release(langgraph): v0.5.3 (#5498)

bump

.github/ISSUE_TEMPLATE/config.yml

@@ -1,15 +1,8 @@
-blank_issues_enabled: true
 version: 2.1
 contact_links:
-  - name: 🤔 Question or Problem
-    about: Ask a question or ask about a problem in GitHub Discussions.
-    url: https://github.com/langchain-ai/langgraph/discussions/categories/q-a
   - name: Feature Request
     url: https://github.com/langchain-ai/langgraph/discussions/categories/ideas
     about: Suggest a feature or an idea
-  - name: Show and tell
-    about: Show what you built with LangChain
-    url: https://github.com/langchain-ai/langgraph/discussions/categories/show-and-tell
   - name: LangChain Forum
     url:  https://forum.langchain.com/
     about: General community discussions and support

.github/workflows/_test_release.yml

@@ -11,6 +11,9 @@ on:
 env:
   PYTHON_VERSION: "3.10"
 
+permissions:
+  contents: read
+
 jobs:
   build:
     if: github.ref == 'refs/heads/main'

.github/workflows/ci.yml

@@ -24,7 +24,6 @@ jobs:
     runs-on: ubuntu-latest
     outputs:
       python: ${{ steps.filter.outputs.python }}
-      sdk-js: ${{ steps.filter.outputs.sdk-js }}
       deps: ${{ steps.filter.outputs.deps }}
     steps:
       - uses: actions/checkout@v4
@@ -40,8 +39,6 @@ jobs:
               - 'libs/checkpoint-sqlite/**'
               - 'libs/checkpoint-postgres/**'
               - 'libs/prebuilt/**'
-            sdk-js:
-              - 'libs/sdk-js/**'
             deps:
               - '**/pyproject.toml'
               - '**/uv.lock'
@@ -152,68 +149,16 @@ jobs:
     uses: ./.github/workflows/_integration_test.yml
     secrets: inherit
 
-  lint-js:
-    needs: changes
-    if: needs.changes.outputs.sdk-js == 'true'
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        working-directory:
-          - "libs/sdk-js"
-    defaults:
-      run:
-        working-directory: ${{ matrix.working-directory }}
-    steps:
-      - uses: actions/checkout@v4
-      - name: Setup Node.js (LTS)
-        uses: actions/setup-node@v4
-        with:
-          node-version: "20"
-          cache: "yarn"
-          cache-dependency-path: ${{ matrix.working-directory }}/yarn.lock
-      - name: Install dependencies
-        run: yarn install
-      - name: Run lint
-        run: yarn lint
-      - name: Build
-        run: yarn build
-
-  test-js:
-    needs: changes
-    if: needs.changes.outputs.sdk-js == 'true'
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        working-directory:
-          - "libs/sdk-js"
-    defaults:
-      run:
-        working-directory: ${{ matrix.working-directory }}
-    steps:
-      - uses: actions/checkout@v4
-      - name: Setup Node.js (LTS)
-        uses: actions/setup-node@v4
-        with:
-          node-version: "20"
-          cache: "yarn"
-          cache-dependency-path: ${{ matrix.working-directory }}/yarn.lock
-      - name: Install dependencies
-        run: yarn install
-      - name: Run tests
-        run: yarn test
-
   ci_success:
     name: "CI Success"
     needs:
       [
         lint,
-        lint-js,
         test,
         test-langgraph,
         check-sdk-methods,
         check-schema,
         integration-test,
-        test-js,
       ]
     if: |
       always()

.github/workflows/pr_lint.yml

@@ -0,0 +1,44 @@
+name: PR Title Lint
+
+permissions:
+  pull-requests: read
+
+on:
+  pull_request:
+    types: [opened, edited, synchronize]
+
+jobs:
+  lint-pr-title:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Validate PR Title
+        uses: amannn/action-semantic-pull-request@v5
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          types: |
+            feat
+            fix
+            docs
+            style
+            refactor
+            perf
+            test
+            build
+            ci
+            chore
+            revert
+            release
+          scopes: |
+            checkpoint
+            checkpoint-postgres
+            checkpoint-sqlite
+            cli
+            langgraph
+            prebuilt
+            scheduler-kafka
+            sdk-py
+            docs
+          requireScope: false
+          ignoreLabels: |
+            ignore-lint-pr-title

.github/workflows/release_js.yml

@@ -1,41 +0,0 @@
-name: JS Release
-
-on:
-  workflow_dispatch:
-
-permissions:
-  contents: read
-
-jobs:
-  publish:
-    # Disallow publishing from branches that aren't `main`.
-    if: github.ref == 'refs/heads/main'
-    runs-on: ubuntu-latest
-
-    strategy:
-      matrix:
-        working-directory:
-          - "libs/sdk-js"
-
-    defaults:
-      run:
-        working-directory: ${{ matrix.working-directory }}
-
-    steps:
-      - uses: actions/checkout@v4
-      # JS Build
-      - name: Use Node.js
-        uses: actions/setup-node@v4
-        with:
-          node-version: "20"
-          cache: "yarn"
-          cache-dependency-path: ${{ matrix.working-directory }}/yarn.lock
-
-      - name: Install dependencies
-        run: yarn install
-      - name: Build
-        run: yarn build
-      - name: Publish package to NPM
-        run: |
-          echo "//registry.npmjs.org/:_authToken=${{ secrets.NPM_TOKEN }}" > .npmrc
-          npm publish

.github/workflows/uv_lock_ugprade.yml

@@ -30,11 +30,11 @@ jobs:
         run: make lock-upgrade
           
       - name: Create Pull Request
-        uses: peter-evans/create-pull-request@v6
+        uses: peter-evans/create-pull-request@v7
         with:
           token: ${{ secrets.GITHUB_TOKEN }}
-          commit-message: "chore: upgrade dependencies with `uv lock --upgrade`"
-          title: "chore: 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`.
             

CONTRIBUTING.md

@@ -60,7 +60,7 @@ In LangGraph, these are often higher level guides that show off end-to-end use c
 Some examples include:
 
 - [Build a Customer Support Bot](https://langchain-ai.github.io/langgraph/tutorials/customer-support/customer-support/)
-- [Build a SQL Agent](https://langchain-ai.github.io/langgraph/tutorials/sql-agent/)
+- [Build a SQL Agent](https://langchain-ai.github.io/langgraph/tutorials/sql/sql-agent/)
 
 Here are some high-level tips on writing a good tutorial:
 

README.md

@@ -74,6 +74,7 @@ While LangGraph can be used standalone, it also integrates seamlessly with any L
 - [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.).
 - [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/tutorials/overview/): 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.
 - [LangChain Academy](https://academy.langchain.com/courses/intro-to-langgraph): Learn the basics of LangGraph in our free, structured course.
 - [Templates](https://langchain-ai.github.io/langgraph/concepts/template_applications/): Pre-built reference apps for common agentic workflows (e.g. ReAct agent, memory, retrieval etc.) that can be cloned and adapted.
 - [Case studies](https://www.langchain.com/built-with-langgraph): Hear how industry leaders use LangGraph to ship AI applications at scale.

docs/.gitignore

@@ -1,4 +1,3 @@
 site/
-docs/cloud/reference/sdk/js_ts_sdk_ref.md
 
 .vercel

docs/Makefile

@@ -1,10 +1,4 @@
-.PHONY: lint-docs format-docs build-docs serve-docs serve-clean-docs clean-docs codespell build-typedoc llms-text build-prebuilt tests
-
-build-typedoc:
-	cd ../libs/sdk-js && yarn install --include-dev && yarn typedoc
-	cd ../libs/sdk-js && yarn --silent concat-md --decrease-title-levels --ignore=js_ts_sdk_ref.md --start-title-level-at 2 docs > ../../docs/docs/cloud/reference/sdk/js_ts_sdk_ref.md 2>/dev/null
-	#  Add links to the monorepo
-	sed -e '1,10s|@langchain/langgraph-sdk|[@langchain/langgraph-sdk](https://github.com/langchain-ai/langgraph/tree/main/libs/sdk-js)|g' docs/cloud/reference/sdk/js_ts_sdk_ref.md > temp_file && mv temp_file docs/cloud/reference/sdk/js_ts_sdk_ref.md
+.PHONY: lint-docs format-docs build-docs serve-docs serve-clean-docs clean-docs codespell llms-text build-prebuilt tests
 
 build-prebuilt:
 	# Use to create an update to date prebuilt page.
@@ -21,7 +15,7 @@ build-prebuilt:
 	fi
 	uv run python -m _scripts.third_party_page.create_third_party_page stats.yml docs/agents/prebuilt.md --language python
 
-build-docs: build-typedoc build-prebuilt
+build-docs: build-prebuilt
 	uv run python -m mkdocs build --clean -f mkdocs.yml --strict
 
 llms-text:
@@ -45,7 +39,7 @@ vercel-build-docs: install-vercel-deps
 serve-clean-docs: clean-docs
 	uv run python -m mkdocs serve -c -f mkdocs.yml --strict -w ../libs/langgraph
 
-serve-docs: build-typedoc
+serve-docs:
 	uv run python -m mkdocs serve -f mkdocs.yml -w ../libs/langgraph  -w ../libs/checkpoint -w ../libs/sdk-py --dirty
 
 clean-docs:

docs/_scripts/generate_llms_text.py

@@ -14,10 +14,7 @@ from mkdocs.structure.pages import Page
 from pydantic import BaseModel, Field
 from yaml import SafeLoader
 
-from _scripts.notebook_hooks import (
-    _on_page_markdown_with_config,
-    _apply_conditional_rendering,
-)
+from _scripts.notebook_hooks import _on_page_markdown_with_config
 
 HERE = os.path.dirname(os.path.abspath(__file__))
 # Get source directory (parent of HERE / docs)

docs/_scripts/notebook_hooks.py

@@ -3,6 +3,7 @@
 Lifecycle events: https://www.mkdocs.org/dev-guide/plugins/#events
 """
 
+import json
 import logging
 import os
 import posixpath
@@ -15,8 +16,8 @@ from mkdocs.structure.files import Files, File
 from mkdocs.structure.pages import Page
 
 from _scripts.generate_api_reference_links import update_markdown_with_imports
-from _scripts.notebook_convert import convert_notebook
 from _scripts.link_map import JS_LINK_MAP
+from _scripts.notebook_convert import convert_notebook
 
 logger = logging.getLogger(__name__)
 logging.basicConfig()
@@ -34,20 +35,20 @@ REDIRECT_MAP = {
     "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",
     # graph-api
-    "how-tos/state-reducers.ipynb": "how-tos/graph-api#define-and-update-state",
-    "how-tos/sequence.ipynb": "how-tos/graph-api#create-a-sequence-of-steps",
-    "how-tos/branching.ipynb": "how-tos/graph-api#create-branches",
-    "how-tos/recursion-limit.ipynb": "how-tos/graph-api#create-and-control-loops",
-    "how-tos/visualization.ipynb": "how-tos/graph-api#visualize-your-graph",
-    "how-tos/input_output_schema.ipynb": "how-tos/graph-api#define-input-and-output-schemas",
-    "how-tos/pass_private_state.ipynb": "how-tos/graph-api#pass-private-state-between-nodes",
-    "how-tos/state-model.ipynb": "how-tos/graph-api#use-pydantic-models-for-graph-state",
-    "how-tos/map-reduce.ipynb": "how-tos/graph-api/#map-reduce-and-the-send-api",
-    "how-tos/command.ipynb": "how-tos/graph-api/#combine-control-flow-and-state-updates-with-command",
-    "how-tos/configuration.ipynb": "how-tos/graph-api/#add-runtime-configuration",
-    "how-tos/node-retries.ipynb": "how-tos/graph-api/#add-retry-policies",
-    "how-tos/return-when-recursion-limit-hits.ipynb": "how-tos/graph-api/#impose-a-recursion-limit",
-    "how-tos/async.ipynb": "how-tos/graph-api/#async",
+    "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",
     # 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",
@@ -55,8 +56,8 @@ REDIRECT_MAP = {
     "how-tos/memory.ipynb": "how-tos/memory/add-memory.md",
     "agents/memory.ipynb": "how-tos/memory/add-memory.md",
     # subgraph how-tos
-    "how-tos/subgraph-transform-state.ipynb": "how-tos/subgraph.ipynb#different-state-schemas",
-    "how-tos/subgraphs-manage-state.ipynb": "how-tos/subgraph.ipynb#add-persistence",
+    "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",
     # 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",
@@ -72,10 +73,11 @@ REDIRECT_MAP = {
     "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",
     # multi-agent how-tos
-    "how-tos/agent-handoffs.ipynb": "how-tos/multi_agent.ipynb#handoffs",
-    "how-tos/multi-agent-network.ipynb": "how-tos/multi_agent.ipynb#use-in-a-multi-agent-system",
-    "how-tos/multi-agent-multi-turn-convo.ipynb": "how-tos/multi_agent.ipynb#multi-turn-conversation",
+    "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",
     # cloud redirects
     "cloud/index.md": "index.md",
     "cloud/how-tos/index.md": "concepts/langgraph_platform",
@@ -99,10 +101,6 @@ REDIRECT_MAP = {
     "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",
-    # Time-travel
-    "how-tos/human_in_the_loop/edit-graph-state.ipynb": "how-tos/human_in_the_loop/time-travel.md",
-    # breakpoints
-    "how-tos/human_in_the_loop/dynamic_breakpoints.ipynb": "how-tos/human_in_the_loop/breakpoints.md",
     # misc
     "prebuilt.md": "agents/prebuilt.md",
     "reference/prebuilt.md": "reference/agents.md",
@@ -124,6 +122,11 @@ REDIRECT_MAP = {
     "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",
 }
 
 
@@ -355,12 +358,16 @@ def _on_page_markdown_with_config(
 
 
 def on_page_markdown(markdown: str, page: Page, **kwargs: Dict[str, Any]):
-    return _on_page_markdown_with_config(
-        markdown,
-        page,
-        add_api_references=True,
-        **kwargs,
+    finalized_markdown = (
+        _on_page_markdown_with_config(
+            markdown,
+            page,
+            add_api_references=True,
+            **kwargs,
+        )
     )
+    page.meta["original_markdown"] = finalized_markdown
+    return finalized_markdown
 
 
 # redirects
@@ -430,20 +437,51 @@ height="0" width="0" style="display:none;visibility:hidden"></iframe></noscript>
     else:
         return html  # fallback if no <body> found
 
+def _inject_markdown_into_html(html: str, page: Page) -> str:
+    """Inject the original markdown content into the HTML page as JSON."""
+    original_markdown = page.meta.get("original_markdown", "")
+    if not original_markdown:
+        return html
+    markdown_data = {
+        "markdown": original_markdown,
+        "title": page.title or "Page Content",
+        "url": page.url or "",
+    }
 
-def on_post_page(output: str, page: Page, config: MkDocsConfig) -> str:
+    # Properly escape the JSON for HTML
+    json_content = json.dumps(markdown_data, ensure_ascii=False)
+
+    json_content = (
+        json_content.replace("</", "\\u003c/")
+        .replace("<script", "\\u003cscript")
+        .replace("</script", "\\u003c/script")
+    )
+
+    script_content = (
+        f'<script id="page-markdown-content" '
+        f'type="application/json">{json_content}</script>'
+    )
+
+    # Insert before </head> if it exists, otherwise before </body>
+    if "</head>" not in html:
+        raise ValueError(
+            "HTML does not contain </head> tag. Cannot inject markdown content."
+        )
+    return html.replace("</head>", f"{script_content}</head>")
+
+def on_post_page(html: str, page: Page, config: MkDocsConfig) -> str:
     """Inject Google Tag Manager noscript tag immediately after <body>.
 
     Args:
-        output: The HTML output of the page.
+        html: The HTML output of the page.
         page: The page instance.
         config: The MkDocs configuration object.
 
     Returns:
         modified HTML output with GTM code injected.
     """
-    return _inject_gtm(output)
-
+    html = _inject_markdown_into_html(html, page)
+    return _inject_gtm(html)
 
 # Create HTML files for redirects after site dir has been built
 def on_post_build(config):

docs/docs/additional-resources/index.md

@@ -0,0 +1,11 @@
+# Additional resources
+
+This section contains additional resources for LangGraph.
+
+- [Community agents](../agents/prebuilt.md): A collection of prebuilt libraries that you can use in your LangGraph applications.
+- [LangGraph Academy](https://academy.langchain.com/courses/intro-to-langgraph): A collection of courses that teach you how to use LangGraph.
+- [Case studies](../adopters.md): A collection of case studies that show how LangGraph is used in production.
+- [FAQ](../concepts/faq.md): A collection of frequently asked questions about LangGraph.
+- [llms.txt](../llms-txt-overview.md): A list of documentation files in the `llms.txt` format that allow LLMs and agents to access our documentation.
+- [LangChain Forum](https://forum.langchain.com/): A place to ask questions and get help from other LangGraph users.
+- [Troubleshooting](../troubleshooting/errors/index.md): A collection of troubleshooting guides for common issues.

docs/docs/adopters.md

@@ -8,24 +8,41 @@ This list of companies using LangGraph and their success stories is compiled fro
 | [AirTop](https://www.airtop.ai/) | Software & Technology (GenAI Native) | Browser automation for AI agents | [Case study, 2024](https://blog.langchain.dev/customers-airtop/) |
 | [AppFolio](https://www.appfolio.com/) | Real Estate | Copilot for domain-specific task | [Case study, 2024](https://blog.langchain.dev/customers-appfolio/) |
 | [Athena Intelligence](https://www.athenaintel.com/) | Software & Technology (GenAI Native) | Research & summarization | [Case study, 2024](https://blog.langchain.dev/customers-athena-intelligence/) |
+| [BlackRock](https://www.blackrock.com/) | Financial Services | Copilot for domain-specific task | [Interrupt talk, 2025](https://youtu.be/oyqeCHFM5U4?feature=shared) |
 | [Captide](https://www.captide.co/) | Software & Technology (GenAI Native) | Data extraction | [Case study, 2025](https://blog.langchain.dev/how-captide-is-redefining-equity-research-with-agentic-workflows-built-on-langgraph-and-langsmith/) |
-| [Cisco Outshift](https://outshift.cisco.com/) | Software & Technology | DevOps | [Blog post, 2025](https://outshift.cisco.com/blog/build-react-agent-application-for-devops-tasks-using-rest-apis) |
+| [Cisco CX](https://www.cisco.com/site/us/en/services/modern-data-center/index.html?CCID=cc005911&DTID=eivtotr001480&OID=srwsas032775) | Software & Technology | Customer support | [Interrupt Talk, 2025](https://youtu.be/gPhyPRtIMn0?feature=shared) |
+| [Cisco Outshift](https://outshift.cisco.com/) | Software & Technology | DevOps | [Video story, 2025](https://www.youtube.com/watch?v=htcb-vGR_x0); [Case study, 2025](https://blog.langchain.com/cisco-outshift/); [Blog post, 2025](https://outshift.cisco.com/blog/build-react-agent-application-for-devops-tasks-using-rest-apis) |
+| [Cisco TAC](https://www.cisco.com/c/en/us/support/index.html) | Software & Technology | Customer support | [Video story, 2025](https://youtu.be/EAj0HBDGqaE?feature=shared) |
+| [City of Hope](https://www.cityofhope.org/) | Non-profit | Copilot for domain-specific task | [Video story, 2025](https://youtu.be/9ABwtK2gIZU?feature=shared) |
 | [C.H. Robinson](https://www.chrobinson.com/en-us/) | Logistics | Automation | [Case study, 2025](https://blog.langchain.dev/customers-chrobinson/) |
+| [Definely](https://www.definely.com/) | Legal | Copilot for domain-specific task | [Case study, 2025](https://blog.langchain.com/customers-definely/) |
+| [Docent Pro](https://docentpro.com/) | Travel | GenAI embedded product experiences | [Case study, 2025](https://blog.langchain.com/customers-docentpro/) |
 | [Elastic](https://www.elastic.co/) | Software & Technology | Copilot for domain-specific task | [Blog post, 2025](https://www.elastic.co/blog/elastic-security-generative-ai-features) |
+| [Exa](https://exa.ai/) | Software & Technology (GenAI Native) | Search | [Case study, 2025](https://blog.langchain.com/exa/) |
 | [GitLab](https://about.gitlab.com/) | Software & Technology | Code generation | [Duo workflow docs](https://handbook.gitlab.com/handbook/engineering/architecture/design-documents/duo_workflow/) |
+| [Harmonic](https://harmonic.ai/) | Software & Technology | Search | [Case study, 2025](https://blog.langchain.com/customers-harmonic/) |
 | [Inconvo](https://inconvo.ai/?ref=blog.langchain.dev) | Software & Technology | Code generation | [Case study, 2025](https://blog.langchain.dev/customers-inconvo/) |
 | [Infor](https://infor.com/) | Software & Technology | GenAI embedded product experiences; customer support; copilot | [Case study, 2025](https://blog.langchain.dev/customers-infor/) |
+| [J.P. Morgan](https://www.jpmorganchase.com/) | Financial Services | Copilot for domain-specific task | [Interrupt talk, 2025](https://youtu.be/yMalr0jiOAc?feature=shared) |
 | [Klarna](https://www.klarna.com/) | Fintech | Copilot for domain-specific task | [Case study, 2025](https://blog.langchain.dev/customers-klarna/) |
 | [Komodo Health](https://www.komodohealth.com/) | Healthcare | Copilot for domain-specific task | [Blog post](https://www.komodohealth.com/perspectives/new-gen-ai-assistant-empowers-the-enterprise/) |
-| [LinkedIn](https://www.linkedin.com/) | Social Media | Code generation; Search & discovery | [Blog post, 2025](https://www.linkedin.com/blog/engineering/ai/practical-text-to-sql-for-data-analytics); [Blog post, 2024](https://www.linkedin.com/blog/engineering/generative-ai/behind-the-platform-the-journey-to-create-the-linkedin-genai-application-tech-stack) |
+| [LinkedIn](https://www.linkedin.com/) | Social Media | Code generation; Search & discovery | [Interrupt talk, 2025](https://youtu.be/NmblVxyBhi8?feature=shared); [Blog post, 2025](https://www.linkedin.com/blog/engineering/ai/practical-text-to-sql-for-data-analytics); [Blog post, 2024](https://www.linkedin.com/blog/engineering/generative-ai/behind-the-platform-the-journey-to-create-the-linkedin-genai-application-tech-stack) |
 | [Minimal](https://gominimal.ai/) | E-commerce | Customer support | [Case study, 2025](https://blog.langchain.dev/how-minimal-built-a-multi-agent-customer-support-system-with-langgraph-langsmith/) |
+| [Modern Treasury](https://www.moderntreasury.com/) | Fintech | GenAI embedded product experiences | [Video story, 2025](https://youtu.be/AwAiffXqaCU?feature=shared) |
+| [Monday](https://monday.com/) | Software & Technology | GenAI embedded product experiences | [Interrupt talk, 2025](https://blog.langchain.dev/how-minimal-built-a-multi-agent-customer-support-system-with-langgraph-langsmith/) |
+| [Morningstar](https://www.morningstar.com/) | Financial Services | Research & summarization | [Video story, 2025](https://youtu.be/6LidoFXCJPs?feature=shared) |
 | [OpenRecovery](https://www.openrecovery.com/) | Healthcare | Copilot for domain-specific task | [Case study, 2024](https://blog.langchain.dev/customers-openrecovery/) |
+| [Pigment](https://www.pigment.com/) | Fintech | GenAI embedded product experiences | [Video story, 2025](https://youtu.be/5JVSO2KYOmE?feature=shared) |
+| [Prosper](https://www.prosper.com/) | Fintech | Customer support | [Video story, 2025](https://youtu.be/9RFNOYtkwsc?feature=shared) |
 | [Qodo](https://www.qodo.ai/) | Software & Technology (GenAI Native) | Code generation | [Blog post, 2025](https://www.qodo.ai/blog/why-we-chose-langgraph-to-build-our-coding-agent/) |
-| [Rakuten](https://www.rakuten.com/) | E-commerce / Fintech | Copilot for domain-specific task | [Blog post, 2025](https://rakuten.today/blog/from-ai-hype-to-real-world-tools-rakuten-teams-up-with-langchain.html) |
+| [Rakuten](https://www.rakuten.com/) | E-commerce / Fintech | Copilot for domain-specific task | [Video story, 2025](https://youtu.be/gD1LIjCkuA8?feature=shared); [Blog post, 2025](https://rakuten.today/blog/from-ai-hype-to-real-world-tools-rakuten-teams-up-with-langchain.html) |
 | [Replit](https://replit.com/) | Software & Technology | Code generation | [Blog post, 2024](https://blog.langchain.dev/customers-replit/); [Breakout agent story, 2024](https://www.langchain.com/breakoutagents/replit); [Fireside chat video, 2024](https://www.youtube.com/watch?v=ViykMqljjxU) |
 | [Rexera](https://www.rexera.com/) | Real Estate (GenAI Native) | Copilot for domain-specific task | [Case study, 2024](https://blog.langchain.dev/customers-rexera/) |
+| [Abu Dhabi Government](https://www.tamm.abudhabi/) | Government | Search | [Case study, 2025](https://blog.langchain.com/customers-abu-dhabi-government/) |
 | [Tradestack](https://www.tradestack.uk/) | Software & Technology (GenAI Native) | Copilot for domain-specific task | [Case study, 2024](https://blog.langchain.dev/customers-tradestack/) |
-| [Uber](https://www.uber.com/) | Transportation | Developer productivity; Code generation | [Presentation, 2024](https://dpe.org/sessions/ty-smith-adam-huda/this-year-in-ubers-ai-driven-developer-productivity-revolution/); [Video, 2024](https://www.youtube.com/watch?v=8rkA5vWUE4Y) |
-| [Unify](https://www.unifygtm.com/) | Software & Technology (GenAI Native) | Copilot for domain-specific task | [Blog post, 2024](https://blog.langchain.dev/unify-launches-agents-for-account-qualification-using-langgraph-and-langsmith/) |
-| [Vizient](https://www.vizientinc.com/) | Healthcare | Copilot for domain-specific task | [Case study, 2025](https://blog.langchain.dev/p/3d2cd58c-13a5-4df9-bd84-7d54ed0ed82c/) |
+| [Uber](https://www.uber.com/) | Transportation | Developer productivity; Code generation | [Interrupt talk, 2025](https://youtu.be/Bugs0dVcNI8?feature=shared); [Presentation, 2024](https://dpe.org/sessions/ty-smith-adam-huda/this-year-in-ubers-ai-driven-developer-productivity-revolution/); [Video, 2024](https://www.youtube.com/watch?v=8rkA5vWUE4Y) |
+| [Unify](https://www.unifygtm.com/) | Software & Technology (GenAI Native) | Copilot for domain-specific task | [Interrupt talk, 2025](https://youtu.be/pKk-LfhujwI?feature=shared); [Blog post, 2024](https://blog.langchain.dev/unify-launches-agents-for-account-qualification-using-langgraph-and-langsmith/) |
+| [Vizient](https://www.vizientinc.com/) | Healthcare | Copilot for domain-specific task | [Video story, 2025](https://www.youtube.com/watch?v=vrjJ6NuyTWA); [Case study, 2025](https://blog.langchain.dev/p/3d2cd58c-13a5-4df9-bd84-7d54ed0ed82c/) |
 | [Vodafone](https://www.vodafone.com/) | Telecommunications | Code generation; internal search | [Case study, 2025](https://blog.langchain.dev/customers-vodafone/) |
+| [WebToon](https://www.webtoons.com/en/) | Media & Entertainment | Data extraction | [Case study, 2025](https://blog.langchain.com/customers-webtoon/) |
+| [11x](https://www.11x.ai/) | Software & Technology (GenAI Native) | Research & outreach | [Interrupt talk, 2025](https://youtu.be/fegwPmaAPQk?feature=shared) |

docs/docs/agents/agents.md

@@ -52,7 +52,7 @@ agent.invoke(
 )
 ```
 
-1. Define a tool for the agent to use. Tools can be defined as vanilla Python functions. For more advanced tool usage and customization, check the [tools](./tools.md) page.
+1. Define a tool for the agent to use. Tools can be defined as vanilla Python functions. For more advanced tool usage and customization, check the [tools](../how-tos/tool-calling.md) page.
 2. Provide a language model for the agent to use. To learn more about configuring language models for the agents, check the [models](./models.md) page.
 3. Provide a list of tools for the model to use.
 4. Provide a system prompt (instructions) to the language model used by the agent.

docs/docs/agents/evals.md

@@ -15,7 +15,7 @@ To evaluate your agent's performance you can use `LangSmith` [evaluations](https
 def evaluator(*, outputs: dict, reference_outputs: dict):
     # compare agent outputs against reference outputs
     output_messages = outputs["messages"]
-    reference_messages = reference["messages"]
+    reference_messages = reference_outputs["messages"]
     score = compare_messages(output_messages, reference_messages)
     return {"key": "evaluator_score", "score": score}
 ```

docs/docs/agents/mcp.md

@@ -9,21 +9,12 @@ hide:
 
 # Use MCP
 
-[Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction) is an open protocol that standardizes how applications provide tools and context to language models. LangGraph agents can use tools defined on MCP servers through the `langchain-mcp-adapters` library.
-
-![MCP](./assets/mcp.png)
-
-Install the `langchain-mcp-adapters` library to use MCP tools in LangGraph:
-
-```bash
-pip install langchain-mcp-adapters
-```
+The Model Context Protocol (MCP) is an open protocol that standardizes how applications provide tools and context to language models. LangGraph agents can use tools defined on MCP servers through the `langchain-mcp-adapters` library.
 
 ## Use MCP tools
 
 The `langchain-mcp-adapters` package enables agents to use tools defined across one or more MCP servers.
 
-
 === "In an agent"
 
     ```python title="Agent using tools defined on MCP servers"

docs/docs/agents/models.md

@@ -7,7 +7,7 @@ LangGraph provides built-in support for [LLMs (language models)](https://python.
 
 Use [`init_chat_model`](https://python.langchain.com/docs/how_to/chat_models_universal_init/) to initialize models:
 
-{!snippets/chat_model_tabs.md!}
+{% include-markdown "../../snippets/chat_model_tabs.md" %}
 
 ### Instantiate a model directly
 

docs/docs/agents/overview.md

@@ -30,7 +30,7 @@ LangGraph includes several capabilities essential for building robust, productio
 - [**Memory integration**](../how-tos/memory/add-memory.md): Native support for *short-term* (session-based) and *long-term* (persistent across sessions) memory, enabling stateful behaviors in chatbots and assistants.
 - [**Human-in-the-loop control**](../concepts/human_in_the_loop.md): Execution can pause *indefinitely* to await human feedback—unlike websocket-based solutions limited to real-time interaction. This enables asynchronous approval, correction, or intervention at any point in the workflow.
 - [**Streaming support**](../how-tos/streaming.md): Real-time streaming of agent state, model tokens, tool outputs, or combined streams.
-- [**Deployment tooling**](./deployment.md): Includes infrastructure-free deployment tools. [**LangGraph Platform**](https://langchain-ai.github.io/langgraph/concepts/langgraph_platform/) supports testing, debugging, and deployment.
+- [**Deployment tooling**](../tutorials/langgraph-platform/local-server.md): Includes infrastructure-free deployment tools. [**LangGraph Platform**](https://langchain-ai.github.io/langgraph/concepts/langgraph_platform/) supports testing, debugging, and deployment.
     - **[Studio](https://langchain-ai.github.io/langgraph/concepts/langgraph_studio/)**: A visual IDE for inspecting and debugging workflows.
     - Supports multiple [**deployment options**](https://langchain-ai.github.io/langgraph/concepts/deployment_options.md) for production.
 
@@ -60,7 +60,7 @@ Use the following tool to visualize the graph generated by
 and to view an outline of the corresponding code.
 It allows you to explore the infrastructure of the agent as defined by the presence of:
 
-* [`tools`](../agents/tools.md): A list of tools (functions, APIs, or other callable objects) that the agent can use to perform tasks.
+* [`tools`](../how-tos/tool-calling.md): A list of tools (functions, APIs, or other callable objects) that the agent can use to perform tasks.
 * [`pre_model_hook`](../how-tos/create-react-agent-manage-message-history.ipynb): A function that is called before the model is invoked. It can be used to condense messages or perform other preprocessing tasks.
 * `post_model_hook`: A function that is called after the model is invoked. It can be used to implement guardrails, human-in-the-loop flows, or other postprocessing tasks.
 * [`response_format`](../agents/agents.md#6-configure-structured-output): A data structure used to constrain the type of the final output, e.g., a `pydantic` `BaseModel`.

docs/docs/agents/tools.md

@@ -1,310 +0,0 @@
----
-search:
-  boost: 2
-tags:
-  - agent
-hide:
-  - tags
----
-
-# Tools
-
-[Tools](https://python.langchain.com/docs/concepts/tools/) are a way to encapsulate a function and its input schema in a way that can be passed to a chat model that supports tool calling. This allows the model to request the execution of this function with specific inputs.
-
-You can either [define your own tools](#define-simple-tools) or use [prebuilt integrations](#prebuilt-tools) that LangChain provides.
-
-## Define simple tools
-
-You can pass a vanilla function to `create_react_agent` to use as a tool:
-
-```python
-from langgraph.prebuilt import create_react_agent
-
-def multiply(a: int, b: int) -> int:
-    """Multiply two numbers."""
-    return a * b
-
-create_react_agent(
-    model="anthropic:claude-3-7-sonnet",
-    tools=[multiply]
-)
-```
-
-`create_react_agent` automatically converts vanilla functions to [LangChain tools](https://python.langchain.com/docs/concepts/tools/#tool-interface).
-
-## Customize tools
-
-For more control over tool behavior, use the `@tool` decorator:
-
-```python
-# highlight-next-line
-from langchain_core.tools import tool
-
-# highlight-next-line
-@tool("multiply_tool", parse_docstring=True)
-def multiply(a: int, b: int) -> int:
-    """Multiply two numbers.
-
-    Args:
-        a: First operand
-        b: Second operand
-    """
-    return a * b
-```
-
-You can also define a custom input schema using Pydantic:
-
-```python
-from pydantic import BaseModel, Field
-
-class MultiplyInputSchema(BaseModel):
-    """Multiply two numbers"""
-    a: int = Field(description="First operand")
-    b: int = Field(description="Second operand")
-
-# highlight-next-line
-@tool("multiply_tool", args_schema=MultiplyInputSchema)
-def multiply(a: int, b: int) -> int:
-    return a * b
-```
-
-For additional customization, refer to the [custom tools guide](https://python.langchain.com/docs/how_to/custom_tools/).
-
-## Hide arguments from the model
-
-Some tools require runtime-only arguments (e.g., user ID or session context) that should not be controllable by the model.
-
-You can put these arguments in the `state` or `config` of the agent, and access
-this information inside the tool:
-
-```python
-from langgraph.prebuilt import InjectedState
-from langgraph.prebuilt.chat_agent_executor import AgentState
-from langchain_core.runnables import RunnableConfig
-
-def my_tool(
-    # This will be populated by an LLM
-    tool_arg: str,
-    # access information that's dynamically updated inside the agent
-    # highlight-next-line
-    state: Annotated[AgentState, InjectedState],
-    # access static data that is passed at agent invocation
-    # highlight-next-line
-    config: RunnableConfig,
-) -> str:
-    """My tool."""
-    do_something_with_state(state["messages"])
-    do_something_with_config(config)
-    ...
-```
-
-## Disable parallel tool calling
-
-Some model providers support executing multiple tools in parallel, but
-allow users to disable this feature.
-
-For supported providers, you can disable parallel tool calling by setting `parallel_tool_calls=False` via the `model.bind_tools()` method:
-
-```python
-from langchain.chat_models import init_chat_model
-
-def add(a: int, b: int) -> int:
-    """Add two numbers"""
-    return a + b
-
-def multiply(a: int, b: int) -> int:
-    """Multiply two numbers."""
-    return a * b
-
-model = init_chat_model("anthropic:claude-3-5-sonnet-latest", temperature=0)
-tools = [add, multiply]
-agent = create_react_agent(
-    # disable parallel tool calls
-    # highlight-next-line
-    model=model.bind_tools(tools, parallel_tool_calls=False),
-    tools=tools
-)
-
-agent.invoke(
-    {"messages": [{"role": "user", "content": "what's 3 + 5 and 4 * 7?"}]}
-)
-```
-
-## Return tool results directly
-
-Use `return_direct=True` to return tool results immediately and stop the agent loop:
-
-```python
-from langchain_core.tools import tool
-
-# highlight-next-line
-@tool(return_direct=True)
-def add(a: int, b: int) -> int:
-    """Add two numbers"""
-    return a + b
-
-agent = create_react_agent(
-    model="anthropic:claude-3-7-sonnet-latest",
-    tools=[add]
-)
-
-agent.invoke(
-    {"messages": [{"role": "user", "content": "what's 3 + 5?"}]}
-)
-```
-
-## Force tool use
-
-To force the agent to use specific tools, you can set the `tool_choice` option in `model.bind_tools()`:
-
-```python
-from langchain_core.tools import tool
-
-# highlight-next-line
-@tool(return_direct=True)
-def greet(user_name: str) -> int:
-    """Greet user."""
-    return f"Hello {user_name}!"
-
-tools = [greet]
-
-agent = create_react_agent(
-    # highlight-next-line
-    model=model.bind_tools(tools, tool_choice={"type": "tool", "name": "greet"}),
-    tools=tools
-)
-
-agent.invoke(
-    {"messages": [{"role": "user", "content": "Hi, I am Bob"}]}
-)
-```
-
-!!! Warning "Avoid infinite loops"
-
-    Forcing tool usage without stopping conditions can create infinite loops. Use one of the following safeguards:
-
-    - Mark the tool with [`return_direct=True`](#return-tool-results-directly) to end the loop after execution.
-    - Set [`recursion_limit`](../concepts/low_level.md#recursion-limit) to restrict the number of execution steps.
-
-## Handle tool errors
-
-By default, the agent will catch all exceptions raised during tool calls and will pass those as tool messages to the LLM. To control how the errors are handled, you can use the prebuilt [`ToolNode`][langgraph.prebuilt.tool_node.ToolNode] — the node that executes tools inside `create_react_agent` — via its `handle_tool_errors` parameter:
-
-=== "Enable error handling (default)"
-
-    ```python
-    from langgraph.prebuilt import create_react_agent
-
-    def multiply(a: int, b: int) -> int:
-        """Multiply two numbers."""
-        if a == 42:
-            raise ValueError("The ultimate error")
-        return a * b
-
-    # Run with error handling (default)
-    agent = create_react_agent(
-        model="anthropic:claude-3-7-sonnet-latest",
-        tools=[multiply]
-    )
-    agent.invoke(
-        {"messages": [{"role": "user", "content": "what's 42 x 7?"}]}
-    )
-    ```
-
-=== "Disable error handling"
-
-    ```python
-    from langgraph.prebuilt import create_react_agent, ToolNode
-
-    def multiply(a: int, b: int) -> int:
-        """Multiply two numbers."""
-        if a == 42:
-            raise ValueError("The ultimate error")
-        return a * b
-
-    # highlight-next-line
-    tool_node = ToolNode(
-        [multiply],
-        # highlight-next-line
-        handle_tool_errors=False  # (1)!
-    )
-    agent_no_error_handling = create_react_agent(
-        model="anthropic:claude-3-7-sonnet-latest",
-        tools=tool_node
-    )
-    agent_no_error_handling.invoke(
-        {"messages": [{"role": "user", "content": "what's 42 x 7?"}]}
-    )
-    ```
-
-    1. This disables error handling (enabled by default). See all available strategies in the [API reference][langgraph.prebuilt.tool_node.ToolNode].
-
-=== "Custom error handling"
-
-    ```python
-    from langgraph.prebuilt import create_react_agent, ToolNode
-
-    def multiply(a: int, b: int) -> int:
-        """Multiply two numbers."""
-        if a == 42:
-            raise ValueError("The ultimate error")
-        return a * b
-
-    # highlight-next-line
-    tool_node = ToolNode(
-        [multiply],
-        # highlight-next-line
-        handle_tool_errors=(
-            "Can't use 42 as a first operand, you must switch operands!"  # (1)!
-        )
-    )
-    agent_custom_error_handling = create_react_agent(
-        model="anthropic:claude-3-7-sonnet-latest",
-        tools=tool_node
-    )
-    agent_custom_error_handling.invoke(
-        {"messages": [{"role": "user", "content": "what's 42 x 7?"}]}
-    )
-    ```
-
-    1. This provides a custom message to send to the LLM in case of an exception. See all available strategies in the [API reference][langgraph.prebuilt.tool_node.ToolNode].
-
-See [API reference][langgraph.prebuilt.tool_node.ToolNode] for more information on different tool error handling options.
-
-## Working with memory
-
-LangGraph allows access to short-term and long-term memory from tools. See [Memory](../how-tos/memory/add-memory.md) guide for more information on:
-
-* how to [read](../how-tos/memory/add-memory.md#read-short-term) from and [write](../how-tos/memory/add-memory.md#write-short-term) to **short-term** memory
-* how to [read](../how-tos/memory/add-memory.md#read-long-term) from and [write](../how-tos/memory/add-memory.md#write-long-term) to **long-term** memory
-
-## Prebuilt tools
-
-You can use prebuilt tools from model providers by passing a dictionary with tool specs to the `tools` parameter of `create_react_agent`. For example, to use the `web_search_preview` tool from OpenAI:
-
-```python
-from langgraph.prebuilt import create_react_agent
-
-agent = create_react_agent(
-    model="openai:gpt-4o-mini", 
-    tools=[{"type": "web_search_preview"}]
-)
-response = agent.invoke(
-    {"messages": ["What was a positive news story from today?"]}
-)
-```
-
-Additionally, LangChain supports a wide range of prebuilt tool integrations for interacting with APIs, databases, file systems, web data, and more. These tools extend the functionality of agents and enable rapid development.
-
-You can browse the full list of available integrations in the [LangChain integrations directory](https://python.langchain.com/docs/integrations/tools/).
-
-Some commonly used tool categories include:
-
-- **Search**: Bing, SerpAPI, Tavily
-- **Code interpreters**: Python REPL, Node.js REPL
-- **Databases**: SQL, MongoDB, Redis
-- **Web data**: Web scraping and browsing
-- **APIs**: OpenWeatherMap, NewsAPI, and others
-
-These integrations can be configured and added to your agents using the same `tools` parameter shown in the examples above.
-

docs/docs/agents/ui.md

@@ -13,7 +13,7 @@ You can use a prebuilt chat UI for interacting with any LangGraph agent through
 
 ## Run agent in UI
 
-First, set up LangGraph API server [locally](./deployment.md#launch-langgraph-server-locally) or deploy your agent on [LangGraph Platform](https://langchain-ai.github.io/langgraph/cloud/quick_start/).
+First, set up LangGraph API server [locally](../tutorials/langgraph-platform/local-server.md) or deploy your agent on [LangGraph Platform](https://langchain-ai.github.io/langgraph/cloud/quick_start/).
 
 Then, navigate to [Agent Chat UI](https://agentchat.vercel.app), or clone the repository and [run the dev server locally](https://github.com/langchain-ai/agent-chat-ui?tab=readme-ov-file#setup):
 
@@ -25,7 +25,7 @@ Then, navigate to [Agent Chat UI](https://agentchat.vercel.app), or clone the re
 
 ## Add human-in-the-loop
 
-Agent Chat UI has full support for [human-in-the-loop](../concepts/human_in_the_loop.md) workflows. To try it out, replace the agent code in `src/agent/graph.py` (from the [deployment](./deployment.md) guide) with this [agent implementation](../how-tos/human_in_the_loop/add-human-in-the-loop.md#add-interrupts-to-any-tool):
+Agent Chat UI has full support for [human-in-the-loop](../concepts/human_in_the_loop.md) workflows. To try it out, replace the agent code in `src/agent/graph.py` (from the [deployment](../tutorials/langgraph-platform/local-server.md) guide) with this [agent implementation](../how-tos/human_in_the_loop/add-human-in-the-loop.md#add-interrupts-to-any-tool):
 
 <video controls src="../assets/interrupt-chat-ui.mp4" type="video/mp4"></video>
 

docs/docs/cloud/concepts/threads.md

@@ -1,12 +0,0 @@
-# Threads
-
-A thread contains the accumulated state of a sequence of [runs](../../concepts/assistants.md#execution). When a run is executed, the [state](../../concepts/low_level.md#state) of the underlying graph of the assistant will be persisted to the thread.
-
-A thread's current and historical state can be retrieved. To persist state, a thread must be created prior to executing a run.
-
-The state of a thread at a particular point in time is called a [checkpoint](../../concepts/persistence.md#checkpoints). Checkpoints are persisted and can be used to restore the state of a thread at a later time.
-
-## Learn more
-
-* For more on threads and checkpoints, see this section of the [LangGraph conceptual guide](../../concepts/persistence.md).
-* The LangGraph Platform API provides several endpoints for creating and managing threads and thread state. See the [API reference](../../cloud/reference/api/api_ref.html#tag/threads) for more details.

docs/docs/cloud/deployment/self_hosted_data_plane.md

@@ -35,7 +35,6 @@ Before deploying, review the [conceptual guide for the Self-Hosted Data Plane](.
 1. Configure your `langgraph-dataplane-values.yaml` file.
 
         config:
-          langgraphPlatformLicenseKey: "" # Your LangGraph Platform license key
           langsmithApiKey: "" # API Key of your Workspace
           langsmithWorkspaceId: "" # Workspace ID
           hostBackendUrl: "https://api.host.langchain.com" # Only override this if on EU

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

@@ -2,7 +2,7 @@
 
 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.
 
-## LangGraph API invoke & resume
+## Dynamic interrupts
 
 === "Python"
 
@@ -305,6 +305,185 @@ To review, edit, and approve tool calls in an agent or workflow, use LangGraph's
         }"
         ```
 
+## 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. 

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

@@ -1,185 +0,0 @@
-# Set breakpoints using Server API
-
-[Breakpoints](../../concepts/breakpoints.md) pause graph execution at defined points and let you step through each stage. They use LangGraph's [**persistence layer**](../../concepts/persistence.md), which saves the graph state after each step.
-
-With breakpoints, you can inspect the graph's state and node inputs at any point. Execution pauses indefinitely until you resume, as the checkpointer preserves the state.
-
-!!! tip
-
-    For conceptual information on breakpoints, see [Breakpoints](../../concepts/breakpoints.md).
-
-## Set static breakpoints
-
-Static breakpoints are triggered either before or after a node executes. You can set static breakpoints by specifying `interrupt_before` and `interrupt_after` at compile time or run time.
-
-=== "Compile time"
-
-    ```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.
-
-=== "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>
-        }"
-        ```
-
-## Example
-
-This example shows how to add **static** breakpoints. See [Use breakpoints](../../how-tos/human_in_the_loop/breakpoints.md) for more options on adding breakpoints.
-
-=== "Python"
-
-    ```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\"
-    }"
-    ```

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

@@ -29,7 +29,7 @@ Click the dropdown next to "Submit" and click the toggle to enable/disable strea
 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/breakpoints.md).
+For more information on breakpoints see [here](../../concepts/human_in_the_loop.md).
 
 ### Submit run
 

docs/docs/cloud/quick_start.md

@@ -154,8 +154,9 @@ You can now test the API:
 
     ```bash
     curl -s --request POST \
-        --url <DEPLOYMENT_URL> \
+        --url <DEPLOYMENT_URL>/runs/stream \
         --header 'Content-Type: application/json' \
+        --header "X-Api-Key: <LANGSMITH API KEY> \
         --data "{
             \"assistant_id\": \"agent\",
             \"input\": {

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

@@ -1,12 +1,12 @@
-# API Reference
+# LangGraph Server API Reference
 
-The LangGraph Platform API reference is available with each deployment at the `/docs` URL path (e.g. `http://localhost:8124/docs`).
+The LangGraph Server API reference is available within each deployment at the `/docs` endpoint (e.g. `http://localhost:8124/docs`).
 
 Click <a href="/langgraph/cloud/reference/api/api_ref.html" target="_blank">here</a> to view the API reference.
 
 ## Authentication
 
-For deployments to LangGraph Platform, authentication is required. Pass the `X-Api-Key` header with each request to the LangGraph Platform API. The value of the header should be set to a valid LangSmith API key for the organization where the API is deployed.
+For deployments to LangGraph Platform, authentication is required. Pass the `X-Api-Key` header with each request to the LangGraph Server. The value of the header should be set to a valid LangSmith API key for the organization where the LangGraph Server is deployed.
 
 Example `curl` command:
 ```shell
@@ -18,5 +18,5 @@ curl --request POST \
   "metadata": {},
   "limit": 10,
   "offset": 0
-}'  
+}'
 ```

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

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

docs/docs/cloud/reference/cli.md

@@ -51,9 +51,10 @@ The LangGraph CLI requires a JSON configuration file that follows this [schema](
     | <span style="white-space: nowrap;">`node_version`</span>     | Specify `node_version: 20` to use LangGraph.js.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
     | <span style="white-space: nowrap;">`pip_config_file`</span>  | Path to `pip` config file.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
     | <span style="white-space: nowrap;">`pip_installer`</span> | _(Added in v0.3)_ Optional. Python package installer selector. It can be set to `"auto"`, `"pip"`, or `"uv"`. From version&nbsp;0.3 onward the default strategy is to run `uv pip`, which typically delivers faster builds while remaining a drop-in replacement. In the uncommon situation where `uv` cannot handle your dependency graph or the structure of your `pyproject.toml`, specify `"pip"` here to revert to the earlier behaviour. |
+    | <span style="white-space: nowrap;">`keep_pkg_tools`</span> | _(Added in v0.3.4)_ Optional. Control whether to retain Python packaging tools (`pip`, `setuptools`, `wheel`) in the final image. Accepted values: <ul><li><code>true</code> : Keep all three tools (skip uninstall).</li><li><code>false</code> / omitted : Uninstall all three tools (default behaviour).</li><li><code>list[str]</code> : Names of tools <strong>to retain</strong>. Each value must be one of "pip", "setuptools", "wheel".</li></ul>. By default, all three tools are uninstalled. |
     | <span style="white-space: nowrap;">`dockerfile_lines`</span> | Array of additional lines to add to Dockerfile following the import from parent image.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
     | <span style="white-space: nowrap;">`checkpointer`</span>   | Configuration for the checkpointer. Contains a `ttl` field which is an object with the following keys: <ul><li>`strategy`: How to handle expired checkpoints (e.g., `"delete"`).</li><li>`sweep_interval_minutes`: How often to check for expired checkpoints (integer).</li><li>`default_ttl`: Default time-to-live for checkpoints in **minutes** (integer). Defines how long checkpoints are kept before the specified strategy is applied.</li></ul> |
-    | <span style="white-space: nowrap;">`http`</span>            | HTTP server configuration with the following fields: <ul><li>`app`: Path to custom Starlette/FastAPI app (e.g., `"./src/agent/webapp.py:app"`). See [custom routes guide](../../how-tos/http/custom_routes.md).</li><li>`disable_assistants`: Disable `/assistants` routes</li><li>`disable_threads`: Disable `/threads` routes</li><li>`disable_runs`: Disable `/runs` routes</li><li>`disable_store`: Disable `/store` routes</li><li>`disable_meta`: Disable `/ok`, `/info`, `/metrics`, and `/docs` routes</li><li>`disable_mcp`: Disable `/mcp` routes</li><li>`cors`: CORS configuration with fields for `allow_origins`, `allow_methods`, `allow_headers`, etc.</li><li>`configurable_headers`: Define which request headers to exclude or include as a run's configurable values.</li></ul> |
+    | <span style="white-space: nowrap;">`http`</span>            | HTTP server configuration with the following fields: <ul><li>`app`: Path to custom Starlette/FastAPI app (e.g., `"./src/agent/webapp.py:app"`). See [custom routes guide](../../how-tos/http/custom_routes.md).</li><li>`cors`: CORS configuration with fields for `allow_origins`, `allow_methods`, `allow_headers`, etc.</li><li>`configurable_headers`: Define which request headers to exclude or include as a run's configurable values.</li><li>`disable_assistants`: Disable `/assistants` routes</li><li>`disable_mcp`: Disable `/mcp` routes</li><li>`disable_meta`: Disable `/ok`, `/info`, `/metrics`, and `/docs` routes</li><li>`disable_runs`: Disable `/runs` routes</li><li>`disable_store`: Disable `/store` routes</li><li>`disable_threads`: Disable `/threads` routes</li><li>`disable_ui`: Disable `/ui` routes</li><li>`disable_webhooks`: Disable webhooks calls on run completion in all routes</li><li>`mount_prefix`: Prefix for mounted routes (e.g., "/my-deployment/api")</li></ul> |
 
 === "JS"
 
@@ -408,6 +409,8 @@ The LangGraph CLI requires a JSON configuration file that follows this [schema](
     | Option                       | Default                   | Description                                                                                                             |
     | ---------------------------- | ------------------------- | ----------------------------------------------------------------------------------------------------------------------- |
     | `--wait`                     |                           | Wait for services to start before returning. Implies --detach                                                           |
+| `--base-image TEXT`          | `langchain/langgraph-api`  | Base image to use for the LangGraph API server. Pin to specific versions using version tags.                            |
+| `--image TEXT`               |                           | Docker image to use for the langgraph-api service. If specified, skips building and uses this image directly.           |
     | `--postgres-uri TEXT`        | Local database            | Postgres URI to use for the database.                                                                                   |
     | `--watch`                    |                           | Restart on file changes                                                                                                 |
     | `--debugger-base-url TEXT`   | `http://127.0.0.1:[PORT]` | URL used by the debugger to access LangGraph API.                                                                       |
@@ -435,6 +438,8 @@ The LangGraph CLI requires a JSON configuration file that follows this [schema](
     | Option                                                                 | Default                   | Description                                                                                                             |
     | ---------------------------------------------------------------------- | ------------------------- | ----------------------------------------------------------------------------------------------------------------------- |
     | <span style="white-space: nowrap;">`--wait`</span>                     |                           | Wait for services to start before returning. Implies --detach                                                           |
+| <span style="white-space: nowrap;">`--base-image TEXT`</span>          | <span style="white-space: nowrap;">`langchain/langgraph-api`</span> | Base image to use for the LangGraph API server. Pin to specific versions using version tags. |
+| <span style="white-space: nowrap;">`--image TEXT`</span>               |                           | Docker image to use for the langgraph-api service. If specified, skips building and uses this image directly. |
     | <span style="white-space: nowrap;">`--postgres-uri TEXT`</span>        | Local database            | Postgres URI to use for the database.                                                                                   |
     | <span style="white-space: nowrap;">`--watch`</span>                    |                           | Restart on file changes                                                                                                 |
     | <span style="white-space: nowrap;">`-c, --config FILE`</span>          | `langgraph.json`          | Path to configuration file declaring dependencies, graphs and environment variables.                                    |

docs/docs/cloud/reference/env_var.md

@@ -10,6 +10,10 @@ This environment variable should be set to `True` if the implementation of a gra
 
 Defaults to `False`.
 
+## `BG_JOB_SHUTDOWN_GRACE_PERIOD_SECS`
+
+Specifies, in seconds, how long the server will wait for background jobs to finish after the queue receives a shutdown signal. After this period, the server will force termination. Defaults to `180` seconds. Set this to ensure jobs have enough time to complete cleanly during shutdown. Added in `langgraph-api==0.2.16`.
+
 ## `BG_JOB_TIMEOUT_SECS`
 
 The timeout of a background run can be increased. However, the infrastructure for a Cloud SaaS deployment enforces a 1 hour timeout limit for API requests. This means the connection between client and server will timeout after 1 hour. This is not configurable.
@@ -18,10 +22,6 @@ A background run can execute for longer than 1 hour, but a client must reconnect
 
 Defaults to `3600`.
 
-## `BG_JOB_SHUTDOWN_GRACE_PERIOD_SECS`
-
-Specifies, in seconds, how long the server will wait for background jobs to finish after the queue receives a shutdown signal. After this period, the server will force termination. Defaults to `3600` seconds. Set this to ensure jobs have enough time to complete cleanly during shutdown. Added in `langgraph-api==0.2.16`.
-
 ## `DD_API_KEY`
 
 Specify `DD_API_KEY` (your [Datadog API Key](https://docs.datadoghq.com/account_management/api-app-keys/)) to automatically enable Datadog tracing for the deployment. Specify other [`DD_*` environment variables](https://ddtrace.readthedocs.io/en/stable/configuration.html) to configure the tracing instrumentation.
@@ -40,6 +40,14 @@ Type of authentication for the LangGraph Server deployment. Valid values: `langs
 
 For deployments to LangGraph Platform, this environment variable is set automatically. For local development or deployments where authentication is handled externally (e.g. self-hosted), set this environment variable to `noop`.
 
+## `LANGGRAPH_POSTGRES_POOL_MAX_SIZE`
+
+Beginning with langgraph-api version `0.2.12`, the maximum size of the Postgres connection pool (per replica) can be controlled using the `LANGGRAPH_POSTGRES_POOL_MAX_SIZE` environment variable. By setting this variable, you can determine the upper bound on the number of simultaneous connections the server will establish with the Postgres database.
+
+For example, if a deployment is scaled up to 10 replicas and `LANGGRAPH_POSTGRES_POOL_MAX_SIZE` is configured to `150`, then up to `1500` connections to Postgres can be established. This is particularly useful for deployments where database resources are limited (or more available) or where you need to tune connection behavior for performance or scaling reasons.
+
+Defaults to `150` connections.
+
 ## `LANGSMITH_RUNS_ENDPOINTS`
 
 For deployments with [self-hosted LangSmith](https://docs.smith.langchain.com/self_hosting) only.
@@ -54,6 +62,10 @@ Set `LANGSMITH_TRACING` to `false` to disable tracing to LangSmith.
 
 Defaults to `true`.
 
+## `LOG_COLOR`
+
+This is mainly relevant in the context of using the dev server via the `langgraph dev` command. Set `LOG_COLOR` to `true` to enable ANSI-colored console output when using the default console renderer. Disabling color output by setting this variable to `false` produces monochrome logs. Defaults to `true`.
+
 ## `LOG_LEVEL`
 
 Configure [log level](https://docs.python.org/3/library/logging.html#logging-levels). Defaults to `INFO`.
@@ -62,9 +74,14 @@ Configure [log level](https://docs.python.org/3/library/logging.html#logging-lev
 
 Set `LOG_JSON` to `true` to render all log messages as JSON objects using the configured `JSONRenderer`. This produces structured logs that can be easily parsed or ingested by log management systems. Defaults to `false`.
 
-## `LOG_COLOR`
+## `MOUNT_PREFIX`
 
-This is mainly relevant in the context of using the dev server via the `langgraph dev` command. Set `LOG_COLOR` to `true` to enable ANSI-colored console output when using the default console renderer. Disabling color output by setting this variable to `false` produces monochrome logs. Defaults to `true`.
+!!! info "Only Allowed in Self-Hosted Deployments"
+    The `MOUNT_PREFIX` environment variable is only allowed in Self-Hosted Deployment models, LangGraph Platform SaaS will not allow this environment variable.
+
+Set `MOUNT_PREFIX` to serve the LangGraph Server under a specific path prefix. This is useful for deployments where the server is behind a reverse proxy or load balancer that requires a specific path prefix.
+
+For example, if the server is to be served under `https://example.com/langgraph`, set `MOUNT_PREFIX` to `/langgraph`.
 
 ## `N_JOBS_PER_WORKER`
 
@@ -94,16 +111,14 @@ Database Connectivity:
 
 - The custom Postgres instance must be accessible by the LangGraph Server. The user is responsible for ensuring connectivity.
 
-## `LANGGRAPH_POSTGRES_POOL_MAX_SIZE`
+## `REDIS_CLUSTER`
 
-Beginning with langgraph-api version `0.2.12`, the maximum size of the Postgres connection pool can be controlled using the `LANGGRAPH_POSTGRES_POOL_MAX_SIZE` environment variable. By setting this variable, you can determine the upper bound on the number of simultaneous connections the server will establish with the Postgres database. This is particularly useful for deployments where database resources are limited (or more available) or where you need to tune connection behavior for performance or scaling reasons. If not specified, the pool size defaults to 150 connections.
+!!! info "Only Allowed in Self-Hosted Deployments"
+    Redis Cluster mode is only available in Self-Hosted Deployment models, LangGraph Platform SaaS will provision a redis instance for you by default.
 
-## `REDIS_URI_CUSTOM`
+Set `REDIS_CLUSTER` to `True` to enable Redis Cluster mode. When enabled, the system will connect to Redis using cluster mode. This is useful when connecting to a Redis Cluster deployment.
 
-!!! info "Only for Self-Hosted Data Plane and Self-Hosted Control Plane"
-    Custom Redis instances are only available for [Self-Hosted Data Plane](../../concepts/langgraph_self_hosted_data_plane.md) and [Self-Hosted Control Plane](../../concepts/langgraph_self_hosted_control_plane.md) deployments.
-
-Specify `REDIS_URI_CUSTOM` to use a custom Redis instance. The value of `REDIS_URI_CUSTOM` must be a valid [Redis connection URI](https://redis-py.readthedocs.io/en/stable/connections.html#redis.Redis.from_url).
+Defaults to `False`.
 
 ## `REDIS_KEY_PREFIX`
 
@@ -114,20 +129,19 @@ Specify a prefix for Redis keys. This allows multiple LangGraph Server instances
 
 Defaults to `''`.
 
-## `REDIS_CLUSTER`
+## `REDIS_URI_CUSTOM`
 
-!!! info "Only Allowed in Self-Hosted Deployments"
-    Redis Cluster mode is only available in Self-Hosted Deployment models, LangGraph Platform SaaS will provision a redis instance for you by default.
+!!! info "Only for Self-Hosted Data Plane and Self-Hosted Control Plane"
+    Custom Redis instances are only available for [Self-Hosted Data Plane](../../concepts/langgraph_self_hosted_data_plane.md) and [Self-Hosted Control Plane](../../concepts/langgraph_self_hosted_control_plane.md) deployments.
 
-Set `REDIS_CLUSTER` to `True` to enable Redis Cluster mode. When enabled, the system will connect to Redis using cluster mode. This is useful when connecting to a Redis Cluster deployment.
+Specify `REDIS_URI_CUSTOM` to use a custom Redis instance. The value of `REDIS_URI_CUSTOM` must be a valid [Redis connection URI](https://redis-py.readthedocs.io/en/stable/connections.html#redis.Redis.from_url).
 
-Defaults to `False`.
+## `RESUMABLE_STREAM_TTL_SECONDS`
 
-## `MOUNT_PREFIX`
+Time-to-live in seconds for resumable stream data in Redis.
 
-!!! info "Only Allowed in Self-Hosted Deployments"
-    The `MOUNT_PREFIX` environment variable is only allowed in Self-Hosted Deployment models, LangGraph Platform SaaS will not allow this environment variable.
+When a run is created and the output is streamed, the stream can be configured to be resumable (e.g. `stream_resumable=True`). If a stream is resumable, output from the stream is temporarily stored in Redis. The TTL for this data can be configured by setting `RESUMABLE_STREAM_TTL_SECONDS`.
 
-Set `MOUNT_PREFIX` to serve the LangGraph Server under a specific path prefix. This is useful for deployments where the server is behind a reverse proxy or load balancer that requires a specific path prefix.
+See the [Python](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/python_sdk_ref/#langgraph_sdk.client.RunsClient.stream) and [JS/TS](https://langchain-ai.github.io/langgraphjs/reference/classes/sdk_client.RunsClient.html#stream) SDKs for more details on how to implement resumable streams.
 
-For example, if the server is to be served under `https://example.com/langgraph`, set `MOUNT_PREFIX` to `/langgraph`.
+Defaults to `120` seconds.

docs/docs/cloud/reference/langgraph_server_changelog.md

@@ -0,0 +1,151 @@
+# LangGraph Server Changelog
+
+[LangGraph Server](../../concepts/langgraph_server.md) is an API platform for creating and managing agent-based applications. It provides built-in persistence, a task queue, and supports deploying, configuring, and running assistants (agentic workflows) at scale. This changelog documents all notable updates, features, and fixes to LangGraph Server releases.
+
+---
+
+## v0.2.86 (2025-07-11)
+- Honored tool descriptions in the `/mcp` endpoint to align with expected functionality.
+
+## v0.2.85 (2025-07-10)
+- Added support for the `on_disconnect` field to `runs/wait` and included disconnect logs for better debugging.
+
+## v0.2.84 (2025-07-09)
+- Removed unnecessary status updates to streamline thread handling and updated version to 0.2.84.
+
+## v0.2.83 (2025-07-09)
+- Reduced the default time-to-live for resumable streams to 2 minutes.
+- Enhanced data submission logic to send data to both Beacon and LangSmith instance based on license configuration.
+- Enabled submission of self-hosted data to a Langsmith instance when the endpoint is configured.
+
+## v0.2.82 (2025-07-03)
+- Addressed a race condition in background runs by implementing a lock using join, ensuring reliable execution across CTEs.
+
+## v0.2.81 (2025-07-03)
+- Optimized run streams by reducing initial wait time to improve responsiveness for older or non-existent runs.
+
+## v0.2.80 (2025-07-03)
+- Corrected parameter passing in the `logger.ainfo()` API call to resolve a TypeError.
+
+## v0.2.79 (2025-07-02)
+- Fixed a JsonDecodeError in checkpointing with remote graph by correcting JSON serialization to handle trailing slashes properly.
+- Introduced a configuration flag to disable webhooks globally across all routes.
+
+## v0.2.78 (2025-07-02)
+- Added timeout retries to webhook calls to improve reliability.
+- Added HTTP request metrics, including a request count and latency histogram, for enhanced monitoring capabilities.
+
+## v0.2.77 (2025-07-02)
+- Added HTTP metrics to improve performance monitoring.
+- Changed the Redis cache delimiter to reduce conflicts with subgraph message names and updated caching behavior.
+
+## v0.2.76 (2025-07-01)
+- Updated Redis cache delimiter to prevent conflicts with subgraph messages.
+
+## v0.2.74 (2025-06-30)
+- Scheduled webhooks in an isolated loop to ensure thread-safe operations and prevent errors with PYTHONASYNCIODEBUG=1.
+
+## v0.2.73 (2025-06-27)
+- Fixed an infinite frame loop issue and removed the dict_parser due to structlog's unexpected behavior.
+- Throw a 409 error on deadlock occurrence during run cancellations to handle lock conflicts gracefully.
+
+## v0.2.72 (2025-06-27)
+- Ensured compatibility with future langgraph versions.
+- Implemented a 409 response status to handle deadlock issues during cancellation.
+
+## v0.2.71 (2025-06-26)
+- Improved logging for better clarity and detail regarding log types.
+
+## v0.2.70 (2025-06-26)
+- Improved error handling to better distinguish and log TimeoutErrors caused by users from internal run timeouts.
+
+## v0.2.69 (2025-06-26)
+- Added sorting and pagination to the crons API and updated schema definitions for improved accuracy.
+
+## v0.2.66 (2025-06-26)
+- Fixed a 404 error when creating multiple runs with the same thread_id using `on_not_exist="create"`.
+
+## v0.2.65 (2025-06-25)
+- Ensured that only fields from `assistant_versions` are returned when necessary.
+- Ensured consistent data types for in-memory and PostgreSQL users, improving internal authentication handling.
+
+## v0.2.64 (2025-06-24)
+- Added descriptions to version entries for better clarity.
+
+## v0.2.62 (2025-06-23)
+- Improved user handling for custom authentication in the JS Studio.
+- Added Prometheus-format run statistics to the metrics endpoint for better monitoring.
+- Added run statistics in Prometheus format to the metrics endpoint.
+
+## v0.2.61 (2025-06-20)
+- Set a maximum idle time for Redis connections to prevent unnecessary open connections.
+
+## v0.2.60 (2025-06-20)
+- Enhanced error logging to include traceback details for dictionary operations.
+- Added a `/metrics` endpoint to expose queue worker metrics for monitoring.
+
+## v0.2.57 (2025-06-18)
+- Removed CancelledError from retriable exceptions to allow local interrupts while maintaining retriability for workers.
+- Introduced middleware to gracefully shut down the server after completing in-flight requests upon receiving a SIGINT.
+- Reduced metadata stored in checkpoint to only include necessary information.
+- Improved error handling in join runs to return error details when present.
+
+## v0.2.56 (2025-06-17)
+- Improved application stability by adding a handler for SIGTERM signals.
+
+## v0.2.55 (2025-06-17)
+- Improved the handling of cancellations in the queue entrypoint.
+- Improved cancellation handling in the queue entry point.
+
+## v0.2.54 (2025-06-16)
+- Enhanced error message for LuaLock timeout during license validation.
+- Fixed the $contains filter in custom auth by requiring an explicit ::text cast and updated tests accordingly.
+- Ensured project and tenant IDs are formatted as UUIDs for consistency.
+
+## v0.2.53 (2025-06-13)
+- Resolved a timing issue to ensure the queue starts only after the graph is registered.
+- Improved performance by setting thread and run status in a single query and enhanced error handling during checkpoint writes.
+- Reduced the default background grace period to 3 minutes.
+
+## v0.2.52 (2025-06-12)
+- Now logging expected graphs when one is omitted to improve traceability.
+- Implemented a time-to-live (TTL) feature for resumable streams.
+- Improved query efficiency and consistency by adding a unique index and optimizing row locking.
+
+## v0.2.51 (2025-06-12)
+- Handled `CancelledError` by marking tasks as ready to retry, improving error management in worker processes.
+- Added LG API version and request ID to metadata and logs for better tracking.
+- Added LG API version and request ID to metadata and logs to improve traceability.
+- Improved database performance by creating indexes concurrently.
+- Ensured postgres write is committed only after the Redis running marker is set to prevent race conditions.
+- Enhanced query efficiency and reliability by adding a unique index on thread_id/running, optimizing row locks, and ensuring deterministic run selection.
+- Resolved a race condition by ensuring Postgres updates only occur after the Redis running marker is set.
+
+## v0.2.46 (2025-06-07)
+- Introduced a new connection for each operation while preserving transaction characteristics in Threads state `update()` and `bulk()` commands.
+
+## v0.2.45 (2025-06-05)
+- Enhanced streaming feature by incorporating tracing contexts.
+- Removed an unnecessary query from the Crons.search function.
+- Resolved connection reuse issue when scheduling next run for multiple cron jobs.
+- Removed an unnecessary query in the Crons.search function to improve efficiency.
+- Resolved an issue with scheduling the next cron run by improving connection reuse.
+
+## v0.2.44 (2025-06-04)
+- Enhanced the worker logic to exit the pipeline before continuing when the Redis message limit is reached.
+- Introduced a ceiling for Redis message size with an option to skip messages larger than 128 MB for improved performance.
+- Ensured the pipeline always closes properly to prevent resource leaks.
+
+## v0.2.43 (2025-06-04)
+- Improved performance by omitting logs in metadata calls and ensuring output schema compliance in value streaming.
+- Ensured the connection is properly closed after use.
+- Aligned output format to strictly adhere to the specified schema.
+- Stopped sending internal logs in metadata requests to improve privacy.
+
+## v0.2.42 (2025-06-04)
+- Added timestamps to track the start and end of a request's run.
+- Added tracer information to the configuration settings.
+- Added support for streaming with tracing contexts.
+
+## v0.2.41 (2025-06-03)
+- Added locking mechanism to prevent errors in pipelined executions.

docs/docs/concepts/agentic_concepts.md

@@ -97,7 +97,7 @@ Parallel processing is vital for efficient multi-agent systems and complex tasks
 - Implementation of map-reduce-like operations
 - Efficient handling of independent subtasks
 
-For practical implementation, see our [map-reduce tutorial](../how-tos/graph-api.ipynb#map-reduce-and-the-send-api)
+For practical implementation, see our [map-reduce tutorial](../how-tos/graph-api.md#map-reduce-and-the-send-api)
 
 ### Subgraphs
 
@@ -107,7 +107,7 @@ For practical implementation, see our [map-reduce tutorial](../how-tos/graph-api
 - Hierarchical organization of agent teams
 - Controlled communication between agents and the main system
 
-Subgraphs communicate with the parent graph through overlapping keys in the state schema. This enables flexible, modular agent design. For implementation details, refer to our [subgraph how-to guide](../how-tos/subgraph.ipynb).
+Subgraphs communicate with the parent graph through overlapping keys in the state schema. This enables flexible, modular agent design. For implementation details, refer to our [subgraph how-to guide](../how-tos/subgraph.md).
 
 ### Reflection
 

docs/docs/concepts/auth.md

@@ -143,6 +143,54 @@ The returned user information is available:
     In many of our tutorials, we will just show the "authorization" parameter to be concise, but you can opt to accept more information as needed
     to implement your custom authentication scheme.
 
+### Agent authentication
+
+Custom authentication permits delegated access. The values you return in  `@auth.authenticate` are added to the run context, giving agents user-scoped credentials lets them access resources on the user’s behalf.
+
+```mermaid
+sequenceDiagram
+  %% Actors
+  participant ClientApp as Client
+  participant AuthProv  as Auth Provider
+  participant LangGraph as LangGraph Backend
+  participant SecretStore as Secret Store
+  participant ExternalService as External Service
+
+  %% Platform login / AuthN
+  ClientApp  ->> AuthProv: 1. Login (username / password)
+  AuthProv   -->> ClientApp: 2. Return token
+  ClientApp  ->> LangGraph: 3. Request with token
+
+  Note over LangGraph: 4. Validate token (@auth.authenticate)
+  LangGraph  -->> AuthProv: 5. Fetch user info
+  AuthProv   -->> LangGraph: 6. Confirm validity
+
+  %% Fetch user tokens from secret store
+  LangGraph  ->> SecretStore: 6a. Fetch user tokens
+  SecretStore -->> LangGraph: 6b. Return tokens
+
+  Note over LangGraph: 7. Apply access control (@auth.on.*)
+
+  %% External Service round-trip
+  LangGraph  ->> ExternalService: 8. Call external service (with header)
+  Note over ExternalService: 9. External service validates header and executes action
+  ExternalService  -->> LangGraph: 10. Service response
+
+  %% Return to caller
+  LangGraph  -->> ClientApp: 11. Return resources 
+```
+
+After authentication, the platform creates a special configuration object that is passed to your graph and all nodes via the configurable context.
+This object contains information about the current user, including any custom fields you return from your [`@auth.authenticate`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.Auth.authenticate) handler.
+
+To enable an agent to act on behalf of the user, use [custom authentication middleware](../how-tos/auth/custom_auth.md). This will allow the agent to interact with external systems like MCP servers, external databases, and even other agents on behalf of the user.
+
+For more information, see the [Use custom auth](../how-tos/auth/custom_auth.md#enable-agent-authentication) guide.
+
+### Agent authentication with MCP
+
+For information on how to authenticate an agent to an MCP server, see the [MCP conceptual guide](../concepts/mcp.md).
+
 ## Authorization
 
 After authentication, LangGraph calls your [`@auth.on`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.Auth.on) handlers to control access to specific resources (e.g., threads, assistants, crons). These handlers can:

docs/docs/concepts/breakpoints.md

@@ -1,18 +0,0 @@
----
-search:
-  boost: 2
----
-
-# Breakpoints
-
-[Breakpoints](../how-tos/human_in_the_loop/breakpoints.md) pause graph execution at defined points and let you step through each stage. They use LangGraph's [**persistence layer**](./persistence.md), which saves the graph state after each step.
-
-With breakpoints, you can inspect the graph's state and node inputs at any point. Execution pauses **indefinitely** until you resume, as the checkpointer preserves the state.
-
-<figure markdown="1">
-![image](img/breakpoints.png){: style="max-height:400px"}
-<figcaption>An example graph consisting of 3 sequential steps with a breakpoint before step_3. </figcaption> </figure>
-
-!!! tip
-
-    For information on how to use breakpoints, see [Set breakpoints](../how-tos/human_in_the_loop/breakpoints.md) and [Set breakpoints using Server API](../cloud/how-tos/human_in_the_loop_breakpoint.md).

docs/docs/concepts/human_in_the_loop.md

@@ -23,9 +23,18 @@ To review, edit, and approve tool calls in an agent or workflow, [use LangGraph'
 
 ## Key capabilities
 
-* **Persistent execution state**: LangGraph allows you to pause execution **indefinitely** — for minutes, hours, or even days—until human input is received. This is possible because LangGraph checkpoints the graph state after each step, which allows the system to persist execution context and later resume the workflow, continuing from where it left off. This supports asynchronous human review or input without time constraints.
+* **Persistent execution state**: Interrupts use LangGraph's [persistence](../../concepts/persistence.md) layer, which saves the graph state, to indefinitely pause graph execution until you resume. This is possible because LangGraph checkpoints the graph state after each step, which allows the system to persist execution context and later resume the workflow, continuing from where it left off. This supports asynchronous human review or input without time constraints.
 
-* **Flexible integration points**: HIL logic can be introduced at any point in the workflow. This allows targeted human involvement, such as approving API calls, correcting outputs, or guiding conversations.
+    There are two ways to pause a graph:
+
+    - [Dynamic interrupts](../how-tos/human_in_the_loop/add-human-in-the-loop.md#pause-using-interrupt): Use `interrupt` to pause a graph from inside a specific node, based on the current state of the graph.
+    - [Static interrupts](../how-tos/human_in_the_loop/add-human-in-the-loop.md#debug-with-interrupts): Use `interrupt_before` and `interrupt_after` to pause the graph at defined points, either before or after a node executes.
+
+    <figure markdown="1">
+    ![image](./img/breakpoints.png){: style="max-height:400px"}
+    <figcaption>An example graph consisting of 3 sequential steps with a breakpoint before step_3. </figcaption> </figure>
+
+* **Flexible integration points**: Human-in-the-loop logic can be introduced at any point in the workflow. This allows targeted human involvement, such as approving API calls, correcting outputs, or guiding conversations.
 
 ## Patterns
 

docs/docs/concepts/langgraph_control_plane.md

@@ -26,7 +26,7 @@ The Control Plane UI is embedded in [LangSmith](https://docs.smith.langchain.com
 
 ## Control Plane API
 
-This section describes data model of the control plane API. The API is used to create, update, and delete deployments. However, they are not publicly accessible.
+This section describes the data model of the control plane API. The API is used to create, update, and delete deployments. See the [control plane API reference](../cloud/reference/api/api_ref_control_plane.md) for more details.
 
 ### Deployment
 
@@ -34,11 +34,7 @@ A deployment is an instance of a LangGraph Server. A single deployment can have
 
 ### Revision
 
-A revision is an iteration of a deployment. When a new deployment is created, an initial revision is automatically created. To deploy code changes or update environment variables for a deployment, a new revision must be created.
-
-### Environment Variable
-
-Environment variables are set for a deployment. All environment variables are stored as secrets (i.e. saved in a secrets store).
+A revision is an iteration of a deployment. When a new deployment is created, an initial revision is automatically created. To deploy code changes or update secrets for a deployment, a new revision must be created.
 
 ## Control Plane Features
 
@@ -50,21 +46,40 @@ For simplicity, the control plane offers two deployment types with different res
 
 | **Deployment Type** | **CPU/Memory**  | **Scaling**         | **Database**                                                                     |
 |---------------------|-----------------|---------------------|----------------------------------------------------------------------------------|
-| Development         | 1 CPU, 1 GB RAM | Up to 1 container   | 10 GB disk, no backups                                                           |
-| Production          | 2 CPU, 2 GB RAM | Up to 10 containers | Autoscaling disk, automatic backups, highly available (multi-zone configuration) |
+| Development         | 1 CPU, 1 GB RAM | Up to 1 replica   | 10 GB disk, no backups                                                           |
+| Production          | 2 CPU, 2 GB RAM | Up to 10 replicas | Autoscaling disk, automatic backups, highly available (multi-zone configuration) |
 
-CPU and memory resources are per container.
+CPU and memory resources are per replica.
 
 !!! warning "Immutable Deployment Type"
 
     Once a deployment is created, the deployment type cannot be changed.
 
-!!! info "Resource Customization"
-    For `Production` type deployments, resources can be manually increased on a case-by-case basis depending on use case and capacity constraints. Contact support@langchain.dev to request an increase in resources.
+!!! info "Self-Hosted Deployment"
+    Resources for [Self-Hosted Data Plane](../concepts/langgraph_self_hosted_data_plane.md) and [Self-Hosted Control Plane](../concepts/langgraph_self_hosted_control_plane.md) deployments can be fully customized. Deployment types are only applicable for [Cloud SaaS](../concepts/langgraph_cloud.md) deployments.
 
-    For `Development` types deployments, database disk size can be manually increased on a case-by-case basis depending on use case and capacity constraints. For most use cases, [TTLs](../how-tos/ttl/configure_ttl.md) should be configured to manage disk usage. Contact support@langchain.dev to request an increase in resources.
+#### Production
 
-    Resources for [Self-Hosted Data Plane](../concepts/langgraph_self_hosted_data_plane.md) and [Self-Hosted Control Plane](../concepts/langgraph_self_hosted_control_plane.md) deployments can be fully customized.
+`Production` type deployments are suitable for "production" workloads. For example, select `Production` for customer-facing applications in the critical path.
+
+Resources for `Production` type deployments can be manually increased on a case-by-case basis depending on use case and capacity constraints. Contact support@langchain.dev to request an increase in resources.
+
+#### Development
+
+`Development` type deployments are suitable development and testing. For example, select `Development` for internal testing environments. `Development` type deployments are not suitable for "production" workloads.
+
+!!! danger "Preemptible Compute Infrastructure"
+    `Development` type deployments (API server, queue server, and database) are provisioned on preemptible compute infrastructure. This means the compute infrastructure **may be terminated at any time without notice**. This may result in intermittent...
+
+    - Redis connection timeouts/errors
+    - Postgres connection timeouts/errors
+    - Failed or retrying background runs
+    
+    This behavior is expected. Preemptible compute infrastructure **significantly reduces the cost to provision a `Development` type deployment**. By design, LangGraph Server is fault-tolerant. The implementation will automatically attempt to recover from Redis/Postgres connection errors and retry failed background runs.
+
+    `Production` type deployments are provisioned on durable compute infrastructure, not preemptible compute infrastructure.
+
+Database disk size for `Development` type deployments can be manually increased on a case-by-case basis depending on use case and capacity constraints. For most use cases, [TTLs](../how-tos/ttl/configure_ttl.md) should be configured to manage disk usage. Contact support@langchain.dev to request an increase in resources.
 
 ### Database Provisioning
 
@@ -97,6 +112,8 @@ After a deployment is ready, the control plane monitors the deployment and recor
 - Number of container restarts.
 - Number of replicas (this will increase with [autoscaling](../concepts/langgraph_data_plane.md#autoscaling)).
 - [Postgres](../concepts/langgraph_data_plane.md#postgres) CPU, memory usage, and disk usage.
+- [LangGraph Server queue](../concepts/langgraph_server.md#persistence-and-task-queue) pending/active run count.
+- [LangGraph Server API](../concepts/langgraph_server.md) success response count, error response count, and latency.
 
 These metrics are displayed as charts in the Control Plane UI.
 

docs/docs/concepts/langgraph_data_plane.md

@@ -50,6 +50,15 @@ Runs in a LangGraph Server may be retried for specific failures (currently only
 
 This section describes various features of the data plane.
 
+### Data Region
+
+!!! info "Only for Cloud SaaS"
+    Data regions are only applicable for [Cloud SaaS](../concepts/langgraph_cloud.md) deployments.
+
+Deployments can be created in 2 data regions: US and EU
+
+The data region for a deployment is implied by the data region of the LangSmith organization where the deployment is created. Deployments and the underlying database for the deployments cannot be migrated between data regions.
+
 ### Autoscaling
 
 [`Production` type](../concepts/langgraph_control_plane.md#deployment-types) deployments automatically scale up to 10 containers. Scaling is based on 3 metrics:

docs/docs/concepts/low_level.md

@@ -45,9 +45,9 @@ The first thing you do when you define a graph is define the `State` of the grap
 
 ### Schema
 
-The main documented way to specify the schema of a graph is by using `TypedDict`. However, we also support [using a Pydantic BaseModel](../how-tos/graph-api.ipynb#use-pydantic-models-for-graph-state) as your graph state to add **default values** and additional data validation.
+The main documented way to specify the schema of a graph is by using `TypedDict`. However, we also support [using a Pydantic BaseModel](../how-tos/graph-api.md#use-pydantic-models-for-graph-state) as your graph state to add **default values** and additional data validation.
 
-By default, the graph will have the same input and output schemas. If you want to change this, you can also specify explicit input and output schemas directly. This is useful when you have a lot of keys, and some are explicitly for input and others for output. See the [guide here](../how-tos/graph-api.ipynb#define-input-and-output-schemas) for how to use.
+By default, the graph will have the same input and output schemas. If you want to change this, you can also specify explicit input and output schemas directly. This is useful when you have a lot of keys, and some are explicitly for input and others for output. See the [guide here](../how-tos/graph-api.md#define-input-and-output-schemas) for how to use.
 
 #### Multiple schemas
 
@@ -56,9 +56,9 @@ Typically, all graph nodes communicate with a single schema. This means that the
 - Internal nodes can pass information that is not required in the graph's input / output.
 - We may also want to use different input / output schemas for the graph. The output might, for example, only contain a single relevant output key.
 
-It is possible to have nodes write to private state channels inside the graph for internal node communication. We can simply define a private schema, `PrivateState`. See [this guide](../how-tos/graph-api.ipynb#pass-private-state-between-nodes) for more detail.
+It is possible to have nodes write to private state channels inside the graph for internal node communication. We can simply define a private schema, `PrivateState`. See [this guide](../how-tos/graph-api.md#pass-private-state-between-nodes) for more detail.
 
-It is also possible to define explicit input and output schemas for a graph. In these cases, we define an "internal" schema that contains _all_ keys relevant to graph operations. But, we also define `input` and `output` schemas that are sub-sets of the "internal" schema to constrain the input and output of the graph. See [this guide](../how-tos/graph-api.ipynb#define-input-and-output-schemas) for more detail.
+It is also possible to define explicit input and output schemas for a graph. In these cases, we define an "internal" schema that contains _all_ keys relevant to graph operations. But, we also define `input` and `output` schemas that are sub-sets of the "internal" schema to constrain the input and output of the graph. See [this guide](../how-tos/graph-api.md#define-input-and-output-schemas) for more detail.
 
 Let's look at an example:
 
@@ -406,7 +406,7 @@ def my_node(state: State) -> Command[Literal["my_other_node"]]:
 
     When returning `Command` in your node functions, you must add return type annotations with the list of node names the node is routing to, e.g. `Command[Literal["my_other_node"]]`. This is necessary for the graph rendering and tells LangGraph that `my_node` can navigate to `my_other_node`.
 
-Check out this [how-to guide](../how-tos/graph-api.ipynb#combine-control-flow-and-state-updates-with-command) for an end-to-end example of how to use `Command`.
+Check out this [how-to guide](../how-tos/graph-api.md#combine-control-flow-and-state-updates-with-command) for an end-to-end example of how to use `Command`.
 
 ### When should I use Command instead of conditional edges?
 
@@ -433,17 +433,17 @@ def my_node(state: State) -> Command[Literal["other_subgraph"]]:
 
 !!! important "State updates with `Command.PARENT`"
 
-    When you send updates from a subgraph node to a parent graph node for a key that's shared by both parent and subgraph [state schemas](#schema), you **must** define a [reducer](#reducers) for the key you're updating in the parent graph state. See this [example](../how-tos/graph-api.ipynb#navigate-to-a-node-in-a-parent-graph).
+    When you send updates from a subgraph node to a parent graph node for a key that's shared by both parent and subgraph [state schemas](#schema), you **must** define a [reducer](#reducers) for the key you're updating in the parent graph state. See this [example](../how-tos/graph-api.md#navigate-to-a-node-in-a-parent-graph).
 
 This is particularly useful when implementing [multi-agent handoffs](./multi_agent.md#handoffs).
 
-Check out [this guide](../how-tos/graph-api.ipynb#navigate-to-a-node-in-a-parent-graph) for detail.
+Check out [this guide](../how-tos/graph-api.md#navigate-to-a-node-in-a-parent-graph) for detail.
 
 ### Using inside tools
 
 A common use case is updating graph state from inside a tool. For example, in a customer support application you might want to look up customer information based on their account number or ID in the beginning of the conversation.
 
-Refer to [this guide](../how-tos/graph-api.ipynb#use-inside-tools) for detail.
+Refer to [this guide](../how-tos/graph-api.md#use-inside-tools) for detail.
 
 ### Human-in-the-loop
 
@@ -489,7 +489,7 @@ def node_a(state, config):
     ...
 ```
 
-See [this guide](../how-tos/graph-api.ipynb#add-runtime-configuration) for a full breakdown on configuration.
+See [this guide](../how-tos/graph-api.md#add-runtime-configuration) for a full breakdown on configuration.
 
 ### Recursion Limit
 
@@ -503,4 +503,4 @@ Read [this how-to](https://langchain-ai.github.io/langgraph/how-tos/recursion-li
 
 ## Visualization
 
-It's often nice to be able to visualize graphs, especially as they get more complex. LangGraph comes with several built-in ways to visualize graphs. See [this how-to guide](../how-tos/graph-api.ipynb#visualize-your-graph) for more info.
+It's often nice to be able to visualize graphs, especially as they get more complex. LangGraph comes with several built-in ways to visualize graphs. See [this how-to guide](../how-tos/graph-api.md#visualize-your-graph) for more info.

docs/docs/concepts/mcp.md

@@ -0,0 +1,57 @@
+# MCP
+
+[Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction) is an open protocol that standardizes how applications provide tools and context to language models. LangGraph agents can use tools defined on MCP servers through the `langchain-mcp-adapters` library.
+
+![MCP](../agents/assets/mcp.png)
+
+Install the `langchain-mcp-adapters` library to use MCP tools in LangGraph:
+
+```bash
+pip install langchain-mcp-adapters
+```
+
+## Authenticate to an MCP server
+
+You can set up [custom authentication middleware](../how-tos/auth/custom_auth.md) to authenticate a user with an MCP server to get access to user-scoped tools within your LangGraph Platform deployment. 
+
+!!! note
+    Custom authentication is a LangGraph Platform feature.
+
+An example architecture for this flow:
+
+```mermaid
+sequenceDiagram
+  %% Actors
+  participant ClientApp as Client
+  participant AuthProv  as Auth Provider
+  participant LangGraph as LangGraph Backend
+  participant SecretStore as Secret Store
+  participant MCPServer as MCP Server
+
+  %% Platform login / AuthN
+  ClientApp  ->> AuthProv: 1. Login (username / password)
+  AuthProv   -->> ClientApp: 2. Return token
+  ClientApp  ->> LangGraph: 3. Request with token
+
+  Note over LangGraph: 4. Validate token (@auth.authenticate)
+  LangGraph  -->> AuthProv: 5. Fetch user info
+  AuthProv   -->> LangGraph: 6. Confirm validity
+
+  %% Fetch user tokens from secret store
+  LangGraph  ->> SecretStore: 6a. Fetch user tokens
+  SecretStore -->> LangGraph: 6b. Return tokens
+
+  Note over LangGraph: 7. Apply access control (@auth.on.*)
+
+  %% MCP round-trip
+  Note over LangGraph: 8. Build MCP client with user token
+  LangGraph  ->> MCPServer: 9. Call MCP tool (with header)
+  Note over MCPServer: 10. MCP validates header and runs tool
+  MCPServer  -->> LangGraph: 11. Tool response
+
+  %% Return to caller
+  LangGraph  -->> ClientApp: 12. Return resources / tool output
+```
+
+For more information, see [MCP endpoint in LangGraph Server](../concepts/server-mcp.md#use-user-scoped-mcp-tools-in-your-deployment).
+

docs/docs/concepts/multi_agent.md

@@ -26,7 +26,7 @@ The primary benefits of using multi-agent systems are:
 There are several ways to connect agents in a multi-agent system:
 
 - **Network**: each agent can communicate with [every other agent](https://langchain-ai.github.io/langgraph/tutorials/multi_agent/multi-agent-collaboration/). Any agent can decide which other agent to call next.
-- **Supervisor**: each agent communicates with a single [supervisor](https://langchain-ai.github.io/langgraph/tutorials/multi_agent/agent_supervisor/) agent. Supervisor agent makes decisions on which agent should be called next.
+- **Supervisor**: each agent communicates with a single [supervisor](../tutorials/multi_agent/agent_supervisor.md) agent. Supervisor agent makes decisions on which agent should be called next.
 - **Supervisor (tool-calling)**: this is a special case of supervisor architecture. Individual agents can be represented as tools. In this case, a supervisor agent uses a tool-calling LLM to decide which of the agent tools to call, as well as the arguments to pass to those agents.
 - **Hierarchical**: you can define a multi-agent system with [a supervisor of supervisors](https://langchain-ai.github.io/langgraph/tutorials/multi_agent/hierarchical_agent_teams/). This is a generalization of the supervisor architecture and allows for more complex control flows.
 - **Custom multi-agent workflow**: each agent communicates with only a subset of agents. Parts of the flow are deterministic, and only some agents can decide which other agents to call next.
@@ -166,7 +166,7 @@ network = builder.compile()
 
 ### Supervisor
 
-In this architecture, we define agents as nodes and add a supervisor node (LLM) that decides which agent nodes should be called next. We use [`Command`](./low_level.md#command) to route execution to the appropriate agent node based on supervisor's decision. This architecture also lends itself well to running multiple agents in parallel or using [map-reduce](../how-tos/graph-api.ipynb#map-reduce-and-the-send-api) pattern.
+In this architecture, we define agents as nodes and add a supervisor node (LLM) that decides which agent nodes should be called next. We use [`Command`](./low_level.md#command) to route execution to the appropriate agent node based on supervisor's decision. This architecture also lends itself well to running multiple agents in parallel or using [map-reduce](../how-tos/graph-api.md#map-reduce-and-the-send-api) pattern.
 
 ```python
 from typing import Literal
@@ -211,7 +211,7 @@ builder.add_edge(START, "supervisor")
 supervisor = builder.compile()
 ```
 
-Check out this [tutorial](https://langchain-ai.github.io/langgraph/tutorials/multi_agent/agent_supervisor/) for an example of supervisor multi-agent architecture.
+Check out this [tutorial](../tutorials/multi_agent/agent_supervisor.md) for an example of supervisor multi-agent architecture.
 
 ### Supervisor (tool-calling)
 
@@ -414,5 +414,5 @@ There are two high-level approaches to achieve that:
 
 An agent might need to have a different state schema from the rest of the agents. For example, a search agent might only need to keep track of queries and retrieved documents. There are two ways to achieve this in LangGraph:
 
-- Define [subgraph](./subgraphs.md) agents with a separate state schema. If there are no shared state keys (channels) between the subgraph and the parent graph, it’s important to [add input / output transformations](../how-tos/subgraph.ipynb#different-state-schemas) so that the parent graph knows how to communicate with the subgraphs.
-- Define agent node functions with a [private input state schema](../how-tos/graph-api.ipynb/#pass-private-state-between-nodes) that is distinct from the overall graph state schema. This allows passing information that is only needed for executing that particular agent.
+- Define [subgraph](./subgraphs.md) agents with a separate state schema. If there are no shared state keys (channels) between the subgraph and the parent graph, it’s important to [add input / output transformations](../how-tos/subgraph.md#different-state-schemas) so that the parent graph knows how to communicate with the subgraphs.
+- Define agent node functions with a [private input state schema](../how-tos/graph-api.md/#pass-private-state-between-nodes) that is distinct from the overall graph state schema. This allows passing information that is only needed for executing that particular agent.

docs/docs/concepts/persistence.md

@@ -5,7 +5,7 @@ search:
 
 # Persistence
 
-LangGraph has a built-in persistence layer, implemented through checkpointers. When you compile graph with a checkpointer, the checkpointer saves a `checkpoint` of the graph state at every super-step. Those checkpoints are saved to a `thread`, which can be accessed after graph execution. Because `threads` allow access to graph's state after execution, several powerful capabilities including human-in-the-loop, memory, time travel, and fault-tolerance are all possible. Below, we'll discuss each of these concepts in more detail. 
+LangGraph has a built-in persistence layer, implemented through checkpointers. When you compile a graph with a checkpointer, the checkpointer saves a `checkpoint` of the graph state at every super-step. Those checkpoints are saved to a `thread`, which can be accessed after graph execution. Because `threads` allow access to graph's state after execution, several powerful capabilities including human-in-the-loop, memory, time travel, and fault-tolerance are all possible. Below, we'll discuss each of these concepts in more detail. 
 
 ![Checkpoints](img/persistence/checkpoints.jpg)
 
@@ -33,7 +33,7 @@ The state of a thread at a particular point in time is called a checkpoint. Chec
 - `metadata`: Metadata associated with this checkpoint.
 - `values`: Values of the state channels at this point in time.
 - `next` A tuple of the node names to execute next in the graph.
-- `tasks`: A tuple of `PregelTask` objects that contain information about next tasks to be executed. If the step was previously attempted, it will include error information. If a graph was interrupted [dynamically](../how-tos/human_in_the_loop/breakpoints.md#dynamic-breakpoints) from within a node, tasks will contain additional data associated with interrupts.
+- `tasks`: A tuple of `PregelTask` objects that contain information about next tasks to be executed. If the step was previously attempted, it will include error information. If a graph was interrupted [dynamically](../how-tos/human_in_the_loop/add-human-in-the-loop.md#pause-using-interrupt) from within a node, tasks will contain additional data associated with interrupts.
 
 Checkpoints are persisted and can be used to restore the state of a thread at a later time.
 
@@ -78,7 +78,7 @@ After we run the graph, we expect to see exactly 4 checkpoints:
 * checkpoint with the outputs of `node_a` `{'foo': 'a', 'bar': ['a']}` and `node_b` as the next node to be executed
 * checkpoint with the outputs of `node_b` `{'foo': 'b', 'bar': ['a', 'b']}` and no next nodes to be executed
 
-Note that we `bar` channel values contain outputs from both nodes as we have a reducer for `bar` channel.
+Note that the `bar` channel values contain outputs from both nodes as we have a reducer for `bar` channel.
 
 ### Get state
 
@@ -525,7 +525,7 @@ When running on LangGraph Platform, encryption is automatically enabled whenever
 
 ### Human-in-the-loop
 
-First, checkpointers facilitate [human-in-the-loop workflows](agentic_concepts.md#human-in-the-loop) workflows by allowing humans to inspect, interrupt, and approve graph steps. Checkpointers are needed for these workflows as the human has to be able to view the state of a graph at any point in time, and the graph has to be to resume execution after the human has made any updates to the state. See [these how-to guides](../how-tos/human_in_the_loop/breakpoints.md) for concrete examples.
+First, checkpointers facilitate [human-in-the-loop workflows](agentic_concepts.md#human-in-the-loop) workflows by allowing humans to inspect, interrupt, and approve graph steps. Checkpointers are needed for these workflows as the human has to be able to view the state of a graph at any point in time, and the graph has to be to resume execution after the human has made any updates to the state. See [the how-to guides](../how-tos/human_in_the_loop/add-human-in-the-loop.md) for examples.
 
 ### Memory
 

docs/docs/concepts/server-mcp.md

@@ -8,8 +8,7 @@ hide:
 
 # MCP endpoint in LangGraph Server
 
-The **Model Context Protocol (MCP)** is an open protocol for describing tools and data sources in a model-agnostic format, enabling LLMs to discover
-and use them via a structured API. 
+The [Model Context Protocol (MCP)](./mcp.md) is an open protocol for describing tools and data sources in a model-agnostic format, enabling LLMs to discover and use them via a structured API. 
 
 [LangGraph Server](./langgraph_server.md) implements MCP using the [Streamable HTTP transport](https://spec.modelcontextprotocol.io/specification/2025-03-26/basic/transports/#streamable-http). This allows LangGraph **agents** to be exposed as **MCP tools**, making them usable with any MCP-compliant client supporting Streamable HTTP.
 
@@ -28,79 +27,6 @@ Install them with:
 pip install "langgraph-api>=0.2.3" "langgraph-sdk>=0.1.61"
 ```
 
-## Exposing an agent as MCP tool
-
-
-When deployed, your agent will appear as a tool in the MCP endpoint
-with this configuration:
-
-- **Tool name**: The agent's name.
-- **Tool description**: The agent's description.
-- **Tool input schema**: The agent's input schema.
-
-### Setting name and description 
-
-You can set the name and description of your agent in `langgraph.json`:
-
-```json
-{
-    "graphs": {
-        "my_agent": {
-            "path": "./my_agent/agent.py:graph",
-            "description": "A description of what the agent does"
-        }
-    },
-    "env": ".env"
-}
-```
-
-After deployment, you can update the name and description using the LangGraph SDK.
-
-### Schema
-
-Define clear, minimal input and output schemas to avoid exposing unnecessary internal complexity to the LLM.
-
-The default [MessagesState](./low_level.md#messagesstate) uses `AnyMessage`, which supports many message types but is too general for direct LLM exposure.
-
-Instead, define **custom agents or workflows** that use explicitly typed input and output structures.
-
-For example, a workflow answering documentation questions might look like this:
-
-```python
-from langgraph.graph import StateGraph, START, END
-from typing_extensions import TypedDict
-
-# Define input schema
-class InputState(TypedDict):
-    question: str
-
-# Define output schema
-class OutputState(TypedDict):
-    answer: str
-
-# Combine input and output
-class OverallState(InputState, OutputState):
-    pass
-
-# Define the processing node
-def answer_node(state: InputState):
-    # Replace with actual logic and do something useful
-    return {"answer": "bye", "question": state["question"]}
-
-# Build the graph with explicit schemas
-builder = StateGraph(OverallState, input_schema=InputState, output_schema=OutputState)
-builder.add_node(answer_node)
-builder.add_edge(START, "answer_node")
-builder.add_edge("answer_node", END)
-graph = builder.compile()
-
-# Run the graph
-print(graph.invoke({"question": "hi"}))
-```
-
-For more details, see the [low-level concepts guide](https://langchain-ai.github.io/langgraph/concepts/low_level/#state).
-
-
 ## Usage overview
 
 To enable MCP:
@@ -201,6 +127,114 @@ Use an MCP-compliant client to connect to the LangGraph server. The following ex
         asyncio.run(main())
     ```
 
+## Expose an agent as MCP tool
+
+When deployed, your agent will appear as a tool in the MCP endpoint
+with this configuration:
+
+- **Tool name**: The agent's name.
+- **Tool description**: The agent's description.
+- **Tool input schema**: The agent's input schema.
+
+### Setting name and description 
+
+You can set the name and description of your agent in `langgraph.json`:
+
+```json
+{
+    "graphs": {
+        "my_agent": {
+            "path": "./my_agent/agent.py:graph",
+            "description": "A description of what the agent does"
+        }
+    },
+    "env": ".env"
+}
+```
+
+After deployment, you can update the name and description using the LangGraph SDK.
+
+### Schema
+
+Define clear, minimal input and output schemas to avoid exposing unnecessary internal complexity to the LLM.
+
+The default [MessagesState](./low_level.md#messagesstate) uses `AnyMessage`, which supports many message types but is too general for direct LLM exposure.
+
+Instead, define **custom agents or workflows** that use explicitly typed input and output structures.
+
+For example, a workflow answering documentation questions might look like this:
+
+```python
+from langgraph.graph import StateGraph, START, END
+from typing_extensions import TypedDict
+
+# Define input schema
+class InputState(TypedDict):
+    question: str
+
+# Define output schema
+class OutputState(TypedDict):
+    answer: str
+
+# Combine input and output
+class OverallState(InputState, OutputState):
+    pass
+
+# Define the processing node
+def answer_node(state: InputState):
+    # Replace with actual logic and do something useful
+    return {"answer": "bye", "question": state["question"]}
+
+# Build the graph with explicit schemas
+builder = StateGraph(OverallState, input_schema=InputState, output_schema=OutputState)
+builder.add_node(answer_node)
+builder.add_edge(START, "answer_node")
+builder.add_edge("answer_node", END)
+graph = builder.compile()
+
+# Run the graph
+print(graph.invoke({"question": "hi"}))
+```
+
+For more details, see the [low-level concepts guide](https://langchain-ai.github.io/langgraph/concepts/low_level/#state).
+
+## Use user-scoped MCP tools in your deployment
+
+!!! tip "Prerequisites"
+
+    You have added your own [custom auth middleware](https://langchain-ai.github.io/langgraph/how-tos/auth/custom_auth/) that populates the `langgraph_auth_user` object, making it accessible through configurable context for every node in your graph. 
+
+To make user-scoped tools available to your LangGraph Platform deployment, start with implementing a snippet like the following: 
+
+```python
+from langchain_mcp_adapters.client import MultiServerMCPClient
+
+def mcp_tools_node(state, config):
+    user = config["configurable"].get("langgraph_auth_user")
+		 # e.g., user["github_token"], user["email"], etc.
+		
+    client = MultiServerMCPClient({
+        "github": {
+            "transport": "streamable_http", # (1)
+            "url": "https://my-github-mcp-server/mcp", # (2)
+            "headers": {
+                "Authorization": f"Bearer {user['github_token']}" 
+            }
+        }
+    })
+    tools = await client.get_tools() # (3)
+    
+    # Your tool-calling logic here
+    
+    tool_messages = ...
+    return {"messages": tool_messages}
+```
+
+1. MCP only supports adding headers to requests made to `streamable_http` and `sse` `transport` servers.
+2. Your MCP server URL.
+3. Get available tools from your MCP server.
+
+_This can also be done by [rebuilding your graph at runtime](https://langchain-ai.github.io/langgraph/cloud/deployment/graph_rebuild/) to have a different configuration for a new run_
 
 ## Session behavior  
 
@@ -210,7 +244,7 @@ The current LangGraph MCP implementation does not support sessions. Each `/mcp`
 
 The `/mcp` endpoint uses the same authentication as the rest of the LangGraph API. Refer to the [authentication guide](./auth.md) for setup details.
 
-## Disabling MCP
+## Disable MCP
 
 To disable the MCP endpoint, set `disable_mcp` to `true` in your `langgraph.json` configuration file:
 
@@ -222,4 +256,4 @@ To disable the MCP endpoint, set `disable_mcp` to `true` in your `langgraph.json
 }
 ```
 
-This will prevent the server from exposing the `/mcp` endpoint.
+This will prevent the server from exposing the `/mcp` endpoint.

docs/docs/concepts/subgraphs.md

@@ -12,7 +12,7 @@ Some reasons for using subgraphs are:
 
 The main question when adding subgraphs is how the parent graph and subgraph communicate, i.e. how they pass the [state](./low_level.md#state) between each other during the graph execution. There are two scenarios:
 
-* parent and subgraph have **shared state keys** in their state [schemas](./low_level.md#state). In this case, you can [include the subgraph as a node in the parent graph](../how-tos/subgraph.ipynb#shared-state-schemas)
+* parent and subgraph have **shared state keys** in their state [schemas](./low_level.md#state). In this case, you can [include the subgraph as a node in the parent graph](../how-tos/subgraph.md#shared-state-schemas)
 
     ```python
     from langgraph.graph import StateGraph, MessagesState, START
@@ -40,7 +40,7 @@ The main question when adding subgraphs is how the parent graph and subgraph com
     graph.invoke({"messages": [{"role": "user", "content": "hi!"}]})
     ```
 
-* parent graph and subgraph have **different schemas** (no shared state keys in their state [schemas](./low_level.md#state)). In this case, you have to [call the subgraph from inside a node in the parent graph](../how-tos/subgraph.ipynb#different-state-schemas): this is useful when the parent graph and the subgraph have different state schemas and you need to transform state before or after calling the subgraph
+* parent graph and subgraph have **different schemas** (no shared state keys in their state [schemas](./low_level.md#state)). In this case, you have to [call the subgraph from inside a node in the parent graph](../how-tos/subgraph.md#different-state-schemas): this is useful when the parent graph and the subgraph have different state schemas and you need to transform state before or after calling the subgraph
 
     ```python
     from typing_extensions import TypedDict, Annotated

docs/docs/concepts/template_applications.md

@@ -64,7 +64,7 @@ To create a new app from a template, use the `langgraph new` command.
 === "JS"
 
     ```bash
-    npx @langchain/langgraph-cli new 
+    npm create langgraph@latest
     ```
 
 ## Next Steps

docs/docs/examples/index.md

@@ -0,0 +1,23 @@
+# Examples
+
+The pages in this section provide end-to-end examples for the following topics:
+
+## General 
+
+- [Template Applications](../concepts/template_applications.md): Create a LangGraph application from a template.
+- [Agentic RAG](../tutorials/rag/langgraph_agentic_rag.md): Build a retrieval agent that can decide when to use a retriever tool.
+- [Agent Supervisor](../tutorials/multi_agent/agent_supervisor.md): Build a supervisor agent that can manage a team of agents.
+- [SQL agent](../tutorials/sql/sql-agent.md): Build a SQL agent that can execute SQL queries and return the results.
+- [Prebuilt chat UI](../agents/ui.md): Use a prebuilt chat UI to interact with any LangGraph agent.
+- [Graph runs in LangSmith](../how-tos/run-id-langsmith.md): Use LangSmith to track and analyze graph runs.
+
+## LangGraph Platform
+
+- [Set up custom authentication](../tutorials/auth/getting_started.md): Set up custom authentication for your LangGraph application.
+- [Make conversations private](../tutorials/auth/resource_auth.md): Make conversations private by using resource-based authentication.
+- [Connect an authentication provider](../tutorials/auth/add_auth_server.md): Connect an authentication provider to your LangGraph application.
+- [Rebuild graph at runtime](../cloud/deployment/graph_rebuild.md): Rebuild a graph at runtime.
+- [Use RemoteGraph](../how-tos/use-remote-graph.md): Use RemoteGraph to deploy your LangGraph application to a remote server.
+- [Deploy CrewAI, AutoGen, and other frameworks](../how-tos/autogen-integration.md): Deploy CrewAI, AutoGen, and other frameworks with LangGraph.
+- [Integrate LangGraph into a React app](../cloud/how-tos/use_stream_react.md)
+- [Implement Generative User Interfaces with LangGraph](../cloud/how-tos/generative_ui_react.md)

docs/docs/guides/index.md

@@ -0,0 +1,40 @@
+# Guides
+
+The pages in this section provide a conceptual overview and how-tos for the following topics:
+
+## LangGraph APIs
+
+- [Graph API](../concepts/low_level.md): Use the Graph API to define workflows using a graph paradigm.
+- [Functional API](../concepts/functional_api.md): Use Functional API to build workflows using a functional paradigm without thinking about the graph structure.
+- [Runtime](../concepts/pregel.md): Pregel implements LangGraph's runtime, managing the execution of LangGraph applications.
+
+## Core capabilities
+
+These capabilities are available in both LangGraph OSS and the LangGraph Platform.
+
+- [Streaming](../concepts/streaming.md): Stream outputs from a LangGraph graph.
+- [Persistence](../concepts/persistence.md): Persist the state of a LangGraph graph.
+- [Durable execution](../concepts/durable_execution.md): Save progress at key points in the graph execution.
+- [Memory](../concepts/memory.md): Remember information about previous interactions.
+- [Context](../agents/context.md): Pass outside data to a LangGraph graph to provide context for the graph execution.
+- [Models](../agents/models.md): Integrate various LLMs into your LangGraph application.
+- [Tools](../concepts/tools.md): Interface directly with external systems.
+- [Human-in-the-loop](../concepts/human_in_the_loop.md): Pause a graph and wait for human input at any point in a workflow.
+- [Time travel](../concepts/time-travel.md): Travel back in time to a specific point in the execution of a LangGraph graph.
+- [Subgraphs](../concepts/subgraphs.md): Build modular graphs.
+- [Multi-agent](../concepts/multi_agent.md): Break down a complex workflow into multiple agents.
+- [MCP](../concepts/mcp.md): Use MCP servers in a LangGraph graph.
+- [Evaluation](../agents/evals.md): Use LangSmith to evaluate your graph's performance.
+
+## Platform-only capabilities
+
+These capabilities are only available in [LangGraph Platform](../concepts/langgraph_platform.md).
+
+- [Authentication and access control](../concepts/auth.md): Authenticate and authorize users to access a LangGraph graph.
+- [Assistants](../concepts/assistants.md): Build assistants that can be used to interact with a LangGraph graph.
+- [Double-texting](../concepts/double_texting.md): Handle double-texting (consecutive messages before a first response is returned) in a LangGraph graph.
+- [Webhooks](../cloud/concepts/webhooks.md): Send webhooks to a LangGraph graph.
+- [Cron jobs](../cloud/concepts/cron_jobs.md): Schedule jobs to run at a specific time.
+- [Server customization](../how-tos/http/custom_lifespan.md): Customize the server that runs a LangGraph graph.
+- [Data management](../cloud/concepts/data_storage_and_privacy.md): Manage data in a LangGraph graph.
+- [Deployment](../concepts/deployment_options.md): Deploy a LangGraph graph to a server.

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

@@ -1,138 +1,147 @@
 # Add custom authentication
 
-!!! tip "Prerequisites"
-
-    This guide assumes familiarity with the following concepts:
-
-      *  [**Authentication & Access Control**](../../concepts/auth.md)
-      *  [**LangGraph Platform**](../../concepts/langgraph_platform.md)
-    
-    For a more guided walkthrough, see [**setting up custom authentication**](../../tutorials/auth/getting_started.md) tutorial.
-
-???+ note "Support by deployment type"
-
-    Custom auth is supported for all deployments in the **managed LangGraph Platform**, as well as **Enterprise** self-hosted plans. It is not supported for **Lite** self-hosted plans.
-
 This guide shows how to add custom authentication to your LangGraph Platform application. This guide applies to both LangGraph Platform and self-hosted deployments. It does not apply to isolated usage of the LangGraph open source library in your own custom server.
 
-## 1. Implement authentication
+!!! note
+
+    Custom auth is supported for all **managed LangGraph Platform** deployments, as well as **Enterprise** self-hosted plans. It is not supported for **Lite** self-hosted plans.
+
+## Add custom authentication to your deployment
+
+To leverage custom authentication and access user-level metadata in your deployments, set up custom authentication to automatically populate the `config["configurable"]["langgraph_auth_user"]` object through a custom authentication handler. You can then access this object in your graph with the `langgraph_auth_user` key to [allow an agent to perform authenticated actions on behalf of the user](#enable-agent-authentication).
+
+1. Implement authentication:
+
+    !!! note
+
+        Without a custom `@auth.authenticate` handler, LangGraph sees only the API-key owner (usually the developer), so requests aren’t scoped to individual end-users. To propagate custom tokens, you must implement your own handler.
+
+    ```python
+    from langgraph_sdk import Auth
+    import requests
+
+    auth = Auth()
+
+    def is_valid_key(api_key: str) -> bool:
+        is_valid = # your API key validation logic
+        return is_valid
+
+    @auth.authenticate # (1)!
+    async def authenticate(headers: dict) -> Auth.types.MinimalUserDict:
+        api_key = headers.get("x-api-key")
+        if not api_key or not is_valid_key(api_key):
+            raise Auth.exceptions.HTTPException(status_code=401, detail="Invalid API key")
+        
+        # Fetch user-specific tokens from your secret store  
+        user_tokens = await fetch_user_tokens(api_key)
+
+        return { # (2)!
+            "identity": api_key,  #  fetch user ID from LangSmith 
+            "github_token" : user_tokens.github_token
+            "jira_token" : user_tokens.jira_token
+            # ... custom fields/secrets here
+        }
+    ```
+
+    1. This handler receives the request (headers, etc.), validates the user, and returns a dictionary with at least an identity field.
+    2. You can add any custom fields you want (e.g., OAuth tokens, roles, org IDs, etc.).
+
+2. In your `langgraph.json`, add the path to your auth file:
+
+    ```json hl_lines="7-9"
+    {
+    "dependencies": ["."],
+    "graphs": {
+        "agent": "./agent.py:graph"
+    },
+    "env": ".env",
+    "auth": {
+        "path": "./auth.py:my_auth"
+    }
+    }
+    ```
+
+3. Once you've set up authentication in your server, requests must include the required authorization information based on your chosen scheme. Assuming you are using JWT token authentication, you could access your deployments using any of the following methods:
+
+    === "Python Client"
+
+        ```python
+        from langgraph_sdk import get_client
+
+        my_token = "your-token" # In practice, you would generate a signed token with your auth provider
+        client = get_client(
+            url="http://localhost:2024",
+            headers={"Authorization": f"Bearer {my_token}"}
+        )
+        threads = await client.threads.search()
+        ```
+
+    === "Python RemoteGraph"
+
+        ```python
+        from langgraph.pregel.remote import RemoteGraph
+        
+        my_token = "your-token" # In practice, you would generate a signed token with your auth provider
+        remote_graph = RemoteGraph(
+            "agent",
+            url="http://localhost:2024",
+            headers={"Authorization": f"Bearer {my_token}"}
+        )
+        threads = await remote_graph.ainvoke(...)
+        ```
+
+    === "JavaScript Client"
+
+        ```javascript
+        import { Client } from "@langchain/langgraph-sdk";
+
+        const my_token = "your-token"; // In practice, you would generate a signed token with your auth provider
+        const client = new Client({
+        apiUrl: "http://localhost:2024",
+        defaultHeaders: { Authorization: `Bearer ${my_token}` },
+        });
+        const threads = await client.threads.search();
+        ```
+
+    === "JavaScript RemoteGraph"
+
+        ```javascript
+        import { RemoteGraph } from "@langchain/langgraph/remote";
+
+        const my_token = "your-token"; // In practice, you would generate a signed token with your auth provider
+        const remoteGraph = new RemoteGraph({
+        graphId: "agent",
+        url: "http://localhost:2024",
+        headers: { Authorization: `Bearer ${my_token}` },
+        });
+        const threads = await remoteGraph.invoke(...);
+        ```
+
+    === "CURL"
+
+        ```bash
+        curl -H "Authorization: Bearer ${your-token}" http://localhost:2024/threads
+        ```
+
+## Enable agent authentication
+
+After [authentication](#add-custom-authentication-to-your-deployment), the platform creates a special configuration object (`config`) that is passed to LangGraph Platform deployment. This object contains information about the current user, including any custom fields you return from your `@auth.authenticate` handler.
+
+To allow an agent to perform authenticated actions on behalf of the user, access this object in your graph with the `langgraph_auth_user` key:
 
 ```python
-from langgraph_sdk import Auth
-
-my_auth = Auth()
-
-@my_auth.authenticate
-async def authenticate(authorization: str) -> str:
-    token = authorization.split(" ", 1)[-1] # "Bearer <token>"
-    try:
-        # Verify token with your auth provider
-        user_id = await verify_token(token)
-        return user_id
-    except Exception:
-        raise Auth.exceptions.HTTPException(
-            status_code=401,
-            detail="Invalid token"
-        )
-
-# Add authorization rules to actually control access to resources
-@my_auth.on
-async def add_owner(
-    ctx: Auth.types.AuthContext,
-    value: dict,
-):
-    """Add owner to resource metadata and filter by owner."""
-    filters = {"owner": ctx.user.identity}
-    metadata = value.setdefault("metadata", {})
-    metadata.update(filters)
-    return filters
-
-# Assumes you organize information in store like (user_id, resource_type, resource_id)
-@my_auth.on.store()
-async def authorize_store(ctx: Auth.types.AuthContext, value: dict):
-    namespace: tuple = value["namespace"]
-    assert namespace[0] == ctx.user.identity, "Not authorized"
-
+def my_node(state, config):
+    user_config = config["configurable"].get("langgraph_auth_user")
+    # token was resolved during the @auth.authenticate function
+    token = user_config.get("github_token","") 
+    ...
 ```
 
-## 2. Update configuration
+!!! note
+    Fetch user credentials from a secure secret store. Storing secrets in graph state is not recommended.
 
-In your `langgraph.json`, add the path to your auth file:
+## Learn more
 
-```json hl_lines="7-9"
-{
-  "dependencies": ["."],
-  "graphs": {
-    "agent": "./agent.py:graph"
-  },
-  "env": ".env",
-  "auth": {
-    "path": "./auth.py:my_auth"
-  }
-}
-```
-
-## 3. Connect from the client
-
-Once you've set up authentication in your server, requests must include the required authorization information based on your chosen scheme.
-Assuming you are using JWT token authentication, you could access your deployments using any of the following methods:
-
-=== "Python Client"
-
-    ```python
-    from langgraph_sdk import get_client
-
-    my_token = "your-token" # In practice, you would generate a signed token with your auth provider
-    client = get_client(
-        url="http://localhost:2024",
-        headers={"Authorization": f"Bearer {my_token}"}
-    )
-    threads = await client.threads.search()
-    ```
-
-=== "Python RemoteGraph"
-
-    ```python
-    from langgraph.pregel.remote import RemoteGraph
-    
-    my_token = "your-token" # In practice, you would generate a signed token with your auth provider
-    remote_graph = RemoteGraph(
-        "agent",
-        url="http://localhost:2024",
-        headers={"Authorization": f"Bearer {my_token}"}
-    )
-    threads = await remote_graph.ainvoke(...)
-    ```
-
-=== "JavaScript Client"
-
-    ```javascript
-    import { Client } from "@langchain/langgraph-sdk";
-
-    const my_token = "your-token"; // In practice, you would generate a signed token with your auth provider
-    const client = new Client({
-      apiUrl: "http://localhost:2024",
-      defaultHeaders: { Authorization: `Bearer ${my_token}` },
-    });
-    const threads = await client.threads.search();
-    ```
-
-=== "JavaScript RemoteGraph"
-
-    ```javascript
-    import { RemoteGraph } from "@langchain/langgraph/remote";
-
-    const my_token = "your-token"; // In practice, you would generate a signed token with your auth provider
-    const remoteGraph = new RemoteGraph({
-      graphId: "agent",
-      url: "http://localhost:2024",
-      headers: { Authorization: `Bearer ${my_token}` },
-    });
-    const threads = await remoteGraph.invoke(...);
-    ```
-
-=== "CURL"
-
-    ```bash
-    curl -H "Authorization: Bearer ${your-token}" http://localhost:2024/threads
-    ```
+* [Authentication & Access Control](../../concepts/auth.md)
+* [LangGraph Platform](../../concepts/langgraph_platform.md)
+* [Setting up custom authentication tutorial](../../tutorials/auth/getting_started.md)

docs/docs/how-tos/autogen-integration.md

@@ -0,0 +1,321 @@
+# How to integrate LangGraph with AutoGen, CrewAI, and other frameworks
+
+This guide shows how to integrate AutoGen agents with LangGraph to leverage features like persistence, streaming, and memory, and then deploy the integrated solution to LangGraph Platform for scalable production use. In this guide we show how to build a LangGraph chatbot that integrates with AutoGen, but you can follow the same approach with other frameworks.
+
+Integrating AutoGen with LangGraph provides several benefits:
+
+- Enhanced features: Add [persistence](../concepts/persistence.md), [streaming](../concepts/streaming.md), [short and long-term memory](../concepts/memory.md) and more to your AutoGen agents.
+- Multi-agent systems: Build [multi-agent systems](../concepts/multi_agent.md) where individual agents are built with different frameworks.
+- Production deployment: Deploy your integrated solution to [LangGraph Platform](../concepts/langgraph_platform.md) for scalable production use.
+
+## Prerequisites
+
+- Python 3.9+
+- Autogen: `pip install autogen`
+- LangGraph: `pip install langgraph`
+- OpenAI API key
+
+## Setup
+
+Set your your environment:
+
+```python
+import getpass
+import os
+
+
+def _set_env(var: str):
+    if not os.environ.get(var):
+        os.environ[var] = getpass.getpass(f"{var}: ")
+
+
+_set_env("OPENAI_API_KEY")
+```
+
+## 1. Define AutoGen agent
+
+Create an AutoGen agent that can execute code. This example is adapted from AutoGen's [official tutorials](https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_web_info.ipynb):
+
+```python
+import autogen
+import os
+
+config_list = [{"model": "gpt-4o", "api_key": os.environ["OPENAI_API_KEY"]}]
+
+llm_config = {
+    "timeout": 600,
+    "cache_seed": 42,
+    "config_list": config_list,
+    "temperature": 0,
+}
+
+autogen_agent = autogen.AssistantAgent(
+    name="assistant",
+    llm_config=llm_config,
+)
+
+user_proxy = autogen.UserProxyAgent(
+    name="user_proxy",
+    human_input_mode="NEVER",
+    max_consecutive_auto_reply=10,
+    is_termination_msg=lambda x: x.get("content", "").rstrip().endswith("TERMINATE"),
+    code_execution_config={
+        "work_dir": "web",
+        "use_docker": False,
+    },  # Please set use_docker=True if docker is available to run the generated code. Using docker is safer than running the generated code directly.
+    llm_config=llm_config,
+    system_message="Reply TERMINATE if the task has been solved at full satisfaction. Otherwise, reply CONTINUE, or the reason why the task is not solved yet.",
+)
+```
+
+## 2. Create the graph
+
+We will now create a LangGraph chatbot graph that calls AutoGen agent.
+
+```python
+from langchain_core.messages import convert_to_openai_messages
+from langgraph.graph import StateGraph, MessagesState, START
+from langgraph.checkpoint.memory import MemorySaver
+
+def call_autogen_agent(state: MessagesState):
+    # Convert LangGraph messages to OpenAI format for AutoGen
+    messages = convert_to_openai_messages(state["messages"])
+    
+    # Get the last user message
+    last_message = messages[-1]
+    
+    # Pass previous message history as context (excluding the last message)
+    carryover = messages[:-1] if len(messages) > 1 else []
+    
+    # Initiate chat with AutoGen
+    response = user_proxy.initiate_chat(
+        autogen_agent,
+        message=last_message,
+        carryover=carryover
+    )
+    
+    # Extract the final response from the agent
+    final_content = response.chat_history[-1]["content"]
+    
+    # Return the response in LangGraph format
+    return {"messages": {"role": "assistant", "content": final_content}}
+
+# Create the graph with memory for persistence
+checkpointer = MemorySaver()
+
+# Build the graph
+builder = StateGraph(MessagesState)
+builder.add_node("autogen", call_autogen_agent)
+builder.add_edge(START, "autogen")
+
+# Compile with checkpointer for persistence
+graph = builder.compile(checkpointer=checkpointer)
+```
+
+```python
+from IPython.display import display, Image
+
+display(Image(graph.get_graph().draw_mermaid_png()))
+```
+
+![Graph](./assets/autogen-output.png)
+
+## 3. Test the graph locally
+
+Before deploying to LangGraph Platform, you can test the graph locally:
+
+```python
+# pass the thread ID to persist agent outputs for future interactions
+# highlight-next-line
+config = {"configurable": {"thread_id": "1"}}
+
+for chunk in graph.stream(
+    {
+        "messages": [
+            {
+                "role": "user",
+                "content": "Find numbers between 10 and 30 in fibonacci sequence",
+            }
+        ]
+    },
+    # highlight-next-line
+    config,
+):
+    print(chunk)
+```
+
+**Output:**
+```
+user_proxy (to assistant):
+
+Find numbers between 10 and 30 in fibonacci sequence
+
+--------------------------------------------------------------------------------
+assistant (to user_proxy):
+
+To find numbers between 10 and 30 in the Fibonacci sequence, we can generate the Fibonacci sequence and check which numbers fall within this range. Here's a plan:
+
+1. Generate Fibonacci numbers starting from 0.
+2. Continue generating until the numbers exceed 30.
+3. Collect and print the numbers that are between 10 and 30.
+
+...
+```
+
+Since we're leveraging LangGraph's [persistence](https://langchain-ai.github.io/langgraph/concepts/persistence/) features we can now continue the conversation using the same thread ID -- LangGraph will automatically pass previous history to the AutoGen agent:
+
+```python
+for chunk in graph.stream(
+    {
+        "messages": [
+            {
+                "role": "user",
+                "content": "Multiply the last number by 3",
+            }
+        ]
+    },
+    # highlight-next-line
+    config,
+):
+    print(chunk)
+```
+
+**Output:**
+```
+user_proxy (to assistant):
+
+Multiply the last number by 3
+Context: 
+Find numbers between 10 and 30 in fibonacci sequence
+The Fibonacci numbers between 10 and 30 are 13 and 21. 
+
+These numbers are part of the Fibonacci sequence, which is generated by adding the two preceding numbers to get the next number, starting from 0 and 1. 
+
+The sequence goes: 0, 1, 1, 2, 3, 5, 8, 13, 21, 34, ...
+
+As you can see, 13 and 21 are the only numbers in this sequence that fall between 10 and 30.
+
+TERMINATE
+
+--------------------------------------------------------------------------------
+assistant (to user_proxy):
+
+The last number in the Fibonacci sequence between 10 and 30 is 21. Multiplying 21 by 3 gives:
+
+21 * 3 = 63
+
+TERMINATE
+
+--------------------------------------------------------------------------------
+{'call_autogen_agent': {'messages': {'role': 'assistant', 'content': 'The last number in the Fibonacci sequence between 10 and 30 is 21. Multiplying 21 by 3 gives:\n\n21 * 3 = 63\n\nTERMINATE'}}}
+``` 
+
+## 4. Prepare for deployment
+
+To deploy to LangGraph Platform, create a file structure like the following:
+
+```
+my-autogen-agent/
+├── agent.py          # Your main agent code
+├── requirements.txt  # Python dependencies
+└── langgraph.json   # LangGraph configuration
+```
+
+=== "agent.py"
+
+    ```python
+    import os
+    import autogen
+    from langchain_core.messages import convert_to_openai_messages
+    from langgraph.graph import StateGraph, MessagesState, START
+    from langgraph.checkpoint.memory import MemorySaver
+
+    # AutoGen configuration
+    config_list = [{"model": "gpt-4o", "api_key": os.environ["OPENAI_API_KEY"]}]
+
+    llm_config = {
+        "timeout": 600,
+        "cache_seed": 42,
+        "config_list": config_list,
+        "temperature": 0,
+    }
+
+    # Create AutoGen agents
+    autogen_agent = autogen.AssistantAgent(
+        name="assistant",
+        llm_config=llm_config,
+    )
+
+    user_proxy = autogen.UserProxyAgent(
+        name="user_proxy",
+        human_input_mode="NEVER",
+        max_consecutive_auto_reply=10,
+        is_termination_msg=lambda x: x.get("content", "").rstrip().endswith("TERMINATE"),
+        code_execution_config={
+            "work_dir": "/tmp/autogen_work",
+            "use_docker": False,
+        },
+        llm_config=llm_config,
+        system_message="Reply TERMINATE if the task has been solved at full satisfaction.",
+    )
+
+    def call_autogen_agent(state: MessagesState):
+        """Node function that calls the AutoGen agent"""
+        messages = convert_to_openai_messages(state["messages"])
+        last_message = messages[-1]
+        carryover = messages[:-1] if len(messages) > 1 else []
+        
+        response = user_proxy.initiate_chat(
+            autogen_agent,
+            message=last_message,
+            carryover=carryover
+        )
+        
+        final_content = response.chat_history[-1]["content"]
+        return {"messages": {"role": "assistant", "content": final_content}}
+
+    # Create and compile the graph
+    def create_graph():
+        checkpointer = MemorySaver()
+        builder = StateGraph(MessagesState)
+        builder.add_node("autogen", call_autogen_agent)
+        builder.add_edge(START, "autogen")
+        return builder.compile(checkpointer=checkpointer)
+
+    # Export the graph for LangGraph Platform
+    graph = create_graph()
+    ```
+
+=== "requirements.txt"
+
+    ```
+    langgraph>=0.1.0
+    pyautogen>=0.2.0
+    langchain-core>=0.1.0
+    langchain-openai>=0.0.5
+    ```
+
+=== "langgraph.json"
+
+    ```json
+    {
+    "dependencies": ["."],
+    "graphs": {
+        "autogen_agent": "./agent.py:graph"
+    },
+    "env": ".env"
+    }
+    ```
+
+
+## 5. Deploy to LangGraph Platform
+
+Deploy the graph with the LangGraph Platform CLI:
+
+```
+pip install -U langgraph-cli
+```
+
+```
+langgraph deploy --config langgraph.json 
+```

docs/docs/how-tos/autogen-langgraph-platform.ipynb

@@ -1,171 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "8381b6e0-29a6-48c5-b451-5d2549351249",
-   "metadata": {},
-   "source": [
-    "# How to use LangGraph Platform to deploy CrewAI, AutoGen, and other frameworks\n",
-    "\n",
-    "[LangGraph Platform](https://langchain-ai.github.io/langgraph/concepts/langgraph_platform/) provides infrastructure for deploying agents. This integrates seamlessly with LangGraph, but can also work with other frameworks. The way to make this work is to wrap the agent in a single LangGraph node, and have that be the entire graph.\n",
-    "\n",
-    "Doing so will allow you to deploy to LangGraph Platform, and allows you to get a lot of the [benefits](https://langchain-ai.github.io/langgraph/concepts/langgraph_platform/). You get horizontally scalable infrastructure, a task queue to handle bursty operations, a persistence layer to power short term memory, and long term memory support.\n",
-    "\n",
-    "In this guide we show how to do this with an AutoGen agent, but this method should work for agents defined in other frameworks like CrewAI, LlamaIndex, and others as well."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "1113cb16-b538-448c-924c-85731ce96ebd",
-   "metadata": {},
-   "source": [
-    "## Setup"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "f05993fa-9d03-4f45-bc13-0a8d87260d86",
-   "metadata": {
-    "scrolled": true
-   },
-   "outputs": [],
-   "source": [
-    "%pip install autogen langgraph"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "f4e0ca12-1714-4776-a30a-9527e519799b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "\n",
-    "def _set_env(var: str):\n",
-    "    if not os.environ.get(var):\n",
-    "        os.environ[var] = getpass.getpass(f\"{var}: \")\n",
-    "\n",
-    "\n",
-    "_set_env(\"OPENAI_API_KEY\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "1926bbc3-6b06-41e0-9604-860a2bbf8fa3",
-   "metadata": {},
-   "source": [
-    "## Define autogen agent\n",
-    "\n",
-    "Here we define our AutoGen agent. From https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_web_info.ipynb"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "d4a14dc7-d565-4207-8788-525f85b9fb27",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import autogen\n",
-    "import os\n",
-    "\n",
-    "config_list = [{\"model\": \"gpt-4o\", \"api_key\": os.environ[\"OPENAI_API_KEY\"]}]\n",
-    "\n",
-    "llm_config = {\n",
-    "    \"timeout\": 600,\n",
-    "    \"cache_seed\": 42,\n",
-    "    \"config_list\": config_list,\n",
-    "    \"temperature\": 0,\n",
-    "}\n",
-    "\n",
-    "autogen_agent = autogen.AssistantAgent(\n",
-    "    name=\"assistant\",\n",
-    "    llm_config=llm_config,\n",
-    ")\n",
-    "\n",
-    "user_proxy = autogen.UserProxyAgent(\n",
-    "    name=\"user_proxy\",\n",
-    "    human_input_mode=\"NEVER\",\n",
-    "    max_consecutive_auto_reply=10,\n",
-    "    is_termination_msg=lambda x: x.get(\"content\", \"\").rstrip().endswith(\"TERMINATE\"),\n",
-    "    code_execution_config={\n",
-    "        \"work_dir\": \"web\",\n",
-    "        \"use_docker\": False,\n",
-    "    },  # Please set use_docker=True if docker is available to run the generated code. Using docker is safer than running the generated code directly.\n",
-    "    llm_config=llm_config,\n",
-    "    system_message=\"Reply TERMINATE if the task has been solved at full satisfaction. Otherwise, reply CONTINUE, or the reason why the task is not solved yet.\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b1170836-f23e-4e4c-ab83-ce791cd7fbd2",
-   "metadata": {},
-   "source": [
-    "## Wrap in LangGraph\n",
-    "\n",
-    "We now wrap the AutoGen agent in a single LangGraph node, and make that the entire graph.\n",
-    "The main thing this involves is defining an Input and Output schema for the node, which you would need to do if deploying this manually, so it's no extra work"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "7b417c16-ff4e-4d5c-a9a9-0aaeeef6ede5",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph.graph import StateGraph, MessagesState\n",
-    "\n",
-    "\n",
-    "def call_autogen_agent(state: MessagesState):\n",
-    "    last_message = state[\"messages\"][-1]\n",
-    "    response = user_proxy.initiate_chat(autogen_agent, message=last_message.content)\n",
-    "    # get the final response from the agent\n",
-    "    content = response.chat_history[-1][\"content\"]\n",
-    "    return {\"messages\": {\"role\": \"assistant\", \"content\": content}}\n",
-    "\n",
-    "\n",
-    "graph = StateGraph(MessagesState)\n",
-    "graph.add_node(call_autogen_agent)\n",
-    "graph.set_entry_point(\"call_autogen_agent\")\n",
-    "graph = graph.compile()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f6a18377-ac29-478f-a76a-b213f1a3c85d",
-   "metadata": {},
-   "source": [
-    "## Deploy with LangGraph Platform\n",
-    "\n",
-    "You can now deploy this as you normally would with LangGraph Platform. See [these instructions](https://langchain-ai.github.io/langgraph/concepts/deployment_options/) for more details."
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.12.3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

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

@@ -11,11 +11,19 @@ hide:
 
 # Enable human intervention
 
-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.
+To review, edit, and approve tool calls in an agent or workflow, use interrupts to pause a graph and wait for human input. Interrupts use LangGraph's [persistence](../../concepts/persistence.md) layer, which saves the graph state, to indefinitely pause graph execution until you resume.
+
+!!! info
+
+    For more information about human-in-the-loop workflows, see the [Human-in-the-Loop](../../concepts/human_in_the_loop.md) conceptual guide.
 
 ## Pause using `interrupt`
 
-The [`interrupt` function][langgraph.types.interrupt] in LangGraph enables human-in-the-loop workflows by pausing the graph at a specific node, presenting information to a human, and resuming the graph with their input. It's useful for tasks like approvals, edits, or gathering additional context.
+[Dynamic interrupts](../../concepts/human_in_the_loop.md#key-capabilities) (also known as dynamic breakpoints) are triggered based on the current state of the graph. You can set dynamic interrupts by calling [`interrupt` function][langgraph.types.interrupt] in the appropriate place. The graph will pause, which allows for human intervention, and then resumes the graph with their input. It's useful for tasks like approvals, edits, or gathering additional context.
+
+!!! note
+
+    As of v1.0, `interrupt` is the recommended way to pause a graph. `NodeInterrupt` is deprecated and will be removed in v2.0.
 
 To use `interrupt` in your graph, you need to:
 
@@ -138,15 +146,10 @@ print(graph.invoke(Command(resume="Edited text"), config=config)) # (7)!
 
 !!! warning
 
-      Interrupts are both powerful and ergonomic. However, while they may resemble Python's input() function in terms of developer experience, it's important to note that they do not automatically resume execution from the interruption point. Instead, they rerun the entire node where the interrupt was used. For this reason, interrupts are typically best placed at the start of a node or in a dedicated node.
-
+      Interrupts resemble Python's input() function in terms of developer experience, but they do not automatically resume execution from the interruption point. Instead, they rerun the entire node where the interrupt was used. For this reason, interrupts are typically best placed at the start of a node or in a dedicated node.
 
 ## Resume using the `Command` primitive
 
-!!! warning
-
-    Resuming from an `interrupt` is different from Python's `input()` function, where execution resumes from the exact point where the `input()` function was called.
-
 When the `interrupt` function is used within a graph, execution pauses at that point and awaits user input.
 
 To resume execution, use the [`Command`][langgraph.types.Command] primitive, which can be supplied via the `invoke`, `ainvoke`, `stream`, or `astream` methods. The graph resumes execution from the beginning of the node where `interrupt(...)` was initially called. This time, the `interrupt` function will return the value provided in `Command(resume=value)` rather than pausing again. All code from the beginning of the node to the `interrupt` will be re-executed.
@@ -712,6 +715,162 @@ def human_node(state: State):
     print(final_result)  # Should include the valid age
     ```
 
+## Debug with interrupts
+
+To debug and test a graph, use [static interrupts](../../concepts/human_in_the_loop.md#key-capabilities) (also known as static breakpoints) to step through the graph execution one node at a time or to pause the graph execution at specific nodes. Static interrupts are triggered at defined points either before or after a node executes. You can set static interrupts by specifying `interrupt_before` and `interrupt_after` at compile time or run time.
+
+!!! warning
+
+    Static interrupts are **not** recommended for human-in-the-loop workflows. Use [dynamic interrupts](#pause-using-interrupt) instead.
+
+=== "Compile time"
+
+    ```python
+    # highlight-next-line
+    graph = graph_builder.compile( # (1)!
+        # highlight-next-line
+        interrupt_before=["node_a"], # (2)!
+        # highlight-next-line
+        interrupt_after=["node_b", "node_c"], # (3)!
+        checkpointer=checkpointer, # (4)!
+    )
+
+    config = {
+        "configurable": {
+            "thread_id": "some_thread"
+        }
+    }
+
+    # Run the graph until the breakpoint
+    graph.invoke(inputs, config=thread_config) # (5)!
+
+    # Resume the graph
+    graph.invoke(None, config=thread_config) # (6)!
+    ```
+
+    1. The breakpoints are set during `compile` time.
+    2. `interrupt_before` specifies the nodes where execution should pause before the node is executed.
+    3. `interrupt_after` specifies the nodes where execution should pause after the node is executed.
+    4. A checkpointer is required to enable breakpoints.
+    5. The graph is run until the first breakpoint is hit.
+    6. The graph is resumed by passing in `None` for the input. This will run the graph until the next breakpoint is hit.
+
+=== "Run time"
+
+    ```python
+    # highlight-next-line
+    graph.invoke( # (1)!
+        inputs, 
+        # highlight-next-line
+        interrupt_before=["node_a"], # (2)!
+        # highlight-next-line
+        interrupt_after=["node_b", "node_c"] # (3)!
+        config={
+            "configurable": {"thread_id": "some_thread"}
+        }, 
+    )
+
+    config = {
+        "configurable": {
+            "thread_id": "some_thread"
+        }
+    }
+
+    # Run the graph until the breakpoint
+    graph.invoke(inputs, config=config) # (4)!
+
+    # Resume the graph
+    graph.invoke(None, config=config) # (5)!
+    ```
+
+    1. `graph.invoke` is called with the `interrupt_before` and `interrupt_after` parameters. This is a run-time configuration and can be changed for every invocation.
+    2. `interrupt_before` specifies the nodes where execution should pause before the node is executed.
+    3. `interrupt_after` specifies the nodes where execution should pause after the node is executed.
+    4. The graph is run until the first breakpoint is hit.
+    5. The graph is resumed by passing in `None` for the input. This will run the graph until the next breakpoint is hit.
+
+    !!! note
+
+        You cannot set static breakpoints at runtime for **sub-graphs**.
+        If you have a sub-graph, you must set the breakpoints at compilation time.
+
+??? example "Setting static breakpoints"
+
+    ```python
+    from IPython.display import Image, display
+    from typing_extensions import TypedDict
+    
+    from langgraph.checkpoint.memory import InMemorySaver 
+    from langgraph.graph import StateGraph, START, END
+    
+    
+    class State(TypedDict):
+        input: str
+    
+    
+    def step_1(state):
+        print("---Step 1---")
+        pass
+    
+    
+    def step_2(state):
+        print("---Step 2---")
+        pass
+    
+    
+    def step_3(state):
+        print("---Step 3---")
+        pass
+    
+    
+    builder = StateGraph(State)
+    builder.add_node("step_1", step_1)
+    builder.add_node("step_2", step_2)
+    builder.add_node("step_3", step_3)
+    builder.add_edge(START, "step_1")
+    builder.add_edge("step_1", "step_2")
+    builder.add_edge("step_2", "step_3")
+    builder.add_edge("step_3", END)
+    
+    # Set up a checkpointer 
+    checkpointer = InMemorySaver() # (1)!
+    
+    graph = builder.compile(
+        checkpointer=checkpointer, # (2)!
+        interrupt_before=["step_3"] # (3)!
+    )
+    
+    # View
+    display(Image(graph.get_graph().draw_mermaid_png()))
+    
+    
+    # Input
+    initial_input = {"input": "hello world"}
+    
+    # Thread
+    thread = {"configurable": {"thread_id": "1"}}
+    
+    # Run the graph until the first interruption
+    for event in graph.stream(initial_input, thread, stream_mode="values"):
+        print(event)
+        
+    # This will run until the breakpoint
+    # You can get the state of the graph at this point
+    print(graph.get_state(config))
+    
+    # You can continue the graph execution by passing in `None` for the input
+    for event in graph.stream(None, thread, stream_mode="values"):
+        print(event)
+    ```
+
+### Use static interrupts in LangGraph Studio
+
+You can use [LangGraph Studio](../../concepts/langgraph_studio.md) to debug your graph. You can set static breakpoints in the UI and then run the graph. You can also use the UI to inspect the graph state at any point in the execution.
+
+![image](../../concepts/img/human_in_the_loop/static-interrupt.png){: style="max-height:400px"}
+
+LangGraph Studio is free with [locally deployed applications](../../tutorials/langgraph-platform/local-server.md) using `langgraph dev`. 
+
 ## Considerations
 
 When using human-in-the-loop, there are some considerations to keep in mind.
@@ -953,4 +1112,3 @@ To avoid issues, refrain from dynamically changing the node's structure between
     Name: N/A. Age: John
     {'human_node': {'age': 'John', 'name': 'N/A'}}
     ```
-

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

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

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

@@ -4,7 +4,7 @@ To use [time-travel](../../concepts/time-travel.md) in LangGraph:
 
 1. [Run the graph](#1-run-the-graph) with initial inputs using [`invoke`][langgraph.graph.state.CompiledStateGraph.invoke] or [`stream`][langgraph.graph.state.CompiledStateGraph.stream] methods.
 2. [Identify a checkpoint in an existing thread](#2-identify-a-checkpoint): Use the [`get_state_history()`][langgraph.graph.state.CompiledStateGraph.get_state_history] method to retrieve the execution history for a specific `thread_id` and locate the desired `checkpoint_id`.  
-   Alternatively, set a [breakpoint](../../concepts/breakpoints.md) before the node(s) where you want execution to pause. You can then find the most recent checkpoint recorded up to that breakpoint.
+   Alternatively, set an [interrupt](../../how-tos/human_in_the_loop/add-human-in-the-loop.md) before the node(s) where you want execution to pause. You can then find the most recent checkpoint recorded up to that interrupt.
 3. [Update the graph state (optional)](#3-update-the-state-optional): Use the [`update_state`][langgraph.graph.state.CompiledStateGraph.update_state] method to modify the graph's state at the checkpoint and resume execution from alternative state.
 4. [Resume execution from the checkpoint](#4-resume-execution-from-the-checkpoint): Use the `invoke` or `stream` methods with an input of `None` and a configuration containing the appropriate `thread_id` and `checkpoint_id`.
 

docs/docs/how-tos/memory/add-memory.md

@@ -1351,7 +1351,7 @@ The problem with trimming or removing messages, as shown above, is that you may
 
     ```python
     from langchain_anthropic import ChatAnthropic
-    from langmem.short_term import SummarizationNode
+    from langmem.short_term import SummarizationNode, RunningSummary
     from langchain_core.messages.utils import count_tokens_approximately
     from langgraph.prebuilt import create_react_agent
     from langgraph.prebuilt.chat_agent_executor import AgentState
@@ -1372,7 +1372,7 @@ The problem with trimming or removing messages, as shown above, is that you may
         # NOTE: we're adding this key to keep track of previous summary information
         # to make sure we're not summarizing on every LLM call
         # highlight-next-line
-        context: dict[str, Any]  # (2)!
+        context: dict[str, RunningSummary]  # (2)!
 
 
     checkpointer = InMemorySaver() # (3)!
@@ -1447,18 +1447,18 @@ The problem with trimming or removing messages, as shown above, is that you may
     from langgraph.graph import StateGraph, START, MessagesState
     from langgraph.checkpoint.memory import InMemorySaver
     # highlight-next-line
-    from langmem.short_term import SummarizationNode
+    from langmem.short_term import SummarizationNode, RunningSummary
     
     model = init_chat_model("anthropic:claude-3-7-sonnet-latest")
     summarization_model = model.bind(max_tokens=128)
     
     class State(MessagesState):
         # highlight-next-line
-        context: dict[str, Any]  # (1)!
+        context: dict[str, RunningSummary]  # (1)!
     
     class LLMInputState(TypedDict):  # (2)!
         summarized_messages: list[AnyMessage]
-        context: dict[str, Any]
+        context: dict[str, RunningSummary]
     
     # highlight-next-line
     summarization_node = SummarizationNode(

docs/docs/how-tos/memory/semantic-search.ipynb

@@ -125,7 +125,7 @@
     "memories = store.search((\"user_123\", \"memories\"), query=\"I like food?\", limit=5)\n",
     "\n",
     "for memory in memories:\n",
-    "    print(f'Memory: {memory.value[\"text\"]} (similarity: {memory.score})')"
+    "    print(f\"Memory: {memory.value['text']} (similarity: {memory.score})\")"
    ]
   },
   {

docs/docs/how-tos/multi_agent.ipynb

@@ -1,657 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "34d3d54e-9a2b-481e-bccd-74aca7a53f9a",
-   "metadata": {},
-   "source": [
-    "# Build multi-agent systems"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "id": "3f0b4f70-f14e-4026-82c0-874786789ee8",
-   "metadata": {},
-   "source": [
-    "A single agent might struggle if it needs to specialize in multiple domains or manage many tools. To tackle this, you can break your agent into smaller, independent agents and composing them into a [multi-agent system](../../concepts/multi_agent).\n",
-    "\n",
-    "In multi-agent systems, agents need to communicate between each other. They do so via [handoffs](#handoffs) — a primitive that describes which agent to hand control to and the payload to send to that agent.\n",
-    "\n",
-    "This guide covers the following:\n",
-    "\n",
-    "* implementing [handoffs](#handoffs) between agents\n",
-    "* using handoffs and the prebuilt [agent](../../agents/agents) to [build a custom multi-agent system](#build-a-multi-agent-system)\n",
-    "\n",
-    "To get started with building multi-agent systems, check out LangGraph [prebuilt implementations](#prebuilt-implementations) of two of the most popular multi-agent architectures — [supervisor](../../agents/multi-agent#supervisor) and [swarm](../../agents/multi-agent#swarm)."
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "id": "7d43e110-16fc-4899-97f1-015d5b804b87",
-   "metadata": {},
-   "source": [
-    "## Handoffs\n",
-    "\n",
-    "To set up communication between the agents in a multi-agent system you can use [**handoffs**](../../concepts/multi_agent#handoffs) — a pattern where one agent *hands off* control to another. Handoffs allow you to specify:\n",
-    "\n",
-    "- **destination**: target agent to navigate to (e.g., name of the LangGraph node to go to)\n",
-    "- **payload**: information to pass to that agent (e.g., state update)\n",
-    "\n",
-    "### Create handoffs\n",
-    "\n",
-    "To implement handoffs, you can return [`Command`](../command) objects from your agent nodes or tools:\n",
-    "\n",
-    "```python\n",
-    "from typing import Annotated\n",
-    "from langchain_core.tools import tool, InjectedToolCallId\n",
-    "from langgraph.prebuilt import create_react_agent, InjectedState\n",
-    "from langgraph.graph import StateGraph, START, MessagesState\n",
-    "from langgraph.types import Command\n",
-    "\n",
-    "def create_handoff_tool(*, agent_name: str, description: str | None = None):\n",
-    "    name = f\"transfer_to_{agent_name}\"\n",
-    "    description = description or f\"Transfer to {agent_name}\"\n",
-    "\n",
-    "    @tool(name, description=description)\n",
-    "    def handoff_tool(\n",
-    "        # highlight-next-line\n",
-    "        state: Annotated[MessagesState, InjectedState], # (1)!\n",
-    "        # highlight-next-line\n",
-    "        tool_call_id: Annotated[str, InjectedToolCallId],\n",
-    "    ) -> Command:\n",
-    "        tool_message = {\n",
-    "            \"role\": \"tool\",\n",
-    "            \"content\": f\"Successfully transferred to {agent_name}\",\n",
-    "            \"name\": name,\n",
-    "            \"tool_call_id\": tool_call_id,\n",
-    "        }\n",
-    "        return Command(  # (2)!\n",
-    "            # highlight-next-line\n",
-    "            goto=agent_name,  # (3)!\n",
-    "            # highlight-next-line\n",
-    "            update={\"messages\": state[\"messages\"] + [tool_message]},  # (4)!\n",
-    "            # highlight-next-line\n",
-    "            graph=Command.PARENT,  # (5)!\n",
-    "        )\n",
-    "    return handoff_tool\n",
-    "```\n",
-    "\n",
-    "1. Access the [state](../../concepts/low_level#state) of the agent that is calling the handoff tool using the [InjectedState][langgraph.prebuilt.InjectedState] annotation. See [this guide](../tool-calling/#read-state) for more information.\n",
-    "2. The `Command` primitive allows specifying a state update and a node transition as a single operation, making it useful for implementing handoffs.\n",
-    "3. Name of the agent or node to hand off to.\n",
-    "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.\n",
-    "5. Indicate to LangGraph that we need to navigate to agent node in a **parent** multi-agent graph.\n",
-    "\n",
-    "!!! tip\n",
-    "\n",
-    "    If you want to use tools that return `Command`, you can either use prebuilt [`create_react_agent`][langgraph.prebuilt.chat_agent_executor.create_react_agent] / [`ToolNode`][langgraph.prebuilt.tool_node.ToolNode] components, or implement your own tool-executing node that collects `Command` objects returned by the tools and returns a list of them, e.g.:\n",
-    "    \n",
-    "    ```python\n",
-    "    def call_tools(state):\n",
-    "        ...\n",
-    "        commands = [tools_by_name[tool_call[\"name\"]].invoke(tool_call) for tool_call in tool_calls]\n",
-    "        return commands\n",
-    "    ```\n",
-    "\n",
-    "!!! Important\n",
-    "\n",
-    "    This handoff implementation assumes that:\n",
-    "    \n",
-    "      - each agent receives overall message history (across all agents) in the multi-agent system as its input. If you want more control over agent inputs, see [this section](#control-agent-inputs)\n",
-    "      - each agent outputs its internal messages history to the overall message history of the multi-agent system. If you want more control over **how agent outputs are added**, wrap the agent in a separate node function:\n",
-    "\n",
-    "        ```python\n",
-    "        def call_hotel_assistant(state):\n",
-    "            # return agent's final response,\n",
-    "            # excluding inner monologue\n",
-    "            response = hotel_assistant.invoke(state)\n",
-    "            # highlight-next-line\n",
-    "            return {\"messages\": response[\"messages\"][-1]}\n",
-    "        ```"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "3956f12d-285a-4799-a0a5-db13def58a15",
-   "metadata": {},
-   "source": [
-    "### Control agent inputs\n",
-    "\n",
-    "You can use the [`Send()`][langgraph.types.Send] primitive to directly send data to the worker agents during the handoff. For example, you can request that the calling agent populate a task description for the next agent:\n",
-    "\n",
-    "```python\n",
-    "\n",
-    "from typing import Annotated\n",
-    "from langchain_core.tools import tool, InjectedToolCallId\n",
-    "from langgraph.prebuilt import InjectedState\n",
-    "from langgraph.graph import StateGraph, START, MessagesState\n",
-    "# highlight-next-line\n",
-    "from langgraph.types import Command, Send\n",
-    "\n",
-    "def create_task_description_handoff_tool(\n",
-    "    *, agent_name: str, description: str | None = None\n",
-    "):\n",
-    "    name = f\"transfer_to_{agent_name}\"\n",
-    "    description = description or f\"Ask {agent_name} for help.\"\n",
-    "\n",
-    "    @tool(name, description=description)\n",
-    "    def handoff_tool(\n",
-    "        # this is populated by the calling agent\n",
-    "        task_description: Annotated[\n",
-    "            str,\n",
-    "            \"Description of what the next agent should do, including all of the relevant context.\",\n",
-    "        ],\n",
-    "        # these parameters are ignored by the LLM\n",
-    "        state: Annotated[MessagesState, InjectedState],\n",
-    "    ) -> Command:\n",
-    "        task_description_message = {\"role\": \"user\", \"content\": task_description}\n",
-    "        agent_input = {**state, \"messages\": [task_description_message]}\n",
-    "        return Command(\n",
-    "            # highlight-next-line\n",
-    "            goto=[Send(agent_name, agent_input)],\n",
-    "            graph=Command.PARENT,\n",
-    "        )\n",
-    "\n",
-    "    return handoff_tool\n",
-    "```\n",
-    "\n",
-    "See the multi-agent [supervisor](../tutorials/agent_supervisor.ipynb#4-create-delegation-tasks) tutorial for a full example of using [`Send()`][langgraph.types.Send] in handoffs."
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "id": "21511f57-7bf3-4223-9a17-ce9fc84c40ab",
-   "metadata": {},
-   "source": [
-    "## Build a multi-agent system\n",
-    "\n",
-    "You can use handoffs in any agents built with LangGraph. We recommend using the prebuilt [agent](../../agents/overview) or [`ToolNode`](../tool-calling#use-prebuilt-toolnode), as they natively support handoffs tools returning `Command`. Below is an example of how you can implement a multi-agent system for booking travel using handoffs:\n",
-    "\n",
-    "```python\n",
-    "from langgraph.prebuilt import create_react_agent\n",
-    "from langgraph.graph import StateGraph, START, MessagesState\n",
-    "\n",
-    "def create_handoff_tool(*, agent_name: str, description: str | None = None):\n",
-    "    # same implementation as above\n",
-    "    ...\n",
-    "    return Command(...)\n",
-    "\n",
-    "# Handoffs\n",
-    "transfer_to_hotel_assistant = create_handoff_tool(agent_name=\"hotel_assistant\")\n",
-    "transfer_to_flight_assistant = create_handoff_tool(agent_name=\"flight_assistant\")\n",
-    "\n",
-    "# Define agents\n",
-    "flight_assistant = create_react_agent(\n",
-    "    model=\"anthropic:claude-3-5-sonnet-latest\",\n",
-    "    # highlight-next-line\n",
-    "    tools=[..., transfer_to_hotel_assistant],\n",
-    "    # highlight-next-line\n",
-    "    name=\"flight_assistant\"\n",
-    ")\n",
-    "hotel_assistant = create_react_agent(\n",
-    "    model=\"anthropic:claude-3-5-sonnet-latest\",\n",
-    "    # highlight-next-line\n",
-    "    tools=[..., transfer_to_flight_assistant],\n",
-    "    # highlight-next-line\n",
-    "    name=\"hotel_assistant\"\n",
-    ")\n",
-    "\n",
-    "# Define multi-agent graph\n",
-    "multi_agent_graph = (\n",
-    "    StateGraph(MessagesState)\n",
-    "    # highlight-next-line\n",
-    "    .add_node(flight_assistant)\n",
-    "    # highlight-next-line\n",
-    "    .add_node(hotel_assistant)\n",
-    "    .add_edge(START, \"flight_assistant\")\n",
-    "    .compile()\n",
-    ")\n",
-    "```\n",
-    "\n",
-    "??? example \"Full example: Multi-agent system for booking travel\"\n",
-    "\n",
-    "    ```python\n",
-    "    from typing import Annotated\n",
-    "    from langchain_core.messages import convert_to_messages\n",
-    "    from langchain_core.tools import tool, InjectedToolCallId\n",
-    "    from langgraph.prebuilt import create_react_agent, InjectedState\n",
-    "    from langgraph.graph import StateGraph, START, MessagesState\n",
-    "    from langgraph.types import Command\n",
-    "    \n",
-    "    # We'll use `pretty_print_messages` helper to render the streamed agent outputs nicely\n",
-    "    \n",
-    "    def pretty_print_message(message, indent=False):\n",
-    "        pretty_message = message.pretty_repr(html=True)\n",
-    "        if not indent:\n",
-    "            print(pretty_message)\n",
-    "            return\n",
-    "    \n",
-    "        indented = \"\\n\".join(\"\\t\" + c for c in pretty_message.split(\"\\n\"))\n",
-    "        print(indented)\n",
-    "    \n",
-    "    \n",
-    "    def pretty_print_messages(update, last_message=False):\n",
-    "        is_subgraph = False\n",
-    "        if isinstance(update, tuple):\n",
-    "            ns, update = update\n",
-    "            # skip parent graph updates in the printouts\n",
-    "            if len(ns) == 0:\n",
-    "                return\n",
-    "    \n",
-    "            graph_id = ns[-1].split(\":\")[0]\n",
-    "            print(f\"Update from subgraph {graph_id}:\")\n",
-    "            print(\"\\n\")\n",
-    "            is_subgraph = True\n",
-    "    \n",
-    "        for node_name, node_update in update.items():\n",
-    "            update_label = f\"Update from node {node_name}:\"\n",
-    "            if is_subgraph:\n",
-    "                update_label = \"\\t\" + update_label\n",
-    "    \n",
-    "            print(update_label)\n",
-    "            print(\"\\n\")\n",
-    "    \n",
-    "            messages = convert_to_messages(node_update[\"messages\"])\n",
-    "            if last_message:\n",
-    "                messages = messages[-1:]\n",
-    "    \n",
-    "            for m in messages:\n",
-    "                pretty_print_message(m, indent=is_subgraph)\n",
-    "            print(\"\\n\")\n",
-    "\n",
-    "\n",
-    "    def create_handoff_tool(*, agent_name: str, description: str | None = None):\n",
-    "        name = f\"transfer_to_{agent_name}\"\n",
-    "        description = description or f\"Transfer to {agent_name}\"\n",
-    "    \n",
-    "        @tool(name, description=description)\n",
-    "        def handoff_tool(\n",
-    "            # highlight-next-line\n",
-    "            state: Annotated[MessagesState, InjectedState], # (1)!\n",
-    "            # highlight-next-line\n",
-    "            tool_call_id: Annotated[str, InjectedToolCallId],\n",
-    "        ) -> Command:\n",
-    "            tool_message = {\n",
-    "                \"role\": \"tool\",\n",
-    "                \"content\": f\"Successfully transferred to {agent_name}\",\n",
-    "                \"name\": name,\n",
-    "                \"tool_call_id\": tool_call_id,\n",
-    "            }\n",
-    "            return Command(  # (2)!\n",
-    "                # highlight-next-line\n",
-    "                goto=agent_name,  # (3)!\n",
-    "                # highlight-next-line\n",
-    "                update={\"messages\": state[\"messages\"] + [tool_message]},  # (4)!\n",
-    "                # highlight-next-line\n",
-    "                graph=Command.PARENT,  # (5)!\n",
-    "            )\n",
-    "        return handoff_tool\n",
-    "    \n",
-    "    # Handoffs\n",
-    "    transfer_to_hotel_assistant = create_handoff_tool(\n",
-    "        agent_name=\"hotel_assistant\",\n",
-    "        description=\"Transfer user to the hotel-booking assistant.\",\n",
-    "    )\n",
-    "    transfer_to_flight_assistant = create_handoff_tool(\n",
-    "        agent_name=\"flight_assistant\",\n",
-    "        description=\"Transfer user to the flight-booking assistant.\",\n",
-    "    )\n",
-    "    \n",
-    "    # Simple agent tools\n",
-    "    def book_hotel(hotel_name: str):\n",
-    "        \"\"\"Book a hotel\"\"\"\n",
-    "        return f\"Successfully booked a stay at {hotel_name}.\"\n",
-    "    \n",
-    "    def book_flight(from_airport: str, to_airport: str):\n",
-    "        \"\"\"Book a flight\"\"\"\n",
-    "        return f\"Successfully booked a flight from {from_airport} to {to_airport}.\"\n",
-    "    \n",
-    "    # Define agents\n",
-    "    flight_assistant = create_react_agent(\n",
-    "        model=\"anthropic:claude-3-5-sonnet-latest\",\n",
-    "        # highlight-next-line\n",
-    "        tools=[book_flight, transfer_to_hotel_assistant],\n",
-    "        prompt=\"You are a flight booking assistant\",\n",
-    "        # highlight-next-line\n",
-    "        name=\"flight_assistant\"\n",
-    "    )\n",
-    "    hotel_assistant = create_react_agent(\n",
-    "        model=\"anthropic:claude-3-5-sonnet-latest\",\n",
-    "        # highlight-next-line\n",
-    "        tools=[book_hotel, transfer_to_flight_assistant],\n",
-    "        prompt=\"You are a hotel booking assistant\",\n",
-    "        # highlight-next-line\n",
-    "        name=\"hotel_assistant\"\n",
-    "    )\n",
-    "    \n",
-    "    # Define multi-agent graph\n",
-    "    multi_agent_graph = (\n",
-    "        StateGraph(MessagesState)\n",
-    "        .add_node(flight_assistant)\n",
-    "        .add_node(hotel_assistant)\n",
-    "        .add_edge(START, \"flight_assistant\")\n",
-    "        .compile()\n",
-    "    )\n",
-    "    \n",
-    "    # Run the multi-agent graph\n",
-    "    for chunk in multi_agent_graph.stream(\n",
-    "        {\n",
-    "            \"messages\": [\n",
-    "                {\n",
-    "                    \"role\": \"user\",\n",
-    "                    \"content\": \"book a flight from BOS to JFK and a stay at McKittrick Hotel\"\n",
-    "                }\n",
-    "            ]\n",
-    "        },\n",
-    "        # highlight-next-line\n",
-    "        subgraphs=True\n",
-    "    ):\n",
-    "        pretty_print_messages(chunk)\n",
-    "    ```\n",
-    "\n",
-    "    1. Access agent's state\n",
-    "    2. The `Command` primitive allows specifying a state update and a node transition as a single operation, making it useful for implementing handoffs.\n",
-    "    3. Name of the agent or node to hand off to.\n",
-    "    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.\n",
-    "    5. Indicate to LangGraph that we need to navigate to agent node in a **parent** multi-agent graph."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e8314da4-9971-429b-9e70-58b40795de74",
-   "metadata": {},
-   "source": [
-    "## Multi-turn conversation\n",
-    "\n",
-    "Users might want to engage in a *multi-turn conversation* with one or more agents. To build a system that can handle this, you can create a node that uses an [`interrupt`][langgraph.types.interrupt] to collect user input and routes back to the **active** agent.\n",
-    "\n",
-    "The agents can then be implemented as nodes in a graph that executes agent steps and determines the next action:\n",
-    "\n",
-    "1. **Wait for user input** to continue the conversation, or  \n",
-    "2. **Route to another agent** (or back to itself, such as in a loop) via a [handoff](#handoffs)\n",
-    "\n",
-    "```python\n",
-    "def human(state) -> Command[Literal[\"agent\", \"another_agent\"]]:\n",
-    "    \"\"\"A node for collecting user input.\"\"\"\n",
-    "    user_input = interrupt(value=\"Ready for user input.\")\n",
-    "\n",
-    "    # Determine the active agent.\n",
-    "    active_agent = ...\n",
-    "\n",
-    "    ...\n",
-    "    return Command(\n",
-    "        update={\n",
-    "            \"messages\": [{\n",
-    "                \"role\": \"human\",\n",
-    "                \"content\": user_input,\n",
-    "            }]\n",
-    "        },\n",
-    "        goto=active_agent\n",
-    "    )\n",
-    "\n",
-    "def agent(state) -> Command[Literal[\"agent\", \"another_agent\", \"human\"]]:\n",
-    "    # The condition for routing/halting can be anything, e.g. LLM tool call / structured output, etc.\n",
-    "    goto = get_next_agent(...)  # 'agent' / 'another_agent'\n",
-    "    if goto:\n",
-    "        return Command(goto=goto, update={\"my_state_key\": \"my_state_value\"})\n",
-    "    else:\n",
-    "        return Command(goto=\"human\") # Go to human node\n",
-    "```\n",
-    "\n",
-    "??? example \"Full example: multi-agent system for travel recommendations\"\n",
-    "\n",
-    "    In this example, we will build a team of travel assistant agents that can communicate with each other via handoffs.\n",
-    "    \n",
-    "    We will create 2 agents:\n",
-    "    \n",
-    "    * travel_advisor: can help with travel destination recommendations. Can ask hotel_advisor for help.\n",
-    "    * hotel_advisor: can help with hotel recommendations. Can ask travel_advisor for help.\n",
-    "\n",
-    "    ```python\n",
-    "    from langchain_anthropic import ChatAnthropic\n",
-    "    from langgraph.graph import MessagesState, StateGraph, START\n",
-    "    from langgraph.prebuilt import create_react_agent, InjectedState\n",
-    "    from langgraph.types import Command, interrupt\n",
-    "    from langgraph.checkpoint.memory import MemorySaver\n",
-    "    \n",
-    "    \n",
-    "    model = ChatAnthropic(model=\"claude-3-5-sonnet-latest\")\n",
-    "\n",
-    "    class MultiAgentState(MessagesState):\n",
-    "        last_active_agent: str\n",
-    "    \n",
-    "    \n",
-    "    # Define travel advisor tools and ReAct agent\n",
-    "    travel_advisor_tools = [\n",
-    "        get_travel_recommendations,\n",
-    "        make_handoff_tool(agent_name=\"hotel_advisor\"),\n",
-    "    ]\n",
-    "    travel_advisor = create_react_agent(\n",
-    "        model,\n",
-    "        travel_advisor_tools,\n",
-    "        prompt=(\n",
-    "            \"You are a general travel expert that can recommend travel destinations (e.g. countries, cities, etc). \"\n",
-    "            \"If you need hotel recommendations, ask 'hotel_advisor' for help. \"\n",
-    "            \"You MUST include human-readable response before transferring to another agent.\"\n",
-    "        ),\n",
-    "    )\n",
-    "    \n",
-    "    \n",
-    "    def call_travel_advisor(\n",
-    "        state: MultiAgentState,\n",
-    "    ) -> Command[Literal[\"hotel_advisor\", \"human\"]]:\n",
-    "        # You can also add additional logic like changing the input to the agent / output from the agent, etc.\n",
-    "        # NOTE: we're invoking the ReAct agent with the full history of messages in the state\n",
-    "        response = travel_advisor.invoke(state)\n",
-    "        update = {**response, \"last_active_agent\": \"travel_advisor\"}\n",
-    "        return Command(update=update, goto=\"human\")\n",
-    "    \n",
-    "    \n",
-    "    # Define hotel advisor tools and ReAct agent\n",
-    "    hotel_advisor_tools = [\n",
-    "        get_hotel_recommendations,\n",
-    "        make_handoff_tool(agent_name=\"travel_advisor\"),\n",
-    "    ]\n",
-    "    hotel_advisor = create_react_agent(\n",
-    "        model,\n",
-    "        hotel_advisor_tools,\n",
-    "        prompt=(\n",
-    "            \"You are a hotel expert that can provide hotel recommendations for a given destination. \"\n",
-    "            \"If you need help picking travel destinations, ask 'travel_advisor' for help.\"\n",
-    "            \"You MUST include human-readable response before transferring to another agent.\"\n",
-    "        ),\n",
-    "    )\n",
-    "    \n",
-    "    \n",
-    "    def call_hotel_advisor(\n",
-    "        state: MultiAgentState,\n",
-    "    ) -> Command[Literal[\"travel_advisor\", \"human\"]]:\n",
-    "        response = hotel_advisor.invoke(state)\n",
-    "        update = {**response, \"last_active_agent\": \"hotel_advisor\"}\n",
-    "        return Command(update=update, goto=\"human\")\n",
-    "    \n",
-    "    \n",
-    "    def human_node(\n",
-    "        state: MultiAgentState, config\n",
-    "    ) -> Command[Literal[\"hotel_advisor\", \"travel_advisor\", \"human\"]]:\n",
-    "        \"\"\"A node for collecting user input.\"\"\"\n",
-    "    \n",
-    "        user_input = interrupt(value=\"Ready for user input.\")\n",
-    "        active_agent = state[\"last_active_agent\"]\n",
-    "    \n",
-    "        return Command(\n",
-    "            update={\n",
-    "                \"messages\": [\n",
-    "                    {\n",
-    "                        \"role\": \"human\",\n",
-    "                        \"content\": user_input,\n",
-    "                    }\n",
-    "                ]\n",
-    "            },\n",
-    "            goto=active_agent,\n",
-    "        )\n",
-    "    \n",
-    "    \n",
-    "    builder = StateGraph(MultiAgentState)\n",
-    "    builder.add_node(\"travel_advisor\", call_travel_advisor)\n",
-    "    builder.add_node(\"hotel_advisor\", call_hotel_advisor)\n",
-    "    \n",
-    "    # This adds a node to collect human input, which will route\n",
-    "    # back to the active agent.\n",
-    "    builder.add_node(\"human\", human_node)\n",
-    "    \n",
-    "    # We'll always start with a general travel advisor.\n",
-    "    builder.add_edge(START, \"travel_advisor\")\n",
-    "    \n",
-    "    \n",
-    "    checkpointer = MemorySaver()\n",
-    "    graph = builder.compile(checkpointer=checkpointer)\n",
-    "    ```\n",
-    "    \n",
-    "    Let's test a multi turn conversation with this application.\n",
-    "\n",
-    "    ```python\n",
-    "    import uuid\n",
-    "    \n",
-    "    thread_config = {\"configurable\": {\"thread_id\": str(uuid.uuid4())}}\n",
-    "    \n",
-    "    inputs = [\n",
-    "        # 1st round of conversation,\n",
-    "        {\n",
-    "            \"messages\": [\n",
-    "                {\"role\": \"user\", \"content\": \"i wanna go somewhere warm in the caribbean\"}\n",
-    "            ]\n",
-    "        },\n",
-    "        # Since we're using `interrupt`, we'll need to resume using the Command primitive.\n",
-    "        # 2nd round of conversation,\n",
-    "        Command(\n",
-    "            resume=\"could you recommend a nice hotel in one of the areas and tell me which area it is.\"\n",
-    "        ),\n",
-    "        # 3rd round of conversation,\n",
-    "        Command(\n",
-    "            resume=\"i like the first one. could you recommend something to do near the hotel?\"\n",
-    "        ),\n",
-    "    ]\n",
-    "    \n",
-    "    for idx, user_input in enumerate(inputs):\n",
-    "        print()\n",
-    "        print(f\"--- Conversation Turn {idx + 1} ---\")\n",
-    "        print()\n",
-    "        print(f\"User: {user_input}\")\n",
-    "        print()\n",
-    "        for update in graph.stream(\n",
-    "            user_input,\n",
-    "            config=thread_config,\n",
-    "            stream_mode=\"updates\",\n",
-    "        ):\n",
-    "            for node_id, value in update.items():\n",
-    "                if isinstance(value, dict) and value.get(\"messages\", []):\n",
-    "                    last_message = value[\"messages\"][-1]\n",
-    "                    if isinstance(last_message, dict) or last_message.type != \"ai\":\n",
-    "                        continue\n",
-    "                    print(f\"{node_id}: {last_message.content}\")\n",
-    "    ```\n",
-    "    \n",
-    "    ```\n",
-    "    --- Conversation Turn 1 ---\n",
-    "    \n",
-    "    User: {'messages': [{'role': 'user', 'content': 'i wanna go somewhere warm in the caribbean'}]}\n",
-    "    \n",
-    "    travel_advisor: Based on the recommendations, Aruba would be an excellent choice for your Caribbean getaway! Aruba is known as \"One Happy Island\" and offers:\n",
-    "    - Year-round warm weather with consistent temperatures around 82°F (28°C)\n",
-    "    - Beautiful white sand beaches like Eagle Beach and Palm Beach\n",
-    "    - Clear turquoise waters perfect for swimming and snorkeling\n",
-    "    - Minimal rainfall and location outside the hurricane belt\n",
-    "    - A blend of Caribbean and Dutch culture\n",
-    "    - Great dining options and nightlife\n",
-    "    - Various water sports and activities\n",
-    "    \n",
-    "    Would you like me to get some specific hotel recommendations in Aruba for your stay? I can transfer you to our hotel advisor who can help with accommodations.\n",
-    "    \n",
-    "    --- Conversation Turn 2 ---\n",
-    "    \n",
-    "    User: Command(resume='could you recommend a nice hotel in one of the areas and tell me which area it is.')\n",
-    "    \n",
-    "    hotel_advisor: Based on the recommendations, I can suggest two excellent options:\n",
-    "    \n",
-    "    1. The Ritz-Carlton, Aruba - Located in Palm Beach\n",
-    "    - This luxury resort is situated in the vibrant Palm Beach area\n",
-    "    - Known for its exceptional service and amenities\n",
-    "    - Perfect if you want to be close to dining, shopping, and entertainment\n",
-    "    - Features multiple restaurants, a casino, and a world-class spa\n",
-    "    - Located on a pristine stretch of Palm Beach\n",
-    "    \n",
-    "    2. Bucuti & Tara Beach Resort - Located in Eagle Beach\n",
-    "    - An adults-only boutique resort on Eagle Beach\n",
-    "    - Known for being more intimate and peaceful\n",
-    "    - Award-winning for its sustainability practices\n",
-    "    - Perfect for a romantic getaway or peaceful vacation\n",
-    "    - Located on one of the most beautiful beaches in the Caribbean\n",
-    "    \n",
-    "    Would you like more specific information about either of these properties or their locations?\n",
-    "    \n",
-    "    --- Conversation Turn 3 ---\n",
-    "    \n",
-    "    User: Command(resume='i like the first one. could you recommend something to do near the hotel?')\n",
-    "    \n",
-    "    travel_advisor: Near the Ritz-Carlton in Palm Beach, here are some highly recommended activities:\n",
-    "    \n",
-    "    1. Visit the Palm Beach Plaza Mall - Just a short walk from the hotel, featuring shopping, dining, and entertainment\n",
-    "    2. Try your luck at the Stellaris Casino - It's right in the Ritz-Carlton\n",
-    "    3. Take a sunset sailing cruise - Many depart from the nearby pier\n",
-    "    4. Visit the California Lighthouse - A scenic landmark just north of Palm Beach\n",
-    "    5. Enjoy water sports at Palm Beach:\n",
-    "       - Jet skiing\n",
-    "       - Parasailing\n",
-    "       - Snorkeling\n",
-    "       - Stand-up paddleboarding\n",
-    "    \n",
-    "    Would you like more specific information about any of these activities or would you like to know about other options in the area?\n",
-    "    ```"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "04d18c63-a0eb-45ac-86dc-0cc5bd683973",
-   "metadata": {},
-   "source": [
-    "## Prebuilt implementations"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e0e4ce57-f8de-4f37-836e-c1e1a02dd7b7",
-   "metadata": {},
-   "source": [
-    "LangGraph comes with prebuilt implementations of two of the most popular multi-agent architectures:\n",
-    "\n",
-    "- [supervisor](../../agents/multi-agent#supervisor) — individual agents are coordinated by a central supervisor agent. The supervisor controls all communication flow and task delegation, making decisions about which agent to invoke based on the current context and task requirements. You can use [`langgraph-supervisor`](https://github.com/langchain-ai/langgraph-supervisor-py) library to create a supervisor multi-agent systems.\n",
-    "- [swarm](../../agents/multi-agent#supervisor) — agents dynamically hand off control to one another based on their specializations. The system remembers which agent was last active, ensuring that on subsequent interactions, the conversation resumes with that agent. You can use [`langgraph-swarm`](https://github.com/langchain-ai/langgraph-swarm-py) library to create a swarm multi-agent systems."
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.12.3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/docs/how-tos/multi_agent.md

@@ -0,0 +1,580 @@
+# Build multi-agent systems
+
+A single agent might struggle if it needs to specialize in multiple domains or manage many tools. To tackle this, you can break your agent into smaller, independent agents and composing them into a [multi-agent system](../concepts/multi_agent.md).
+
+In multi-agent systems, agents need to communicate between each other. They do so via [handoffs](#handoffs) — a primitive that describes which agent to hand control to and the payload to send to that agent.
+
+This guide covers the following:
+
+* implementing [handoffs](#handoffs) between agents
+* using handoffs and the prebuilt [agent](../agents/agents.md) to [build a custom multi-agent system](#build-a-multi-agent-system)
+
+To get started with building multi-agent systems, check out LangGraph [prebuilt implementations](#prebuilt-implementations) of two of the most popular multi-agent architectures — [supervisor](../agents/multi-agent.md#supervisor) and [swarm](../agents/multi-agent.md#swarm).
+
+## Handoffs
+
+To set up communication between the agents in a multi-agent system you can use [**handoffs**](../concepts/multi_agent.md#handoffs) — a pattern where one agent *hands off* control to another. Handoffs allow you to specify:
+
+- **destination**: target agent to navigate to (e.g., name of the LangGraph node to go to)
+- **payload**: information to pass to that agent (e.g., state update)
+
+### Create handoffs
+
+To implement handoffs, you can return `Command` objects from your agent nodes or tools:
+
+```python
+from typing import Annotated
+from langchain_core.tools import tool, InjectedToolCallId
+from langgraph.prebuilt import create_react_agent, InjectedState
+from langgraph.graph import StateGraph, START, MessagesState
+from langgraph.types import Command
+
+def create_handoff_tool(*, agent_name: str, description: str | None = None):
+    name = f"transfer_to_{agent_name}"
+    description = description or f"Transfer to {agent_name}"
+
+    @tool(name, description=description)
+    def handoff_tool(
+        # highlight-next-line
+        state: Annotated[MessagesState, InjectedState], # (1)!
+        # highlight-next-line
+        tool_call_id: Annotated[str, InjectedToolCallId],
+    ) -> Command:
+        tool_message = {
+            "role": "tool",
+            "content": f"Successfully transferred to {agent_name}",
+            "name": name,
+            "tool_call_id": tool_call_id,
+        }
+        return Command(  # (2)!
+            # highlight-next-line
+            goto=agent_name,  # (3)!
+            # highlight-next-line
+            update={"messages": state["messages"] + [tool_message]},  # (4)!
+            # highlight-next-line
+            graph=Command.PARENT,  # (5)!
+        )
+    return handoff_tool
+```
+
+1. Access the [state](../concepts/low_level.md#state) of the agent that is calling the handoff tool using the [InjectedState][langgraph.prebuilt.InjectedState] annotation. 
+2. The `Command` primitive allows specifying a state update and a node transition as a single operation, making it useful for implementing handoffs.
+3. Name of the agent or node to hand off to.
+4. Take the agent's messages and **add** them to the parent's **state** as part of the handoff. The next agent will see the parent state.
+5. Indicate to LangGraph that we need to navigate to agent node in a **parent** multi-agent graph.
+
+!!! tip
+
+    If you want to use tools that return `Command`, you can either use prebuilt [`create_react_agent`][langgraph.prebuilt.chat_agent_executor.create_react_agent] / [`ToolNode`][langgraph.prebuilt.tool_node.ToolNode] components, or implement your own tool-executing node that collects `Command` objects returned by the tools and returns a list of them, e.g.:
+    
+    ```python
+    def call_tools(state):
+        ...
+        commands = [tools_by_name[tool_call["name"]].invoke(tool_call) for tool_call in tool_calls]
+        return commands
+    ```
+
+!!! Important
+
+    This handoff implementation assumes that:
+    
+      - each agent receives overall message history (across all agents) in the multi-agent system as its input. If you want more control over agent inputs, see [this section](#control-agent-inputs)
+      - each agent outputs its internal messages history to the overall message history of the multi-agent system. If you want more control over **how agent outputs are added**, wrap the agent in a separate node function:
+
+        ```python
+        def call_hotel_assistant(state):
+            # return agent's final response,
+            # excluding inner monologue
+            response = hotel_assistant.invoke(state)
+            # highlight-next-line
+            return {"messages": response["messages"][-1]}
+        ```
+
+### Control agent inputs
+
+You can use the [`Send()`][langgraph.types.Send] primitive to directly send data to the worker agents during the handoff. For example, you can request that the calling agent populate a task description for the next agent:
+
+```python
+
+from typing import Annotated
+from langchain_core.tools import tool, InjectedToolCallId
+from langgraph.prebuilt import InjectedState
+from langgraph.graph import StateGraph, START, MessagesState
+# highlight-next-line
+from langgraph.types import Command, Send
+
+def create_task_description_handoff_tool(
+    *, agent_name: str, description: str | None = None
+):
+    name = f"transfer_to_{agent_name}"
+    description = description or f"Ask {agent_name} for help."
+
+    @tool(name, description=description)
+    def handoff_tool(
+        # this is populated by the calling agent
+        task_description: Annotated[
+            str,
+            "Description of what the next agent should do, including all of the relevant context.",
+        ],
+        # these parameters are ignored by the LLM
+        state: Annotated[MessagesState, InjectedState],
+    ) -> Command:
+        task_description_message = {"role": "user", "content": task_description}
+        agent_input = {**state, "messages": [task_description_message]}
+        return Command(
+            # highlight-next-line
+            goto=[Send(agent_name, agent_input)],
+            graph=Command.PARENT,
+        )
+
+    return handoff_tool
+```
+
+See the multi-agent [supervisor](../tutorials/multi_agent/agent_supervisor.md#4-create-delegation-tasks) example for a full example of using [`Send()`][langgraph.types.Send] in handoffs.
+
+## Build a multi-agent system
+
+You can use handoffs in any agents built with LangGraph. We recommend using the prebuilt [agent](../agents/overview.md) or [`ToolNode`](./tool-calling.md#toolnode), as they natively support handoffs tools returning `Command`. Below is an example of how you can implement a multi-agent system for booking travel using handoffs:
+
+```python
+from langgraph.prebuilt import create_react_agent
+from langgraph.graph import StateGraph, START, MessagesState
+
+def create_handoff_tool(*, agent_name: str, description: str | None = None):
+    # same implementation as above
+    ...
+    return Command(...)
+
+# Handoffs
+transfer_to_hotel_assistant = create_handoff_tool(agent_name="hotel_assistant")
+transfer_to_flight_assistant = create_handoff_tool(agent_name="flight_assistant")
+
+# Define agents
+flight_assistant = create_react_agent(
+    model="anthropic:claude-3-5-sonnet-latest",
+    # highlight-next-line
+    tools=[..., transfer_to_hotel_assistant],
+    # highlight-next-line
+    name="flight_assistant"
+)
+hotel_assistant = create_react_agent(
+    model="anthropic:claude-3-5-sonnet-latest",
+    # highlight-next-line
+    tools=[..., transfer_to_flight_assistant],
+    # highlight-next-line
+    name="hotel_assistant"
+)
+
+# Define multi-agent graph
+multi_agent_graph = (
+    StateGraph(MessagesState)
+    # highlight-next-line
+    .add_node(flight_assistant)
+    # highlight-next-line
+    .add_node(hotel_assistant)
+    .add_edge(START, "flight_assistant")
+    .compile()
+)
+```
+
+??? example "Full example: Multi-agent system for booking travel"
+
+    ```python
+    from typing import Annotated
+    from langchain_core.messages import convert_to_messages
+    from langchain_core.tools import tool, InjectedToolCallId
+    from langgraph.prebuilt import create_react_agent, InjectedState
+    from langgraph.graph import StateGraph, START, MessagesState
+    from langgraph.types import Command
+    
+    # We'll use `pretty_print_messages` helper to render the streamed agent outputs nicely
+    
+    def pretty_print_message(message, indent=False):
+        pretty_message = message.pretty_repr(html=True)
+        if not indent:
+            print(pretty_message)
+            return
+    
+        indented = "\n".join("\t" + c for c in pretty_message.split("\n"))
+        print(indented)
+    
+    
+    def pretty_print_messages(update, last_message=False):
+        is_subgraph = False
+        if isinstance(update, tuple):
+            ns, update = update
+            # skip parent graph updates in the printouts
+            if len(ns) == 0:
+                return
+    
+            graph_id = ns[-1].split(":")[0]
+            print(f"Update from subgraph {graph_id}:")
+            print("\n")
+            is_subgraph = True
+    
+        for node_name, node_update in update.items():
+            update_label = f"Update from node {node_name}:"
+            if is_subgraph:
+                update_label = "\t" + update_label
+    
+            print(update_label)
+            print("\n")
+    
+            messages = convert_to_messages(node_update["messages"])
+            if last_message:
+                messages = messages[-1:]
+    
+            for m in messages:
+                pretty_print_message(m, indent=is_subgraph)
+            print("\n")
+
+
+    def create_handoff_tool(*, agent_name: str, description: str | None = None):
+        name = f"transfer_to_{agent_name}"
+        description = description or f"Transfer to {agent_name}"
+    
+        @tool(name, description=description)
+        def handoff_tool(
+            # highlight-next-line
+            state: Annotated[MessagesState, InjectedState], # (1)!
+            # highlight-next-line
+            tool_call_id: Annotated[str, InjectedToolCallId],
+        ) -> Command:
+            tool_message = {
+                "role": "tool",
+                "content": f"Successfully transferred to {agent_name}",
+                "name": name,
+                "tool_call_id": tool_call_id,
+            }
+            return Command(  # (2)!
+                # highlight-next-line
+                goto=agent_name,  # (3)!
+                # highlight-next-line
+                update={"messages": state["messages"] + [tool_message]},  # (4)!
+                # highlight-next-line
+                graph=Command.PARENT,  # (5)!
+            )
+        return handoff_tool
+    
+    # Handoffs
+    transfer_to_hotel_assistant = create_handoff_tool(
+        agent_name="hotel_assistant",
+        description="Transfer user to the hotel-booking assistant.",
+    )
+    transfer_to_flight_assistant = create_handoff_tool(
+        agent_name="flight_assistant",
+        description="Transfer user to the flight-booking assistant.",
+    )
+    
+    # Simple agent tools
+    def book_hotel(hotel_name: str):
+        """Book a hotel"""
+        return f"Successfully booked a stay at {hotel_name}."
+    
+    def book_flight(from_airport: str, to_airport: str):
+        """Book a flight"""
+        return f"Successfully booked a flight from {from_airport} to {to_airport}."
+    
+    # Define agents
+    flight_assistant = create_react_agent(
+        model="anthropic:claude-3-5-sonnet-latest",
+        # highlight-next-line
+        tools=[book_flight, transfer_to_hotel_assistant],
+        prompt="You are a flight booking assistant",
+        # highlight-next-line
+        name="flight_assistant"
+    )
+    hotel_assistant = create_react_agent(
+        model="anthropic:claude-3-5-sonnet-latest",
+        # highlight-next-line
+        tools=[book_hotel, transfer_to_flight_assistant],
+        prompt="You are a hotel booking assistant",
+        # highlight-next-line
+        name="hotel_assistant"
+    )
+    
+    # Define multi-agent graph
+    multi_agent_graph = (
+        StateGraph(MessagesState)
+        .add_node(flight_assistant)
+        .add_node(hotel_assistant)
+        .add_edge(START, "flight_assistant")
+        .compile()
+    )
+    
+    # Run the multi-agent graph
+    for chunk in multi_agent_graph.stream(
+        {
+            "messages": [
+                {
+                    "role": "user",
+                    "content": "book a flight from BOS to JFK and a stay at McKittrick Hotel"
+                }
+            ]
+        },
+        # highlight-next-line
+        subgraphs=True
+    ):
+        pretty_print_messages(chunk)
+    ```
+
+    1. Access agent's state
+    2. The `Command` primitive allows specifying a state update and a node transition as a single operation, making it useful for implementing handoffs.
+    3. Name of the agent or node to hand off to.
+    4. Take the agent's messages and **add** them to the parent's **state** as part of the handoff. The next agent will see the parent state.
+    5. Indicate to LangGraph that we need to navigate to agent node in a **parent** multi-agent graph.
+
+## Multi-turn conversation
+
+Users might want to engage in a *multi-turn conversation* with one or more agents. To build a system that can handle this, you can create a node that uses an [`interrupt`][langgraph.types.interrupt] to collect user input and routes back to the **active** agent.
+
+The agents can then be implemented as nodes in a graph that executes agent steps and determines the next action:
+
+1. **Wait for user input** to continue the conversation, or  
+2. **Route to another agent** (or back to itself, such as in a loop) via a [handoff](#handoffs)
+
+```python
+def human(state) -> Command[Literal["agent", "another_agent"]]:
+    """A node for collecting user input."""
+    user_input = interrupt(value="Ready for user input.")
+
+    # Determine the active agent.
+    active_agent = ...
+
+    ...
+    return Command(
+        update={
+            "messages": [{
+                "role": "human",
+                "content": user_input,
+            }]
+        },
+        goto=active_agent
+    )
+
+def agent(state) -> Command[Literal["agent", "another_agent", "human"]]:
+    # The condition for routing/halting can be anything, e.g. LLM tool call / structured output, etc.
+    goto = get_next_agent(...)  # 'agent' / 'another_agent'
+    if goto:
+        return Command(goto=goto, update={"my_state_key": "my_state_value"})
+    else:
+        return Command(goto="human") # Go to human node
+```
+
+??? example "Full example: multi-agent system for travel recommendations"
+
+    In this example, we will build a team of travel assistant agents that can communicate with each other via handoffs.
+    
+    We will create 2 agents:
+    
+    * travel_advisor: can help with travel destination recommendations. Can ask hotel_advisor for help.
+    * hotel_advisor: can help with hotel recommendations. Can ask travel_advisor for help.
+
+    ```python
+    from langchain_anthropic import ChatAnthropic
+    from langgraph.graph import MessagesState, StateGraph, START
+    from langgraph.prebuilt import create_react_agent, InjectedState
+    from langgraph.types import Command, interrupt
+    from langgraph.checkpoint.memory import MemorySaver
+    
+    
+    model = ChatAnthropic(model="claude-3-5-sonnet-latest")
+
+    class MultiAgentState(MessagesState):
+        last_active_agent: str
+    
+    
+    # Define travel advisor tools and ReAct agent
+    travel_advisor_tools = [
+        get_travel_recommendations,
+        make_handoff_tool(agent_name="hotel_advisor"),
+    ]
+    travel_advisor = create_react_agent(
+        model,
+        travel_advisor_tools,
+        prompt=(
+            "You are a general travel expert that can recommend travel destinations (e.g. countries, cities, etc). "
+            "If you need hotel recommendations, ask 'hotel_advisor' for help. "
+            "You MUST include human-readable response before transferring to another agent."
+        ),
+    )
+    
+    
+    def call_travel_advisor(
+        state: MultiAgentState,
+    ) -> Command[Literal["hotel_advisor", "human"]]:
+        # You can also add additional logic like changing the input to the agent / output from the agent, etc.
+        # NOTE: we're invoking the ReAct agent with the full history of messages in the state
+        response = travel_advisor.invoke(state)
+        update = {**response, "last_active_agent": "travel_advisor"}
+        return Command(update=update, goto="human")
+    
+    
+    # Define hotel advisor tools and ReAct agent
+    hotel_advisor_tools = [
+        get_hotel_recommendations,
+        make_handoff_tool(agent_name="travel_advisor"),
+    ]
+    hotel_advisor = create_react_agent(
+        model,
+        hotel_advisor_tools,
+        prompt=(
+            "You are a hotel expert that can provide hotel recommendations for a given destination. "
+            "If you need help picking travel destinations, ask 'travel_advisor' for help."
+            "You MUST include human-readable response before transferring to another agent."
+        ),
+    )
+    
+    
+    def call_hotel_advisor(
+        state: MultiAgentState,
+    ) -> Command[Literal["travel_advisor", "human"]]:
+        response = hotel_advisor.invoke(state)
+        update = {**response, "last_active_agent": "hotel_advisor"}
+        return Command(update=update, goto="human")
+    
+    
+    def human_node(
+        state: MultiAgentState, config
+    ) -> Command[Literal["hotel_advisor", "travel_advisor", "human"]]:
+        """A node for collecting user input."""
+    
+        user_input = interrupt(value="Ready for user input.")
+        active_agent = state["last_active_agent"]
+    
+        return Command(
+            update={
+                "messages": [
+                    {
+                        "role": "human",
+                        "content": user_input,
+                    }
+                ]
+            },
+            goto=active_agent,
+        )
+    
+    
+    builder = StateGraph(MultiAgentState)
+    builder.add_node("travel_advisor", call_travel_advisor)
+    builder.add_node("hotel_advisor", call_hotel_advisor)
+    
+    # This adds a node to collect human input, which will route
+    # back to the active agent.
+    builder.add_node("human", human_node)
+    
+    # We'll always start with a general travel advisor.
+    builder.add_edge(START, "travel_advisor")
+    
+    
+    checkpointer = MemorySaver()
+    graph = builder.compile(checkpointer=checkpointer)
+    ```
+    
+    Let's test a multi turn conversation with this application.
+
+    ```python
+    import uuid
+    
+    thread_config = {"configurable": {"thread_id": str(uuid.uuid4())}}
+    
+    inputs = [
+        # 1st round of conversation,
+        {
+            "messages": [
+                {"role": "user", "content": "i wanna go somewhere warm in the caribbean"}
+            ]
+        },
+        # Since we're using `interrupt`, we'll need to resume using the Command primitive.
+        # 2nd round of conversation,
+        Command(
+            resume="could you recommend a nice hotel in one of the areas and tell me which area it is."
+        ),
+        # 3rd round of conversation,
+        Command(
+            resume="i like the first one. could you recommend something to do near the hotel?"
+        ),
+    ]
+    
+    for idx, user_input in enumerate(inputs):
+        print()
+        print(f"--- Conversation Turn {idx + 1} ---")
+        print()
+        print(f"User: {user_input}")
+        print()
+        for update in graph.stream(
+            user_input,
+            config=thread_config,
+            stream_mode="updates",
+        ):
+            for node_id, value in update.items():
+                if isinstance(value, dict) and value.get("messages", []):
+                    last_message = value["messages"][-1]
+                    if isinstance(last_message, dict) or last_message.type != "ai":
+                        continue
+                    print(f"{node_id}: {last_message.content}")
+    ```
+    
+    ```
+    --- Conversation Turn 1 ---
+    
+    User: {'messages': [{'role': 'user', 'content': 'i wanna go somewhere warm in the caribbean'}]}
+    
+    travel_advisor: Based on the recommendations, Aruba would be an excellent choice for your Caribbean getaway! Aruba is known as "One Happy Island" and offers:
+    - Year-round warm weather with consistent temperatures around 82°F (28°C)
+    - Beautiful white sand beaches like Eagle Beach and Palm Beach
+    - Clear turquoise waters perfect for swimming and snorkeling
+    - Minimal rainfall and location outside the hurricane belt
+    - A blend of Caribbean and Dutch culture
+    - Great dining options and nightlife
+    - Various water sports and activities
+    
+    Would you like me to get some specific hotel recommendations in Aruba for your stay? I can transfer you to our hotel advisor who can help with accommodations.
+    
+    --- Conversation Turn 2 ---
+    
+    User: Command(resume='could you recommend a nice hotel in one of the areas and tell me which area it is.')
+    
+    hotel_advisor: Based on the recommendations, I can suggest two excellent options:
+    
+    1. The Ritz-Carlton, Aruba - Located in Palm Beach
+    - This luxury resort is situated in the vibrant Palm Beach area
+    - Known for its exceptional service and amenities
+    - Perfect if you want to be close to dining, shopping, and entertainment
+    - Features multiple restaurants, a casino, and a world-class spa
+    - Located on a pristine stretch of Palm Beach
+    
+    2. Bucuti & Tara Beach Resort - Located in Eagle Beach
+    - An adults-only boutique resort on Eagle Beach
+    - Known for being more intimate and peaceful
+    - Award-winning for its sustainability practices
+    - Perfect for a romantic getaway or peaceful vacation
+    - Located on one of the most beautiful beaches in the Caribbean
+    
+    Would you like more specific information about either of these properties or their locations?
+    
+    --- Conversation Turn 3 ---
+    
+    User: Command(resume='i like the first one. could you recommend something to do near the hotel?')
+    
+    travel_advisor: Near the Ritz-Carlton in Palm Beach, here are some highly recommended activities:
+    
+    1. Visit the Palm Beach Plaza Mall - Just a short walk from the hotel, featuring shopping, dining, and entertainment
+    2. Try your luck at the Stellaris Casino - It's right in the Ritz-Carlton
+    3. Take a sunset sailing cruise - Many depart from the nearby pier
+    4. Visit the California Lighthouse - A scenic landmark just north of Palm Beach
+    5. Enjoy water sports at Palm Beach:
+       - Jet skiing
+       - Parasailing
+       - Snorkeling
+       - Stand-up paddleboarding
+    
+    Would you like more specific information about any of these activities or would you like to know about other options in the area?
+    ```
+
+## Prebuilt implementations
+
+LangGraph comes with prebuilt implementations of two of the most popular multi-agent architectures:
+
+- [supervisor](../agents/multi-agent.md#supervisor) — individual agents are coordinated by a central supervisor agent. The supervisor controls all communication flow and task delegation, making decisions about which agent to invoke based on the current context and task requirements. You can use [`langgraph-supervisor`](https://github.com/langchain-ai/langgraph-supervisor-py) library to create a supervisor multi-agent systems.
+- [swarm](../agents/multi-agent.md#supervisor) — agents dynamically hand off control to one another based on their specializations. The system remembers which agent was last active, ensuring that on subsequent interactions, the conversation resumes with that agent. You can use [`langgraph-swarm`](https://github.com/langchain-ai/langgraph-swarm-py) library to create a swarm multi-agent systems. 

docs/docs/how-tos/run-id-langsmith.md

@@ -0,0 +1,155 @@
+# How to pass custom run ID or set tags and metadata for graph runs in LangSmith
+
+!!! tip "Prerequisites"
+    This guide assumes familiarity with the following:
+    
+    - [LangSmith Documentation](https://docs.smith.langchain.com)
+    - [LangSmith Platform](https://smith.langchain.com)
+    - [RunnableConfig](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.config.RunnableConfig.html#langchain_core.runnables.config.RunnableConfig)
+    - [Add metadata and tags to traces](https://docs.smith.langchain.com/how_to_guides/tracing/trace_with_langchain#add-metadata-and-tags-to-traces)
+    - [Customize run name](https://docs.smith.langchain.com/how_to_guides/tracing/trace_with_langchain#customize-run-name)
+
+Debugging graph runs can sometimes be difficult to do in an IDE or terminal. [LangSmith](https://docs.smith.langchain.com) lets you use trace data to debug, test, and monitor your LLM apps built with LangGraph — read the [LangSmith documentation](https://docs.smith.langchain.com) for more information on how to get started.
+
+To make it easier to identify and analyzed traces generated during graph invocation, you can set additional configuration at run time (see [RunnableConfig](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.config.RunnableConfig.html#langchain_core.runnables.config.RunnableConfig)):
+
+| **Field**   | **Type**            | **Description**                                                                                                    |
+|-------------|---------------------|--------------------------------------------------------------------------------------------------------------------|
+| run_name    | `str`               | Name for the tracer run for this call. Defaults to the name of the class.                                          |
+| run_id      | `UUID`              | Unique identifier for the tracer run for this call. If not provided, a new UUID will be generated.                 |
+| tags        | `List[str]`         | Tags for this call and any sub-calls (e.g., a Chain calling an LLM). You can use these to filter calls.            |
+| metadata    | `Dict[str, Any]`    | Metadata for this call and any sub-calls (e.g., a Chain calling an LLM). Keys should be strings, values should be JSON-serializable. |
+
+LangGraph graphs implement the [LangChain Runnable Interface](https://python.langchain.com/api_reference/core/runnables/langchain_core.runnables.base.Runnable.html) and accept a second argument (`RunnableConfig`) in methods like `invoke`, `ainvoke`, `stream` etc.
+
+The LangSmith platform will allow you to search and filter traces based on `run_name`, `run_id`, `tags` and `metadata`.
+
+## TLDR
+
+```python
+import uuid
+# Generate a random UUID -- it must be a UUID
+config = {"run_id": uuid.uuid4()}, "tags": ["my_tag1"], "metadata": {"a": 5}}
+# Works with all standard Runnable methods 
+# like invoke, batch, ainvoke, astream_events etc
+graph.stream(inputs, config, stream_mode="values")
+```
+
+The rest of the how to guide will show a full agent.
+
+## Setup
+
+First, let's install the required packages and set our API keys
+
+```python
+%%capture --no-stderr
+%pip install --quiet -U langgraph langchain_openai
+```
+
+```python
+import getpass
+import os
+
+
+def _set_env(var: str):
+    if not os.environ.get(var):
+        os.environ[var] = getpass.getpass(f"{var}: ")
+
+
+_set_env("OPENAI_API_KEY")
+_set_env("LANGSMITH_API_KEY")
+```
+
+!!! tip
+    Sign up for LangSmith to quickly spot issues and improve the performance of your LangGraph projects. [LangSmith](https://docs.smith.langchain.com) lets you use trace data to debug, test, and monitor your LLM apps built with LangGraph — read more about how to get started [here](https://docs.smith.langchain.com).
+
+## Define the graph
+
+For this example we will use the [prebuilt ReAct agent](https://langchain-ai.github.io/langgraph/how-tos/create-react-agent/).
+
+```python
+from langchain_openai import ChatOpenAI
+from typing import Literal
+from langgraph.prebuilt import create_react_agent
+from langchain_core.tools import tool
+
+# First we initialize the model we want to use.
+model = ChatOpenAI(model="gpt-4o", temperature=0)
+
+
+# For this tutorial we will use custom tool that returns pre-defined values for weather in two cities (NYC & SF)
+@tool
+def get_weather(city: Literal["nyc", "sf"]):
+    """Use this to get weather information."""
+    if city == "nyc":
+        return "It might be cloudy in nyc"
+    elif city == "sf":
+        return "It's always sunny in sf"
+    else:
+        raise AssertionError("Unknown city")
+
+
+tools = [get_weather]
+
+
+# Define the graph
+graph = create_react_agent(model, tools=tools)
+```
+
+## Run your graph
+
+Now that we've defined our graph let's run it once and view the trace in LangSmith. In order for our trace to be easily accessible in LangSmith, we will pass in a custom `run_id` in the config.
+
+This assumes that you have set your `LANGSMITH_API_KEY` environment variable.
+
+Note that you can also configure what project to trace to by setting the `LANGCHAIN_PROJECT` environment variable, by default runs will be traced to the `default` project.
+
+```python
+import uuid
+
+
+def print_stream(stream):
+    for s in stream:
+        message = s["messages"][-1]
+        if isinstance(message, tuple):
+            print(message)
+        else:
+            message.pretty_print()
+
+
+inputs = {"messages": [("user", "what is the weather in sf")]}
+
+config = {"run_name": "agent_007", "tags": ["cats are awesome"]}
+
+print_stream(graph.stream(inputs, config, stream_mode="values"))
+```
+
+**Output:**
+```
+================================ Human Message ==================================
+
+what is the weather in sf
+================================== Ai Message ===================================
+Tool Calls:
+  get_weather (call_9ZudXyMAdlUjptq9oMGtQo8o)
+ Call ID: call_9ZudXyMAdlUjptq9oMGtQo8o
+  Args:
+    city: sf
+================================= Tool Message ==================================
+Name: get_weather
+
+It's always sunny in sf
+================================== Ai Message ===================================
+
+The weather in San Francisco is currently sunny.
+```
+
+## View the trace in LangSmith
+
+Now that we've ran our graph, let's head over to LangSmith and view our trace. First click into the project that you traced to (in our case the default project). You should see a run with the custom run name "agent_007".
+
+![LangSmith Trace View](assets/d38d1f2b-0f4c-4707-b531-a3c749de987f.png)
+
+In addition, you will be able to filter traces after the fact using the tags or metadata provided. For example,
+
+![LangSmith Filter View](assets/410e0089-2ab8-46bb-a61a-827187fd46b3.png) 

docs/docs/how-tos/subgraph.ipynb

@@ -1,559 +0,0 @@
-{
- "cells": [
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Use subgraphs\n",
-    "\n",
-    "This guide explains the mechanics of using [subgraphs](../../concepts/subgraphs). A common application of subgraphs is to build [multi-agent](../../concepts/multi_agent) systems.\n",
-    "\n",
-    "When adding subgraphs, you need to define how the parent graph and the subgraph communicate:\n",
-    "\n",
-    "* [Shared state schemas](#shared-state-schemas) — parent and subgraph have **shared state keys** in their state [schemas](../../concepts/low_level#state)\n",
-    "* [Different state schemas](#different-state-schemas) — **no shared state keys** in parent and subgraph [schemas](../../concepts/low_level#state)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install -U langgraph"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "<div class=\"admonition tip\">\n",
-    "    <p class=\"admonition-title\">Set up <a href=\"https://smith.langchain.com\">LangSmith</a> for LangGraph development</p>\n",
-    "    <p style=\"padding-top: 5px;\">\n",
-    "        Sign up for LangSmith to quickly spot issues and improve the performance of your LangGraph projects. LangSmith lets you use trace data to debug, test, and monitor your LLM apps built with LangGraph — read more about how to get started <a href=\"https://docs.smith.langchain.com\">here</a>. \n",
-    "    </p>\n",
-    "</div>"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Shared state schemas\n",
-    "\n",
-    "A common case is for the parent graph and subgraph to communicate over a shared state key (channel) in the [schema](../../concepts/low_level#state). For example, in [multi-agent](../../concepts/multi_agent) systems, the agents often communicate over a shared [messages](https://langchain-ai.github.io/langgraph/concepts/low_level/#why-use-messages) key.\n",
-    "\n",
-    "If your subgraph shares state keys with the parent graph, you can follow these steps to add it to your graph:\n",
-    "\n",
-    "1. Define the subgraph workflow (`subgraph_builder` in the example below) and compile it\n",
-    "2. Pass compiled subgraph to the `.add_node` method when defining the parent graph workflow\n",
-    "\n",
-    "```python\n",
-    "from typing_extensions import TypedDict\n",
-    "from langgraph.graph.state import StateGraph, START\n",
-    "\n",
-    "class State(TypedDict):\n",
-    "    foo: str\n",
-    "\n",
-    "# Subgraph\n",
-    "\n",
-    "def subgraph_node_1(state: State):\n",
-    "    return {\"foo\": \"hi! \" + state[\"foo\"]}\n",
-    "\n",
-    "subgraph_builder = StateGraph(State)\n",
-    "subgraph_builder.add_node(subgraph_node_1)\n",
-    "subgraph_builder.add_edge(START, \"subgraph_node_1\")\n",
-    "# highlight-next-line\n",
-    "subgraph = subgraph_builder.compile()\n",
-    "\n",
-    "# Parent graph\n",
-    "\n",
-    "builder = StateGraph(State)\n",
-    "# highlight-next-line\n",
-    "builder.add_node(\"node_1\", subgraph)\n",
-    "builder.add_edge(START, \"node_1\")\n",
-    "graph = builder.compile()\n",
-    "```\n",
-    "\n",
-    "??? example \"Full example: shared state schemas\"\n",
-    "\n",
-    "    ```python\n",
-    "    from typing_extensions import TypedDict\n",
-    "    from langgraph.graph.state import StateGraph, START\n",
-    "\n",
-    "    # Define subgraph\n",
-    "    class SubgraphState(TypedDict):\n",
-    "        foo: str  # (1)! \n",
-    "        bar: str  # (2)!\n",
-    "    \n",
-    "    def subgraph_node_1(state: SubgraphState):\n",
-    "        return {\"bar\": \"bar\"}\n",
-    "    \n",
-    "    def subgraph_node_2(state: SubgraphState):\n",
-    "        # note that this node is using a state key ('bar') that is only available in the subgraph\n",
-    "        # and is sending update on the shared state key ('foo')\n",
-    "        return {\"foo\": state[\"foo\"] + state[\"bar\"]}\n",
-    "    \n",
-    "    subgraph_builder = StateGraph(SubgraphState)\n",
-    "    subgraph_builder.add_node(subgraph_node_1)\n",
-    "    subgraph_builder.add_node(subgraph_node_2)\n",
-    "    subgraph_builder.add_edge(START, \"subgraph_node_1\")\n",
-    "    subgraph_builder.add_edge(\"subgraph_node_1\", \"subgraph_node_2\")\n",
-    "    subgraph = subgraph_builder.compile()\n",
-    "    \n",
-    "    # Define parent graph\n",
-    "    class ParentState(TypedDict):\n",
-    "        foo: str\n",
-    "    \n",
-    "    def node_1(state: ParentState):\n",
-    "        return {\"foo\": \"hi! \" + state[\"foo\"]}\n",
-    "    \n",
-    "    builder = StateGraph(ParentState)\n",
-    "    builder.add_node(\"node_1\", node_1)\n",
-    "    # highlight-next-line\n",
-    "    builder.add_node(\"node_2\", subgraph)\n",
-    "    builder.add_edge(START, \"node_1\")\n",
-    "    builder.add_edge(\"node_1\", \"node_2\")\n",
-    "    graph = builder.compile()\n",
-    "    \n",
-    "    for chunk in graph.stream({\"foo\": \"foo\"}):\n",
-    "        print(chunk)\n",
-    "    ```\n",
-    "\n",
-    "    1. This key is shared with the parent graph state\n",
-    "    2. This key is private to the `SubgraphState` and is not visible to the parent graph\n",
-    "    \n",
-    "    ```\n",
-    "    {'node_1': {'foo': 'hi! foo'}}\n",
-    "    {'node_2': {'foo': 'hi! foobar'}}\n",
-    "    ```\n",
-    "\n",
-    "    ```"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Different state schemas\n",
-    "\n",
-    "For more complex systems you might want to define subgraphs that have a **completely different schema** from the parent graph (no shared keys). For example, you might want to keep a private message history for each of the agents in a [multi-agent](../concepts/multi_agent.md) system.\n",
-    "\n",
-    "If that's the case for your application, you need to define a node **function that invokes the subgraph**. This function needs to transform the input (parent) state to the subgraph state before invoking the subgraph, and transform the results back to the parent state before returning the state update from the node.\n",
-    "\n",
-    "```python\n",
-    "from typing_extensions import TypedDict\n",
-    "from langgraph.graph.state import StateGraph, START\n",
-    "\n",
-    "class SubgraphState(TypedDict):\n",
-    "    bar: str\n",
-    "\n",
-    "# Subgraph\n",
-    "\n",
-    "def subgraph_node_1(state: SubgraphState):\n",
-    "    return {\"bar\": \"hi! \" + state[\"bar\"]}\n",
-    "\n",
-    "subgraph_builder = StateGraph(SubgraphState)\n",
-    "subgraph_builder.add_node(subgraph_node_1)\n",
-    "subgraph_builder.add_edge(START, \"subgraph_node_1\")\n",
-    "# highlight-next-line\n",
-    "subgraph = subgraph_builder.compile()\n",
-    "\n",
-    "# Parent graph\n",
-    "\n",
-    "class State(TypedDict):\n",
-    "    foo: str\n",
-    "\n",
-    "def call_subgraph(state: State):\n",
-    "    # highlight-next-line\n",
-    "    subgraph_output = subgraph.invoke({\"bar\": state[\"foo\"]})  # (1)!\n",
-    "    # highlight-next-line\n",
-    "    return {\"foo\": subgraph_output[\"bar\"]}  # (2)!\n",
-    "\n",
-    "builder = StateGraph(State)\n",
-    "# highlight-next-line\n",
-    "builder.add_node(\"node_1\", call_subgraph)\n",
-    "builder.add_edge(START, \"node_1\")\n",
-    "graph = builder.compile()\n",
-    "```\n",
-    "\n",
-    "1. Transform the state to the subgraph state\n",
-    "2. Transform response back to the parent state\n",
-    "\n",
-    "??? example \"Full example: different state schemas\"\n",
-    "\n",
-    "    ```python\n",
-    "    from typing_extensions import TypedDict\n",
-    "    from langgraph.graph.state import StateGraph, START\n",
-    "\n",
-    "    # Define subgraph\n",
-    "    class SubgraphState(TypedDict):\n",
-    "        # note that none of these keys are shared with the parent graph state\n",
-    "        bar: str\n",
-    "        baz: str\n",
-    "    \n",
-    "    def subgraph_node_1(state: SubgraphState):\n",
-    "        return {\"baz\": \"baz\"}\n",
-    "    \n",
-    "    def subgraph_node_2(state: SubgraphState):\n",
-    "        return {\"bar\": state[\"bar\"] + state[\"baz\"]}\n",
-    "    \n",
-    "    subgraph_builder = StateGraph(SubgraphState)\n",
-    "    subgraph_builder.add_node(subgraph_node_1)\n",
-    "    subgraph_builder.add_node(subgraph_node_2)\n",
-    "    subgraph_builder.add_edge(START, \"subgraph_node_1\")\n",
-    "    subgraph_builder.add_edge(\"subgraph_node_1\", \"subgraph_node_2\")\n",
-    "    subgraph = subgraph_builder.compile()\n",
-    "    \n",
-    "    # Define parent graph\n",
-    "    class ParentState(TypedDict):\n",
-    "        foo: str\n",
-    "    \n",
-    "    def node_1(state: ParentState):\n",
-    "        return {\"foo\": \"hi! \" + state[\"foo\"]}\n",
-    "    \n",
-    "    def node_2(state: ParentState):\n",
-    "        # highlight-next-line\n",
-    "        response = subgraph.invoke({\"bar\": state[\"foo\"]})  # (1)!\n",
-    "        # highlight-next-line\n",
-    "        return {\"foo\": response[\"bar\"]}  # (2)!\n",
-    "    \n",
-    "    \n",
-    "    builder = StateGraph(ParentState)\n",
-    "    builder.add_node(\"node_1\", node_1)\n",
-    "    # highlight-next-line\n",
-    "    builder.add_node(\"node_2\", node_2)\n",
-    "    builder.add_edge(START, \"node_1\")\n",
-    "    builder.add_edge(\"node_1\", \"node_2\")\n",
-    "    graph = builder.compile()\n",
-    "    \n",
-    "    for chunk in graph.stream({\"foo\": \"foo\"}, subgraphs=True):\n",
-    "        print(chunk)\n",
-    "    ```\n",
-    "\n",
-    "    1. Transform the state to the subgraph state\n",
-    "    2. Transform response back to the parent state\n",
-    "\n",
-    "    ```\n",
-    "    ((), {'node_1': {'foo': 'hi! foo'}})\n",
-    "    (('node_2:9c36dd0f-151a-cb42-cbad-fa2f851f9ab7',), {'subgraph_node_1': {'baz': 'baz'}})\n",
-    "    (('node_2:9c36dd0f-151a-cb42-cbad-fa2f851f9ab7',), {'subgraph_node_2': {'bar': 'hi! foobaz'}})\n",
-    "    ((), {'node_2': {'foo': 'hi! foobaz'}})\n",
-    "    ```\n",
-    "\n",
-    "??? example \"Full example: different state schemas (two levels of subgraphs)\"\n",
-    "\n",
-    "    This is an example with two levels of subgraphs: parent -> child -> grandchild.\n",
-    "\n",
-    "    ```python\n",
-    "    # Grandchild graph\n",
-    "    from typing_extensions import TypedDict\n",
-    "    from langgraph.graph.state import StateGraph, START, END\n",
-    "    \n",
-    "    class GrandChildState(TypedDict):\n",
-    "        my_grandchild_key: str\n",
-    "    \n",
-    "    def grandchild_1(state: GrandChildState) -> GrandChildState:\n",
-    "        # NOTE: child or parent keys will not be accessible here\n",
-    "        return {\"my_grandchild_key\": state[\"my_grandchild_key\"] + \", how are you\"}\n",
-    "    \n",
-    "    \n",
-    "    grandchild = StateGraph(GrandChildState)\n",
-    "    grandchild.add_node(\"grandchild_1\", grandchild_1)\n",
-    "    \n",
-    "    grandchild.add_edge(START, \"grandchild_1\")\n",
-    "    grandchild.add_edge(\"grandchild_1\", END)\n",
-    "    \n",
-    "    grandchild_graph = grandchild.compile()\n",
-    "    \n",
-    "    # Child graph\n",
-    "    class ChildState(TypedDict):\n",
-    "        my_child_key: str\n",
-    "    \n",
-    "    def call_grandchild_graph(state: ChildState) -> ChildState:\n",
-    "        # NOTE: parent or grandchild keys won't be accessible here\n",
-    "        grandchild_graph_input = {\"my_grandchild_key\": state[\"my_child_key\"]}  # (1)!\n",
-    "        # highlight-next-line\n",
-    "        grandchild_graph_output = grandchild_graph.invoke(grandchild_graph_input)\n",
-    "        return {\"my_child_key\": grandchild_graph_output[\"my_grandchild_key\"] + \" today?\"}  # (2)!\n",
-    "    \n",
-    "    child = StateGraph(ChildState)\n",
-    "    # highlight-next-line\n",
-    "    child.add_node(\"child_1\", call_grandchild_graph)  # (3)!\n",
-    "    child.add_edge(START, \"child_1\")\n",
-    "    child.add_edge(\"child_1\", END)\n",
-    "    child_graph = child.compile()\n",
-    "    \n",
-    "    # Parent graph\n",
-    "    class ParentState(TypedDict):\n",
-    "        my_key: str\n",
-    "    \n",
-    "    def parent_1(state: ParentState) -> ParentState:\n",
-    "        # NOTE: child or grandchild keys won't be accessible here\n",
-    "        return {\"my_key\": \"hi \" + state[\"my_key\"]}\n",
-    "    \n",
-    "    def parent_2(state: ParentState) -> ParentState:\n",
-    "        return {\"my_key\": state[\"my_key\"] + \" bye!\"}\n",
-    "    \n",
-    "    def call_child_graph(state: ParentState) -> ParentState:\n",
-    "        child_graph_input = {\"my_child_key\": state[\"my_key\"]}  # (4)!\n",
-    "        # highlight-next-line\n",
-    "        child_graph_output = child_graph.invoke(child_graph_input)\n",
-    "        return {\"my_key\": child_graph_output[\"my_child_key\"]}  # (5)!\n",
-    "    \n",
-    "    parent = StateGraph(ParentState)\n",
-    "    parent.add_node(\"parent_1\", parent_1)\n",
-    "    # highlight-next-line\n",
-    "    parent.add_node(\"child\", call_child_graph)  # (6)!\n",
-    "    parent.add_node(\"parent_2\", parent_2)\n",
-    "    \n",
-    "    parent.add_edge(START, \"parent_1\")\n",
-    "    parent.add_edge(\"parent_1\", \"child\")\n",
-    "    parent.add_edge(\"child\", \"parent_2\")\n",
-    "    parent.add_edge(\"parent_2\", END)\n",
-    "    \n",
-    "    parent_graph = parent.compile()\n",
-    "    \n",
-    "    for chunk in parent_graph.stream({\"my_key\": \"Bob\"}, subgraphs=True):\n",
-    "        print(chunk)\n",
-    "    ```\n",
-    "\n",
-    "    1. We're transforming the state from the child state channels (`my_child_key`) to the child state channels (`my_grandchild_key`)\n",
-    "    2. We're transforming the state from the grandchild state channels (`my_grandchild_key`) back to the child state channels (`my_child_key`)\n",
-    "    3. We're passing a function here instead of just compiled graph (`grandchild_graph`)\n",
-    "    4. We're transforming the state from the parent state channels (`my_key`) to the child state channels (`my_child_key`)\n",
-    "    5. We're transforming the state from the child state channels (`my_child_key`) back to the parent state channels (`my_key`)\n",
-    "    6. We're passing a function here instead of just a compiled graph (`child_graph`)\n",
-    "\n",
-    "    ```\n",
-    "    ((), {'parent_1': {'my_key': 'hi Bob'}})\n",
-    "    (('child:2e26e9ce-602f-862c-aa66-1ea5a4655e3b', 'child_1:781bb3b1-3971-84ce-810b-acf819a03f9c'), {'grandchild_1': {'my_grandchild_key': 'hi Bob, how are you'}})\n",
-    "    (('child:2e26e9ce-602f-862c-aa66-1ea5a4655e3b',), {'child_1': {'my_child_key': 'hi Bob, how are you today?'}})\n",
-    "    ((), {'child': {'my_key': 'hi Bob, how are you today?'}})\n",
-    "    ((), {'parent_2': {'my_key': 'hi Bob, how are you today? bye!'}})\n",
-    "    ```"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Add persistence \n",
-    "\n",
-    "You only need to **provide the checkpointer when compiling the parent graph**. LangGraph will automatically propagate the checkpointer to the child subgraphs.\n",
-    "\n",
-    "```python\n",
-    "from langgraph.graph import START, StateGraph\n",
-    "from langgraph.checkpoint.memory import InMemorySaver\n",
-    "from typing_extensions import TypedDict\n",
-    "\n",
-    "class State(TypedDict):\n",
-    "    foo: str\n",
-    "\n",
-    "# Subgraph\n",
-    "\n",
-    "def subgraph_node_1(state: State):\n",
-    "    return {\"foo\": state[\"foo\"] + \"bar\"}\n",
-    "\n",
-    "subgraph_builder = StateGraph(State)\n",
-    "subgraph_builder.add_node(subgraph_node_1)\n",
-    "subgraph_builder.add_edge(START, \"subgraph_node_1\")\n",
-    "# highlight-next-line\n",
-    "subgraph = subgraph_builder.compile()\n",
-    "\n",
-    "# Parent graph\n",
-    "\n",
-    "builder = StateGraph(State)\n",
-    "# highlight-next-line\n",
-    "builder.add_node(\"node_1\", subgraph)\n",
-    "builder.add_edge(START, \"node_1\")\n",
-    "\n",
-    "checkpointer = InMemorySaver()\n",
-    "# highlight-next-line\n",
-    "graph = builder.compile(checkpointer=checkpointer)\n",
-    "```    \n",
-    "\n",
-    "If you want the subgraph to **have its own memory**, you can compile it `with checkpointer=True`. This is useful in [multi-agent](../../concepts/multi_agent) systems, if you want agents to keep track of their internal message histories:\n",
-    "\n",
-    "```python\n",
-    "subgraph_builder = StateGraph(...)\n",
-    "# highlight-next-line\n",
-    "subgraph = subgraph_builder.compile(checkpointer=True)\n",
-    "```"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## View subgraph state\n",
-    "\n",
-    "When you enable [persistence](../persistence), you can [inspect the graph state](../persistence#manage-checkpoints) (checkpoint) via `graph.get_state(config)`. To view the subgraph state, you can use `graph.get_state(config, subgraphs=True)`.\n",
-    "\n",
-    "!!! important \"Available **only** when interrupted\"\n",
-    "\n",
-    "    Subgraph state can only be viewed **when the subgraph is interrupted**. Once you resume the graph, you won't be able to access the subgraph state.\n",
-    "\n",
-    "??? example \"View interrupted subgraph state\"\n",
-    "\n",
-    "    ```python\n",
-    "    from langgraph.graph import START, StateGraph\n",
-    "    from langgraph.checkpoint.memory import InMemorySaver\n",
-    "    from langgraph.types import interrupt, Command\n",
-    "    from typing_extensions import TypedDict\n",
-    "    \n",
-    "    class State(TypedDict):\n",
-    "        foo: str\n",
-    "    \n",
-    "    # Subgraph\n",
-    "    \n",
-    "    def subgraph_node_1(state: State):\n",
-    "        # highlight-next-line\n",
-    "        value = interrupt(\"Provide value:\")\n",
-    "        return {\"foo\": state[\"foo\"] + value}\n",
-    "    \n",
-    "    subgraph_builder = StateGraph(State)\n",
-    "    subgraph_builder.add_node(subgraph_node_1)\n",
-    "    subgraph_builder.add_edge(START, \"subgraph_node_1\")\n",
-    "    \n",
-    "    subgraph = subgraph_builder.compile()\n",
-    "    \n",
-    "    # Parent graph\n",
-    "        \n",
-    "    builder = StateGraph(State)\n",
-    "    # highlight-next-line\n",
-    "    builder.add_node(\"node_1\", subgraph)\n",
-    "    builder.add_edge(START, \"node_1\")\n",
-    "    \n",
-    "    checkpointer = InMemorySaver()\n",
-    "    # highlight-next-line\n",
-    "    graph = builder.compile(checkpointer=checkpointer)\n",
-    "    \n",
-    "    config = {\"configurable\": {\"thread_id\": \"1\"}}\n",
-    "    \n",
-    "    graph.invoke({\"foo\": \"\"}, config)\n",
-    "    parent_state = graph.get_state(config)\n",
-    "    # highlight-next-line\n",
-    "    subgraph_state = graph.get_state(config, subgraphs=True).tasks[0].state  # (1)!\n",
-    "    \n",
-    "    # resume the subgraph\n",
-    "    graph.invoke(Command(resume=\"bar\"), config)\n",
-    "    ```\n",
-    "    \n",
-    "    1. This will be available only when the subgraph is interrupted. Once you resume the graph, you won't be able to access the subgraph state."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Stream subgraph outputs\n",
-    "\n",
-    "To include outputs from [subgraphs](../concepts/low_level.md#subgraphs) in the streamed outputs, you can set `subgraphs=True` in the `.stream()` method of the parent graph. This will stream outputs from both the parent graph and any subgraphs.\n",
-    "\n",
-    "```python\n",
-    "for chunk in graph.stream(\n",
-    "    {\"foo\": \"foo\"},\n",
-    "    # highlight-next-line\n",
-    "    subgraphs=True, # (1)!\n",
-    "    stream_mode=\"updates\",\n",
-    "):\n",
-    "    print(chunk)\n",
-    "```\n",
-    "\n",
-    "1. Set `subgraphs=True` to stream outputs from subgraphs.\n",
-    "\n",
-    "??? example \"Stream from subgraphs\"\n",
-    "\n",
-    "    ```python\n",
-    "    from typing_extensions import TypedDict\n",
-    "    from langgraph.graph.state import StateGraph, START\n",
-    "\n",
-    "    # Define subgraph\n",
-    "    class SubgraphState(TypedDict):\n",
-    "        foo: str\n",
-    "        bar: str\n",
-    "    \n",
-    "    def subgraph_node_1(state: SubgraphState):\n",
-    "        return {\"bar\": \"bar\"}\n",
-    "    \n",
-    "    def subgraph_node_2(state: SubgraphState):\n",
-    "        # note that this node is using a state key ('bar') that is only available in the subgraph\n",
-    "        # and is sending update on the shared state key ('foo')\n",
-    "        return {\"foo\": state[\"foo\"] + state[\"bar\"]}\n",
-    "    \n",
-    "    subgraph_builder = StateGraph(SubgraphState)\n",
-    "    subgraph_builder.add_node(subgraph_node_1)\n",
-    "    subgraph_builder.add_node(subgraph_node_2)\n",
-    "    subgraph_builder.add_edge(START, \"subgraph_node_1\")\n",
-    "    subgraph_builder.add_edge(\"subgraph_node_1\", \"subgraph_node_2\")\n",
-    "    subgraph = subgraph_builder.compile()\n",
-    "    \n",
-    "    # Define parent graph\n",
-    "    class ParentState(TypedDict):\n",
-    "        foo: str\n",
-    "    \n",
-    "    def node_1(state: ParentState):\n",
-    "        return {\"foo\": \"hi! \" + state[\"foo\"]}\n",
-    "    \n",
-    "    builder = StateGraph(ParentState)\n",
-    "    builder.add_node(\"node_1\", node_1)\n",
-    "    # highlight-next-line\n",
-    "    builder.add_node(\"node_2\", subgraph)\n",
-    "    builder.add_edge(START, \"node_1\")\n",
-    "    builder.add_edge(\"node_1\", \"node_2\")\n",
-    "    graph = builder.compile()\n",
-    "\n",
-    "    for chunk in graph.stream(\n",
-    "        {\"foo\": \"foo\"},\n",
-    "        stream_mode=\"updates\",\n",
-    "        # highlight-next-line\n",
-    "        subgraphs=True, # (1)!\n",
-    "    ):\n",
-    "        print(chunk)\n",
-    "    ```\n",
-    "  \n",
-    "    1. Set `subgraphs=True` to stream outputs from subgraphs.\n",
-    "\n",
-    "    ```\n",
-    "    ((), {'node_1': {'foo': 'hi! foo'}})\n",
-    "    (('node_2:e58e5673-a661-ebb0-70d4-e298a7fc28b7',), {'subgraph_node_1': {'bar': 'bar'}})\n",
-    "    (('node_2:e58e5673-a661-ebb0-70d4-e298a7fc28b7',), {'subgraph_node_2': {'foo': 'hi! foobar'}})\n",
-    "    ((), {'node_2': {'foo': 'hi! foobar'}})\n",
-    "    ```"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.12.3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

docs/docs/how-tos/subgraph.md

@@ -0,0 +1,453 @@
+# Use subgraphs
+
+This guide explains the mechanics of using [subgraphs](../concepts/subgraphs.md). A common application of subgraphs is to build [multi-agent](../concepts/multi_agent.md) systems.
+
+When adding subgraphs, you need to define how the parent graph and the subgraph communicate:
+
+* [Shared state schemas](#shared-state-schemas) — parent and subgraph have **shared state keys** in their state [schemas](../concepts/low_level.md#state)
+* [Different state schemas](#different-state-schemas) — **no shared state keys** in parent and subgraph [schemas](../concepts/low_level.md#state)
+
+## Setup
+
+```bash
+pip install -U langgraph
+```
+
+!!! tip "Set up LangSmith for LangGraph development"
+    Sign up for [LangSmith](https://smith.langchain.com) to quickly spot issues and improve the performance of your LangGraph projects. LangSmith lets you use trace data to debug, test, and monitor your LLM apps built with LangGraph — read more about how to get started [here](https://docs.smith.langchain.com).
+
+## Shared state schemas
+
+A common case is for the parent graph and subgraph to communicate over a shared state key (channel) in the [schema](../concepts/low_level.md#state). For example, in [multi-agent](../concepts/multi_agent.md) systems, the agents often communicate over a shared [messages](https://langchain-ai.github.io/langgraph/concepts/low_level.md#why-use-messages) key.
+
+If your subgraph shares state keys with the parent graph, you can follow these steps to add it to your graph:
+
+1. Define the subgraph workflow (`subgraph_builder` in the example below) and compile it
+2. Pass compiled subgraph to the `.add_node` method when defining the parent graph workflow
+
+```python
+from typing_extensions import TypedDict
+from langgraph.graph.state import StateGraph, START
+
+class State(TypedDict):
+    foo: str
+
+# Subgraph
+
+def subgraph_node_1(state: State):
+    return {"foo": "hi! " + state["foo"]}
+
+subgraph_builder = StateGraph(State)
+subgraph_builder.add_node(subgraph_node_1)
+subgraph_builder.add_edge(START, "subgraph_node_1")
+subgraph = subgraph_builder.compile()
+
+# Parent graph
+
+builder = StateGraph(State)
+builder.add_node("node_1", subgraph)
+builder.add_edge(START, "node_1")
+graph = builder.compile()
+```
+
+??? example "Full example: shared state schemas"
+
+    ```python
+    from typing_extensions import TypedDict
+    from langgraph.graph.state import StateGraph, START
+
+    # Define subgraph
+    class SubgraphState(TypedDict):
+        foo: str  # (1)! 
+        bar: str  # (2)!
+    
+    def subgraph_node_1(state: SubgraphState):
+        return {"bar": "bar"}
+    
+    def subgraph_node_2(state: SubgraphState):
+        # note that this node is using a state key ('bar') that is only available in the subgraph
+        # and is sending update on the shared state key ('foo')
+        return {"foo": state["foo"] + state["bar"]}
+    
+    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()
+    
+    for chunk in graph.stream({"foo": "foo"}):
+        print(chunk)
+    ```
+
+    1. This key is shared with the parent graph state
+    2. This key is private to the `SubgraphState` and is not visible to the parent graph
+    
+    ```
+    {'node_1': {'foo': 'hi! foo'}}
+    {'node_2': {'foo': 'hi! foobar'}}
+    ```
+
+## Different state schemas
+
+For more complex systems you might want to define subgraphs that have a **completely different schema** from the parent graph (no shared keys). For example, you might want to keep a private message history for each of the agents in a [multi-agent](../concepts/multi_agent.md) system.
+
+If that's the case for your application, you need to define a node **function that invokes the subgraph**. This function needs to transform the input (parent) state to the subgraph state before invoking the subgraph, and transform the results back to the parent state before returning the state update from the node.
+
+```python
+from typing_extensions import TypedDict
+from langgraph.graph.state import StateGraph, START
+
+class SubgraphState(TypedDict):
+    bar: str
+
+# Subgraph
+
+def subgraph_node_1(state: SubgraphState):
+    return {"bar": "hi! " + state["bar"]}
+
+subgraph_builder = StateGraph(SubgraphState)
+subgraph_builder.add_node(subgraph_node_1)
+subgraph_builder.add_edge(START, "subgraph_node_1")
+subgraph = subgraph_builder.compile()
+
+# Parent graph
+
+class State(TypedDict):
+    foo: str
+
+def call_subgraph(state: State):
+    subgraph_output = subgraph.invoke({"bar": state["foo"]})  # (1)!
+    return {"foo": subgraph_output["bar"]}  # (2)!
+
+builder = StateGraph(State)
+builder.add_node("node_1", call_subgraph)
+builder.add_edge(START, "node_1")
+graph = builder.compile()
+```
+
+1. Transform the state to the subgraph state
+2. Transform response back to the parent state
+
+??? example "Full example: different state schemas"
+
+    ```python
+    from typing_extensions import TypedDict
+    from langgraph.graph.state import StateGraph, START
+
+    # Define subgraph
+    class SubgraphState(TypedDict):
+        # note that none of these keys are shared with the parent graph state
+        bar: str
+        baz: str
+    
+    def subgraph_node_1(state: SubgraphState):
+        return {"baz": "baz"}
+    
+    def subgraph_node_2(state: SubgraphState):
+        return {"bar": state["bar"] + state["baz"]}
+    
+    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"]}
+    
+    def node_2(state: ParentState):
+        response = subgraph.invoke({"bar": state["foo"]})  # (1)!
+        return {"foo": response["bar"]}  # (2)!
+    
+    
+    builder = StateGraph(ParentState)
+    builder.add_node("node_1", node_1)
+    builder.add_node("node_2", node_2)
+    builder.add_edge(START, "node_1")
+    builder.add_edge("node_1", "node_2")
+    graph = builder.compile()
+    
+    for chunk in graph.stream({"foo": "foo"}, subgraphs=True):
+        print(chunk)
+    ```
+
+    1. Transform the state to the subgraph state
+    2. Transform response back to the parent state
+
+    ```
+    ((), {'node_1': {'foo': 'hi! foo'}})
+    (('node_2:9c36dd0f-151a-cb42-cbad-fa2f851f9ab7',), {'grandchild_1': {'my_grandchild_key': 'hi Bob, how are you'}})
+    (('node_2:9c36dd0f-151a-cb42-cbad-fa2f851f9ab7',), {'grandchild_2': {'bar': 'hi! foobaz'}})
+    ((), {'node_2': {'foo': 'hi! foobaz'}})
+    ```
+
+??? example "Full example: different state schemas (two levels of subgraphs)"
+
+    This is an example with two levels of subgraphs: parent -> child -> grandchild.
+
+    ```python
+    # Grandchild graph
+    from typing_extensions import TypedDict
+    from langgraph.graph.state import StateGraph, START, END
+    
+    class GrandChildState(TypedDict):
+        my_grandchild_key: str
+    
+    def grandchild_1(state: GrandChildState) -> GrandChildState:
+        # NOTE: child or parent keys will not be accessible here
+        return {"my_grandchild_key": state["my_grandchild_key"] + ", how are you"}
+    
+    
+    grandchild = StateGraph(GrandChildState)
+    grandchild.add_node("grandchild_1", grandchild_1)
+    
+    grandchild.add_edge(START, "grandchild_1")
+    grandchild.add_edge("grandchild_1", END)
+    
+    grandchild_graph = grandchild.compile()
+    
+    # Child graph
+    class ChildState(TypedDict):
+        my_child_key: str
+    
+    def call_grandchild_graph(state: ChildState) -> ChildState:
+        # NOTE: parent or grandchild keys won't be accessible here
+        grandchild_graph_input = {"my_grandchild_key": state["my_child_key"]}  # (1)!
+        grandchild_graph_output = grandchild_graph.invoke(grandchild_graph_input)
+        return {"my_child_key": grandchild_graph_output["my_grandchild_key"] + " today?"}  # (2)!
+    
+    child = StateGraph(ChildState)
+    child.add_node("child_1", call_grandchild_graph)  # (3)!
+    child.add_edge(START, "child_1")
+    child.add_edge("child_1", END)
+    child_graph = child.compile()
+    
+    # Parent graph
+    class ParentState(TypedDict):
+        my_key: str
+    
+    def parent_1(state: ParentState) -> ParentState:
+        # NOTE: child or grandchild keys won't be accessible here
+        return {"my_key": "hi " + state["my_key"]}
+    
+    def parent_2(state: ParentState) -> ParentState:
+        return {"my_key": state["my_key"] + " bye!"}
+    
+    def call_child_graph(state: ParentState) -> ParentState:
+        child_graph_input = {"my_child_key": state["my_key"]}  # (4)!
+        child_graph_output = child_graph.invoke(child_graph_input)
+        return {"my_key": child_graph_output["my_child_key"]}  # (5)!
+    
+    parent = StateGraph(ParentState)
+    parent.add_node("parent_1", parent_1)
+    parent.add_node("child", call_child_graph)  # (6)!
+    parent.add_node("parent_2", parent_2)
+    
+    parent.add_edge(START, "parent_1")
+    parent.add_edge("parent_1", "child")
+    parent.add_edge("child", "parent_2")
+    parent.add_edge("parent_2", END)
+    
+    parent_graph = parent.compile()
+    
+    for chunk in parent_graph.stream({"my_key": "Bob"}, subgraphs=True):
+        print(chunk)
+    ```
+
+    1. We're transforming the state from the child state channels (`my_child_key`) to the child state channels (`my_grandchild_key`)
+    2. We're transforming the state from the grandchild state channels (`my_grandchild_key`) back to the child state channels (`my_child_key`)
+    3. We're passing a function here instead of just compiled graph (`grandchild_graph`)
+    4. We're transforming the state from the parent state channels (`my_key`) to the child state channels (`my_child_key`)
+    5. We're transforming the state from the child state channels (`my_child_key`) back to the parent state channels (`my_key`)
+    6. We're passing a function here instead of just a compiled graph (`child_graph`)
+
+    ```
+    ((), {'parent_1': {'my_key': 'hi Bob'}})
+    (('child:2e26e9ce-602f-862c-aa66-1ea5a4655e3b', 'child_1:781bb3b1-3971-84ce-810b-acf819a03f9c'), {'grandchild_1': {'my_grandchild_key': 'hi Bob, how are you'}})
+    (('child:2e26e9ce-602f-862c-aa66-1ea5a4655e3b',), {'child_1': {'my_child_key': 'hi Bob, how are you today?'}})
+    ((), {'child': {'my_key': 'hi Bob, how are you today?'}})
+    ((), {'parent_2': {'my_key': 'hi Bob, how are you today? bye!'}})
+    ```
+
+## Add persistence 
+
+You only need to **provide the checkpointer when compiling the parent graph**. LangGraph will automatically propagate the checkpointer to the child subgraphs.
+
+```python
+from langgraph.graph import START, StateGraph
+from langgraph.checkpoint.memory import InMemorySaver
+from typing_extensions import TypedDict
+
+class State(TypedDict):
+    foo: str
+
+# Subgraph
+
+def subgraph_node_1(state: State):
+    return {"foo": state["foo"] + "bar"}
+
+subgraph_builder = StateGraph(State)
+subgraph_builder.add_node(subgraph_node_1)
+subgraph_builder.add_edge(START, "subgraph_node_1")
+subgraph = subgraph_builder.compile()
+
+# Parent graph
+
+builder = StateGraph(State)
+builder.add_node("node_1", subgraph)
+builder.add_edge(START, "node_1")
+
+checkpointer = InMemorySaver()
+graph = builder.compile(checkpointer=checkpointer)
+```    
+
+If you want the subgraph to **have its own memory**, you can compile it `with checkpointer=True`. This is useful in [multi-agent](../concepts/multi_agent.md) systems, if you want agents to keep track of their internal message histories:
+
+```python
+subgraph_builder = StateGraph(...)
+subgraph = subgraph_builder.compile(checkpointer=True)
+```
+
+## View subgraph state
+
+When you enable [persistence](../concepts/persistence.md), you can [inspect the graph state](../concepts/persistence.md#checkpoints) (checkpoint) via `graph.get_state(config)`. To view the subgraph state, you can use `graph.get_state(config, subgraphs=True)`.
+
+!!! important "Available **only** when interrupted"
+
+    Subgraph state can only be viewed **when the subgraph is interrupted**. Once you resume the graph, you won't be able to access the subgraph state.
+
+??? example "View interrupted subgraph state"
+
+    ```python
+    from langgraph.graph import START, StateGraph
+    from langgraph.checkpoint.memory import InMemorySaver
+    from langgraph.types import interrupt, Command
+    from typing_extensions import TypedDict
+    
+    class State(TypedDict):
+        foo: str
+    
+    # Subgraph
+    
+    def subgraph_node_1(state: State):
+        value = interrupt("Provide value:")
+        return {"foo": state["foo"] + value}
+    
+    subgraph_builder = StateGraph(State)
+    subgraph_builder.add_node(subgraph_node_1)
+    subgraph_builder.add_edge(START, "subgraph_node_1")
+    
+    subgraph = subgraph_builder.compile()
+    
+    # Parent graph
+        
+    builder = StateGraph(State)
+    builder.add_node("node_1", subgraph)
+    builder.add_edge(START, "node_1")
+    
+    checkpointer = InMemorySaver()
+    graph = builder.compile(checkpointer=checkpointer)
+    
+    config = {"configurable": {"thread_id": "1"}}
+    
+    graph.invoke({"foo": ""}, config)
+    parent_state = graph.get_state(config)
+    subgraph_state = graph.get_state(config, subgraphs=True).tasks[0].state  # (1)!
+    
+    # resume the subgraph
+    graph.invoke(Command(resume="bar"), config)
+    ```
+    
+    1. This will be available only when the subgraph is interrupted. Once you resume the graph, you won't be able to access the subgraph state.
+
+## Stream subgraph outputs
+
+To include outputs from subgraphs in the streamed outputs, you can set `subgraphs=True` in the `.stream()` method of the parent graph. This will stream outputs from both the parent graph and any subgraphs.
+
+```python
+for chunk in graph.stream(
+    {"foo": "foo"},
+    subgraphs=True, # (1)!
+    stream_mode="updates",
+):
+    print(chunk)
+```
+
+1. Set `subgraphs=True` to stream outputs from subgraphs.
+
+??? example "Stream from subgraphs"
+
+    ```python
+    from typing_extensions import TypedDict
+    from langgraph.graph.state import StateGraph, START
+
+    # Define subgraph
+    class SubgraphState(TypedDict):
+        foo: str
+        bar: str
+    
+    def subgraph_node_1(state: SubgraphState):
+        return {"bar": "bar"}
+    
+    def subgraph_node_2(state: SubgraphState):
+        # note that this node is using a state key ('bar') that is only available in the subgraph
+        # and is sending update on the shared state key ('foo')
+        return {"foo": state["foo"] + state["bar"]}
+    
+    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()
+
+    for chunk in graph.stream(
+        {"foo": "foo"},
+        stream_mode="updates",
+        subgraphs=True, # (1)!
+    ):
+        print(chunk)
+    ```
+  
+    1. Set `subgraphs=True` to stream outputs from subgraphs.
+
+    ```
+    ((), {'node_1': {'foo': 'hi! foo'}})
+    (('node_2:e58e5673-a661-ebb0-70d4-e298a7fc28b7',), {'subgraph_node_1': {'bar': 'bar'}})
+    (('node_2:e58e5673-a661-ebb0-70d4-e298a7fc28b7',), {'subgraph_node_2': {'foo': 'hi! foobar'}})
+    ((), {'node_2': {'foo': 'hi! foobar'}})
+    

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

@@ -344,6 +344,8 @@ tool_node.invoke({"messages": [...]})
 
 ## Tool customization
 
+For more control over tool behavior, use the `@tool` decorator.
+
 ### Parameter descriptions
 
 Auto-generate descriptions from docstrings:

docs/docs/index.md

@@ -28,4 +28,4 @@ title: LangGraph
 }
 </style>
 
-{!../README.md!}
+{% include-markdown "../../README.md" %}

docs/docs/snippets/chat_model_tabs.md

@@ -0,0 +1,87 @@
+=== "OpenAI"
+
+    ```shell
+    pip install -U "langchain[openai]"
+    ```
+    ```python
+    import os
+    from langchain.chat_models import init_chat_model
+
+    os.environ["OPENAI_API_KEY"] = "sk-..."
+
+    llm = init_chat_model("openai:gpt-4.1")
+    ```
+
+    👉 Read the [OpenAI integration docs](https://python.langchain.com/docs/integrations/chat/openai/)
+
+=== "Anthropic"
+
+    ```shell
+    pip install -U "langchain[anthropic]"
+    ```
+    ```python
+    import os
+    from langchain.chat_models import init_chat_model
+
+    os.environ["ANTHROPIC_API_KEY"] = "sk-..."
+
+    llm = init_chat_model("anthropic:claude-3-5-sonnet-latest")
+    ```
+
+    👉 Read the [Anthropic integration docs](https://python.langchain.com/docs/integrations/chat/anthropic/)
+
+=== "Azure"
+
+    ```shell
+    pip install -U "langchain[openai]"
+    ```
+    ```python
+    import os
+    from langchain.chat_models import init_chat_model
+
+    os.environ["AZURE_OPENAI_API_KEY"] = "..."
+    os.environ["AZURE_OPENAI_ENDPOINT"] = "..."
+    os.environ["OPENAI_API_VERSION"] = "2025-03-01-preview"
+
+    llm = init_chat_model(
+        "azure_openai:gpt-4.1",
+        azure_deployment=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],
+    )
+    ```
+ 
+    👉 Read the [Azure integration docs](https://python.langchain.com/docs/integrations/chat/azure_chat_openai/)
+
+=== "Google Gemini"
+
+    ```shell
+    pip install -U "langchain[google-genai]"
+    ```
+    ```python
+    import os
+    from langchain.chat_models import init_chat_model
+
+    os.environ["GOOGLE_API_KEY"] = "..."
+
+    llm = init_chat_model("google_genai:gemini-2.0-flash")
+    ```
+
+    👉 Read the [Google GenAI integration docs](https://python.langchain.com/docs/integrations/chat/google_generative_ai/)
+
+=== "AWS Bedrock"
+
+    ```shell
+    pip install -U "langchain[aws]"
+    ```
+    ```python
+    from langchain.chat_models import init_chat_model
+
+    # Follow the steps here to configure your credentials:
+    # https://docs.aws.amazon.com/bedrock/latest/userguide/getting-started.html
+
+    llm = init_chat_model(
+        "anthropic.claude-3-5-sonnet-20240620-v1:0",
+        model_provider="bedrock_converse",
+    )
+    ```
+
+    👉 Read the [AWS Bedrock integration docs](https://python.langchain.com/docs/integrations/chat/bedrock/)

docs/docs/stylesheets/navigation_title_ovverides.css

@@ -1,29 +0,0 @@
-/*
- * This file is used to override the navigation title for the LangGraph documentation.
- * It is used to change the title of the first and second items in the navigation menu.
- * The first item is the Guides page, and the second item is the Reference page.
- */
-
-.md-nav--primary > .md-nav__list > .md-nav__item:nth-child(1) > .md-nav__link .md-ellipsis {
-  visibility: hidden !important;
-  position: relative;
-}
-
-.md-nav--primary > .md-nav__list > .md-nav__item:nth-child(1) > .md-nav__link .md-ellipsis::after {
-  content: "Home";
-  visibility: visible;
-  position: absolute;
-  left: 0;
-}
-
-.md-nav--primary > .md-nav__list > .md-nav__item:nth-child(2) > .md-nav__link .md-ellipsis {
-  visibility: hidden !important;
-  position: relative;
-}
-
-.md-nav--primary > .md-nav__list > .md-nav__item:nth-child(2) > .md-nav__link .md-ellipsis::after {
-  content: "Home";
-  visibility: visible;
-  position: absolute;
-  left: 0;
-}

docs/docs/troubleshooting/studio.md

@@ -17,7 +17,7 @@ Safari blocks plain-HTTP traffic on localhost. When running Studio with `langgra
 
     ```shell
     # Requires @langchain/langgraph-cli>=0.0.26
-    npx @langchain/langgraph-cli dev
+    npx @langchain/langgraph-cli dev --tunnel
     ```
 
 The command outputs a URL in this format:
@@ -55,7 +55,7 @@ Disable Brave Shields for LangSmith using the Brave icon in the URL bar.
 
     ```shell
     # Requires @langchain/langgraph-cli>=0.0.26
-    npx @langchain/langgraph-cli dev
+    npx @langchain/langgraph-cli dev --tunnel
     ```
 
 The command outputs a URL in this format:

docs/docs/tutorials/get-started/1-build-basic-chatbot.md

@@ -63,7 +63,7 @@ Next, add a "`chatbot`" node. **Nodes** represent units of work and are typicall
 
 Let's first select a chat model:
 
-{!snippets/chat_model_tabs.md!}
+{% include-markdown "../../../snippets/chat_model_tabs.md" %}
 
 <!---
 ```python
@@ -112,7 +112,7 @@ This tells the graph to terminate after running the chatbot node.
 ## 6. Compile the graph
 
 Before running the graph, we'll need to compile it. We can do so by calling `compile()`
-on the graph builder. This creates a `CompiledGraph` we can invoke on our state.
+on the graph builder. This creates a `CompiledStateGraph` we can invoke on our state.
 
 ```python
 graph = graph_builder.compile()

docs/docs/tutorials/get-started/2-add-tools.md

@@ -23,12 +23,16 @@ pip install -U langchain-tavily
 
 Configure your environment with your search engine API key:
 
-```bash
+```python
+def _set_env(var: str):
+    if not os.environ.get(var):
+        os.environ[var] = getpass.getpass(f"{var}: ")
+
 _set_env("TAVILY_API_KEY")
 ```
 
 ```
-TAVILY_API_KEY:  ········
+os.environ["TAVILY_API_KEY"]:  "········"
 ```
 
 ## 3. Define the tool
@@ -69,7 +73,7 @@ For the `StateGraph` you created in the [first tutorial](./1-build-basic-chatbot
 
 Let's first select our LLM:
 
-{!snippets/chat_model_tabs.md!}
+{% include-markdown "../../../snippets/chat_model_tabs.md" %}
 
 <!---
 ```python
@@ -282,7 +286,7 @@ For ease of use, adjust your code to replace the following with LangGraph prebui
 - `BasicToolNode` is replaced with the prebuilt [ToolNode](https://langchain-ai.github.io/langgraph/reference/prebuilt/#toolnode)
 - `route_tools` is replaced with the prebuilt [tools_condition](https://langchain-ai.github.io/langgraph/reference/prebuilt/#tools_condition)
 
-{!snippets/chat_model_tabs.md!}
+{% include-markdown "../../../snippets/chat_model_tabs.md" %}
 
 
 ```python hl_lines="25 30"

docs/docs/tutorials/get-started/3-add-memory.md

@@ -154,7 +154,7 @@ The snapshot above contains the current state values, corresponding config, and
   
 Check out the code snippet below to review the graph from this tutorial:
 
-{!snippets/chat_model_tabs.md!}
+{% include-markdown "../../../snippets/chat_model_tabs.md" %}
 
 <!---
 ```python

docs/docs/tutorials/get-started/4-human-in-the-loop.md

@@ -14,7 +14,7 @@ Starting with the existing code from the [Add memory to the chatbot](./3-add-mem
 
 Let's first select a chat model:
 
-{!snippets/chat_model_tabs.md!}
+{% include-markdown "../../../snippets/chat_model_tabs.md" %}
 
 <!---
 ```python
@@ -221,7 +221,7 @@ The input has been received and processed as a tool message. Review this call's
 
 Check out the code snippet below to review the graph from this tutorial:
 
-{!snippets/chat_model_tabs.md!}
+{% include-markdown "../../../snippets/chat_model_tabs.md" %}
 
 ```python
 from typing import Annotated

docs/docs/tutorials/get-started/5-customize-state.md

@@ -221,7 +221,7 @@ Manual state updates will [generate a trace](https://smith.langchain.com/public/
 
 Check out the code snippet below to review the graph from this tutorial:
 
-{!snippets/chat_model_tabs.md!}
+{% include-markdown "../../../snippets/chat_model_tabs.md" %}
 
 <!---
 ```python

docs/docs/tutorials/get-started/6-time-travel.md

@@ -14,7 +14,7 @@ You can create these types of experiences using LangGraph's built-in **time trav
 
 Rewind your graph by fetching a checkpoint using the graph's `get_state_history` method. You can then resume execution at this previous point in time.
 
-{!snippets/chat_model_tabs.md!}
+{% include-markdown "../../../snippets/chat_model_tabs.md" %}
 
 <!---
 ```python

docs/docs/tutorials/llm-compiler/LLMCompiler.ipynb

@@ -540,11 +540,11 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "================================\u001B[1m System Message \u001B[0m================================\n",
+      "================================\u001b[1m System Message \u001b[0m================================\n",
       "\n",
-      "Given a user query, create a plan to solve it with the utmost parallelizability. Each plan should comprise an action from the following \u001B[33;1m\u001B[1;3m{num_tools}\u001B[0m types:\n",
-      "\u001B[33;1m\u001B[1;3m{tool_descriptions}\u001B[0m\n",
-      "\u001B[33;1m\u001B[1;3m{num_tools}\u001B[0m. join(): Collects and combines results from prior actions.\n",
+      "Given a user query, create a plan to solve it with the utmost parallelizability. Each plan should comprise an action from the following \u001b[33;1m\u001b[1;3m{num_tools}\u001b[0m types:\n",
+      "\u001b[33;1m\u001b[1;3m{tool_descriptions}\u001b[0m\n",
+      "\u001b[33;1m\u001b[1;3m{num_tools}\u001b[0m. join(): Collects and combines results from prior actions.\n",
       "\n",
       " - An LLM agent is called upon invoking join() to either finalize the user query or wait until the plans are executed.\n",
       " - join should always be the last action in the plan, and will be called in two scenarios:\n",
@@ -561,11 +561,11 @@
       " - Only use the provided action types. If a query cannot be addressed using these, invoke the join action for the next steps.\n",
       " - Never introduce new actions other than the ones provided.\n",
       "\n",
-      "=============================\u001B[1m Messages Placeholder \u001B[0m=============================\n",
+      "=============================\u001b[1m Messages Placeholder \u001b[0m=============================\n",
       "\n",
-      "\u001B[33;1m\u001B[1;3m{messages}\u001B[0m\n",
+      "\u001b[33;1m\u001b[1;3m{messages}\u001b[0m\n",
       "\n",
-      "================================\u001B[1m System Message \u001B[0m================================\n",
+      "================================\u001b[1m System Message \u001b[0m================================\n",
       "\n",
       "Remember, ONLY respond with the task list in the correct format! E.g.:\n",
       "idx. tool(arg_name=args)\n",
@@ -605,7 +605,7 @@
     "    llm: BaseChatModel, tools: Sequence[BaseTool], base_prompt: ChatPromptTemplate\n",
     "):\n",
     "    tool_descriptions = \"\\n\".join(\n",
-    "        f\"{i+1}. {tool.description}\\n\"\n",
+    "        f\"{i + 1}. {tool.description}\\n\"\n",
     "        for i, tool in enumerate(\n",
     "            tools\n",
     "        )  # +1 to offset the 0 starting index, we want it count normally from 1.\n",

docs/docs/tutorials/multi_agent/agent_supervisor.md

@@ -0,0 +1,812 @@
+# Multi-agent supervisor
+
+[**Supervisor**](../../concepts/multi_agent.md#supervisor) is a multi-agent architecture where **specialized** agents are coordinated by a central **supervisor agent**. The supervisor agent controls all communication flow and task delegation, making decisions about which agent to invoke based on the current context and task requirements.
+
+In this tutorial, you will build a supervisor system with two agents — a research and a math expert. By the end of the tutorial you will:
+
+1. Build specialized research and math agents
+2. Build a supervisor for orchestrating them with the prebuilt [`langgraph-supervisor`](https://langchain-ai.github.io/langgraph/agents/multi-agent/#supervisor)
+3. Build a supervisor from scratch
+4. Implement advanced task delegation
+
+![diagram](assets/diagram.png)
+
+## Setup
+
+First, let's install required packages and set our API keys
+
+```python
+%%capture --no-stderr
+%pip install -U langgraph langgraph-supervisor langchain-tavily "langchain[openai]"
+```
+
+```python
+import getpass
+import os
+
+
+def _set_if_undefined(var: str):
+    if not os.environ.get(var):
+        os.environ[var] = getpass.getpass(f"Please provide your {var}")
+
+
+_set_if_undefined("OPENAI_API_KEY")
+_set_if_undefined("TAVILY_API_KEY")
+```
+
+!!! tip
+    Sign up for LangSmith to quickly spot issues and improve the performance of your LangGraph projects. [LangSmith](https://docs.smith.langchain.com) lets you use trace data to debug, test, and monitor your LLM apps built with LangGraph.
+
+## 1. Create worker agents
+
+First, let's create our specialized worker agents — research agent and math agent:
+
+* Research agent will have access to a web search tool using [Tavily API](https://tavily.com/)
+* Math agent will have access to simple math tools (`add`, `multiply`, `divide`)
+
+### Research agent
+
+For web search, we will use `TavilySearch` tool from `langchain-tavily`:
+
+```python
+from langchain_tavily import TavilySearch
+
+web_search = TavilySearch(max_results=3)
+web_search_results = web_search.invoke("who is the mayor of NYC?")
+
+print(web_search_results["results"][0]["content"])
+```
+
+**Output:**
+```
+Find events, attractions, deals, and more at nyctourism.com Skip Main Navigation Menu The Official Website of the City of New York Text Size Powered by Translate SearchSearch Primary Navigation The official website of NYC Home NYC Resources NYC311 Office of the Mayor Events Connect Jobs Search Office of the Mayor | Mayor's Bio | City of New York Secondary Navigation MayorBiographyNewsOfficials Eric L. Adams 110th Mayor of New York City Mayor Eric Adams has served the people of New York City as an NYPD officer, State Senator, Brooklyn Borough President, and now as the 110th Mayor of the City of New York. Mayor Eric Adams has served the people of New York City as an NYPD officer, State Senator, Brooklyn Borough President, and now as the 110th Mayor of the City of New York. He gave voice to a diverse coalition of working families in all five boroughs and is leading the fight to bring back New York City's economy, reduce inequality, improve public safety, and build a stronger, healthier city that delivers for all New Yorkers. As the representative of one of the nation's largest counties, Eric fought tirelessly to grow the local economy, invest in schools, reduce inequality, improve public safety, and advocate for smart policies and better government that delivers for all New Yorkers.
+```
+
+To create individual worker agents, we will use LangGraph's prebuilt [agent](../../agents/agents.md).
+
+```python
+from langgraph.prebuilt import create_react_agent
+
+research_agent = create_react_agent(
+    model="openai:gpt-4.1",
+    tools=[web_search],
+    prompt=(
+        "You are a research agent.\n\n"
+        "INSTRUCTIONS:\n"
+        "- Assist ONLY with research-related tasks, DO NOT do any math\n"
+        "- After you're done with your tasks, respond to the supervisor directly\n"
+        "- Respond ONLY with the results of your work, do NOT include ANY other text."
+    ),
+    name="research_agent",
+)
+```
+
+Let's [run the agent](../../agents/run_agents.md) to verify that it behaves as expected. 
+
+!!! note "We'll use `pretty_print_messages` helper to render the streamed agent outputs nicely"
+
+    ```python
+    from langchain_core.messages import convert_to_messages
+    
+    
+    def pretty_print_message(message, indent=False):
+        pretty_message = message.pretty_repr(html=True)
+        if not indent:
+            print(pretty_message)
+            return
+    
+        indented = "\n".join("\t" + c for c in pretty_message.split("\n"))
+        print(indented)
+    
+    
+    def pretty_print_messages(update, last_message=False):
+        is_subgraph = False
+        if isinstance(update, tuple):
+            ns, update = update
+            # skip parent graph updates in the printouts
+            if len(ns) == 0:
+                return
+    
+            graph_id = ns[-1].split(":")[0]
+            print(f"Update from subgraph {graph_id}:")
+            print("\n")
+            is_subgraph = True
+    
+        for node_name, node_update in update.items():
+            update_label = f"Update from node {node_name}:"
+            if is_subgraph:
+                update_label = "\t" + update_label
+    
+            print(update_label)
+            print("\n")
+    
+            messages = convert_to_messages(node_update["messages"])
+            if last_message:
+                messages = messages[-1:]
+    
+            for m in messages:
+                pretty_print_message(m, indent=is_subgraph)
+            print("\n")
+    ```
+
+```python
+from langchain_core.messages import convert_to_messages
+
+
+def pretty_print_message(message, indent=False):
+    pretty_message = message.pretty_repr(html=True)
+    if not indent:
+        print(pretty_message)
+        return
+
+    indented = "\n".join("\t" + c for c in pretty_message.split("\n"))
+    print(indented)
+
+
+def pretty_print_messages(update, last_message=False):
+    is_subgraph = False
+    if isinstance(update, tuple):
+        ns, update = update
+        # skip parent graph updates in the printouts
+        if len(ns) == 0:
+            return
+
+        graph_id = ns[-1].split(":")[0]
+        print(f"Update from subgraph {graph_id}:")
+        print("\n")
+        is_subgraph = True
+
+    for node_name, node_update in update.items():
+        update_label = f"Update from node {node_name}:"
+        if is_subgraph:
+            update_label = "\t" + update_label
+
+        print(update_label)
+        print("\n")
+
+        messages = convert_to_messages(node_update["messages"])
+        if last_message:
+            messages = messages[-1:]
+
+        for m in messages:
+            pretty_print_message(m, indent=is_subgraph)
+        print("\n")
+```
+
+```python
+for chunk in research_agent.stream(
+    {"messages": [{"role": "user", "content": "who is the mayor of NYC?"}]}
+):
+    pretty_print_messages(chunk)
+```
+
+**Output:**
+```
+Update from node agent:
+
+
+================================== Ai Message ==================================
+Name: research_agent
+Tool Calls:
+  tavily_search (call_U748rQhQXT36sjhbkYLSXQtJ)
+ Call ID: call_U748rQhQXT36sjhbkYLSXQtJ
+  Args:
+    query: current mayor of New York City
+    search_depth: basic
+
+
+Update from node tools:
+
+
+================================= Tool Message ==================================
+Name: tavily_search
+
+{"query": "current mayor of New York City", "follow_up_questions": null, "answer": null, "images": [], "results": [{"title": "List of mayors of New York City - Wikipedia", "url": "https://en.wikipedia.org/wiki/List_of_mayors_of_New_York_City", "content": "The mayor of New York City is the chief executive of the Government of New York City, as stipulated by New York City's charter.The current officeholder, the 110th in the sequence of regular mayors, is Eric Adams, a member of the Democratic Party.. During the Dutch colonial period from 1624 to 1664, New Amsterdam was governed by the Director of Netherland.", "score": 0.9039154, "raw_content": null}, {"title": "Office of the Mayor | Mayor's Bio | City of New York - NYC.gov", "url": "https://www.nyc.gov/office-of-the-mayor/bio.page", "content": "Mayor Eric Adams has served the people of New York City as an NYPD officer, State Senator, Brooklyn Borough President, and now as the 110th Mayor of the City of New York. He gave voice to a diverse coalition of working families in all five boroughs and is leading the fight to bring back New York City's economy, reduce inequality, improve", "score": 0.8405867, "raw_content": null}, {"title": "Eric Adams - Wikipedia", "url": "https://en.wikipedia.org/wiki/Eric_Adams", "content": "Eric Leroy Adams (born September 1, 1960) is an American politician and former police officer who has served as the 110th mayor of New York City since 2022. Adams was an officer in the New York City Transit Police and then the New York City Police Department (```
+```
+
+### Math agent
+
+For math agent tools we will use [vanilla Python functions](../../how-tos/tool-calling.md#define-a-tool):
+
+```python
+def add(a: float, b: float):
+    """Add two numbers."""
+    return a + b
+
+
+def multiply(a: float, b: float):
+    """Multiply two numbers."""
+    return a * b
+
+
+def divide(a: float, b: float):
+    """Divide two numbers."""
+    return a / b
+
+
+math_agent = create_react_agent(
+    model="openai:gpt-4.1",
+    tools=[add, multiply, divide],
+    prompt=(
+        "You are a math agent.\n\n"
+        "INSTRUCTIONS:\n"
+        "- Assist ONLY with math-related tasks\n"
+        "- After you're done with your tasks, respond to the supervisor directly\n"
+        "- Respond ONLY with the results of your work, do NOT include ANY other text."
+    ),
+    name="math_agent",
+)
+```
+
+Let's run the math agent:
+
+```python
+for chunk in math_agent.stream(
+    {"messages": [{"role": "user", "content": "what's (3 + 5) x 7"}]}
+):
+    pretty_print_messages(chunk)
+```
+
+**Output:**
+```
+Update from node agent:
+
+
+================================== Ai Message ==================================
+Name: math_agent
+Tool Calls:
+  add (call_p6OVLDHB4LyCNCxPOZzWR15v)
+ Call ID: call_p6OVLDHB4LyCNCxPOZzWR15v
+  Args:
+    a: 3
+    b: 5
+
+
+Update from node tools:
+
+
+================================= Tool Message ==================================
+Name: add
+
+8.0
+
+
+Update from node agent:
+
+
+================================== Ai Message ==================================
+Name: math_agent
+Tool Calls:
+  multiply (call_EoaWHMLFZAX4AkajQCtZvbli)
+ Call ID: call_EoaWHMLFZAX4AkajQCtZvbli
+  Args:
+    a: 8
+    b: 7
+
+
+Update from node tools:
+
+
+================================= Tool Message ==================================
+Name: multiply
+
+56.0
+
+
+Update from node agent:
+
+
+================================== Ai Message ==================================
+Name: math_agent
+
+56
+
+
+```
+
+## 2. Create supervisor with `langgraph-supervisor`
+
+To implement out multi-agent system, we will use [`create_supervisor`][langgraph_supervisor.supervisor.create_supervisor] from the prebuilt `langgraph-supervisor` library:
+
+```python
+from langgraph_supervisor import create_supervisor
+from langchain.chat_models import init_chat_model
+
+supervisor = create_supervisor(
+    model=init_chat_model("openai:gpt-4.1"),
+    agents=[research_agent, math_agent],
+    prompt=(
+        "You are a supervisor managing two agents:\n"
+        "- a research agent. Assign research-related tasks to this agent\n"
+        "- a math agent. Assign math-related tasks to this agent\n"
+        "Assign work to one agent at a time, do not call agents in parallel.\n"
+        "Do not do any work yourself."
+    ),
+    add_handoff_back_messages=True,
+    output_mode="full_history",
+).compile()
+```
+
+```python
+from IPython.display import display, Image
+
+display(Image(supervisor.get_graph().draw_mermaid_png()))
+```
+
+![Graph](assets/output.png)
+
+**Note:** When you run this code, it will generate and display a visual representation of the supervisor graph showing the flow between the supervisor and worker agents.
+
+Let's now run it with a query that requires both agents:
+
+* research agent will look up the necessary GDP information
+* math agent will perform division to find the percentage of NY state GDP, as requested
+
+```python
+for chunk in supervisor.stream(
+    {
+        "messages": [
+            {
+                "role": "user",
+                "content": "find US and New York state GDP in 2024. what % of US GDP was New York state?",
+            }
+        ]
+    },
+):
+    pretty_print_messages(chunk, last_message=True)
+
+final_message_history = chunk["supervisor"]["messages"]
+```
+
+**Output:**
+```
+Update from node supervisor:
+
+
+================================= Tool Message ==================================
+Name: transfer_to_research_agent
+
+Successfully transferred to research_agent
+
+
+Update from node research_agent:
+
+
+================================= Tool Message ==================================
+Name: transfer_back_to_supervisor
+
+Successfully transferred back to supervisor
+
+
+Update from node supervisor:
+
+
+================================= Tool Message ==================================
+Name: transfer_to_math_agent
+
+Successfully transferred to math_agent
+
+
+Update from node math_agent:
+
+
+================================= Tool Message ==================================
+Name: transfer_back_to_supervisor
+
+Successfully transferred back to supervisor
+
+
+Update from node supervisor:
+
+
+================================== Ai Message ==================================
+Name: supervisor
+
+In 2024, the US GDP was $29.18 trillion and New York State's GDP was $2.297 trillion. New York State accounted for approximately 7.87% of the total US GDP in 2024.
+
+
+```
+
+## 3. Create supervisor from scratch
+
+Let's now implement this same multi-agent system from scratch. We will need to:
+
+1. [Set up how the supervisor communicates](#set-up-agent-communication) with individual agents
+2. [Create the supervisor agent](#create-supervisor-agent)
+3. Combine supervisor and worker agents into a [single multi-agent graph](#create-multi-agent-graph).
+
+### Set up agent communication
+
+We will need to define a way for the supervisor agent to communicate with the worker agents. A common way to implement this in multi-agent architectures is using **handoffs**, where one agent *hands off* control to another. Handoffs allow you to specify:
+
+- **destination**: target agent to transfer to
+- **payload**: information to pass to that agent
+
+We will implement handoffs via **handoff tools** and give these tools to the supervisor agent: when the supervisor calls these tools, it will hand off control to a worker agent, passing the full message history to that agent.
+
+```python
+from typing import Annotated
+from langchain_core.tools import tool, InjectedToolCallId
+from langgraph.prebuilt import InjectedState
+from langgraph.graph import StateGraph, START, MessagesState
+from langgraph.types import Command
+
+
+def create_handoff_tool(*, agent_name: str, description: str | None = None):
+    name = f"transfer_to_{agent_name}"
+    description = description or f"Ask {agent_name} for help."
+
+    @tool(name, description=description)
+    def handoff_tool(
+        state: Annotated[MessagesState, InjectedState],
+        tool_call_id: Annotated[str, InjectedToolCallId],
+    ) -> Command:
+        tool_message = {
+            "role": "tool",
+            "content": f"Successfully transferred to {agent_name}",
+            "name": name,
+            "tool_call_id": tool_call_id,
+        }
+        # highlight-next-line
+        return Command(
+            # highlight-next-line
+            goto=agent_name,  # (1)!
+            # highlight-next-line
+            update={**state, "messages": state["messages"] + [tool_message]},  # (2)!
+            # highlight-next-line
+            graph=Command.PARENT,  # (3)!
+        )
+
+    return handoff_tool
+
+
+# Handoffs
+assign_to_research_agent = create_handoff_tool(
+    agent_name="research_agent",
+    description="Assign task to a researcher agent.",
+)
+
+assign_to_math_agent = create_handoff_tool(
+    agent_name="math_agent",
+    description="Assign task to a math agent.",
+)
+```
+
+1. Name of the agent or node to hand off to.
+2. 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.
+3. Indicate to LangGraph that we need to navigate to agent node in a **parent** multi-agent graph.
+
+### Create supervisor agent
+
+Then, let's create the supervisor agent with the handoff tools we just defined. We will use the prebuilt [`create_react_agent`][langgraph.prebuilt.chat_agent_executor.create_react_agent]:
+
+```python
+supervisor_agent = create_react_agent(
+    model="openai:gpt-4.1",
+    tools=[assign_to_research_agent, assign_to_math_agent],
+    prompt=(
+        "You are a supervisor managing two agents:\n"
+        "- a research agent. Assign research-related tasks to this agent\n"
+        "- a math agent. Assign math-related tasks to this agent\n"
+        "Assign work to one agent at a time, do not call agents in parallel.\n"
+        "Do not do any work yourself."
+    ),
+    name="supervisor",
+)
+```
+
+### Create multi-agent graph
+
+Putting this all together, let's create a graph for our overall multi-agent system. We will add the supervisor and the individual agents as subgraph [nodes](../../concepts/low_level.md#nodes).
+
+```python
+from langgraph.graph import END
+
+# Define the multi-agent supervisor graph
+supervisor = (
+    StateGraph(MessagesState)
+    # NOTE: `destinations` is only needed for visualization and doesn't affect runtime behavior
+    .add_node(supervisor_agent, destinations=("research_agent", "math_agent", END))
+    .add_node(research_agent)
+    .add_node(math_agent)
+    .add_edge(START, "supervisor")
+    # always return back to the supervisor
+    .add_edge("research_agent", "supervisor")
+    .add_edge("math_agent", "supervisor")
+    .compile()
+)
+```
+
+Notice that we've added explicit [edges](../../concepts/low_level.md#edges) from worker agents back to the supervisor — this means that they are guaranteed to return control back to the supervisor. If you want the agents to respond directly to the user (i.e., turn the system into a router, you can remove these edges).
+
+```python
+from IPython.display import display, Image
+
+display(Image(supervisor.get_graph().draw_mermaid_png()))
+```
+
+![Graph](assets/multi-output.png)
+
+**Note:** When you run this code, it will generate and display a visual representation of the multi-agent supervisor graph showing the flow between the supervisor and worker agents.
+
+With the multi-agent graph created, let's now run it!
+
+```python
+for chunk in supervisor.stream(
+    {
+        "messages": [
+            {
+                "role": "user",
+                "content": "find US and New York state GDP in 2024. what % of US GDP was New York state?",
+            }
+        ]
+    },
+):
+    pretty_print_messages(chunk, last_message=True)
+
+final_message_history = chunk["supervisor"]["messages"]
+```
+
+**Output:**
+```
+Update from node supervisor:
+
+
+================================= Tool Message ==================================
+Name: transfer_to_research_agent
+
+Successfully transferred to research_agent
+
+
+Update from node research_agent:
+
+
+================================== Ai Message ==================================
+Name: research_agent
+
+- US GDP in 2024 is projected to be about $28.18 trillion USD (Statista; CBO projection).
+- New York State's nominal GDP for 2024 is estimated at approximately $2.16 trillion USD (various economic reports).
+- New York State's share of US GDP in 2024 is roughly 7.7%.
+
+Sources:
+- https://www.statista.com/statistics/216985/forecast-of-us-gross-domestic-product/
+- https://nyassembly.gov/Reports/WAM/2025economic_revenue/2025_report.pdf?v=1740533306
+
+
+Update from node supervisor:
+
+
+================================= Tool Message ==================================
+Name: transfer_to_math_agent
+
+Successfully transferred to math_agent
+
+
+Update from node math_agent:
+
+
+================================== Ai Message ==================================
+Name: math_agent
+
+US GDP in 2024: $28.18 trillion
+New York State GDP in 2024: $2.16 trillion
+Percentage of US GDP from New York State: 7.67%
+
+
+Update from node supervisor:
+
+
+================================== Ai Message ==================================
+Name: supervisor
+
+Here are your results:
+
+- 2024 US GDP (projected): $28.18 trillion USD
+- 2024 New York State GDP (estimated): $2.16 trillion USD
+- New York State's share of US GDP: approximately 7.7%
+
+If you need the calculation steps or sources, let me know!
+
+
+```
+
+Let's examine the full resulting message history:
+
+```python
+for message in final_message_history:
+    message.pretty_print()
+```
+
+**Output:**
+```
+================================ Human Message ==================================
+
+find US and New York state GDP in 2024. what % of US GDP was New York state?
+================================== Ai Message ===================================
+Name: supervisor
+Tool Calls:
+  transfer_to_research_agent (call_KlGgvF5ahlAbjX8d2kHFjsC3)
+ Call ID: call_KlGgvF5ahlAbjX8d2kHFjsC3
+  Args:
+================================= Tool Message ==================================
+Name: transfer_to_research_agent
+
+Successfully transferred to research_agent
+================================== Ai Message ===================================
+Name: research_agent
+Tool Calls:
+  tavily_search (call_ZOaTVUA6DKrOjWQldLhtrsO2)
+ Call ID: call_ZOaTVUA6DKrOjWQldLhtrsO2
+  Args:
+    query: US GDP 2024 estimate or actual
+    search_depth: advanced
+  tavily_search (call_QsRAasxW9K03lTlqjuhNLFbZ)
+ Call ID: call_QsRAasxW9K03lTlqjuhNLFbZ
+  Args:
+    query: New York state GDP 2024 estimate or actual
+    search_depth: advanced
+================================= Tool Message ==================================
+Name: tavily_search
+
+{"query": "US GDP 2024 estimate or actual", "follow_up_questions": null, "answer": null, "images": [], "results": [{"url": "https://www.advisorperspectives.com/dshort/updates/2025/05/29/gdp-gross-domestic-product-q1-2025-second-estimate", "title": "Q1 GDP Second Estimate: Real GDP at -0.2%, Higher Than Expected", "content": "> Real gross domestic product (GDP) decreased at an annual rate of 0.2 percent in the first quarter of 2025 (January, February, and March), according to the second estimate released by the U.S. Bureau of Economic Analysis. In the fourth quarter of 2024, real GDP increased 2.4 percent. The decrease in real GDP in the first quarter primarily reflected an increase in imports, which are a subtraction in the calculation of GDP, and a decrease in government spending. These movements were partly [...] by [Harry Mamaysky](https://www.advisor```
+```
+
+!!! important
+    You can see that the supervisor system appends **all** of the individual agent messages (i.e., their internal tool-calling loop) to the full message history. This means that on every supervisor turn, supervisor agent sees this full history. If you want more control over:
+
+    * **how inputs are passed to agents**: you can use LangGraph [`Send()`][langgraph.types.Send] primitive to directly send data to the worker agents during the handoff. See the [task delegation](#4-create-delegation-tasks) example below
+    * **how agent outputs are added**: you can control how much of the agent's internal message history is added to the overall supervisor message history by wrapping the agent in a separate node function:
+
+        ```python
+        def call_research_agent(state):
+            # return agent's final response,
+            # excluding inner monologue
+            response = research_agent.invoke(state)
+            # highlight-next-line
+            return {"messages": response["messages"][-1]}
+        ```
+
+## 4. Create delegation tasks
+
+So far the individual agents relied on **interpreting full message history** to determine their tasks. An alternative approach is to ask the supervisor to **formulate a task explicitly**. We can do so by adding a `task_description` parameter to the `handoff_tool` function.
+
+```python
+from langgraph.types import Send
+
+
+def create_task_description_handoff_tool(
+    *, agent_name: str, description: str | None = None
+):
+    name = f"transfer_to_{agent_name}"
+    description = description or f"Ask {agent_name} for help."
+
+    @tool(name, description=description)
+    def handoff_tool(
+        # this is populated by the supervisor LLM
+        task_description: Annotated[
+            str,
+            "Description of what the next agent should do, including all of the relevant context.",
+        ],
+        # these parameters are ignored by the LLM
+        state: Annotated[MessagesState, InjectedState],
+    ) -> Command:
+        task_description_message = {"role": "user", "content": task_description}
+        agent_input = {**state, "messages": [task_description_message]}
+        return Command(
+            # highlight-next-line
+            goto=[Send(agent_name, agent_input)],
+            graph=Command.PARENT,
+        )
+
+    return handoff_tool
+
+
+assign_to_research_agent_with_description = create_task_description_handoff_tool(
+    agent_name="research_agent",
+    description="Assign task to a researcher agent.",
+)
+
+assign_to_math_agent_with_description = create_task_description_handoff_tool(
+    agent_name="math_agent",
+    description="Assign task to a math agent.",
+)
+
+supervisor_agent_with_description = create_react_agent(
+    model="openai:gpt-4.1",
+    tools=[
+        assign_to_research_agent_with_description,
+        assign_to_math_agent_with_description,
+    ],
+    prompt=(
+        "You are a supervisor managing two agents:\n"
+        "- a research agent. Assign research-related tasks to this assistant\n"
+        "- a math agent. Assign math-related tasks to this assistant\n"
+        "Assign work to one agent at a time, do not call agents in parallel.\n"
+        "Do not do any work yourself."
+    ),
+    name="supervisor",
+)
+
+supervisor_with_description = (
+    StateGraph(MessagesState)
+    .add_node(
+        supervisor_agent_with_description, destinations=("research_agent", "math_agent")
+    )
+    .add_node(research_agent)
+    .add_node(math_agent)
+    .add_edge(START, "supervisor")
+    .add_edge("research_agent", "supervisor")
+    .add_edge("math_agent", "supervisor")
+    .compile()
+)
+```
+
+!!! note
+    We're using [`Send()`][langgraph.types.Send] primitive in the `handoff_tool`. This means that instead of receiving the full `supervisor` graph state as input, each worker agent only sees the contents of the `Send` payload. In this example, we're sending the task description as a single "human" message.
+
+Let's now running it with the same input query:
+
+```python
+for chunk in supervisor_with_description.stream(
+    {
+        "messages": [
+            {
+                "role": "user",
+                "content": "find US and New York state GDP in 2024. what % of US GDP was New York state?",
+            }
+        ]
+    },
+    subgraphs=True,
+):
+    pretty_print_messages(chunk, last_message=True)
+```
+
+**Output:**
+```
+Update from subgraph supervisor:
+
+
+	Update from node agent:
+
+
+	================================== Ai Message ==================================
+	Name: supervisor
+	Tool Calls:
+	  transfer_to_research_agent (call_tk8q8py8qK6MQz6Kj6mijKua)
+	 Call ID: call_tk8q8py8qK6MQz6Kj6mijKua
+	  Args:
+	    task_description: Find the 2024 GDP (Gross Domestic Product) for both the United States and New York state, using the most up-to-date and reputable sources available. Provide both GDP values and cite the data sources.
+
+
+Update from subgraph research_agent:
+
+
+	Update from node agent:
+
+
+	================================== Ai Message ==================================
+	Name: research_agent
+	Tool Calls:
+	  tavily_search (call_KqvhSvOIhAvXNsT6BOwbPlRB)
+	 Call ID: call_KqvhSvOIhAvXNsT6BOwbPlRB
+	  Args:
+	    query: 2024 United States GDP value from a reputable source
+	    search_depth: advanced
+	  tavily_search (call_kbbAWBc9KwCWKHmM5v04H88t)
+	 Call ID: call_kbbAWBc9KwCWKHmM5v04H88t
+	  Args:
+	    query: 2024 New York state GDP value from a reputable source
+	    search_depth: advanced
+
+
+Update from subgraph research_agent:
+
+
+	Update from node tools:
+
+
+	================================= Tool Message ==================================
+	Name: tavily_search
+	
+	{"query": "2024 United States GDP value from a reputable source", "follow_up_questions": null, "answer": null, "images": [], "results": [{"url": "https://www.focus-economics.com/countries/united-states/", "title": "United States Economy Overview - Focus Economics", "content": "The United States' Macroeconomic Analysis:\n------------------------------------------\n\n**Nominal GDP of USD 29,185 billion in 2024.**\n\n**Nominal GDP of USD 29,179 billion in 2024.**\n\n**GDP per capita of USD 86,635 compared to the global average of USD 10,589.**\n\n**GDP per capita of USD 86,652 compared to the global average of USD 10,589.**\n\n**Average real GDP growth of 2.5% over the last decade.**\n\n**Average real GDP growth of ```
+``` 

docs/docs/tutorials/multi_agent/hierarchical_agent_teams.ipynb

@@ -49,7 +49,7 @@
    "outputs": [],
    "source": [
     "%%capture --no-stderr\n",
-    "%pip install -U langgraph langchain_community langchain_anthropic langchain_experimental"
+    "%pip install -U langgraph langchain_community langchain_anthropic langchain-tavily langchain_experimental"
    ]
   },
   {
@@ -121,10 +121,10 @@
     "from typing import Annotated, List\n",
     "\n",
     "from langchain_community.document_loaders import WebBaseLoader\n",
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
+    "from langchain_tavily import TavilySearch\n",
     "from langchain_core.tools import tool\n",
     "\n",
-    "tavily_tool = TavilySearchResults(max_results=5)\n",
+    "tavily_tool = TavilySearch(max_results=5)\n",
     "\n",
     "\n",
     "@tool\n",

docs/docs/tutorials/multi_agent/multi-agent-collaboration.ipynb

@@ -37,7 +37,7 @@
    "outputs": [],
    "source": [
     "%%capture --no-stderr\n",
-    "%pip install -U langchain_community langchain_anthropic langchain_experimental matplotlib langgraph"
+    "%pip install -U langchain_community langchain_anthropic langchain-tavily langchain_experimental matplotlib langgraph"
    ]
   },
   {
@@ -92,11 +92,11 @@
    "source": [
     "from typing import Annotated\n",
     "\n",
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
+    "from langchain_tavily import TavilySearch\n",
     "from langchain_core.tools import tool\n",
     "from langchain_experimental.utilities import PythonREPL\n",
     "\n",
-    "tavily_tool = TavilySearchResults(max_results=5)\n",
+    "tavily_tool = TavilySearch(max_results=5)\n",
     "\n",
     "# Warning: This executes code locally, which can be unsafe when not sandboxed\n",
     "\n",

docs/docs/tutorials/overview.md

@@ -1,21 +0,0 @@
-# Examples
-
-The pages in this section provide end-to-end examples for the following topics:
-
-## General 
-
-- [Agentic RAG](./rag/langgraph_adaptive_rag.ipynb)
-- [Agent Supervisor](./multi_agent/agent_supervisor.ipynb)
-- [SQL agent](./sql-agent.ipynb)
-- [Graph runs in LangSmith](../how-tos/run-id-langsmith.ipynb)
-
-## LangGraph Platform
-
-- [Set up custom authentication](./auth/getting_started.md)
-- [Make conversations private](./auth/resource_auth.md)
-- [Connect an authentication provider](./auth/add_auth_server.md)
-- [Rebuild graph at runtime](../cloud/deployment/graph_rebuild.md)
-- [Use RemoteGraph](../how-tos/use-remote-graph.md)
-- [Deploy CrewAI, AutoGen, and other frameworks](../how-tos/autogen-langgraph-platform.ipynb)
-- [Integrate LangGraph into a React app](../cloud/how-tos/use_stream_react.md)
-- [Implement Generative User Interfaces with LangGraph](../cloud/how-tos/generative_ui_react.md)

docs/docs/tutorials/plan-and-execute/plan-and-execute.ipynb

@@ -378,7 +378,7 @@
     "\n",
     "async def execute_step(state: PlanExecute):\n",
     "    plan = state[\"plan\"]\n",
-    "    plan_str = \"\\n\".join(f\"{i+1}. {step}\" for i, step in enumerate(plan))\n",
+    "    plan_str = \"\\n\".join(f\"{i + 1}. {step}\" for i, step in enumerate(plan))\n",
     "    task = plan[0]\n",
     "    task_formatted = f\"\"\"For the following plan:\n",
     "{plan_str}\\n\\nYou are tasked with executing step {1}, {task}.\"\"\"\n",