release: langgraph + prebuilt (#6875 )

fix: inject ToolRuntime for dynamically registered tools (#6874 )
Fixes https://github.com/langchain-ai/langchain/issues/35305 Co-authored-by: Shivangi Sharma <shivangi.sharma7004@gmail.com>
2026-08-28 10:49:56 +02:00 · 2026-02-19 13:12:01 -05:00 · 2026-02-19 17:39:57 +00:00 · 2026-02-19 07:24:18 -08:00 · 2026-02-19 07:16:26 -08:00 · 2026-02-18 14:35:38 -05:00
17 changed files with 1369 additions and 35 deletions
@@ -0,0 +1,49 @@
+name: Deploy Redirects to GitHub Pages
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - 'docs/**'
+      - '.github/workflows/deploy-redirects.yml'
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+concurrency:
+  group: "pages"
+  cancel-in-progress: false
+
+jobs:
+  deploy:
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+      - name: Generate redirect files
+        run: python docs/generate_redirects.py
+
+      - name: Setup Pages
+        uses: actions/configure-pages@v4
+
+      - name: Upload artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: 'docs/_site'
+
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4
@@ -0,0 +1 @@
+_site/
@@ -0,0 +1,142 @@
+#!/usr/bin/env python3
+"""
+Generate HTML redirect files from redirects.json.
+
+Usage:
+    python generate_redirects.py
+
+This script reads redirects.json and generates individual HTML files
+for each redirect path. Each HTML file uses meta refresh (0 delay)
+which is SEO-friendly and treated similarly to 301 redirects by Google.
+
+To add new redirects, simply edit redirects.json and re-run this script.
+"""
+
+import json
+import os
+from pathlib import Path
+
+# Default fallback URL for any path not in the redirect map
+DEFAULT_REDIRECT = "https://docs.langchain.com/oss/python/langgraph/overview"
+
+HTML_TEMPLATE = """<!doctype html>
+<html lang="en">
+<head>
+    <meta charset="utf-8">
+    <title>Redirecting...</title>
+    <link rel="canonical" href="{url}">
+    <meta name="robots" content="noindex">
+    <script>var anchor=window.location.hash.substr(1);location.href="{url}"+(anchor?"#"+anchor:"")</script>
+    <meta http-equiv="refresh" content="0; url={url}">
+</head>
+<body>
+Redirecting...
+</body>
+</html>
+"""
+
+ROOT_HTML_TEMPLATE = """<!doctype html>
+<html lang="en">
+<head>
+    <meta charset="utf-8">
+    <title>Redirecting to LangGraph Documentation</title>
+    <link rel="canonical" href="{url}">
+    <meta name="robots" content="noindex">
+    <script>var anchor=window.location.hash.substr(1);location.href="{url}"+(anchor?"#"+anchor:"")</script>
+    <meta http-equiv="refresh" content="0; url={url}">
+</head>
+<body>
+<h1>Documentation has moved</h1>
+<p>The LangGraph documentation has moved to <a href="{url}">docs.langchain.com</a>.</p>
+<p>Redirecting you now...</p>
+</body>
+</html>
+"""
+
+CATCHALL_404_TEMPLATE = """<!doctype html>
+<html lang="en">
+<head>
+    <meta charset="utf-8">
+    <title>Redirecting to LangGraph Documentation</title>
+    <link rel="canonical" href="{default_url}">
+    <meta name="robots" content="noindex">
+    <script>
+        // Catchall redirect for any unmapped paths
+        window.location.replace("{default_url}");
+    </script>
+    <meta http-equiv="refresh" content="0; url={default_url}">
+</head>
+<body>
+<h1>Documentation has moved</h1>
+<p>The LangGraph documentation has moved to <a href="{default_url}">docs.langchain.com</a>.</p>
+<p>Redirecting you now...</p>
+</body>
+</html>
+"""
+
+
+def generate_redirects():
+    script_dir = Path(__file__).parent
+    output_dir = script_dir / "_site"
+
+    # Load redirects
+    with open(script_dir / "redirects.json") as f:
+        redirects = json.load(f)
+
+    # Clean output directory
+    if output_dir.exists():
+        import shutil
+        shutil.rmtree(output_dir)
+    output_dir.mkdir(parents=True)
+
+    # Generate individual HTML files for each redirect
+    for old_path, new_url in redirects.items():
+        # Remove leading slash and create directory structure
+        path = old_path.lstrip("/")
+
+        # Check if path has a file extension (e.g., .txt, .xml)
+        # If so, create the file directly instead of a directory with index.html
+        path_obj = Path(path)
+        has_extension = path_obj.suffix and len(path_obj.suffix) <= 5
+
+        if not path:
+            html_path = output_dir / "index.html"
+        elif has_extension:
+            # For files with extensions, create the file directly
+            html_path = output_dir / path
+        else:
+            # For directory-style URLs, create index.html inside
+            html_path = output_dir / path / "index.html"
+
+        # Create parent directories
+        html_path.parent.mkdir(parents=True, exist_ok=True)
+
+        # Write the redirect HTML
+        html_path.write_text(HTML_TEMPLATE.format(url=new_url))
+        print(f"Created: {html_path}")
+
+    # Create root index.html
+    root_index = output_dir / "index.html"
+    if not root_index.exists():
+        root_index.write_text(ROOT_HTML_TEMPLATE.format(url=DEFAULT_REDIRECT))
+        print(f"Created: {root_index}")
+
+    # Create 404.html for catchall
+    catchall_404 = output_dir / "404.html"
+    catchall_404.write_text(CATCHALL_404_TEMPLATE.format(default_url=DEFAULT_REDIRECT))
+    print(f"Created: {catchall_404}")
+
+    # Copy static files (like llms.txt) that can't be redirected via HTML
+    static_files = ["llms.txt"]
+    for static_file in static_files:
+        src = script_dir / static_file
+        if src.exists():
+            dst = output_dir / static_file
+            dst.write_text(src.read_text())
+            print(f"Copied: {dst}")
+
+    print(f"\nGenerated {len(redirects)} redirect files in {output_dir}")
+
+
+if __name__ == "__main__":
+    generate_redirects()
@@ -0,0 +1,35 @@
+# LangGraph
+
+LangGraph documentation has moved to docs.langchain.com.
+
+## Overview
+
+- [LangGraph Overview](https://docs.langchain.com/oss/python/langgraph/overview): Introduction to LangGraph, a library for building stateful, multi-actor applications with LLMs.
+- [Why LangGraph?](https://docs.langchain.com/oss/python/langgraph/why-langgraph): Motivation for LangGraph and its key features.
+
+## Core Concepts
+
+- [Graph API](https://docs.langchain.com/oss/python/langgraph/graph-api): Learn how to define state, create nodes, and connect them with edges.
+- [Streaming](https://docs.langchain.com/oss/python/langgraph/streaming): Stream outputs from your graph for better UX.
+- [Persistence](https://docs.langchain.com/oss/python/langgraph/persistence): Add memory and checkpointing to your graphs.
+- [Add Memory](https://docs.langchain.com/oss/python/langgraph/add-memory): Implement short-term and long-term memory.
+- [Workflows & Agents](https://docs.langchain.com/oss/python/langgraph/workflows-agents): Build agents and workflows with LangGraph.
+
+## How-To Guides
+
+- [Use Subgraphs](https://docs.langchain.com/oss/python/langgraph/use-subgraphs): Compose graphs using subgraphs.
+- [Observability](https://docs.langchain.com/oss/python/langgraph/observability): Add tracing and debugging to your graphs.
+- [Common Errors](https://docs.langchain.com/oss/python/langgraph/common-errors): Troubleshoot common LangGraph errors.
+
+## Tutorials
+
+- [Agentic RAG](https://docs.langchain.com/oss/python/langgraph/agentic-rag): Build an agentic RAG system with LangGraph.
+- [SQL Agent](https://docs.langchain.com/oss/python/langgraph/sql-agent): Create a SQL agent with LangGraph.
+
+## Reference
+
+- [API Reference](https://reference.langchain.com/python/langgraph/): Complete API documentation for LangGraph.
+
+## LangGraph Platform
+
+For deploying LangGraph applications in production, see the [LangSmith documentation](https://docs.langchain.com/langsmith/agent-server).
@@ -0,0 +1,296 @@
+{
+  "/how-tos/stream-values": "https://docs.langchain.com/oss/python/langgraph/streaming",
+  "/how-tos/stream-updates": "https://docs.langchain.com/oss/python/langgraph/streaming",
+  "/how-tos/streaming-content": "https://docs.langchain.com/oss/python/langgraph/streaming",
+  "/how-tos/stream-multiple": "https://docs.langchain.com/oss/python/langgraph/streaming",
+  "/how-tos/streaming-tokens-without-langchain": "https://docs.langchain.com/oss/python/langgraph/streaming",
+  "/how-tos/streaming-from-final-node": "https://docs.langchain.com/oss/python/langgraph/streaming",
+  "/how-tos/streaming-events-from-within-tools-without-langchain": "https://docs.langchain.com/oss/python/langgraph/streaming",
+  "/how-tos/state-reducers": "https://docs.langchain.com/oss/python/langgraph/graph-api#define-and-update-state",
+  "/how-tos/sequence": "https://docs.langchain.com/oss/python/langgraph/graph-api#create-a-sequence-of-steps",
+  "/how-tos/branching": "https://docs.langchain.com/oss/python/langgraph/graph-api#create-branches",
+  "/how-tos/recursion-limit": "https://docs.langchain.com/oss/python/langgraph/graph-api#create-and-control-loops",
+  "/how-tos/visualization": "https://docs.langchain.com/oss/python/langgraph/graph-api#visualize-your-graph",
+  "/how-tos/input_output_schema": "https://docs.langchain.com/oss/python/langgraph/graph-api#define-input-and-output-schemas",
+  "/how-tos/pass_private_state": "https://docs.langchain.com/oss/python/langgraph/graph-api#pass-private-state-between-nodes",
+  "/how-tos/state-model": "https://docs.langchain.com/oss/python/langgraph/graph-api#use-pydantic-models-for-graph-state",
+  "/how-tos/map-reduce": "https://docs.langchain.com/oss/python/langgraph/graph-api#map-reduce-and-the-send-api",
+  "/how-tos/command": "https://docs.langchain.com/oss/python/langgraph/graph-api#combine-control-flow-and-state-updates-with-command",
+  "/how-tos/configuration": "https://docs.langchain.com/oss/python/langgraph/graph-api#add-runtime-configuration",
+  "/how-tos/node-retries": "https://docs.langchain.com/oss/python/langgraph/graph-api#add-retry-policies",
+  "/how-tos/return-when-recursion-limit-hits": "https://docs.langchain.com/oss/python/langgraph/graph-api#impose-a-recursion-limit",
+  "/how-tos/async": "https://docs.langchain.com/oss/python/langgraph/graph-api#async",
+  "/how-tos/memory/manage-conversation-history": "https://docs.langchain.com/oss/python/langgraph/add-memory",
+  "/how-tos/memory/delete-messages": "https://docs.langchain.com/oss/python/langgraph/add-memory#delete-messages",
+  "/how-tos/memory/add-summary-conversation-history": "https://docs.langchain.com/oss/python/langgraph/add-memory#summarize-messages",
+  "/how-tos/memory": "https://docs.langchain.com/oss/python/langgraph/add-memory",
+  "/agents/memory": "https://docs.langchain.com/oss/python/langgraph/add-memory",
+  "/how-tos/subgraph-transform-state": "https://docs.langchain.com/oss/python/langgraph/use-subgraphs#different-state-schemas",
+  "/how-tos/subgraphs-manage-state": "https://docs.langchain.com/oss/python/langgraph/use-subgraphs#add-persistence",
+  "/how-tos/persistence_postgres": "https://docs.langchain.com/oss/python/langgraph/add-memory#use-in-production",
+  "/how-tos/persistence_mongodb": "https://docs.langchain.com/oss/python/langgraph/add-memory#use-in-production",
+  "/how-tos/persistence_redis": "https://docs.langchain.com/oss/python/langgraph/add-memory#use-in-production",
+  "/how-tos/subgraph-persistence": "https://docs.langchain.com/oss/python/langgraph/add-memory#use-with-subgraphs",
+  "/how-tos/cross-thread-persistence": "https://docs.langchain.com/oss/python/langgraph/add-memory#add-long-term-memory",
+  "/cloud/how-tos/copy_threads": "https://docs.langchain.com/langsmith/use-threads",
+  "/cloud/how-tos/check-thread-status": "https://docs.langchain.com/langsmith/use-threads",
+  "/cloud/concepts/threads": "https://docs.langchain.com/oss/python/langgraph/persistence#threads",
+  "/how-tos/persistence": "https://docs.langchain.com/oss/python/langgraph/add-memory",
+  "/how-tos/tool-calling-errors": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+  "/how-tos/pass-config-to-tools": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+  "/how-tos/pass-run-time-values-to-tools": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+  "/how-tos/update-state-from-tools": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+  "/agents/tools": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+  "/how-tos/agent-handoffs": "https://docs.langchain.com/oss/python/langgraph/graph-api",
+  "/how-tos/multi-agent-network": "https://docs.langchain.com/oss/python/langgraph/graph-api",
+  "/how-tos/multi-agent-multi-turn-convo": "https://docs.langchain.com/oss/python/langgraph/graph-api",
+  "/cloud/index": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/cloud/how-tos/index": "https://docs.langchain.com/langsmith/home",
+  "/cloud/concepts/api": "https://docs.langchain.com/langsmith/agent-server",
+  "/cloud/concepts/cloud": "https://docs.langchain.com/langsmith/cloud",
+  "/cloud/faq/studio": "https://docs.langchain.com/langsmith/studio",
+  "/cloud/how-tos/human_in_the_loop_edit_state": "https://docs.langchain.com/langsmith/add-human-in-the-loop",
+  "/cloud/how-tos/human_in_the_loop_user_input": "https://docs.langchain.com/langsmith/add-human-in-the-loop",
+  "/concepts/platform_architecture": "https://docs.langchain.com/langsmith/cloud#architecture",
+  "/cloud/how-tos/stream_values": "https://docs.langchain.com/langsmith/streaming",
+  "/cloud/how-tos/stream_updates": "https://docs.langchain.com/langsmith/streaming",
+  "/cloud/how-tos/stream_messages": "https://docs.langchain.com/langsmith/streaming",
+  "/cloud/how-tos/stream_events": "https://docs.langchain.com/langsmith/streaming",
+  "/cloud/how-tos/stream_debug": "https://docs.langchain.com/langsmith/streaming",
+  "/cloud/how-tos/stream_multiple": "https://docs.langchain.com/langsmith/streaming",
+  "/cloud/concepts/streaming": "https://docs.langchain.com/oss/python/langgraph/streaming",
+  "/agents/streaming": "https://docs.langchain.com/oss/python/langgraph/streaming",
+  "/how-tos/create-react-agent": "https://docs.langchain.com/oss/python/langchain/agents#basic-configuration",
+  "/how-tos/create-react-agent-memory": "https://docs.langchain.com/oss/python/langgraph/add-memory",
+  "/how-tos/create-react-agent-system-prompt": "https://docs.langchain.com/oss/python/langgraph/add-memory",
+  "/how-tos/create-react-agent-structured-output": "https://docs.langchain.com/oss/python/langchain/agents#structured-output",
+  "/prebuilt": "https://docs.langchain.com/oss/python/langchain/agents",
+  "/reference/prebuilt": "https://reference.langchain.com/python/langgraph/agents/",
+  "/concepts/high_level": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/concepts/index": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/concepts/v0-human-in-the-loop": "https://docs.langchain.com/oss/python/langgraph/interrupts",
+  "/how-tos/index": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/tutorials/introduction": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/agents/deployment": "https://docs.langchain.com/oss/python/langgraph/local-server",
+  "/how-tos/deploy-self-hosted": "https://docs.langchain.com/langsmith/platform-setup",
+  "/concepts/self_hosted": "https://docs.langchain.com/langsmith/platform-setup",
+  "/tutorials/deployment": "https://docs.langchain.com/langsmith/deployments",
+  "/cloud/how-tos/assistant_versioning": "https://docs.langchain.com/langsmith/configuration-cloud",
+  "/cloud/concepts/runs": "https://docs.langchain.com/langsmith/assistants#execution",
+  "/how-tos/wait-user-input-functional": "https://docs.langchain.com/oss/python/langgraph/functional-api",
+  "/how-tos/review-tool-calls-functional": "https://docs.langchain.com/oss/python/langgraph/functional-api",
+  "/how-tos/create-react-agent-hitl": "https://docs.langchain.com/oss/python/langgraph/interrupts",
+  "/agents/human-in-the-loop": "https://docs.langchain.com/oss/python/langgraph/interrupts",
+  "/how-tos/human_in_the_loop/dynamic_breakpoints": "https://docs.langchain.com/oss/python/langgraph/interrupts",
+  "/concepts/breakpoints": "https://docs.langchain.com/oss/python/langgraph/interrupts",
+  "/how-tos/human_in_the_loop/breakpoints": "https://docs.langchain.com/oss/python/langgraph/interrupts",
+  "/cloud/how-tos/human_in_the_loop_breakpoint": "https://docs.langchain.com/langsmith/add-human-in-the-loop",
+  "/how-tos/human_in_the_loop/edit-graph-state": "https://docs.langchain.com/oss/python/langgraph/use-time-travel",
+  "/examples/index": "https://docs.langchain.com/oss/python/langgraph/case-studies",
+  "/guides/index": "https://docs.langchain.com/oss/python/langchain/overview",
+  "/tutorials/index": "https://docs.langchain.com/oss/python/learn",
+  "/llms-txt-overview": "https://docs.langchain.com/llms.txt",
+  "/tutorials/rag/langgraph_adaptive_rag": "https://docs.langchain.com/oss/python/langgraph/agentic-rag",
+  "/tutorials/multi_agent/multi-agent-collaboration": "https://docs.langchain.com/oss/python/langchain/multi-agent",
+  "/how-tos/create-react-agent-manage-message-history": "https://docs.langchain.com/oss/python/langgraph/add-memory",
+  "/how-tos/many-tools": "https://docs.langchain.com/oss/python/langchain/tools",
+  "/tutorials/customer-support/customer-support": "https://docs.langchain.com/oss/python/langgraph/agentic-rag",
+  "/how-tos/react-agent-structured-output": "https://docs.langchain.com/oss/python/langchain/agents#structured-output",
+  "/tutorials/code_assistant/langgraph_code_assistant": "https://docs.langchain.com/oss/python/langgraph/agentic-rag",
+  "/tutorials/multi_agent/hierarchical_agent_teams": "https://docs.langchain.com/oss/python/langchain/supervisor",
+  "/tutorials/auth/getting_started": "https://docs.langchain.com/langsmith/auth",
+  "/tutorials/auth/resource_auth": "https://docs.langchain.com/langsmith/resource-auth",
+  "/tutorials/auth/add_auth_server": "https://docs.langchain.com/langsmith/add-auth-server",
+  "/how-tos/use-remote-graph": "https://docs.langchain.com/langsmith/use-remote-graph",
+  "/how-tos/autogen-integration": "https://docs.langchain.com/langsmith/autogen-integration",
+  "/how-tos/human_in_the_loop/wait-user-input": "https://docs.langchain.com/oss/python/langgraph/interrupts",
+  "/cloud/how-tos/use_stream_react": "https://docs.langchain.com/langsmith/use-stream-react",
+  "/cloud/how-tos/generative_ui_react": "https://docs.langchain.com/langsmith/generative-ui-react",
+  "/concepts/langgraph_platform": "https://docs.langchain.com/langsmith/home",
+  "/concepts/langgraph_components": "https://docs.langchain.com/langsmith/components",
+  "/concepts/langgraph_server": "https://docs.langchain.com/langsmith/agent-server",
+  "/concepts/langgraph_data_plane": "https://docs.langchain.com/langsmith/data-plane",
+  "/concepts/langgraph_control_plane": "https://docs.langchain.com/langsmith/control-plane",
+  "/concepts/langgraph_cli": "https://docs.langchain.com/langsmith/cli",
+  "/concepts/langgraph_studio": "https://docs.langchain.com/langsmith/studio",
+  "/cloud/how-tos/studio/quick_start": "https://docs.langchain.com/langsmith/quick-start-studio",
+  "/cloud/how-tos/invoke_studio": "https://docs.langchain.com/langsmith/use-studio",
+  "/cloud/how-tos/studio/manage_assistants": "https://docs.langchain.com/langsmith/use-studio",
+  "/cloud/how-tos/threads_studio": "https://docs.langchain.com/langsmith/use-threads",
+  "/cloud/how-tos/iterate_graph_studio": "https://docs.langchain.com/langsmith/use-studio",
+  "/cloud/how-tos/studio/run_evals": "https://docs.langchain.com/langsmith/observability",
+  "/cloud/how-tos/clone_traces_studio": "https://docs.langchain.com/langsmith/observability",
+  "/cloud/how-tos/datasets_studio": "https://docs.langchain.com/langsmith/use-studio",
+  "/concepts/sdk": "https://docs.langchain.com/langsmith/sdk",
+  "/concepts/plans": "https://docs.langchain.com/langsmith/home",
+  "/concepts/application_structure": "https://docs.langchain.com/langsmith/application-structure",
+  "/concepts/scalability_and_resilience": "https://docs.langchain.com/langsmith/scalability-and-resilience",
+  "/concepts/auth": "https://docs.langchain.com/langsmith/auth",
+  "/how-tos/auth/custom_auth": "https://docs.langchain.com/langsmith/custom-auth",
+  "/how-tos/auth/openapi_security": "https://docs.langchain.com/langsmith/openapi-security",
+  "/concepts/assistants": "https://docs.langchain.com/langsmith/assistants",
+  "/cloud/how-tos/configuration_cloud": "https://docs.langchain.com/langsmith/configuration-cloud",
+  "/cloud/how-tos/use_threads": "https://docs.langchain.com/langsmith/use-threads",
+  "/cloud/how-tos/background_run": "https://docs.langchain.com/langsmith/background-run",
+  "/cloud/how-tos/same-thread": "https://docs.langchain.com/langsmith/same-thread",
+  "/cloud/how-tos/stateless_runs": "https://docs.langchain.com/langsmith/stateless-runs",
+  "/cloud/how-tos/configurable_headers": "https://docs.langchain.com/langsmith/configurable-headers",
+  "/concepts/double_texting": "https://docs.langchain.com/langsmith/double-texting",
+  "/cloud/how-tos/interrupt_concurrent": "https://docs.langchain.com/langsmith/interrupt-concurrent",
+  "/cloud/how-tos/rollback_concurrent": "https://docs.langchain.com/langsmith/rollback-concurrent",
+  "/cloud/how-tos/reject_concurrent": "https://docs.langchain.com/langsmith/reject-concurrent",
+  "/cloud/how-tos/enqueue_concurrent": "https://docs.langchain.com/langsmith/enqueue-concurrent",
+  "/cloud/concepts/webhooks": "https://docs.langchain.com/langsmith/use-webhooks",
+  "/cloud/how-tos/webhooks": "https://docs.langchain.com/langsmith/use-webhooks",
+  "/cloud/concepts/cron_jobs": "https://docs.langchain.com/langsmith/cron-jobs",
+  "/cloud/how-tos/cron_jobs": "https://docs.langchain.com/langsmith/cron-jobs",
+  "/how-tos/http/custom_lifespan": "https://docs.langchain.com/langsmith/custom-lifespan",
+  "/how-tos/http/custom_middleware": "https://docs.langchain.com/langsmith/custom-middleware",
+  "/how-tos/http/custom_routes": "https://docs.langchain.com/langsmith/custom-routes",
+  "/cloud/concepts/data_storage_and_privacy": "https://docs.langchain.com/langsmith/data-storage-and-privacy",
+  "/cloud/deployment/semantic_search": "https://docs.langchain.com/langsmith/semantic-search",
+  "/how-tos/ttl/configure_ttl": "https://docs.langchain.com/langsmith/configure-ttl",
+  "/concepts/deployment_options": "https://docs.langchain.com/langsmith/deployments",
+  "/cloud/quick_start": "https://docs.langchain.com/langsmith/deployment-quickstart",
+  "/cloud/deployment/setup": "https://docs.langchain.com/langsmith/setup-app-requirements-txt",
+  "/cloud/deployment/setup_pyproject": "https://docs.langchain.com/langsmith/setup-pyproject",
+  "/cloud/deployment/setup_javascript": "https://docs.langchain.com/langsmith/setup-javascript",
+  "/cloud/deployment/custom_docker": "https://docs.langchain.com/langsmith/custom-docker",
+  "/cloud/deployment/graph_rebuild": "https://docs.langchain.com/langsmith/graph-rebuild",
+  "/concepts/langgraph_cloud": "https://docs.langchain.com/langsmith/cloud",
+  "/concepts/langgraph_self_hosted_data_plane": "https://docs.langchain.com/langsmith/platform-setup",
+  "/concepts/langgraph_self_hosted_control_plane": "https://docs.langchain.com/langsmith/platform-setup",
+  "/concepts/langgraph_standalone_container": "https://docs.langchain.com/langsmith/docker",
+  "/cloud/deployment/cloud": "https://docs.langchain.com/langsmith/cloud",
+  "/cloud/deployment/self_hosted_data_plane": "https://docs.langchain.com/langsmith/platform-setup",
+  "/cloud/deployment/self_hosted_control_plane": "https://docs.langchain.com/langsmith/platform-setup",
+  "/cloud/deployment/standalone_container": "https://docs.langchain.com/langsmith/docker",
+  "/concepts/server-mcp": "https://docs.langchain.com/langsmith/server-mcp",
+  "/cloud/how-tos/human_in_the_loop_time_travel": "https://docs.langchain.com/langsmith/human-in-the-loop-time-travel",
+  "/cloud/how-tos/add-human-in-the-loop": "https://docs.langchain.com/langsmith/add-human-in-the-loop",
+  "/cloud/deployment/egress": "https://docs.langchain.com/langsmith/env-var",
+  "/cloud/how-tos/streaming": "https://docs.langchain.com/langsmith/streaming",
+  "/cloud/reference/api/api_ref": "https://docs.langchain.com/langsmith/server-api-ref",
+  "/cloud/reference/langgraph_server_changelog": "https://docs.langchain.com/langsmith/agent-server-changelog",
+  "/cloud/reference/api/api_ref_control_plane": "https://docs.langchain.com/langsmith/api-ref-control-plane",
+  "/cloud/reference/cli": "https://docs.langchain.com/langsmith/cli",
+  "/cloud/reference/env_var": "https://docs.langchain.com/langsmith/env-var",
+  "/troubleshooting/studio": "https://docs.langchain.com/langsmith/troubleshooting-studio",
+  "/index": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/agents/agents": "https://docs.langchain.com/oss/python/langchain/agents",
+  "/concepts/why-langgraph": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/tutorials/get-started/1-build-basic-chatbot": "https://docs.langchain.com/oss/python/langgraph/quickstart",
+  "/tutorials/get-started/2-add-tools": "https://docs.langchain.com/oss/python/langgraph/quickstart",
+  "/tutorials/get-started/3-add-memory": "https://docs.langchain.com/oss/python/langgraph/quickstart",
+  "/tutorials/get-started/4-human-in-the-loop": "https://docs.langchain.com/oss/python/langgraph/quickstart",
+  "/tutorials/get-started/5-customize-state": "https://docs.langchain.com/oss/python/langgraph/quickstart",
+  "/tutorials/get-started/6-time-travel": "https://docs.langchain.com/oss/python/langgraph/quickstart",
+  "/tutorials/langsmith/local-server": "https://docs.langchain.com/oss/python/langgraph/local-server",
+  "/tutorials/workflows": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+  "/tutorials/plan-and-execute/plan-and-execute": "https://docs.langchain.com/oss/python/langchain/middleware/built-in#to-do-list",
+  "/tutorials/langgraph-platform/local-server/local-server": "https://docs.langchain.com/langsmith/local-server",
+  "/concepts/agentic_concepts": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+  "/agents/overview": "https://docs.langchain.com/oss/python/langchain/agents",
+  "/agents/run_agents": "https://docs.langchain.com/oss/python/langgraph/quickstart",
+  "/concepts/low_level": "https://docs.langchain.com/oss/python/langgraph/graph-api",
+  "/how-tos/graph-api": "https://docs.langchain.com/oss/python/langgraph/graph-api",
+  "/how-tos/react-agent-from-scratch": "https://docs.langchain.com/oss/python/langchain/quickstart",
+  "/concepts/functional_api": "https://docs.langchain.com/oss/python/langgraph/functional-api",
+  "/how-tos/use-functional-api": "https://docs.langchain.com/oss/python/langgraph/functional-api",
+  "/concepts/pregel": "https://docs.langchain.com/oss/python/langgraph/pregel",
+  "/concepts/streaming": "https://docs.langchain.com/oss/python/langgraph/streaming",
+  "/how-tos/streaming": "https://docs.langchain.com/oss/python/langgraph/streaming",
+  "/concepts/persistence": "https://docs.langchain.com/oss/python/langgraph/persistence",
+  "/concepts/durable_execution": "https://docs.langchain.com/oss/python/langgraph/durable-execution",
+  "/concepts/memory": "https://docs.langchain.com/oss/python/langgraph/memory",
+  "/how-tos/memory/add-memory": "https://docs.langchain.com/oss/python/langgraph/add-memory",
+  "/agents/context": "https://docs.langchain.com/oss/python/langgraph/add-memory",
+  "/agents/models": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/concepts/tools": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+  "/how-tos/tool-calling": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+  "/concepts/human_in_the_loop": "https://docs.langchain.com/oss/python/langgraph/interrupts",
+  "/how-tos/human_in_the_loop/add-human-in-the-loop": "https://docs.langchain.com/oss/python/langgraph/interrupts",
+  "/concepts/time-travel": "https://docs.langchain.com/oss/python/langgraph/persistence",
+  "/how-tos/human_in_the_loop/time-travel": "https://docs.langchain.com/oss/python/langgraph/use-time-travel",
+  "/concepts/subgraphs": "https://docs.langchain.com/oss/python/langgraph/use-subgraphs",
+  "/how-tos/subgraph": "https://docs.langchain.com/oss/python/langgraph/use-subgraphs",
+  "/concepts/multi_agent": "https://docs.langchain.com/oss/python/langgraph/graph-api",
+  "/agents/multi-agent": "https://docs.langchain.com/oss/python/langchain/multi-agent",
+  "/how-tos/multi_agent": "https://docs.langchain.com/oss/python/langgraph/graph-api",
+  "/concepts/mcp": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/agents/mcp": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/concepts/tracing": "https://docs.langchain.com/oss/python/langgraph/observability",
+  "/how-tos/enable-tracing": "https://docs.langchain.com/oss/python/langgraph/observability",
+  "/agents/evals": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/concepts/template_applications": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/tutorials/rag/langgraph_agentic_rag": "https://docs.langchain.com/oss/python/langgraph/agentic-rag",
+  "/tutorials/multi_agent/agent_supervisor": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+  "/tutorials/sql/sql-agent": "https://docs.langchain.com/oss/python/langgraph/sql-agent",
+  "/agents/ui": "https://docs.langchain.com/oss/python/langgraph/ui",
+  "/how-tos/run-id-langsmith": "https://docs.langchain.com/oss/python/langgraph/observability",
+  "/troubleshooting/errors/index": "https://docs.langchain.com/oss/python/langgraph/common-errors",
+  "/troubleshooting/errors/INVALID_CHAT_HISTORY": "https://docs.langchain.com/oss/python/langgraph/INVALID_CHAT_HISTORY",
+  "/troubleshooting/errors/INVALID_LICENSE": "https://docs.langchain.com/oss/python/langgraph/common-errors",
+  "/adopters": "https://docs.langchain.com/oss/python/langgraph/case-studies",
+  "/concepts/faq": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/agents/prebuilt": "https://docs.langchain.com/oss/python/langchain/agents",
+  "/reference/index": "https://reference.langchain.com/python/langgraph/",
+  "/reference/graphs": "https://reference.langchain.com/python/langgraph/graphs/",
+  "/reference/func": "https://reference.langchain.com/python/langgraph/func/",
+  "/reference/pregel": "https://reference.langchain.com/python/langgraph/pregel/",
+  "/reference/checkpoints": "https://reference.langchain.com/python/langgraph/checkpoints/",
+  "/reference/store": "https://reference.langchain.com/python/langgraph/store/",
+  "/reference/cache": "https://reference.langchain.com/python/langgraph/cache/",
+  "/reference/types": "https://reference.langchain.com/python/langgraph/types/",
+  "/reference/runtime": "https://reference.langchain.com/python/langgraph/runtime/",
+  "/reference/config": "https://reference.langchain.com/python/langgraph/config/",
+  "/reference/errors": "https://reference.langchain.com/python/langgraph/errors/",
+  "/reference/constants": "https://reference.langchain.com/python/langgraph/constants/",
+  "/reference/channels": "https://reference.langchain.com/python/langgraph/channels/",
+  "/reference/agents": "https://reference.langchain.com/python/langgraph/agents/",
+  "/reference/supervisor": "https://reference.langchain.com/python/langgraph/supervisor/",
+  "/reference/swarm": "https://reference.langchain.com/python/langgraph/swarm/",
+  "/reference/mcp": "https://reference.langchain.com/python/langgraph/mcp/",
+  "/cloud/reference/sdk/python_sdk_ref": "https://reference.langchain.com/python/langsmith/deployment/sdk/",
+  "/reference/remote_graph": "https://reference.langchain.com/python/langsmith/deployment/remote_graph/",
+  "/additional-resources/index": "https://docs.langchain.com/oss/python/langchain/overview",
+  "/cloud/reference/sdk/js_ts_sdk_ref": "https://reference.langchain.com/javascript/modules/langsmith.html",
+  "/snippets/chat_model_tabs": "https://docs.langchain.com/oss/python/langchain/overview",
+  "/troubleshooting/errors/GRAPH_RECURSION_LIMIT": "https://docs.langchain.com/oss/python/langgraph/GRAPH_RECURSION_LIMIT",
+  "/troubleshooting/errors/INVALID_CONCURRENT_GRAPH_UPDATE": "https://docs.langchain.com/oss/python/langgraph/INVALID_CONCURRENT_GRAPH_UPDATE",
+  "/troubleshooting/errors/INVALID_GRAPH_NODE_RETURN_VALUE": "https://docs.langchain.com/oss/python/langgraph/INVALID_GRAPH_NODE_RETURN_VALUE",
+  "/troubleshooting/errors/MULTIPLE_SUBGRAPHS": "https://docs.langchain.com/oss/python/langgraph/MULTIPLE_SUBGRAPHS",
+  "/tutorials/rag/langgraph_self_rag": "https://docs.langchain.com/oss/python/langgraph/agentic-rag",
+  "/additional-resources": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/examples": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/guides": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/how-tos/autogen-integration-functional": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/how-tos/cross-thread-persistence-functional": "https://docs.langchain.com/oss/python/langgraph/add-memory#add-long-term-memory",
+  "/how-tos/disable-streaming": "https://docs.langchain.com/oss/python/langgraph/streaming",
+  "/how-tos/memory/semantic-search": "https://docs.langchain.com/oss/python/langgraph/add-memory",
+  "/how-tos/multi-agent-multi-turn-convo-functional": "https://docs.langchain.com/oss/python/langgraph/graph-api",
+  "/how-tos/multi-agent-network-functional": "https://docs.langchain.com/oss/python/langgraph/graph-api",
+  "/how-tos/persistence-functional": "https://docs.langchain.com/oss/python/langgraph/add-memory",
+  "/how-tos/react-agent-from-scratch-functional": "https://docs.langchain.com/oss/python/langgraph/workflows-agents",
+  "/reference": "https://reference.langchain.com/python/langgraph/",
+  "/troubleshooting/errors": "https://docs.langchain.com/oss/python/langgraph/common-errors",
+  "/tutorials/chatbot-simulation-evaluation/agent-simulation-evaluation": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/tutorials/chatbot-simulation-evaluation/langsmith-agent-simulation-evaluation": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/tutorials/chatbots/information-gather-prompting": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/tutorials/extraction/retries": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/tutorials/langgraph-platform/local-server": "https://docs.langchain.com/langsmith/agent-server",
+  "/tutorials/lats/lats": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/tutorials/llm-compiler/LLMCompiler": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/tutorials/rag/langgraph_adaptive_rag_local": "https://docs.langchain.com/oss/python/langgraph/agentic-rag",
+  "/tutorials/rag/langgraph_crag": "https://docs.langchain.com/oss/python/langgraph/agentic-rag",
+  "/tutorials/rag/langgraph_crag_local": "https://docs.langchain.com/oss/python/langgraph/agentic-rag",
+  "/tutorials/rag/langgraph_self_rag_local": "https://docs.langchain.com/oss/python/langgraph/agentic-rag",
+  "/tutorials/reflection/reflection": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/tutorials/reflexion/reflexion": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/tutorials/rewoo/rewoo": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/tutorials/self-discover/self-discover": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/tutorials/tnt-llm/tnt-llm": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/tutorials/tot/tot": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/tutorials/usaco/usaco": "https://docs.langchain.com/oss/python/langgraph/overview",
+  "/tutorials/web-navigation/web_voyager": "https://docs.langchain.com/oss/python/langgraph/overview"
+}
@@ -728,7 +728,6 @@ async def _acall_impl(
                    )
                else:
                    fut.set_result(None)
-                futures()[fut] = next_task  # type: ignore[index]
            else:
                # schedule the next task
                fut = cast(
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"

 [project]
 name = "langgraph"
-version = "1.0.8"
+version = "1.0.9"
 description = "Building stateful, multi-actor applications with LLMs"
 authors = []
 requires-python = ">=3.10"
@@ -27,7 +27,7 @@ dependencies = [
    "langchain-core>=0.1",
    "langgraph-checkpoint>=2.1.0,<5.0.0",
    "langgraph-sdk>=0.3.0,<0.4.0",
-    "langgraph-prebuilt>=1.0.7,<1.1.0",
+    "langgraph-prebuilt>=1.0.8,<1.1.0",
    "xxhash>=3.5.0",
    "pydantic>=2.7.4",
 ]
@@ -5800,6 +5800,284 @@ def test_multiple_interrupts_functional_cache(
    assert counter == 6


+def test_task_before_interrupt_resume(
+    sync_checkpointer: BaseCheckpointSaver,
+) -> None:
+    """Test that Command(resume=value) works correctly when a @task runs
+    before interrupt-producing tasks in an @entrypoint.
+
+    The @task wrapper on both setup and ask is essential to reproduce the bug:
+    - @task on setup triggers a mid-step put_writes (creating a new pending_writes list)
+    - @task on ask means interrupt() runs in a child scratchpad that must
+      delegate to the parent for null resume consumption tracking
+    """
+
+    @entrypoint(checkpointer=sync_checkpointer)
+    def workflow(number_of_topics: int) -> dict:
+        @task
+        def setup() -> int:
+            return number_of_topics
+
+        @task
+        def ask(question: str) -> str:
+            return interrupt(question)
+
+        n = setup().result()
+
+        answers = []
+        for i in range(n):
+            q = f"Whats the answer for topic {i + 1}?"
+            answers.append(ask(q).result())
+
+        return {"answers": answers}
+
+    config = {"configurable": {"thread_id": "1"}}
+
+    # First invocation - should get first interrupt
+    result = workflow.invoke(2, config=config)
+    assert "__interrupt__" in result
+    assert len(result["__interrupt__"]) == 1
+    assert result["__interrupt__"][0].value == "Whats the answer for topic 1?"
+
+    # Resume with answer for topic 1 - should get second interrupt
+    result = workflow.invoke(Command(resume="answer1"), config=config)
+    assert "__interrupt__" in result, f"Expected interrupt for topic 2, got: {result}"
+    assert len(result["__interrupt__"]) == 1
+    assert result["__interrupt__"][0].value == "Whats the answer for topic 2?"
+
+    # Resume with answer for topic 2 - should get final result
+    result = workflow.invoke(Command(resume="answer2"), config=config)
+    assert result == {"answers": ["answer1", "answer2"]}
+
+
+def test_multiple_tasks_before_interrupt_resume(
+    sync_checkpointer: BaseCheckpointSaver,
+) -> None:
+    """Test that Command(resume=value) works correctly when multiple @tasks
+    run before an interrupt-producing task in an @entrypoint."""
+
+    @entrypoint(checkpointer=sync_checkpointer)
+    def workflow(inputs: dict) -> dict:
+        @task
+        def step_a(x: int) -> int:
+            return x + 1
+
+        @task
+        def step_b(x: int) -> int:
+            return x * 2
+
+        @task
+        def ask(question: str) -> str:
+            return interrupt(question)
+
+        a = step_a(inputs["x"]).result()
+        b = step_b(a).result()
+
+        answer = ask(f"Result so far is {b}. What next?").result()
+
+        return {"computed": b, "answer": answer}
+
+    config = {"configurable": {"thread_id": "1"}}
+
+    # First invocation - should get interrupt
+    result = workflow.invoke({"x": 5}, config=config)
+    assert "__interrupt__" in result
+    assert result["__interrupt__"][0].value == "Result so far is 12. What next?"
+
+    # Resume
+    result = workflow.invoke(Command(resume="continue"), config=config)
+    assert result == {"computed": 12, "answer": "continue"}
+
+
+def test_no_redundant_put_writes_for_cached_task(
+    sync_checkpointer: BaseCheckpointSaver,
+) -> None:
+    """Cached @tasks on resume must not trigger redundant put_writes."""
+    from unittest.mock import patch
+
+    from langgraph.pregel._loop import PregelLoop
+
+    @task
+    def setup(x: int) -> int:
+        return x
+
+    @task
+    def ask(question: str) -> str:
+        return interrupt(question)
+
+    @entrypoint(checkpointer=sync_checkpointer)
+    def workflow(x: int) -> dict:
+        n = setup(x).result()
+        answer = ask(f"q{n}").result()
+        return {"answer": answer}
+
+    config = {"configurable": {"thread_id": "1"}}
+    result = workflow.invoke(1, config=config)
+    assert "__interrupt__" in result
+
+    put_writes_task_ids: list[str] = []
+    orig = PregelLoop.put_writes
+
+    def spy(self, task_id, writes):
+        put_writes_task_ids.append(task_id)
+        return orig(self, task_id, writes)
+
+    with patch.object(PregelLoop, "put_writes", spy):
+        result = workflow.invoke(Command(resume="ans"), config=config)
+
+    assert result == {"answer": "ans"}
+    # Count unique non-null task IDs that got put_writes.
+    # Should be exactly 2: the ask task and the entrypoint task.
+    # If 3, the cached setup task is being redundantly re-committed.
+    non_null = set(tid for tid in put_writes_task_ids if not tid.startswith("00000000"))
+    assert len(non_null) == 2, (
+        f"Expected 2 task IDs in put_writes (ask + entrypoint), got {len(non_null)}"
+    )
+
+
+def test_node_before_interrupt_resume_graph_api(
+    sync_checkpointer: BaseCheckpointSaver,
+) -> None:
+    """Test that Command(resume=value) works correctly in a StateGraph when a
+    node runs before a node that calls interrupt(). This is the graph-API
+    analog of test_task_before_interrupt_resume (entrypoint API)."""
+
+    class State(TypedDict):
+        topics: list[str]
+        answers: Annotated[list[str], operator.add]
+
+    def setup(state: State) -> dict:
+        return {"topics": [f"topic {i + 1}" for i in range(len(state["topics"]))]}
+
+    def ask(state: State) -> dict:
+        answers = []
+        for topic in state["topics"]:
+            answer = interrupt(f"Whats the answer for {topic}?")
+            answers.append(answer)
+        return {"answers": answers}
+
+    graph = (
+        StateGraph(State)
+        .add_node("setup", setup)
+        .add_node("ask", ask)
+        .add_edge(START, "setup")
+        .add_edge("setup", "ask")
+        .add_edge("ask", END)
+        .compile(checkpointer=sync_checkpointer)
+    )
+
+    config = {"configurable": {"thread_id": "1"}}
+
+    # First invocation - setup runs, then ask interrupts on the first topic
+    result = graph.invoke({"topics": ["a", "b"], "answers": []}, config=config)
+    assert "__interrupt__" in result
+    assert len(result["__interrupt__"]) == 1
+    assert result["__interrupt__"][0].value == "Whats the answer for topic 1?"
+
+    # Resume with answer for topic 1 - should get second interrupt
+    result = graph.invoke(Command(resume="answer1"), config=config)
+    assert "__interrupt__" in result, f"Expected interrupt for topic 2, got: {result}"
+    assert len(result["__interrupt__"]) == 1
+    assert result["__interrupt__"][0].value == "Whats the answer for topic 2?"
+
+    # Resume with answer for topic 2 - should complete
+    result = graph.invoke(Command(resume="answer2"), config=config)
+    assert result == {
+        "topics": ["topic 1", "topic 2"],
+        "answers": ["answer1", "answer2"],
+    }
+
+
+def test_multiple_nodes_before_interrupt_resume_graph_api(
+    sync_checkpointer: BaseCheckpointSaver,
+) -> None:
+    """Test that Command(resume=value) works correctly in a StateGraph when
+    multiple nodes run before a node that calls interrupt(). This is the
+    graph-API analog of test_multiple_tasks_before_interrupt_resume."""
+
+    class State(TypedDict):
+        value: int
+        answer: str
+
+    def step_a(state: State) -> dict:
+        return {"value": state["value"] + 1}
+
+    def step_b(state: State) -> dict:
+        return {"value": state["value"] * 2}
+
+    def ask(state: State) -> dict:
+        answer = interrupt(f"Result so far is {state['value']}. What next?")
+        return {"answer": answer}
+
+    graph = (
+        StateGraph(State)
+        .add_node("step_a", step_a)
+        .add_node("step_b", step_b)
+        .add_node("ask", ask)
+        .add_edge(START, "step_a")
+        .add_edge("step_a", "step_b")
+        .add_edge("step_b", "ask")
+        .add_edge("ask", END)
+        .compile(checkpointer=sync_checkpointer)
+    )
+
+    config = {"configurable": {"thread_id": "1"}}
+
+    # First invocation - step_a and step_b run, then ask interrupts
+    result = graph.invoke({"value": 5, "answer": ""}, config=config)
+    assert "__interrupt__" in result
+    assert result["__interrupt__"][0].value == "Result so far is 12. What next?"
+
+    # Resume - should complete
+    result = graph.invoke(Command(resume="continue"), config=config)
+    assert result == {"value": 12, "answer": "continue"}
+
+
+def test_node_before_multiple_interrupt_cycles_graph_api(
+    sync_checkpointer: BaseCheckpointSaver,
+) -> None:
+    """Test that a node running before an interrupt node does not interfere
+    with multiple interrupt/resume cycles in a StateGraph."""
+
+    class State(TypedDict):
+        count: int
+        data: str
+
+    def prepare(state: State) -> dict:
+        return {"count": state["count"] + 10}
+
+    def multi_interrupt(state: State) -> dict:
+        first = interrupt("First question?")
+        second = interrupt("Second question?")
+        return {"data": f"{first},{second}"}
+
+    graph = (
+        StateGraph(State)
+        .add_node("prepare", prepare)
+        .add_node("multi_interrupt", multi_interrupt)
+        .add_edge(START, "prepare")
+        .add_edge("prepare", "multi_interrupt")
+        .add_edge("multi_interrupt", END)
+        .compile(checkpointer=sync_checkpointer)
+    )
+
+    config = {"configurable": {"thread_id": "1"}}
+
+    # First invocation - prepare runs, multi_interrupt hits first interrupt
+    result = graph.invoke({"count": 0, "data": ""}, config=config)
+    assert "__interrupt__" in result
+    assert result["__interrupt__"][0].value == "First question?"
+
+    # Resume first interrupt - hits second interrupt
+    result = graph.invoke(Command(resume="first_answer"), config=config)
+    assert "__interrupt__" in result
+    assert result["__interrupt__"][0].value == "Second question?"
+
+    # Resume second interrupt - completes
+    result = graph.invoke(Command(resume="second_answer"), config=config)
+    assert result == {"count": 10, "data": "first_answer,second_answer"}
+
+
 def test_double_interrupt_subgraph(sync_checkpointer: BaseCheckpointSaver) -> None:
    class AgentState(TypedDict):
        input: str
@@ -7920,6 +7920,290 @@ async def test_interrupts_in_tasks_surfaced_once(
    assert result[1] == "Added Will!"


+@NEEDS_CONTEXTVARS
+async def test_task_before_interrupt_resume(
+    async_checkpointer: BaseCheckpointSaver,
+) -> None:
+    """Test that Command(resume=value) works correctly when a @task runs
+    before interrupt-producing tasks in an @entrypoint.
+
+    The @task wrapper on both setup and ask is essential to reproduce the bug:
+    - @task on setup triggers a mid-step put_writes (creating a new pending_writes list)
+    - @task on ask means interrupt() runs in a child scratchpad that must
+      delegate to the parent for null resume consumption tracking
+    """
+
+    @entrypoint(checkpointer=async_checkpointer)
+    async def workflow(number_of_topics: int) -> dict:
+        @task
+        async def setup() -> int:
+            return number_of_topics
+
+        @task
+        async def ask(question: str) -> str:
+            return interrupt(question)
+
+        n = await setup()
+
+        answers = []
+        for i in range(n):
+            q = f"Whats the answer for topic {i + 1}?"
+            answers.append(await ask(q))
+
+        return {"answers": answers}
+
+    config = {"configurable": {"thread_id": "1"}}
+
+    # First invocation - should get first interrupt
+    result = await workflow.ainvoke(2, config=config)
+    assert "__interrupt__" in result
+    assert len(result["__interrupt__"]) == 1
+    assert result["__interrupt__"][0].value == "Whats the answer for topic 1?"
+
+    # Resume with answer for topic 1 - should get second interrupt
+    result = await workflow.ainvoke(Command(resume="answer1"), config=config)
+    assert "__interrupt__" in result, f"Expected interrupt for topic 2, got: {result}"
+    assert len(result["__interrupt__"]) == 1
+    assert result["__interrupt__"][0].value == "Whats the answer for topic 2?"
+
+    # Resume with answer for topic 2 - should get final result
+    result = await workflow.ainvoke(Command(resume="answer2"), config=config)
+    assert result == {"answers": ["answer1", "answer2"]}
+
+
+@NEEDS_CONTEXTVARS
+async def test_multiple_tasks_before_interrupt_resume(
+    async_checkpointer: BaseCheckpointSaver,
+) -> None:
+    """Test that Command(resume=value) works correctly when multiple @tasks
+    run before an interrupt-producing task in an @entrypoint."""
+
+    @entrypoint(checkpointer=async_checkpointer)
+    async def workflow(inputs: dict) -> dict:
+        @task
+        async def step_a(x: int) -> int:
+            return x + 1
+
+        @task
+        async def step_b(x: int) -> int:
+            return x * 2
+
+        @task
+        async def ask(question: str) -> str:
+            return interrupt(question)
+
+        a = await step_a(inputs["x"])
+        b = await step_b(a)
+
+        answer = await ask(f"Result so far is {b}. What next?")
+
+        return {"computed": b, "answer": answer}
+
+    config = {"configurable": {"thread_id": "1"}}
+
+    # First invocation - should get interrupt
+    result = await workflow.ainvoke({"x": 5}, config=config)
+    assert "__interrupt__" in result
+    assert result["__interrupt__"][0].value == "Result so far is 12. What next?"
+
+    # Resume
+    result = await workflow.ainvoke(Command(resume="continue"), config=config)
+    assert result == {"computed": 12, "answer": "continue"}
+
+
+@NEEDS_CONTEXTVARS
+async def test_no_redundant_put_writes_for_cached_task(
+    async_checkpointer: BaseCheckpointSaver,
+) -> None:
+    """Cached @tasks on resume must not trigger redundant put_writes."""
+    from unittest.mock import patch
+
+    from langgraph.pregel._loop import PregelLoop
+
+    @task
+    async def setup(x: int) -> int:
+        return x
+
+    @task
+    async def ask(question: str) -> str:
+        return interrupt(question)
+
+    @entrypoint(checkpointer=async_checkpointer)
+    async def workflow(x: int) -> dict:
+        n = await setup(x)
+        answer = await ask(f"q{n}")
+        return {"answer": answer}
+
+    config = {"configurable": {"thread_id": "1"}}
+    result = await workflow.ainvoke(1, config=config)
+    assert "__interrupt__" in result
+
+    put_writes_task_ids: list[str] = []
+    orig = PregelLoop.put_writes
+
+    def spy(self, task_id, writes):
+        put_writes_task_ids.append(task_id)
+        return orig(self, task_id, writes)
+
+    with patch.object(PregelLoop, "put_writes", spy):
+        result = await workflow.ainvoke(Command(resume="ans"), config=config)
+
+    assert result == {"answer": "ans"}
+    # Count unique non-null task IDs that got put_writes.
+    # Should be exactly 2: the ask task and the entrypoint task.
+    # If 3, the cached setup task is being redundantly re-committed.
+    non_null = set(tid for tid in put_writes_task_ids if not tid.startswith("00000000"))
+    assert len(non_null) == 2, (
+        f"Expected 2 task IDs in put_writes (ask + entrypoint), got {len(non_null)}"
+    )
+
+
+@NEEDS_CONTEXTVARS
+async def test_node_before_interrupt_resume_graph_api(
+    async_checkpointer: BaseCheckpointSaver,
+) -> None:
+    """Test that Command(resume=value) works correctly in a StateGraph when a
+    node runs before a node that calls interrupt(). This is the graph-API
+    analog of test_task_before_interrupt_resume (entrypoint API)."""
+
+    class State(TypedDict):
+        topics: list[str]
+        answers: Annotated[list[str], operator.add]
+
+    def setup(state: State) -> dict:
+        return {"topics": [f"topic {i + 1}" for i in range(len(state["topics"]))]}
+
+    def ask(state: State) -> dict:
+        answers = []
+        for topic in state["topics"]:
+            answer = interrupt(f"Whats the answer for {topic}?")
+            answers.append(answer)
+        return {"answers": answers}
+
+    graph = (
+        StateGraph(State)
+        .add_node("setup", setup)
+        .add_node("ask", ask)
+        .add_edge(START, "setup")
+        .add_edge("setup", "ask")
+        .add_edge("ask", END)
+        .compile(checkpointer=async_checkpointer)
+    )
+
+    config = {"configurable": {"thread_id": "1"}}
+
+    # First invocation - setup runs, then ask interrupts on the first topic
+    result = await graph.ainvoke({"topics": ["a", "b"], "answers": []}, config=config)
+    assert "__interrupt__" in result
+    assert len(result["__interrupt__"]) == 1
+    assert result["__interrupt__"][0].value == "Whats the answer for topic 1?"
+
+    # Resume with answer for topic 1 - should get second interrupt
+    result = await graph.ainvoke(Command(resume="answer1"), config=config)
+    assert "__interrupt__" in result, f"Expected interrupt for topic 2, got: {result}"
+    assert len(result["__interrupt__"]) == 1
+    assert result["__interrupt__"][0].value == "Whats the answer for topic 2?"
+
+    # Resume with answer for topic 2 - should complete
+    result = await graph.ainvoke(Command(resume="answer2"), config=config)
+    assert result == {
+        "topics": ["topic 1", "topic 2"],
+        "answers": ["answer1", "answer2"],
+    }
+
+
+@NEEDS_CONTEXTVARS
+async def test_multiple_nodes_before_interrupt_resume_graph_api(
+    async_checkpointer: BaseCheckpointSaver,
+) -> None:
+    """Test that Command(resume=value) works correctly in a StateGraph when
+    multiple nodes run before a node that calls interrupt(). This is the
+    graph-API analog of test_multiple_tasks_before_interrupt_resume."""
+
+    class State(TypedDict):
+        value: int
+        answer: str
+
+    def step_a(state: State) -> dict:
+        return {"value": state["value"] + 1}
+
+    def step_b(state: State) -> dict:
+        return {"value": state["value"] * 2}
+
+    def ask(state: State) -> dict:
+        answer = interrupt(f"Result so far is {state['value']}. What next?")
+        return {"answer": answer}
+
+    graph = (
+        StateGraph(State)
+        .add_node("step_a", step_a)
+        .add_node("step_b", step_b)
+        .add_node("ask", ask)
+        .add_edge(START, "step_a")
+        .add_edge("step_a", "step_b")
+        .add_edge("step_b", "ask")
+        .add_edge("ask", END)
+        .compile(checkpointer=async_checkpointer)
+    )
+
+    config = {"configurable": {"thread_id": "1"}}
+
+    # First invocation - step_a and step_b run, then ask interrupts
+    result = await graph.ainvoke({"value": 5, "answer": ""}, config=config)
+    assert "__interrupt__" in result
+    assert result["__interrupt__"][0].value == "Result so far is 12. What next?"
+
+    # Resume - should complete
+    result = await graph.ainvoke(Command(resume="continue"), config=config)
+    assert result == {"value": 12, "answer": "continue"}
+
+
+@NEEDS_CONTEXTVARS
+async def test_node_before_multiple_interrupt_cycles_graph_api(
+    async_checkpointer: BaseCheckpointSaver,
+) -> None:
+    """Test that a node running before an interrupt node does not interfere
+    with multiple interrupt/resume cycles in a StateGraph."""
+
+    class State(TypedDict):
+        count: int
+        data: str
+
+    def prepare(state: State) -> dict:
+        return {"count": state["count"] + 10}
+
+    def multi_interrupt(state: State) -> dict:
+        first = interrupt("First question?")
+        second = interrupt("Second question?")
+        return {"data": f"{first},{second}"}
+
+    graph = (
+        StateGraph(State)
+        .add_node("prepare", prepare)
+        .add_node("multi_interrupt", multi_interrupt)
+        .add_edge(START, "prepare")
+        .add_edge("prepare", "multi_interrupt")
+        .add_edge("multi_interrupt", END)
+        .compile(checkpointer=async_checkpointer)
+    )
+
+    config = {"configurable": {"thread_id": "1"}}
+
+    # First invocation - prepare runs, multi_interrupt hits first interrupt
+    result = await graph.ainvoke({"count": 0, "data": ""}, config=config)
+    assert "__interrupt__" in result
+    assert result["__interrupt__"][0].value == "First question?"
+
+    # Resume first interrupt - hits second interrupt
+    result = await graph.ainvoke(Command(resume="first_answer"), config=config)
+    assert "__interrupt__" in result
+    assert result["__interrupt__"][0].value == "Second question?"
+
+    # Resume second interrupt - completes
+    result = await graph.ainvoke(Command(resume="second_answer"), config=config)
+    assert result == {"count": 10, "data": "first_answer,second_answer"}
+
+
 async def test_pregel_loop_refcount():
    gc.collect()
    try:
@@ -1367,7 +1367,7 @@ wheels = [

 [[package]]
 name = "langgraph"
-version = "1.0.8"
+version = "1.0.9"
 source = { editable = "." }
 dependencies = [
    { name = "langchain-core" },
@@ -1735,7 +1735,7 @@ test = [

 [[package]]
 name = "langgraph-prebuilt"
-version = "1.0.7"
+version = "1.0.8"
 source = { editable = "../prebuilt" }
 dependencies = [
    { name = "langchain-core" },
@@ -922,7 +922,7 @@ class ToolNode(RunnableCallable):
            raise TypeError(msg)

        # Inject state, store, and runtime right before invocation
-        injected_call = self._inject_tool_args(call, request.runtime)
+        injected_call = self._inject_tool_args(call, request.runtime, tool)
        call_args = {**injected_call, "type": "tool_call"}

        try:
@@ -1075,7 +1075,7 @@ class ToolNode(RunnableCallable):
            raise TypeError(msg)

        # Inject state, store, and runtime right before invocation
-        injected_call = self._inject_tool_args(call, request.runtime)
+        injected_call = self._inject_tool_args(call, request.runtime, tool)
        call_args = {**injected_call, "type": "tool_call"}

        try:
@@ -1281,6 +1281,7 @@ class ToolNode(RunnableCallable):
        self,
        tool_call: ToolCall,
        tool_runtime: ToolRuntime,
+        tool: BaseTool | None = None,
    ) -> ToolCall:
        """Inject graph state, store, and runtime into tool call arguments.

@@ -1299,6 +1300,9 @@ class ToolNode(RunnableCallable):
                Must contain 'name', 'args', 'id', and 'type' fields.
            tool_runtime: The ToolRuntime instance containing all runtime context
                (state, config, store, context, stream_writer) to inject into tools.
+            tool: Optional tool instance. When provided, allows injection for
+                dynamically registered tools that are not in self.tools_by_name
+                (e.g., tools added via middleware's wrap_tool_call).

        Returns:
            A new ToolCall dictionary with the same structure as the input but with
@@ -1312,10 +1316,12 @@ class ToolNode(RunnableCallable):
            This method is called automatically during tool execution. It should not
            be called from outside the `ToolNode`.
        """
-        if tool_call["name"] not in self.tools_by_name:
-            return tool_call
-
        injected = self._injected_args.get(tool_call["name"])
+        if not injected and tool is not None:
+            # For dynamically registered tools (e.g., added via middleware's
+            # wrap_tool_call), compute injected args on-the-fly since they
+            # were not present during ToolNode initialization.
+            injected = _get_all_injected_args(tool)
        if not injected:
            return tool_call

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

 [project]
 name = "langgraph-prebuilt"
-version = "1.0.7"
+version = "1.0.8"
 description = "Library with high-level APIs for creating and executing LangGraph agents and tools."
 authors = []
 requires-python = ">=3.10"
@@ -1902,3 +1902,109 @@ async def test_tool_node_tool_runtime_generic() -> None:
    assert tool_message.type == "tool"
    assert tool_message.content == "test_info"
    assert tool_message.tool_call_id == "call_1"
+
+
+def test_tool_node_inject_runtime_dynamic_tool_via_wrap_tool_call() -> None:
+    """Test that ToolRuntime is injected for dynamically registered tools.
+
+    Regression test for https://github.com/langchain-ai/langchain/issues/35305.
+    When a tool is dynamically provided via wrap_tool_call (not registered at
+    ToolNode init time), ToolRuntime should still be injected into the tool.
+    """
+
+    @dec_tool
+    def static_tool(x: int) -> str:
+        """A static tool registered at init."""
+        return f"static: {x}"
+
+    @dec_tool
+    def dynamic_tool_with_runtime(x: int, runtime: ToolRuntime) -> str:
+        """A dynamic tool that needs ToolRuntime injection."""
+        return f"dynamic: x={x}, tool_call_id={runtime.tool_call_id}"
+
+    def wrap_tool_call(request, execute):
+        """Middleware that swaps in a dynamic tool."""
+        if request.tool_call["name"] == "dynamic_tool_with_runtime":
+            # Override tool to the dynamic one (not registered at init)
+            new_request = request.override(tool=dynamic_tool_with_runtime)
+            return execute(new_request)
+        return execute(request)
+
+    # ToolNode only knows about static_tool at init time
+    tool_node = ToolNode(
+        [static_tool],
+        wrap_tool_call=wrap_tool_call,
+    )
+
+    # Verify the dynamic tool is NOT in the tool node's registered tools
+    assert "dynamic_tool_with_runtime" not in tool_node.tools_by_name
+
+    # Call the dynamic tool
+    tool_call = {
+        "name": "dynamic_tool_with_runtime",
+        "args": {"x": 42},
+        "id": "call_dynamic_1",
+        "type": "tool_call",
+    }
+    msg = AIMessage("", tool_calls=[tool_call])
+    result = tool_node.invoke(
+        {"messages": [msg]},
+        config=_create_config_with_runtime(),
+    )
+
+    # ToolRuntime should be injected and the tool should execute successfully
+    tool_message = result["messages"][-1]
+    assert tool_message.content == "dynamic: x=42, tool_call_id=call_dynamic_1"
+    assert tool_message.tool_call_id == "call_dynamic_1"
+
+
+async def test_tool_node_inject_runtime_dynamic_tool_via_wrap_tool_call_async() -> None:
+    """Test that ToolRuntime is injected for dynamically registered tools (async).
+
+    Async version of the regression test for
+    https://github.com/langchain-ai/langchain/issues/35305.
+    """
+
+    @dec_tool
+    def static_tool(x: int) -> str:
+        """A static tool registered at init."""
+        return f"static: {x}"
+
+    @dec_tool
+    async def dynamic_tool_with_runtime(x: int, runtime: ToolRuntime) -> str:
+        """A dynamic async tool that needs ToolRuntime injection."""
+        return f"dynamic: x={x}, tool_call_id={runtime.tool_call_id}"
+
+    async def awrap_tool_call(request, execute):
+        """Async middleware that swaps in a dynamic tool."""
+        if request.tool_call["name"] == "dynamic_tool_with_runtime":
+            new_request = request.override(tool=dynamic_tool_with_runtime)
+            return await execute(new_request)
+        return await execute(request)
+
+    # ToolNode only knows about static_tool at init time
+    tool_node = ToolNode(
+        [static_tool],
+        awrap_tool_call=awrap_tool_call,
+    )
+
+    # Verify the dynamic tool is NOT in the tool node's registered tools
+    assert "dynamic_tool_with_runtime" not in tool_node.tools_by_name
+
+    # Call the dynamic tool
+    tool_call = {
+        "name": "dynamic_tool_with_runtime",
+        "args": {"x": 42},
+        "id": "call_dynamic_2",
+        "type": "tool_call",
+    }
+    msg = AIMessage("", tool_calls=[tool_call])
+    result = await tool_node.ainvoke(
+        {"messages": [msg]},
+        config=_create_config_with_runtime(),
+    )
+
+    # ToolRuntime should be injected and the tool should execute successfully
+    tool_message = result["messages"][-1]
+    assert tool_message.content == "dynamic: x=42, tool_call_id=call_dynamic_2"
+    assert tool_message.tool_call_id == "call_dynamic_2"
@@ -268,7 +268,7 @@ wheels = [

 [[package]]
 name = "langgraph"
-version = "1.0.8"
+version = "1.0.9"
 source = { editable = "../langgraph" }
 dependencies = [
    { name = "langchain-core" },
@@ -489,7 +489,7 @@ test = [

 [[package]]
 name = "langgraph-prebuilt"
-version = "1.0.7"
+version = "1.0.8"
 source = { editable = "." }
 dependencies = [
    { name = "langchain-core" },
@@ -72,8 +72,13 @@ class Auth:
            assert params.get("metadata", {}).get("owner") == "allowed_user"

        @auth.on.store
-        async def authorize_store(ctx: Auth.types.AuthContext, value: Auth.types.on):
-            assert ctx.user.identity in value["namespace"], "Not authorized"
+        async def authorize_store(ctx: Auth.types.AuthContext, value: Auth.types.on.store.value):
+            # Automatically scope all store operations to the user's namespace.
+            namespace = tuple(value["namespace"]) if value.get("namespace") else ()
+            assert isinstance(namespace, tuple)
+            if not namespace or namespace[0] != ctx.user.identity:
+                namespace = (ctx.user.identity, *namespace)
+            value["namespace"] = namespace
        ```

    ???+ note "Request Processing Flow"
@@ -170,13 +175,32 @@ class Auth:
            ```

            Auth for the `store` resource is a bit different since its structure is developer defined.
-            You typically want to enforce user creds in the namespace.
+            You typically want to scope store operations by rewriting the namespace to include the user's identity.
+            The `value` dict is mutable — changes to `value["namespace"]` are used by the server for the actual operation.

            ```python
            @auth.on.store
-            async def check_store_access(ctx: AuthContext, value: Auth.types.on) -> bool:
-                # Assuming you structure your store like (store.aput((user_id, application_context), key, value))
-                assert value["namespace"][0] == ctx.user.identity
+            async def authorize_store(ctx: AuthContext, value: Auth.types.on.store.value):
+                # Automatically scope all store operations to the user's namespace.
+                namespace = tuple(value["namespace"]) if value.get("namespace") else ()
+                assert isinstance(namespace, tuple)
+                if not namespace or namespace[0] != ctx.user.identity:
+                    namespace = (ctx.user.identity, *namespace)
+                value["namespace"] = namespace
+            ```
+
+            You can also register handlers for specific store actions:
+
+            ```python
+            @auth.on.store.put
+            async def on_put(ctx: AuthContext, value: Auth.types.on.store.put.value):
+                # value has typed fields: namespace, key, value, index
+                ...
+
+            @auth.on.store.get
+            async def on_get(ctx: AuthContext, value: Auth.types.on.store.get.value):
+                # value has typed fields: namespace, key
+                ...
            ```
        """
        # These are accessed by the API. Changes to their names or types is
@@ -483,9 +507,85 @@ class _CronsOn(
    Search = types.CronsSearch


+class _StoreActionOn(typing.Generic[T]):
+    """Decorator for registering a handler for a specific store action."""
+
+    def __init__(
+        self,
+        auth: Auth,
+        action: typing.Literal["put", "get", "search", "delete", "list_namespaces"],
+        value: type[T],
+    ) -> None:
+        self.auth = auth
+        self.action = action
+        self.value = value
+
+    def __call__(self, fn: _ActionHandler[T]) -> _ActionHandler[T]:
+        _validate_handler(fn)
+        _register_handler(self.auth, "store", self.action, fn)
+        return fn
+
+
 class _StoreOn:
    def __init__(self, auth: Auth) -> None:
        self._auth = auth
+        self.put = _StoreActionOn(auth, "put", types.StorePut)
+        """Register a handler for store put operations.
+
+        ???+ example "Example"
+            ```python
+            @auth.on.store.put
+            async def on_store_put(ctx: Auth.types.AuthContext, value: Auth.types.on.store.put.value):
+                # Scope puts to user's namespace
+                ...
+            ```
+        """
+        self.get = _StoreActionOn(auth, "get", types.StoreGet)
+        """Register a handler for store get operations.
+
+        ???+ example "Example"
+            ```python
+            @auth.on.store.get
+            async def on_store_get(ctx: Auth.types.AuthContext, value: Auth.types.on.store.get.value):
+                # Scope gets to user's namespace
+                ...
+            ```
+        """
+        self.search = _StoreActionOn(auth, "search", types.StoreSearch)
+        """Register a handler for store search operations.
+
+        ???+ example "Example"
+            ```python
+            @auth.on.store.search
+            async def on_store_search(ctx: Auth.types.AuthContext, value: Auth.types.on.store.search.value):
+                # Scope searches to user's namespace
+                ...
+            ```
+        """
+        self.delete = _StoreActionOn(auth, "delete", types.StoreDelete)
+        """Register a handler for store delete operations.
+
+        ???+ example "Example"
+            ```python
+            @auth.on.store.delete
+            async def on_store_delete(ctx: Auth.types.AuthContext, value: Auth.types.on.store.delete.value):
+                # Scope deletes to user's namespace
+                ...
+            ```
+        """
+        self.list_namespaces = _StoreActionOn(
+            auth, "list_namespaces", types.StoreListNamespaces
+        )
+        """Register a handler for store list_namespaces operations.
+
+        ???+ example "Example"
+            ```python
+            @auth.on.store.list_namespaces
+            async def on_list_ns(ctx: Auth.types.AuthContext, value: Auth.types.on.store.list_namespaces.value):
+                # Scope namespace listing to user's prefix
+                ...
+            ```
+        """

    @typing.overload
    def __call__(
@@ -402,7 +402,7 @@ class AuthContext(BaseAuthContext):
        "list_namespaces",
    ]
    """The action being performed on the resource.
-    
+
    Most resources support the following actions:
    - create: Create a new resource
    - read: Read information about a resource
@@ -411,8 +411,10 @@ class AuthContext(BaseAuthContext):
    - search: Search for resources

    The store supports the following actions:
-    - put: Add or update a document in the store
-    - get: Get a document from the store
+    - put: Add or update an item in the store
+    - get: Get an item from the store
+    - search: Search for items within a namespace prefix
+    - delete: Delete an item from the store
    - list_namespaces: List the namespaces in the store
    """

@@ -851,20 +853,34 @@ class CronsSearch(typing.TypedDict, total=False):


 class StoreGet(typing.TypedDict):
-    """Operation to retrieve a specific item by its namespace and key."""
+    """Operation to retrieve a specific item by its namespace and key.
+
+    This dict is mutable — auth handlers can modify `namespace` to enforce
+    access scoping (e.g., prepending the user's identity).
+    """

    namespace: tuple[str, ...]
-    """Hierarchical path that uniquely identifies the item's location."""
+    """Hierarchical path that uniquely identifies the item's location.
+
+    Auth handlers can modify this to enforce per-user scoping.
+    """

    key: str
    """Unique identifier for the item within its specific namespace."""


 class StoreSearch(typing.TypedDict):
-    """Operation to search for items within a specified namespace hierarchy."""
+    """Operation to search for items within a specified namespace hierarchy.
+
+    This dict is mutable — auth handlers can modify `namespace` to enforce
+    access scoping (e.g., prepending the user's identity).
+    """

    namespace: tuple[str, ...]
-    """Prefix filter for defining the search scope."""
+    """Prefix filter for defining the search scope.
+
+    Auth handlers can modify this to enforce per-user scoping.
+    """

    filter: dict[str, typing.Any] | None
    """Key-value pairs for filtering results based on exact matches or comparison operators."""
@@ -876,14 +892,22 @@ class StoreSearch(typing.TypedDict):
    """Number of matching items to skip for pagination."""

    query: str | None
-    """Naturalj language search query for semantic search capabilities."""
+    """Natural language search query for semantic search capabilities."""


 class StoreListNamespaces(typing.TypedDict):
-    """Operation to list and filter namespaces in the store."""
+    """Operation to list and filter namespaces in the store.
+
+    This dict is mutable — auth handlers can modify `namespace` (the prefix)
+    to enforce access scoping (e.g., prepending the user's identity).
+    """

    namespace: tuple[str, ...] | None
-    """Prefix filter namespaces."""
+    """Prefix filter for namespaces. Can be `None` if no prefix was provided.
+
+    Auth handlers can modify this to enforce per-user scoping. When `None`,
+    handlers should set it to `(user_id,)` to scope listing to the user's namespaces.
+    """

    suffix: tuple[str, ...] | None
    """Optional conditions for filtering namespaces."""
@@ -903,10 +927,17 @@ class StoreListNamespaces(typing.TypedDict):


 class StorePut(typing.TypedDict):
-    """Operation to store, update, or delete an item in the store."""
+    """Operation to store, update, or delete an item in the store.
+
+    This dict is mutable — auth handlers can modify `namespace` to enforce
+    access scoping (e.g., prepending the user's identity).
+    """

    namespace: tuple[str, ...]
-    """Hierarchical path that identifies the location of the item."""
+    """Hierarchical path that identifies the location of the item.
+
+    Auth handlers can modify this to enforce per-user scoping.
+    """

    key: str
    """Unique identifier for the item within its namespace."""
@@ -919,10 +950,17 @@ class StorePut(typing.TypedDict):


 class StoreDelete(typing.TypedDict):
-    """Operation to delete an item from the store."""
+    """Operation to delete an item from the store.
+
+    This dict is mutable — auth handlers can modify `namespace` to enforce
+    access scoping (e.g., prepending the user's identity).
+    """

    namespace: tuple[str, ...]
-    """Hierarchical path that uniquely identifies the item's location."""
+    """Hierarchical path that uniquely identifies the item's location.
+
+    Auth handlers can modify this to enforce per-user scoping.
+    """

    key: str
    """Unique identifier for the item within its specific namespace."""
@@ -265,7 +265,7 @@ wheels = [

 [[package]]
 name = "langgraph"
-version = "1.0.8"
+version = "1.0.9"
 source = { editable = "../langgraph" }
 dependencies = [
    { name = "langchain-core" },
@@ -396,7 +396,7 @@ test = [

 [[package]]
 name = "langgraph-prebuilt"
-version = "1.0.7"
+version = "1.0.8"
 source = { editable = "../prebuilt" }
 dependencies = [
    { name = "langchain-core" },
Author	SHA1	Message	Date
Sydney RunkleandGitHub	73cebea3c2	release: langgraph + prebuilt (#6875 )	2026-02-19 13:12:01 -05:00
Sydney Runkle GitHub Shivangi Sharma	b73b2d19eb	fix: inject ToolRuntime for dynamically registered tools (#6874 ) Fixes https://github.com/langchain-ai/langchain/issues/35305 Co-authored-by: Shivangi Sharma <shivangi.sharma7004@gmail.com>	2026-02-19 17:39:57 +00:00
Sydney Runkle GitHub William FH	ca26805b5f	fix: sequential interrupt handling w/ functional API (#6863 ) In the original proposed fix https://github.com/langchain-ai/langgraph/pull/6863, we were guarding this specific case by only checking for null resume in the scratchpad. But I noticed the tests passed on main for the sync case, indicating an inconsistency between the two paths. Seems like we were making a redundant put_writes call when replaying the async tasks --------- Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com>	2026-02-19 07:24:18 -08:00
William FH GitHub Claude Opus 4.6	5ac837d7cd	feat(sdk-py): improve store auth type safety and docstrings (#6867 ) ## Summary - Add `_StoreActionOn` class with action-specific decorator properties (`.put`, `.get`, `.search`, `.delete`, `.list_namespaces`) to `_StoreOn`, enabling `@auth.on.store.put` etc. which was documented but not implemented - Update docstring examples to show namespace-rewriting pattern as the canonical store auth approach - Fix `AuthContext.action` docstring: add missing `search` and `delete` store actions - Fix typo in `StoreSearch.query` docstring - Add auth-handler-aware docstrings to all store TypedDicts ## Test plan - [x] `make format && make lint` passes in `libs/sdk-py` - [] Verify `@auth.on.store.put` decorator works at runtime Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>	2026-02-19 07:16:26 -08:00
Lauren Hirata SinghandGitHub	c4f5861166	chore(docs): Add new redirects file(s) so we can update/add (#6778 ) Adds redirects for all old LangGraph docs URLs to docs.langchain.com using meta refresh and GitHub Pages	2026-02-18 14:35:38 -05:00