraphs.md": "https://docs.langchain.com/oss/python/langgraph/use-subgraphs",
+    "how-tos/subgraph.md": "https://docs.langchain.com/oss/python/langgraph/use-subgraphs",
+    "concepts/multi_agent.md": "https://docs.langchain.com/oss/python/langgraph/graph-api",
+    "agents/multi-agent.md": "https://docs.langchain.com/oss/python/langchain/multi-agent",
+    "how-tos/multi_agent.md": "https://docs.langchain.com/oss/python/langgraph/graph-api",
+    "concepts/mcp.md": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "agents/mcp.md": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "concepts/tracing.md": "https://docs.langchain.com/oss/python/langgraph/observability",
+    "how-tos/enable-tracing.md": "https://docs.langchain.com/oss/python/langgraph/observability",
+    "agents/evals.md": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "examples/index.md": "https://docs.langchain.com/oss/python/langgraph/case-studies",
+    "concepts/template_applications.md": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "tutorials/rag/langgraph_agentic_rag.md": "https://docs.langchain.com/oss/python/langgraph/agentic-rag",
+    "tutorials/multi_agent/agent_supervisor.md": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+    "tutorials/sql/sql-agent.md": "https://docs.langchain.com/oss/python/langgraph/sql-agent",
+    "agents/ui.md": "https://docs.langchain.com/oss/python/langgraph/ui",
+    "how-tos/run-id-langsmith.md": "https://docs.langchain.com/oss/python/langgraph/observability",
+    "troubleshooting/errors/index.md": "https://docs.langchain.com/oss/python/langgraph/common-errors",
+    "troubleshooting/errors/INVALID_CHAT_HISTORY.md": "https://docs.langchain.com/oss/python/langgraph/INVALID_CHAT_HISTORY",
+    "troubleshooting/errors/INVALID_LICENSE.md": "https://docs.langchain.com/oss/python/langgraph/common-errors",
+    "adopters.md": "https://docs.langchain.com/oss/python/langgraph/case-studies",
+    "concepts/faq.md": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "agents/prebuilt.md": "https://docs.langchain.com/oss/python/langchain/agents",
+    "reference/index.md": "https://reference.langchain.com/python/langgraph/",
+    "reference/graphs.md": "https://reference.langchain.com/python/langgraph/graphs/",
+    "reference/func.md": "https://reference.langchain.com/python/langgraph/func/",
+    "reference/pregel.md": "https://reference.langchain.com/python/langgraph/pregel/",
+    "reference/checkpoints.md": "https://reference.langchain.com/python/langgraph/checkpoints/",
+    "reference/store.md": "https://reference.langchain.com/python/langgraph/store/",
+    "reference/cache.md": "https://reference.langchain.com/python/langgraph/cache/",
+    "reference/types.md": "https://reference.langchain.com/python/langgraph/types/",
+    "reference/runtime.md": "https://reference.langchain.com/python/langgraph/runtime/",
+    "reference/config.md": "https://reference.langchain.com/python/langgraph/config/",
+    "reference/errors.md": "https://reference.langchain.com/python/langgraph/errors/",
+    "reference/constants.md": "https://reference.langchain.com/python/langgraph/constants/",
+    "reference/channels.md": "https://reference.langchain.com/python/langgraph/channels/",
+    "reference/agents.md": "https://reference.langchain.com/python/langgraph/agents/",
+    "reference/supervisor.md": "https://reference.langchain.com/python/langgraph/supervisor/",
+    "reference/swarm.md": "https://reference.langchain.com/python/langgraph/swarm/",
+    "reference/mcp.md": "https://reference.langchain.com/python/langgraph/mcp/",
+    "cloud/reference/sdk/python_sdk_ref.md": "https://reference.langchain.com/python/langsmith/deployment/sdk/",
+    "reference/remote_graph.md": "https://reference.langchain.com/python/langsmith/deployment/remote_graph/",
+
+    # additional exclude-search entries from mkdocs.yml
+    "additional-resources/index.md": "https://docs.langchain.com/oss/python/langchain/overview",
+    "cloud/concepts/cron_jobs.md": "https://docs.langchain.com/langsmith/cron-jobs",
+    "cloud/concepts/data_storage_and_privacy.md": "https://docs.langchain.com/langsmith/data-storage-and-privacy",
+    "cloud/concepts/webhooks.md": "https://docs.langchain.com/langsmith/use-webhooks",
+    "cloud/deployment/cloud.md": "https://docs.langchain.com/langsmith/cloud",
+    "cloud/deployment/custom_docker.md": "https://docs.langchain.com/langsmith/custom-docker",
+    "cloud/deployment/egress.md": "https://docs.langchain.com/langsmith/env-var",
+    "cloud/deployment/graph_rebuild.md": "https://docs.langchain.com/langsmith/graph-rebuild",
+    "cloud/deployment/self_hosted_control_plane.md": "https://docs.langchain.com/langsmith/platform-setup",
+    "cloud/deployment/self_hosted_data_plane.md": "https://docs.langchain.com/langsmith/platform-setup",
+    "cloud/deployment/semantic_search.md": "https://docs.langchain.com/langsmith/semantic-search",
+    "cloud/deployment/setup_javascript.md": "https://docs.langchain.com/langsmith/setup-javascript",
+    "cloud/deployment/setup_pyproject.md": "https://docs.langchain.com/langsmith/setup-pyproject",
+    "cloud/deployment/setup.md": "https://docs.langchain.com/langsmith/setup-app-requirements-txt",
+    "cloud/deployment/standalone_container.md": "https://docs.langchain.com/langsmith/docker",
+    "cloud/how-tos/add-human-in-the-loop.md": "https://docs.langchain.com/langsmith/add-human-in-the-loop",
+    "cloud/how-tos/background_run.md": "https://docs.langchain.com/langsmith/background-run",
+    "cloud/how-tos/clone_traces_studio.md": "https://docs.langchain.com/langsmith/observability",
+    "cloud/how-tos/configurable_headers.md": "https://docs.langchain.com/langsmith/configurable-headers",
+    "cloud/how-tos/configuration_cloud.md": "https://docs.langchain.com/langsmith/configuration-cloud",
+    "cloud/how-tos/cron_jobs.md": "https://docs.langchain.com/langsmith/cron-jobs",
+    "cloud/how-tos/datasets_studio.md": "https://docs.langchain.com/langsmith/use-studio",
+    "cloud/how-tos/enqueue_concurrent.md": "https://docs.langchain.com/langsmith/enqueue-concurrent",
+    "cloud/how-tos/generative_ui_react.md": "https://docs.langchain.com/langsmith/generative-ui-react",
+    "cloud/how-tos/human_in_the_loop_time_travel.md": "https://docs.langchain.com/langsmith/human-in-the-loop-time-travel",
+    "cloud/how-tos/interrupt_concurrent.md": "https://docs.langchain.com/langsmith/interrupt-concurrent",
+    "cloud/how-tos/invoke_studio.md": "https://docs.langchain.com/langsmith/use-studio",
+    "cloud/how-tos/iterate_graph_studio.md": "https://docs.langchain.com/langsmith/use-studio",
+    "cloud/how-tos/reject_concurrent.md": "https://docs.langchain.com/langsmith/reject-concurrent",
+    "cloud/how-tos/rollback_concurrent.md": "https://docs.langchain.com/langsmith/rollback-concurrent",
+    "cloud/how-tos/same-thread.md": "https://docs.langchain.com/langsmith/same-thread",
+    "cloud/how-tos/stateless_runs.md": "https://docs.langchain.com/langsmith/stateless-runs",
+    "cloud/how-tos/streaming.md": "https://docs.langchain.com/langsmith/streaming",
+    "cloud/how-tos/studio/manage_assistants.md": "https://docs.langchain.com/langsmith/use-studio",
+    "cloud/how-tos/studio/quick_start.md": "https://docs.langchain.com/langsmith/quick-start-studio",
+    "cloud/how-tos/studio/run_evals.md": "https://docs.langchain.com/langsmith/observability",
+    "cloud/how-tos/threads_studio.md": "https://docs.langchain.com/langsmith/use-threads",
+    "cloud/how-tos/use_stream_react.md": "https://docs.langchain.com/langsmith/use-stream-react",
+    "cloud/how-tos/use_threads.md": "https://docs.langchain.com/langsmith/use-threads",
+    "cloud/how-tos/webhooks.md": "https://docs.langchain.com/langsmith/use-webhooks",
+    "cloud/quick_start.md": "https://docs.langchain.com/langsmith/deployment-quickstart",
+    "cloud/reference/api/api_ref_control_plane.md": "https://docs.langchain.com/langsmith/api-ref-control-plane",
+    "cloud/reference/api/api_ref.md": "https://docs.langchain.com/langsmith/server-api-ref",
+    "cloud/reference/cli.md": "https://docs.langchain.com/langsmith/cli",
+    "cloud/reference/env_var.md": "https://docs.langchain.com/langsmith/env-var",
+    "cloud/reference/langgraph_server_changelog.md": "https://docs.langchain.com/langsmith/agent-server-changelog",
+    "cloud/reference/sdk/js_ts_sdk_ref.md": "https://reference.langchain.com/javascript/modules/langsmith.html",
+    "concepts/application_structure.md": "https://docs.langchain.com/langsmith/application-structure",
+    "concepts/assistants.md": "https://docs.langchain.com/langsmith/assistants",
+    "concepts/auth.md": "https://docs.langchain.com/langsmith/auth",
+    "concepts/deployment_options.md": "https://docs.langchain.com/langsmith/deployments",
+    "concepts/double_texting.md": "https://docs.langchain.com/langsmith/double-texting",
+    "concepts/faq.md": "https://docs.langchain.com/langsmith/faq",
+    "concepts/langgraph_cli.md": "https://docs.langchain.com/langsmith/cli",
+    "concepts/langgraph_cloud.md": "https://docs.langchain.com/langsmith/cloud",
+    "concepts/langgraph_components.md": "https://docs.langchain.com/langsmith/components",
+    "concepts/langgraph_control_plane.md": "https://docs.langchain.com/langsmith/control-plane",
+    "concepts/langgraph_data_plane.md": "https://docs.langchain.com/langsmith/data-plane",
+    "concepts/langgraph_platform.md": "https://docs.langchain.com/langsmith/home",
+    "concepts/langgraph_self_hosted_control_plane.md": "https://docs.langchain.com/langsmith/platform-setup",
+    "concepts/langgraph_self_hosted_data_plane.md": "https://docs.langchain.com/langsmith/platform-setup",
+    "concepts/langgraph_server.md": "https://docs.langchain.com/langsmith/agent-server",
+    "concepts/langgraph_standalone_container.md": "https://docs.langchain.com/langsmith/docker",
+    "concepts/langgraph_studio.md": "https://docs.langchain.com/langsmith/studio",
+    "concepts/plans.md": "https://docs.langchain.com/langsmith/home",
+    "concepts/scalability_and_resilience.md": "https://docs.langchain.com/langsmith/scalability-and-resilience",
+    "concepts/sdk.md": "https://docs.langchain.com/langsmith/sdk",
+    "concepts/server-mcp.md": "https://docs.langchain.com/langsmith/server-mcp",
+    "concepts/template_applications.md": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "concepts/why-langgraph.md": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "examples/index.md": "https://docs.langchain.com/oss/python/langgraph/case-studies",
+    "guides/index.md": "https://docs.langchain.com/oss/python/langchain/overview",
+    "how-tos/auth/custom_auth.md": "https://docs.langchain.com/langsmith/custom-auth",
+    "how-tos/auth/openapi_security.md": "https://docs.langchain.com/langsmith/openapi-security",
+    "how-tos/autogen-integration.md": "https://docs.langchain.com/langsmith/autogen-integration",
+    "how-tos/http/custom_lifespan.md": "https://docs.langchain.com/langsmith/custom-lifespan",
+    "how-tos/http/custom_middleware.md": "https://docs.langchain.com/langsmith/custom-middleware",
+    "how-tos/http/custom_routes.md": "https://docs.langchain.com/langsmith/custom-routes",
+    "how-tos/ttl/configure_ttl.md": "https://docs.langchain.com/langsmith/configure-ttl",
+    "how-tos/use-remote-graph.md": "https://docs.langchain.com/langsmith/use-remote-graph",
+    "index.md": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "snippets/chat_model_tabs.md": "https://docs.langchain.com/oss/python/langchain/overview",
+    "troubleshooting/errors/GRAPH_RECURSION_LIMIT.md": "https://docs.langchain.com/oss/python/langgraph/GRAPH_RECURSION_LIMIT",
+    "troubleshooting/errors/index.md": "https://docs.langchain.com/oss/python/langgraph/common-errors",
+    "troubleshooting/errors/INVALID_CHAT_HISTORY.md": "https://docs.langchain.com/oss/python/langgraph/INVALID_CHAT_HISTORY",
+    "troubleshooting/errors/INVALID_CONCURRENT_GRAPH_UPDATE.md": "https://docs.langchain.com/oss/python/langgraph/INVALID_CONCURRENT_GRAPH_UPDATE",
+    "troubleshooting/errors/INVALID_GRAPH_NODE_RETURN_VALUE.md": "https://docs.langchain.com/oss/python/langgraph/INVALID_GRAPH_NODE_RETURN_VALUE",
+    "troubleshooting/errors/INVALID_LICENSE.md": "https://docs.langchain.com/oss/python/langgraph/common-errors",
+    "troubleshooting/errors/MULTIPLE_SUBGRAPHS.md": "https://docs.langchain.com/oss/python/langgraph/MULTIPLE_SUBGRAPHS",
+    "troubleshooting/studio.md": "https://docs.langchain.com/langsmith/troubleshooting-studio",
+    "tutorials/auth/add_auth_server.md": "https://docs.langchain.com/langsmith/add-auth-server",
+    "tutorials/auth/getting_started.md": "https://docs.langchain.com/langsmith/auth",
+    "tutorials/auth/resource_auth.md": "https://docs.langchain.com/langsmith/resource-auth",
+    "agents/agents.md": "https://docs.langchain.com/oss/python/langchain/agents",
+    "concepts/why-langgraph.md": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "tutorials/langsmith/local-server.md": "https://docs.langchain.com/oss/python/langgraph/local-server",
+    "tutorials/workflows.md": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+    "concepts/agentic_concepts.md": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+    "guides/index.md": "https://docs.langchain.com/oss/python/langchain/overview",
+    "agents/overview.md": "https://docs.langchain.com/oss/python/langchain/agents",
+    "concepts/agentic_concepts.md": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+    "agents/run_agents.md": "https://docs.langchain.com/oss/python/langgraph/quickstart",
+    "concepts/low_level.md": "https://docs.langchain.com/oss/python/langgraph/graph-api",
+    "how-tos/graph-api.md": "https://docs.langchain.com/oss/python/langgraph/graph-api",
+    "concepts/functional_api.md": "https://docs.langchain.com/oss/python/langgraph/functional-api",
+    "how-tos/use-functional-api.md": "https://docs.langchain.com/oss/python/langgraph/functional-api",
+    "concepts/pregel.md": "https://docs.langchain.com/oss/python/langgraph/pregel",
+    "concepts/streaming.md": "https://docs.langchain.com/oss/python/langgraph/streaming",
+    "how-tos/streaming.md": "https://docs.langchain.com/oss/python/langgraph/streaming",
+    "concepts/persistence.md": "https://docs.langchain.com/oss/python/langgraph/persistence",
+    "concepts/durable_execution.md": "https://docs.langchain.com/oss/python/langgraph/durable-execution",
+    "concepts/memory.md": "https://docs.langchain.com/oss/python/langgraph/memory",
+    "how-tos/memory/add-memory.md": "https://docs.langchain.com/oss/python/langgraph/add-memory",
+    "agents/context.md": "https://docs.langchain.com/oss/python/langgraph/add-memory",
+    "agents/models.md": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "concepts/tools.md": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+    "how-tos/tool-calling.md": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+    "concepts/human_in_the_loop.md": "https://docs.langchain.com/oss/python/langgraph/interrupts",
+    "how-tos/human_in_the_loop/add-human-in-the-loop.md": "https://docs.langchain.com/oss/python/langgraph/interrupts",
+    "concepts/time-travel.md": "https://docs.langchain.com/oss/python/langgraph/persistence",
+    "how-tos/human_in_the_loop/time-travel.md": "https://docs.langchain.com/oss/python/langgraph/use-time-travel",
+    "concepts/subgraphs.md": "https://docs.langchain.com/oss/python/langgraph/use-subgraphs",
+    "how-tos/subgraph.md": "https://docs.langchain.com/oss/python/langgraph/use-subgraphs",
+    "concepts/multi_agent.md": "https://docs.langchain.com/oss/python/langgraph/graph-api",
+    "agents/multi-agent.md": "https://docs.langchain.com/oss/python/langchain/multi-agent",
+    "how-tos/multi_agent.md": "https://docs.langchain.com/oss/python/langgraph/graph-api",
+    "concepts/mcp.md": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "agents/mcp.md": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "concepts/tracing.md": "https://docs.langchain.com/oss/python/langgraph/observability",
+    "how-tos/enable-tracing.md": "https://docs.langchain.com/oss/python/langgraph/observability",
+    "agents/evals.md": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "examples/index.md": "https://docs.langchain.com/oss/python/langgraph/case-studies",
+    "concepts/template_applications.md": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "tutorials/rag/langgraph_agentic_rag.md": "https://docs.langchain.com/oss/python/langgraph/agentic-rag",
+    "tutorials/multi_agent/agent_supervisor.md": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+    "tutorials/sql/sql-agent.md": "https://docs.langchain.com/oss/python/langgraph/sql-agent",
+    "agents/ui.md": "https://docs.langchain.com/oss/python/langgraph/ui",
+    "how-tos/run-id-langsmith.md": "https://docs.langchain.com/oss/python/langgraph/observability",
+    "troubleshooting/errors/index.md": "https://docs.langchain.com/oss/python/langgraph/common-errors",
+    "troubleshooting/errors/GRAPH_RECURSION_LIMIT.md": "https://docs.langchain.com/oss/python/langgraph/GRAPH_RECURSION_LIMIT",
+    "troubleshooting/errors/INVALID_CONCURRENT_GRAPH_UPDATE.md": "https://docs.langchain.com/oss/python/langgraph/INVALID_CONCURRENT_GRAPH_UPDATE",
+    "troubleshooting/errors/INVALID_GRAPH_NODE_RETURN_VALUE.md": "https://docs.langchain.com/oss/python/langgraph/INVALID_GRAPH_NODE_RETURN_VALUE",
+    "troubleshooting/errors/MULTIPLE_SUBGRAPHS.md": "https://docs.langchain.com/oss/python/langgraph/MULTIPLE_SUBGRAPHS",
+    "troubleshooting/errors/INVALID_CHAT_HISTORY.md": "https://docs.langchain.com/oss/python/langgraph/INVALID_CHAT_HISTORY",
+    "troubleshooting/errors/INVALID_LICENSE.md": "https://docs.langchain.com/oss/python/langgraph/common-errors",
+    "adopters.md": "https://docs.langchain.com/oss/python/langgraph/case-studies",
+    "concepts/faq.md": "https://docs.langchain.com/oss/python/langgraph/overview",
+    "agents/prebuilt.md": "https://docs.langchain.com/oss/python/langchain/agents",
 }
 
 
@@ -505,17 +805,131 @@ def on_post_page(html: str, page: Page, config: MkDocsConfig) -> str:
 # Create HTML files for redirects after site dir has been built
 def on_post_build(config):
     use_directory_urls = config.get("use_directory_urls")
+    site_dir = config["site_dir"]
+
+    # Track which paths have explicit redirects
+    redirected_paths = set()
+
+    # Collect all existing HTML files in the site
+    all_html_files = set()
+    for root, dirs, files in os.walk(site_dir):
+        for file in files:
+            if file.endswith(".html"):
+                # Get relative path from site_dir
+                html_path = os.path.relpath(os.path.join(root, file), site_dir)
+                # Normalize path separators to forward slashes
+                html_path = html_path.replace(os.sep, "/")
+                all_html_files.add(html_path)
+
+    # Process explicit redirects from REDIRECT_MAP
     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"
+
+        # Track this path as redirected
+        redirected_paths.add(old_html_path)
+
+        if isinstance(page_new, str) and page_new.startswith("http"):
+            # Handle external redirects
+            _write_html(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(site_dir, old_html_path, new_html_path)
+
+    # Create catch-all redirects for any HTML files not explicitly redirected
+    catchall_url = "https://docs.langchain.com/oss/python/langgraph/overview"
+    for html_file in all_html_files:
+        # Skip if this file is already explicitly redirected
+        if html_file in redirected_paths:
+            continue
+
+        # Skip the root index.html (we handle that separately)
+        if html_file == "index.html":
+            continue
+
+        # Skip reference documentation (keep those accessible)
+        if html_file.startswith("reference/"):
+            continue
+
+        # Create redirect for this unmapped file
+        _write_html(site_dir, html_file, catchall_url)
+
+    # Create root index.html redirect
+    root_redirect_html = """<!doctype html>
+<html lang="en">
+<head>
+    <meta charset="utf-8">
+    <title>Redirecting to LangGraph Documentation</title>
+    <link rel="canonical" href="https://docs.langchain.com/oss/python/langgraph/overview">
+    <meta name="robots" content="noindex">
+    <script>var anchor=window.location.hash.substr(1);location.href="https://docs.langchain.com/oss/python/langgraph/overview"+(anchor?"#"+anchor:"")</script>
+    <meta http-equiv="refresh" content="0; url=https://docs.langchain.com/oss/python/langgraph/overview">
+</head>
+<body>
+<h1>Documentation has moved</h1>
+<p>The LangGraph documentation has moved to <a href="https://docs.langchain.com/oss/python/langgraph/overview">docs.langchain.com</a>.</p>
+<p>Redirecting you now...</p>
+</body>
+</html>
+"""
+
+    root_index_path = os.path.join(site_dir, "index.html")
+    with open(root_index_path, "w", encoding="utf-8") as f:
+        f.write(root_redirect_html)
+
+    # Create server-side catch-all redirect file for Netlify/Cloudflare Pages
+    # This handles any pages not explicitly mapped in REDIRECT_MAP
+    # Note: This won't work on GitHub Pages, but kept for potential future use
+    redirects_content = """# Netlify/Cloudflare Pages redirect rules
+# Specific redirects are handled by individual HTML redirect pages
+# This is the catch-all for any unmapped pages
+
+# Exclude reference docs from catch-all
+/reference/*  200
+
+# Catch-all: redirect any page not explicitly mapped
+/*  https://docs.langchain.com/oss/python/langgraph/overview  301
+"""
+
+    redirects_path = os.path.join(site_dir, "_redirects")
+    with open(redirects_path, "w", encoding="utf-8") as f:
+        f.write(redirects_content)

docs/_scripts/third_party_page/get_download_stats.py

@@ -20,16 +20,19 @@ class Package(TypedDict):
     description: str
     """A brief description of what the package does."""
 
+
 class ResolvedPackage(Package):
     weekly_downloads: int | None
     """The weekly download count of the package."""
     language: str
     """The language of the package. (either 'python' or 'js')"""
 
+
 HERE = pathlib.Path(__file__).parent
 PACKAGES_FILE = HERE / "packages.yml"
 PACKAGES = yaml.safe_load(PACKAGES_FILE.read_text())["packages"]
 
+
 def _get_pypi_downloads(package: Package) -> int:
     """Retrieve the weekly download count for a package from PyPIStats."""
 
@@ -72,7 +75,8 @@ def _get_pypi_downloads(package: Package) -> int:
         return sum(entry["downloads"] for entry in sorted_data[:7])
     else:
         return None
-    
+
+
 def _get_npm_downloads(package: Package) -> int:
     """Retrieve the weekly download count for a package on the npm registry."""
 
@@ -82,14 +86,18 @@ def _get_npm_downloads(package: Package) -> int:
         npm_response = requests.get(npm_url)
         npm_response.raise_for_status()
     except requests.exceptions.HTTPError:
-        raise AssertionError(f"Package {package['name']} does not exist on npm registry")
+        raise AssertionError(
+            f"Package {package['name']} does not exist on npm registry"
+        )
 
     npm_data = npm_response.json()
 
     # Retrieve the first publish date using the 'created' timestamp from the 'time' field.
     created_str = npm_data.get("time", {}).get("created")
     if created_str is None:
-        raise AssertionError(f"Package {package['name']} has no creation time in registry data")
+        raise AssertionError(
+            f"Package {package['name']} has no creation time in registry data"
+        )
     # Remove the trailing 'Z' if present and parse the ISO format timestamp
     first_publish_date = datetime.fromisoformat(created_str.rstrip("Z"))
 
@@ -103,7 +111,10 @@ def _get_npm_downloads(package: Package) -> int:
     else:
         return None
 
-def _get_weekly_downloads(packages: dict[str, list[Package]], fake: bool) -> list[ResolvedPackage]:
+
+def _get_weekly_downloads(
+    packages: dict[str, list[Package]], fake: bool
+) -> list[ResolvedPackage]:
     """Retrieve the weekly download count for a dictionary of python or js packages."""
     resolved_packages: list[ResolvedPackage] = []
 
@@ -131,7 +142,7 @@ def _get_weekly_downloads(packages: dict[str, list[Package]], fake: bool) -> lis
                 num_downloads = _get_npm_downloads(package)
             else:
                 num_downloads = None
-            
+
             resolved_packages.append(
                 {
                     "name": package["name"],
@@ -145,12 +156,13 @@ def _get_weekly_downloads(packages: dict[str, list[Package]], fake: bool) -> lis
 
     return resolved_packages
 
+
 def main(output_file: str, fake: bool) -> None:
     """Main function to generate package download information.
 
     Args:
         output_file: Path to the output YAML file.
-        fake: If True, use fake download counts for testing purposes.
+        fake: If `True`, use fake download counts for testing purposes.
     """
     resolved_packages: list[ResolvedPackage] = _get_weekly_downloads(PACKAGES, fake)
 

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"
 
@@ -33,7 +33,7 @@ LangGraph provides three ways to manage context, which combines the mutability a
 
 **Static runtime context** represents immutable data like user metadata, tools, and database connections that are passed to an application at the start of a run via the `context` argument to `invoke`/`stream`. This data does not change during execution.
 
-!!! version-added "New in LangGraph v0.6: `context` replaces `config['configurable']`"
+!!! version-added "Added in version 0.6.0: `context` replaces `config['configurable']`"
 
     Runtime context is now passed to the `context` argument of `invoke`/`stream`,
     which replaces the previous pattern of passing application configuration to `config['configurable']`.
@@ -90,7 +90,7 @@ graph.invoke( # (1)!
     from langgraph.runtime import Runtime
 
     # highlight-next-line
-    def node(state: State, config: Runtime[ContextSchema]):
+    def node(state: State, runtime: Runtime[ContextSchema]):
         user_name = runtime.context.user_name
         ...
     ```

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 "Added in version 0.6.0"
+
+:::
+
 ## Advanced model configuration
 
 ### Disable streaming
@@ -281,11 +351,13 @@ If your desired LLM isn't officially supported by LangChain, consider these opti
 :::python
 
 1. **Implement a custom LangChain chat model**: Create a model conforming to the [LangChain chat model interface](https://python.langchain.com/docs/how_to/custom_chat_model/). This enables full compatibility with LangGraph's agents and workflows but requires understanding of the LangChain framework.
+
    :::
 
 :::js
 
 1. **Implement a custom LangChain chat model**: Create a model conforming to the [LangChain chat model interface](https://js.langchain.com/docs/how_to/custom_chat/). This enables full compatibility with LangGraph's agents and workflows but requires understanding of the LangChain framework.
+
    :::
 
 2. **Direct invocation with custom streaming**: Use your model directly by [adding custom streaming logic](../how-tos/streaming.md#use-with-any-llm) with `StreamWriter`.
@@ -301,6 +373,7 @@ If your desired LLM isn't officially supported by LangChain, consider these opti
 - [Force model to call a specific tool](https://python.langchain.com/docs/how_to/tool_choice/)
 - [All chat model how-to guides](https://python.langchain.com/docs/how_to/#chat-models)
 - [Chat model integrations](https://python.langchain.com/docs/integrations/chat/)
+
   :::
 
 :::js
@@ -311,4 +384,5 @@ If your desired LLM isn't officially supported by LangChain, consider these opti
 - [Force model to call a specific tool](https://js.langchain.com/docs/how_to/tool_choice/)
 - [All chat model how-to guides](https://js.langchain.com/docs/how_to/#chat-models)
 - [Chat model integrations](https://js.langchain.com/docs/integrations/chat/)
+
   :::

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)