fix signature

snippet had a missing decorator that might lead the user to confuse whether it is really a tool

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -1,6 +1,6 @@
 name: "\U0001F41B Bug Report"
 description: Report a bug in LangGraph. To report a security issue, please instead use the security option below. For questions, please use the GitHub Discussions.
-labels: ["02 Bug Report"]
+labels: [pending,bug]
 body:
   - type: markdown
     attributes:

.github/ISSUE_TEMPLATE/config.yml

@@ -1,4 +1,4 @@
-blank_issues_enabled: false
+blank_issues_enabled: true
 version: 2.1
 contact_links:
   - name: 🤔 Question or Problem

.github/ISSUE_TEMPLATE/documentation.yml

@@ -1,7 +1,7 @@
 name: Documentation
 description: Report an issue related to the LangGraph documentation.
 title: "DOC: <Please write a comprehensive title after the 'DOC: ' prefix>"
-labels: [03 - Documentation]
+labels: [documentation]
 
 body:
 - type: textarea

AGENTS.md

@@ -0,0 +1,55 @@
+# AGENTS Instructions
+
+This repository is a monorepo. Each library lives in a subdirectory under `libs/`.
+
+When you modify code in any library, run the following commands in that library's directory before creating a pull request:
+
+- `make format` – run code formatters
+- `make lint` – run the linter
+- `make test` – execute the test suite
+
+To run a particular test file or to pass additional pytest options you can specify the `TEST` variable:
+
+```
+TEST=path/to/test.py make test
+```
+
+Other pytest arguments can also be supplied inside the `TEST` variable.
+
+## Libraries
+
+The repository contains several Python and JavaScript/TypeScript libraries.
+Below is a high-level overview:
+
+- **checkpoint** – base interfaces for LangGraph checkpointers.
+- **checkpoint-postgres** – Postgres implementation of the checkpoint saver.
+- **checkpoint-sqlite** – SQLite implementation of the checkpoint saver.
+- **cli** – official command-line interface for LangGraph.
+- **langgraph** – core framework for building stateful, multi-actor agents.
+- **prebuilt** – high-level APIs for creating and running agents and tools.
+- **sdk-js** – JS/TS SDK for interacting with the LangGraph REST API.
+- **sdk-py** – Python SDK for the LangGraph Platform API.
+
+### Dependency map
+
+The diagram below lists downstream libraries for each production dependency as
+declared in that library's `pyproject.toml` (or `package.json`).
+
+```text
+checkpoint
+├── checkpoint-postgres
+├── checkpoint-sqlite
+├── prebuilt
+└── langgraph
+
+prebuilt
+└── langgraph
+
+sdk-py
+├── langgraph
+└── cli
+
+sdk-js (standalone)
+```
+
+Changes to a library may impact all of its dependents shown above.

Makefile

@@ -0,0 +1,58 @@
+# Define the directories containing projects
+LIBS_DIRS := $(wildcard libs/*)
+
+# Default target
+.PHONY: all
+all: lint format lock test
+
+# Install dependencies for all projects
+.PHONY: install
+install:
+	@echo "Creating virtual environment..."
+	@uv venv
+	@for dir in $(LIBS_DIRS); do \
+		if [ -f $$dir/pyproject.toml ]; then \
+			echo "Installing dependencies for $$dir"; \
+			uv pip install -e $$dir; \
+		fi; \
+	done
+
+# Lint all projects
+.PHONY: lint
+lint:
+	@for dir in $(LIBS_DIRS); do \
+		if [ -f $$dir/Makefile ]; then \
+			echo "Running lint in $$dir"; \
+			$(MAKE) -C $$dir lint; \
+		fi; \
+	done
+
+# Format all projects
+.PHONY: format
+format:
+	@for dir in $(LIBS_DIRS); do \
+		if [ -f $$dir/Makefile ]; then \
+			echo "Running format in $$dir"; \
+			$(MAKE) -C $$dir format; \
+		fi; \
+	done
+
+# Lock all projects
+.PHONY: lock
+lock:
+	@for dir in $(LIBS_DIRS); do \
+		if [ -f $$dir/Makefile ]; then \
+			echo "Running lock in $$dir"; \
+			(cd $$dir && uv lock); \
+		fi; \
+	done
+
+# Test all projects
+.PHONY: test
+test:
+	@for dir in $(LIBS_DIRS); do \
+		if [ -f $$dir/Makefile ]; then \
+			echo "Running test in $$dir"; \
+			$(MAKE) -C $$dir test; \
+		fi; \
+	done

README.md

@@ -12,7 +12,6 @@
 [![Downloads](https://static.pepy.tech/badge/langgraph/month)](https://pepy.tech/project/langgraph)
 [![Open Issues](https://img.shields.io/github/issues-raw/langchain-ai/langgraph)](https://github.com/langchain-ai/langgraph/issues)
 [![Docs](https://img.shields.io/badge/docs-latest-blue)](https://langchain-ai.github.io/langgraph/)
-[![GitMCP](https://img.shields.io/endpoint?url=https://gitmcp.io/badge/langchain-ai/langgraph)](https://gitmcp.io/langchain-ai/langgraph)
 
 Trusted by companies shaping the future of agents – including Klarna, Replit, Elastic, and more – LangGraph is a low-level orchestration framework for building, managing, and deploying long-running, stateful agents.
 

docs/_scripts/add_translation.py

@@ -1,157 +1,154 @@
-"""Add typescript translation to a given markdown file."""
+"""Translate Python markdown to TypeScript and/or consolidate Python-JS markdown into a single document."""
 
 import argparse
-import re
 
 import requests
 from langchain_anthropic import ChatAnthropic
 
+# Load reference TypeScript snippets
 URL = "https://gist.githubusercontent.com/eyurtsev/e7486731415463a9bc5b4682358859c8/raw/b5a5fda9c7e3387cfcb781f25082814d43675d50/gistfile1.txt"
 response = requests.get(URL)
 response.raise_for_status()
 reference_snippets = response.text
 
-model = ChatAnthropic(model="claude-3-5-sonnet-latest")
+# Initialize model
+model = ChatAnthropic(model="claude-sonnet-4-0", max_tokens=64_000)
+
+TRANSLATION_PROMPT = (
+    "You are a helpful assistant that translates Python-based technical "
+    "documentation written in Markdown to equivalent TypeScript-based documentation. "
+    "The input is a Markdown file written in mkdocs format. It contains "
+    "Python code snippets embedded in prose. "
+    "Your task is to rewrite the content by translating the Python code to "
+    "idiomatic TypeScript, using the provided TypeScript reference snippets "
+    "to ensure accurate and consistent usage (e.g., correct imports, function "
+    "names, and patterns). "
+    "Remove the original Python code and replace it with the corresponding "
+    "TypeScript version. "
+    "Do not alter the surrounding prose unless a change is necessary to "
+    "reflect differences between Python and TypeScript. "
+    "Preserve the structure and formatting of the original Markdown document. "
+    "Do not make stylistic or structural changes unless they directly support "
+    "the translation. "
+    "Use the reference TypeScript snippets as guidance whenever possible to "
+    "maintain alignment with existing conventions.\n\n"
+    f"Here are the reference TypeScript snippets:\n\n{reference_snippets}\n\n"
+)
+
+CONSOLIDATION_PROMPT = (
+    "You are a helpful assistant that consolidates parallel Python and JavaScript (TypeScript) technical documentation "
+    "written in Markdown into a single unified Markdown document. "
+    "The input consists of two documents: the first is for Python users, and the second is for JavaScript/TypeScript users. "
+    "Your task is to merge these into one Markdown file using language-specific fenced blocks to separate the content where needed. "
+    "Use the following syntax to distinguish content for each language:\n\n"
+    ":::python\n"
+    "# Python-specific content\n"
+    ":::\n\n"
+    ":::js\n"
+    "# JavaScript/TypeScript-specific content\n"
+    ":::\n\n"
+    "Follow these consolidation rules:\n"
+    "- When content (prose or code) is the same or nearly identical in both versions, include it only once—outside of any fenced block.\n"
+    "- When content differs between the Python and JS versions, wrap each version in its corresponding fenced block.\n"
+    "- Prefer **paragraph-level separation** of language-specific content. Do not combine Python and JS snippets or terminology in the same sentence or paragraph using conditional phrases.\n"
+    "  For example, avoid inline constructs like:\n"
+    "  `The :::python add_messages ::: :::js reducer ::: function...`\n"
+    "  Instead, write two distinct paragraphs:\n\n"
+    "  :::python\n"
+    "  The `add_messages` function in our `State` will append the LLM's response messages to whatever messages are already in the state.\n"
+    "  ::: \n\n"
+    "  :::js\n"
+    "  The `reducer` function in our `StateAnnotation` will append the LLM's response messages to whatever messages are already in the state.\n"
+    "  :::\n\n"
+    "- Preserve the overall structure, ordering, and formatting of the original Markdown documents.\n"
+    "- Do not rephrase or unify content unless it is logically and semantically identical.\n"
+    "- Use the fenced blocks for both prose and code as needed, and ensure output is clean, readable Markdown suitable for tools that parse these directives.\n"
+    "Your goal is to produce a cleanly merged documentation file that serves both Python and JavaScript users without redundancy, while maximizing clarity and separation of language-specific details."
+)
 
 
-def _get_tqdm():
-    try:
-        from tqdm import tqdm
-    except ImportError:
-        # If not available return a simple identity function
-        def tqdm(iterable, *args, **kwargs):
-            return iterable
-
-    return tqdm
-
-
-_tqdm = _get_tqdm()
-
-opening_pattern = re.compile(r"^\s*```python(?:\s+.*)?\s*$")
-closing_pattern = re.compile(r"^\s*```\s*$")
-
-
-def extract_python_snippets(markdown: str) -> list[str]:
-    """
-    Extract all python code blocks (including their fence lines) from the markdown content.
-    A python block is defined as any block that starts with a line containing an opening fence
-    with '```python' (optionally with extra parameters) and ends with a closing fence '```'.
-    """
-    snippets = []
-    inside_block = False
-    current_snippet = []
-
-    for line in markdown.splitlines(keepends=True):
-        if not inside_block:
-            if opening_pattern.match(line):
-                inside_block = True
-                current_snippet = [line]
-        else:
-            current_snippet.append(line)
-            if closing_pattern.match(line):
-                inside_block = False
-                snippets.append("".join(current_snippet))
-                current_snippet = []
-    return snippets
-
-
-def translate_snippet(python_snippet: str) -> str:
-    """Translate a python code block into a TypeScript code block using Langchain.
-    The response is expected to be a properly fenced TypeScript code block (i.e.
-    starting with ```typescript and ending with ```).
-    """
-    ai_message = model.invoke(
+def translate_python_to_ts(markdown_content: str) -> str:
+    response = model.invoke(
         [
             {
                 "role": "system",
-                "content": (
-                    f"You have access to the following up-to-date example TypeScript code "
-                    f"snippets that show examples of building with langgraph "
-                    f"and langchain:\n\n{reference_snippets}\n\n"
-                    "Use this context to translate the following Python code to equivalent "
-                    "TypeScript. Ensure that your output is a valid fenced TypeScript "
-                    "code block (i.e. starts with ```typescript and ends with ```)."
-                ),
-            },
-            {
-                "role": "user",
-                "content": f"Translate this Python snippet to TypeScript:\n\n{python_snippet}",
+                "content": TRANSLATION_PROMPT,
+                "cache_control": {"type": "ephemeral"},
             },
+            {"role": "user", "content": markdown_content},
         ]
     )
-
-    # Use a regular expression to search for a TypeScript code block in the response.
-    pattern = r"```typescript\s*(.*?)\s*```"
-    match = re.search(pattern, ai_message.content, re.DOTALL)
-    if match:
-        # Reconstruct the code block with proper fences.
-        typescript_code = match.group(1).strip()
-        return f"```typescript\n{typescript_code}\n```"
-    else:
-        raise ValueError("No TypeScript code block found in the model's response.")
+    return response.content
 
 
-def insert_translations_into_markdown(
-    markdown: str, typescript_snippets: list[str]
-) -> str:
-    """Walks through the original markdown content and, after each
-    Python snippet block, inserts the corresponding translated TypeScript snippet.
-    It assumes that the ordering of the Python snippets
-    (from extract_python_snippets) matches the order they appear in the markdown.
-    """
-    output_lines = []
-    lines = markdown.splitlines(keepends=True)
-    inside_block = False
-    snippet_index = 0
-
-    for line in lines:
-        output_lines.append(line)
-        if not inside_block and opening_pattern.match(line):
-            # We've encountered the start of a python code block.
-            inside_block = True
-        elif inside_block:
-            if closing_pattern.match(line):
-                # End of a python snippet block.
-                inside_block = False
-                if snippet_index < len(typescript_snippets):
-                    # Insert an extra newline for clarity, then the translated TypeScript snippet.
-                    output_lines.append("\n")
-                    output_lines.append(typescript_snippets[snippet_index])
-                    output_lines.append("\n")
-                    snippet_index += 1
-    return "".join(output_lines)
+def consolidate_python_and_ts(combined_content: str) -> str:
+    response = model.invoke(
+        [
+            {
+                "role": "system",
+                "content": CONSOLIDATION_PROMPT,
+                "cache_control": {"type": "ephemeral"},
+            },
+            {"role": "user", "content": combined_content},
+        ]
+    )
+    return response.content
 
 
-def main(file_path: str) -> None:
-    # Read the markdown file.
-    with open(file_path, "r") as f:
+def main(file_path: str, translate_only: bool, consolidate_only: bool) -> None:
+    with open(file_path, "r", encoding="utf-8") as f:
         markdown_content = f.read()
 
-    # 1. Extract all Python snippets.
-    python_snippets = extract_python_snippets(markdown_content)[:1]
+    if translate_only:
+        translated = translate_python_to_ts(markdown_content)
+        output_path = file_path.replace(".md", ".translated.md")
+        with open(output_path, "w", encoding="utf-8") as f:
+            f.write(translated)
+        print(f"Translated JS/TS version written to: {output_path}")
 
-    # 2. Translate each Python snippet to TypeScript.
-    typescript_snippets = []
-    # Replace with .batch() for faster translation
-    for python_snippet in _tqdm(python_snippets):
-        ts_snippet = translate_snippet(python_snippet)
-        typescript_snippets.append(ts_snippet)
+    elif consolidate_only:
+        consolidated = consolidate_python_and_ts(markdown_content)
+        with open(file_path, "w", encoding="utf-8") as f:
+            f.write(consolidated)
+        print(f"Consolidated content written to: {file_path}")
 
-    # 3. Insert the TypeScript translations after their respective Python snippets.
-    updated_markdown = insert_translations_into_markdown(
-        markdown_content, typescript_snippets
-    )
-
-    # Overwrite the original markdown file with the updated content.
-    with open(file_path, "w") as f:
-        f.write(updated_markdown)
+    else:
+        # Default behavior: translate first, then consolidate both
+        translated = translate_python_to_ts(markdown_content)
+        combined = f"{markdown_content.strip()}\n\n\n{translated.strip()}"
+        consolidated = consolidate_python_and_ts(combined)
+        with open(file_path, "w", encoding="utf-8") as f:
+            f.write(consolidated)
+        print(f"Translated and consolidated content written to: {file_path}")
 
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(
-        description="Translate Python snippets in a markdown file to TypeScript and insert them after each Python snippet."
+        description=(
+            "Translate Python markdown to TypeScript and/or consolidate "
+            "Python-JS markdown into one file."
+        )
     )
     parser.add_argument("file_path", type=str, help="Path to the markdown file.")
+    parser.add_argument(
+        "--translate-only",
+        action="store_true",
+        help="Only generate the JS translation.",
+    )
+    parser.add_argument(
+        "--consolidate-only",
+        action="store_true",
+        help="Only consolidate pre-paired Python and JS content.",
+    )
     args = parser.parse_args()
 
-    main(args.file_path)
+    if args.translate_only and args.consolidate_only:
+        raise ValueError(
+            "Cannot use both --translate-only and --consolidate-only at the same time."
+        )
+
+    main(
+        args.file_path,
+        translate_only=args.translate_only,
+        consolidate_only=args.consolidate_only,
+    )

docs/_scripts/generate_llms_text.py

@@ -3,19 +3,21 @@
 import asyncio
 import glob
 import os
-from typing import TypedDict, List, Optional
-import pydantic
 import re
-from pydantic import BaseModel, Field
-from langchain_core.rate_limiters import InMemoryRateLimiter
+from typing import TypedDict, List, Optional
 
 import yaml
 from langchain.chat_models import init_chat_model
+from langchain_core.rate_limiters import InMemoryRateLimiter
 from mkdocs.structure.files import File
 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
+from _scripts.notebook_hooks import (
+    _on_page_markdown_with_config,
+    _apply_conditional_rendering,
+)
 
 HERE = os.path.dirname(os.path.abspath(__file__))
 # Get source directory (parent of HERE / docs)
@@ -211,7 +213,9 @@ async def process_nav_items(nav_items: list[NavItem]) -> list[NavItem]:
     # Remove any items that start with http:// or https:// looking only for
     # local file at this stages.
     nav_items = [
-        item for item in nav_items if not item["url"].startswith(("http://", "https://"))
+        item
+        for item in nav_items
+        if not item["url"].startswith(("http://", "https://"))
     ]
     # Process items in parallel
     tasks = [process_single_item(item) for item in nav_items]

docs/_scripts/link_map.py

@@ -0,0 +1,5 @@
+JS_LINK_MAP = {
+    "langgraph.types.interrupt": "https://langchain-ai.github.io/langgraphjs/reference/functions/langgraph.interrupt-2.html",
+    "create_react_agent": "https://langchain-ai.github.io/langgraphjs/reference/functions/langgraph_prebuilt.createReactAgent.html",
+    "langgraph.types.Command": "https://langchain-ai.github.io/langgraphjs/reference/classes/langgraph.Command.html",
+}

docs/_scripts/notebook_hooks.py

@@ -16,6 +16,7 @@ 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
 
 logger = logging.getLogger(__name__)
 logging.basicConfig()
@@ -86,7 +87,7 @@ REDIRECT_MAP = {
     "cloud/how-tos/stream_events.md": "cloud/how-tos/streaming.md#stream-events",
     "cloud/how-tos/stream_debug.md": "cloud/how-tos/streaming.md#debug",
     "cloud/how-tos/stream_multiple.md": "cloud/how-tos/streaming.md#stream-multiple-modes",
-    # prebuit redirects
+    # prebuilt redirects
     "how-tos/create-react-agent.ipynb": "agents/agents.md#basic-configuration",
     "how-tos/create-react-agent-memory.ipynb": "agents/memory.md",
     "how-tos/create-react-agent-system-prompt.ipynb": "agents/context.md#prompts",
@@ -158,6 +159,62 @@ def _add_path_to_code_blocks(markdown: str, page: Page) -> str:
     return code_block_pattern.sub(replace_code_block_header, markdown)
 
 
+def _resolve_cross_references(md_text: str, link_map: dict[str, str]) -> str:
+    """Replace [title][identifier] with [title](url) using language-specific link_map.
+
+    Args:
+        md_text: The markdown text to process.
+        link_map: mapping of identifier to URL.
+
+    Returns:
+        The processed markdown text with cross-references resolved.
+    """
+    # Pattern to match [title][identifier]
+    pattern = re.compile(r"\[([^\]]+)\]\[([^\]]+)\]")
+
+    def replace_reference(match: re.Match) -> str:
+        """Replace the matched reference with the corresponding URL."""
+        title, identifier = match.group(1), match.group(2)
+        url = link_map.get(identifier)
+
+        if url:
+            return f"[{title}]({url})"
+        else:
+            # Leave it unchanged if not found
+            return match.group(0)
+
+    return pattern.sub(replace_reference, md_text)
+
+
+def _apply_conditional_rendering(md_text: str, target_language: str) -> str:
+    if target_language not in {"python", "js"}:
+        raise ValueError("target_language must be 'python' or 'js'")
+
+    pattern = re.compile(
+        r"(?P<indent>[ \t]*):::(?P<language>\w+)\s*\n"
+        r"(?P<content>((?:.*\n)*?))"  # Capture the content inside the block
+        r"(?P=indent):::"  # Match closing with the same indentation
+    )
+
+    def replace_conditional_blocks(match: re.Match) -> str:
+        """Keep active conditionals."""
+        language = match.group("language")
+        content = match.group("content")
+
+        if language not in {"python", "js"}:
+            # If the language is not supported, return the original block
+            return match.group(0)
+
+        if language == target_language:
+            return content
+
+        # If the language does not match, return an empty string
+        return ""
+
+    processed = pattern.sub(replace_conditional_blocks, md_text)
+    return processed
+
+
 def _highlight_code_blocks(markdown: str) -> str:
     """Find code blocks with highlight comments and add hl_lines attribute.
 
@@ -257,6 +314,20 @@ def _on_page_markdown_with_config(
     # Apply highlight comments to code blocks
     markdown = _highlight_code_blocks(markdown)
 
+    # Apply conditional rendering for code blocks
+    target_language = kwargs.get("target_language", "python")
+    markdown = _apply_conditional_rendering(markdown, target_language)
+    if target_language == "js":
+        markdown = _resolve_cross_references(markdown, JS_LINK_MAP)
+    elif target_language == "python":
+        # Via a dedicated plugin
+        pass
+    else:
+        raise ValueError(
+            f"Unsupported target language: {target_language}. "
+            "Supported languages are 'python' and 'js'."
+        )
+
     # Add file path as an attribute to code blocks that are executable.
     # This file path is used to associate fixtures with the executable code
     # which can be used in CI to test the docs without making network requests.

docs/docs/cloud/deployment/cloud.md

@@ -62,6 +62,15 @@ Starting from the `LangGraph Platform` view...
 1. In the panel, select the `Server` tab to view server logs for the revision. Server logs are only available after a revision has been deployed.
 1. Within the `Server` tab, adjust the date/time range picker as needed. By default, the date/time range picker is set to the `Last 7 days`.
 
+## View Deployment Metrics
+
+Starting from the <a href="https://smith.langchain.com/" target="_blank">LangSmith UI</a>...
+
+1. In the left-hand navigation panel, select `LangGraph Platform`. The `LangGraph Platform` view contains a list of existing LangGraph Platform deployments.
+1. Select an existing deployment to monitor.
+1. Select the `Monitoring` tab to view the deployment metrics. See a list of [all available metrics](../../concepts/langgraph_control_plane.md#monitoring).
+1. Within the `Monitoring` tab, use the date/time range picker as needed. By default, the date/time range picker is set to the `Last 15 minutes`.
+
 ## Interrupt Revision
 
 Interrupting a revision will stop deployment of the revision.

docs/docs/cloud/deployment/graph_rebuild.md

@@ -20,7 +20,7 @@ my-app/
 |-- openai_agent.py     # code for your graph
 ```
 
-where the graph is defined in `openai_agent.py`.
+where the graph is defined in `openai_agent.py`. 
 
 ### No rebuild
 
@@ -28,11 +28,11 @@ In the standard LangGraph API configuration, the server uses the compiled graph
 
 ```python
 from langchain_openai import ChatOpenAI
-from langgraph.graph import END, START, StateGraph, MessagesState
+from langgraph.graph import END, START, MessageGraph
 
 model = ChatOpenAI(temperature=0)
 
-graph_workflow = StateGraph(MessagesState)
+graph_workflow = MessageGraph()
 
 graph_workflow.add_node("agent", model)
 graph_workflow.add_edge("agent", END)
@@ -61,7 +61,7 @@ To make your graph rebuild on each new run with custom configuration, you need t
 from typing import Annotated
 from typing_extensions import TypedDict
 from langchain_openai import ChatOpenAI
-from langgraph.graph import END, START
+from langgraph.graph import END, START, MessageGraph
 from langgraph.graph.state import StateGraph
 from langgraph.graph.message import add_messages
 from langgraph.prebuilt import ToolNode
@@ -144,4 +144,4 @@ Finally, you need to specify the path to your graph-making function (`make_graph
 }
 ```
 
-See more info on LangGraph API configuration file [here](../reference/cli.md#configuration-file)
+See more info on LangGraph API configuration file [here](../reference/cli.md#configuration-file)

docs/docs/cloud/deployment/self_hosted_control_plane.md

@@ -30,18 +30,16 @@ Before deploying, review the [conceptual guide for the Self-Hosted Control Plane
     1. `LangGraphPlatform CRD`: A CRD for LangGraph Platform deployments. This contains the spec for managing an instance of a LangGraph platform deployment.
     1. `operator`: This operator handles changes to your LangGraph Platform CRDs.
     1. `host-backend`: This is the [control plane](../../concepts/langgraph_control_plane.md).
-1. Two additional images will be used by the chart.
+1. Two additional images will be used by the chart. Use the images that are specified in the latest release.
 
         hostBackendImage:
           repository: "docker.io/langchain/hosted-langserve-backend"
           pullPolicy: IfNotPresent
-          tag: "0.9.80"
         operatorImage:
           repository: "docker.io/langchain/langgraph-operator"
           pullPolicy: IfNotPresent
-          tag: "aa9dff4"
 
-1. In your `langsmith_config.yaml` file, enable the `langgraphPlatform` option. Note that you must also have a valid ingress setup:
+1. In your config file for langsmith (usually `langsmith_config.yaml`, enable the `langgraphPlatform` option. Note that you must also have a valid ingress setup:
 
         config:
           langgraphPlatform:

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

@@ -212,6 +212,7 @@ We have now created an assistant called "Open AI Assistant" that has `model_name
 
 Output:
 
+    ```
     Receiving event of type: metadata
     {'run_id': '1ef6746e-5893-67b1-978a-0f1cd4060e16'}
 
@@ -219,6 +220,7 @@ Output:
 
     Receiving event of type: updates
     {'agent': {'messages': [{'content': 'I was created by OpenAI, a research organization focused on developing and advancing artificial intelligence technology.', 'additional_kwargs': {}, 'response_metadata': {'finish_reason': 'stop', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_157b3831f5'}, 'type': 'ai', 'name': None, 'id': 'run-e1a6b25c-8416-41f2-9981-f9cfe043f414', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+    ```
 
 ### LangGraph Platform UI
 
@@ -231,9 +233,11 @@ Inside your deployment, select the "Assistants" tab. For the assistant you would
 To edit the assistant, use the `update` method. This will create a new version of the assistant with the provided edits. See the [Python](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/python_sdk_ref/#langgraph_sdk.client.AssistantsClient.update) and [JS](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#update) SDK reference docs for more information.
 
 !!! note "Note"
-You must pass in the ENTIRE config (and metadata if you are using it). The update endpoint creates new versions completely from scratch and does not rely on previous versions.
+
+    You must pass in the ENTIRE config (and metadata if you are using it). The update endpoint creates new versions completely from scratch and does not rely on previous versions.
 
 For example, to update your assistant's system prompt:
+
 === "Python"
 
     ```python

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

@@ -247,5 +247,7 @@ Verify that the original, interrupted run was interrupted
 
 Output:
 
+    ```
     'interrupted'
+    ```
 

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

@@ -2,7 +2,7 @@
 
 !!! info "Prerequisites"
 
-    - [Assistants Overview](../../concepts/assistants.md)
+    - [Assistants Overview](../../../concepts/assistants.md)
 
 LangGraph Studio lets you view, edit, and update your assistants, and allows you to run your graph using these assistant configurations.
 

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

@@ -73,9 +73,11 @@ langgraph dev --debug-port 5678
 Then attach your preferred debugger:
 
 === "VS Code"
-Add this configuration to `launch.json`:
-`json
-      {
+
+    Add this configuration to `launch.json`:
+
+    ```json
+    {
         "name": "Attach to LangGraph",
         "type": "debugpy",
         "request": "attach",
@@ -83,11 +85,16 @@ Add this configuration to `launch.json`:
           "host": "0.0.0.0",
           "port": 5678
         }
-      }
-    `
-Specify the port number you chose in the previous step.
+    }
+    ```
 
-=== "PyCharm" 1. Go to Run → Edit Configurations 2. Click + and select "Python Debug Server" 3. Set IDE host name: `localhost` 4. Set port: `5678` (or the port number you chose in the previous step) 5. Click "OK" and start debugging
+=== "PyCharm" 
+
+    1. Go to Run → Edit Configurations 
+    2. Click + and select "Python Debug Server" 
+    3. Set IDE host name: `localhost` 
+    4. Set port: `5678` (or the port number you chose in the previous step) 
+    5. Click "OK" and start debugging
 
 ## Troubleshooting
 

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

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

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

@@ -8,15 +8,15 @@ Currently, the SDK does not provide built-in support for defining webhook endpoi
 
 The following API endpoints accept a `webhook` parameter:
 
-| Operation | HTTP Method | Endpoint |
-|-----------|------------|----------|
-| Create Run | `POST` | `/thread/{thread_id}/runs` |
-| Create Thread Cron | `POST` | `/thread/{thread_id}/runs/crons` |
-| Stream Run | `POST` | `/thread/{thread_id}/runs/stream` |
-| Wait Run | `POST` | `/thread/{thread_id}/runs/wait` |
-| Create Cron | `POST` | `/runs/crons` |
-| Stream Run Stateless | `POST` | `/runs/stream` |
-| Wait Run Stateless | `POST` | `/runs/wait` |
+| Operation            | HTTP Method | Endpoint                          |
+|----------------------|-------------|-----------------------------------|
+| Create Run           | `POST`      | `/thread/{thread_id}/runs`        |
+| Create Thread Cron   | `POST`      | `/thread/{thread_id}/runs/crons`  |
+| Stream Run           | `POST`      | `/thread/{thread_id}/runs/stream` |
+| Wait Run             | `POST`      | `/thread/{thread_id}/runs/wait`   |
+| Create Cron          | `POST`      | `/runs/crons`                     |
+| Stream Run Stateless | `POST`      | `/runs/stream`                    |
+| Wait Run Stateless   | `POST`      | `/runs/wait`                      |
 
 In this guide, we’ll show how to trigger a webhook after streaming a run.
 
@@ -25,36 +25,39 @@ In this guide, we’ll show how to trigger a webhook after streaming a run.
 Before making API calls, set up your assistant and thread.
 
 === "Python"
-```python
-from langgraph_sdk import get_client
 
-client = get_client(url=<DEPLOYMENT_URL>)
-assistant_id = "agent"
-thread = await client.threads.create()
-print(thread)
-```
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url=<DEPLOYMENT_URL>)
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    print(thread)
+    ```
 
 === "JavaScript"
-```js
-import { Client } from "@langchain/langgraph-sdk";
 
-const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
-const assistantID = "agent";
-const thread = await client.threads.create();
-console.log(thread);
-```
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
+    const assistantID = "agent";
+    const thread = await client.threads.create();
+    console.log(thread);
+    ```
 
 === "CURL"
-```bash
-curl --request POST \
-    --url <DEPLOYMENT_URL>/assistants/search \
-    --header 'Content-Type: application/json' \
-    --data '{ "limit": 10, "offset": 0 }' | jq -c 'map(select(.config == null or .config == {})) | .[0]' && \
-curl --request POST \
-    --url <DEPLOYMENT_URL>/threads \
-    --header 'Content-Type: application/json' \
-    --data '{}'
-```
+
+    ```bash
+    curl --request POST \
+        --url <DEPLOYMENT_URL>/assistants/search \
+        --header 'Content-Type: application/json' \
+        --data '{ "limit": 10, "offset": 0 }' | jq -c 'map(select(.config == null or .config == {})) | .[0]' && \
+    curl --request POST \
+        --url <DEPLOYMENT_URL>/threads \
+        --header 'Content-Type: application/json' \
+        --data '{}'
+    ```
 
 Example response:
 
@@ -77,48 +80,51 @@ To use a webhook, specify the `webhook` parameter in your API request. When the
 For example, if your server listens for webhook events at `https://my-server.app/my-webhook-endpoint`, include this in your request:
 
 === "Python"
-```python
-input = { "messages": [{ "role": "user", "content": "Hello!" }] }
 
-async for chunk in client.runs.stream(
-    thread_id=thread["thread_id"],
-    assistant_id=assistant_id,
-    input=input,
-    stream_mode="events",
-    webhook="https://my-server.app/my-webhook-endpoint"
-):
-    pass
-```
+    ```python
+    input = { "messages": [{ "role": "user", "content": "Hello!" }] }
+
+    async for chunk in client.runs.stream(
+        thread_id=thread["thread_id"],
+        assistant_id=assistant_id,
+        input=input,
+        stream_mode="events",
+        webhook="https://my-server.app/my-webhook-endpoint"
+    ):
+        pass
+    ```
 
 === "JavaScript"
-```js
-const input = { messages: [{ role: "human", content: "Hello!" }] };
 
-const streamResponse = client.runs.stream(
-  thread["thread_id"],
-  assistantID,
-  {
-    input: input,
-    webhook: "https://my-server.app/my-webhook-endpoint"
-  }
-);
+    ```js
+    const input = { messages: [{ role: "human", content: "Hello!" }] };
 
-for await (const chunk of streamResponse) {
-  // Handle stream output
-}
-```
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantID,
+      {
+        input: input,
+        webhook: "https://my-server.app/my-webhook-endpoint"
+      }
+    );
+
+    for await (const chunk of streamResponse) {
+      // Handle stream output
+    }
+    ```
 
 === "CURL"
-```bash
-curl --request POST \
-    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/stream \
-    --header 'Content-Type: application/json' \
-    --data '{
-        "assistant_id": <ASSISTANT_ID>,
-        "input": {"messages": [{"role": "user", "content": "Hello!"}]},
-        "webhook": "https://my-server.app/my-webhook-endpoint"
-    }'
-```
+
+    ```bash
+    curl --request POST \
+        --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/stream \
+        --header 'Content-Type: application/json' \
+        --data '{
+            "assistant_id": <ASSISTANT_ID>,
+            "input": {"messages": [{"role": "user", "content": "Hello!"}]},
+            "webhook": "https://my-server.app/my-webhook-endpoint"
+        }'
+    ```
 
 ## Webhook payload
 

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

@@ -3818,6 +3818,14 @@
             "title": "Filter",
             "description": "Optional dictionary of key-value pairs to filter results."
           },
+          "query": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "title": "Query",
+            "description": "Query string for semantic/vector search."
+          },
           "limit": {
             "type": "integer",
             "default": 10,

docs/docs/cloud/reference/cli.md

@@ -43,15 +43,17 @@ The LangGraph CLI requires a JSON configuration file that follows this [schema](
     | <span style="white-space: nowrap;">`graphs`</span>           | **Required**. Mapping from graph ID to path where the compiled graph or a function that makes a graph is defined. Example: <ul><li>`./your_package/your_file.py:variable`, where `variable` is an instance of `langgraph.graph.state.CompiledStateGraph`</li><li>`./your_package/your_file.py:make_graph`, where `make_graph` is a function that takes a config dictionary (`langchain_core.runnables.RunnableConfig`) and returns an instance of `langgraph.graph.state.StateGraph` or `langgraph.graph.state.CompiledStateGraph`. See [how to rebuild a graph at runtime](../../cloud/deployment/graph_rebuild.md) for more details.</li></ul>                                    |
     | <span style="white-space: nowrap;">`auth`</span>             | _(Added in v0.0.11)_ Auth configuration containing the path to your authentication handler. Example: `./your_package/auth.py:auth`, where `auth` is an instance of `langgraph_sdk.Auth`. See [authentication guide](../../concepts/auth.md) for details.                                                                                                                                                                                                                                                                                                                        |
     | <span style="white-space: nowrap;">`base_image`</span>       | Optional. Base image to use for the LangGraph API server. Defaults to `langchain/langgraph-api` or `langchain/langgraphjs-api`. Use this to pin your builds to a particular version of the langgraph API, such as `"langchain/langgraph-server:0.2"`. See https://hub.docker.com/r/langchain/langgraph-server/tags for more details. (added in `langgraph-cli==0.2.8`) |
+    | <span style="white-space: nowrap;">`image_distro`</span>     | Optional. Linux distribution for the base image. Must be either `"debian"` or `"wolfi"`. If omitted, defaults to `"debian"`. Available in `langgraph-cli>=0.2.11`.|
     | <span style="white-space: nowrap;">`env`</span>              | Path to `.env` file or a mapping from environment variable to its value.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
     | <span style="white-space: nowrap;">`store`</span>            | Configuration for adding semantic search and/or time-to-live (TTL) to the BaseStore. Contains the following fields: <ul><li>`index` (optional): Configuration for semantic search indexing with fields `embed`, `dims`, and optional `fields`.</li><li>`ttl` (optional): Configuration for item expiration. An object with optional fields: `refresh_on_read` (boolean, defaults to `true`), `default_ttl` (float, lifespan in **minutes**, defaults to no expiration), and `sweep_interval_minutes` (integer, how often to check for expired items, defaults to no sweeping).</li></ul> |
     | <span style="white-space: nowrap;">`ui`</span>               | Optional. Named definitions of UI components emitted by the agent, each pointing to a JS/TS file. (added in `langgraph-cli==0.1.84`)                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
     | <span style="white-space: nowrap;">`python_version`</span>   | `3.11`, `3.12`, or `3.13`. Defaults to `3.11`.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
     | <span style="white-space: nowrap;">`node_version`</span>     | Specify `node_version: 20` to use LangGraph.js.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
     | <span style="white-space: nowrap;">`pip_config_file`</span>  | Path to `pip` config file.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
+    | <span style="white-space: nowrap;">`pip_installer`</span> | _(Added in v0.3)_ Optional. Python package installer selector. It can be set to `"auto"`, `"pip"`, or `"uv"`. From version&nbsp;0.3 onward the default strategy is to run `uv pip`, which typically delivers faster builds while remaining a drop-in replacement. In the uncommon situation where `uv` cannot handle your dependency graph or the structure of your `pyproject.toml`, specify `"pip"` here to revert to the earlier behaviour. |
     | <span style="white-space: nowrap;">`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>`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>`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> |
 
 === "JS"
 
@@ -79,6 +81,20 @@ The LangGraph CLI requires a JSON configuration file that follows this [schema](
     }
     ```
 
+    #### Using Wolfi Base Images
+
+    You can specify the Linux distribution for your base image using the `image_distro` field. Valid options are `debian` or `wolfi`. Wolfi is the recommended option as it provides smaller and more secure images. This is available in `langgraph-cli>=0.2.11`.
+
+    ```json
+    {
+      "dependencies": ["."],
+      "graphs": {
+        "chat": "./chat/graph.py:graph"
+      },
+      "image_distro": "wolfi"
+    }
+    ```
+
     #### Adding semantic search to the store
 
     All deployments come with a DB-backed BaseStore. Adding an "index" configuration to your `langgraph.json` will enable [semantic search](../deployment/semantic_search.md) within the BaseStore of your deployment.
@@ -113,7 +129,7 @@ The LangGraph CLI requires a JSON configuration file that follows this [schema](
         - `cohere:embed-english-v3.0`: 1024 
         - `cohere:embed-english-light-v3.0`: 384 
         - `cohere:embed-multilingual-v3.0`: 1024 
-        - `cohere:embed-multilingual-light-v3.0`: 384
+        - `cohere:embed-multilingual-light-v3.0`: 384 
 
     #### Semantic search with a custom embedding function
 
@@ -346,8 +362,8 @@ The LangGraph CLI requires a JSON configuration file that follows this [schema](
 
     **Options**
 
-    | Option               | Default          | Description                                                                                                                  |
-    | -------------------- | ---------------- | ---------------------------------------------------------------------------------------------------------------------------- |
+    | Option               | Default          | Description                                                                                                     |
+    | -------------------- | ---------------- | --------------------------------------------------------------------------------------------------------------- |
     | `--platform TEXT`    |                  | Target platform(s) to build the Docker image for. Example: `langgraph build --platform linux/amd64,linux/arm64`              |
     | `-t, --tag TEXT`     |                  | **Required**. Tag for the Docker image. Example: `langgraph build -t my-image`                                               |
     | `--pull / --no-pull` | `--pull`         | Build with latest remote Docker image. Use `--no-pull` for running the LangGraph Platform API server with locally built images. |
@@ -366,8 +382,8 @@ The LangGraph CLI requires a JSON configuration file that follows this [schema](
 
     **Options**
 
-    | Option               | Default          | Description                                                                                                                  |
-    | -------------------- | ---------------- | ---------------------------------------------------------------------------------------------------------------------------- |
+    | Option               | Default          | Description                                                                                                     |
+    | -------------------- | ---------------- | --------------------------------------------------------------------------------------------------------------- |
     | `--platform TEXT`    |                  | Target platform(s) to build the Docker image for. Example: `langgraph build --platform linux/amd64,linux/arm64`              |
     | `-t, --tag TEXT`     |                  | **Required**. Tag for the Docker image. Example: `langgraph build -t my-image`                                               |
     | `--no-pull`          |                  | Use locally built images. Defaults to `false` to build with latest remote Docker image.                                      |

docs/docs/cloud/reference/env_var.md

@@ -50,11 +50,10 @@ Set this environment variable to have a deployment send traces to a self-hosted
 
 ## `LANGSMITH_TRACING`
 
-!!! info "Only for Self-Hosted Data Plane, Self-Hosted Control Plane, and Standalone Container"
-    Disabling LangSmith tracing is only available for [Self-Hosted Data Plane](../../concepts/langgraph_self_hosted_data_plane.md), [Self-Hosted Control Plane](../../concepts/langgraph_self_hosted_control_plane.md), and [Standalone Container](../../concepts/langgraph_standalone_container.md) deployments.
-
 Set `LANGSMITH_TRACING` to `false` to disable tracing to LangSmith.
 
+Defaults to `true`.
+
 ## `LOG_LEVEL`
 
 Configure [log level](https://docs.python.org/3/library/logging.html#logging-levels). Defaults to `INFO`.
@@ -123,3 +122,12 @@ Defaults to `''`.
 Set `REDIS_CLUSTER` to `True` to enable Redis Cluster mode. When enabled, the system will connect to Redis using cluster mode. This is useful when connecting to a Redis Cluster deployment.
 
 Defaults to `False`.
+
+## `MOUNT_PREFIX`
+
+!!! info "Only Allowed in Self-Hosted Deployments"
+    The `MOUNT_PREFIX` environment variable is only allowed in Self-Hosted Deployment models, LangGraph Platform SaaS will not allow this environment variable.
+
+Set `MOUNT_PREFIX` to serve the LangGraph Server under a specific path prefix. This is useful for deployments where the server is behind a reverse proxy or load balancer that requires a specific path prefix.
+
+For example, if the server is to be served under `https://example.com/langgraph`, set `MOUNT_PREFIX` to `/langgraph`.

docs/docs/concepts/auth.md

@@ -198,7 +198,7 @@ async def add_owner(
 You can register handlers for specific resources and actions by chaining the resource and action names together with the [`@auth.on`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.Auth.on) decorator.
 When a request is made, the most specific handler that matches that resource and action is called. Below is an example of how to register handlers for specific resources and actions. For the following setup:
 
-1. Authenticated users are able to create threads, read thread, create runs on threads
+1. Authenticated users are able to create threads, read threads, and create runs on threads
 2. Only users with the "assistants:create" permission are allowed to create new assistants
 3. All other endpoints (e.g., e.g., delete assistant, crons, store) are disabled for all users.
 

docs/docs/concepts/langgraph_cli.md

@@ -9,13 +9,18 @@ search:
 
 ## Installation
 
-The LangGraph CLI can be installed via pip:
+The LangGraph CLI can be installed via pip or [Homebrew](https://brew.sh/):
 
 === "pip" 
     ```bash
     pip install langgraph-cli
     ```
 
+=== "Homebrew"
+    ```bash
+    brew install langgraph-cli
+    ```
+
 ## Commands
 
 LangGraph CLI provides the following core functionality:

docs/docs/concepts/langgraph_control_plane.md

@@ -19,6 +19,7 @@ From the control plane UI, you can:
 - Update a deployment.
 - Update environment variables for a deployment.
 - View build and server logs of a deployment.
+- View deployment metrics such as CPU and memory usage.
 - Delete a deployment.
 
 The Control Plane UI is embedded in [LangSmith](https://docs.smith.langchain.com/langgraph_cloud).
@@ -88,6 +89,17 @@ Infrastructure for deployments and revisions are provisioned and deployed asynch
 
 The control plane and [LangGraph Data Plane](./langgraph_data_plane.md) "listener" application coordinate to achieve asynchronous deployments.
 
+### Monitoring
+
+After a deployment is ready, the control plane monitors the deployment and records various metrics, such as:
+
+- CPU and memory usage of the deployment.
+- 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.
+
+These metrics are displayed as charts in the Control Plane UI.
+
 ### LangSmith Integration
 
 A [LangSmith](https://docs.smith.langchain.com/) tracing project is automatically created for each deployment. The tracing project has the same name as the deployment. When creating a deployment, the `LANGCHAIN_TRACING` and `LANGSMITH_API_KEY`/`LANGCHAIN_API_KEY` environment variables do not need to be specified; they are set automatically by the control plane.

docs/docs/concepts/langgraph_studio.md

@@ -24,6 +24,7 @@ Key features of LangGraph Studio:
 - [Manage assistants](../cloud/how-tos/studio/manage_assistants.md)
 - [Manage threads](../cloud/how-tos/threads_studio.md)
 - [Iterate on prompts](../cloud/how-tos/iterate_graph_studio.md)
+- [Run experiments over a dataset](../cloud/how-tos/studio/run_evals.md)
 - Manage [long term memory](memory.md)
 - Debug agent state via [time travel](time-travel.md)
 
@@ -41,4 +42,4 @@ Chat mode is a simpler UI for iterating on and testing chat-specific agents. It
 
 ## Learn more
 
-- See this guide on how to [get started](../cloud/how-tos/studio/quick_start.md) with LangGraph Studio.
+- See this guide on how to [get started](../cloud/how-tos/studio/quick_start.md) with LangGraph Studio.

docs/docs/concepts/low_level.md

@@ -89,7 +89,7 @@ def node_3(state: PrivateState) -> OutputState:
     # Read from PrivateState, write to OutputState
     return {"graph_output": state["bar"] + " Lance"}
 
-builder = StateGraph(OverallState,input=InputState,output=OutputState)
+builder = StateGraph(OverallState,input_schema=InputState,output_schema=OutputState)
 builder.add_node("node_1", node_1)
 builder.add_node("node_2", node_2)
 builder.add_node("node_3", node_3)
@@ -107,7 +107,7 @@ There are two subtle and important points to note here:
 
 1. We pass `state: InputState` as the input schema to `node_1`. But, we write out to `foo`, a channel in `OverallState`. How can we write out to a state channel that is not included in the input schema? This is because a node _can write to any state channel in the graph state._ The graph state is the union of the state channels defined at initialization, which includes `OverallState` and the filters `InputState` and `OutputState`.
 
-2. We initialize the graph with `StateGraph(OverallState,input=InputState,output=OutputState)`. So, how can we write to `PrivateState` in `node_2`? How does the graph gain access to this schema if it was not passed in the `StateGraph` initialization? We can do this because _nodes can also declare additional state channels_ as long as the state schema definition exists. In this case, the `PrivateState` schema is defined, so we can add `bar` as a new state channel in the graph and write to it.
+2. We initialize the graph with `StateGraph(OverallState,input_schema=InputState,output_schema=OutputState)`. So, how can we write to `PrivateState` in `node_2`? How does the graph gain access to this schema if it was not passed in the `StateGraph` initialization? We can do this because _nodes can also declare additional state channels_ as long as the state schema definition exists. In this case, the `PrivateState` schema is defined, so we can add `bar` as a new state channel in the graph and write to it.
 
 ### Reducers
 
@@ -197,19 +197,25 @@ In LangGraph, nodes are typically python functions (sync or async) where the **f
 Similar to `NetworkX`, you add these nodes to a graph using the [add_node][langgraph.graph.StateGraph.add_node] method:
 
 ```python
+from typing_extensions import TypedDict
+
 from langchain_core.runnables import RunnableConfig
 from langgraph.graph import StateGraph
 
-builder = StateGraph(dict)
+class State(TypedDict):
+    input: str
+    results: str
+
+builder = StateGraph(State)
 
 
-def my_node(state: dict, config: RunnableConfig):
+def my_node(state: State, config: RunnableConfig):
     print("In node: ", config["configurable"]["user_id"])
     return {"results": f"Hello, {state['input']}!"}
 
 
 # The second argument is optional
-def my_other_node(state: dict):
+def my_other_node(state: State):
     return state
 
 

docs/docs/concepts/multi_agent.md

@@ -87,6 +87,7 @@ One of the most common agent types is a [tool-calling agent](../agents/overview.
 ```python
 from langchain_core.tools import tool
 
+@tool
 def transfer_to_bob():
     """Transfer to bob."""
     return Command(
@@ -414,4 +415,4 @@ 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 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.

docs/docs/concepts/persistence.md

@@ -470,9 +470,51 @@ If the checkpointer is used with asynchronous graph execution (i.e. executing th
 
 ### Serializer
 
-When checkpointers save the graph state, they need to serialize the channel values in the state. This is done using serializer objects. 
+When checkpointers save the graph state, they need to serialize the channel values in the state. This is done using serializer objects.
 `langgraph_checkpoint` defines [protocol][langgraph.checkpoint.serde.base.SerializerProtocol] for implementing serializers provides a default implementation ([JsonPlusSerializer][langgraph.checkpoint.serde.jsonplus.JsonPlusSerializer]) that handles a wide variety of types, including LangChain and LangGraph primitives, datetimes, enums and more.
 
+#### Serialization with `pickle`
+
+The default serializer, [`JsonPlusSerializer`][langgraph.checkpoint.serde.jsonplus.JsonPlusSerializer], uses ormsgpack and JSON under the hood, which is not suitable for all types of objects.
+
+If you want to fallback to pickle for objects not currently supported by our msgpack encoder (such as Pandas dataframes),
+you can use the `pickle_fallback` argument of the `JsonPlusSerializer`:
+
+```python
+from langgraph.checkpoint.memory import MemorySaver
+from langgraph.checkpoint.serde.jsonplus import JsonPlusSerializer
+
+# ... Define the graph ...
+graph.compile(
+    checkpointer=MemorySaver(serde=JsonPlusSerializer(pickle_fallback=True))
+)
+```
+
+#### Encryption
+
+Checkpointers can optionally encrypt all persisted state. To enable this, pass an instance of [`EncryptedSerializer`][langgraph.checkpoint.serde.encrypted.EncryptedSerializer] to the `serde` argument of any `BaseCheckpointSaver` implementation. The easiest way to create an encrypted serializer is via [`from_pycryptodome_aes`][langgraph.checkpoint.serde.encrypted.EncryptedSerializer.from_pycryptodome_aes], which reads the AES key from the `LANGGRAPH_AES_KEY` environment variable (or accepts a `key` argument):
+
+```python
+import sqlite3
+
+from langgraph.checkpoint.serde.encrypted import EncryptedSerializer
+from langgraph.checkpoint.sqlite import SqliteSaver
+
+serde = EncryptedSerializer.from_pycryptodome_aes()  # reads LANGGRAPH_AES_KEY
+checkpointer = SqliteSaver(sqlite3.connect("checkpoint.db"), serde=serde)
+```
+
+```python
+from langgraph.checkpoint.serde.encrypted import EncryptedSerializer
+from langgraph.checkpoint.postgres import PostgresSaver
+
+serde = EncryptedSerializer.from_pycryptodome_aes()
+checkpointer = PostgresSaver.from_conn_string("postgresql://...", serde=serde)
+checkpointer.setup()
+```
+
+When running on LangGraph Platform, encryption is automatically enabled whenever `LANGGRAPH_AES_KEY` is present, so you only need to provide the environment variable. Other encryption schemes can be used by implementing [`CipherProtocol`][langgraph.checkpoint.serde.base.CipherProtocol] and supplying it to `EncryptedSerializer`.
+
 ## Capabilities
 
 ### Human-in-the-loop

docs/docs/concepts/server-mcp.md

@@ -94,7 +94,7 @@ def answer_node(state: InputState):
     return {"answer": "bye", "question": state["question"]}
 
 # Build the graph with explicit schemas
-builder = StateGraph(OverallState, input=InputState, output=OutputState)
+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)

docs/docs/concepts/subgraphs.md

@@ -59,8 +59,9 @@ The main question when adding subgraphs is how the parent graph and subgraph com
         response = model.invoke(state["subgraph_messages"])
         return {"subgraph_messages": response}
 
-    subgraph_builder = StateGraph(State)
-    subgraph_builder.add_node(call_model)
+    subgraph_builder = StateGraph(SubgraphMessagesState)
+    subgraph_builder.add_node("call_model_from_subgraph", call_model)
+    subgraph_builder.add_edge(START, "call_model_from_subgraph")
     ...
     # highlight-next-line
     subgraph = subgraph_builder.compile()

docs/docs/how-tos/graph-api.ipynb

@@ -439,7 +439,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "id": "6ec0eb77-874e-443e-8c73-93125b515106",
    "metadata": {},
    "outputs": [
@@ -478,7 +478,7 @@
     "\n",
     "\n",
     "# Build the graph with input and output schemas specified\n",
-    "builder = StateGraph(OverallState, input=InputState, output=OutputState)\n",
+    "builder = StateGraph(OverallState, input_schema=InputState, output_schema=OutputState)\n",
     "builder.add_node(answer_node)  # Add the answer node\n",
     "builder.add_edge(START, \"answer_node\")  # Define the starting edge\n",
     "builder.add_edge(\"answer_node\", END)  # Define the ending edge\n",
@@ -3430,7 +3430,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.9"
+   "version": "3.9.6"
   }
  },
  "nbformat": 4,

docs/docs/how-tos/http/custom_routes.md

@@ -34,7 +34,7 @@ def read_root():
 
 ## Configure `langgraph.json`
 
-Add the following to your `langgraph.json` configuration file. Make sure the path points to the `app.py` file you created above.
+Add the following to your `langgraph.json` configuration file. Make sure the path points to the FastAPI application instance `app` in the `webapp.py` file you created above.
 
 ```json
 {
@@ -71,4 +71,4 @@ You can deploy this app as-is to LangGraph Platform or to your self-hosted platf
 
 ## Next steps
 
-Now that you've added a custom route to your deployment, you can use this same technique to further customize how your server behaves, such as defining custom [custom middleware](./custom_middleware.md) and [custom lifespan events](./custom_lifespan.md). 
+Now that you've added a custom route to your deployment, you can use this same technique to further customize how your server behaves, such as defining custom [custom middleware](./custom_middleware.md) and [custom lifespan events](./custom_lifespan.md). 

docs/docs/how-tos/persistence.ipynb

@@ -1107,10 +1107,10 @@
    "source": [
     "### Use in production\n",
     "\n",
-    "In production, you would want to use a checkpointer backed by a database:\n",
+    "In production, you would want to use a store backed by a database:\n",
     "\n",
     "```python\n",
-    "from langgraph.checkpoint.postgres import PostgresSaver\n",
+    "from langgraph.store.postgres import PostgresStore\n",
     "\n",
     "DB_URI = \"postgresql://postgres:postgres@localhost:5442/postgres?sslmode=disable\"\n",
     "# highlight-next-line\n",

docs/docs/reference/checkpoints.md

@@ -12,12 +12,18 @@
     options:
       members:
         - SerializerProtocol
+        - CipherProtocol
 
 ::: langgraph.checkpoint.serde.jsonplus
     options:
       members:
         - JsonPlusSerializer
 
+::: langgraph.checkpoint.serde.encrypted
+    options:
+      members:
+        - EncryptedSerializer
+
 ::: langgraph.checkpoint.memory
 
 ::: langgraph.checkpoint.sqlite
@@ -32,4 +38,4 @@
 ::: langgraph.checkpoint.postgres.aio
     options:
       members:
-        - AsyncPostgresSaver
+        - AsyncPostgresSaver

docs/docs/reference/index.md

@@ -22,7 +22,7 @@ Welcome to the LangGraph reference docs! These pages detail the core interfaces
 
 ## LangGraph
 
-The core APIs for the LangGraph opens source library.
+The core APIs for the LangGraph open source library.
 
 - [Graphs](graphs.md): Main graph abstraction and usage.
 - [Functional API](func.md): Functional programming interface for graphs.

docs/docs/tutorials/chatbot-simulation-evaluation/langsmith-agent-simulation-evaluation.ipynb

@@ -580,9 +580,7 @@
     "    ]\n",
     ")\n",
     "\n",
-    "evaluator = prompt | ChatOpenAI(model=\"gpt-4-turbo-preview\").with_structured_output(\n",
-    "    RedTeamingResult, method=\"function_calling\"\n",
-    ")\n",
+    "evaluator = prompt | ChatOpenAI(model=\"gpt-4o\").with_structured_output(RedTeamingResult)\n",
     "\n",
     "\n",
     "def did_resist(run, example):\n",

docs/docs/tutorials/extraction/retries.ipynb

@@ -89,7 +89,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "id": "baf669a0-04ee-492d-80d8-8fcb658ed128",
    "metadata": {},
    "outputs": [],
@@ -313,8 +313,8 @@
     "\n",
     "    builder.add_edge(\"finalizer\", END)\n",
     "\n",
-    "    # These functions let the step be used in a\n",
-    "    # StateGraph with 'messages' as the key.\n",
+    "    # These functions let the step be used in a MessageGraph\n",
+    "    # or a StateGraph with 'messages' as the key.\n",
     "    def encode(x: Union[Sequence[AnyMessage], PromptValue]) -> dict:\n",
     "        \"\"\"Ensure the input is the correct format.\"\"\"\n",
     "        if isinstance(x, PromptValue):\n",

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

@@ -32,7 +32,7 @@ from typing import Annotated
 
 from typing_extensions import TypedDict
 
-from langgraph.graph import StateGraph, START
+from langgraph.graph import StateGraph, START, END
 from langgraph.graph.message import add_messages
 
 
@@ -100,7 +100,16 @@ Add an `entry` point to tell the graph **where to start its work** each time it
 graph_builder.add_edge(START, "chatbot")
 ```
 
-## 5. Compile the graph
+## 5. Add an `exit` point
+
+Add an `exit` point to indicate **where the graph should finish execution**. This is helpful for more complex flows, but even in a simple graph like this, adding an end node improves clarity.
+
+```python
+graph_builder.add_edge("chatbot", END)
+```
+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.
@@ -109,7 +118,7 @@ on the graph builder. This creates a `CompiledGraph` we can invoke on our state.
 graph = graph_builder.compile()
 ```
 
-## 6. Visualize the graph (optional)
+## 7. Visualize the graph (optional)
 
 You can visualize the graph using the `get_graph` method and one of the "draw" methods, like `draw_ascii` or `draw_png`. The `draw` methods each require additional dependencies.
 
@@ -126,7 +135,7 @@ except Exception:
 ![basic chatbot diagram](basic-chatbot.png)
 
 
-## 7. Run the chatbot
+## 8. Run the chatbot
 
 Now run the chatbot! 
 
@@ -171,7 +180,7 @@ from typing import Annotated
 from langchain.chat_models import init_chat_model
 from typing_extensions import TypedDict
 
-from langgraph.graph import StateGraph, START
+from langgraph.graph import StateGraph, START, END
 from langgraph.graph.message import add_messages
 
 
@@ -194,6 +203,7 @@ def chatbot(state: State):
 # the node is used.
 graph_builder.add_node("chatbot", chatbot)
 graph_builder.add_edge(START, "chatbot")
+graph_builder.add_edge("chatbot", END)
 graph = graph_builder.compile()
 ```
 

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

@@ -164,7 +164,7 @@ llm = init_chat_model("anthropic:claude-3-5-sonnet-latest")
 ```
 -->
 
-```python
+```python hl_lines="36 37"
 from typing import Annotated
 
 from langchain.chat_models import init_chat_model
@@ -206,4 +206,4 @@ graph = graph_builder.compile(checkpointer=memory)
 
 ## Next steps
 
-In the next tutorial, you will [add human-in-the-loop to the chatbot](./4-human-in-the-loop.md) to handle situations where it may need guidance or verification before proceeding.
+In the next tutorial, you will [add human-in-the-loop to the chatbot](./4-human-in-the-loop.md) to handle situations where it may need guidance or verification before proceeding.

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

@@ -471,7 +471,7 @@
     "\n",
     "_get_pass(\"TAVILY_API_KEY\")\n",
     "\n",
-    "calculate = get_math_tool(ChatOpenAI(model=\"gpt-4-turbo-preview\"))\n",
+    "calculate = get_math_tool(ChatOpenAI(model=\"gpt-4o\"))\n",
     "search = TavilySearchResults(\n",
     "    max_results=1,\n",
     "    description='tavily_search_results_json(query=\"the search query\") - a search engine.',\n",
@@ -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",
@@ -1030,7 +1030,7 @@
     "joiner_prompt = hub.pull(\"wfh/llm-compiler-joiner\").partial(\n",
     "    examples=\"\"\n",
     ")  # You can optionally add examples\n",
-    "llm = ChatOpenAI(model=\"gpt-4-turbo-preview\")\n",
+    "llm = ChatOpenAI(model=\"gpt-4o\")\n",
     "\n",
     "runnable = joiner_prompt | llm.with_structured_output(\n",
     "    JoinOutputs, method=\"function_calling\"\n",

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

@@ -135,7 +135,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain import hub\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
     "from langgraph.prebuilt import create_react_agent\n",

docs/docs/tutorials/rag/langgraph_adaptive_rag.ipynb

@@ -90,7 +90,11 @@
    "id": "9ac1c2cd-81fb-40eb-8ba1-e9197800cba6",
    "metadata": {},
    "source": [
-    "## Create Index"
+    "## Create Index\n",
+    "\n",
+    "Set up a vector database using OpenAI Embeddings and the Chroma vector database.  \n",
+    "Input URLs of blog posts related to agents, prompt engineering, and large language models (LLMs).  \n",
+    "Generate vector indices for use in Retrieval-Augmented Generation (RAG)."
    ]
   },
   {
@@ -159,6 +163,21 @@
     "</div>"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "6cdd5ac0-fa18-4ee9-8051-062a0c56268f",
+   "metadata": {},
+   "source": [
+    "### Router for Query Analysis\n",
+    "\n",
+    "Let’s start with Routing. First, assign the query analysis to the LLM.\n",
+    "\n",
+    "Create a RouteQuery data model and specify it in a structured format for the LLM. The decision for routing should be embedded in the prompt. You need to clearly define which parts of the document should be directed to RAG based on the topic.\n",
+    "\n",
+    "While you could automate this process by having the LLM summarize the RAG documents again, it’s more cost-effective to manually manage this when dealing with large documents, as automation could become expensive.\n",
+    "\n"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 4,
@@ -219,6 +238,18 @@
     "print(question_router.invoke({\"question\": \"What are the types of agent memory?\"}))"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "cb248c94-0b0c-4d86-8565-32aa8d7424e4",
+   "metadata": {},
+   "source": [
+    "### Retrieval Grader\n",
+    "\n",
+    "After performing retrieval, evaluate the results. Although you initially decided to use RAG based on the query, the retrieved documents might not be satisfactory. Assess whether the retrieved documents are sufficiently relevant to the query.\n",
+    "\n",
+    "For this, rely on the LLM to evaluate the relevance, providing a binary ‘yes’ or ‘no’ decision."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 5,
@@ -309,6 +340,17 @@
     "print(generation)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "cb0ab54a-4a4f-45fa-b1c5-cea1bf4c59d5",
+   "metadata": {},
+   "source": [
+    "### Hallucination Grader\n",
+    "\n",
+    "Verify if the LLM produced any hallucinations by comparing its output to the retrieved facts.  \n",
+    "Provide the LLM’s evaluation in a binary ‘yes’ or ‘no’ format.\n"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 7,
@@ -357,6 +399,16 @@
     "hallucination_grader.invoke({\"documents\": docs, \"generation\": generation})"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "4f58502a-c25f-4d80-a402-5583b0cd3e41",
+   "metadata": {},
+   "source": [
+    "### Answer Grader\n",
+    "\n",
+    "Evaluate the answer finally."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 8,
@@ -405,6 +457,18 @@
     "answer_grader.invoke({\"question\": question, \"generation\": generation})"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "af77946c-2646-4039-86b0-e2fde1ab7459",
+   "metadata": {},
+   "source": [
+    "### Question Rewriting\n",
+    "\n",
+    "The original question from user was directly used in RAG.  \n",
+    "However, the user’s question might not be in a form suitable for RAG.  \n",
+    "To improve retrieval, rephrase the question to ensure it aligns better with vector similarity search."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 9,
@@ -450,7 +514,9 @@
    "id": "d07c0b31-b919-4498-869f-9673125c2473",
    "metadata": {},
    "source": [
-    "## Web Search Tool"
+    "## Web Search Tool\n",
+    "\n",
+    "Use Tavily Search tool to get information from the web."
    ]
   },
   {

docs/docs/tutorials/rag/langgraph_crag.ipynb

@@ -185,7 +185,7 @@
     "\n",
     "\n",
     "# LLM with function call\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
     "structured_llm_grader = llm.with_structured_output(GradeDocuments)\n",
     "\n",
     "# Prompt\n",

docs/docs/tutorials/usaco/usaco.ipynb

@@ -1758,7 +1758,7 @@
    "id": "4eb67198-c84f-458b-8baf-783d7246dddc",
    "metadata": {},
    "source": [
-    "Let's let the agent try again. Call `stream` with `None` to just use the inputs loaded from the memory. We will skip our human review for the next few attempats\n",
+    "Let's let the agent try again. Call `stream` with `None` to just use the inputs loaded from the memory. We will skip our human review for the next few attempts\n",
     "to see if it can correct itself."
    ]
   },

docs/docs/tutorials/workflows.md

@@ -648,7 +648,7 @@ With orchestrator-worker, an orchestrator breaks down a task and delegates each
     Because orchestrator-worker workflows are common, LangGraph **has the `Send` API to support this**. It lets you dynamically create worker nodes and send each one a specific input. Each worker has its own state, and all worker outputs are written to a *shared state key* that is accessible to the orchestrator graph. This gives the orchestrator access to all worker output and allows it to synthesize them into a final output. As you can see below, we iterate over a list of sections and `Send` each to a worker node. See further documentation [here](https://langchain-ai.github.io/langgraph/how-tos/map-reduce/) and [here](https://langchain-ai.github.io/langgraph/concepts/low_level/#send).
 
     ```python
-    from langgraph.constants import Send
+    from langgraph.types import Send
 
 
     # Graph state

docs/mkdocs.yml

@@ -179,6 +179,7 @@ nav:
           - cloud/how-tos/studio/manage_assistants.md
           - cloud/how-tos/threads_studio.md
           - cloud/how-tos/iterate_graph_studio.md
+          - cloud/how-tos/studio/run_evals.md
           - cloud/how-tos/clone_traces_studio.md
           - cloud/how-tos/datasets_studio.md
         - LangGraph SDK: concepts/sdk.md
@@ -364,16 +365,6 @@ markdown_extensions:
 hooks:
   - _scripts/notebook_hooks.py
 extra:
-  consent:
-    title: Cookie consent
-    actions:
-      - accept
-      - reject
-    description: >- 
-      We use cookies to recognize your repeated visits and preferences, as well
-      as to measure the effectiveness of our documentation and whether users
-      find what they're searching for. <strong>Clicking "Accept" makes our
-      documentation better. Thank you!</strong> ❤️
   social:
     - icon: fontawesome/brands/js
       link: https://langchain-ai.github.io/langgraphjs/
@@ -381,25 +372,6 @@ extra:
       link: https://github.com/langchain-ai/langgraph
     - icon: fontawesome/brands/twitter
       link: https://twitter.com/LangChainAI
-  analytics:
-    provider: google
-    property: G-G8X6ELZYE0
-    feedback:
-      title: Was this page helpful?
-      ratings:
-        - icon: material/emoticon-happy-outline
-          name: This page was helpful
-          data: 1
-          note: >-
-            Thanks for your feedback!
-        - icon: material/emoticon-sad-outline
-          name: This page could be improved
-          data: 0
-          note: >-
-            Thanks for your feedback! Please help us improve this page by adding to the discussion below.
-  shared_analytics:
-    provider: google
-    property: G-47WX3HKKY2
 validation:
   # https://www.mkdocs.org/user-guide/configuration/
   # We are still raising for omitted files because they determine the breadcrumbs for pages.

docs/overrides/language-switcher.css

@@ -0,0 +1,41 @@
+.lang-python,
+.lang-javascript {
+    display: none;
+}
+
+.language-switcher-global {
+    display: flex;
+    align-items: center;
+    padding-left: 0.5rem;
+    margin-right: 0.5rem;
+}
+
+/* Style the select to match the header */
+.language-switcher-global select {
+    appearance: none;
+    font: inherit;
+    border: none;
+    padding: 0.25rem 0.6rem;
+    cursor: pointer;
+    outline: none;
+    font-weight: bolder;
+}
+
+/* Hover/focus effect */
+.language-switcher-global select:hover,
+.language-switcher-global select:focus {
+    text-decoration: underline;
+}
+
+/* Theme-specific overrides */
+html[data-md-color-scheme="default"] .language-switcher-global select,
+html[data-md-color-scheme="default"] .language-switcher-global option {
+    color: #333;
+    background-color: transparent;
+}
+
+html[data-md-color-scheme="slate"] .language-switcher-global select,
+html[data-md-color-scheme="slate"] .language-switcher-global option {
+    color: #eee;
+    background-color: transparent;
+}

docs/overrides/language-switcher.js

@@ -0,0 +1,38 @@
+function applyLanguageSwitching() {
+    const selector = document.getElementById("global-language-selector");
+
+    const langBlocks = {
+        python: document.querySelectorAll(".lang-python"),
+        javascript: document.querySelectorAll(".lang-javascript"),
+    };
+
+    const setLanguage = (lang) => {
+        for (const [key, blocks] of Object.entries(langBlocks)) {
+            blocks.forEach((block) => {
+                block.style.display = key === lang ? "block" : "none";
+            });
+        }
+        localStorage.setItem("preferredLang", lang);
+    };
+
+    const saved = localStorage.getItem("preferredLang") || "python";
+
+    if (selector) {
+        selector.value = saved;
+        selector.addEventListener("change", (e) => setLanguage(e.target.value));
+    }
+
+    setLanguage(saved);
+}
+
+// Run on initial load
+document.addEventListener("DOMContentLoaded", applyLanguageSwitching);
+
+// Re-run after client-side navigation (MkDocs Material)
+document.addEventListener("pjax:success", applyLanguageSwitching);
+
+// Optional: observe DOM changes (e.g., for late-loaded content)
+if (window.MutationObserver) {
+    const observer = new MutationObserver(() => applyLanguageSwitching());
+    observer.observe(document.body, { childList: true, subtree: true });
+}

docs/overrides/partials/language-toggle.html

@@ -0,0 +1,6 @@
+<div class="md-header__button language-switcher-global" title="Select Language">
+  <select id="global-language-selector" aria-label="Select Language">
+    <option value="python">🐍 Python</option>
+    <option value="javascript">⚡️ JavaScript</option>
+  </select>
+</div>

docs/tests/unit_tests/test_conditional_rendering.py

@@ -0,0 +1,22 @@
+from _scripts.notebook_hooks import _apply_conditional_rendering
+
+
+CONDITIONAL_RENDERING = """
+above
+:::js
+js-content
+:::
+between
+:::python
+python-content
+:::
+below
+"""
+
+
+def test_conditional_rendering() -> None:
+    """Test logic for conditional rendering of content."""
+    output = _apply_conditional_rendering(CONDITIONAL_RENDERING, "js")
+    assert output.strip() == "above\njs-content\n\nbetween\n\nbelow"
+    output = _apply_conditional_rendering(CONDITIONAL_RENDERING, "python")
+    assert output.strip() == "above\n\nbetween\npython-content\n\nbelow"

examples/rag/langgraph_adaptive_rag.ipynb

@@ -184,7 +184,7 @@
     "\n",
     "\n",
     "# LLM with function call\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
     "structured_llm_router = llm.with_structured_output(RouteQuery)\n",
     "\n",
     "# Prompt\n",
@@ -235,7 +235,7 @@
     "\n",
     "\n",
     "# LLM with function call\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
     "structured_llm_grader = llm.with_structured_output(GradeDocuments)\n",
     "\n",
     "# Prompt\n",
@@ -328,7 +328,7 @@
     "\n",
     "\n",
     "# LLM with function call\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
     "structured_llm_grader = llm.with_structured_output(GradeHallucinations)\n",
     "\n",
     "# Prompt\n",
@@ -376,7 +376,7 @@
     "\n",
     "\n",
     "# LLM with function call\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
     "structured_llm_grader = llm.with_structured_output(GradeAnswer)\n",
     "\n",
     "# Prompt\n",

examples/rag/langgraph_agentic_rag.ipynb

@@ -200,11 +200,11 @@
      "output_type": "stream",
      "text": [
       "********************Prompt[rlm/rag-prompt]********************\n",
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
+      "================================\u001B[1m Human Message \u001B[0m=================================\n",
       "\n",
       "You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question. If you don't know the answer, just say that you don't know. Use three sentences maximum and keep the answer concise.\n",
-      "Question: \u001b[33;1m\u001b[1;3m{question}\u001b[0m \n",
-      "Context: \u001b[33;1m\u001b[1;3m{context}\u001b[0m \n",
+      "Question: \u001B[33;1m\u001B[1;3m{question}\u001B[0m \n",
+      "Context: \u001B[33;1m\u001B[1;3m{context}\u001B[0m \n",
       "Answer:\n"
      ]
     }
@@ -244,7 +244,7 @@
     "        binary_score: str = Field(description=\"Relevance score 'yes' or 'no'\")\n",
     "\n",
     "    # LLM\n",
-    "    model = ChatOpenAI(temperature=0, model=\"gpt-4-0125-preview\", streaming=True)\n",
+    "    model = ChatOpenAI(temperature=0, model=\"gpt-4o\", streaming=True)\n",
     "\n",
     "    # LLM with tool and validation\n",
     "    llm_with_tool = model.with_structured_output(grade)\n",

examples/rag/langgraph_crag.ipynb

@@ -171,7 +171,7 @@
     "\n",
     "\n",
     "# LLM with function call\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
     "structured_llm_grader = llm.with_structured_output(GradeDocuments)\n",
     "\n",
     "# Prompt\n",

examples/rag/langgraph_self_rag.ipynb

@@ -191,7 +191,7 @@
     "\n",
     "\n",
     "# LLM with function call\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
     "structured_llm_grader = llm.with_structured_output(GradeDocuments)\n",
     "\n",
     "# Prompt\n",
@@ -284,7 +284,7 @@
     "\n",
     "\n",
     "# LLM with function call\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
     "structured_llm_grader = llm.with_structured_output(GradeHallucinations)\n",
     "\n",
     "# Prompt\n",
@@ -332,7 +332,7 @@
     "\n",
     "\n",
     "# LLM with function call\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
     "structured_llm_grader = llm.with_structured_output(GradeAnswer)\n",
     "\n",
     "# Prompt\n",

examples/rag/langgraph_self_rag_pinecone_movies.ipynb

@@ -33,7 +33,9 @@
    "id": "a384cc48-0425-4e8f-aafc-cfb8e56025c9",
    "metadata": {},
    "outputs": [],
-   "source": ["%pip install -qU langchain-pinecone langchain-openai langchainhub langgraph"]
+   "source": [
+    "%pip install -qU langchain-pinecone langchain-openai langchainhub langgraph"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -51,7 +53,9 @@
    "id": "ccc3dae5-1df6-48ca-af8a-50f0e6128876",
    "metadata": {},
    "outputs": [],
-   "source": ["import os\n\nos.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_ENDPOINT\"] = \"https://api.smith.langchain.com\"\nos.environ[\"LANGCHAIN_API_KEY\"] = \"<your-api-key>\""]
+   "source": [
+    "import os\n\nos.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_ENDPOINT\"] = \"https://api.smith.langchain.com\"\nos.environ[\"LANGCHAIN_API_KEY\"] = \"<your-api-key>\""
+   ]
   },
   {
    "cell_type": "code",
@@ -59,7 +63,9 @@
    "id": "88637820",
    "metadata": {},
    "outputs": [],
-   "source": ["import os\n\nos.environ[\"LANGCHAIN_PROJECT\"] = \"pinecone-devconnect\""]
+   "source": [
+    "import os\n\nos.environ[\"LANGCHAIN_PROJECT\"] = \"pinecone-devconnect\""
+   ]
   },
   {
    "cell_type": "markdown",
@@ -77,7 +83,9 @@
    "id": "565a6d44-2c9f-4fff-b1ec-eea05df9350d",
    "metadata": {},
    "outputs": [],
-   "source": ["from langchain_openai import OpenAIEmbeddings\nfrom langchain_pinecone import PineconeVectorStore\n\n# use pinecone movies database\n\n# Add to vectorDB\nvectorstore = PineconeVectorStore(\n    embedding=OpenAIEmbeddings(),\n    index_name=\"sample-movies\",\n    text_key=\"summary\",\n)\nretriever = vectorstore.as_retriever()"]
+   "source": [
+    "from langchain_openai import OpenAIEmbeddings\nfrom langchain_pinecone import PineconeVectorStore\n\n# use pinecone movies database\n\n# Add to vectorDB\nvectorstore = PineconeVectorStore(\n    embedding=OpenAIEmbeddings(),\n    index_name=\"sample-movies\",\n    text_key=\"summary\",\n)\nretriever = vectorstore.as_retriever()"
+   ]
   },
   {
    "cell_type": "code",
@@ -104,7 +112,9 @@
      ]
     }
    ],
-   "source": ["docs = retriever.invoke(\"James Cameron\")\nfor doc in docs:\n    print(\"# \" + doc.metadata[\"title\"])\n    print(doc.page_content)\n    print()"]
+   "source": [
+    "docs = retriever.invoke(\"James Cameron\")\nfor doc in docs:\n    print(\"# \" + doc.metadata[\"title\"])\n    print(doc.page_content)\n    print()"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -120,7 +130,32 @@
    "id": "1fafad21-60cc-483e-92a3-6a7edb1838e3",
    "metadata": {},
    "outputs": [],
-   "source": ["### Retrieval Grader\n\nfrom langchain import hub\nfrom langchain_core.pydantic_v1 import BaseModel, Field\nfrom langchain_openai import ChatOpenAI\n\n\n# Data model\nclass GradeDocuments(BaseModel):\n    \"\"\"Binary score for relevance check on retrieved documents.\"\"\"\n\n    binary_score: str = Field(\n        description=\"Documents are relevant to the question, 'yes' or 'no'\"\n    )\n\n\n# https://smith.langchain.com/hub/efriis/self-rag-retrieval-grader\ngrade_prompt = hub.pull(\"efriis/self-rag-retrieval-grader\")\n\n# LLM with function call\nllm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\nstructured_llm_grader = llm.with_structured_output(GradeDocuments)\n\nretrieval_grader = grade_prompt | structured_llm_grader"]
+   "source": [
+    "### Retrieval Grader\n",
+    "\n",
+    "from langchain import hub\n",
+    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "\n",
+    "# Data model\n",
+    "class GradeDocuments(BaseModel):\n",
+    "    \"\"\"Binary score for relevance check on retrieved documents.\"\"\"\n",
+    "\n",
+    "    binary_score: str = Field(\n",
+    "        description=\"Documents are relevant to the question, 'yes' or 'no'\"\n",
+    "    )\n",
+    "\n",
+    "\n",
+    "# https://smith.langchain.com/hub/efriis/self-rag-retrieval-grader\n",
+    "grade_prompt = hub.pull(\"efriis/self-rag-retrieval-grader\")\n",
+    "\n",
+    "# LLM with function call\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
+    "structured_llm_grader = llm.with_structured_output(GradeDocuments)\n",
+    "\n",
+    "retrieval_grader = grade_prompt | structured_llm_grader"
+   ]
   },
   {
    "cell_type": "code",
@@ -137,7 +172,9 @@
      ]
     }
    ],
-   "source": ["# Test the retrieval grader\nquestion = \"movies starring jason momoa\"\ndocs = retriever.invoke(question)\ndoc_txt = docs[0].page_content\nprint(doc_txt)\nprint(retrieval_grader.invoke({\"question\": question, \"document\": doc_txt}))"]
+   "source": [
+    "# Test the retrieval grader\nquestion = \"movies starring jason momoa\"\ndocs = retriever.invoke(question)\ndoc_txt = docs[0].page_content\nprint(doc_txt)\nprint(retrieval_grader.invoke({\"question\": question, \"document\": doc_txt}))"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -163,7 +200,9 @@
      ]
     }
    ],
-   "source": ["### Generate\n\nfrom langchain import hub\nfrom langchain_core.output_parsers import StrOutputParser\n\n# Prompt\nprompt = hub.pull(\"rlm/rag-prompt\")\n\n# LLM\nllm = ChatOpenAI(model_name=\"gpt-3.5-turbo\", temperature=0)\n\n# Chain\nrag_chain = prompt | llm | StrOutputParser()\n\n# Run\ngeneration = rag_chain.invoke({\"context\": docs, \"question\": question})\nprint(generation)"]
+   "source": [
+    "### Generate\n\nfrom langchain import hub\nfrom langchain_core.output_parsers import StrOutputParser\n\n# Prompt\nprompt = hub.pull(\"rlm/rag-prompt\")\n\n# LLM\nllm = ChatOpenAI(model_name=\"gpt-3.5-turbo\", temperature=0)\n\n# Chain\nrag_chain = prompt | llm | StrOutputParser()\n\n# Run\ngeneration = rag_chain.invoke({\"context\": docs, \"question\": question})\nprint(generation)"
+   ]
   },
   {
    "cell_type": "code",
@@ -189,7 +228,30 @@
      "output_type": "execute_result"
     }
    ],
-   "source": ["### Hallucination Grader\n\n\n# Data model\nclass GradeHallucinations(BaseModel):\n    \"\"\"Binary score for hallucination present in generation answer.\"\"\"\n\n    binary_score: str = Field(\n        description=\"Answer is grounded in the facts, 'yes' or 'no'\"\n    )\n\n\n# LLM with function call\nllm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\nstructured_llm_grader = llm.with_structured_output(GradeHallucinations)\n\n# https://smith.langchain.com/hub/efriis/self-rag-hallucination-grader\nhallucination_prompt = hub.pull(\"efriis/self-rag-hallucination-grader\")\n\nhallucination_grader = hallucination_prompt | structured_llm_grader\nprint(generation)\nhallucination_grader.invoke({\"documents\": docs, \"generation\": generation})"]
+   "source": [
+    "### Hallucination Grader\n",
+    "\n",
+    "\n",
+    "# Data model\n",
+    "class GradeHallucinations(BaseModel):\n",
+    "    \"\"\"Binary score for hallucination present in generation answer.\"\"\"\n",
+    "\n",
+    "    binary_score: str = Field(\n",
+    "        description=\"Answer is grounded in the facts, 'yes' or 'no'\"\n",
+    "    )\n",
+    "\n",
+    "\n",
+    "# LLM with function call\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
+    "structured_llm_grader = llm.with_structured_output(GradeHallucinations)\n",
+    "\n",
+    "# https://smith.langchain.com/hub/efriis/self-rag-hallucination-grader\n",
+    "hallucination_prompt = hub.pull(\"efriis/self-rag-hallucination-grader\")\n",
+    "\n",
+    "hallucination_grader = hallucination_prompt | structured_llm_grader\n",
+    "print(generation)\n",
+    "hallucination_grader.invoke({\"documents\": docs, \"generation\": generation})"
+   ]
   },
   {
    "cell_type": "code",
@@ -216,7 +278,31 @@
      "output_type": "execute_result"
     }
    ],
-   "source": ["### Answer Grader\n\n\n# Data model\nclass GradeAnswer(BaseModel):\n    \"\"\"Binary score to assess answer addresses question.\"\"\"\n\n    binary_score: str = Field(\n        description=\"Answer addresses the question, 'yes' or 'no'\"\n    )\n\n\n# LLM with function call\nllm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\nstructured_llm_grader = llm.with_structured_output(GradeAnswer)\n\n# Prompt\nanswer_prompt = hub.pull(\"efriis/self-rag-answer-grader\")\n\nanswer_grader = answer_prompt | structured_llm_grader\nprint(question)\nprint(generation)\nanswer_grader.invoke({\"question\": question, \"generation\": generation})"]
+   "source": [
+    "### Answer Grader\n",
+    "\n",
+    "\n",
+    "# Data model\n",
+    "class GradeAnswer(BaseModel):\n",
+    "    \"\"\"Binary score to assess answer addresses question.\"\"\"\n",
+    "\n",
+    "    binary_score: str = Field(\n",
+    "        description=\"Answer addresses the question, 'yes' or 'no'\"\n",
+    "    )\n",
+    "\n",
+    "\n",
+    "# LLM with function call\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
+    "structured_llm_grader = llm.with_structured_output(GradeAnswer)\n",
+    "\n",
+    "# Prompt\n",
+    "answer_prompt = hub.pull(\"efriis/self-rag-answer-grader\")\n",
+    "\n",
+    "answer_grader = answer_prompt | structured_llm_grader\n",
+    "print(question)\n",
+    "print(generation)\n",
+    "answer_grader.invoke({\"question\": question, \"generation\": generation})"
+   ]
   },
   {
    "cell_type": "code",
@@ -242,7 +328,9 @@
      "output_type": "execute_result"
     }
    ],
-   "source": ["### Question Re-writer\n\n# LLM\nllm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n\n# Prompt\nre_write_prompt = hub.pull(\"efriis/self-rag-question-rewriter\")\n\nquestion_rewriter = re_write_prompt | llm | StrOutputParser()\nprint(question)\nquestion_rewriter.invoke({\"question\": question})"]
+   "source": [
+    "### Question Re-writer\n\n# LLM\nllm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n\n# Prompt\nre_write_prompt = hub.pull(\"efriis/self-rag-question-rewriter\")\n\nquestion_rewriter = re_write_prompt | llm | StrOutputParser()\nprint(question)\nquestion_rewriter.invoke({\"question\": question})"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -262,7 +350,9 @@
    "id": "f1617e9e-66a8-4c1a-a1fe-cc936284c085",
    "metadata": {},
    "outputs": [],
-   "source": ["from typing import List\n\nfrom typing_extensions import TypedDict\n\n\nclass GraphState(TypedDict):\n    \"\"\"\n    Represents the state of our graph.\n\n    Attributes:\n        question: question\n        generation: LLM generation\n        documents: list of documents\n    \"\"\"\n\n    question: str\n    generation: str\n    documents: List[str]"]
+   "source": [
+    "from typing import List\n\nfrom typing_extensions import TypedDict\n\n\nclass GraphState(TypedDict):\n    \"\"\"\n    Represents the state of our graph.\n\n    Attributes:\n        question: question\n        generation: LLM generation\n        documents: list of documents\n    \"\"\"\n\n    question: str\n    generation: str\n    documents: List[str]"
+   ]
   },
   {
    "cell_type": "code",
@@ -270,7 +360,9 @@
    "id": "add509d8-6682-4127-8d95-13dd37d79702",
    "metadata": {},
    "outputs": [],
-   "source": ["### Nodes\n\n\ndef retrieve(state):\n    \"\"\"\n    Retrieve documents\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        state (dict): New key added to state, documents, that contains retrieved documents\n    \"\"\"\n    print(\"---RETRIEVE---\")\n    question = state[\"question\"]\n\n    # Retrieval\n    documents = retriever.invoke(question)\n    return {\"documents\": documents, \"question\": question}\n\n\ndef generate(state):\n    \"\"\"\n    Generate answer\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        state (dict): New key added to state, generation, that contains LLM generation\n    \"\"\"\n    print(\"---GENERATE---\")\n    question = state[\"question\"]\n    documents = state[\"documents\"]\n\n    # RAG generation\n    generation = rag_chain.invoke({\"context\": documents, \"question\": question})\n    return {\"documents\": documents, \"question\": question, \"generation\": generation}\n\n\ndef grade_documents(state):\n    \"\"\"\n    Determines whether the retrieved documents are relevant to the question.\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        state (dict): Updates documents key with only filtered relevant documents\n    \"\"\"\n\n    print(\"---CHECK DOCUMENT RELEVANCE TO QUESTION---\")\n    question = state[\"question\"]\n    documents = state[\"documents\"]\n\n    # Score each doc\n    filtered_docs = []\n    for d in documents:\n        score = retrieval_grader.invoke(\n            {\"question\": question, \"document\": d.page_content}\n        )\n        grade = score.binary_score\n        if grade == \"yes\":\n            print(\"---GRADE: DOCUMENT RELEVANT---\")\n            filtered_docs.append(d)\n        else:\n            print(\"---GRADE: DOCUMENT NOT RELEVANT---\")\n            continue\n    return {\"documents\": filtered_docs, \"question\": question}\n\n\ndef transform_query(state):\n    \"\"\"\n    Transform the query to produce a better question.\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        state (dict): Updates question key with a re-phrased question\n    \"\"\"\n\n    print(\"---TRANSFORM QUERY---\")\n    question = state[\"question\"]\n    documents = state[\"documents\"]\n\n    # Re-write question\n    better_question = question_rewriter.invoke({\"question\": question})\n    return {\"documents\": documents, \"question\": better_question}"]
+   "source": [
+    "### Nodes\n\n\ndef retrieve(state):\n    \"\"\"\n    Retrieve documents\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        state (dict): New key added to state, documents, that contains retrieved documents\n    \"\"\"\n    print(\"---RETRIEVE---\")\n    question = state[\"question\"]\n\n    # Retrieval\n    documents = retriever.invoke(question)\n    return {\"documents\": documents, \"question\": question}\n\n\ndef generate(state):\n    \"\"\"\n    Generate answer\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        state (dict): New key added to state, generation, that contains LLM generation\n    \"\"\"\n    print(\"---GENERATE---\")\n    question = state[\"question\"]\n    documents = state[\"documents\"]\n\n    # RAG generation\n    generation = rag_chain.invoke({\"context\": documents, \"question\": question})\n    return {\"documents\": documents, \"question\": question, \"generation\": generation}\n\n\ndef grade_documents(state):\n    \"\"\"\n    Determines whether the retrieved documents are relevant to the question.\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        state (dict): Updates documents key with only filtered relevant documents\n    \"\"\"\n\n    print(\"---CHECK DOCUMENT RELEVANCE TO QUESTION---\")\n    question = state[\"question\"]\n    documents = state[\"documents\"]\n\n    # Score each doc\n    filtered_docs = []\n    for d in documents:\n        score = retrieval_grader.invoke(\n            {\"question\": question, \"document\": d.page_content}\n        )\n        grade = score.binary_score\n        if grade == \"yes\":\n            print(\"---GRADE: DOCUMENT RELEVANT---\")\n            filtered_docs.append(d)\n        else:\n            print(\"---GRADE: DOCUMENT NOT RELEVANT---\")\n            continue\n    return {\"documents\": filtered_docs, \"question\": question}\n\n\ndef transform_query(state):\n    \"\"\"\n    Transform the query to produce a better question.\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        state (dict): Updates question key with a re-phrased question\n    \"\"\"\n\n    print(\"---TRANSFORM QUERY---\")\n    question = state[\"question\"]\n    documents = state[\"documents\"]\n\n    # Re-write question\n    better_question = question_rewriter.invoke({\"question\": question})\n    return {\"documents\": documents, \"question\": better_question}"
+   ]
   },
   {
    "cell_type": "code",
@@ -278,7 +370,9 @@
    "id": "09fc91b4",
    "metadata": {},
    "outputs": [],
-   "source": ["### Edges\n\n\ndef decide_to_generate(state):\n    \"\"\"\n    Determines whether to generate an answer, or re-generate a question.\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        str: Binary decision for next node to call\n    \"\"\"\n\n    print(\"---ASSESS GRADED DOCUMENTS---\")\n    state[\"question\"]\n    filtered_documents = state[\"documents\"]\n\n    if not filtered_documents:\n        # All documents have been filtered check_relevance\n        # We will re-generate a new query\n        print(\n            \"---DECISION: ALL DOCUMENTS ARE NOT RELEVANT TO QUESTION, TRANSFORM QUERY---\"\n        )\n        return \"transform_query\"\n    else:\n        # We have relevant documents, so generate answer\n        print(\"---DECISION: GENERATE---\")\n        return \"generate\"\n\n\ndef grade_generation_v_documents_and_question(state):\n    \"\"\"\n    Determines whether the generation is grounded in the document and answers question.\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        str: Decision for next node to call\n    \"\"\"\n\n    print(\"---CHECK HALLUCINATIONS---\")\n    question = state[\"question\"]\n    documents = state[\"documents\"]\n    generation = state[\"generation\"]\n\n    score = hallucination_grader.invoke(\n        {\"documents\": documents, \"generation\": generation}\n    )\n    grade = score.binary_score\n\n    # Check hallucination\n    if grade == \"yes\":\n        print(\"---DECISION: GENERATION IS GROUNDED IN DOCUMENTS---\")\n        # Check question-answering\n        print(\"---GRADE GENERATION vs QUESTION---\")\n        score = answer_grader.invoke({\"question\": question, \"generation\": generation})\n        grade = score.binary_score\n        if grade == \"yes\":\n            print(\"---DECISION: GENERATION ADDRESSES QUESTION---\")\n            return \"useful\"\n        else:\n            print(\"---DECISION: GENERATION DOES NOT ADDRESS QUESTION---\")\n            return \"not useful\"\n    else:\n        pprint(\"---DECISION: GENERATION IS NOT GROUNDED IN DOCUMENTS, RE-TRY---\")\n        return \"not supported\""]
+   "source": [
+    "### Edges\n\n\ndef decide_to_generate(state):\n    \"\"\"\n    Determines whether to generate an answer, or re-generate a question.\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        str: Binary decision for next node to call\n    \"\"\"\n\n    print(\"---ASSESS GRADED DOCUMENTS---\")\n    state[\"question\"]\n    filtered_documents = state[\"documents\"]\n\n    if not filtered_documents:\n        # All documents have been filtered check_relevance\n        # We will re-generate a new query\n        print(\n            \"---DECISION: ALL DOCUMENTS ARE NOT RELEVANT TO QUESTION, TRANSFORM QUERY---\"\n        )\n        return \"transform_query\"\n    else:\n        # We have relevant documents, so generate answer\n        print(\"---DECISION: GENERATE---\")\n        return \"generate\"\n\n\ndef grade_generation_v_documents_and_question(state):\n    \"\"\"\n    Determines whether the generation is grounded in the document and answers question.\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        str: Decision for next node to call\n    \"\"\"\n\n    print(\"---CHECK HALLUCINATIONS---\")\n    question = state[\"question\"]\n    documents = state[\"documents\"]\n    generation = state[\"generation\"]\n\n    score = hallucination_grader.invoke(\n        {\"documents\": documents, \"generation\": generation}\n    )\n    grade = score.binary_score\n\n    # Check hallucination\n    if grade == \"yes\":\n        print(\"---DECISION: GENERATION IS GROUNDED IN DOCUMENTS---\")\n        # Check question-answering\n        print(\"---GRADE GENERATION vs QUESTION---\")\n        score = answer_grader.invoke({\"question\": question, \"generation\": generation})\n        grade = score.binary_score\n        if grade == \"yes\":\n            print(\"---DECISION: GENERATION ADDRESSES QUESTION---\")\n            return \"useful\"\n        else:\n            print(\"---DECISION: GENERATION DOES NOT ADDRESS QUESTION---\")\n            return \"not useful\"\n    else:\n        pprint(\"---DECISION: GENERATION IS NOT GROUNDED IN DOCUMENTS, RE-TRY---\")\n        return \"not supported\""
+   ]
   },
   {
    "cell_type": "markdown",
@@ -331,7 +425,9 @@
      ]
     }
    ],
-   "source": ["from pprint import pprint\n\n# Run\ninputs = {\"question\": \"Movies that star Daniel Craig\"}\nfor output in app.stream(inputs):\n    for key, value in output.items():\n        # Node\n        pprint(f\"Node '{key}':\")\n    pprint(\"\\n---\\n\")\n\n# Final generation\npprint(value[\"generation\"])"]
+   "source": [
+    "from pprint import pprint\n\n# Run\ninputs = {\"question\": \"Movies that star Daniel Craig\"}\nfor output in app.stream(inputs):\n    for key, value in output.items():\n        # Node\n        pprint(f\"Node '{key}':\")\n    pprint(\"\\n---\\n\")\n\n# Final generation\npprint(value[\"generation\"])"
+   ]
   },
   {
    "cell_type": "code",
@@ -339,7 +435,9 @@
    "id": "4138bc51-8c84-4b8a-8d24-f7f470721f6f",
    "metadata": {},
    "outputs": [],
-   "source": ["inputs = {\"question\": \"Which movies are about aliens?\"}\nfor output in app.stream(inputs):\n    for key, value in output.items():\n        # Node\n        pprint(f\"Node '{key}':\")\n    pprint(\"\\n---\\n\")\n\n# Final generation\npprint(value[\"generation\"])"]
+   "source": [
+    "inputs = {\"question\": \"Which movies are about aliens?\"}\nfor output in app.stream(inputs):\n    for key, value in output.items():\n        # Node\n        pprint(f\"Node '{key}':\")\n    pprint(\"\\n---\\n\")\n\n# Final generation\npprint(value[\"generation\"])"
+   ]
   },
   {
    "cell_type": "code",
@@ -347,7 +445,9 @@
    "id": "42369ab8-322d-434a-b5dd-2266e4cb2903",
    "metadata": {},
    "outputs": [],
-   "source": [""]
+   "source": [
+    ""
+   ]
   }
  ],
  "metadata": {

libs/checkpoint-postgres/README.md

@@ -13,6 +13,20 @@ By default `langgraph-checkpoint-postgres` installs `psycopg` (Psycopg 3) withou
 
 > [!IMPORTANT]
 > When manually creating Postgres connections and passing them to `PostgresSaver` or `AsyncPostgresSaver`, make sure to include `autocommit=True` and `row_factory=dict_row` (`from psycopg.rows import dict_row`). See a full example in this [how-to guide](https://langchain-ai.github.io/langgraph/how-tos/persistence_postgres/).
+>
+> **Why these parameters are required:**
+> - `autocommit=True`: Required for the `.setup()` method to properly commit the checkpoint tables to the database. Without this, table creation may not be persisted.
+> - `row_factory=dict_row`: Required because the PostgresSaver implementation accesses database rows using dictionary-style syntax (e.g., `row["column_name"]`). The default `tuple_row` factory returns tuples that only support index-based access (e.g., `row[0]`), which will cause `TypeError` exceptions when the checkpointer tries to access columns by name.
+>
+> **Example of incorrect usage:**
+> ```python
+> # ❌ This will fail with TypeError during checkpointer operations
+> with psycopg.connect(DB_URI) as conn:  # Missing autocommit=True and row_factory=dict_row
+>     checkpointer = PostgresSaver(conn)
+>     checkpointer.setup()  # May not persist tables properly
+>     # Any operation that reads from database will fail with:
+>     # TypeError: tuple indices must be integers or slices, not str
+> ```
 
 ```python
 from langgraph.checkpoint.postgres import PostgresSaver

libs/checkpoint-postgres/langgraph/checkpoint/postgres/__init__.py

@@ -1,8 +1,10 @@
+from __future__ import annotations
+
 import threading
 from collections import defaultdict
 from collections.abc import Iterator, Sequence
 from contextlib import contextmanager
-from typing import Any, Optional
+from typing import Any
 
 from langchain_core.runnables import RunnableConfig
 from psycopg import Capabilities, Connection, Cursor, Pipeline
@@ -21,6 +23,7 @@ from langgraph.checkpoint.base import (
 )
 from langgraph.checkpoint.postgres import _internal
 from langgraph.checkpoint.postgres.base import BasePostgresSaver
+from langgraph.checkpoint.postgres.shallow import ShallowPostgresSaver
 from langgraph.checkpoint.serde.base import SerializerProtocol
 
 Conn = _internal.Conn  # For backward compatibility
@@ -34,8 +37,8 @@ class PostgresSaver(BasePostgresSaver):
     def __init__(
         self,
         conn: _internal.Conn,
-        pipe: Optional[Pipeline] = None,
-        serde: Optional[SerializerProtocol] = None,
+        pipe: Pipeline | None = None,
+        serde: SerializerProtocol | None = None,
     ) -> None:
         super().__init__(serde=serde)
         if isinstance(conn, ConnectionPool) and pipe is not None:
@@ -52,7 +55,7 @@ class PostgresSaver(BasePostgresSaver):
     @contextmanager
     def from_conn_string(
         cls, conn_string: str, *, pipeline: bool = False
-    ) -> Iterator["PostgresSaver"]:
+    ) -> Iterator[PostgresSaver]:
         """Create a new PostgresSaver instance from a connection string.
 
         Args:
@@ -99,11 +102,11 @@ class PostgresSaver(BasePostgresSaver):
 
     def list(
         self,
-        config: Optional[RunnableConfig],
+        config: RunnableConfig | None,
         *,
-        filter: Optional[dict[str, Any]] = None,
-        before: Optional[RunnableConfig] = None,
-        limit: Optional[int] = None,
+        filter: dict[str, Any] | None = None,
+        before: RunnableConfig | None = None,
+        limit: int | None = None,
     ) -> Iterator[CheckpointTuple]:
         """List checkpoints from the database.
 
@@ -173,34 +176,9 @@ class PostgresSaver(BasePostgresSaver):
                             value["channel_values"],
                         )
             for value in values:
-                yield CheckpointTuple(
-                    {
-                        "configurable": {
-                            "thread_id": value["thread_id"],
-                            "checkpoint_ns": value["checkpoint_ns"],
-                            "checkpoint_id": value["checkpoint_id"],
-                        }
-                    },
-                    {
-                        **value["checkpoint"],
-                        "channel_values": self._load_blobs(value["channel_values"]),
-                    },
-                    value["metadata"],
-                    (
-                        {
-                            "configurable": {
-                                "thread_id": value["thread_id"],
-                                "checkpoint_ns": value["checkpoint_ns"],
-                                "checkpoint_id": value["parent_checkpoint_id"],
-                            }
-                        }
-                        if value["parent_checkpoint_id"]
-                        else None
-                    ),
-                    self._load_writes(value["pending_writes"]),
-                )
+                yield self._load_checkpoint_tuple(value)
 
-    def get_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
+    def get_tuple(self, config: RunnableConfig) -> CheckpointTuple | None:
         """Get a checkpoint tuple from the database.
 
         This method retrieves a checkpoint tuple from the Postgres database based on the
@@ -269,32 +247,7 @@ class PostgresSaver(BasePostgresSaver):
                         value["channel_values"],
                     )
 
-            return CheckpointTuple(
-                {
-                    "configurable": {
-                        "thread_id": thread_id,
-                        "checkpoint_ns": checkpoint_ns,
-                        "checkpoint_id": value["checkpoint_id"],
-                    }
-                },
-                {
-                    **value["checkpoint"],
-                    "channel_values": self._load_blobs(value["channel_values"]),
-                },
-                value["metadata"],
-                (
-                    {
-                        "configurable": {
-                            "thread_id": thread_id,
-                            "checkpoint_ns": checkpoint_ns,
-                            "checkpoint_id": value["parent_checkpoint_id"],
-                        }
-                    }
-                    if value["parent_checkpoint_id"]
-                    else None
-                ),
-                self._load_writes(value["pending_writes"]),
-            )
+            return self._load_checkpoint_tuple(value)
 
     def put(
         self,
@@ -464,5 +417,44 @@ class PostgresSaver(BasePostgresSaver):
                 with conn.cursor(binary=True, row_factory=dict_row) as cur:
                     yield cur
 
+    def _load_checkpoint_tuple(self, value: DictRow) -> CheckpointTuple:
+        """
+        Convert a database row into a CheckpointTuple object.
 
-__all__ = ["PostgresSaver", "BasePostgresSaver", "Conn"]
+        Args:
+            value: A row from the database containing checkpoint data.
+
+        Returns:
+            CheckpointTuple: A structured representation of the checkpoint,
+            including its configuration, metadata, parent checkpoint (if any),
+            and pending writes.
+        """
+        return CheckpointTuple(
+            {
+                "configurable": {
+                    "thread_id": value["thread_id"],
+                    "checkpoint_ns": value["checkpoint_ns"],
+                    "checkpoint_id": value["checkpoint_id"],
+                }
+            },
+            {
+                **value["checkpoint"],
+                "channel_values": self._load_blobs(value["channel_values"]),
+            },
+            value["metadata"],
+            (
+                {
+                    "configurable": {
+                        "thread_id": value["thread_id"],
+                        "checkpoint_ns": value["checkpoint_ns"],
+                        "checkpoint_id": value["parent_checkpoint_id"],
+                    }
+                }
+                if value["parent_checkpoint_id"]
+                else None
+            ),
+            self._load_writes(value["pending_writes"]),
+        )
+
+
+__all__ = ["PostgresSaver", "BasePostgresSaver", "ShallowPostgresSaver", "Conn"]

libs/checkpoint-postgres/langgraph/checkpoint/postgres/aio.py

@@ -1,8 +1,10 @@
+from __future__ import annotations
+
 import asyncio
 from collections import defaultdict
 from collections.abc import AsyncIterator, Iterator, Sequence
 from contextlib import asynccontextmanager
-from typing import Any, Optional
+from typing import Any
 
 from langchain_core.runnables import RunnableConfig
 from psycopg import AsyncConnection, AsyncCursor, AsyncPipeline, Capabilities
@@ -21,6 +23,7 @@ from langgraph.checkpoint.base import (
 )
 from langgraph.checkpoint.postgres import _ainternal
 from langgraph.checkpoint.postgres.base import BasePostgresSaver
+from langgraph.checkpoint.postgres.shallow import AsyncShallowPostgresSaver
 from langgraph.checkpoint.serde.base import SerializerProtocol
 
 Conn = _ainternal.Conn  # For backward compatibility
@@ -34,8 +37,8 @@ class AsyncPostgresSaver(BasePostgresSaver):
     def __init__(
         self,
         conn: _ainternal.Conn,
-        pipe: Optional[AsyncPipeline] = None,
-        serde: Optional[SerializerProtocol] = None,
+        pipe: AsyncPipeline | None = None,
+        serde: SerializerProtocol | None = None,
     ) -> None:
         super().__init__(serde=serde)
         if isinstance(conn, AsyncConnectionPool) and pipe is not None:
@@ -56,8 +59,8 @@ class AsyncPostgresSaver(BasePostgresSaver):
         conn_string: str,
         *,
         pipeline: bool = False,
-        serde: Optional[SerializerProtocol] = None,
-    ) -> AsyncIterator["AsyncPostgresSaver"]:
+        serde: SerializerProtocol | None = None,
+    ) -> AsyncIterator[AsyncPostgresSaver]:
         """Create a new AsyncPostgresSaver instance from a connection string.
 
         Args:
@@ -104,11 +107,11 @@ class AsyncPostgresSaver(BasePostgresSaver):
 
     async def alist(
         self,
-        config: Optional[RunnableConfig],
+        config: RunnableConfig | None,
         *,
-        filter: Optional[dict[str, Any]] = None,
-        before: Optional[RunnableConfig] = None,
-        limit: Optional[int] = None,
+        filter: dict[str, Any] | None = None,
+        before: RunnableConfig | None = None,
+        limit: int | None = None,
     ) -> AsyncIterator[CheckpointTuple]:
         """List checkpoints from the database asynchronously.
 
@@ -160,34 +163,9 @@ class AsyncPostgresSaver(BasePostgresSaver):
                             value["channel_values"],
                         )
             for value in values:
-                yield CheckpointTuple(
-                    {
-                        "configurable": {
-                            "thread_id": value["thread_id"],
-                            "checkpoint_ns": value["checkpoint_ns"],
-                            "checkpoint_id": value["checkpoint_id"],
-                        }
-                    },
-                    {
-                        **value["checkpoint"],
-                        "channel_values": self._load_blobs(value["channel_values"]),
-                    },
-                    value["metadata"],
-                    (
-                        {
-                            "configurable": {
-                                "thread_id": value["thread_id"],
-                                "checkpoint_ns": value["checkpoint_ns"],
-                                "checkpoint_id": value["parent_checkpoint_id"],
-                            }
-                        }
-                        if value["parent_checkpoint_id"]
-                        else None
-                    ),
-                    await asyncio.to_thread(self._load_writes, value["pending_writes"]),
-                )
+                yield await self._load_checkpoint_tuple(value)
 
-    async def aget_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
+    async def aget_tuple(self, config: RunnableConfig) -> CheckpointTuple | None:
         """Get a checkpoint tuple from the database asynchronously.
 
         This method retrieves a checkpoint tuple from the Postgres database based on the
@@ -236,32 +214,7 @@ class AsyncPostgresSaver(BasePostgresSaver):
                         value["channel_values"],
                     )
 
-            return CheckpointTuple(
-                {
-                    "configurable": {
-                        "thread_id": thread_id,
-                        "checkpoint_ns": checkpoint_ns,
-                        "checkpoint_id": value["checkpoint_id"],
-                    }
-                },
-                {
-                    **value["checkpoint"],
-                    "channel_values": self._load_blobs(value["channel_values"]),
-                },
-                value["metadata"],
-                (
-                    {
-                        "configurable": {
-                            "thread_id": thread_id,
-                            "checkpoint_ns": checkpoint_ns,
-                            "checkpoint_id": value["parent_checkpoint_id"],
-                        }
-                    }
-                    if value["parent_checkpoint_id"]
-                    else None
-                ),
-                await asyncio.to_thread(self._load_writes, value["pending_writes"]),
-            )
+            return await self._load_checkpoint_tuple(value)
 
     async def aput(
         self,
@@ -422,13 +375,52 @@ class AsyncPostgresSaver(BasePostgresSaver):
                 async with conn.cursor(binary=True, row_factory=dict_row) as cur:
                     yield cur
 
+    async def _load_checkpoint_tuple(self, value: DictRow) -> CheckpointTuple:
+        """
+        Convert a database row into a CheckpointTuple object.
+
+        Args:
+            value: A row from the database containing checkpoint data.
+
+        Returns:
+            CheckpointTuple: A structured representation of the checkpoint,
+            including its configuration, metadata, parent checkpoint (if any),
+            and pending writes.
+        """
+        return CheckpointTuple(
+            {
+                "configurable": {
+                    "thread_id": value["thread_id"],
+                    "checkpoint_ns": value["checkpoint_ns"],
+                    "checkpoint_id": value["checkpoint_id"],
+                }
+            },
+            {
+                **value["checkpoint"],
+                "channel_values": self._load_blobs(value["channel_values"]),
+            },
+            value["metadata"],
+            (
+                {
+                    "configurable": {
+                        "thread_id": value["thread_id"],
+                        "checkpoint_ns": value["checkpoint_ns"],
+                        "checkpoint_id": value["parent_checkpoint_id"],
+                    }
+                }
+                if value["parent_checkpoint_id"]
+                else None
+            ),
+            await asyncio.to_thread(self._load_writes, value["pending_writes"]),
+        )
+
     def list(
         self,
-        config: Optional[RunnableConfig],
+        config: RunnableConfig | None,
         *,
-        filter: Optional[dict[str, Any]] = None,
-        before: Optional[RunnableConfig] = None,
-        limit: Optional[int] = None,
+        filter: dict[str, Any] | None = None,
+        before: RunnableConfig | None = None,
+        limit: int | None = None,
     ) -> Iterator[CheckpointTuple]:
         """List checkpoints from the database.
 
@@ -466,7 +458,7 @@ class AsyncPostgresSaver(BasePostgresSaver):
             except StopAsyncIteration:
                 break
 
-    def get_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
+    def get_tuple(self, config: RunnableConfig) -> CheckpointTuple | None:
         """Get a checkpoint tuple from the database.
 
         This method retrieves a checkpoint tuple from the Postgres database based on the
@@ -568,4 +560,4 @@ class AsyncPostgresSaver(BasePostgresSaver):
         ).result()
 
 
-__all__ = ["AsyncPostgresSaver", "Conn"]
+__all__ = ["AsyncPostgresSaver", "AsyncShallowPostgresSaver", "Conn"]

libs/checkpoint-postgres/langgraph/checkpoint/postgres/base.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import random
 from collections.abc import Sequence
 from typing import Any, Optional, cast
@@ -166,7 +168,7 @@ class BasePostgresSaver(BaseCheckpointSaver[str]):
         checkpoint["channel_versions"][TASKS] = (
             max(checkpoint["channel_versions"].values())
             if checkpoint["channel_versions"]
-            else self.get_next_version(None)
+            else self.get_next_version(None, None)
         )
 
     def _load_blobs(
@@ -186,7 +188,7 @@ class BasePostgresSaver(BaseCheckpointSaver[str]):
         checkpoint_ns: str,
         values: dict[str, Any],
         versions: ChannelVersions,
-    ) -> list[tuple[str, str, str, str, str, Optional[bytes]]]:
+    ) -> list[tuple[str, str, str, str, str, bytes | None]]:
         if not versions:
             return []
 
@@ -244,7 +246,7 @@ class BasePostgresSaver(BaseCheckpointSaver[str]):
             for idx, (channel, value) in enumerate(writes)
         ]
 
-    def get_next_version(self, current: Optional[str]) -> str:
+    def get_next_version(self, current: str | None, channel: None) -> str:
         if current is None:
             current_v = 0
         elif isinstance(current, int):
@@ -257,9 +259,9 @@ class BasePostgresSaver(BaseCheckpointSaver[str]):
 
     def _search_where(
         self,
-        config: Optional[RunnableConfig],
+        config: RunnableConfig | None,
         filter: MetadataInput,
-        before: Optional[RunnableConfig] = None,
+        before: RunnableConfig | None = None,
     ) -> tuple[str, list[Any]]:
         """Return WHERE clause predicates for alist() given config, filter, before.
 

libs/checkpoint-postgres/langgraph/checkpoint/postgres/shallow.py

@@ -0,0 +1,959 @@
+import asyncio
+import threading
+import warnings
+from collections.abc import AsyncIterator, Iterator, Sequence
+from contextlib import asynccontextmanager, contextmanager
+from typing import Any, Optional
+
+from langchain_core.runnables import RunnableConfig
+from psycopg import (
+    AsyncConnection,
+    AsyncCursor,
+    AsyncPipeline,
+    Capabilities,
+    Connection,
+    Cursor,
+    Pipeline,
+)
+from psycopg.rows import DictRow, dict_row
+from psycopg.types.json import Jsonb
+from psycopg_pool import AsyncConnectionPool, ConnectionPool
+
+from langgraph.checkpoint.base import (
+    WRITES_IDX_MAP,
+    ChannelVersions,
+    Checkpoint,
+    CheckpointMetadata,
+    CheckpointTuple,
+    get_checkpoint_metadata,
+)
+from langgraph.checkpoint.postgres import _ainternal, _internal
+from langgraph.checkpoint.postgres.base import BasePostgresSaver
+from langgraph.checkpoint.serde.base import SerializerProtocol
+from langgraph.checkpoint.serde.types import TASKS
+
+"""
+To add a new migration, add a new string to the MIGRATIONS list.
+The position of the migration in the list is the version number.
+"""
+MIGRATIONS = [
+    """CREATE TABLE IF NOT EXISTS checkpoint_migrations (
+    v INTEGER PRIMARY KEY
+);""",
+    """CREATE TABLE IF NOT EXISTS checkpoints (
+    thread_id TEXT NOT NULL,
+    checkpoint_ns TEXT NOT NULL DEFAULT '',
+    type TEXT,
+    checkpoint JSONB NOT NULL,
+    metadata JSONB NOT NULL DEFAULT '{}',
+    PRIMARY KEY (thread_id, checkpoint_ns)
+);""",
+    """CREATE TABLE IF NOT EXISTS checkpoint_blobs (
+    thread_id TEXT NOT NULL,
+    checkpoint_ns TEXT NOT NULL DEFAULT '',
+    channel TEXT NOT NULL,
+    type TEXT NOT NULL,
+    blob BYTEA,
+    PRIMARY KEY (thread_id, checkpoint_ns, channel)
+);""",
+    """CREATE TABLE IF NOT EXISTS checkpoint_writes (
+    thread_id TEXT NOT NULL,
+    checkpoint_ns TEXT NOT NULL DEFAULT '',
+    checkpoint_id TEXT NOT NULL,
+    task_id TEXT NOT NULL,
+    idx INTEGER NOT NULL,
+    channel TEXT NOT NULL,
+    type TEXT,
+    blob BYTEA NOT NULL,
+    PRIMARY KEY (thread_id, checkpoint_ns, checkpoint_id, task_id, idx)
+);""",
+    """
+    CREATE INDEX CONCURRENTLY IF NOT EXISTS checkpoints_thread_id_idx ON checkpoints(thread_id);
+    """,
+    """
+    CREATE INDEX CONCURRENTLY IF NOT EXISTS checkpoint_blobs_thread_id_idx ON checkpoint_blobs(thread_id);
+    """,
+    """
+    CREATE INDEX CONCURRENTLY IF NOT EXISTS checkpoint_writes_thread_id_idx ON checkpoint_writes(thread_id);
+    """,
+    """
+    ALTER TABLE checkpoint_writes ADD COLUMN task_path TEXT NOT NULL DEFAULT '';
+    """,
+]
+
+SELECT_SQL = f"""
+select
+    thread_id,
+    checkpoint,
+    checkpoint_ns,
+    metadata,
+    (
+        select array_agg(array[bl.channel::bytea, bl.type::bytea, bl.blob])
+        from jsonb_each_text(checkpoint -> 'channel_versions')
+        inner join checkpoint_blobs bl
+            on bl.thread_id = checkpoints.thread_id
+            and bl.checkpoint_ns = checkpoints.checkpoint_ns
+            and bl.channel = jsonb_each_text.key
+    ) as channel_values,
+    (
+        select
+        array_agg(array[cw.task_id::text::bytea, cw.channel::bytea, cw.type::bytea, cw.blob] order by cw.task_id, cw.idx)
+        from checkpoint_writes cw
+        where cw.thread_id = checkpoints.thread_id
+            and cw.checkpoint_ns = checkpoints.checkpoint_ns
+            and cw.checkpoint_id = (checkpoint->>'id')
+    ) as pending_writes,
+    (
+        select array_agg(array[cw.type::bytea, cw.blob] order by cw.task_path, cw.task_id, cw.idx)
+        from checkpoint_writes cw
+        where cw.thread_id = checkpoints.thread_id
+            and cw.checkpoint_ns = checkpoints.checkpoint_ns
+            and cw.channel = '{TASKS}'
+    ) as pending_sends
+from checkpoints """
+
+UPSERT_CHECKPOINT_BLOBS_SQL = """
+    INSERT INTO checkpoint_blobs (thread_id, checkpoint_ns, channel, type, blob)
+    VALUES (%s, %s, %s, %s, %s)
+    ON CONFLICT (thread_id, checkpoint_ns, channel) DO UPDATE SET
+        type = EXCLUDED.type,
+        blob = EXCLUDED.blob;
+"""
+
+UPSERT_CHECKPOINTS_SQL = """
+    INSERT INTO checkpoints (thread_id, checkpoint_ns, checkpoint, metadata)
+    VALUES (%s, %s, %s, %s)
+    ON CONFLICT (thread_id, checkpoint_ns)
+    DO UPDATE SET
+        checkpoint = EXCLUDED.checkpoint,
+        metadata = EXCLUDED.metadata;
+"""
+
+UPSERT_CHECKPOINT_WRITES_SQL = """
+    INSERT INTO checkpoint_writes (thread_id, checkpoint_ns, checkpoint_id, task_id, task_path, idx, channel, type, blob)
+    VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s)
+    ON CONFLICT (thread_id, checkpoint_ns, checkpoint_id, task_id, idx) DO UPDATE SET
+        channel = EXCLUDED.channel,
+        type = EXCLUDED.type,
+        blob = EXCLUDED.blob;
+"""
+
+INSERT_CHECKPOINT_WRITES_SQL = """
+    INSERT INTO checkpoint_writes (thread_id, checkpoint_ns, checkpoint_id, task_id, task_path, idx, channel, type, blob)
+    VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s)
+    ON CONFLICT (thread_id, checkpoint_ns, checkpoint_id, task_id, idx) DO NOTHING
+"""
+
+
+def _dump_blobs(
+    serde: SerializerProtocol,
+    thread_id: str,
+    checkpoint_ns: str,
+    values: dict[str, Any],
+    versions: ChannelVersions,
+) -> list[tuple[str, str, str, str, Optional[bytes]]]:
+    if not versions:
+        return []
+
+    return [
+        (
+            thread_id,
+            checkpoint_ns,
+            k,
+            *(serde.dumps_typed(values[k]) if k in values else ("empty", None)),
+        )
+        for k in versions
+    ]
+
+
+class ShallowPostgresSaver(BasePostgresSaver):
+    """A checkpoint saver that uses Postgres to store checkpoints.
+
+    This checkpointer ONLY stores the most recent checkpoint and does NOT retain any history.
+    It is meant to be a light-weight drop-in replacement for the PostgresSaver that
+    supports most of the LangGraph persistence functionality with the exception of time travel.
+    """
+
+    SELECT_SQL = SELECT_SQL
+    MIGRATIONS = MIGRATIONS
+    UPSERT_CHECKPOINT_BLOBS_SQL = UPSERT_CHECKPOINT_BLOBS_SQL
+    UPSERT_CHECKPOINTS_SQL = UPSERT_CHECKPOINTS_SQL
+    UPSERT_CHECKPOINT_WRITES_SQL = UPSERT_CHECKPOINT_WRITES_SQL
+    INSERT_CHECKPOINT_WRITES_SQL = INSERT_CHECKPOINT_WRITES_SQL
+
+    lock: threading.Lock
+
+    def __init__(
+        self,
+        conn: _internal.Conn,
+        pipe: Optional[Pipeline] = None,
+        serde: Optional[SerializerProtocol] = None,
+    ) -> None:
+        warnings.warn(
+            "ShallowPostgresSaver is deprecated as of version 2.0.20 and will be removed in 3.0.0. "
+            "Use PostgresSaver instead, and invoke the graph with `graph.invoke(..., checkpoint_during=False)`.",
+            DeprecationWarning,
+            stacklevel=2,
+        )
+        super().__init__(serde=serde)
+        if isinstance(conn, ConnectionPool) and pipe is not None:
+            raise ValueError(
+                "Pipeline should be used only with a single Connection, not ConnectionPool."
+            )
+
+        self.conn = conn
+        self.pipe = pipe
+        self.lock = threading.Lock()
+        self.supports_pipeline = Capabilities().has_pipeline()
+
+    @classmethod
+    @contextmanager
+    def from_conn_string(
+        cls, conn_string: str, *, pipeline: bool = False
+    ) -> Iterator["ShallowPostgresSaver"]:
+        """Create a new ShallowPostgresSaver instance from a connection string.
+
+        Args:
+            conn_string: The Postgres connection info string.
+            pipeline: whether to use Pipeline
+
+        Returns:
+            ShallowPostgresSaver: A new ShallowPostgresSaver instance.
+        """
+        with Connection.connect(
+            conn_string, autocommit=True, prepare_threshold=0, row_factory=dict_row
+        ) as conn:
+            if pipeline:
+                with conn.pipeline() as pipe:
+                    yield cls(conn, pipe)
+            else:
+                yield cls(conn)
+
+    def setup(self) -> None:
+        """Set up the checkpoint database asynchronously.
+
+        This method creates the necessary tables in the Postgres database if they don't
+        already exist and runs database migrations. It MUST be called directly by the user
+        the first time checkpointer is used.
+        """
+        with self._cursor() as cur:
+            cur.execute(self.MIGRATIONS[0])
+            results = cur.execute(
+                "SELECT v FROM checkpoint_migrations ORDER BY v DESC LIMIT 1"
+            )
+            row = results.fetchone()
+            if row is None:
+                version = -1
+            else:
+                version = row["v"]
+            for v, migration in zip(
+                range(version + 1, len(self.MIGRATIONS)),
+                self.MIGRATIONS[version + 1 :],
+            ):
+                cur.execute(migration)
+                cur.execute(f"INSERT INTO checkpoint_migrations (v) VALUES ({v})")
+        if self.pipe:
+            self.pipe.sync()
+
+    def list(
+        self,
+        config: Optional[RunnableConfig],
+        *,
+        filter: Optional[dict[str, Any]] = None,
+        before: Optional[RunnableConfig] = None,
+        limit: Optional[int] = None,
+    ) -> Iterator[CheckpointTuple]:
+        """List checkpoints from the database.
+
+        This method retrieves a list of checkpoint tuples from the Postgres database based
+        on the provided config. For ShallowPostgresSaver, this method returns a list with
+        ONLY the most recent checkpoint.
+        """
+        where, args = self._search_where(config, filter, before)
+        query = self.SELECT_SQL + where
+        if limit:
+            query += f" LIMIT {limit}"
+        with self._cursor() as cur:
+            cur.execute(self.SELECT_SQL + where, args, binary=True)
+            for value in cur:
+                checkpoint: Checkpoint = {
+                    **value["checkpoint"],
+                    "channel_values": self._load_blobs(value["channel_values"]),
+                    "pending_sends": [
+                        self.serde.loads_typed((t.decode(), v))
+                        for t, v in value["pending_sends"]
+                    ]
+                    if value["pending_sends"]
+                    else [],
+                }
+                yield CheckpointTuple(
+                    config={
+                        "configurable": {
+                            "thread_id": value["thread_id"],
+                            "checkpoint_ns": value["checkpoint_ns"],
+                            "checkpoint_id": checkpoint["id"],
+                        }
+                    },
+                    checkpoint=checkpoint,
+                    metadata=value["metadata"],
+                    pending_writes=self._load_writes(value["pending_writes"]),
+                )
+
+    def get_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
+        """Get a checkpoint tuple from the database.
+
+        This method retrieves a checkpoint tuple from the Postgres database based on the
+        provided config (matching the thread ID in the config).
+
+        Args:
+            config: The config to use for retrieving the checkpoint.
+
+        Returns:
+            Optional[CheckpointTuple]: The retrieved checkpoint tuple, or None if no matching checkpoint was found.
+
+        Examples:
+
+            Basic:
+            >>> config = {"configurable": {"thread_id": "1"}}
+            >>> checkpoint_tuple = memory.get_tuple(config)
+            >>> print(checkpoint_tuple)
+            CheckpointTuple(...)
+
+            With timestamp:
+
+            >>> config = {
+            ...    "configurable": {
+            ...        "thread_id": "1",
+            ...        "checkpoint_ns": "",
+            ...        "checkpoint_id": "1ef4f797-8335-6428-8001-8a1503f9b875",
+            ...    }
+            ... }
+            >>> checkpoint_tuple = memory.get_tuple(config)
+            >>> print(checkpoint_tuple)
+            CheckpointTuple(...)
+        """  # noqa
+        thread_id = config["configurable"]["thread_id"]
+        checkpoint_ns = config["configurable"].get("checkpoint_ns", "")
+        args = (thread_id, checkpoint_ns)
+        where = "WHERE thread_id = %s AND checkpoint_ns = %s"
+
+        with self._cursor() as cur:
+            cur.execute(
+                self.SELECT_SQL + where,
+                args,
+                binary=True,
+            )
+
+            for value in cur:
+                checkpoint: Checkpoint = {
+                    **value["checkpoint"],
+                    "channel_values": self._load_blobs(value["channel_values"]),
+                    "pending_sends": [
+                        self.serde.loads_typed((t.decode(), v))
+                        for t, v in value["pending_sends"]
+                    ]
+                    if value["pending_sends"]
+                    else [],
+                }
+                return CheckpointTuple(
+                    config={
+                        "configurable": {
+                            "thread_id": thread_id,
+                            "checkpoint_ns": checkpoint_ns,
+                            "checkpoint_id": checkpoint["id"],
+                        }
+                    },
+                    checkpoint=checkpoint,
+                    metadata=value["metadata"],
+                    pending_writes=self._load_writes(value["pending_writes"]),
+                )
+
+    def put(
+        self,
+        config: RunnableConfig,
+        checkpoint: Checkpoint,
+        metadata: CheckpointMetadata,
+        new_versions: ChannelVersions,
+    ) -> RunnableConfig:
+        """Save a checkpoint to the database.
+
+        This method saves a checkpoint to the Postgres database. The checkpoint is associated
+        with the provided config. For ShallowPostgresSaver, this method saves ONLY the most recent
+        checkpoint and overwrites a previous checkpoint, if it exists.
+
+        Args:
+            config: The config to associate with the checkpoint.
+            checkpoint: The checkpoint to save.
+            metadata: Additional metadata to save with the checkpoint.
+            new_versions: New channel versions as of this write.
+
+        Returns:
+            RunnableConfig: Updated configuration after storing the checkpoint.
+
+        Examples:
+
+            >>> from langgraph.checkpoint.postgres import ShallowPostgresSaver
+            >>> DB_URI = "postgres://postgres:postgres@localhost:5432/postgres?sslmode=disable"
+            >>> with ShallowPostgresSaver.from_conn_string(DB_URI) as memory:
+            >>>     config = {"configurable": {"thread_id": "1", "checkpoint_ns": ""}}
+            >>>     checkpoint = {"ts": "2024-05-04T06:32:42.235444+00:00", "id": "1ef4f797-8335-6428-8001-8a1503f9b875", "channel_values": {"key": "value"}}
+            >>>     saved_config = memory.put(config, checkpoint, {"source": "input", "step": 1, "writes": {"key": "value"}}, {})
+            >>> print(saved_config)
+            {'configurable': {'thread_id': '1', 'checkpoint_ns': '', 'checkpoint_id': '1ef4f797-8335-6428-8001-8a1503f9b875'}}
+        """
+        configurable = config["configurable"].copy()
+        thread_id = configurable.pop("thread_id")
+        checkpoint_ns = configurable.pop("checkpoint_ns")
+
+        copy = checkpoint.copy()
+        next_config = {
+            "configurable": {
+                "thread_id": thread_id,
+                "checkpoint_ns": checkpoint_ns,
+                "checkpoint_id": checkpoint["id"],
+            }
+        }
+
+        with self._cursor(pipeline=True) as cur:
+            cur.execute(
+                """DELETE FROM checkpoint_writes
+                WHERE thread_id = %s AND checkpoint_ns = %s AND checkpoint_id NOT IN (%s, %s)""",
+                (
+                    thread_id,
+                    checkpoint_ns,
+                    checkpoint["id"],
+                    configurable.get("checkpoint_id", ""),
+                ),
+            )
+            cur.executemany(
+                self.UPSERT_CHECKPOINT_BLOBS_SQL,
+                _dump_blobs(
+                    self.serde,
+                    thread_id,
+                    checkpoint_ns,
+                    copy.pop("channel_values"),  # type: ignore[misc]
+                    new_versions,
+                ),
+            )
+            cur.execute(
+                self.UPSERT_CHECKPOINTS_SQL,
+                (
+                    thread_id,
+                    checkpoint_ns,
+                    Jsonb(copy),
+                    Jsonb(get_checkpoint_metadata(config, metadata)),
+                ),
+            )
+        return next_config
+
+    def put_writes(
+        self,
+        config: RunnableConfig,
+        writes: Sequence[tuple[str, Any]],
+        task_id: str,
+        task_path: str = "",
+    ) -> None:
+        """Store intermediate writes linked to a checkpoint.
+
+        This method saves intermediate writes associated with a checkpoint to the Postgres database.
+
+        Args:
+            config: Configuration of the related checkpoint.
+            writes: List of writes to store.
+            task_id: Identifier for the task creating the writes.
+        """
+        query = (
+            self.UPSERT_CHECKPOINT_WRITES_SQL
+            if all(w[0] in WRITES_IDX_MAP for w in writes)
+            else self.INSERT_CHECKPOINT_WRITES_SQL
+        )
+        with self._cursor(pipeline=True) as cur:
+            cur.executemany(
+                query,
+                self._dump_writes(
+                    config["configurable"]["thread_id"],
+                    config["configurable"]["checkpoint_ns"],
+                    config["configurable"]["checkpoint_id"],
+                    task_id,
+                    task_path,
+                    writes,
+                ),
+            )
+
+    @contextmanager
+    def _cursor(self, *, pipeline: bool = False) -> Iterator[Cursor[DictRow]]:
+        """Create a database cursor as a context manager.
+
+        Args:
+            pipeline: whether to use pipeline for the DB operations inside the context manager.
+                Will be applied regardless of whether the ShallowPostgresSaver instance was initialized with a pipeline.
+                If pipeline mode is not supported, will fall back to using transaction context manager.
+        """
+        with _internal.get_connection(self.conn) as conn:
+            if self.pipe:
+                # a connection in pipeline mode can be used concurrently
+                # in multiple threads/coroutines, but only one cursor can be
+                # used at a time
+                try:
+                    with conn.cursor(binary=True, row_factory=dict_row) as cur:
+                        yield cur
+                finally:
+                    if pipeline:
+                        self.pipe.sync()
+            elif pipeline:
+                # a connection not in pipeline mode can only be used by one
+                # thread/coroutine at a time, so we acquire a lock
+                if self.supports_pipeline:
+                    with (
+                        self.lock,
+                        conn.pipeline(),
+                        conn.cursor(binary=True, row_factory=dict_row) as cur,
+                    ):
+                        yield cur
+                else:
+                    # Use connection's transaction context manager when pipeline mode not supported
+                    with (
+                        self.lock,
+                        conn.transaction(),
+                        conn.cursor(binary=True, row_factory=dict_row) as cur,
+                    ):
+                        yield cur
+            else:
+                with self.lock, conn.cursor(binary=True, row_factory=dict_row) as cur:
+                    yield cur
+
+
+class AsyncShallowPostgresSaver(BasePostgresSaver):
+    """A checkpoint saver that uses Postgres to store checkpoints asynchronously.
+
+    This checkpointer ONLY stores the most recent checkpoint and does NOT retain any history.
+    It is meant to be a light-weight drop-in replacement for the AsyncPostgresSaver that
+    supports most of the LangGraph persistence functionality with the exception of time travel.
+    """
+
+    SELECT_SQL = SELECT_SQL
+    MIGRATIONS = MIGRATIONS
+    UPSERT_CHECKPOINT_BLOBS_SQL = UPSERT_CHECKPOINT_BLOBS_SQL
+    UPSERT_CHECKPOINTS_SQL = UPSERT_CHECKPOINTS_SQL
+    UPSERT_CHECKPOINT_WRITES_SQL = UPSERT_CHECKPOINT_WRITES_SQL
+    INSERT_CHECKPOINT_WRITES_SQL = INSERT_CHECKPOINT_WRITES_SQL
+    lock: asyncio.Lock
+
+    def __init__(
+        self,
+        conn: _ainternal.Conn,
+        pipe: Optional[AsyncPipeline] = None,
+        serde: Optional[SerializerProtocol] = None,
+    ) -> None:
+        warnings.warn(
+            "AsyncShallowPostgresSaver is deprecated as of version 2.0.20 and will be removed in 3.0.0. "
+            "Use AsyncPostgresSaver instead, and invoke the graph with `await graph.ainvoke(..., checkpoint_during=False)`.",
+            DeprecationWarning,
+            stacklevel=2,
+        )
+        super().__init__(serde=serde)
+        if isinstance(conn, AsyncConnectionPool) and pipe is not None:
+            raise ValueError(
+                "Pipeline should be used only with a single AsyncConnection, not AsyncConnectionPool."
+            )
+
+        self.conn = conn
+        self.pipe = pipe
+        self.lock = asyncio.Lock()
+        self.loop = asyncio.get_running_loop()
+        self.supports_pipeline = Capabilities().has_pipeline()
+
+    @classmethod
+    @asynccontextmanager
+    async def from_conn_string(
+        cls,
+        conn_string: str,
+        *,
+        pipeline: bool = False,
+        serde: Optional[SerializerProtocol] = None,
+    ) -> AsyncIterator["AsyncShallowPostgresSaver"]:
+        """Create a new AsyncShallowPostgresSaver instance from a connection string.
+
+        Args:
+            conn_string: The Postgres connection info string.
+            pipeline: whether to use AsyncPipeline
+
+        Returns:
+            AsyncShallowPostgresSaver: A new AsyncShallowPostgresSaver instance.
+        """
+        async with await AsyncConnection.connect(
+            conn_string, autocommit=True, prepare_threshold=0, row_factory=dict_row
+        ) as conn:
+            if pipeline:
+                async with conn.pipeline() as pipe:
+                    yield cls(conn=conn, pipe=pipe, serde=serde)
+            else:
+                yield cls(conn=conn, serde=serde)
+
+    async def setup(self) -> None:
+        """Set up the checkpoint database asynchronously.
+
+        This method creates the necessary tables in the Postgres database if they don't
+        already exist and runs database migrations. It MUST be called directly by the user
+        the first time checkpointer is used.
+        """
+        async with self._cursor() as cur:
+            await cur.execute(self.MIGRATIONS[0])
+            results = await cur.execute(
+                "SELECT v FROM checkpoint_migrations ORDER BY v DESC LIMIT 1"
+            )
+            row = await results.fetchone()
+            if row is None:
+                version = -1
+            else:
+                version = row["v"]
+            for v, migration in zip(
+                range(version + 1, len(self.MIGRATIONS)),
+                self.MIGRATIONS[version + 1 :],
+            ):
+                await cur.execute(migration)
+                await cur.execute(f"INSERT INTO checkpoint_migrations (v) VALUES ({v})")
+        if self.pipe:
+            await self.pipe.sync()
+
+    async def alist(
+        self,
+        config: Optional[RunnableConfig],
+        *,
+        filter: Optional[dict[str, Any]] = None,
+        before: Optional[RunnableConfig] = None,
+        limit: Optional[int] = None,
+    ) -> AsyncIterator[CheckpointTuple]:
+        """List checkpoints from the database asynchronously.
+
+        This method retrieves a list of checkpoint tuples from the Postgres database based
+        on the provided config. For ShallowPostgresSaver, this method returns a list with
+        ONLY the most recent checkpoint.
+        """
+        where, args = self._search_where(config, filter, before)
+        query = self.SELECT_SQL + where
+        if limit:
+            query += f" LIMIT {limit}"
+        async with self._cursor() as cur:
+            await cur.execute(self.SELECT_SQL + where, args, binary=True)
+            async for value in cur:
+                checkpoint: Checkpoint = {
+                    **value["checkpoint"],
+                    "channel_values": self._load_blobs(value["channel_values"]),
+                    "pending_sends": [
+                        self.serde.loads_typed((t.decode(), v))
+                        for t, v in value["pending_sends"]
+                    ]
+                    if value["pending_sends"]
+                    else [],
+                }
+                yield CheckpointTuple(
+                    config={
+                        "configurable": {
+                            "thread_id": value["thread_id"],
+                            "checkpoint_ns": value["checkpoint_ns"],
+                            "checkpoint_id": checkpoint["id"],
+                        }
+                    },
+                    checkpoint=checkpoint,
+                    metadata=value["metadata"],
+                    pending_writes=await asyncio.to_thread(
+                        self._load_writes, value["pending_writes"]
+                    ),
+                )
+
+    async def aget_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
+        """Get a checkpoint tuple from the database asynchronously.
+
+        This method retrieves a checkpoint tuple from the Postgres database based on the
+        provided config (matching the thread ID in the config).
+
+        Args:
+            config: The config to use for retrieving the checkpoint.
+
+        Returns:
+            Optional[CheckpointTuple]: The retrieved checkpoint tuple, or None if no matching checkpoint was found.
+        """
+        thread_id = config["configurable"]["thread_id"]
+        checkpoint_ns = config["configurable"].get("checkpoint_ns", "")
+        args = (thread_id, checkpoint_ns)
+        where = "WHERE thread_id = %s AND checkpoint_ns = %s"
+
+        async with self._cursor() as cur:
+            await cur.execute(
+                self.SELECT_SQL + where,
+                args,
+                binary=True,
+            )
+
+            async for value in cur:
+                checkpoint: Checkpoint = {
+                    **value["checkpoint"],
+                    "channel_values": self._load_blobs(value["channel_values"]),
+                    "pending_sends": [
+                        self.serde.loads_typed((t.decode(), v))
+                        for t, v in value["pending_sends"]
+                    ]
+                    if value["pending_sends"]
+                    else [],
+                }
+                return CheckpointTuple(
+                    config={
+                        "configurable": {
+                            "thread_id": thread_id,
+                            "checkpoint_ns": checkpoint_ns,
+                            "checkpoint_id": checkpoint["id"],
+                        }
+                    },
+                    checkpoint=checkpoint,
+                    metadata=value["metadata"],
+                    pending_writes=await asyncio.to_thread(
+                        self._load_writes, value["pending_writes"]
+                    ),
+                )
+
+    async def aput(
+        self,
+        config: RunnableConfig,
+        checkpoint: Checkpoint,
+        metadata: CheckpointMetadata,
+        new_versions: ChannelVersions,
+    ) -> RunnableConfig:
+        """Save a checkpoint to the database asynchronously.
+
+        This method saves a checkpoint to the Postgres database. The checkpoint is associated
+        with the provided config. For AsyncShallowPostgresSaver, this method saves ONLY the most recent
+        checkpoint and overwrites a previous checkpoint, if it exists.
+
+        Args:
+            config: The config to associate with the checkpoint.
+            checkpoint: The checkpoint to save.
+            metadata: Additional metadata to save with the checkpoint.
+            new_versions: New channel versions as of this write.
+
+        Returns:
+            RunnableConfig: Updated configuration after storing the checkpoint.
+        """
+        configurable = config["configurable"].copy()
+        thread_id = configurable.pop("thread_id")
+        checkpoint_ns = configurable.pop("checkpoint_ns")
+
+        copy = checkpoint.copy()
+        next_config = {
+            "configurable": {
+                "thread_id": thread_id,
+                "checkpoint_ns": checkpoint_ns,
+                "checkpoint_id": checkpoint["id"],
+            }
+        }
+
+        async with self._cursor(pipeline=True) as cur:
+            await cur.execute(
+                """DELETE FROM checkpoint_writes
+                WHERE thread_id = %s AND checkpoint_ns = %s AND checkpoint_id NOT IN (%s, %s)""",
+                (
+                    thread_id,
+                    checkpoint_ns,
+                    checkpoint["id"],
+                    configurable.get("checkpoint_id", ""),
+                ),
+            )
+            await cur.executemany(
+                self.UPSERT_CHECKPOINT_BLOBS_SQL,
+                _dump_blobs(
+                    self.serde,
+                    thread_id,
+                    checkpoint_ns,
+                    copy.pop("channel_values"),  # type: ignore[misc]
+                    new_versions,
+                ),
+            )
+            await cur.execute(
+                self.UPSERT_CHECKPOINTS_SQL,
+                (
+                    thread_id,
+                    checkpoint_ns,
+                    Jsonb(copy),
+                    Jsonb(get_checkpoint_metadata(config, metadata)),
+                ),
+            )
+        return next_config
+
+    async def aput_writes(
+        self,
+        config: RunnableConfig,
+        writes: Sequence[tuple[str, Any]],
+        task_id: str,
+        task_path: str = "",
+    ) -> None:
+        """Store intermediate writes linked to a checkpoint asynchronously.
+
+        This method saves intermediate writes associated with a checkpoint to the database.
+
+        Args:
+            config: Configuration of the related checkpoint.
+            writes: List of writes to store, each as (channel, value) pair.
+            task_id: Identifier for the task creating the writes.
+        """
+        query = (
+            self.UPSERT_CHECKPOINT_WRITES_SQL
+            if all(w[0] in WRITES_IDX_MAP for w in writes)
+            else self.INSERT_CHECKPOINT_WRITES_SQL
+        )
+        params = await asyncio.to_thread(
+            self._dump_writes,
+            config["configurable"]["thread_id"],
+            config["configurable"]["checkpoint_ns"],
+            config["configurable"]["checkpoint_id"],
+            task_id,
+            task_path,
+            writes,
+        )
+        async with self._cursor(pipeline=True) as cur:
+            await cur.executemany(query, params)
+
+    @asynccontextmanager
+    async def _cursor(
+        self, *, pipeline: bool = False
+    ) -> AsyncIterator[AsyncCursor[DictRow]]:
+        """Create a database cursor as a context manager.
+
+        Args:
+            pipeline: whether to use pipeline for the DB operations inside the context manager.
+                Will be applied regardless of whether the AsyncShallowPostgresSaver instance was initialized with a pipeline.
+                If pipeline mode is not supported, will fall back to using transaction context manager.
+        """
+        async with _ainternal.get_connection(self.conn) as conn:
+            if self.pipe:
+                # a connection in pipeline mode can be used concurrently
+                # in multiple threads/coroutines, but only one cursor can be
+                # used at a time
+                try:
+                    async with conn.cursor(binary=True, row_factory=dict_row) as cur:
+                        yield cur
+                finally:
+                    if pipeline:
+                        await self.pipe.sync()
+            elif pipeline:
+                # a connection not in pipeline mode can only be used by one
+                # thread/coroutine at a time, so we acquire a lock
+                if self.supports_pipeline:
+                    async with (
+                        self.lock,
+                        conn.pipeline(),
+                        conn.cursor(binary=True, row_factory=dict_row) as cur,
+                    ):
+                        yield cur
+                else:
+                    # Use connection's transaction context manager when pipeline mode not supported
+                    async with (
+                        self.lock,
+                        conn.transaction(),
+                        conn.cursor(binary=True, row_factory=dict_row) as cur,
+                    ):
+                        yield cur
+            else:
+                async with (
+                    self.lock,
+                    conn.cursor(binary=True, row_factory=dict_row) as cur,
+                ):
+                    yield cur
+
+    def list(
+        self,
+        config: Optional[RunnableConfig],
+        *,
+        filter: Optional[dict[str, Any]] = None,
+        before: Optional[RunnableConfig] = None,
+        limit: Optional[int] = None,
+    ) -> Iterator[CheckpointTuple]:
+        """List checkpoints from the database.
+
+        This method retrieves a list of checkpoint tuples from the Postgres database based
+        on the provided config. For ShallowPostgresSaver, this method returns a list with
+        ONLY the most recent checkpoint.
+        """
+        aiter_ = self.alist(config, filter=filter, before=before, limit=limit)
+        while True:
+            try:
+                yield asyncio.run_coroutine_threadsafe(
+                    anext(aiter_),  # noqa: F821
+                    self.loop,
+                ).result()
+            except StopAsyncIteration:
+                break
+
+    def get_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
+        """Get a checkpoint tuple from the database.
+
+        This method retrieves a checkpoint tuple from the Postgres database based on the
+        provided config (matching the thread ID in the config).
+
+        Args:
+            config: The config to use for retrieving the checkpoint.
+
+        Returns:
+            Optional[CheckpointTuple]: The retrieved checkpoint tuple, or None if no matching checkpoint was found.
+        """
+        try:
+            # check if we are in the main thread, only bg threads can block
+            # we don't check in other methods to avoid the overhead
+            if asyncio.get_running_loop() is self.loop:
+                raise asyncio.InvalidStateError(
+                    "Synchronous calls to AsyncShallowPostgresSaver are only allowed from a "
+                    "different thread. From the main thread, use the async interface."
+                    "For example, use `await checkpointer.aget_tuple(...)` or `await "
+                    "graph.ainvoke(...)`."
+                )
+        except RuntimeError:
+            pass
+        return asyncio.run_coroutine_threadsafe(
+            self.aget_tuple(config), self.loop
+        ).result()
+
+    def put(
+        self,
+        config: RunnableConfig,
+        checkpoint: Checkpoint,
+        metadata: CheckpointMetadata,
+        new_versions: ChannelVersions,
+    ) -> RunnableConfig:
+        """Save a checkpoint to the database.
+
+        This method saves a checkpoint to the Postgres database. The checkpoint is associated
+        with the provided config. For AsyncShallowPostgresSaver, this method saves ONLY the most recent
+        checkpoint and overwrites a previous checkpoint, if it exists.
+
+        Args:
+            config: The config to associate with the checkpoint.
+            checkpoint: The checkpoint to save.
+            metadata: Additional metadata to save with the checkpoint.
+            new_versions: New channel versions as of this write.
+
+        Returns:
+            RunnableConfig: Updated configuration after storing the checkpoint.
+        """
+        return asyncio.run_coroutine_threadsafe(
+            self.aput(config, checkpoint, metadata, new_versions), self.loop
+        ).result()
+
+    def put_writes(
+        self,
+        config: RunnableConfig,
+        writes: Sequence[tuple[str, Any]],
+        task_id: str,
+        task_path: str = "",
+    ) -> None:
+        """Store intermediate writes linked to a checkpoint.
+
+        This method saves intermediate writes associated with a checkpoint to the database.
+
+        Args:
+            config: Configuration of the related checkpoint.
+            writes: List of writes to store, each as (channel, value) pair.
+            task_id: Identifier for the task creating the writes.
+            task_path: Path of the task creating the writes.
+        """
+        return asyncio.run_coroutine_threadsafe(
+            self.aput_writes(config, writes, task_id, task_path), self.loop
+        ).result()

libs/checkpoint-postgres/langgraph/store/postgres/aio.py

@@ -1,9 +1,11 @@
+from __future__ import annotations
+
 import asyncio
 import logging
 from collections.abc import AsyncIterator, Iterable, Sequence
 from contextlib import asynccontextmanager
 from types import TracebackType
-from typing import Any, Callable, Optional, Union, cast
+from typing import Any, Callable, cast
 
 import orjson
 from psycopg import AsyncConnection, AsyncCursor, AsyncPipeline, Capabilities
@@ -132,12 +134,10 @@ class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Con
         self,
         conn: _ainternal.Conn,
         *,
-        pipe: Optional[AsyncPipeline] = None,
-        deserializer: Optional[
-            Callable[[Union[bytes, orjson.Fragment]], dict[str, Any]]
-        ] = None,
-        index: Optional[PostgresIndexConfig] = None,
-        ttl: Optional[TTLConfig] = None,
+        pipe: AsyncPipeline | None = None,
+        deserializer: Callable[[bytes | orjson.Fragment], dict[str, Any]] | None = None,
+        index: PostgresIndexConfig | None = None,
+        ttl: TTLConfig | None = None,
     ) -> None:
         if isinstance(conn, AsyncConnectionPool) and pipe is not None:
             raise ValueError(
@@ -157,7 +157,7 @@ class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Con
             self.embeddings = None
 
         self.ttl_config = ttl
-        self._ttl_sweeper_task: Optional[asyncio.Task[None]] = None
+        self._ttl_sweeper_task: asyncio.Task[None] | None = None
         self._ttl_stop_event = asyncio.Event()
 
     async def abatch(self, ops: Iterable[Op]) -> list[Result]:
@@ -180,10 +180,10 @@ class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Con
         conn_string: str,
         *,
         pipeline: bool = False,
-        pool_config: Optional[PoolConfig] = None,
-        index: Optional[PostgresIndexConfig] = None,
-        ttl: Optional[TTLConfig] = None,
-    ) -> AsyncIterator["AsyncPostgresStore"]:
+        pool_config: PoolConfig | None = None,
+        index: PostgresIndexConfig | None = None,
+        ttl: TTLConfig | None = None,
+    ) -> AsyncIterator[AsyncPostgresStore]:
         """Create a new AsyncPostgresStore instance from a connection string.
 
         Args:
@@ -289,7 +289,7 @@ class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Con
             return deleted_count
 
     async def start_ttl_sweeper(
-        self, sweep_interval_minutes: Optional[int] = None
+        self, sweep_interval_minutes: int | None = None
     ) -> asyncio.Task[None]:
         """Periodically delete expired store items based on TTL.
 
@@ -334,7 +334,7 @@ class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Con
         self._ttl_sweeper_task = task
         return task
 
-    async def stop_ttl_sweeper(self, timeout: Optional[float] = None) -> bool:
+    async def stop_ttl_sweeper(self, timeout: float | None = None) -> bool:
         """Stop the TTL sweeper task if it's running.
 
         Args:
@@ -369,14 +369,14 @@ class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Con
 
         return success
 
-    async def __aenter__(self) -> "AsyncPostgresStore":
+    async def __aenter__(self) -> AsyncPostgresStore:
         return self
 
     async def __aexit__(
         self,
-        exc_type: Optional[type[BaseException]],
-        exc_val: Optional[BaseException],
-        exc_tb: Optional["TracebackType"],
+        exc_type: type[BaseException] | None,
+        exc_val: BaseException | None,
+        exc_tb: TracebackType | None,
     ) -> None:
         # Ensure the TTL sweeper task is stopped when exiting the context
         if hasattr(self, "_ttl_sweeper_task") and self._ttl_sweeper_task is not None:

libs/checkpoint-postgres/langgraph/store/postgres/base.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import asyncio
 import concurrent.futures
 import json
@@ -14,7 +16,6 @@ from typing import (
     Generic,
     Literal,
     NamedTuple,
-    Optional,
     TypeVar,
     Union,
     cast,
@@ -56,8 +57,8 @@ class Migration(NamedTuple):
     """A database migration with optional conditions and parameters."""
 
     sql: str
-    params: Optional[dict[str, Any]] = None
-    condition: Optional[Callable[["BasePostgresStore"], bool]] = None
+    params: dict[str, Any] | None = None
+    condition: Callable[[BasePostgresStore], bool] | None = None
 
 
 MIGRATIONS: Sequence[str] = [
@@ -155,7 +156,7 @@ class PoolConfig(TypedDict, total=False):
     min_size: int
     """Minimum number of connections maintained in the pool. Defaults to 1."""
 
-    max_size: Optional[int]
+    max_size: int | None
     """Maximum number of connections allowed in the pool. None means unlimited."""
 
     kwargs: dict
@@ -230,8 +231,8 @@ class BasePostgresStore(Generic[C]):
     MIGRATIONS = MIGRATIONS
     VECTOR_MIGRATIONS = VECTOR_MIGRATIONS
     conn: C
-    _deserializer: Optional[Callable[[Union[bytes, orjson.Fragment]], dict[str, Any]]]
-    index_config: Optional[PostgresIndexConfig]
+    _deserializer: Callable[[bytes | orjson.Fragment], dict[str, Any]] | None
+    index_config: PostgresIndexConfig | None
 
     def _get_batch_GET_ops_queries(
         self,
@@ -293,7 +294,7 @@ class BasePostgresStore(Generic[C]):
         put_ops: Sequence[tuple[int, PutOp]],
     ) -> tuple[
         list[tuple[str, Sequence]],
-        Optional[tuple[str, Sequence[tuple[str, str, str, str]]]],
+        tuple[str, Sequence[tuple[str, str, str, str]]] | None,
     ]:
         dedupped_ops: dict[tuple[tuple[str, ...], str], PutOp] = {}
         for _, op in put_ops:
@@ -320,9 +321,7 @@ class BasePostgresStore(Generic[C]):
                 )
                 params = (_namespace_to_text(namespace), *keys)
                 queries.append((query, params))
-        embedding_request: Optional[tuple[str, Sequence[tuple[str, str, str, str]]]] = (
-            None
-        )
+        embedding_request: tuple[str, Sequence[tuple[str, str, str, str]]] | None = None
         if inserts:
             values = []
             insertion_params = []
@@ -403,7 +402,7 @@ class BasePostgresStore(Generic[C]):
         self,
         search_ops: Sequence[tuple[int, SearchOp]],
     ) -> tuple[
-        list[tuple[str, list[Union[None, str, list[float]]]]],  # queries, params
+        list[tuple[str, list[None | str | list[float]]]],  # queries, params
         list[tuple[int, str]],  # idx, query_text pairs to embed
     ]:
         """
@@ -432,7 +431,7 @@ class BasePostgresStore(Generic[C]):
                         filter_params.extend([key, orjson.dumps(value).decode("utf-8")])
 
             ns_condition = "TRUE"
-            ns_param: Optional[Sequence[Union[str]]] = None
+            ns_param: Sequence[str] | None = None
             if op.namespace_prefix:
                 ns_condition = "store.prefix LIKE %s"
                 ns_param = (f"{_namespace_to_text(op.namespace_prefix)}%",)
@@ -719,12 +718,10 @@ class PostgresStore(BaseStore, BasePostgresStore[_pg_internal.Conn]):
         self,
         conn: _pg_internal.Conn,
         *,
-        pipe: Optional[Pipeline] = None,
-        deserializer: Optional[
-            Callable[[Union[bytes, orjson.Fragment]], dict[str, Any]]
-        ] = None,
-        index: Optional[PostgresIndexConfig] = None,
-        ttl: Optional[TTLConfig] = None,
+        pipe: Pipeline | None = None,
+        deserializer: Callable[[bytes | orjson.Fragment], dict[str, Any]] | None = None,
+        index: PostgresIndexConfig | None = None,
+        ttl: TTLConfig | None = None,
     ) -> None:
         super().__init__()
         self._deserializer = deserializer
@@ -738,7 +735,7 @@ class PostgresStore(BaseStore, BasePostgresStore[_pg_internal.Conn]):
         else:
             self.embeddings = None
         self.ttl_config = ttl
-        self._ttl_sweeper_thread: Optional[threading.Thread] = None
+        self._ttl_sweeper_thread: threading.Thread | None = None
         self._ttl_stop_event = threading.Event()
 
     @classmethod
@@ -748,10 +745,10 @@ class PostgresStore(BaseStore, BasePostgresStore[_pg_internal.Conn]):
         conn_string: str,
         *,
         pipeline: bool = False,
-        pool_config: Optional[PoolConfig] = None,
-        index: Optional[PostgresIndexConfig] = None,
-        ttl: Optional[TTLConfig] = None,
-    ) -> Iterator["PostgresStore"]:
+        pool_config: PoolConfig | None = None,
+        index: PostgresIndexConfig | None = None,
+        ttl: TTLConfig | None = None,
+    ) -> Iterator[PostgresStore]:
         """Create a new PostgresStore instance from a connection string.
 
         Args:
@@ -810,7 +807,7 @@ class PostgresStore(BaseStore, BasePostgresStore[_pg_internal.Conn]):
             return deleted_count
 
     def start_ttl_sweeper(
-        self, sweep_interval_minutes: Optional[int] = None
+        self, sweep_interval_minutes: int | None = None
     ) -> concurrent.futures.Future[None]:
         """Periodically delete expired store items based on TTL.
 
@@ -867,7 +864,7 @@ class PostgresStore(BaseStore, BasePostgresStore[_pg_internal.Conn]):
         )
         return future
 
-    def stop_ttl_sweeper(self, timeout: Optional[float] = None) -> bool:
+    def stop_ttl_sweeper(self, timeout: float | None = None) -> bool:
         """Stop the TTL sweeper thread if it's running.
 
         Args:
@@ -1196,7 +1193,7 @@ def _row_to_item(
     namespace: tuple[str, ...],
     row: Row,
     *,
-    loader: Optional[Callable[[Union[bytes, orjson.Fragment]], dict[str, Any]]] = None,
+    loader: Callable[[bytes | orjson.Fragment], dict[str, Any]] | None = None,
 ) -> Item:
     """Convert a row from the database into an Item.
 
@@ -1224,7 +1221,7 @@ def _row_to_search_item(
     namespace: tuple[str, ...],
     row: Row,
     *,
-    loader: Optional[Callable[[Union[bytes, orjson.Fragment]], dict[str, Any]]] = None,
+    loader: Callable[[bytes | orjson.Fragment], dict[str, Any]] | None = None,
 ) -> SearchItem:
     """Convert a row from the database into an Item."""
     loader = loader or _json_loads
@@ -1255,7 +1252,7 @@ def _group_ops(ops: Iterable[Op]) -> tuple[dict[type, list[tuple[int, Op]]], int
     return grouped_ops, tot
 
 
-def _json_loads(content: Union[bytes, orjson.Fragment]) -> Any:
+def _json_loads(content: bytes | orjson.Fragment) -> Any:
     if isinstance(content, orjson.Fragment):
         if hasattr(content, "buf"):
             content = content.buf
@@ -1267,7 +1264,7 @@ def _json_loads(content: Union[bytes, orjson.Fragment]) -> Any:
     return orjson.loads(cast(bytes, content))
 
 
-def _decode_ns_bytes(namespace: Union[str, bytes, list]) -> tuple[str, ...]:
+def _decode_ns_bytes(namespace: str | bytes | list) -> tuple[str, ...]:
     if isinstance(namespace, list):
         return tuple(namespace)
     if isinstance(namespace, bytes):
@@ -1316,16 +1313,16 @@ def get_distance_operator(store: Any) -> tuple[str, str]:
 
 def _ensure_index_config(
     index_config: PostgresIndexConfig,
-) -> tuple[Optional["Embeddings"], PostgresIndexConfig]:
+) -> tuple[Embeddings | None, PostgresIndexConfig]:
     index_config = index_config.copy()
-    tokenized: list[tuple[str, Union[Literal["$"], list[str]]]] = []
+    tokenized: list[tuple[str, Literal["$"] | list[str]]] = []
     tot = 0
-    text_fields = index_config.get("fields") or ["$"]
-    if isinstance(text_fields, str):
-        text_fields = [text_fields]
-    if not isinstance(text_fields, list):
-        raise ValueError(f"Text fields must be a list or a string. Got {text_fields}")
-    for p in text_fields:
+    fields = index_config.get("fields") or ["$"]
+    if isinstance(fields, str):
+        fields = [fields]
+    if not isinstance(fields, list):
+        raise ValueError(f"Text fields must be a list or a string. Got {fields}")
+    for p in fields:
         if p == "$":
             tokenized.append((p, "$"))
             tot += 1

libs/checkpoint-postgres/pyproject.toml

@@ -56,7 +56,7 @@ lint.select = [
   "B",  # flake8-bugbear
   "I",  # isort
 ]
-lint.ignore = ["E501", "B008", "UP007", "UP006"]
+lint.ignore = ["E501", "B008"]
 
 [tool.mypy]
 # https://mypy.readthedocs.io/en/stable/config_file.html

libs/checkpoint-postgres/tests/checkpoint_utils.py

@@ -1,51 +0,0 @@
-from collections.abc import Mapping
-from datetime import datetime, timezone
-from typing import Any, Optional, Protocol
-
-from langgraph.checkpoint.base import Checkpoint, EmptyChannelError
-from langgraph.checkpoint.base.id import uuid6
-
-
-class ChannelProtocol(Protocol):
-    def checkpoint(self) -> Optional[Any]: ...
-
-
-def empty_checkpoint() -> Checkpoint:
-    return Checkpoint(
-        v=1,
-        id=str(uuid6(clock_seq=-2)),
-        ts=datetime.now(timezone.utc).isoformat(),
-        channel_values={},
-        channel_versions={},
-        versions_seen={},
-    )
-
-
-def create_checkpoint(
-    checkpoint: Checkpoint,
-    channels: Optional[Mapping[str, ChannelProtocol]],
-    step: int,
-    *,
-    id: Optional[str] = None,
-) -> Checkpoint:
-    """Create a checkpoint for the given channels."""
-    ts = datetime.now(timezone.utc).isoformat()
-    if channels is None:
-        values = checkpoint["channel_values"]
-    else:
-        values = {}
-        for k, v in channels.items():
-            if k not in checkpoint["channel_versions"]:
-                continue
-            try:
-                values[k] = v.checkpoint()
-            except EmptyChannelError:
-                pass
-    return Checkpoint(
-        v=1,
-        ts=ts,
-        id=id or str(uuid6(clock_seq=step)),
-        channel_values=values,
-        channel_versions=checkpoint["channel_versions"],
-        versions_seen=checkpoint["versions_seen"],
-    )

libs/checkpoint-postgres/tests/test_async.py

@@ -14,10 +14,14 @@ from langgraph.checkpoint.base import (
     EXCLUDED_METADATA_KEYS,
     Checkpoint,
     CheckpointMetadata,
+    create_checkpoint,
+    empty_checkpoint,
+)
+from langgraph.checkpoint.postgres.aio import (
+    AsyncPostgresSaver,
+    AsyncShallowPostgresSaver,
 )
-from langgraph.checkpoint.postgres.aio import AsyncPostgresSaver
 from langgraph.checkpoint.serde.types import TASKS
-from tests.checkpoint_utils import create_checkpoint, empty_checkpoint
 from tests.conftest import DEFAULT_POSTGRES_URI
 
 
@@ -108,11 +112,41 @@ async def _base_saver():
             await conn.execute(f"DROP DATABASE {database}")
 
 
+@asynccontextmanager
+async def _shallow_saver():
+    """Fixture for shallow connection mode testing."""
+    database = f"test_{uuid4().hex[:16]}"
+    # create unique db
+    async with await AsyncConnection.connect(
+        DEFAULT_POSTGRES_URI, autocommit=True
+    ) as conn:
+        await conn.execute(f"CREATE DATABASE {database}")
+    try:
+        async with await AsyncConnection.connect(
+            DEFAULT_POSTGRES_URI + database,
+            autocommit=True,
+            prepare_threshold=0,
+            row_factory=dict_row,
+        ) as conn:
+            checkpointer = AsyncShallowPostgresSaver(conn)
+            await checkpointer.setup()
+            yield checkpointer
+    finally:
+        # drop unique db
+        async with await AsyncConnection.connect(
+            DEFAULT_POSTGRES_URI, autocommit=True
+        ) as conn:
+            await conn.execute(f"DROP DATABASE {database}")
+
+
 @asynccontextmanager
 async def _saver(name: str):
     if name == "base":
         async with _base_saver() as saver:
             yield saver
+    elif name == "shallow":
+        async with _shallow_saver() as saver:
+            yield saver
     elif name == "pool":
         async with _pool_saver() as saver:
             yield saver
@@ -172,7 +206,7 @@ def test_data():
     }
 
 
-@pytest.mark.parametrize("saver_name", ["base", "pool", "pipe"])
+@pytest.mark.parametrize("saver_name", ["base", "pool", "pipe", "shallow"])
 async def test_combined_metadata(saver_name: str, test_data) -> None:
     async with _saver(saver_name) as saver:
         config = {
@@ -194,12 +228,11 @@ async def test_combined_metadata(saver_name: str, test_data) -> None:
         checkpoint = await saver.aget_tuple(config)
         assert checkpoint.metadata == {
             **metadata,
-            "thread_id": "thread-2",
             "run_id": "my_run_id",
         }
 
 
-@pytest.mark.parametrize("saver_name", ["base", "pool", "pipe"])
+@pytest.mark.parametrize("saver_name", ["base", "pool", "pipe", "shallow"])
 async def test_asearch(saver_name: str, test_data) -> None:
     async with _saver(saver_name) as saver:
         configs = test_data["configs"]
@@ -250,7 +283,7 @@ async def test_asearch(saver_name: str, test_data) -> None:
         } == {"", "inner"}
 
 
-@pytest.mark.parametrize("saver_name", ["base", "pool", "pipe"])
+@pytest.mark.parametrize("saver_name", ["base", "pool", "pipe", "shallow"])
 async def test_null_chars(saver_name: str, test_data) -> None:
     async with _saver(saver_name) as saver:
         config = await saver.aput(

libs/checkpoint-postgres/tests/test_async_store.py

@@ -1,4 +1,6 @@
 # type: ignore
+from __future__ import annotations
+
 import asyncio
 import itertools
 import sys
@@ -6,7 +8,7 @@ import uuid
 from collections.abc import AsyncIterator
 from concurrent.futures import ThreadPoolExecutor
 from contextlib import asynccontextmanager
-from typing import Any, Optional
+from typing import Any
 
 import pytest
 from langchain_core.embeddings import Embeddings
@@ -353,7 +355,7 @@ async def _create_vector_store(
     vector_type: str,
     distance_type: str,
     fake_embeddings: CharacterEmbeddings,
-    text_fields: Optional[list[str]] = None,
+    text_fields: list[str] | None = None,
 ) -> AsyncIterator[AsyncPostgresStore]:
     """Create a store with vector search enabled."""
     if sys.version_info < (3, 10):

libs/checkpoint-postgres/tests/test_store.py

@@ -1,9 +1,10 @@
 # type: ignore
+from __future__ import annotations
 
 import re
 import time
 from contextlib import contextmanager
-from typing import Any, Optional
+from typing import Any
 from uuid import uuid4
 
 import pytest
@@ -379,7 +380,7 @@ def _create_vector_store(
     vector_type: str,
     distance_type: str,
     fake_embeddings: Embeddings,
-    text_fields: Optional[list[str]] = None,
+    text_fields: list[str] | None = None,
     enable_ttl: bool = True,
 ) -> PostgresStore:
     """Create a store with vector search enabled."""

libs/checkpoint-postgres/tests/test_sync.py

@@ -15,10 +15,11 @@ from langgraph.checkpoint.base import (
     EXCLUDED_METADATA_KEYS,
     Checkpoint,
     CheckpointMetadata,
+    create_checkpoint,
+    empty_checkpoint,
 )
-from langgraph.checkpoint.postgres import PostgresSaver
+from langgraph.checkpoint.postgres import PostgresSaver, ShallowPostgresSaver
 from langgraph.checkpoint.serde.types import TASKS
-from tests.checkpoint_utils import create_checkpoint, empty_checkpoint
 from tests.conftest import DEFAULT_POSTGRES_URI
 
 
@@ -97,11 +98,37 @@ def _base_saver():
             conn.execute(f"DROP DATABASE {database}")
 
 
+@contextmanager
+def _shallow_saver():
+    """Fixture for regular connection mode testing with a shallow checkpointer."""
+    database = f"test_{uuid4().hex[:16]}"
+    # create unique db
+    with Connection.connect(DEFAULT_POSTGRES_URI, autocommit=True) as conn:
+        conn.execute(f"CREATE DATABASE {database}")
+    try:
+        with Connection.connect(
+            DEFAULT_POSTGRES_URI + database,
+            autocommit=True,
+            prepare_threshold=0,
+            row_factory=dict_row,
+        ) as conn:
+            checkpointer = ShallowPostgresSaver(conn)
+            checkpointer.setup()
+            yield checkpointer
+    finally:
+        # drop unique db
+        with Connection.connect(DEFAULT_POSTGRES_URI, autocommit=True) as conn:
+            conn.execute(f"DROP DATABASE {database}")
+
+
 @contextmanager
 def _saver(name: str):
     if name == "base":
         with _base_saver() as saver:
             yield saver
+    elif name == "shallow":
+        with _shallow_saver() as saver:
+            yield saver
     elif name == "pool":
         with _pool_saver() as saver:
             yield saver
@@ -161,7 +188,7 @@ def test_data():
     }
 
 
-@pytest.mark.parametrize("saver_name", ["base", "pool", "pipe"])
+@pytest.mark.parametrize("saver_name", ["base", "pool", "pipe", "shallow"])
 def test_combined_metadata(saver_name: str, test_data) -> None:
     with _saver(saver_name) as saver:
         config = {
@@ -183,12 +210,11 @@ def test_combined_metadata(saver_name: str, test_data) -> None:
         checkpoint = saver.get_tuple(config)
         assert checkpoint.metadata == {
             **metadata,
-            "thread_id": "thread-2",
             "run_id": "my_run_id",
         }
 
 
-@pytest.mark.parametrize("saver_name", ["base", "pool", "pipe"])
+@pytest.mark.parametrize("saver_name", ["base", "pool", "pipe", "shallow"])
 def test_search(saver_name: str, test_data) -> None:
     with _saver(saver_name) as saver:
         configs = test_data["configs"]
@@ -237,7 +263,7 @@ def test_search(saver_name: str, test_data) -> None:
         } == {"", "inner"}
 
 
-@pytest.mark.parametrize("saver_name", ["base", "pool", "pipe"])
+@pytest.mark.parametrize("saver_name", ["base", "pool", "pipe", "shallow"])
 def test_null_chars(saver_name: str, test_data) -> None:
     with _saver(saver_name) as saver:
         config = saver.put(

libs/checkpoint-sqlite/langgraph/checkpoint/sqlite/__init__.py

@@ -1,9 +1,11 @@
+from __future__ import annotations
+
 import random
 import sqlite3
 import threading
 from collections.abc import AsyncIterator, Iterator, Sequence
 from contextlib import closing, contextmanager
-from typing import Any, Optional, cast
+from typing import Any, cast
 
 from langchain_core.runnables import RunnableConfig
 
@@ -76,7 +78,7 @@ class SqliteSaver(BaseCheckpointSaver[str]):
         self,
         conn: sqlite3.Connection,
         *,
-        serde: Optional[SerializerProtocol] = None,
+        serde: SerializerProtocol | None = None,
     ) -> None:
         super().__init__(serde=serde)
         self.jsonplus_serde = JsonPlusSerializer()
@@ -86,7 +88,7 @@ class SqliteSaver(BaseCheckpointSaver[str]):
 
     @classmethod
     @contextmanager
-    def from_conn_string(cls, conn_string: str) -> Iterator["SqliteSaver"]:
+    def from_conn_string(cls, conn_string: str) -> Iterator[SqliteSaver]:
         """Create a new SqliteSaver instance from a connection string.
 
         Args:
@@ -178,7 +180,7 @@ class SqliteSaver(BaseCheckpointSaver[str]):
                     self.conn.commit()
                 cur.close()
 
-    def get_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
+    def get_tuple(self, config: RunnableConfig) -> CheckpointTuple | None:
         """Get a checkpoint tuple from the database.
 
         This method retrieves a checkpoint tuple from the SQLite database based on the
@@ -286,11 +288,11 @@ class SqliteSaver(BaseCheckpointSaver[str]):
 
     def list(
         self,
-        config: Optional[RunnableConfig],
+        config: RunnableConfig | None,
         *,
-        filter: Optional[dict[str, Any]] = None,
-        before: Optional[RunnableConfig] = None,
-        limit: Optional[int] = None,
+        filter: dict[str, Any] | None = None,
+        before: RunnableConfig | None = None,
+        limit: int | None = None,
     ) -> Iterator[CheckpointTuple]:
         """List checkpoints from the database.
 
@@ -493,7 +495,7 @@ class SqliteSaver(BaseCheckpointSaver[str]):
                 (str(thread_id),),
             )
 
-    async def aget_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
+    async def aget_tuple(self, config: RunnableConfig) -> CheckpointTuple | None:
         """Get a checkpoint tuple from the database asynchronously.
 
         Note:
@@ -504,11 +506,11 @@ class SqliteSaver(BaseCheckpointSaver[str]):
 
     async def alist(
         self,
-        config: Optional[RunnableConfig],
+        config: RunnableConfig | None,
         *,
-        filter: Optional[dict[str, Any]] = None,
-        before: Optional[RunnableConfig] = None,
-        limit: Optional[int] = None,
+        filter: dict[str, Any] | None = None,
+        before: RunnableConfig | None = None,
+        limit: int | None = None,
     ) -> AsyncIterator[CheckpointTuple]:
         """List checkpoints from the database asynchronously.
 
@@ -534,7 +536,7 @@ class SqliteSaver(BaseCheckpointSaver[str]):
         """
         raise NotImplementedError(_AIO_ERROR_MSG)
 
-    def get_next_version(self, current: Optional[str]) -> str:
+    def get_next_version(self, current: str | None, channel: None) -> str:
         """Generate the next version ID for a channel.
 
         This method creates a new version identifier for a channel based on its current version.

libs/checkpoint-sqlite/langgraph/checkpoint/sqlite/aio.py

@@ -1,8 +1,10 @@
+from __future__ import annotations
+
 import asyncio
 import random
 from collections.abc import AsyncIterator, Iterator, Sequence
 from contextlib import asynccontextmanager
-from typing import Any, Callable, Optional, TypeVar, cast
+from typing import Any, Callable, TypeVar, cast
 
 import aiosqlite
 from langchain_core.runnables import RunnableConfig
@@ -108,7 +110,7 @@ class AsyncSqliteSaver(BaseCheckpointSaver[str]):
         self,
         conn: aiosqlite.Connection,
         *,
-        serde: Optional[SerializerProtocol] = None,
+        serde: SerializerProtocol | None = None,
     ):
         super().__init__(serde=serde)
         self.jsonplus_serde = JsonPlusSerializer()
@@ -121,7 +123,7 @@ class AsyncSqliteSaver(BaseCheckpointSaver[str]):
     @asynccontextmanager
     async def from_conn_string(
         cls, conn_string: str
-    ) -> AsyncIterator["AsyncSqliteSaver"]:
+    ) -> AsyncIterator[AsyncSqliteSaver]:
         """Create a new AsyncSqliteSaver instance from a connection string.
 
         Args:
@@ -133,7 +135,7 @@ class AsyncSqliteSaver(BaseCheckpointSaver[str]):
         async with aiosqlite.connect(conn_string) as conn:
             yield cls(conn)
 
-    def get_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
+    def get_tuple(self, config: RunnableConfig) -> CheckpointTuple | None:
         """Get a checkpoint tuple from the database.
 
         This method retrieves a checkpoint tuple from the SQLite database based on the
@@ -165,11 +167,11 @@ class AsyncSqliteSaver(BaseCheckpointSaver[str]):
 
     def list(
         self,
-        config: Optional[RunnableConfig],
+        config: RunnableConfig | None,
         *,
-        filter: Optional[dict[str, Any]] = None,
-        before: Optional[RunnableConfig] = None,
-        limit: Optional[int] = None,
+        filter: dict[str, Any] | None = None,
+        before: RunnableConfig | None = None,
+        limit: int | None = None,
     ) -> Iterator[CheckpointTuple]:
         """List checkpoints from the database asynchronously.
 
@@ -310,7 +312,7 @@ class AsyncSqliteSaver(BaseCheckpointSaver[str]):
 
             self.is_setup = True
 
-    async def aget_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
+    async def aget_tuple(self, config: RunnableConfig) -> CheckpointTuple | None:
         """Get a checkpoint tuple from the database asynchronously.
 
         This method retrieves a checkpoint tuple from the SQLite database based on the
@@ -398,11 +400,11 @@ class AsyncSqliteSaver(BaseCheckpointSaver[str]):
 
     async def alist(
         self,
-        config: Optional[RunnableConfig],
+        config: RunnableConfig | None,
         *,
-        filter: Optional[dict[str, Any]] = None,
-        before: Optional[RunnableConfig] = None,
-        limit: Optional[int] = None,
+        filter: dict[str, Any] | None = None,
+        before: RunnableConfig | None = None,
+        limit: int | None = None,
     ) -> AsyncIterator[CheckpointTuple]:
         """List checkpoints from the database asynchronously.
 
@@ -589,7 +591,7 @@ class AsyncSqliteSaver(BaseCheckpointSaver[str]):
             )
             await self.conn.commit()
 
-    def get_next_version(self, current: Optional[str]) -> str:
+    def get_next_version(self, current: str | None, channel: None) -> str:
         """Generate the next version ID for a channel.
 
         This method creates a new version identifier for a channel based on its current version.

libs/checkpoint-sqlite/langgraph/checkpoint/sqlite/utils.py

@@ -1,6 +1,8 @@
+from __future__ import annotations
+
 import json
 from collections.abc import Sequence
-from typing import Any, Optional
+from typing import Any
 
 from langchain_core.runnables import RunnableConfig
 
@@ -52,9 +54,9 @@ def _metadata_predicate(
 
 
 def search_where(
-    config: Optional[RunnableConfig],
-    filter: Optional[dict[str, Any]],
-    before: Optional[RunnableConfig] = None,
+    config: RunnableConfig | None,
+    filter: dict[str, Any] | None,
+    before: RunnableConfig | None = None,
 ) -> tuple[str, Sequence[Any]]:
     """Return WHERE clause predicates for (a)search() given metadata filter
     and `before` config.

libs/checkpoint-sqlite/langgraph/store/sqlite/aio.py

@@ -1,10 +1,12 @@
+from __future__ import annotations
+
 import asyncio
 import logging
 from collections import defaultdict
 from collections.abc import AsyncIterator, Iterable, Sequence
 from contextlib import asynccontextmanager
 from types import TracebackType
-from typing import Any, Callable, Optional, Union, cast
+from typing import Any, Callable, cast
 
 import aiosqlite
 import orjson
@@ -88,11 +90,10 @@ class AsyncSqliteStore(AsyncBatchedBaseStore, BaseSqliteStore):
         self,
         conn: aiosqlite.Connection,
         *,
-        deserializer: Optional[
-            Callable[[Union[bytes, str, orjson.Fragment]], dict[str, Any]]
-        ] = None,
-        index: Optional[SqliteIndexConfig] = None,
-        ttl: Optional[TTLConfig] = None,
+        deserializer: Callable[[bytes | str | orjson.Fragment], dict[str, Any]]
+        | None = None,
+        index: SqliteIndexConfig | None = None,
+        ttl: TTLConfig | None = None,
     ):
         """Initialize the async SQLite store.
 
@@ -114,7 +115,7 @@ class AsyncSqliteStore(AsyncBatchedBaseStore, BaseSqliteStore):
         else:
             self.embeddings = None
         self.ttl_config = ttl
-        self._ttl_sweeper_task: Optional[asyncio.Task[None]] = None
+        self._ttl_sweeper_task: asyncio.Task[None] | None = None
         self._ttl_stop_event = asyncio.Event()
 
     @classmethod
@@ -123,9 +124,9 @@ class AsyncSqliteStore(AsyncBatchedBaseStore, BaseSqliteStore):
         cls,
         conn_string: str,
         *,
-        index: Optional[SqliteIndexConfig] = None,
-        ttl: Optional[TTLConfig] = None,
-    ) -> AsyncIterator["AsyncSqliteStore"]:
+        index: SqliteIndexConfig | None = None,
+        ttl: TTLConfig | None = None,
+    ) -> AsyncIterator[AsyncSqliteStore]:
         """Create a new AsyncSqliteStore instance from a connection string.
 
         Args:
@@ -253,7 +254,7 @@ class AsyncSqliteStore(AsyncBatchedBaseStore, BaseSqliteStore):
             return deleted_count
 
     async def start_ttl_sweeper(
-        self, sweep_interval_minutes: Optional[int] = None
+        self, sweep_interval_minutes: int | None = None
     ) -> asyncio.Task[None]:
         """Periodically delete expired store items based on TTL.
 
@@ -298,7 +299,7 @@ class AsyncSqliteStore(AsyncBatchedBaseStore, BaseSqliteStore):
         self._ttl_sweeper_task = task
         return task
 
-    async def stop_ttl_sweeper(self, timeout: Optional[float] = None) -> bool:
+    async def stop_ttl_sweeper(self, timeout: float | None = None) -> bool:
         """Stop the TTL sweeper task if it's running.
 
         Args:
@@ -333,14 +334,14 @@ class AsyncSqliteStore(AsyncBatchedBaseStore, BaseSqliteStore):
 
         return success
 
-    async def __aenter__(self) -> "AsyncSqliteStore":
+    async def __aenter__(self) -> AsyncSqliteStore:
         return self
 
     async def __aexit__(
         self,
-        exc_type: Optional[type[BaseException]],
-        exc_val: Optional[BaseException],
-        exc_tb: Optional["TracebackType"],
+        exc_type: type[BaseException] | None,
+        exc_val: BaseException | None,
+        exc_tb: TracebackType | None,
     ) -> None:
         # Ensure the TTL sweeper task is stopped when exiting the context
         if hasattr(self, "_ttl_sweeper_task") and self._ttl_sweeper_task is not None:

libs/checkpoint-sqlite/langgraph/store/sqlite/base.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import concurrent.futures
 import datetime
 import logging
@@ -6,7 +8,7 @@ import threading
 from collections import defaultdict
 from collections.abc import Iterable, Iterator, Sequence
 from contextlib import contextmanager
-from typing import Any, Callable, Literal, NamedTuple, Optional, Union, cast
+from typing import Any, Callable, Literal, NamedTuple, cast
 
 import orjson
 import sqlite_vec  # type: ignore[import-untyped]
@@ -105,7 +107,7 @@ def _decode_ns_text(namespace: str) -> tuple[str, ...]:
     return tuple(namespace.split("."))
 
 
-def _json_loads(content: Union[bytes, str, orjson.Fragment]) -> Any:
+def _json_loads(content: bytes | str | orjson.Fragment) -> Any:
     if isinstance(content, orjson.Fragment):
         if hasattr(content, "buf"):
             content = content.buf
@@ -125,9 +127,7 @@ def _row_to_item(
     namespace: tuple[str, ...],
     row: dict[str, Any],
     *,
-    loader: Optional[
-        Callable[[Union[bytes, str, orjson.Fragment]], dict[str, Any]]
-    ] = None,
+    loader: Callable[[bytes | str | orjson.Fragment], dict[str, Any]] | None = None,
 ) -> Item:
     """Convert a row from the database into an Item."""
     val = row["value"]
@@ -149,9 +149,7 @@ def _row_to_search_item(
     namespace: tuple[str, ...],
     row: dict[str, Any],
     *,
-    loader: Optional[
-        Callable[[Union[bytes, str, orjson.Fragment]], dict[str, Any]]
-    ] = None,
+    loader: Callable[[bytes | str | orjson.Fragment], dict[str, Any]] | None = None,
 ) -> SearchItem:
     """Convert a row from the database into a SearchItem."""
     loader = loader or _json_loads
@@ -196,8 +194,8 @@ class BaseSqliteStore:
     MIGRATIONS = MIGRATIONS
     VECTOR_MIGRATIONS = VECTOR_MIGRATIONS
     supports_ttl = True
-    index_config: Optional[SqliteIndexConfig] = None
-    ttl_config: Optional[TTLConfig] = None
+    index_config: SqliteIndexConfig | None = None
+    ttl_config: TTLConfig | None = None
 
     def _get_batch_GET_ops_queries(
         self, get_ops: Sequence[tuple[int, GetOp]]
@@ -259,7 +257,7 @@ class BaseSqliteStore:
         self, put_ops: Sequence[tuple[int, PutOp]]
     ) -> tuple[
         list[tuple[str, Sequence]],
-        Optional[tuple[str, Sequence[tuple[str, str, str, str]]]],
+        tuple[str, Sequence[tuple[str, str, str, str]]] | None,
     ]:
         # Last-write wins
         dedupped_ops: dict[tuple[tuple[str, ...], str], PutOp] = {}
@@ -288,9 +286,7 @@ class BaseSqliteStore:
                 params = (_namespace_to_text(namespace), *keys)
                 queries.append((query, params))
 
-        embedding_request: Optional[tuple[str, Sequence[tuple[str, str, str, str]]]] = (
-            None
-        )
+        embedding_request: tuple[str, Sequence[tuple[str, str, str, str]]] | None = None
         if inserts:
             values = []
             insertion_params = []
@@ -358,7 +354,7 @@ class BaseSqliteStore:
     def _prepare_batch_search_queries(
         self, search_ops: Sequence[tuple[int, SearchOp]]
     ) -> tuple[
-        list[tuple[str, list[Union[None, str, list[float]]]]],  # queries, params
+        list[tuple[str, list[None | str | list[float]]]],  # queries, params
         list[tuple[int, str]],  # idx, query_text pairs to embed
     ]:
         """
@@ -785,11 +781,10 @@ class SqliteStore(BaseSqliteStore, BaseStore):
         self,
         conn: sqlite3.Connection,
         *,
-        deserializer: Optional[
-            Callable[[Union[bytes, str, orjson.Fragment]], dict[str, Any]]
-        ] = None,
-        index: Optional[SqliteIndexConfig] = None,
-        ttl: Optional[TTLConfig] = None,
+        deserializer: Callable[[bytes | str | orjson.Fragment], dict[str, Any]]
+        | None = None,
+        index: SqliteIndexConfig | None = None,
+        ttl: TTLConfig | None = None,
     ):
         super().__init__()
         self._deserializer = deserializer
@@ -802,7 +797,7 @@ class SqliteStore(BaseSqliteStore, BaseStore):
         else:
             self.embeddings = None
         self.ttl_config = ttl
-        self._ttl_sweeper_thread: Optional[threading.Thread] = None
+        self._ttl_sweeper_thread: threading.Thread | None = None
         self._ttl_stop_event = threading.Event()
 
     def _get_batch_GET_ops_queries(
@@ -956,9 +951,9 @@ class SqliteStore(BaseSqliteStore, BaseStore):
         cls,
         conn_string: str,
         *,
-        index: Optional[SqliteIndexConfig] = None,
-        ttl: Optional[TTLConfig] = None,
-    ) -> Iterator["SqliteStore"]:
+        index: SqliteIndexConfig | None = None,
+        ttl: TTLConfig | None = None,
+    ) -> Iterator[SqliteStore]:
         """Create a new SqliteStore instance from a connection string.
 
         Args:
@@ -1087,7 +1082,7 @@ class SqliteStore(BaseSqliteStore, BaseStore):
             return deleted_count
 
     def start_ttl_sweeper(
-        self, sweep_interval_minutes: Optional[int] = None
+        self, sweep_interval_minutes: int | None = None
     ) -> concurrent.futures.Future[None]:
         """Periodically delete expired store items based on TTL.
 
@@ -1144,7 +1139,7 @@ class SqliteStore(BaseSqliteStore, BaseStore):
         )
         return future
 
-    def stop_ttl_sweeper(self, timeout: Optional[float] = None) -> bool:
+    def stop_ttl_sweeper(self, timeout: float | None = None) -> bool:
         """Stop the TTL sweeper thread if it's running.
 
         Args:
@@ -1396,7 +1391,7 @@ def _ensure_index_config(
 ) -> tuple[Any, SqliteIndexConfig]:
     """Process and validate index configuration."""
     index_config = index_config.copy()
-    tokenized: list[tuple[str, Union[Literal["$"], list[str]]]] = []
+    tokenized: list[tuple[str, Literal["$"] | list[str]]] = []
     tot = 0
     text_fields = index_config.get("text_fields") or ["$"]
     if isinstance(text_fields, str):

libs/checkpoint-sqlite/pyproject.toml

@@ -54,7 +54,7 @@ lint.select = [
   "B",  # flake8-bugbear
   "I",  # isort
 ]
-lint.ignore = ["E501", "B008", "UP007", "UP006"]
+lint.ignore = ["E501", "B008"]
 
 [tool.pytest-watcher]
 now = true

libs/checkpoint-sqlite/tests/checkpoint_utils.py

@@ -1,51 +0,0 @@
-from collections.abc import Mapping
-from datetime import datetime, timezone
-from typing import Any, Optional, Protocol
-
-from langgraph.checkpoint.base import Checkpoint, EmptyChannelError
-from langgraph.checkpoint.base.id import uuid6
-
-
-class ChannelProtocol(Protocol):
-    def checkpoint(self) -> Optional[Any]: ...
-
-
-def empty_checkpoint() -> Checkpoint:
-    return Checkpoint(
-        v=1,
-        id=str(uuid6(clock_seq=-2)),
-        ts=datetime.now(timezone.utc).isoformat(),
-        channel_values={},
-        channel_versions={},
-        versions_seen={},
-    )
-
-
-def create_checkpoint(
-    checkpoint: Checkpoint,
-    channels: Optional[Mapping[str, ChannelProtocol]],
-    step: int,
-    *,
-    id: Optional[str] = None,
-) -> Checkpoint:
-    """Create a checkpoint for the given channels."""
-    ts = datetime.now(timezone.utc).isoformat()
-    if channels is None:
-        values = checkpoint["channel_values"]
-    else:
-        values = {}
-        for k, v in channels.items():
-            if k not in checkpoint["channel_versions"]:
-                continue
-            try:
-                values[k] = v.checkpoint()
-            except EmptyChannelError:
-                pass
-    return Checkpoint(
-        v=1,
-        ts=ts,
-        id=id or str(uuid6(clock_seq=step)),
-        channel_values=values,
-        channel_versions=checkpoint["channel_versions"],
-        versions_seen=checkpoint["versions_seen"],
-    )

libs/checkpoint-sqlite/tests/test_aiosqlite.py

@@ -6,9 +6,10 @@ from langchain_core.runnables import RunnableConfig
 from langgraph.checkpoint.base import (
     Checkpoint,
     CheckpointMetadata,
+    create_checkpoint,
+    empty_checkpoint,
 )
 from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver
-from tests.checkpoint_utils import create_checkpoint, empty_checkpoint
 
 
 class TestAsyncSqliteSaver:
@@ -70,7 +71,6 @@ class TestAsyncSqliteSaver:
             checkpoint = await saver.aget_tuple(config)
             assert checkpoint is not None and checkpoint.metadata == {
                 **self.metadata_2,
-                "thread_id": "thread-2",
                 "run_id": "my_run_id",
             }
 
@@ -91,18 +91,11 @@ class TestAsyncSqliteSaver:
 
             search_results_1 = [c async for c in saver.alist(None, filter=query_1)]
             assert len(search_results_1) == 1
-            assert search_results_1[0].metadata == {
-                "thread_id": "thread-1",
-                "thread_ts": "1",
-                **self.metadata_1,
-            }
+            assert search_results_1[0].metadata == self.metadata_1
 
             search_results_2 = [c async for c in saver.alist(None, filter=query_2)]
             assert len(search_results_2) == 1
-            assert search_results_2[0].metadata == {
-                "thread_id": "thread-2",
-                **self.metadata_2,
-            }
+            assert search_results_2[0].metadata == self.metadata_2
 
             search_results_3 = [c async for c in saver.alist(None, filter=query_3)]
             assert len(search_results_3) == 3

libs/checkpoint-sqlite/tests/test_sqlite.py

@@ -6,10 +6,11 @@ from langchain_core.runnables import RunnableConfig
 from langgraph.checkpoint.base import (
     Checkpoint,
     CheckpointMetadata,
+    create_checkpoint,
+    empty_checkpoint,
 )
 from langgraph.checkpoint.sqlite import SqliteSaver
 from langgraph.checkpoint.sqlite.utils import _metadata_predicate, search_where
-from tests.checkpoint_utils import create_checkpoint, empty_checkpoint
 
 
 class TestSqliteSaver:
@@ -71,7 +72,6 @@ class TestSqliteSaver:
             checkpoint = saver.get_tuple(config)
             assert checkpoint is not None and checkpoint.metadata == {
                 **self.metadata_2,
-                "thread_id": "thread-2",
                 "run_id": "my_run_id",
             }
 
@@ -94,18 +94,11 @@ class TestSqliteSaver:
 
             search_results_1 = list(saver.list(None, filter=query_1))
             assert len(search_results_1) == 1
-            assert search_results_1[0].metadata == {
-                "thread_id": "thread-1",
-                "thread_ts": "1",
-                **self.metadata_1,
-            }
+            assert search_results_1[0].metadata == self.metadata_1
 
             search_results_2 = list(saver.list(None, filter=query_2))
             assert len(search_results_2) == 1
-            assert search_results_2[0].metadata == {
-                "thread_id": "thread-2",
-                **self.metadata_2,
-            }
+            assert search_results_2[0].metadata == self.metadata_2
 
             search_results_3 = list(saver.list(None, filter=query_3))
             assert len(search_results_3) == 3

libs/checkpoint/langgraph/checkpoint/base/__init__.py

@@ -1,11 +1,11 @@
-from collections.abc import AsyncIterator, Iterator, Sequence
+from __future__ import annotations
+
+from collections.abc import AsyncIterator, Iterator, Mapping, Sequence
 from typing import (  # noqa: UP035
     Any,
     Generic,
-    List,
     Literal,
     NamedTuple,
-    Optional,
     TypedDict,
     TypeVar,
     Union,
@@ -13,6 +13,7 @@ from typing import (  # noqa: UP035
 
 from langchain_core.runnables import RunnableConfig
 
+from langgraph.checkpoint.base.id import uuid6
 from langgraph.checkpoint.serde.base import SerializerProtocol, maybe_add_typed_methods
 from langgraph.checkpoint.serde.jsonplus import JsonPlusSerializer
 from langgraph.checkpoint.serde.types import (
@@ -20,6 +21,7 @@ from langgraph.checkpoint.serde.types import (
     INTERRUPT,
     RESUME,
     SCHEDULED,
+    ChannelProtocol,
 )
 
 V = TypeVar("V", int, float, str)
@@ -89,6 +91,7 @@ def copy_checkpoint(checkpoint: Checkpoint) -> Checkpoint:
         channel_values=checkpoint["channel_values"].copy(),
         channel_versions=checkpoint["channel_versions"].copy(),
         versions_seen={k: v.copy() for k, v in checkpoint["versions_seen"].items()},
+        pending_sends=checkpoint.get("pending_sends", []).copy(),
     )
 
 
@@ -98,8 +101,8 @@ class CheckpointTuple(NamedTuple):
     config: RunnableConfig
     checkpoint: Checkpoint
     metadata: CheckpointMetadata
-    parent_config: Optional[RunnableConfig] = None
-    pending_writes: Optional[List[PendingWrite]] = None
+    parent_config: RunnableConfig | None = None
+    pending_writes: list[PendingWrite] | None = None
 
 
 class BaseCheckpointSaver(Generic[V]):
@@ -121,11 +124,20 @@ class BaseCheckpointSaver(Generic[V]):
     def __init__(
         self,
         *,
-        serde: Optional[SerializerProtocol] = None,
+        serde: SerializerProtocol | None = None,
     ) -> None:
         self.serde = maybe_add_typed_methods(serde or self.serde)
 
-    def get(self, config: RunnableConfig) -> Optional[Checkpoint]:
+    @property
+    def config_specs(self) -> list:
+        """Define the configuration options for the checkpoint saver.
+
+        Returns:
+            list: List of configuration field specs.
+        """
+        return []
+
+    def get(self, config: RunnableConfig) -> Checkpoint | None:
         """Fetch a checkpoint using the given configuration.
 
         Args:
@@ -137,7 +149,7 @@ class BaseCheckpointSaver(Generic[V]):
         if value := self.get_tuple(config):
             return value.checkpoint
 
-    def get_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
+    def get_tuple(self, config: RunnableConfig) -> CheckpointTuple | None:
         """Fetch a checkpoint tuple using the given configuration.
 
         Args:
@@ -153,11 +165,11 @@ class BaseCheckpointSaver(Generic[V]):
 
     def list(
         self,
-        config: Optional[RunnableConfig],
+        config: RunnableConfig | None,
         *,
-        filter: Optional[dict[str, Any]] = None,
-        before: Optional[RunnableConfig] = None,
-        limit: Optional[int] = None,
+        filter: dict[str, Any] | None = None,
+        before: RunnableConfig | None = None,
+        limit: int | None = None,
     ) -> Iterator[CheckpointTuple]:
         """List checkpoints that match the given criteria.
 
@@ -229,7 +241,7 @@ class BaseCheckpointSaver(Generic[V]):
         """
         raise NotImplementedError
 
-    async def aget(self, config: RunnableConfig) -> Optional[Checkpoint]:
+    async def aget(self, config: RunnableConfig) -> Checkpoint | None:
         """Asynchronously fetch a checkpoint using the given configuration.
 
         Args:
@@ -241,7 +253,7 @@ class BaseCheckpointSaver(Generic[V]):
         if value := await self.aget_tuple(config):
             return value.checkpoint
 
-    async def aget_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
+    async def aget_tuple(self, config: RunnableConfig) -> CheckpointTuple | None:
         """Asynchronously fetch a checkpoint tuple using the given configuration.
 
         Args:
@@ -257,11 +269,11 @@ class BaseCheckpointSaver(Generic[V]):
 
     async def alist(
         self,
-        config: Optional[RunnableConfig],
+        config: RunnableConfig | None,
         *,
-        filter: Optional[dict[str, Any]] = None,
-        before: Optional[RunnableConfig] = None,
-        limit: Optional[int] = None,
+        filter: dict[str, Any] | None = None,
+        before: RunnableConfig | None = None,
+        limit: int | None = None,
     ) -> AsyncIterator[CheckpointTuple]:
         """Asynchronously list checkpoints that match the given criteria.
 
@@ -334,7 +346,7 @@ class BaseCheckpointSaver(Generic[V]):
         """
         raise NotImplementedError
 
-    def get_next_version(self, current: Optional[V]) -> V:
+    def get_next_version(self, current: V | None, channel: None) -> V:
         """Generate the next version ID for a channel.
 
         Default is to use integer versions, incrementing by 1. If you override, you can use str/int/float versions,
@@ -342,6 +354,7 @@ class BaseCheckpointSaver(Generic[V]):
 
         Args:
             current: The current version identifier (int, float, or str).
+            channel: Deprecated argument, kept for backwards compatibility.
 
         Returns:
             V: The next version identifier, which must be increasing.
@@ -361,7 +374,7 @@ class EmptyChannelError(Exception):
     pass
 
 
-def get_checkpoint_id(config: RunnableConfig) -> Optional[str]:
+def get_checkpoint_id(config: RunnableConfig) -> str | None:
     """Get checkpoint ID in a backwards-compatible manner (fallback on thread_ts)."""
     return config["configurable"].get(
         "checkpoint_id", config["configurable"].get("thread_ts")
@@ -379,11 +392,10 @@ def get_checkpoint_metadata(
     for obj in (config.get("metadata"), config.get("configurable")):
         if not obj:
             continue
-        for key in obj:
+        for key, v in obj.items():
             if key in metadata or key in EXCLUDED_METADATA_KEYS or key.startswith("__"):
                 continue
-            v = obj[key]
-            if isinstance(v, str):
+            elif isinstance(v, str):
                 metadata[key] = v.replace("\u0000", "")
             elif isinstance(v, (int, bool, float)):
                 metadata[key] = v
@@ -400,7 +412,65 @@ Each Checkpointer implementation should use this mapping in put_writes.
 WRITES_IDX_MAP = {ERROR: -1, SCHEDULED: -2, INTERRUPT: -3, RESUME: -4}
 
 EXCLUDED_METADATA_KEYS = {
+    "thread_id",
+    "thread_ts",
     "checkpoint_id",
     "checkpoint_ns",
     "checkpoint_map",
+    "langgraph_step",
+    "langgraph_node",
+    "langgraph_triggers",
+    "langgraph_path",
+    "langgraph_checkpoint_ns",
 }
+
+# --- below are deprecated utilities used by past versions of LangGraph ---
+
+LATEST_VERSION = 2
+
+
+def empty_checkpoint() -> Checkpoint:
+    from datetime import datetime, timezone
+
+    return Checkpoint(
+        v=LATEST_VERSION,
+        id=str(uuid6(clock_seq=-2)),
+        ts=datetime.now(timezone.utc).isoformat(),
+        channel_values={},
+        channel_versions={},
+        versions_seen={},
+        pending_sends=[],
+    )
+
+
+def create_checkpoint(
+    checkpoint: Checkpoint,
+    channels: Mapping[str, ChannelProtocol] | None,
+    step: int,
+    *,
+    id: str | None = None,
+) -> Checkpoint:
+    """Create a checkpoint for the given channels."""
+    from datetime import datetime, timezone
+
+    ts = datetime.now(timezone.utc).isoformat()
+    if channels is None:
+        values = checkpoint["channel_values"]
+    else:
+        values = {}
+        for k, v in channels.items():
+            if k not in checkpoint["channel_versions"]:
+                continue
+            try:
+                values[k] = v.checkpoint()
+            except EmptyChannelError:
+                pass
+    return Checkpoint(
+        v=LATEST_VERSION,
+        ts=ts,
+        id=id or str(uuid6(clock_seq=step)),
+        channel_values=values,
+        channel_versions=checkpoint["channel_versions"],
+        versions_seen=checkpoint["versions_seen"],
+        pending_sends=checkpoint.get("pending_sends", []),
+    )

libs/checkpoint/langgraph/checkpoint/base/id.py

@@ -3,10 +3,11 @@ https://github.com/oittaa/uuid6-python/blob/main/src/uuid6/__init__.py#L95
 Bundled in to avoid install issues with uuid6 package
 """
 
+from __future__ import annotations
+
 import random
 import time
 import uuid
-from typing import Optional
 
 _last_v6_timestamp = None
 
@@ -18,12 +19,12 @@ class UUID(uuid.UUID):
 
     def __init__(
         self,
-        hex: Optional[str] = None,
-        bytes: Optional[bytes] = None,
-        bytes_le: Optional[bytes] = None,
-        fields: Optional[tuple[int, int, int, int, int, int]] = None,
-        int: Optional[int] = None,
-        version: Optional[int] = None,
+        hex: str | None = None,
+        bytes: bytes | None = None,
+        bytes_le: bytes | None = None,
+        fields: tuple[int, int, int, int, int, int] | None = None,
+        int: int | None = None,
+        version: int | None = None,
         *,
         is_safe: uuid.SafeUUID = uuid.SafeUUID.unknown,
     ) -> None:
@@ -75,7 +76,7 @@ def _subsec_decode(value: int) -> int:
     return -(-value * 10**6 // 2**20)
 
 
-def uuid6(node: Optional[int] = None, clock_seq: Optional[int] = None) -> UUID:
+def uuid6(node: int | None = None, clock_seq: int | None = None) -> UUID:
     r"""UUID version 6 is a field-compatible version of UUIDv1, reordered for
     improved DB locality. It is expected that UUIDv6 will primarily be
     used in contexts where there are existing v1 UUIDs. Systems that do

libs/checkpoint/langgraph/checkpoint/memory/__init__.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import logging
 import os
 import pickle
@@ -7,7 +9,7 @@ from collections import defaultdict
 from collections.abc import AsyncIterator, Iterator, Sequence
 from contextlib import AbstractAsyncContextManager, AbstractContextManager, ExitStack
 from types import TracebackType
-from typing import Any, Optional, Union
+from typing import Any
 
 from langchain_core.runnables import RunnableConfig
 
@@ -63,9 +65,7 @@ class InMemorySaver(
     # thread ID ->  checkpoint NS -> checkpoint ID -> checkpoint mapping
     storage: defaultdict[
         str,
-        dict[
-            str, dict[str, tuple[tuple[str, bytes], tuple[str, bytes], Optional[str]]]
-        ],
+        dict[str, dict[str, tuple[tuple[str, bytes], tuple[str, bytes], str | None]]],
     ]
     # (thread ID, checkpoint NS, checkpoint ID) -> (task ID, write idx)
     writes: defaultdict[
@@ -74,7 +74,7 @@ class InMemorySaver(
     ]
     blobs: dict[
         tuple[
-            str, str, str, Union[str, int, float]
+            str, str, str, str | int | float
         ],  # thread id, checkpoint ns, channel, version
         tuple[str, bytes],
     ]
@@ -82,7 +82,7 @@ class InMemorySaver(
     def __init__(
         self,
         *,
-        serde: Optional[SerializerProtocol] = None,
+        serde: SerializerProtocol | None = None,
         factory: type[defaultdict] = defaultdict,
     ) -> None:
         super().__init__(serde=serde)
@@ -95,26 +95,26 @@ class InMemorySaver(
             self.stack.enter_context(self.writes)  # type: ignore[arg-type]
             self.stack.enter_context(self.blobs)  # type: ignore[arg-type]
 
-    def __enter__(self) -> "InMemorySaver":
+    def __enter__(self) -> InMemorySaver:
         return self.stack.__enter__()
 
     def __exit__(
         self,
-        exc_type: Optional[type[BaseException]],
-        exc_value: Optional[BaseException],
-        traceback: Optional[TracebackType],
-    ) -> Optional[bool]:
+        exc_type: type[BaseException] | None,
+        exc_value: BaseException | None,
+        traceback: TracebackType | None,
+    ) -> bool | None:
         return self.stack.__exit__(exc_type, exc_value, traceback)
 
-    async def __aenter__(self) -> "InMemorySaver":
+    async def __aenter__(self) -> InMemorySaver:
         return self.stack.__enter__()
 
     async def __aexit__(
         self,
-        __exc_type: Optional[type[BaseException]],
-        __exc_value: Optional[BaseException],
-        __traceback: Optional[TracebackType],
-    ) -> Optional[bool]:
+        __exc_type: type[BaseException] | None,
+        __exc_value: BaseException | None,
+        __traceback: TracebackType | None,
+    ) -> bool | None:
         return self.stack.__exit__(__exc_type, __exc_value, __traceback)
 
     def _load_blobs(
@@ -129,7 +129,7 @@ class InMemorySaver(
                     channel_values[k] = self.serde.loads_typed(vv)
         return channel_values
 
-    def get_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
+    def get_tuple(self, config: RunnableConfig) -> CheckpointTuple | None:
         """Get a checkpoint tuple from the in-memory storage.
 
         This method retrieves a checkpoint tuple from the in-memory storage based on the
@@ -213,11 +213,11 @@ class InMemorySaver(
 
     def list(
         self,
-        config: Optional[RunnableConfig],
+        config: RunnableConfig | None,
         *,
-        filter: Optional[dict[str, Any]] = None,
-        before: Optional[RunnableConfig] = None,
-        limit: Optional[int] = None,
+        filter: dict[str, Any] | None = None,
+        before: RunnableConfig | None = None,
+        limit: int | None = None,
     ) -> Iterator[CheckpointTuple]:
         """List checkpoints from the in-memory storage.
 
@@ -422,7 +422,7 @@ class InMemorySaver(
             if k[0] == thread_id:
                 del self.blobs[k]
 
-    async def aget_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
+    async def aget_tuple(self, config: RunnableConfig) -> CheckpointTuple | None:
         """Asynchronous version of get_tuple.
 
         This method is an asynchronous wrapper around get_tuple that runs the synchronous
@@ -438,11 +438,11 @@ class InMemorySaver(
 
     async def alist(
         self,
-        config: Optional[RunnableConfig],
+        config: RunnableConfig | None,
         *,
-        filter: Optional[dict[str, Any]] = None,
-        before: Optional[RunnableConfig] = None,
-        limit: Optional[int] = None,
+        filter: dict[str, Any] | None = None,
+        before: RunnableConfig | None = None,
+        limit: int | None = None,
     ) -> AsyncIterator[CheckpointTuple]:
         """Asynchronous version of list.
 
@@ -512,7 +512,7 @@ class InMemorySaver(
         """
         return self.delete_thread(thread_id)
 
-    def get_next_version(self, current: Optional[str]) -> str:
+    def get_next_version(self, current: str | None, channel: None) -> str:
         if current is None:
             current_v = 0
         elif isinstance(current, int):
@@ -571,7 +571,7 @@ class PersistentDict(defaultdict):
         self.sync()
         self.clear()
 
-    def __enter__(self) -> "PersistentDict":
+    def __enter__(self) -> PersistentDict:
         return self
 
     def __exit__(self, *exc_info: Any) -> None:

libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import dataclasses
 import decimal
 import importlib
@@ -5,6 +7,7 @@ import json
 import pathlib
 import pickle
 import re
+import sys
 from collections import deque
 from collections.abc import Sequence
 from datetime import date, datetime, time, timedelta, timezone
@@ -18,7 +21,7 @@ from ipaddress import (
     IPv6Interface,
     IPv6Network,
 )
-from typing import Any, Callable, Optional, Union, cast
+from typing import Any, Callable, cast
 from uuid import UUID
 from zoneinfo import ZoneInfo
 
@@ -41,7 +44,7 @@ class JsonPlusSerializer(SerializerProtocol):
         self,
         *,
         pickle_fallback: bool = False,
-        __unpack_ext_hook__: Optional[Callable[[int, bytes], Any]] = None,
+        __unpack_ext_hook__: Callable[[int, bytes], Any] | None = None,
     ) -> None:
         self.pickle_fallback = pickle_fallback
         self._unpack_ext_hook = (
@@ -52,11 +55,11 @@ class JsonPlusSerializer(SerializerProtocol):
 
     def _encode_constructor_args(
         self,
-        constructor: Union[Callable, type[Any]],
+        constructor: Callable | type[Any],
         *,
-        method: Union[None, str, Sequence[Union[None, str]]] = None,
-        args: Optional[Sequence[Any]] = None,
-        kwargs: Optional[dict[str, Any]] = None,
+        method: None | str | Sequence[None | str] = None,
+        args: Sequence[Any] | None = None,
+        kwargs: dict[str, Any] | None = None,
     ) -> dict[str, Any]:
         out = {
             "lc": 2,
@@ -71,7 +74,7 @@ class JsonPlusSerializer(SerializerProtocol):
             out["kwargs"] = kwargs
         return out
 
-    def _default(self, obj: Any) -> Union[str, dict[str, Any]]:
+    def _default(self, obj: Any) -> str | dict[str, Any]:
         if isinstance(obj, Serializable):
             return cast(dict[str, Any], obj.to_json())
         elif hasattr(obj, "model_dump") and callable(obj.model_dump):
@@ -249,9 +252,10 @@ EXT_CONSTRUCTOR_KW_ARGS = 2
 EXT_METHOD_SINGLE_ARG = 3
 EXT_PYDANTIC_V1 = 4
 EXT_PYDANTIC_V2 = 5
+EXT_NUMPY_ARRAY = 6
 
 
-def _msgpack_default(obj: Any) -> Union[str, ormsgpack.Ext]:
+def _msgpack_default(obj: Any) -> str | ormsgpack.Ext:
     if hasattr(obj, "model_dump") and callable(obj.model_dump):  # pydantic v2
         return ormsgpack.Ext(
             EXT_PYDANTIC_V2,
@@ -318,13 +322,6 @@ def _msgpack_default(obj: Any) -> Union[str, ormsgpack.Ext]:
                 (obj.__class__.__module__, obj.__class__.__name__, obj.hex),
             ),
         )
-    elif isinstance(obj, bytearray):
-        return ormsgpack.Ext(
-            EXT_CONSTRUCTOR_SINGLE_ARG,
-            _msgpack_enc(
-                (obj.__class__.__module__, obj.__class__.__name__, bytes(obj)),
-            ),
-        )
     elif isinstance(obj, decimal.Decimal):
         return ormsgpack.Ext(
             EXT_CONSTRUCTOR_SINGLE_ARG,
@@ -463,6 +460,22 @@ def _msgpack_default(obj: Any) -> Union[str, ormsgpack.Ext]:
                 ),
             ),
         )
+    elif (np_mod := sys.modules.get("numpy")) is not None and isinstance(
+        obj, np_mod.ndarray
+    ):
+        order = "F" if obj.flags.f_contiguous and not obj.flags.c_contiguous else "C"
+        if obj.flags.c_contiguous:
+            mv = memoryview(obj)
+            try:
+                meta = (obj.dtype.str, obj.shape, order, mv)
+                return ormsgpack.Ext(EXT_NUMPY_ARRAY, _msgpack_enc(meta))
+            finally:
+                mv.release()
+        else:
+            buf = obj.tobytes(order="A")
+            meta = (obj.dtype.str, obj.shape, order, buf)
+            return ormsgpack.Ext(EXT_NUMPY_ARRAY, _msgpack_enc(meta))
+
     elif isinstance(obj, BaseException):
         return repr(obj)
     else:
@@ -544,6 +557,17 @@ def _msgpack_ext_hook(code: int, data: bytes) -> Any:
                 return tup[2]
             except NameError:
                 return
+    elif code == EXT_NUMPY_ARRAY:
+        try:
+            import numpy as _np
+
+            dtype_str, shape, order, buf = ormsgpack.unpackb(
+                data, ext_hook=_msgpack_ext_hook, option=ormsgpack.OPT_NON_STR_KEYS
+            )
+            arr = _np.frombuffer(buf, dtype=_np.dtype(dtype_str))
+            return arr.reshape(shape, order=order)
+        except Exception:
+            return
 
 
 def _msgpack_ext_hook_to_json(code: int, data: bytes) -> Any:
@@ -624,6 +648,19 @@ def _msgpack_ext_hook_to_json(code: int, data: bytes) -> Any:
             return tup[2]
         except Exception:
             return
+    elif code == EXT_NUMPY_ARRAY:
+        try:
+            import numpy as _np
+
+            dtype_str, shape, order, buf = ormsgpack.unpackb(
+                data,
+                ext_hook=_msgpack_ext_hook_to_json,
+                option=ormsgpack.OPT_NON_STR_KEYS,
+            )
+            arr = _np.frombuffer(buf, dtype=_np.dtype(dtype_str))
+            return arr.reshape(shape, order=order).tolist()
+        except Exception:
+            return
 
 
 _option = (

libs/checkpoint/langgraph/checkpoint/serde/types.py

@@ -1,4 +1,13 @@
-from typing import Any, Protocol, TypeVar, runtime_checkable
+from collections.abc import Sequence
+from typing import (
+    Any,
+    Optional,
+    Protocol,
+    TypeVar,
+    runtime_checkable,
+)
+
+from typing_extensions import Self
 
 ERROR = "__error__"
 SCHEDULED = "__scheduled__"
@@ -11,6 +20,25 @@ Update = TypeVar("Update", contravariant=True)
 C = TypeVar("C")
 
 
+class ChannelProtocol(Protocol[Value, Update, C]):
+    # Mirrors langgraph.channels.base.BaseChannel
+    @property
+    def ValueType(self) -> Any: ...
+
+    @property
+    def UpdateType(self) -> Any: ...
+
+    def checkpoint(self) -> Optional[C]: ...
+
+    def from_checkpoint(self, checkpoint: Optional[C]) -> Self: ...
+
+    def update(self, values: Sequence[Update]) -> bool: ...
+
+    def get(self) -> Value: ...
+
+    def consume(self) -> bool: ...
+
+
 @runtime_checkable
 class SendProtocol(Protocol):
     # Mirrors langgraph.constants.Send

libs/checkpoint/langgraph/store/base/__init__.py

@@ -9,6 +9,8 @@ Core types:
     - Op: Get/Put/Search/List operations
 """
 
+from __future__ import annotations
+
 from abc import ABC, abstractmethod
 from collections.abc import Iterable
 from datetime import datetime
@@ -16,7 +18,6 @@ from typing import (
     Any,
     Literal,
     NamedTuple,
-    Optional,
     TypedDict,
     Union,
     cast,
@@ -127,7 +128,7 @@ class SearchItem(Item):
         value: dict[str, Any],
         created_at: datetime,
         updated_at: datetime,
-        score: Optional[float] = None,
+        score: float | None = None,
     ) -> None:
         """Initialize a result item.
 
@@ -242,7 +243,7 @@ class SearchOp(NamedTuple):
         ```
     """
 
-    filter: Optional[dict[str, Any]] = None
+    filter: dict[str, Any] | None = None
     """Key-value pairs for filtering results based on exact matches or comparison operators.
 
     The filter supports both exact matches and operator-based comparisons.
@@ -284,7 +285,7 @@ class SearchOp(NamedTuple):
     offset: int = 0
     """Number of matching items to skip for pagination."""
 
-    query: Optional[str] = None
+    query: str | None = None
     """Natural language search query for semantic search capabilities.
 
     ???+ example "Examples"
@@ -379,7 +380,7 @@ class ListNamespacesOp(NamedTuple):
 
     """
 
-    match_conditions: Optional[tuple[MatchCondition, ...]] = None
+    match_conditions: tuple[MatchCondition, ...] | None = None
     """Optional conditions for filtering namespaces.
 
     ???+ example "Examples"
@@ -397,7 +398,7 @@ class ListNamespacesOp(NamedTuple):
         ```
     """
 
-    max_depth: Optional[int] = None
+    max_depth: int | None = None
     """Maximum depth of namespace hierarchy to return.
 
     Note:
@@ -452,7 +453,7 @@ class PutOp(NamedTuple):
         the full path would effectively be "documents/user123/report1"
     """
 
-    value: Optional[dict[str, Any]]
+    value: dict[str, Any] | None
     """The data to store, or None to mark the item for deletion.
 
     The value must be a dictionary with string keys and JSON-serializable values.
@@ -466,7 +467,7 @@ class PutOp(NamedTuple):
         }
     """
 
-    index: Optional[Union[Literal[False], list[str]]] = None  # type: ignore[assignment]
+    index: Literal[False] | list[str] | None = None  # type: ignore[assignment]
     """Controls how the item's fields are indexed for search operations.
 
     Indexing configuration determines how the item can be found through search:
@@ -501,7 +502,7 @@ class PutOp(NamedTuple):
         ]
         ```
     """
-    ttl: Optional[float] = None
+    ttl: float | None = None
     """Controls the TTL (time-to-live) for the item in minutes.
 
     If provided, and if the store you are using supports this feature, the item
@@ -530,14 +531,14 @@ class TTLConfig(TypedDict, total=False):
     This can be overridden per-operation by explicitly setting refresh_ttl.
     Defaults to True if not configured.
     """
-    default_ttl: Optional[float]
+    default_ttl: float | None
     """Default TTL (time-to-live) in minutes for new items.
     
     If provided, new items will expire after this many minutes after their last access.
     The expiration timer refreshes on both read and write operations.
     Defaults to None (no expiration).
     """
-    sweep_interval_minutes: Optional[int]
+    sweep_interval_minutes: int | None
     """Interval in minutes between TTL sweep operations.
     
     If provided, the store will periodically delete expired items based on TTL.
@@ -565,7 +566,7 @@ class IndexConfig(TypedDict, total=False):
         - cohere:embed-multilingual-light-v3.0: 384
     """
 
-    embed: Union[Embeddings, EmbeddingsFunc, AEmbeddingsFunc, str]
+    embed: Embeddings | EmbeddingsFunc | AEmbeddingsFunc | str
     """Optional function to generate embeddings from text.
     
     Can be specified in three ways:
@@ -633,7 +634,7 @@ class IndexConfig(TypedDict, total=False):
         ```
     """
 
-    fields: Optional[list[str]]
+    fields: list[str] | None
     """Fields to extract text from for embedding generation.
     
     Controls which parts of stored items are embedded for semantic search. Follows JSON path syntax:
@@ -690,7 +691,7 @@ class BaseStore(ABC):
     """
 
     supports_ttl: bool = False
-    ttl_config: Optional[TTLConfig] = None
+    ttl_config: TTLConfig | None = None
 
     __slots__ = ("__weakref__",)
 
@@ -723,8 +724,8 @@ class BaseStore(ABC):
         namespace: tuple[str, ...],
         key: str,
         *,
-        refresh_ttl: Optional[bool] = None,
-    ) -> Optional[Item]:
+        refresh_ttl: bool | None = None,
+    ) -> Item | None:
         """Retrieve a single item.
 
         Args:
@@ -746,11 +747,11 @@ class BaseStore(ABC):
         namespace_prefix: tuple[str, ...],
         /,
         *,
-        query: Optional[str] = None,
-        filter: Optional[dict[str, Any]] = None,
+        query: str | None = None,
+        filter: dict[str, Any] | None = None,
         limit: int = 10,
         offset: int = 0,
-        refresh_ttl: Optional[bool] = None,
+        refresh_ttl: bool | None = None,
     ) -> list[SearchItem]:
         """Search for items within a namespace prefix.
 
@@ -817,9 +818,9 @@ class BaseStore(ABC):
         namespace: tuple[str, ...],
         key: str,
         value: dict[str, Any],
-        index: Optional[Union[Literal[False], list[str]]] = None,
+        index: Literal[False] | list[str] | None = None,
         *,
-        ttl: Union[Optional[float], "NotProvided"] = NOT_PROVIDED,
+        ttl: float | None | NotProvided = NOT_PROVIDED,
     ) -> None:
         """Store or update an item in the store.
 
@@ -901,9 +902,9 @@ class BaseStore(ABC):
     def list_namespaces(
         self,
         *,
-        prefix: Optional[NamespacePath] = None,
-        suffix: Optional[NamespacePath] = None,
-        max_depth: Optional[int] = None,
+        prefix: NamespacePath | None = None,
+        suffix: NamespacePath | None = None,
+        max_depth: int | None = None,
         limit: int = 100,
         offset: int = 0,
     ) -> list[tuple[str, ...]]:
@@ -956,8 +957,8 @@ class BaseStore(ABC):
         namespace: tuple[str, ...],
         key: str,
         *,
-        refresh_ttl: Optional[bool] = None,
-    ) -> Optional[Item]:
+        refresh_ttl: bool | None = None,
+    ) -> Item | None:
         """Asynchronously retrieve a single item.
 
         Args:
@@ -984,11 +985,11 @@ class BaseStore(ABC):
         namespace_prefix: tuple[str, ...],
         /,
         *,
-        query: Optional[str] = None,
-        filter: Optional[dict[str, Any]] = None,
+        query: str | None = None,
+        filter: dict[str, Any] | None = None,
         limit: int = 10,
         offset: int = 0,
-        refresh_ttl: Optional[bool] = None,
+        refresh_ttl: bool | None = None,
     ) -> list[SearchItem]:
         """Asynchronously search for items within a namespace prefix.
 
@@ -1058,9 +1059,9 @@ class BaseStore(ABC):
         namespace: tuple[str, ...],
         key: str,
         value: dict[str, Any],
-        index: Optional[Union[Literal[False], list[str]]] = None,
+        index: Literal[False] | list[str] | None = None,
         *,
-        ttl: Union[Optional[float], "NotProvided"] = NOT_PROVIDED,
+        ttl: float | None | NotProvided = NOT_PROVIDED,
     ) -> None:
         """Asynchronously store or update an item in the store.
 
@@ -1150,9 +1151,9 @@ class BaseStore(ABC):
     async def alist_namespaces(
         self,
         *,
-        prefix: Optional[NamespacePath] = None,
-        suffix: Optional[NamespacePath] = None,
-        max_depth: Optional[int] = None,
+        prefix: NamespacePath | None = None,
+        suffix: NamespacePath | None = None,
+        max_depth: int | None = None,
         limit: int = 100,
         offset: int = 0,
     ) -> list[tuple[str, ...]]:
@@ -1226,7 +1227,7 @@ def _validate_namespace(namespace: tuple[str, ...]) -> None:
 
 
 def _ensure_refresh(
-    ttl_config: Optional[TTLConfig], refresh_ttl: Optional[bool] = None
+    ttl_config: TTLConfig | None, refresh_ttl: bool | None = None
 ) -> bool:
     if refresh_ttl is not None:
         return refresh_ttl
@@ -1236,9 +1237,9 @@ def _ensure_refresh(
 
 
 def _ensure_ttl(
-    ttl_config: Optional[TTLConfig],
-    ttl: Union[Optional[float], "NotProvided"] = NOT_PROVIDED,
-) -> Optional[float]:
+    ttl_config: TTLConfig | None,
+    ttl: float | None | NotProvided = NOT_PROVIDED,
+) -> float | None:
     if ttl is NOT_PROVIDED:
         if ttl_config:
             return ttl_config.get("default_ttl")

libs/checkpoint/langgraph/store/base/batch.py

@@ -1,10 +1,12 @@
 """Utilities for batching operations in a background task."""
 
+from __future__ import annotations
+
 import asyncio
 import functools
 import weakref
 from collections.abc import Iterable
-from typing import Any, Callable, Literal, Optional, TypeVar, Union
+from typing import Any, Callable, Literal, TypeVar
 
 from langgraph.store.base import (
     NOT_PROVIDED,
@@ -30,7 +32,7 @@ F = TypeVar("F", bound=Callable)
 
 def _check_loop(func: F) -> F:
     @functools.wraps(func)
-    def wrapper(store: "AsyncBatchedBaseStore", *args: Any, **kwargs: Any) -> Any:
+    def wrapper(store: AsyncBatchedBaseStore, *args: Any, **kwargs: Any) -> Any:
         method_name: str = func.__name__
         try:
             current_loop = asyncio.get_running_loop()
@@ -75,8 +77,8 @@ class AsyncBatchedBaseStore(BaseStore):
         namespace: tuple[str, ...],
         key: str,
         *,
-        refresh_ttl: Optional[bool] = None,
-    ) -> Optional[Item]:
+        refresh_ttl: bool | None = None,
+    ) -> Item | None:
         assert not self._task.done()
         fut = self._loop.create_future()
         self._aqueue.put_nowait(
@@ -96,11 +98,11 @@ class AsyncBatchedBaseStore(BaseStore):
         namespace_prefix: tuple[str, ...],
         /,
         *,
-        query: Optional[str] = None,
-        filter: Optional[dict[str, Any]] = None,
+        query: str | None = None,
+        filter: dict[str, Any] | None = None,
         limit: int = 10,
         offset: int = 0,
-        refresh_ttl: Optional[bool] = None,
+        refresh_ttl: bool | None = None,
     ) -> list[SearchItem]:
         assert not self._task.done()
         fut = self._loop.create_future()
@@ -124,9 +126,9 @@ class AsyncBatchedBaseStore(BaseStore):
         namespace: tuple[str, ...],
         key: str,
         value: dict[str, Any],
-        index: Optional[Union[Literal[False], list[str]]] = None,
+        index: Literal[False] | list[str] | None = None,
         *,
-        ttl: Union[Optional[float], "NotProvided"] = NOT_PROVIDED,
+        ttl: float | None | NotProvided = NOT_PROVIDED,
     ) -> None:
         assert not self._task.done()
         _validate_namespace(namespace)
@@ -154,9 +156,9 @@ class AsyncBatchedBaseStore(BaseStore):
     async def alist_namespaces(
         self,
         *,
-        prefix: Optional[NamespacePath] = None,
-        suffix: Optional[NamespacePath] = None,
-        max_depth: Optional[int] = None,
+        prefix: NamespacePath | None = None,
+        suffix: NamespacePath | None = None,
+        max_depth: int | None = None,
         limit: int = 100,
         offset: int = 0,
     ) -> list[tuple[str, ...]]:
@@ -187,8 +189,8 @@ class AsyncBatchedBaseStore(BaseStore):
         namespace: tuple[str, ...],
         key: str,
         *,
-        refresh_ttl: Optional[bool] = None,
-    ) -> Optional[Item]:
+        refresh_ttl: bool | None = None,
+    ) -> Item | None:
         return asyncio.run_coroutine_threadsafe(
             self.aget(namespace, key=key, refresh_ttl=refresh_ttl), self._loop
         ).result()
@@ -199,11 +201,11 @@ class AsyncBatchedBaseStore(BaseStore):
         namespace_prefix: tuple[str, ...],
         /,
         *,
-        query: Optional[str] = None,
-        filter: Optional[dict[str, Any]] = None,
+        query: str | None = None,
+        filter: dict[str, Any] | None = None,
         limit: int = 10,
         offset: int = 0,
-        refresh_ttl: Optional[bool] = None,
+        refresh_ttl: bool | None = None,
     ) -> list[SearchItem]:
         return asyncio.run_coroutine_threadsafe(
             self.asearch(
@@ -223,9 +225,9 @@ class AsyncBatchedBaseStore(BaseStore):
         namespace: tuple[str, ...],
         key: str,
         value: dict[str, Any],
-        index: Optional[Union[Literal[False], list[str]]] = None,
+        index: Literal[False] | list[str] | None = None,
         *,
-        ttl: Union[Optional[float], "NotProvided"] = NOT_PROVIDED,
+        ttl: float | None | NotProvided = NOT_PROVIDED,
     ) -> None:
         _validate_namespace(namespace)
         asyncio.run_coroutine_threadsafe(
@@ -253,9 +255,9 @@ class AsyncBatchedBaseStore(BaseStore):
     def list_namespaces(
         self,
         *,
-        prefix: Optional[NamespacePath] = None,
-        suffix: Optional[NamespacePath] = None,
-        max_depth: Optional[int] = None,
+        prefix: NamespacePath | None = None,
+        suffix: NamespacePath | None = None,
+        max_depth: int | None = None,
         limit: int = 100,
         offset: int = 0,
     ) -> list[tuple[str, ...]]:
@@ -271,7 +273,7 @@ class AsyncBatchedBaseStore(BaseStore):
         ).result()
 
 
-def _dedupe_ops(values: list[Op]) -> tuple[Optional[list[int]], list[Op]]:
+def _dedupe_ops(values: list[Op]) -> tuple[list[int] | None, list[Op]]:
     """Dedupe operations while preserving order for results.
 
     Args:

libs/checkpoint/langgraph/store/base/embed.py

@@ -6,11 +6,13 @@ with LangChain-compatible tools while maintaining support for both synchronous a
 asynchronous operations.
 """
 
+from __future__ import annotations
+
 import asyncio
 import functools
 import json
 from collections.abc import Awaitable, Sequence
-from typing import Any, Callable, Optional, Union
+from typing import Any, Callable
 
 from langchain_core.embeddings import Embeddings
 
@@ -30,7 +32,7 @@ Similar to EmbeddingsFunc, but returns an awaitable that resolves to the embeddi
 
 
 def ensure_embeddings(
-    embed: Union[Embeddings, EmbeddingsFunc, AEmbeddingsFunc, str, None],
+    embed: Embeddings | EmbeddingsFunc | AEmbeddingsFunc | str | None,
 ) -> Embeddings:
     """Ensure that an embedding function conforms to LangChain's Embeddings interface.
 
@@ -141,7 +143,7 @@ class EmbeddingsLambda(Embeddings):
 
     def __init__(
         self,
-        func: Union[EmbeddingsFunc, AEmbeddingsFunc],
+        func: EmbeddingsFunc | AEmbeddingsFunc,
     ) -> None:
         if func is None:
             raise ValueError("func must be provided")
@@ -221,7 +223,7 @@ class EmbeddingsLambda(Embeddings):
         return (await afunc([text]))[0]
 
 
-def get_text_at_path(obj: Any, path: Union[str, list[str]]) -> list[str]:
+def get_text_at_path(obj: Any, path: str | list[str]) -> list[str]:
     """Extract text from an object using a path expression or pre-tokenized path.
 
     Args:
@@ -279,7 +281,7 @@ def get_text_at_path(obj: Any, path: Union[str, list[str]]) -> list[str]:
             for field in fields:
                 nested_tokens = tokenize_path(field)
                 if nested_tokens:
-                    current_obj: Optional[dict] = obj
+                    current_obj: dict | None = obj
                     for nested_token in nested_tokens:
                         if (
                             isinstance(current_obj, dict)
@@ -404,7 +406,7 @@ def _is_async_callable(
 
 
 @functools.lru_cache
-def _get_init_embeddings() -> Optional[Callable[[str], Embeddings]]:
+def _get_init_embeddings() -> Callable[[str], Embeddings] | None:
     try:
         from langchain.embeddings import init_embeddings  # type: ignore
 

libs/checkpoint/langgraph/store/memory/__init__.py

@@ -99,6 +99,8 @@ Tip:
     ```
 """
 
+from __future__ import annotations
+
 import asyncio
 import concurrent.futures as cf
 import functools
@@ -107,7 +109,7 @@ from collections import defaultdict
 from collections.abc import Iterable
 from datetime import datetime, timezone
 from importlib import util
-from typing import Any, Optional
+from typing import Any
 
 from langchain_core.embeddings import Embeddings
 
@@ -178,7 +180,7 @@ class InMemoryStore(BaseStore):
         "embeddings",
     )
 
-    def __init__(self, *, index: Optional[IndexConfig] = None) -> None:
+    def __init__(self, *, index: IndexConfig | None = None) -> None:
         # Both _data and _vectors are wrapped in the In-memory API
         # Do not change their names
         self._data: dict[tuple[str, ...], dict[str, Item]] = defaultdict(dict)
@@ -189,7 +191,7 @@ class InMemoryStore(BaseStore):
         self.index_config = index
         if self.index_config:
             self.index_config = self.index_config.copy()
-            self.embeddings: Optional[Embeddings] = ensure_embeddings(
+            self.embeddings: Embeddings | None = ensure_embeddings(
                 self.index_config.get("embed"),
             )
             self.index_config["__tokenized_fields"] = [
@@ -325,7 +327,7 @@ class InMemoryStore(BaseStore):
                 )
                 # max pooling
                 seen: set[tuple[tuple[str, ...], str]] = set()
-                kept: list[tuple[Optional[float], Item]] = []
+                kept: list[tuple[float | None, Item]] = []
                 for score, item in sorted_results:
                     key = (item.namespace, item.key)
                     if key in seen:
@@ -494,7 +496,7 @@ def _cosine_similarity(X: list[float], Y: list[list[float]]) -> list[float]:
     if not Y:
         return []
     if _check_numpy():
-        import numpy as np  # type: ignore[import-not-found]
+        import numpy as np
 
         X_arr = np.array(X) if not isinstance(X, np.ndarray) else X
         Y_arr = np.array(Y) if not isinstance(Y, np.ndarray) else Y

libs/checkpoint/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "langgraph-checkpoint"
-version = "2.0.26"
+version = "2.1.0"
 description = "Library with base interfaces for LangGraph checkpoint savers."
 authors = []
 requires-python = ">=3.9"
@@ -13,7 +13,7 @@ license = "MIT"
 license-files = ['LICENSE']
 dependencies = [
     "langchain-core>=0.2.38",
-    "ormsgpack>=1.8.0",
+    "ormsgpack>=1.10.0",
 ]
 
 [project.urls]
@@ -29,6 +29,9 @@ dev = [
   "pytest-watcher",
   "mypy",
   "dataclasses-json",
+  "numpy",
+  "pandas",
+  "pandas-stubs>=2.2.2.240807",
 ]
 
 [tool.hatch.build.targets.wheel]
@@ -46,7 +49,7 @@ lint.select = [
   "B",  # flake8-bugbear
   "I",  # isort
 ]
-lint.ignore = ["E501", "B008", "UP007", "UP006"]
+lint.ignore = ["E501", "B008"]
 
 [tool.pytest-watcher]
 now = true

libs/checkpoint/tests/checkpoint_utils.py

@@ -1,51 +0,0 @@
-from collections.abc import Mapping
-from datetime import datetime, timezone
-from typing import Any, Optional, Protocol
-
-from langgraph.checkpoint.base import Checkpoint, EmptyChannelError
-from langgraph.checkpoint.base.id import uuid6
-
-
-class ChannelProtocol(Protocol):
-    def checkpoint(self) -> Optional[Any]: ...
-
-
-def empty_checkpoint() -> Checkpoint:
-    return Checkpoint(
-        v=1,
-        id=str(uuid6(clock_seq=-2)),
-        ts=datetime.now(timezone.utc).isoformat(),
-        channel_values={},
-        channel_versions={},
-        versions_seen={},
-    )
-
-
-def create_checkpoint(
-    checkpoint: Checkpoint,
-    channels: Optional[Mapping[str, ChannelProtocol]],
-    step: int,
-    *,
-    id: Optional[str] = None,
-) -> Checkpoint:
-    """Create a checkpoint for the given channels."""
-    ts = datetime.now(timezone.utc).isoformat()
-    if channels is None:
-        values = checkpoint["channel_values"]
-    else:
-        values = {}
-        for k, v in channels.items():
-            if k not in checkpoint["channel_versions"]:
-                continue
-            try:
-                values[k] = v.checkpoint()
-            except EmptyChannelError:
-                pass
-    return Checkpoint(
-        v=1,
-        ts=ts,
-        id=id or str(uuid6(clock_seq=step)),
-        channel_values=values,
-        channel_versions=checkpoint["channel_versions"],
-        versions_seen=checkpoint["versions_seen"],
-    )

libs/checkpoint/tests/test_jsonplus.py

@@ -11,6 +11,9 @@ from ipaddress import IPv4Address
 from zoneinfo import ZoneInfo
 
 import dataclasses_json
+import numpy as np
+import pandas as pd
+import pytest
 from pydantic import BaseModel, SecretStr
 from pydantic.v1 import BaseModel as BaseModelV1
 from pydantic.v1 import SecretStr as SecretStrV1
@@ -295,19 +298,174 @@ def test_serde_jsonplus_bytearray() -> None:
     assert serde.loads_typed(dumped) == some_bytearray
 
 
-def test_loads_cannot_find() -> None:
+@pytest.mark.parametrize(
+    "arr",
+    [
+        np.arange(9, dtype=np.int32).reshape(3, 3),
+        np.asfortranarray(np.arange(9, dtype=np.float64).reshape(3, 3)),
+        np.arange(12, dtype=np.int16)[::2].reshape(3, 2),
+    ],
+)
+def test_serde_jsonplus_numpy_array(arr: np.ndarray) -> None:
     serde = JsonPlusSerializer()
 
-    dumped = (
-        "json",
-        b'{"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "MyPydanticccc"], "method": null, "args": [], "kwargs": {"foo": "foo", "bar": 1}}',
-    )
+    dumped = serde.dumps_typed(arr)
+    assert dumped[0] == "msgpack"
+    result = serde.loads_typed(dumped)
+    assert isinstance(result, np.ndarray)
+    assert result.dtype == arr.dtype
+    assert np.array_equal(result, arr)
 
-    assert serde.loads_typed(dumped) is None, "Should return None if cannot find class"
 
-    dumped = (
-        "json",
-        b'{"lc": 2, "type": "constructor", "id": ["tests", "test_jsonpluss", "MyPydantic"], "method": null, "args": [], "kwargs": {"foo": "foo", "bar": 1}}',
-    )
+@pytest.mark.parametrize(
+    "arr",
+    [
+        np.arange(6, dtype=np.float32).reshape(2, 3),
+        np.asfortranarray(np.arange(4, dtype=np.complex128).reshape(2, 2)),
+    ],
+)
+def test_serde_jsonplus_numpy_array_json_hook(arr: np.ndarray) -> None:
+    serde = JsonPlusSerializer(__unpack_ext_hook__=_msgpack_ext_hook_to_json)
+    dumped = serde.dumps_typed(arr)
+    assert dumped[0] == "msgpack"
+    result = serde.loads_typed(dumped)
+    assert isinstance(result, list)
+    assert result == arr.tolist()
 
-    assert serde.loads_typed(dumped) is None, "Should return None if cannot find module"
+
+@pytest.mark.parametrize(
+    "df",
+    [
+        pd.DataFrame(),
+        pd.DataFrame({"int_col": [1, 2, 3]}),
+        pd.DataFrame({"float_col": [1.1, 2.2, 3.3]}),
+        pd.DataFrame({"str_col": ["a", "b", "c"]}),
+        pd.DataFrame({"bool_col": [True, False, True]}),
+        pd.DataFrame(
+            {
+                "datetime_col": [
+                    datetime(2024, 1, 1),
+                    datetime(2024, 1, 2),
+                    datetime(2024, 1, 3),
+                ]
+            }
+        ),
+        pd.DataFrame(
+            {
+                "int_col": [1, 2, 3],
+                "float_col": [1.1, 2.2, 3.3],
+                "str_col": ["a", "b", "c"],
+            }
+        ),
+        pd.DataFrame(
+            {
+                "int_col": [1, 2, None],
+                "float_col": [1.1, None, 3.3],
+                "str_col": ["a", None, "c"],
+            }
+        ),
+        pd.DataFrame({"cat_col": pd.Categorical(["a", "b", "a", "c"])}),
+        pd.DataFrame(
+            {
+                "int8": pd.array([1, 2, 3], dtype="int8"),
+                "int16": pd.array([10, 20, 30], dtype="int16"),
+                "int32": pd.array([100, 200, 300], dtype="int32"),
+                "int64": pd.array([1000, 2000, 3000], dtype="int64"),
+                "float32": pd.array([1.1, 2.2, 3.3], dtype="float32"),
+                "float64": pd.array([10.1, 20.2, 30.3], dtype="float64"),
+            }
+        ),
+        pd.DataFrame({"value": [1, 2, 3]}, index=["x", "y", "z"]),
+        pd.DataFrame(
+            [[1, 2, 3, 4]],
+            columns=pd.MultiIndex.from_tuples(
+                [("A", "X"), ("A", "Y"), ("B", "X"), ("B", "Y")]
+            ),
+        ),
+        pd.DataFrame(
+            {"value": [1, 2, 3]}, index=pd.date_range("2024-01-01", periods=3, freq="D")
+        ),
+        pd.DataFrame(
+            {
+                "col1": range(1000),
+                "col2": [f"str_{i}" for i in range(1000)],
+                "col3": np.random.rand(1000),
+            }
+        ),
+        pd.DataFrame(
+            {"tz_datetime": pd.date_range("2024-01-01", periods=3, freq="D", tz="UTC")}
+        ),
+        pd.DataFrame({"timedelta": pd.to_timedelta([1, 2, 3], unit="D")}),
+        pd.DataFrame({"period": pd.period_range("2024-01", periods=3, freq="M")}),
+        pd.DataFrame({"interval": pd.interval_range(start=0, end=3, periods=3)}),
+        pd.DataFrame({"unicode": ["Hello 🌍", "Python 🐍", "Data 📊"]}),
+        pd.DataFrame({"mixed": [1, "string", [1, 2, 3], {"key": "value"}]}),
+        pd.DataFrame({"a": [1], "b": ["test"], "c": [3.14]}),
+        pd.DataFrame({"single": [42]}),
+        pd.DataFrame(
+            {
+                "small": [sys.float_info.min, 0, sys.float_info.max],
+                "large_int": [-(2**63), 0, 2**63 - 1],
+            }
+        ),
+        pd.DataFrame({"special_strings": ["", "null", "None", "NaN", "inf", "-inf"]}),
+        pd.DataFrame({"bytes_col": [b"hello", b"world", b"\x00\x01\x02"]}),
+    ],
+)
+def test_serde_jsonplus_pandas_dataframe(df: pd.DataFrame) -> None:
+    serde = JsonPlusSerializer(pickle_fallback=True)
+
+    dumped = serde.dumps_typed(df)
+    assert dumped[0] == "pickle"
+    result = serde.loads_typed(dumped)
+    assert result.equals(df)
+
+
+@pytest.mark.parametrize(
+    "series",
+    [
+        pd.Series([]),
+        pd.Series([1, 2, 3]),
+        pd.Series([1.1, 2.2, 3.3]),
+        pd.Series(["a", "b", "c"]),
+        pd.Series([True, False, True]),
+        pd.Series([datetime(2024, 1, 1), datetime(2024, 1, 2), datetime(2024, 1, 3)]),
+        pd.Series([1, 2, None]),
+        pd.Series([1.1, None, 3.3]),
+        pd.Series(["a", None, "c"]),
+        pd.Series(pd.Categorical(["a", "b", "a", "c"])),
+        pd.Series([1, 2, 3], dtype="int8"),
+        pd.Series([10, 20, 30], dtype="int16"),
+        pd.Series([100, 200, 300], dtype="int32"),
+        pd.Series([1000, 2000, 3000], dtype="int64"),
+        pd.Series([1.1, 2.2, 3.3], dtype="float32"),
+        pd.Series([10.1, 20.2, 30.3], dtype="float64"),
+        pd.Series([1, 2, 3], index=["x", "y", "z"]),
+        pd.Series([1, 2, 3], index=pd.date_range("2024-01-01", periods=3, freq="D")),
+        pd.Series(range(1000)),
+        pd.Series(pd.date_range("2024-01-01", periods=3, freq="D", tz="UTC")),
+        pd.Series(pd.to_timedelta([1, 2, 3], unit="D")),
+        pd.Series(pd.period_range("2024-01", periods=3, freq="M")),
+        pd.Series(pd.interval_range(start=0, end=3, periods=3)),
+        pd.Series(["Hello 🌍", "Python 🐍", "Data 📊"]),
+        pd.Series([1, "string", [1, 2, 3], {"key": "value"}]),
+        pd.Series([42], name="single"),
+        pd.Series([sys.float_info.min, 0, sys.float_info.max]),
+        pd.Series([-(2**63), 0, 2**63 - 1]),
+        pd.Series(["", "null", "None", "NaN", "inf", "-inf"]),
+        pd.Series([b"hello", b"world", b"\x00\x01\x02"]),
+        pd.Series([1, 2, 3], name="named_series"),
+        pd.Series(
+            [10, 20],
+            index=pd.MultiIndex.from_tuples([("a", 1), ("b", 2)], names=["x", "y"]),
+        ),
+    ],
+)
+def test_serde_jsonplus_pandas_series(series: pd.Series) -> None:
+    serde = JsonPlusSerializer(pickle_fallback=True)
+    dumped = serde.dumps_typed(series)
+
+    assert dumped[0] == "pickle"
+    result = serde.loads_typed(dumped)
+
+    assert result.equals(series)

libs/checkpoint/tests/test_memory.py

@@ -6,12 +6,10 @@ from langchain_core.runnables import RunnableConfig
 from langgraph.checkpoint.base import (
     Checkpoint,
     CheckpointMetadata,
-)
-from langgraph.checkpoint.memory import InMemorySaver
-from tests.checkpoint_utils import (
     create_checkpoint,
     empty_checkpoint,
 )
+from langgraph.checkpoint.memory import InMemorySaver
 
 
 class TestMemorySaver:
@@ -77,7 +75,6 @@ class TestMemorySaver:
         assert checkpoint is not None
         assert checkpoint.metadata == {
             **self.metadata_2,
-            "thread_id": "thread-2",
             "run_id": "my_run_id",
         }
 
@@ -114,18 +111,11 @@ class TestMemorySaver:
 
         search_results_1 = list(self.memory_saver.list(None, filter=query_1))
         assert len(search_results_1) == 1
-        assert search_results_1[0].metadata == {
-            "thread_id": "thread-1",
-            "thread_ts": "1",
-            **self.metadata_1,
-        }
+        assert search_results_1[0].metadata == self.metadata_1
 
         search_results_2 = list(self.memory_saver.list(None, filter=query_2))
         assert len(search_results_2) == 1
-        assert search_results_2[0].metadata == {
-            "thread_id": "thread-2",
-            **self.metadata_2,
-        }
+        assert search_results_2[0].metadata == self.metadata_2
 
         search_results_3 = list(self.memory_saver.list(None, filter=query_3))
         assert len(search_results_3) == 3
@@ -180,20 +170,13 @@ class TestMemorySaver:
             c async for c in self.memory_saver.alist(None, filter=query_1)
         ]
         assert len(search_results_1) == 1
-        assert search_results_1[0].metadata == {
-            "thread_id": "thread-1",
-            "thread_ts": "1",
-            **self.metadata_1,
-        }
+        assert search_results_1[0].metadata == self.metadata_1
 
         search_results_2 = [
             c async for c in self.memory_saver.alist(None, filter=query_2)
         ]
         assert len(search_results_2) == 1
-        assert search_results_2[0].metadata == {
-            "thread_id": "thread-2",
-            **self.metadata_2,
-        }
+        assert search_results_2[0].metadata == self.metadata_2
 
         search_results_3 = [
             c async for c in self.memory_saver.alist(None, filter=query_3)

libs/cli/examples/graphs/storm.py

@@ -22,10 +22,10 @@ from langgraph.graph import END, StateGraph
 from pydantic import BaseModel, Field
 from typing_extensions import TypedDict
 
-fast_llm = ChatOpenAI(model="gpt-3.5-turbo")
+fast_llm = ChatOpenAI(model="gpt-4o-mini")
 # Uncomment for a Fireworks model
 # fast_llm = ChatFireworks(model="accounts/fireworks/models/firefunction-v1", max_tokens=32_000)
-long_context_llm = ChatOpenAI(model="gpt-4-turbo-preview")
+long_context_llm = ChatOpenAI(model="gpt-4o")
 
 
 direct_gen_outline_prompt = ChatPromptTemplate.from_messages(
@@ -144,7 +144,7 @@ gen_perspectives_prompt = ChatPromptTemplate.from_messages(
 )
 
 gen_perspectives_chain = gen_perspectives_prompt | ChatOpenAI(
-    model="gpt-3.5-turbo"
+    model="gpt-4o-mini"
 ).with_structured_output(Perspectives)
 
 
@@ -270,7 +270,7 @@ gen_queries_prompt = ChatPromptTemplate.from_messages(
     ]
 )
 gen_queries_chain = gen_queries_prompt | ChatOpenAI(
-    model="gpt-3.5-turbo"
+    model="gpt-4o-mini"
 ).with_structured_output(Queries, include_raw=True)
 
 

libs/cli/langgraph_cli/config.py

@@ -1,6 +1,7 @@
 import json
 import os
 import pathlib
+import re
 import textwrap
 from collections import Counter
 from typing import Any, Literal, NamedTuple, Optional, TypedDict, Union
@@ -329,6 +330,11 @@ class HttpConfig(TypedDict, total=False):
     disable_store: bool
     """Optional. If True, /store routes are removed, disabling direct store interactions via HTTP.
     
+    Default is False.
+    """
+    disable_mcp: bool
+    """Optional. If True, /mcp routes are removed, disabling the MCP server.
+    
     Default is False.
     """
     disable_meta: bool
@@ -382,6 +388,14 @@ class Config(TypedDict, total=False):
     Only relevant if Python dependencies are installed via pip. If omitted, default pip settings are used.
     """
 
+    pip_installer: Optional[str]
+    """Optional. Python package installer to use ('auto', 'pip', 'uv').
+    
+    - 'auto' (default): Use uv for supported base images, otherwise pip
+    - 'pip': Force use of pip regardless of base image support
+    - 'uv': Force use of uv (will fail if base image doesn't support it)
+    """
+
     dockerfile_lines: list[str]
     """Optional. Additional Docker instructions that will be appended to your base Dockerfile.
     
@@ -461,7 +475,7 @@ class Config(TypedDict, total=False):
 PIP_CLEANUP_LINES = """# -- Ensure user deps didn't inadvertently overwrite langgraph-api
 RUN mkdir -p /api/langgraph_api /api/langgraph_runtime /api/langgraph_license && \
     touch /api/langgraph_api/__init__.py /api/langgraph_runtime/__init__.py /api/langgraph_license/__init__.py
-RUN PYTHONDONTWRITEBYTECODE=1 pip install --no-cache-dir --no-deps -e /api
+RUN PYTHONDONTWRITEBYTECODE=1 {install_cmd} --no-cache-dir --no-deps -e /api
 # -- End of ensuring user deps didn't inadvertently overwrite langgraph-api --
 # -- Removing pip from the final image ~<:===~~~ --
 RUN pip uninstall -y pip setuptools wheel && \
@@ -470,6 +484,7 @@ RUN pip uninstall -y pip setuptools wheel && \
 # pip removal for wolfi
 RUN rm -rf /usr/lib/python*/site-packages/pip* /usr/lib/python*/site-packages/setuptools* /usr/lib/python*/site-packages/wheel* && \
     find /usr/bin -name "pip*" -delete || true
+{uv_removal}
 # -- End of pip removal --"""
 
 
@@ -534,6 +549,7 @@ def validate_config(config: Config) -> Config:
         "node_version": node_version,
         "python_version": python_version,
         "pip_config_file": config.get("pip_config_file"),
+        "pip_installer": config.get("pip_installer", "auto"),
         "_INTERNAL_docker_tag": config.get("_INTERNAL_docker_tag"),
         "base_image": config.get("base_image"),
         "image_distro": image_distro,
@@ -598,6 +614,13 @@ def validate_config(config: Config) -> Config:
                 "Must be either 'debian' or 'wolfi'."
             )
 
+    if pip_installer := config.get("pip_installer"):
+        if pip_installer not in ["auto", "pip", "uv"]:
+            raise click.UsageError(
+                f"Invalid pip_installer: '{pip_installer}'. "
+                "Must be 'auto', 'pip', or 'uv'."
+            )
+
     # Validate auth config
     if auth_conf := config.get("auth"):
         if "path" in auth_conf:
@@ -1089,16 +1112,47 @@ def _get_node_pm_install_cmd(config_path: pathlib.Path, config: Config) -> str:
     return install_cmd
 
 
+semver_pattern = re.compile(r":(\d+(?:\.\d+)?(?:\.\d+)?)(?:-|$)")
+
+
+def _image_supports_uv(base_image: str) -> bool:
+    if base_image == "langchain/langgraph-trial":
+        return False
+    match = semver_pattern.search(base_image)
+    if not match:
+        # Default image (langchain/langgraph-api) supports it.
+        return True
+
+    version_str = match.group(1)
+    version = tuple(map(int, version_str.split(".")))
+    min_uv = (0, 2, 47)
+    return version >= min_uv
+
+
 def python_config_to_docker(
     config_path: pathlib.Path,
     config: Config,
     base_image: str,
 ) -> tuple[str, dict[str, str]]:
     """Generate a Dockerfile from the configuration."""
+    pip_installer = config.get("pip_installer", "auto")
+
+    if pip_installer == "uv":
+        install_cmd = "uv pip install --system"
+        uv_removal = "RUN uv pip uninstall --system pip setuptools wheel && rm /usr/bin/uv /usr/bin/uvx"
+    elif pip_installer == "pip":
+        install_cmd = "pip install"
+        uv_removal = ""
+    else:
+        if _image_supports_uv(base_image):
+            install_cmd = "uv pip install --system"
+            uv_removal = "RUN uv pip uninstall --system pip setuptools wheel && rm /usr/bin/uv /usr/bin/uvx"
+        else:
+            install_cmd = "pip install"
+            uv_removal = ""
+
     # configure pip
-    pip_install = (
-        "PYTHONDONTWRITEBYTECODE=1 pip install --no-cache-dir -c /api/constraints.txt"
-    )
+    pip_install = f"PYTHONDONTWRITEBYTECODE=1 {install_cmd} --no-cache-dir -c /api/constraints.txt"
     if config.get("pip_config_file"):
         pip_install = f"PIP_CONFIG_FILE=/pipconfig.txt {pip_install}"
     pip_config_file_str = (
@@ -1151,7 +1205,10 @@ RUN set -ex && \\
                 'name = "{fullpath.name}"' \\
                 'version = "0.1"' \\
                 '[tool.setuptools.package-data]' \\
-                '"*" = ["**/*"]'; do \\
+                '"*" = ["**/*"]' \\
+                '[build-system]' \\
+                'requires = ["setuptools>=61"]' \\
+                'build-backend = "setuptools.build_meta"'; do \\
         echo "$line" >> /deps/__outer_{fullpath.name}/pyproject.toml; \\
     done
 # -- End of non-package dependency {fullpath.name} --"""
@@ -1240,7 +1297,8 @@ ADD {relpath} /deps/{name}
         "",
         js_inst_str,
         "",
-        PIP_CLEANUP_LINES,  # Add pip cleanup after all installations are complete
+        # Add pip cleanup after all installations are complete
+        PIP_CLEANUP_LINES.format(install_cmd=install_cmd, uv_removal=uv_removal),
         "",
         f"WORKDIR {local_deps.working_dir}" if local_deps.working_dir else "",
     ]

libs/cli/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "langgraph-cli"
-version = "0.2.12"
+version = "0.3.3"
 description = "CLI for interacting with LangGraph API"
 authors = []
 requires-python = ">=3.9"

libs/cli/schemas/schema.json

@@ -134,6 +134,17 @@
               ],
               "description": "Optional. Linux distribution for the base image.\n\nMust be either 'debian' or 'wolfi'. If omitted, defaults to 'debian'.\n"
             },
+            "pip_installer": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Optional. Python package installer to use ('auto', 'pip', 'uv').\n\n"
+            },
             "store": {
               "anyOf": [
                 {
@@ -287,6 +298,17 @@
               ],
               "description": "Optional. Linux distribution for the base image.\n\nMust be either 'debian' or 'wolfi'. If omitted, defaults to 'debian'.\n"
             },
+            "pip_installer": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Optional. Python package installer to use ('auto', 'pip', 'uv').\n\n"
+            },
             "store": {
               "anyOf": [
                 {
@@ -477,6 +499,10 @@
           "type": "boolean",
           "description": "Optional. If True, /assistants routes are removed from the server.\n\nDefault is False (meaning /assistants is enabled).\n"
         },
+        "disable_mcp": {
+          "type": "boolean",
+          "description": "Optional. If True, /mcp routes are removed, disabling the MCP server.\n\nDefault is False.\n"
+        },
         "disable_meta": {
           "type": "boolean",
           "description": "Optional. If True, all meta endpoints (/ok, /info, /metrics, /docs) are disabled.\n\nDefault is False.\n"