refactor

enforce config injection
fix(langgraph): always use parent runtime info if available (#5707 )
2026-08-18 05:35:43 +02:00 · 2025-07-29 15:19:12 -04:00 · 2025-07-29 15:13:51 -04:00 · 2025-07-29 15:05:54 -04:00 · 2025-07-29 14:59:14 -04:00 · 2025-07-29 14:58:16 -04:00
30 changed files with 1481 additions and 210 deletions
@@ -35,16 +35,7 @@ jobs:
        with:
          filter: "docs/docs/**"

-  # TODO: Uncomment this to run on PRs
-  # run-changed-notebooks:
-  #   needs: get-changed-files
-  #   uses: ./.github/workflows/run_notebooks.yml
-  #   secrets: inherit
-  #   with:
-  #     changed-files: ${{ needs.get-changed-files.outputs.changed-files }}
-
  deploy:
-    # needs: run-changed-notebooks
    runs-on: ubuntu-latest
    timeout-minutes: 10 # Job will be cancelled if it runs for more than 10 minutes
    env:
@@ -39,6 +39,7 @@ jobs:
            scheduler-kafka
            sdk-py
            docs
+            ci
          requireScope: false
          ignoreLabels: |
            ignore-lint-pr-title
@@ -137,7 +137,9 @@ jobs:
    needs:
      - build
      - release-notes
-    permissions: write-all
+    permissions:
+      contents: read
+      id-token: write
    uses: ./.github/workflows/_test_release.yml
    with:
      working-directory: ${{ inputs.working-directory }}
@@ -0,0 +1,181 @@
+"""Logic to identify and transform cross-reference links in markdown files.
+
+This module allows supporting custom markdown syntax for "autolinks". These are links
+that will be transformed based on the current scope context, such as "global", "python",
+or "js" into an appropriate markdown link format.
+
+For example,
+
+```markdown
+@[StateGraph]
+```
+
+May be transformed into:
+
+```markdown
+[StateGraph](some_path/api-reference/state-graph.md)
+```
+
+The transformation value depends on the scope in which the link is used.
+"""
+
+import logging
+import re
+from typing import Optional
+
+from _scripts.link_map import SCOPE_LINK_MAPS
+
+logger = logging.getLogger(__name__)
+
+
+def _transform_link(
+    link_name: str, scope: str, file_path: str, line_number: int, custom_title: Optional[str] = None
+) -> Optional[str]:
+    """Transform a cross-reference link based on the current scope.
+
+    Args:
+        link_name: The name of the link to transform (e.g., "StateGraph").
+        scope: The current scope context ("global", "python", "js", etc.).
+        file_path: The file path for error reporting.
+        line_number: The line number for error reporting.
+        custom_title: Optional custom title for the link. If None, uses link_name.
+
+    Returns:
+        A formatted markdown link if the link is found in the scope mapping,
+        None otherwise.
+
+    Example:
+        >>> _transform_link("StateGraph", "python", "file.md", 5)
+        "[StateGraph](https://langchain-ai.github.io/langgraph/reference/graphs/#langgraph.graph.StateGraph)"
+
+        >>> _transform_link("StateGraph", "python", "file.md", 5, "Custom Title")
+        "[Custom Title](https://langchain-ai.github.io/langgraph/reference/graphs/#langgraph.graph.StateGraph)"
+
+        >>> _transform_link("unknown-link", "python", "file.md", 5)
+        None
+    """
+    if scope == "global":
+        # Special scope that is composed of both Python and JS links
+        # For now, we will substitute in the python scope!
+        # But we need to add support for handling both scopes.
+        scope = "python"
+        logger.error(
+            "Encountered unhandled 'global' scope. Defaulting to 'python'."
+            "In file: %s, line %d, link_name: %s",
+            file_path,
+            line_number,
+            link_name,
+        )
+    link_map = SCOPE_LINK_MAPS.get(scope, {})
+    url = link_map.get(link_name)
+
+    if url:
+        title = custom_title if custom_title is not None else link_name
+        return f"[{title}]({url})"
+    else:
+        # Log error with file location information
+        logger.info(
+            # Using %s
+            "Link '%s' not found in scope '%s'. "
+            "In file: %s, line %d. Available links in scope: %s",
+            link_name,
+            scope,
+            file_path,
+            line_number,
+            list(link_map.keys() if link_map else []),
+        )
+        return None
+
+
+CONDITIONAL_FENCE_PATTERN = re.compile(
+    r"""
+    ^                       # Start of line
+    (?P<indent>[ \t]*)      # Optional indentation (spaces or tabs)
+    :::                     # Literal fence marker
+    (?P<language>\w+)?      # Optional language identifier (named group: language)
+    \s*                     # Optional trailing whitespace
+    $                       # End of line
+    """,
+    re.VERBOSE,
+)
+CROSS_REFERENCE_PATTERN = re.compile(
+    r"""
+    @                       # Literal @ symbol
+    (?:                     # Non-capturing group for two possible formats:
+        \[                  # Opening bracket for title
+        (?P<title>[^\]]+)   # Custom title - one or more non-bracket characters
+        \]                  # Closing bracket for title
+        \[                  # Opening bracket for link name
+        (?P<link_name_with_title>[^\]]+)  # Link name - one or more non-bracket characters
+        \]                  # Closing bracket for link name
+        |                   # OR
+        \[                  # Opening bracket
+        (?P<link_name>[^\]]+)   # Link name - one or more non-bracket characters
+        \]                  # Closing bracket
+    )
+    """,
+    re.VERBOSE,
+)
+
+
+def _replace_autolinks(markdown: str, file_path: str) -> str:
+    """Preprocess markdown lines to handle @[links] with conditional fence scopes.
+
+    This function processes markdown content to transform @[link_name] references
+    based on the current conditional fence scope. Conditional fences use the
+    syntax :::language to define scope boundaries.
+
+    Args:
+        markdown: The markdown content to process.
+        file_path: The file path for error reporting.
+
+    Returns:
+        Processed markdown content with @[references] transformed to proper
+        markdown links or left unchanged if not found.
+
+    Example:
+        Input:
+            "@[StateGraph]\\n:::python\\n@[Command]\\n:::\\n"
+        Output:
+            "[StateGraph](url)\\n:::python\\n[Command](url)\\n:::\\n"
+    """
+    # Track the current scope context
+    current_scope = "global"
+    lines = markdown.splitlines(keepends=True)
+    processed_lines = []
+
+    for line_number, line in enumerate(lines, 1):
+        line_stripped = line.strip()
+
+        # Check if this line defines a new conditional fence scope
+        fence_match = CONDITIONAL_FENCE_PATTERN.match(line_stripped)
+        if fence_match:
+            language = fence_match.group("language")
+            # Set scope to the specified language, or reset to global if no language
+            current_scope = language.lower() if language else "global"
+            processed_lines.append(line)
+            continue
+
+        # Transform all @[link_name] references in this line based on current scope
+        def replace_cross_reference(match: re.Match[str]) -> str:
+            """Replace a single @[link_name] with the scoped equivalent."""
+            # Check if this is the @[title][ref] format or @[ref] format
+            title = match.group("title")
+            if title is not None:
+                # This is @[title][ref] format
+                link_name = match.group("link_name_with_title")
+                custom_title = title
+            else:
+                # This is @[ref] format
+                link_name = match.group("link_name")
+                custom_title = None
+            
+            transformed = _transform_link(
+                link_name, current_scope, file_path, line_number, custom_title
+            )
+            return transformed if transformed is not None else match.group(0)
+
+        transformed_line = CROSS_REFERENCE_PATTERN.sub(replace_cross_reference, line)
+        processed_lines.append(transformed_line)
+
+    return "".join(processed_lines)
@@ -1,5 +1,142 @@
-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",
+"""Link mapping for cross-reference resolution across different scopes.
+
+This module provides link mappings for different language/framework scopes
+to resolve @[link_name] references to actual URLs.
+"""
+
+# Python-specific link mappings
+# Python-specific link mappings
+PYTHON_LINK_MAP = {
+    "StateGraph": "reference/graphs/#langgraph.graph.StateGraph",
+    "add_conditional_edges": "reference/graphs/#langgraph.graph.StateGraph.add_conditional_edges",
+    "add_edge": "reference/graphs/#langgraph.graph.StateGraph.add_edge",
+    "add_node": "reference/graphs/#langgraph.graph.StateGraph.add_node",
+    "add_messages": "reference/messages/#langgraph.graph.message.add_messages",
+    "ToolNode": "reference/prebuilt/#langgraph.prebuilt.tool_node.ToolNode",
+    "CompiledStateGraph.astream": "reference/graphs/#langgraph.graph.state.CompiledStateGraph.astream",
+    "Pregel.astream": "reference/graphs/#langgraph.pregel.Pregel.astream",
+    "AsyncPostgresSaver": "reference/checkpoints/#langgraph.checkpoint.postgres.aio.AsyncPostgresSaver",
+    "AsyncSqliteSaver": "reference/checkpoints/#langgraph.checkpoint.sqlite.aio.AsyncSqliteSaver",
+    "BaseCheckpointSaver": "reference/checkpoints/#langgraph.checkpoint.base.BaseCheckpointSaver",
+    "BaseStore": "reference/stores/#langgraph.store.base.BaseStore",
+    "BaseStore.put": "reference/stores/#langgraph.store.base.BaseStore.put",
+    "BinaryOperatorAggregate": "reference/channels/#langgraph.channels.BinaryOperatorAggregate",
+    "CipherProtocol": "reference/checkpoints/#langgraph.checkpoint.serde.base.CipherProtocol",
+    "client.runs.stream": "reference/client/#langgraph_sdk.client.RunsClient.stream",
+    "client.runs.wait": "reference/client/#langgraph_sdk.client.RunsClient.wait",
+    "client.threads.get_history": "reference/client/#langgraph_sdk.client.ThreadsClient.get_history",
+    "client.threads.update_state": "reference/client/#langgraph_sdk.client.ThreadsClient.update_state",
+    "Command": "reference/types/#langgraph.types.Command",
+    "CompiledStateGraph": "reference/graphs/#langgraph.graph.state.CompiledStateGraph",
+    "create_react_agent": "reference/prebuilt/#langgraph.prebuilt.chat_agent_executor.create_react_agent",
+    "create_supervisor": "reference/supervisor/#langgraph_supervisor.supervisor.create_supervisor",
+    "EncryptedSerializer": "reference/checkpoints/#langgraph.checkpoint.serde.encrypted.EncryptedSerializer",
+    "entrypoint.final": "reference/functions/#langgraph.func.entrypoint.final",
+    "entrypoint": "reference/functions/#langgraph.func.entrypoint",
+    "from_pycryptodome_aes": "reference/checkpoints/#langgraph.checkpoint.serde.encrypted.EncryptedSerializer.from_pycryptodome_aes",
+    # "getContextVariable": "<insert-ref>",
+    "get_state_history": "reference/graphs/#langgraph.graph.state.CompiledStateGraph.get_state_history",
+    "get_stream_writer": "reference/config/#langgraph.config.get_stream_writer",
+    "HumanInterrupt": "reference/prebuilt/#langgraph.prebuilt.interrupt.HumanInterrupt",
+    "InjectedState": "reference/prebuilt/#langgraph.prebuilt.InjectedState",
+    "InMemorySaver": "reference/checkpoints/#langgraph.checkpoint.memory.InMemorySaver",
+    "interrupt": "reference/graphs/#langgraph.graph.interrupt",
+    "CompiledStateGraph.invoke": "reference/graphs/#langgraph.graph.state.CompiledStateGraph.invoke",
+    "JsonPlusSerializer": "reference/checkpoints/#langgraph.checkpoint.serde.jsonplus.JsonPlusSerializer",
+    "langgraph.json": "reference/configuration/#configuration-file",
+    "LastValue": "reference/channels/#langgraph.channels.LastValue",
+    # "MemorySaver": "<insert-ref>",
+    # "messagesStateReducer": "<insert-ref>",
+    "PostgresSaver": "reference/checkpoints/#langgraph.checkpoint.postgres.PostgresSaver",
+    "Pregel": "reference/graphs/#langgraph.pregel.Pregel",
+    "Pregel.stream": "reference/graphs/#langgraph.pregel.Pregel.stream",
+    "pre_model_hook": "reference/prebuilt/#langgraph.prebuilt.chat_agent_executor.create_react_agent",
+    "protocol": "reference/checkpoints/#langgraph.checkpoint.serde.base.SerializerProtocol",
+    "Send": "reference/types/#langgraph.types.Send",
+    "SerializerProtocol": "reference/checkpoints/#langgraph.checkpoint.serde.base.SerializerProtocol",
+    "SqliteSaver": "reference/checkpoints/#langgraph.checkpoint.sqlite.SqliteSaver",
+    "START": "reference/constants/#langgraph.constants.START",
+    "CompiledStateGraph.stream": "reference/graphs/#langgraph.graph.state.CompiledStateGraph.stream",
+    "task": "reference/functions/#langgraph.func.task",
+    "Topic": "reference/channels/#langgraph.channels.Topic",
+    "update_state": "reference/graphs/#langgraph.graph.state.CompiledStateGraph.update_state",
+}
+
+
+# JavaScript-specific link mappings
+JS_LINK_MAP = {
+    "StateGraph": "reference/classes/langgraph.StateGraph.html",
+    "add_conditional_edges": "reference/functions/langgraph_StateGraph.addConditionalEdges.html",
+    "add_edge": "reference/functions/langgraph_StateGraph.addEdge.html",
+    "add_node": "reference/functions/langgraph_StateGraph.addNode.html",
+    "add_messages": "reference/functions/langgraph_message.addMessages.html",
+    "ToolNode": "reference/classes/langgraph_prebuilt.ToolNode.html",
+    "CompiledStateGraph.astream()": "reference/functions/langgraph_CompiledStateGraph.astream.html",
+    "Pregel.astream": "reference/functions/langgraph_Pregel.astream.html",
+    "AsyncPostgresSaver": "reference/classes/langgraph_checkpoint_postgres_aio.AsyncPostgresSaver.html",
+    "AsyncSqliteSaver": "reference/classes/langgraph_checkpoint_sqlite_aio.AsyncSqliteSaver.html",
+    "BaseCheckpointSaver": "reference/classes/langgraph_checkpoint_base.BaseCheckpointSaver.html",
+    "BaseStore": "reference/classes/langgraph_store_base.BaseStore.html",
+    "BaseStore.put": "reference/functions/langgraph_store_base.BaseStore.put.html",
+    "BinaryOperatorAggregate": "reference/classes/langgraph_channels.BinaryOperatorAggregate.html",
+    "CipherProtocol": "reference/classes/langgraph_checkpoint_serde_base.CipherProtocol.html",
+    "client.runs.stream": "reference/functions/langgraph_sdk_client.RunsClient.stream.html",
+    "client.runs.wait": "reference/functions/langgraph_sdk_client.RunsClient.wait.html",
+    "client.threads.get_history": "reference/functions/langgraph_sdk_client.ThreadsClient.getHistory.html",
+    "client.threads.update_state": "reference/functions/langgraph_sdk_client.ThreadsClient.updateState.html",
+    "Command": "reference/classes/langgraph.Command.html",
+    "CompiledStateGraph": "reference/classes/langgraph.CompiledStateGraph.html",
+    "create_react_agent": "reference/functions/langgraph_prebuilt.createReactAgent.html",
+    "create_supervisor": "reference/functions/langgraph_supervisor.createSupervisor.html",
+    "EncryptedSerializer": "reference/classes/langgraph_checkpoint_serde_encrypted.EncryptedSerializer.html",
+    "entrypoint.final": "reference/functions/langgraph_func.entrypoint.final.html",
+    "entrypoint": "reference/functions/langgraph_func.entrypoint.html",
+    "from_pycryptodome_aes": "reference/functions/langgraph_checkpoint_serde_encrypted.EncryptedSerializer.fromPycryptodomeAes.html",
+    # "getContextVariable": "<insert-ref>",
+    "get_state_history": "reference/functions/langgraph_CompiledStateGraph.getStateHistory.html",
+    "get_stream_writer": "reference/functions/langgraph_config.getStreamWriter.html",
+    "HumanInterrupt": "reference/classes/langgraph_prebuilt.HumanInterrupt.html",
+    "InjectedState": "reference/classes/langgraph_prebuilt.InjectedState.html",
+    "InMemorySaver": "reference/classes/langgraph_checkpoint_memory.InMemorySaver.html",
+    "interrupt": "reference/functions/langgraph.interrupt-2.html",
+    "CompiledStateGraph.invoke": "reference/functions/langgraph_CompiledStateGraph.invoke.html",
+    "JsonPlusSerializer": "reference/classes/langgraph_checkpoint_serde_jsonplus.JsonPlusSerializer.html",
+    "langgraph.json": "reference/configuration.html",
+    "LastValue": "reference/classes/langgraph_channels.LastValue.html",
+    # "MemorySaver": "<insert-ref>",
+    # "messagesStateReducer": "<insert-ref>",
+    "PostgresSaver": "reference/classes/langgraph_checkpoint_postgres.PostgresSaver.html",
+    "Pregel": "reference/classes/langgraph.Pregel.html",
+    "Pregel.stream": "reference/functions/langgraph_Pregel.stream.html",
+    "pre_model_hook": "reference/functions/langgraph_prebuilt.createReactAgent.html",
+    "protocol": "reference/classes/langgraph_checkpoint_serde_base.SerializerProtocol.html",
+    "Send": "reference/classes/langgraph.Send.html",
+    "SerializerProtocol": "reference/classes/langgraph_checkpoint_serde_base.SerializerProtocol.html",
+    "SqliteSaver": "reference/classes/langgraph_checkpoint_sqlite.SqliteSaver.html",
+    "START": "reference/constants.html#START",
+    "CompiledStateGraph.stream": "reference/functions/langgraph_CompiledStateGraph.stream.html",
+    "task": "reference/functions/langgraph_func.task.html",
+    "Topic": "reference/classes/langgraph_channels.Topic.html",
+    "update_state": "reference/functions/langgraph_CompiledStateGraph.updateState.html",
+}
+
+# TODO: Allow updating these to localhost for local development
+PY_REFERENCE_HOST = "https://langchain-ai.github.io/langgraph/"
+JS_REFERENCE_HOST = "https://langchain-ai.github.io/langgraphjs/"
+
+for key, value in PYTHON_LINK_MAP.items():
+    # Ensure the link is absolute
+    if not value.startswith("http"):
+        PYTHON_LINK_MAP[key] = f"{PY_REFERENCE_HOST}{value}"
+
+for key, value in JS_LINK_MAP.items():
+    # Ensure the link is absolute
+    if not value.startswith("http"):
+        JS_LINK_MAP[key] = f"{JS_REFERENCE_HOST}{value}"
+
+# Global scope is assembled from the Python and JS mappings
+# Combined mapping by scope
+SCOPE_LINK_MAPS = {
+    "python": PYTHON_LINK_MAP,
+    "js": JS_LINK_MAP,
 }
@@ -16,7 +16,7 @@ from mkdocs.structure.files import Files, File
 from mkdocs.structure.pages import Page

 from _scripts.generate_api_reference_links import update_markdown_with_imports
-from _scripts.link_map import JS_LINK_MAP
+from _scripts.handle_auto_links import _replace_autolinks
 from _scripts.notebook_convert import convert_notebook

 logger = logging.getLogger(__name__)
@@ -176,31 +176,7 @@ 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)
+# Compiled regex patterns for better performance and readability


 def _apply_conditional_rendering(md_text: str, target_language: str) -> str:
@@ -295,7 +271,7 @@ def _highlight_code_blocks(markdown: str) -> str:
            opening_fence += f" {attributes}"

        if highlighted_lines:
-            opening_fence += f" hl_lines=\"{' '.join(highlighted_lines)}\""
+            opening_fence += f' hl_lines="{" ".join(highlighted_lines)}"'

        return (
            # The indent and opening fence
@@ -325,6 +301,9 @@ def _on_page_markdown_with_config(
        # logger.info("Processing Jupyter notebook: %s", page.file.src_path)
        markdown = convert_notebook(page.file.abs_src_path)

+    # Apply cross-reference preprocessing to all markdown content
+    markdown = _replace_autolinks(markdown, page.file.src_path)
+
    # Append API reference links to code blocks
    if add_api_references:
        markdown = update_markdown_with_imports(markdown, page.file.abs_src_path)
@@ -334,16 +313,6 @@ def _on_page_markdown_with_config(
    # 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
@@ -358,13 +327,11 @@ def _on_page_markdown_with_config(


 def on_page_markdown(markdown: str, page: Page, **kwargs: Dict[str, Any]):
-    finalized_markdown = (
-        _on_page_markdown_with_config(
-            markdown,
-            page,
-            add_api_references=True,
-            **kwargs,
-        )
+    finalized_markdown = _on_page_markdown_with_config(
+        markdown,
+        page,
+        add_api_references=True,
+        **kwargs,
    )
    page.meta["original_markdown"] = finalized_markdown
    return finalized_markdown
@@ -437,6 +404,7 @@ height="0" width="0" style="display:none;visibility:hidden"></iframe></noscript>
    else:
        return html  # fallback if no <body> found

+
 def _inject_markdown_into_html(html: str, page: Page) -> str:
    """Inject the original markdown content into the HTML page as JSON."""
    original_markdown = page.meta.get("original_markdown", "")
@@ -469,6 +437,7 @@ def _inject_markdown_into_html(html: str, page: Page) -> str:
        )
    return html.replace("</head>", f"{script_content}</head>")

+
 def on_post_page(html: str, page: Page, config: MkDocsConfig) -> str:
    """Inject Google Tag Manager noscript tag immediately after <body>.

@@ -483,6 +452,7 @@ def on_post_page(html: str, page: Page, config: MkDocsConfig) -> str:
    html = _inject_markdown_into_html(html, page)
    return _inject_gtm(html)

+
 # Create HTML files for redirects after site dir has been built
 def on_post_build(config):
    use_directory_urls = config.get("use_directory_urls")
@@ -1,33 +1,43 @@
 # Context

-**Context engineering** is the practice of building dynamic systems that provide the right information and tools, in the right format, so that a language model can plausibly accomplish a task.
+**Context engineering** is the practice of building dynamic systems that provide the right information and tools, in the right format, so that an AI application can accomplish a task. Context can be characterized along two key dimensions:

-Context includes *any* data outside the message list that can shape behavior. This can be:
+1. By **mutability**:

- Information passed at runtime, like a `user_id` or API credentials.
- Internal state updated during a multi-step reasoning process.
- Persistent memory or facts from previous interactions.
+    - **Static context**: Immutable data that doesn't change during execution (e.g., user metadata, database connections, tools)
+    - **Dynamic context**: Mutable data that evolves as the application runs (e.g., conversation history, intermediate results, tool call observations)

-LangGraph provides **three** primary ways to supply context:
+2. By **lifetime**:

-| Type                                                                         | Description                                   | Mutable? | Lifetime                |
-|------------------------------------------------------------------------------|-----------------------------------------------|----------|-------------------------|
-| [**Runtime Context**](#runtime-context)                                      | data passed at the start of a run             | ❌        | per run                 |
-| [**Short-term memory (State)**](#short-term-memory-mutable-context)          | dynamic data that can change during execution | ✅        | per run or conversation |
-| [**Long-term memory (Store)**](#long-term-memory-cross-conversation-context) | data that can be shared between conversations | ✅        | across conversations    |
+    - **Runtime context**: Data scoped to a single run or invocation
+    - **Cross-conversation context**: Data that persists across multiple conversations or sessions

-### Runtime Context
+!!! tip "Runtime context vs LLM context"

-!!! note "`config['configurable']` -> `runtime.context`"
+    Runtime context refers to local context: data and dependencies your code needs to run. It does **not** refer to:

-    In LangGraph < v1.0, static runtime context was passed via the `config['configurable']` key, paired with a `config_schema` argument
-    to `StateGraph` or `Pregel`. This is now deprecated and will be removed in v2.0.
+    * The LLM context, which is the data passed into the LLM's prompt.
+    * The "context window", which is the maximum number of tokens that can be passed to the LLM.

-    As of LangGraph v1.0, the Runtime object is recommended to access static context and runtime-specific information like the store and stream writer.
+    Runtime context can be used to optimize the LLM context. For example, you can use user metadata
+    in the runtime context to fetch user preferences and feed them into the context window.

-Runtime context is for immutable data like user metadata or API keys. Use this when you have values that don't change mid-run.
+LangGraph provides three ways to manage context, which combines the mutability and lifetime dimensions:

-Specify static context via the `context` argument to `invoke` / `stream`, which is reserved for this purpose:
+| Context type                                                                 | Description                                            | Mutability | Lifetime                | Access method                    |
+|------------------------------------------------------------------------------|--------------------------------------------------------|------------|-------------------------|-----------------------------------|
+| [**Static runtime context**](#static-runtime-context)                        | User metadata, tools, db connections passed at startup | Static     | Single run              | `context` argument to `invoke`/`stream` |
+| [**Dynamic runtime context (state)**](#dynamic-runtime-context-state)        | Mutable data that evolves during a single run         | Dynamic    | Single run              | LangGraph state object           |
+| [**Dynamic cross-conversation context (store)**](#dynamic-cross-conversation-context-store) | Persistent data shared across conversations            | Dynamic    | Cross-conversation      | LangGraph store                  |
+
+## Static runtime context
+
+**Static runtime context** represents immutable data like user metadata, tools, and database connections that are passed to an application at the start of a run via the `context` argument to `invoke`/`stream`. This data does not change during execution.
+
+!!! version-added "New in LangGraph v0.6: `context` replaces `config['configurable']`"
+
+    Runtime context is now passed to the `context` argument of `invoke`/`stream`,
+    which replaces the previous pattern of passing application configuration to `config['configurable']`.

 ```python
@dataclass
@@ -105,9 +115,14 @@ graph.invoke( # (1)!

    See the [tool calling guide](../how-tos/tool-calling.md#configuration) for details.

-### Short-term memory (mutable context)
+!!! tip

-State acts as [short-term memory](../concepts/memory.md) during a run. It holds dynamic data that can evolve during execution, such as values derived from tools or LLM outputs.
+    The `Runtime` object can be used to access static context and other utilities like the active store and stream writer.
+    See the [Runtime][langgraph.runtime.Runtime] documentation for details.
+
+## Dynamic runtime context (state)
+
+**Dynamic runtime context** represents mutable data that can evolve during a single run and is managed through the LangGraph state object. This includes conversation history, intermediate results, and values derived from tools or LLM outputs. In LangGraph, the state object acts as [short-term memory](../concepts/memory.md) during a run.

 === "In an agent"

@@ -187,8 +202,8 @@ State acts as [short-term memory](../concepts/memory.md) during a run. It holds

    Please see the [memory guide](../how-tos/memory/add-memory.md) for more details on how to enable memory. This is a powerful feature that allows you to persist the agent's state across multiple invocations. Otherwise, the state is scoped only to a single run.

-### Long-term memory (cross-conversation context)
+## Dynamic cross-conversation context (store)

-For context that spans *across* conversations or sessions, LangGraph allows access to **long-term memory** via a `store`. This can be used to read or update persistent facts (e.g., user profiles, preferences, prior interactions). 
+**Dynamic cross-conversation context** represents persistent, mutable data that spans across multiple conversations or sessions and is managed through the LangGraph store. This includes user profiles, preferences, and historical interactions. The LangGraph store acts as [long-term memory](../concepts/memory.md#long-term-memory) across multiple runs. This can be used to read or update persistent facts (e.g., user profiles, preferences, prior interactions). 

 For more information, see the [Memory guide](../how-tos/memory/add-memory.md).
@@ -4,6 +4,22 @@

 ---

+## v0.2.109 (2025-07-28)
+- Fixed an issue where missing config schema occurred when `config_type` was not set.
+
+## v0.2.108 (2025-07-28)
+- Added compatibility for langgraph v0.6, including new context API support and a migration to enhance context handling in assistant operations.
+
+## v0.2.107 (2025-07-27)
+- Implemented caching for authentication processes to improve performance.
+- Merged count and select queries to improve database query efficiency.
+
+## v0.2.106 (2025-07-27)
+- Log whether run uses resumable streams.
+
+## v0.2.105 (2025-07-27)
+- Added a `/heapdump` endpoint to capture and save JS process heap data.
+
 ## v0.2.103 (2025-07-25)
 - Corrected the metadata endpoint to ensure accurate data retrieval.

@@ -28,7 +28,7 @@ To review, edit, and approve tool calls in an agent or workflow, [use LangGraph'
    There are two ways to pause a graph:

    - [Dynamic interrupts](../how-tos/human_in_the_loop/add-human-in-the-loop.md#pause-using-interrupt): Use `interrupt` to pause a graph from inside a specific node, based on the current state of the graph.
-    - [Static interrupts](../how-tos/human_in_the_loop/add-human-in-the-loop.md#debug-with-interrupts): Use `interrupt_before` and `interrupt_after` to pause the graph at defined points, either before or after a node executes.
+    - [Static interrupts](../how-tos/human_in_the_loop/add-human-in-the-loop.md#debug-with-interrupts): Use `interrupt_before` and `interrupt_after` to pause the graph at pre-defined points, either before or after a node executes.

    <figure markdown="1">
    ![image](./img/breakpoints.png){: style="max-height:400px"}
@@ -128,7 +128,7 @@ print(graph.invoke(Command(resume="Edited text"), config=config)) # (7)!

 !!! tip "New in 0.4.0"

-      `__interrupt__` is a special key that will be returned when running the graph if the graph is interrupted. Support for `__interrupt__` in `invoke` and `ainvoke` has been added in version 0.4.0. If you're on an older version, you will only see `__interrupt__` in the result if you use `stream` or `astream`. You can also use `graph.get_state(thread_id)` to get the interrupt value.
+      `__interrupt__` is a special key that will be returned when running the graph if the graph is interrupted. Support for `__interrupt__` in `invoke` and `ainvoke` has been added in version 0.4.0. If you're on an older version, you will only see `__interrupt__` in the result if you use `stream` or `astream`. You can also use `graph.get_state(thread_id)` to get the interrupt value(s).

 !!! warning

@@ -145,19 +145,67 @@ To resume execution, use the [`Command`][langgraph.types.Command] primitive, whi
 graph.invoke(Command(resume={"age": "25"}), thread_config)
 ```

-### Resume multiple interrupts with one invocation
+## Resuming Multiple interrupts

-If you have multiple interrupts in the task queue, you can use `Command.resume` with a dictionary mapping of interrupt ids to resume with a single `invoke` / `stream` call.
+When nodes with interrupt conditions are run in parallel, it's possible to have multiple interrupts in the task queue.
+For example, the following graph has two nodes run in parallel that require human input:
+
+<figure markdown="1">
+![image](../assets/human_in_loop_parallel.png){: style="max-height:400px"}
+</figure>
+
+Once your graph has been interrupted and is stalled, you can resume all the interrupts at once with `Command.resume`, passing a dictionary mapping of interrupt ids to resume values.

-For example, once your graph has been interrupted (multiple times, theoretically) and is stalled:

 ```python
-resume_map = {
-    i.id: f"human input for prompt {i.value}"
-    for i in parent.get_state(thread_config).interrupts
-}
+from typing import TypedDict
+import uuid
+from langchain_core.runnables import RunnableConfig
+from langgraph.checkpoint.memory import InMemorySaver
+from langgraph.constants import START
+from langgraph.graph import StateGraph
+from langgraph.types import interrupt, Command

-parent_graph.invoke(Command(resume=resume_map), config=thread_config)
+
+class State(TypedDict):
+    text_1: str
+    text_2: str
+
+
+def human_node_1(state: State):
+    value = interrupt({"text_to_revise": state["text_1"]})
+    return {"text_1": value}
+
+
+def human_node_2(state: State):
+    value = interrupt({"text_to_revise": state["text_2"]})
+    return {"text_2": value}
+
+
+graph_builder = StateGraph(State)
+graph_builder.add_node("human_node_1", human_node_1)
+graph_builder.add_node("human_node_2", human_node_2)
+
+# Add both nodes in parallel from START
+graph_builder.add_edge(START, "human_node_1")
+graph_builder.add_edge(START, "human_node_2")
+
+checkpointer = InMemorySaver()
+graph = graph_builder.compile(checkpointer=checkpointer)
+
+thread_id = str(uuid.uuid4())
+config: RunnableConfig = {"configurable": {"thread_id": thread_id}}
+result = graph.invoke(
+    {"text_1": "original text 1", "text_2": "original text 2"}, config=config
+)
+
+# Resume with mapping of interrupt IDs to values
+resume_map = {
+    i.id: f"edited text for {i.value['text_to_revise']}"
+    for i in result["__interrupt__"]
+}
+print(graph.invoke(Command(resume=resume_map), config=config))
+# > {'text_1': 'edited text for original text 1', 'text_2': 'edited text for original text 2'}
 ```

 ## Common patterns
@@ -1027,7 +1075,7 @@ def node_in_parent_graph(state: State):
    {'parent_node': {'state_counter': 1}}
    ```

-### Using multiple interrupts
+### Using multiple interrupts in a single node

 Using multiple interrupts within a **single** node can be helpful for patterns like [validating human input](#validate-human-input). However, using multiple interrupts in the same node can lead to unexpected behavior if not handled carefully.

@@ -0,0 +1,216 @@
+"""Unit tests for cross-reference preprocessing functionality."""
+
+from unittest.mock import patch
+
+import pytest
+
+from _scripts.handle_auto_links import _transform_link, _replace_autolinks
+
+
+@pytest.fixture
+def mock_link_maps():
+    """Fixture providing mock link maps for testing."""
+    mock_scope_maps = {
+        "python": {"py-link": "https://example.com/python"},
+        "js": {"js-link": "https://example.com/js"},
+    }
+
+    with patch("_scripts.handle_auto_links.SCOPE_LINK_MAPS", mock_scope_maps):
+        yield mock_scope_maps
+
+
+def test_transform_link_basic(mock_link_maps) -> None:
+    """Test basic link transformation."""
+    # Test with a known link
+    result = _transform_link("py-link", "python", "test.md", 1)
+    assert result == "[py-link](https://example.com/python)"
+
+    # Test with an unknown link (returns None)
+    result = _transform_link("unknown-link", "global", "test.md", 1)
+    assert result is None
+
+
+def test_transform_link_with_custom_title(mock_link_maps) -> None:
+    """Test link transformation with custom title."""
+    # Test with a known link and custom title
+    result = _transform_link("py-link", "python", "test.md", 1, "Custom Python Link")
+    assert result == "[Custom Python Link](https://example.com/python)"
+
+    # Test with unknown link and custom title (should still return None)
+    result = _transform_link("unknown-link", "python", "test.md", 1, "Custom Title")
+    assert result is None
+
+
+def test_no_cross_refs(mock_link_maps) -> None:
+    """Test markdown with no @[references]."""
+    lines = ["# Title\n", "Regular text.\n"]
+    markdown = "".join(lines)
+    result = _replace_autolinks(markdown, "test.md")
+    expected = "".join(["# Title\n", "Regular text.\n"])
+    assert result == expected
+
+
+def test_global_cross_refs(mock_link_maps) -> None:
+    """Test @[references] in global scope (no conditional blocks)."""
+    lines = ["@[global-link]\n", "Text with @[unknown-link].\n"]
+    markdown = "".join(lines)
+    result = _replace_autolinks(markdown, "test.md")
+    expected = "".join(["@[global-link]\n", "Text with @[unknown-link].\n"])
+    assert result == expected
+
+
+def test_python_conditional_block(mock_link_maps) -> None:
+    """Test @[references] inside Python conditional block."""
+    lines = [":::python\n", "@[py-link]\n", ":::\n"]
+    markdown = "".join(lines)
+    result = _replace_autolinks(markdown, "test.md")
+    expected = "".join(
+        [":::python\n", "[py-link](https://example.com/python)\n", ":::\n"]
+    )
+    assert result == expected
+
+
+def test_js_conditional_block(mock_link_maps) -> None:
+    """Test @[references] inside JavaScript conditional block."""
+    lines = [":::js\n", "@[js-link]\n", ":::\n"]
+    markdown = "".join(lines)
+    result = _replace_autolinks(markdown, "test.md")
+    expected = "".join([":::js\n", "[js-link](https://example.com/js)\n", ":::\n"])
+    assert result == expected
+
+
+def test_all_scopes(mock_link_maps) -> None:
+    """Test @[references] in global, Python, and JavaScript scopes."""
+    lines = [
+        "@[global-link]\n",
+        ":::python\n",
+        "@[py-link]\n",
+        ":::\n",
+        "@[global-link]\n",
+        ":::js\n",
+        "@[js-link]\n",
+        ":::\n",
+        "@[global-link]\n",
+    ]
+    markdown = "".join(lines)
+    result = _replace_autolinks(markdown, "test.md")
+    expected = "".join(
+        [
+            "@[global-link]\n",
+            ":::python\n",
+            "[py-link](https://example.com/python)\n",
+            ":::\n",
+            "@[global-link]\n",
+            ":::js\n",
+            "[js-link](https://example.com/js)\n",
+            ":::\n",
+            "@[global-link]\n",
+        ]
+    )
+    assert result == expected
+
+
+def test_fence_resets_to_global(mock_link_maps) -> None:
+    """Test that closing fence resets scope to global."""
+    lines = [":::python\n", "@[py-link]\n", ":::\n", "@[global-link]\n"]
+    markdown = "".join(lines)
+    result = _replace_autolinks(markdown, "test.md")
+    expected = "".join(
+        [
+            ":::python\n",
+            "[py-link](https://example.com/python)\n",
+            ":::\n",
+            "@[global-link]\n",
+        ]
+    )
+    assert result == expected
+
+
+def test_indented_conditional_fences(mock_link_maps) -> None:
+    """Test @[references] inside indented conditional fences (e.g., in tabs or admonitions)."""
+    lines = [
+        "@[global-link]\n",
+        "    :::python\n",
+        "    @[py-link]\n",
+        "    :::\n",
+        "@[global-link]\n",
+        "\t\t:::js\n",
+        "\t\t@[js-link]\n",
+        "\t\t:::\n",
+        "@[global-link]\n",
+    ]
+    markdown = "".join(lines)
+    result = _replace_autolinks(markdown, "test.md")
+    expected = "".join(
+        [
+            "@[global-link]\n",
+            "    :::python\n",
+            "    [py-link](https://example.com/python)\n",
+            "    :::\n",
+            "@[global-link]\n",
+            "\t\t:::js\n",
+            "\t\t[js-link](https://example.com/js)\n",
+            "\t\t:::\n",
+            "@[global-link]\n",
+        ]
+    )
+    assert result == expected
+
+
+def test_custom_title_syntax(mock_link_maps) -> None:
+    """Test @[title][ref] syntax with custom titles."""
+    lines = [
+        ":::python\n",
+        "@[Custom Python Title][py-link]\n",
+        ":::\n",
+        ":::js\n", 
+        "@[Custom JS Title][js-link]\n",
+        ":::\n"
+    ]
+    markdown = "".join(lines)
+    result = _replace_autolinks(markdown, "test.md")
+    expected = "".join([
+        ":::python\n",
+        "[Custom Python Title](https://example.com/python)\n",
+        ":::\n",
+        ":::js\n",
+        "[Custom JS Title](https://example.com/js)\n",
+        ":::\n"
+    ])
+    assert result == expected
+
+
+def test_mixed_syntax_compatibility(mock_link_maps) -> None:
+    """Test that both @[ref] and @[title][ref] syntax work together."""
+    lines = [
+        ":::python\n",
+        "@[py-link]\n",  # Old syntax
+        "@[Custom Title][py-link]\n",  # New syntax
+        ":::\n"
+    ]
+    markdown = "".join(lines)
+    result = _replace_autolinks(markdown, "test.md")
+    expected = "".join([
+        ":::python\n",
+        "[py-link](https://example.com/python)\n",
+        "[Custom Title](https://example.com/python)\n",
+        ":::\n"
+    ])
+    assert result == expected
+
+
+def test_custom_title_with_unknown_link(mock_link_maps) -> None:
+    """Test @[title][ref] syntax with unknown reference."""
+    lines = [
+        ":::python\n",
+        "@[Custom Title][unknown-link]\n",
+        ":::\n"
+    ]
+    markdown = "".join(lines)
+    result = _replace_autolinks(markdown, "test.md")
+    expected = "".join([
+        ":::python\n",
+        "@[Custom Title][unknown-link]\n",  # Should remain unchanged
+        ":::\n"
+    ])
+    assert result == expected
@@ -152,6 +152,14 @@ base64-js@^1.5.1:
  resolved "https://registry.yarnpkg.com/base64-js/-/base64-js-1.5.1.tgz#1b1b440160a5bf7ad40b650f095963481903930a"
  integrity sha512-AKpaYlHn8t4SVbOHCy+b5+KKgvR4vrsD8vbvrbiQJps7fKDTkjkDry6ji0rUJjC0kzbNePLwzxq8iypo41qeWA==

+call-bind-apply-helpers@^1.0.1, call-bind-apply-helpers@^1.0.2:
+  version "1.0.2"
+  resolved "https://registry.yarnpkg.com/call-bind-apply-helpers/-/call-bind-apply-helpers-1.0.2.tgz#4b5428c222be985d79c3d82657479dbe0b59b2d6"
+  integrity sha512-Sp1ablJ0ivDkSzjcaJdxEunN5/XvksFJ2sMBFfq6x0ryhQV/2b/KwFe21cMpmHtPOSij8K99/wSfoEuTObmuMQ==
+  dependencies:
+    es-errors "^1.3.0"
+    function-bind "^1.1.2"
+
 camelcase@6:
  version "6.3.0"
  resolved "https://registry.yarnpkg.com/camelcase/-/camelcase-6.3.0.tgz#5685b95eb209ac9c0c177467778c9c84df58ba9a"
@@ -201,6 +209,42 @@ delayed-stream@~1.0.0:
  resolved "https://registry.yarnpkg.com/delayed-stream/-/delayed-stream-1.0.0.tgz#df3ae199acadfb7d440aaae0b29e2272b24ec619"
  integrity sha512-ZySD7Nf91aLB0RxL4KGrKHBXl7Eds1DAmEdcoVawXnLD7SDhpNgtuII2aAkg7a7QS41jxPSZ17p4VdGnMHk3MQ==

+dunder-proto@^1.0.1:
+  version "1.0.1"
+  resolved "https://registry.yarnpkg.com/dunder-proto/-/dunder-proto-1.0.1.tgz#d7ae667e1dc83482f8b70fd0f6eefc50da30f58a"
+  integrity sha512-KIN/nDJBQRcXw0MLVhZE9iQHmG68qAVIBg9CqmUYjmQIhgij9U5MFvrqkUL5FbtyyzZuOeOt0zdeRe4UY7ct+A==
+  dependencies:
+    call-bind-apply-helpers "^1.0.1"
+    es-errors "^1.3.0"
+    gopd "^1.2.0"
+
+es-define-property@^1.0.1:
+  version "1.0.1"
+  resolved "https://registry.yarnpkg.com/es-define-property/-/es-define-property-1.0.1.tgz#983eb2f9a6724e9303f61addf011c72e09e0b0fa"
+  integrity sha512-e3nRfgfUZ4rNGL232gUgX06QNyyez04KdjFrF+LTRoOXmrOgFKDg4BCdsjW8EnT69eqdYGmRpJwiPVYNrCaW3g==
+
+es-errors@^1.3.0:
+  version "1.3.0"
+  resolved "https://registry.yarnpkg.com/es-errors/-/es-errors-1.3.0.tgz#05f75a25dab98e4fb1dcd5e1472c0546d5057c8f"
+  integrity sha512-Zf5H2Kxt2xjTvbJvP2ZWLEICxA6j+hAmMzIlypy4xcBg1vKVnx89Wy0GbS+kf5cwCVFFzdCFh2XSCFNULS6csw==
+
+es-object-atoms@^1.0.0, es-object-atoms@^1.1.1:
+  version "1.1.1"
+  resolved "https://registry.yarnpkg.com/es-object-atoms/-/es-object-atoms-1.1.1.tgz#1c4f2c4837327597ce69d2ca190a7fdd172338c1"
+  integrity sha512-FGgH2h8zKNim9ljj7dankFPcICIK9Cp5bm+c2gQSYePhpaG5+esrLODihIorn+Pe6FGJzWhXQotPv73jTaldXA==
+  dependencies:
+    es-errors "^1.3.0"
+
+es-set-tostringtag@^2.1.0:
+  version "2.1.0"
+  resolved "https://registry.yarnpkg.com/es-set-tostringtag/-/es-set-tostringtag-2.1.0.tgz#f31dbbe0c183b00a6d26eb6325c810c0fd18bd4d"
+  integrity sha512-j6vWzfrGVfyXxge+O0x5sh6cvxAog0a/4Rdd2K36zCMV5eJ+/+tOAngRO8cODMNWbVRdVlmGZQL2YS3yR8bIUA==
+  dependencies:
+    es-errors "^1.3.0"
+    get-intrinsic "^1.2.6"
+    has-tostringtag "^1.0.2"
+    hasown "^2.0.2"
+
 event-lite@^0.1.1:
  version "0.1.3"
  resolved "https://registry.yarnpkg.com/event-lite/-/event-lite-0.1.3.tgz#3dfe01144e808ac46448f0c19b4ab68e403a901d"
@@ -222,12 +266,14 @@ form-data-encoder@1.7.2:
  integrity sha512-qfqtYan3rxrnCk1VYaA4H+Ms9xdpPqvLZa6xmMgFvhO32x7/3J/ExcTd6qpxM0vH2GdMI+poehyBZvqfMTto8A==

 form-data@^4.0.0:
-  version "4.0.1"
-  resolved "https://registry.yarnpkg.com/form-data/-/form-data-4.0.1.tgz#ba1076daaaa5bfd7e99c1a6cb02aa0a5cff90d48"
-  integrity sha512-tzN8e4TX8+kkxGPK8D5u0FNmjPUjw3lwC9lSLxxoB/+GtsJG91CO8bSWy73APlgAZzZbXEYZJuxjkHH2w+Ezhw==
+  version "4.0.4"
+  resolved "https://registry.yarnpkg.com/form-data/-/form-data-4.0.4.tgz#784cdcce0669a9d68e94d11ac4eea98088edd2c4"
+  integrity sha512-KrGhL9Q4zjj0kiUt5OO4Mr/A/jlI2jDYs5eHBpYHPcBEVSiipAvn2Ko2HnPe20rmcuuvMHNdZFp+4IlGTMF0Ow==
  dependencies:
    asynckit "^0.4.0"
    combined-stream "^1.0.8"
+    es-set-tostringtag "^2.1.0"
+    hasown "^2.0.2"
    mime-types "^2.1.12"

 formdata-node@^4.3.2:
@@ -238,11 +284,69 @@ formdata-node@^4.3.2:
    node-domexception "1.0.0"
    web-streams-polyfill "4.0.0-beta.3"

+function-bind@^1.1.2:
+  version "1.1.2"
+  resolved "https://registry.yarnpkg.com/function-bind/-/function-bind-1.1.2.tgz#2c02d864d97f3ea6c8830c464cbd11ab6eab7a1c"
+  integrity sha512-7XHNxH7qX9xG5mIwxkhumTox/MIRNcOgDrxWsMt2pAr23WHp6MrRlN7FBSFpCpr+oVO0F744iUgR82nJMfG2SA==
+
+get-intrinsic@^1.2.6:
+  version "1.3.0"
+  resolved "https://registry.yarnpkg.com/get-intrinsic/-/get-intrinsic-1.3.0.tgz#743f0e3b6964a93a5491ed1bffaae054d7f98d01"
+  integrity sha512-9fSjSaos/fRIVIp+xSJlE6lfwhES7LNtKaCBIamHsjr2na1BiABJPo0mOjjz8GJDURarmCPGqaiVg5mfjb98CQ==
+  dependencies:
+    call-bind-apply-helpers "^1.0.2"
+    es-define-property "^1.0.1"
+    es-errors "^1.3.0"
+    es-object-atoms "^1.1.1"
+    function-bind "^1.1.2"
+    get-proto "^1.0.1"
+    gopd "^1.2.0"
+    has-symbols "^1.1.0"
+    hasown "^2.0.2"
+    math-intrinsics "^1.1.0"
+
+get-proto@^1.0.1:
+  version "1.0.1"
+  resolved "https://registry.yarnpkg.com/get-proto/-/get-proto-1.0.1.tgz#150b3f2743869ef3e851ec0c49d15b1d14d00ee1"
+  integrity sha512-sTSfBjoXBp89JvIKIefqw7U2CCebsc74kiY6awiGogKtoSGbgjYE/G/+l9sF3MWFPNc9IcoOC4ODfKHfxFmp0g==
+  dependencies:
+    dunder-proto "^1.0.1"
+    es-object-atoms "^1.0.0"
+
+gopd@^1.2.0:
+  version "1.2.0"
+  resolved "https://registry.yarnpkg.com/gopd/-/gopd-1.2.0.tgz#89f56b8217bdbc8802bd299df6d7f1081d7e51a1"
+  integrity sha512-ZUKRh6/kUFoAiTAtTYPZJ3hw9wNxx+BIBOijnlG9PnrJsCcSjs1wyyD6vJpaYtgnzDrKYRSqf3OO6Rfa93xsRg==
+
 has-flag@^4.0.0:
  version "4.0.0"
  resolved "https://registry.yarnpkg.com/has-flag/-/has-flag-4.0.0.tgz#944771fd9c81c81265c4d6941860da06bb59479b"
  integrity sha512-EykJT/Q1KjTWctppgIAgfSO0tKVuZUjhgMr17kqTumMl6Afv3EISleU7qZUzoXDFTAHTDC4NOoG/ZxU3EvlMPQ==

+has-symbols@^1.0.3, has-symbols@^1.1.0:
+  version "1.1.0"
+  resolved "https://registry.yarnpkg.com/has-symbols/-/has-symbols-1.1.0.tgz#fc9c6a783a084951d0b971fe1018de813707a338"
+  integrity sha512-1cDNdwJ2Jaohmb3sg4OmKaMBwuC48sYni5HUw2DvsC8LjGTLK9h+eb1X6RyuOHe4hT0ULCW68iomhjUoKUqlPQ==
+
+has-tostringtag@^1.0.2:
+  version "1.0.2"
+  resolved "https://registry.yarnpkg.com/has-tostringtag/-/has-tostringtag-1.0.2.tgz#2cdc42d40bef2e5b4eeab7c01a73c54ce7ab5abc"
+  integrity sha512-NqADB8VjPFLM2V0VvHUewwwsw0ZWBaIdgo+ieHtK3hasLz4qeCRjYcqfB6AQrBggRKppKF8L52/VqdVsO47Dlw==
+  dependencies:
+    has-symbols "^1.0.3"
+
+hasown@^2.0.2:
+  version "2.0.2"
+  resolved "https://registry.yarnpkg.com/hasown/-/hasown-2.0.2.tgz#003eaf91be7adc372e84ec59dc37252cedb80003"
+  integrity sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ==
+  dependencies:
+    function-bind "^1.1.2"
+
+he@^1.2.0:
+  version "1.2.0"
+  resolved "https://registry.yarnpkg.com/he/-/he-1.2.0.tgz#84ae65fa7eafb165fddb61566ae14baf05664f0f"
+  integrity sha512-F/1DnUGPopORZi0ni+CvrCgHQ5FyEAHRLSApuYWMmrbSwoN2Mn/7k+Gl38gJnR7yyDZk6WLXwiGod1JOWNDKGw==
+
 humanize-ms@^1.2.1:
  version "1.2.1"
  resolved "https://registry.yarnpkg.com/humanize-ms/-/humanize-ms-1.2.1.tgz#c46e3159a293f6b896da29316d8b6fe8bb79bbed"
@@ -295,6 +399,11 @@ json-stringify-safe@^5.0.1:
    semver "^7.6.3"
    uuid "^10.0.0"

+math-intrinsics@^1.1.0:
+  version "1.1.0"
+  resolved "https://registry.yarnpkg.com/math-intrinsics/-/math-intrinsics-1.1.0.tgz#a0dd74be81e2aa5c2f27e65ce283605ee4e2b7f9"
+  integrity sha512-/IXtbwEk5HTPyEwyKX6hGkYXxM9nbj64B+ilVJnC/R6B0pH5G4V3b0pVbL7DBj4tkhBAppbQUlf6F6Xl9LHu1g==
+
 mime-db@1.52.0:
  version "1.52.0"
  resolved "https://registry.yarnpkg.com/mime-db/-/mime-db-1.52.0.tgz#bbabcdc02859f4987301c856e3387ce5ec43bf70"
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"

 [project]
 name = "langgraph-checkpoint-sqlite"
-version = "2.0.10"
+version = "2.0.11"
 description = "Library with a SQLite implementation of LangGraph checkpoint saver."
 authors = []
 requires-python = ">=3.9"
@@ -346,7 +346,7 @@ dev = [

 [[package]]
 name = "langgraph-checkpoint-sqlite"
-version = "2.0.10"
+version = "2.0.11"
 source = { editable = "." }
 dependencies = [
    { name = "aiosqlite" },
@@ -165,7 +165,7 @@ def patch_config(
          Defaults to None.
        recursion_limit: The recursion limit to set.
          Defaults to None.
-        max_concurrency: The max concurrency to set.
+        max_concurrency: The max number of concurrent steps to run, which also applies to parallelized steps.
          Defaults to None.
        run_name: The run name to set. Defaults to None.
        configurable: The configurable to set.
@@ -22,6 +22,7 @@ from typing import (
    Protocol,
    Union,
    cast,
+    get_type_hints,
 )

 from langchain_core.runnables.base import (
@@ -127,71 +128,27 @@ ANY_TYPE = object()

 ASYNCIO_ACCEPTS_CONTEXT = sys.version_info >= (3, 11)

-# List of keyword arguments that can be injected into nodes / tasks / tools at runtime.
-# A named argument may appear multiple times if it appears with distinct types.
-KWARGS_CONFIG_KEYS: tuple[tuple[str, tuple[Any, ...], str, Any], ...] = (
-    (
-        "config",
-        (RunnableConfig, "RunnableConfig", inspect.Parameter.empty),
-        # for now, use config directly, eventually, will pop off of Runtime
-        "N/A",
-        inspect.Parameter.empty,
-    ),
-    (
-        "writer",
-        (StreamWriter, "StreamWriter", inspect.Parameter.empty),
-        "stream_writer",
-        lambda _: None,
-    ),
-    (
-        "store",
-        (
-            BaseStore,
-            "BaseStore",
-            inspect.Parameter.empty,
-        ),
-        "store",
-        inspect.Parameter.empty,
-    ),
-    (
-        "store",
-        (
-            Optional[BaseStore],
-            "Optional[BaseStore]",
-        ),
-        "store",
-        None,
-    ),
-    (
-        "previous",
-        (ANY_TYPE,),
-        "previous",
-        inspect.Parameter.empty,
-    ),
-    (
-        "runtime",
-        (ANY_TYPE,),
-        # we never hit this block, we just inject runtime directly
-        "N/A",
-        inspect.Parameter.empty,
-    ),
+# Configuration for keyword arguments that can be injected at runtime
+KWARGS_CONFIG_KEYS: tuple[tuple[str, str, Any], ...] = (
+    ("config", "N/A", inspect.Parameter.empty),
+    ("writer", "stream_writer", lambda _: None),
+    ("store", "store", inspect.Parameter.empty),
+    ("previous", "previous", inspect.Parameter.empty),
+    ("runtime", "N/A", inspect.Parameter.empty),
 )
 """List of kwargs that can be passed to functions, and their corresponding
-config keys, default values and type annotations.
+runtime keys and default values.

 Used to configure keyword arguments that can be injected at runtime
 from the `Runtime` object as kwargs to `invoke`, `ainvoke`, `stream` and `astream`.

 For a keyword to be injected from the config object, the function signature
-must contain a kwarg with the same name and a matching type annotation.
+must contain a kwarg with the same name and a compatible type annotation.

 Each tuple contains:
 - the name of the kwarg in the function signature
- the type annotation(s) for the kwarg
- the `Runtime` attribute for fetching the value (N/A if not applicable)
-
-This is fully internal and should be further refactored to use `get_type_hints`
-to resolve forward references and optional types formatted like BaseStore | None.
+- the `Runtime` attribute for fetching the value (N/A if not applicable)  
+- the default value to use if the runtime value is missing
 """

 VALID_KINDS = (inspect.Parameter.POSITIONAL_OR_KEYWORD, inspect.Parameter.KEYWORD_ONLY)
@@ -285,22 +242,63 @@ class RunnableCallable(Runnable):
            raise ValueError("At least one of func or afunc must be provided.")

        self.func_accepts: dict[str, tuple[str, Any]] = {}
-        params = inspect.signature(cast(Callable, func or afunc)).parameters
+        func_or_afunc = cast(Callable, func or afunc)
+        params = inspect.signature(func_or_afunc).parameters
+        
+        # Get resolved type hints to properly handle forward references and unions
+        try:
+            type_hints = get_type_hints(func_or_afunc)
+        except (NameError, AttributeError):
+            # Fallback to raw annotations if type resolution fails
+            type_hints = getattr(func_or_afunc, '__annotations__', {})

-        for kw, typ, runtime_key, default in KWARGS_CONFIG_KEYS:
+        for kw, runtime_key, default in KWARGS_CONFIG_KEYS:
            p = params.get(kw)

            if p is None or p.kind not in VALID_KINDS:
                # If parameter is not found or is not a valid kind, skip
                continue

-            if typ != (ANY_TYPE,) and p.annotation not in typ:
-                # A specific type is required, but the function annotation does
-                # not match the expected type.
-                continue
-
-            # If the kwarg is accepted by the function, store the key / runtime attribute to inject
-            self.func_accepts[kw] = (runtime_key, default)
+            # Get the resolved type hint for this parameter
+            param_type = type_hints.get(kw, p.annotation)
+            
+            # Check if this parameter should be injected based on its type
+            if self._should_inject_param(kw, param_type):
+                self.func_accepts[kw] = (runtime_key, default)
+    
+    def _should_inject_param(self, param_name: str, param_type: Any) -> bool:
+        """Determine if a parameter should be injected based on its name and type."""
+        if param_name == "config":
+            # Accept RunnableConfig, Optional[RunnableConfig], or no annotation
+            return (
+                param_type is inspect.Parameter.empty
+                or param_type is RunnableConfig
+                or param_type == Optional[RunnableConfig]
+                or (hasattr(param_type, '__origin__') and param_type.__origin__ is Union
+                    and RunnableConfig in param_type.__args__
+                    and type(None) in param_type.__args__)
+            )
+        elif param_name == "writer":
+            # Accept StreamWriter or no annotation
+            return (
+                param_type is inspect.Parameter.empty
+                or param_type is StreamWriter
+            )
+        elif param_name == "store":
+            # Accept BaseStore, Optional[BaseStore], or no annotation
+            return (
+                param_type is inspect.Parameter.empty
+                or param_type is BaseStore
+                or param_type == Optional[BaseStore]
+                or (hasattr(param_type, '__origin__') and param_type.__origin__ is Union
+                    and BaseStore in param_type.__args__
+                    and type(None) in param_type.__args__)
+            )
+        elif param_name in ("previous", "runtime"):
+            # Accept any type for previous and runtime
+            return True
+        
+        return False

    def __repr__(self) -> str:
        repr_args = {
@@ -116,7 +116,7 @@ from langgraph.pregel._validate import validate_graph, validate_keys
 from langgraph.pregel._write import ChannelWrite, ChannelWriteEntry
 from langgraph.pregel.debug import get_bolded_text, get_colored_text, tasks_w_writes
 from langgraph.pregel.protocol import PregelProtocol, StreamChunk, StreamProtocol
-from langgraph.runtime import Runtime
+from langgraph.runtime import DEFAULT_RUNTIME, Runtime
 from langgraph.store.base import BaseStore
 from langgraph.types import (
    All,
@@ -2570,12 +2570,16 @@ class Pregel(
            if durability is not None or deprecated_checkpoint_during is not None:
                config[CONF][CONFIG_KEY_DURABILITY] = durability_

-            config[CONF][CONFIG_KEY_RUNTIME] = Runtime(
+            runtime = Runtime(
                context=context,
                store=store,
                stream_writer=stream_writer,
                previous=None,
            )
+            parent_runtime = config[CONF].get(CONFIG_KEY_RUNTIME, DEFAULT_RUNTIME)
+            runtime = parent_runtime.merge(runtime)
+            config[CONF][CONFIG_KEY_RUNTIME] = runtime
+
            with SyncPregelLoop(
                input,
                stream=StreamProtocol(stream.put, stream_modes),
@@ -2861,12 +2865,16 @@ class Pregel(
            if durability is not None or deprecated_checkpoint_during is not None:
                config[CONF][CONFIG_KEY_DURABILITY] = durability_

-            config[CONF][CONFIG_KEY_RUNTIME] = Runtime(
+            runtime = Runtime(
                context=context,
                store=store,
                stream_writer=stream_writer,
                previous=None,
            )
+            parent_runtime = config[CONF].get(CONFIG_KEY_RUNTIME, DEFAULT_RUNTIME)
+            runtime = parent_runtime.merge(runtime)
+            config[CONF][CONFIG_KEY_RUNTIME] = runtime
+
            async with AsyncPregelLoop(
                input,
                stream=StreamProtocol(stream.put_nowait, stream_modes),
@@ -0,0 +1 @@
+"""Legacy utilities module, to be removed in v1."""
@@ -0,0 +1,4 @@
+"""Backwards compat imports for config utilities, to be removed in v1."""
+
+from langgraph._internal._config import ensure_config, patch_configurable  # noqa: F401
+from langgraph.config import get_config, get_store  # noqa: F401
@@ -0,0 +1,3 @@
+"""Backwards compat imports for runnable utilities, to be removed in v1."""
+
+from langgraph._internal._runnable import RunnableCallable, RunnableLike  # noqa: F401
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"

 [project]
 name = "langgraph"
-version = "0.6.0a1"
+version = "0.6.0"
 description = "Building stateful, multi-actor applications with LLMs"
 authors = []
 requires-python = ">=3.9"
@@ -3,6 +3,7 @@ from __future__ import annotations
 from typing import Any, Optional

 import pytest
+from langchain_core.runnables.config import RunnableConfig

 from langgraph._internal._runnable import RunnableCallable
 from langgraph.runtime import Runtime
@@ -370,3 +371,26 @@ async def test_runnable_callable_injectable_arguments_async() -> None:
        )
        == "success"
    )
+
+
+def test_config_injection() -> None:
+    def func(x: Any, config: RunnableConfig) -> list[str]:
+        return config.get("tags", [])
+
+    assert RunnableCallable(func).invoke(
+        "test", config={"tags": ["test"], "configurable": {}}
+    ) == ["test"]
+
+    def func_optional(x: Any, config: Optional[RunnableConfig]) -> list[str]:
+        return config.get("tags", []) if config else []
+
+    assert RunnableCallable(func_optional).invoke(
+        "test", config={"tags": ["test"], "configurable": {}}
+    ) == ["test"]
+
+    def func_untyped(x: Any, config) -> list[str]:
+        return config.get("tags", [])
+
+    assert RunnableCallable(func_untyped).invoke(
+        "test", config={"tags": ["test"], "configurable": {}}
+    ) == ["test"]
@@ -7,16 +7,14 @@ from langgraph.graph import END, START, StateGraph
 from langgraph.runtime import Runtime, get_runtime


-@dataclass
-class Context:
-    api_key: str
-
-
-class State(TypedDict):
-    message: str
-
-
 def test_injected_runtime() -> None:
+    @dataclass
+    class Context:
+        api_key: str
+
+    class State(TypedDict):
+        message: str
+
    def injected_runtime(state: State, runtime: Runtime[Context]) -> dict[str, Any]:
        return {"message": f"api key: {runtime.context.api_key}"}

@@ -32,6 +30,13 @@ def test_injected_runtime() -> None:


 def test_context_runtime() -> None:
+    @dataclass
+    class Context:
+        api_key: str
+
+    class State(TypedDict):
+        message: str
+
    def context_runtime(state: State) -> dict[str, Any]:
        runtime = get_runtime(Context)
        return {"message": f"api key: {runtime.context.api_key}"}
@@ -45,3 +50,59 @@ def test_context_runtime() -> None:
        {"message": "hello world"}, context=Context(api_key="sk_123456")
    )
    assert result == {"message": "api key: sk_123456"}
+
+
+def test_override_runtime() -> None:
+    @dataclass
+    class Context:
+        api_key: str
+
+    prev = Runtime(context=Context(api_key="abc"))
+    new = prev.override(context=Context(api_key="def"))
+    assert new.override(context=Context(api_key="def")).context.api_key == "def"
+
+
+def test_merge_runtime() -> None:
+    @dataclass
+    class Context:
+        api_key: str
+
+    runtime1 = Runtime(context=Context(api_key="abc"))
+    runtime2 = Runtime(context=Context(api_key="def"))
+    runtime3 = Runtime(context=None)
+
+    assert runtime1.merge(runtime2).context.api_key == "def"
+    # override only applies to non-falsy values
+    assert runtime1.merge(runtime3).context.api_key == "abc"  # type: ignore
+
+
+def test_runtime_propogated_to_subgraph() -> None:
+    @dataclass
+    class Context:
+        username: str
+
+    class State(TypedDict, total=False):
+        subgraph: str
+        main: str
+
+    def subgraph_node_1(state: State, runtime: Runtime[Context]):
+        return {"subgraph": f"{runtime.context.username}!"}
+
+    subgraph_builder = StateGraph(State, context_schema=Context)
+    subgraph_builder.add_node(subgraph_node_1)
+    subgraph_builder.set_entry_point("subgraph_node_1")
+    subgraph = subgraph_builder.compile()
+
+    def main_node(state: State, runtime: Runtime[Context]):
+        return {"main": f"{runtime.context.username}!"}
+
+    builder = StateGraph(State, context_schema=Context)
+    builder.add_node(main_node)
+    builder.add_node("node_1", subgraph)
+    builder.set_entry_point("main_node")
+    builder.add_edge("main_node", "node_1")
+    graph = builder.compile()
+
+    context = Context(username="Alice")
+    result = graph.invoke({}, context=context)
+    assert result == {"subgraph": "Alice!", "main": "Alice!"}
@@ -1,2 +0,0 @@
-# import for backwards compatibility
-from langgraph._internal._runnable import RunnableCallable, RunnableSeq  # noqa: F401
@@ -1192,7 +1192,7 @@ wheels = [

 [[package]]
 name = "langgraph"
-version = "0.6.0a1"
+version = "0.6.0"
 source = { editable = "." }
 dependencies = [
    { name = "langchain-core" },
@@ -1364,7 +1364,7 @@ dev = [

 [[package]]
 name = "langgraph-checkpoint-sqlite"
-version = "2.0.10"
+version = "2.0.11"
 source = { editable = "../checkpoint-sqlite" }
 dependencies = [
    { name = "aiosqlite" },
@@ -1,6 +1,7 @@
 import inspect
 from typing import (
    Any,
+    Awaitable,
    Callable,
    Literal,
    Optional,
@@ -44,8 +45,10 @@ from langgraph.graph.state import CompiledStateGraph
 from langgraph.managed import IsLastStep, RemainingSteps
 from langgraph.prebuilt._internal import ToolCallWithContext
 from langgraph.prebuilt.tool_node import ToolNode
+from langgraph.runtime import Runtime
 from langgraph.store.base import BaseStore
 from langgraph.types import Checkpointer, Send
+from langgraph.typing import ContextT
 from langgraph.warnings import LangGraphDeprecatedSinceV10

 StructuredResponse = Union[dict, BaseModel]
@@ -246,7 +249,12 @@ def _validate_chat_history(


 def create_react_agent(
-    model: Union[str, LanguageModelLike],
+    model: Union[
+        str,
+        LanguageModelLike,
+        Callable[[StateSchema, Runtime[ContextT]], BaseChatModel],
+        Callable[[StateSchema, Runtime[ContextT]], Awaitable[BaseChatModel]],
+    ],
    tools: Union[Sequence[Union[BaseTool, Callable, dict[str, Any]]], ToolNode],
    *,
    prompt: Optional[Prompt] = None,
@@ -271,7 +279,43 @@ def create_react_agent(
    For more details on using `create_react_agent`, visit [Agents](https://langchain-ai.github.io/langgraph/agents/overview/) documentation.

    Args:
-        model: The `LangChain` chat model that supports tool calling.
+        model: The language model for the agent. Supports static and dynamic
+            model selection.
+
+            - **Static model**: A chat model instance (e.g., `ChatOpenAI()`) or
+              string identifier (e.g., `"openai:gpt-4"`)
+            - **Dynamic model**: A callable with signature
+              `(state, runtime) -> BaseChatModel` that returns different models
+              based on runtime context
+
+            Dynamic functions receive graph state and runtime, enabling
+            context-dependent model selection. Must return a `BaseChatModel`
+            instance. For tool calling, bind tools using `.bind_tools()`.
+            Bound tools must be a subset of the `tools` parameter.
+
+            Dynamic model example:
+            ```python
+            from dataclasses import dataclass
+
+            @dataclass
+            class ModelContext:
+                model_name: str = "gpt-3.5-turbo"
+
+            # Instantiate models globally
+            gpt4_model = ChatOpenAI(model="gpt-4")
+            gpt35_model = ChatOpenAI(model="gpt-3.5-turbo")
+
+            def select_model(state: AgentState, runtime: Runtime[ModelContext]) -> ChatOpenAI:
+                model_name = runtime.context.model_name
+                model = gpt4_model if model_name == "gpt-4" else gpt35_model
+                return model.bind_tools(tools)
+            ```
+
+            !!! note "Dynamic Model Requirements"
+                Ensure returned models have appropriate tools bound via
+                `.bind_tools()` and support required functionality. Bound tools
+                must be a subset of those specified in the `tools` parameter.
+
        tools: A list of tools or a ToolNode instance.
            If an empty list is provided, the agent will consist of a single LLM node without tool calling.
        prompt: An optional prompt for the LLM. Can take a few different forms:
@@ -452,32 +496,63 @@ def create_react_agent(
        tool_node = ToolNode([t for t in tools if not isinstance(t, dict)])
        tool_classes = list(tool_node.tools_by_name.values())

-    if isinstance(model, str):
-        try:
-            from langchain.chat_models import (  # type: ignore[import-not-found]
-                init_chat_model,
-            )
-        except ImportError:
-            raise ImportError(
-                "Please install langchain (`pip install langchain`) to use '<provider>:<model>' string syntax for `model` parameter."
-            )
-
-        model = cast(BaseChatModel, init_chat_model(model))
+    is_dynamic_model = not isinstance(model, (str, Runnable)) and callable(model)
+    is_async_dynamic_model = is_dynamic_model and inspect.iscoroutinefunction(model)

    tool_calling_enabled = len(tool_classes) > 0

-    if (
-        _should_bind_tools(model, tool_classes, num_builtin=len(llm_builtin_tools))
-        and len(tool_classes + llm_builtin_tools) > 0
-    ):
-        model = cast(BaseChatModel, model).bind_tools(tool_classes + llm_builtin_tools)  # type: ignore[operator]
+    if not is_dynamic_model:
+        if isinstance(model, str):
+            try:
+                from langchain.chat_models import (  # type: ignore[import-not-found]
+                    init_chat_model,
+                )
+            except ImportError:
+                raise ImportError(
+                    "Please install langchain (`pip install langchain`) to "
+                    "use '<provider>:<model>' string syntax for `model` parameter."
+                )

-    model_runnable = _get_prompt_runnable(prompt) | model
+            model = cast(BaseChatModel, init_chat_model(model))
+
+        if (
+            _should_bind_tools(model, tool_classes, num_builtin=len(llm_builtin_tools))  # type: ignore[arg-type]
+            and len(tool_classes + llm_builtin_tools) > 0
+        ):
+            model = cast(BaseChatModel, model).bind_tools(
+                tool_classes + llm_builtin_tools  # type: ignore[operator]
+            )
+
+        static_model: Optional[Runnable] = _get_prompt_runnable(prompt) | model  # type: ignore[operator]
+    else:
+        # For dynamic models, we'll create the runnable at runtime
+        static_model = None

    # If any of the tools are configured to return_directly after running,
    # our graph needs to check if these were called
    should_return_direct = {t.name for t in tool_classes if t.return_direct}

+    def _resolve_model(
+        state: StateSchema, runtime: Runtime[ContextT]
+    ) -> LanguageModelLike:
+        """Resolve the model to use, handling both static and dynamic models."""
+        if is_dynamic_model:
+            return _get_prompt_runnable(prompt) | model(state, runtime)  # type: ignore[operator]
+        else:
+            return static_model
+
+    async def _aresolve_model(
+        state: StateSchema, runtime: Runtime[ContextT]
+    ) -> LanguageModelLike:
+        """Async resolve the model to use, handling both static and dynamic models."""
+        if is_async_dynamic_model:
+            resolved_model = await model(state, runtime)  # type: ignore[misc,operator]
+            return _get_prompt_runnable(prompt) | resolved_model
+        elif is_dynamic_model:
+            return _get_prompt_runnable(prompt) | model(state, runtime)  # type: ignore[operator]
+        else:
+            return static_model
+
    def _are_more_steps_needed(state: StateSchema, response: BaseMessage) -> bool:
        has_tool_calls = isinstance(response, AIMessage) and response.tool_calls
        all_tools_return_direct = (
@@ -522,9 +597,26 @@ def create_react_agent(
        return state

    # Define the function that calls the model
-    def call_model(state: StateSchema, config: RunnableConfig) -> StateSchema:
-        state = _get_model_input_state(state)
-        response = cast(AIMessage, model_runnable.invoke(state, config))
+    def call_model(
+        state: StateSchema, runtime: Runtime[ContextT], config: RunnableConfig
+    ) -> StateSchema:
+        if is_async_dynamic_model:
+            msg = (
+                "Async model callable provided but agent invoked synchronously. "
+                "Use agent.ainvoke() or agent.astream(), or "
+                "provide a sync model callable."
+            )
+            raise RuntimeError(msg)
+
+        model_input = _get_model_input_state(state)
+
+        if is_dynamic_model:
+            # Resolve dynamic model at runtime and apply prompt
+            dynamic_model = _resolve_model(state, runtime)
+            response = cast(AIMessage, dynamic_model.invoke(model_input, config))  # type: ignore[arg-type]
+        else:
+            response = cast(AIMessage, static_model.invoke(model_input, config))  # type: ignore[union-attr]
+
        # add agent name to the AIMessage
        response.name = name

@@ -540,9 +632,19 @@ def create_react_agent(
        # We return a list, because this will get added to the existing list
        return {"messages": [response]}

-    async def acall_model(state: StateSchema, config: RunnableConfig) -> StateSchema:
-        state = _get_model_input_state(state)
-        response = cast(AIMessage, await model_runnable.ainvoke(state, config))
+    async def acall_model(
+        state: StateSchema, runtime: Runtime[ContextT], config: RunnableConfig
+    ) -> StateSchema:
+        model_input = _get_model_input_state(state)
+
+        if is_dynamic_model:
+            # Resolve dynamic model at runtime and apply prompt
+            # (supports both sync and async)
+            dynamic_model = await _aresolve_model(state, runtime)
+            response = cast(AIMessage, await dynamic_model.ainvoke(model_input, config))  # type: ignore[arg-type]
+        else:
+            response = cast(AIMessage, await static_model.ainvoke(model_input, config))  # type: ignore[union-attr]
+
        # add agent name to the AIMessage
        response.name = name
        if _are_more_steps_needed(state, response):
@@ -579,22 +681,32 @@ def create_react_agent(
        input_schema = state_schema

    def generate_structured_response(
-        state: StateSchema, config: RunnableConfig
+        state: StateSchema, runtime: Runtime[ContextT], config: RunnableConfig
    ) -> StateSchema:
+        if is_async_dynamic_model:
+            msg = (
+                "Async model callable provided but agent invoked synchronously. "
+                "Use agent.ainvoke() or agent.astream(), or provide a sync model callable."
+            )
+            raise RuntimeError(msg)
+
        messages = _get_state_value(state, "messages")
        structured_response_schema = response_format
        if isinstance(response_format, tuple):
            system_prompt, structured_response_schema = response_format
            messages = [SystemMessage(content=system_prompt)] + list(messages)

-        model_with_structured_output = _get_model(model).with_structured_output(
+        resolved_model = _resolve_model(state, runtime)
+        model_with_structured_output = _get_model(
+            resolved_model
+        ).with_structured_output(
            cast(StructuredResponseSchema, structured_response_schema)
        )
        response = model_with_structured_output.invoke(messages, config)
        return {"structured_response": response}

    async def agenerate_structured_response(
-        state: StateSchema, config: RunnableConfig
+        state: StateSchema, runtime: Runtime[ContextT], config: RunnableConfig
    ) -> StateSchema:
        messages = _get_state_value(state, "messages")
        structured_response_schema = response_format
@@ -602,7 +714,10 @@ def create_react_agent(
            system_prompt, structured_response_schema = response_format
            messages = [SystemMessage(content=system_prompt)] + list(messages)

-        model_with_structured_output = _get_model(model).with_structured_output(
+        resolved_model = await _aresolve_model(state, runtime)
+        model_with_structured_output = _get_model(
+            resolved_model
+        ).with_structured_output(
            cast(StructuredResponseSchema, structured_response_schema)
        )
        response = await model_with_structured_output.ainvoke(messages, config)
@@ -13,10 +13,12 @@ from typing import (
 )

 import pytest
+from langchain_core.language_models import BaseChatModel
 from langchain_core.messages import (
    AIMessage,
    AnyMessage,
    HumanMessage,
+    MessageLikeRepresentation,
    RemoveMessage,
    SystemMessage,
    ToolCall,
@@ -52,6 +54,7 @@ from langgraph.prebuilt.tool_node import (
    _get_state_args,
    _infer_handled_types,
 )
+from langgraph.runtime import Runtime
 from langgraph.store.base import BaseStore
 from langgraph.store.memory import InMemoryStore
 from langgraph.types import Command, Interrupt, interrupt
@@ -1092,7 +1095,7 @@ def test_inspect_react() -> None:

@pytest.mark.parametrize("version", REACT_TOOL_CALL_VERSIONS)
 def test_react_with_subgraph_tools(
-    sync_checkpointer: BaseCheckpointSaver, version: str
+    sync_checkpointer: BaseCheckpointSaver, version: Literal["v1", "v2"]
 ) -> None:
    class State(TypedDict):
        a: int
@@ -1367,6 +1370,376 @@ def test_get_model() -> None:
        _get_model(RunnableLambda(lambda message: message))


+@pytest.mark.parametrize("version", REACT_TOOL_CALL_VERSIONS)
+def test_dynamic_model_basic(version: str) -> None:
+    """Test basic dynamic model functionality."""
+
+    def dynamic_model(state, runtime: Runtime):
+        # Return different models based on state
+        if "urgent" in state["messages"][-1].content:
+            return FakeToolCallingModel(tool_calls=[])
+        else:
+            return FakeToolCallingModel(tool_calls=[])
+
+    agent = create_react_agent(dynamic_model, [], version=version)
+
+    result = agent.invoke({"messages": [HumanMessage("hello")]})
+    assert len(result["messages"]) == 2
+    assert result["messages"][-1].content == "hello"
+
+    result = agent.invoke({"messages": [HumanMessage("urgent help")]})
+    assert len(result["messages"]) == 2
+    assert result["messages"][-1].content == "urgent help"
+
+
+@pytest.mark.parametrize("version", REACT_TOOL_CALL_VERSIONS)
+def test_dynamic_model_with_tools(version: Literal["v1", "v2"]) -> None:
+    """Test dynamic model with tool calling."""
+
+    @dec_tool
+    def basic_tool(x: int) -> str:
+        """Basic tool."""
+        return f"basic: {x}"
+
+    @dec_tool
+    def advanced_tool(x: int) -> str:
+        """Advanced tool."""
+        return f"advanced: {x}"
+
+    def dynamic_model(state: dict, runtime: Runtime) -> BaseChatModel:
+        # Return model with different behaviors based on message content
+        if "advanced" in state["messages"][-1].content:
+            return FakeToolCallingModel(
+                tool_calls=[
+                    [{"args": {"x": 1}, "id": "1", "name": "advanced_tool"}],
+                    [],
+                ]
+            )
+        else:
+            return FakeToolCallingModel(
+                tool_calls=[[{"args": {"x": 1}, "id": "1", "name": "basic_tool"}], []]
+            )
+
+    agent = create_react_agent(
+        dynamic_model, [basic_tool, advanced_tool], version=version
+    )
+
+    # Test basic tool usage
+    result = agent.invoke({"messages": [HumanMessage("basic request")]})
+    assert len(result["messages"]) == 3
+    tool_message = result["messages"][-1]
+    assert tool_message.content == "basic: 1"
+    assert tool_message.name == "basic_tool"
+
+    # Test advanced tool usage
+    result = agent.invoke({"messages": [HumanMessage("advanced request")]})
+    assert len(result["messages"]) == 3
+    tool_message = result["messages"][-1]
+    assert tool_message.content == "advanced: 1"
+    assert tool_message.name == "advanced_tool"
+
+
+@dataclasses.dataclass
+class Context:
+    user_id: str
+
+
+@pytest.mark.parametrize("version", REACT_TOOL_CALL_VERSIONS)
+def test_dynamic_model_with_context(version: str) -> None:
+    """Test dynamic model using config parameters."""
+
+    def dynamic_model(state, runtime: Runtime[Context]):
+        # Use context to determine model behavior
+        user_id = runtime.context.user_id
+        if user_id == "user_premium":
+            return FakeToolCallingModel(tool_calls=[])
+        else:
+            return FakeToolCallingModel(tool_calls=[])
+
+    agent = create_react_agent(
+        dynamic_model, [], context_schema=Context, version=version
+    )
+
+    # Test with basic user
+    result = agent.invoke(
+        {"messages": [HumanMessage("hello")]},
+        context=Context(user_id="user_basic"),
+    )
+    assert len(result["messages"]) == 2
+
+    # Test with premium user
+    result = agent.invoke(
+        {"messages": [HumanMessage("hello")]},
+        context=Context(user_id="user_premium"),
+    )
+    assert len(result["messages"]) == 2
+
+
+@pytest.mark.parametrize("version", REACT_TOOL_CALL_VERSIONS)
+def test_dynamic_model_with_state_schema(version: Literal["v1", "v2"]) -> None:
+    """Test dynamic model with custom state schema."""
+
+    class CustomDynamicState(AgentState):
+        model_preference: str = "default"
+
+    def dynamic_model(state: CustomDynamicState, runtime: Runtime) -> BaseChatModel:
+        # Use custom state field to determine model
+        if state.get("model_preference") == "advanced":
+            return FakeToolCallingModel(tool_calls=[])
+        else:
+            return FakeToolCallingModel(tool_calls=[])
+
+    agent = create_react_agent(
+        dynamic_model, [], state_schema=CustomDynamicState, version=version
+    )
+
+    result = agent.invoke(
+        {"messages": [HumanMessage("hello")], "model_preference": "advanced"}
+    )
+    assert len(result["messages"]) == 2
+    assert result["model_preference"] == "advanced"
+
+
+@pytest.mark.parametrize("version", REACT_TOOL_CALL_VERSIONS)
+def test_dynamic_model_with_prompt(version: Literal["v1", "v2"]) -> None:
+    """Test dynamic model with different prompt types."""
+
+    def dynamic_model(state: AgentState, runtime: Runtime) -> BaseChatModel:
+        return FakeToolCallingModel(tool_calls=[])
+
+    # Test with string prompt
+    agent = create_react_agent(dynamic_model, [], prompt="system_msg", version=version)
+    result = agent.invoke({"messages": [HumanMessage("human_msg")]})
+    assert result["messages"][-1].content == "system_msg-human_msg"
+
+    # Test with callable prompt
+    def dynamic_prompt(state: AgentState) -> list[MessageLikeRepresentation]:
+        """Generate a dynamic system message based on state."""
+        return [{"role": "system", "content": "system_msg"}] + list(state["messages"])
+
+    agent = create_react_agent(
+        dynamic_model, [], prompt=dynamic_prompt, version=version
+    )
+    result = agent.invoke({"messages": [HumanMessage("human_msg")]})
+    assert result["messages"][-1].content == "system_msg-human_msg"
+
+
+async def test_dynamic_model_async() -> None:
+    """Test dynamic model with async operations."""
+
+    def dynamic_model(state: AgentState, runtime: Runtime) -> BaseChatModel:
+        return FakeToolCallingModel(tool_calls=[])
+
+    agent = create_react_agent(dynamic_model, [])
+
+    result = await agent.ainvoke({"messages": [HumanMessage("hello async")]})
+    assert len(result["messages"]) == 2
+    assert result["messages"][-1].content == "hello async"
+
+
+@pytest.mark.parametrize("version", REACT_TOOL_CALL_VERSIONS)
+def test_dynamic_model_with_structured_response(version: str) -> None:
+    """Test dynamic model with structured response format."""
+
+    class TestResponse(BaseModel):
+        message: str
+        confidence: float
+
+    def dynamic_model(state, runtime: Runtime):
+        expected_response = TestResponse(message="dynamic response", confidence=0.9)
+        return FakeToolCallingModel(
+            tool_calls=[], structured_response=expected_response
+        )
+
+    agent = create_react_agent(
+        dynamic_model, [], response_format=TestResponse, version=version
+    )
+
+    result = agent.invoke({"messages": [HumanMessage("hello")]})
+    assert "structured_response" in result
+    assert result["structured_response"].message == "dynamic response"
+    assert result["structured_response"].confidence == 0.9
+
+
+def test_dynamic_model_with_checkpointer(sync_checkpointer):
+    """Test dynamic model with checkpointer."""
+    call_count = 0
+
+    def dynamic_model(state: AgentState, runtime: Runtime) -> BaseChatModel:
+        nonlocal call_count
+        call_count += 1
+        return FakeToolCallingModel(
+            tool_calls=[],
+            # Incrementing the call count as it is used to assign an id
+            # to the AIMessage.
+            # The default reducer semantics are to overwrite an existing message
+            # with the new one if the id matches.
+            index=call_count,
+        )
+
+    agent = create_react_agent(dynamic_model, [], checkpointer=sync_checkpointer)
+    config = {"configurable": {"thread_id": "test_dynamic"}}
+
+    # First call
+    result1 = agent.invoke({"messages": [HumanMessage("hello")]}, config)
+    assert len(result1["messages"]) == 2  # Human + AI message
+
+    # Second call - should load from checkpoint
+    result2 = agent.invoke({"messages": [HumanMessage("world")]}, config)
+    assert len(result2["messages"]) == 4
+
+    # Dynamic model should be called each time
+    assert call_count >= 2
+
+
+@pytest.mark.parametrize("version", REACT_TOOL_CALL_VERSIONS)
+def test_dynamic_model_state_dependent_tools(version: Literal["v1", "v2"]) -> None:
+    """Test dynamic model that changes available tools based on state."""
+
+    @dec_tool
+    def tool_a(x: int) -> str:
+        """Tool A."""
+        return f"A: {x}"
+
+    @dec_tool
+    def tool_b(x: int) -> str:
+        """Tool B."""
+        return f"B: {x}"
+
+    def dynamic_model(state, runtime: Runtime):
+        # Switch tools based on message history
+        if any("use_b" in msg.content for msg in state["messages"]):
+            return FakeToolCallingModel(
+                tool_calls=[[{"args": {"x": 2}, "id": "1", "name": "tool_b"}], []]
+            )
+        else:
+            return FakeToolCallingModel(
+                tool_calls=[[{"args": {"x": 1}, "id": "1", "name": "tool_a"}], []]
+            )
+
+    agent = create_react_agent(dynamic_model, [tool_a, tool_b], version=version)
+
+    # Ask to use tool B
+    result = agent.invoke({"messages": [HumanMessage("use_b please")]})
+    last_message = result["messages"][-1]
+    assert isinstance(last_message, ToolMessage)
+    assert last_message.content == "B: 2"
+
+    # Ask to use tool A
+    result = agent.invoke({"messages": [HumanMessage("hello")]})
+    last_message = result["messages"][-1]
+    assert isinstance(last_message, ToolMessage)
+    assert last_message.content == "A: 1"
+
+
+@pytest.mark.parametrize("version", REACT_TOOL_CALL_VERSIONS)
+def test_dynamic_model_error_handling(version: Literal["v1", "v2"]) -> None:
+    """Test error handling in dynamic model."""
+
+    def failing_dynamic_model(state, runtime: Runtime):
+        if "fail" in state["messages"][-1].content:
+            raise ValueError("Dynamic model failed")
+        return FakeToolCallingModel(tool_calls=[])
+
+    agent = create_react_agent(failing_dynamic_model, [], version=version)
+
+    # Normal operation should work
+    result = agent.invoke({"messages": [HumanMessage("hello")]})
+    assert len(result["messages"]) == 2
+
+    # Should propagate the error
+    with pytest.raises(ValueError, match="Dynamic model failed"):
+        agent.invoke({"messages": [HumanMessage("fail now")]})
+
+
+def test_dynamic_model_vs_static_model_behavior():
+    """Test that dynamic and static models produce equivalent results when configured the same."""
+    # Static model
+    static_model = FakeToolCallingModel(tool_calls=[])
+    static_agent = create_react_agent(static_model, [])
+
+    # Dynamic model returning the same model
+    def dynamic_model(state, runtime: Runtime):
+        return FakeToolCallingModel(tool_calls=[])
+
+    dynamic_agent = create_react_agent(dynamic_model, [])
+
+    input_msg = {"messages": [HumanMessage("test message")]}
+
+    static_result = static_agent.invoke(input_msg)
+    dynamic_result = dynamic_agent.invoke(input_msg)
+
+    # Results should be equivalent (content-wise, IDs may differ)
+    assert len(static_result["messages"]) == len(dynamic_result["messages"])
+    assert static_result["messages"][0].content == dynamic_result["messages"][0].content
+    assert static_result["messages"][1].content == dynamic_result["messages"][1].content
+
+
+def test_dynamic_model_receives_correct_state():
+    """Test that the dynamic model function receives the correct state, not the model input."""
+    received_states = []
+
+    class CustomAgentState(AgentState):
+        custom_field: str
+
+    def dynamic_model(state, runtime: Runtime) -> BaseChatModel:
+        # Capture the state that's passed to the dynamic model function
+        received_states.append(state)
+        return FakeToolCallingModel(tool_calls=[])
+
+    agent = create_react_agent(dynamic_model, [], state_schema=CustomAgentState)
+
+    # Test with initial state
+    input_state = {"messages": [HumanMessage("hello")], "custom_field": "test_value"}
+    agent.invoke(input_state)
+
+    # The dynamic model function should receive the original state, not the processed model input
+    assert len(received_states) == 1
+    received_state = received_states[0]
+
+    # Should have the custom field from original state
+    assert "custom_field" in received_state
+    assert received_state["custom_field"] == "test_value"
+
+    # Should have the original messages
+    assert len(received_state["messages"]) == 1
+    assert received_state["messages"][0].content == "hello"
+
+
+async def test_dynamic_model_receives_correct_state_async():
+    """Test that the async dynamic model function receives the correct state, not the model input."""
+    received_states = []
+
+    class CustomAgentStateAsync(AgentState):
+        custom_field: str
+
+    def dynamic_model(state, runtime: Runtime):
+        # Capture the state that's passed to the dynamic model function
+        received_states.append(state)
+        return FakeToolCallingModel(tool_calls=[])
+
+    agent = create_react_agent(dynamic_model, [], state_schema=CustomAgentStateAsync)
+
+    # Test with initial state
+    input_state = {
+        "messages": [HumanMessage("hello async")],
+        "custom_field": "test_value_async",
+    }
+    await agent.ainvoke(input_state)
+
+    # The dynamic model function should receive the original state, not the processed model input
+    assert len(received_states) == 1
+    received_state = received_states[0]
+
+    # Should have the custom field from original state
+    assert "custom_field" in received_state
+    assert received_state["custom_field"] == "test_value_async"
+
+    # Should have the original messages
+    assert len(received_state["messages"]) == 1
+    assert received_state["messages"][0].content == "hello async"
+
+
 def test_pre_model_hook() -> None:
    model = FakeToolCallingModel(tool_calls=[])

@@ -316,7 +316,7 @@ wheels = [

 [[package]]
 name = "langgraph"
-version = "0.6.0a1"
+version = "0.6.0"
 source = { editable = "../langgraph" }
 dependencies = [
    { name = "langchain-core" },
@@ -430,7 +430,7 @@ dev = [

 [[package]]
 name = "langgraph-checkpoint-sqlite"
-version = "2.0.10"
+version = "2.0.11"
 source = { editable = "../checkpoint-sqlite" }
 dependencies = [
    { name = "aiosqlite" },
Author	SHA1	Message	Date
Sydney Runkle	f72b2db4d0	refactor	2025-07-29 15:19:12 -04:00
Sydney Runkle	dd91819c92	enforce config injection	2025-07-29 15:13:51 -04:00
Sydney RunkleandGitHub	b07964c98e	fix(langgraph): always use parent runtime info if available (#5707 )	2025-07-29 15:05:54 -04:00
Sydney Runkle	163d14f812	typo	2025-07-29 14:59:14 -04:00
Sydney Runkle	c0185f04e5	more robust tests	2025-07-29 14:58:16 -04:00
Sydney Runkle	82b31c9ffd	nits	2025-07-29 14:54:58 -04:00
Sydney Runkle	aade865727	remove unintentional import	2025-07-29 14:50:11 -04:00
Sydney Runkle	184bcacb53	use parent runtime	2025-07-29 14:47:05 -04:00
Eugene YurtsevandGitHub	d68bac3865	chore(docs): Support custom link titles (#5706 ) Support custom link titles for custom link syntax	2025-07-29 14:17:03 -04:00
Sydney RunkleandGitHub	824c309035	docs: update context conceptual page (#5696 )	2025-07-29 11:06:08 -04:00
Sydney Runkle	fdfd06056e	move tip	2025-07-29 11:00:40 -04:00
Sydney Runkle GitHub Lauren Hirata Singh	469ebd3492	Apply suggestions from code review Co-authored-by: Lauren Hirata Singh <lauren@langchain.dev>	2025-07-29 10:58:59 -04:00
Sydney Runkle	474fb7b33e	consolidate	2025-07-29 10:22:50 -04:00
Eugene YurtsevandGitHub	416da06d6b	feat(docs): manually insert fill in most of the magic links (#5702 ) These were done "manually" using openai. Likely error prone. We'll need to validate all the links.	2025-07-29 14:22:45 +00:00
Sydney Runkle	2297271863	refining tips	2025-07-29 10:19:48 -04:00
Sydney Runkle GitHub Lauren Hirata Singh	4910830efe	Apply suggestions from code review Co-authored-by: Lauren Hirata Singh <lauren@langchain.dev>	2025-07-29 10:04:49 -04:00
Eugene YurtsevandGitHub	027bb0a1b8	feat(docs): Support cross language "auto links" (#5699 ) Introduces a syntax for cross-reference links that work across language and change behavior depending on which scope they appear in. ```markdown @[interrupt] :::python @[StateGraph] ::: :::js @[create_react_agent] ::: ``` Can be compiled to ```markdown # a link that changes based on global context or compile target <div> ... </div> -> `interrupt` in global context :::python [StateGraph](link to python cross reference) ::: :::js [create_react_agent](link to js cross reference) ::: ``` TODO: - [x] fix broken unit test - [x] no f strings in logger (it's a sin) - [x] remove cross-refs.txt (we'll instead start updating the cross link map)	2025-07-29 10:00:23 -04:00
Sydney RunkleandGitHub	cd30b9cfea	docs: Add better definition for max_concurrency (#5701 )	2025-07-29 08:39:46 -04:00
Lauren Hirata Singh	5eb9826c46	docs: Add better definition for max_concurrency	2025-07-29 07:15:47 -04:00
Lauren Hirata SinghandGitHub	fa43b4694a	Apply suggestions from code review	2025-07-29 07:03:12 -04:00
Sydney Runkle	4d80f4b1a5	a few more nits	2025-07-28 19:11:30 -04:00
Sydney Runkle	70185d350e	adding xlinks	2025-07-28 19:02:47 -04:00
Sydney Runkle	89efd6e915	formatting	2025-07-28 18:50:37 -04:00
Lance Martin	d88ca6f649	Update	2025-07-28 15:15:45 -07:00
Sydney RunkleandGitHub	fadbe7d710	fix(docs): clarify value of context (#5689 )	2025-07-28 16:38:02 -04:00
Sydney Runkle	c861614337	Merge branch 'sr/more-context-for-context' of https://github.com/langchain-ai/langgraph into sr/more-context-for-context	2025-07-28 16:34:54 -04:00
Sydney Runkle	c020f01425	final nits	2025-07-28 16:34:13 -04:00
Sydney Runkle GitHub Lauren Hirata Singh	14949c81c8	Apply suggestions from code review Co-authored-by: Lauren Hirata Singh <lauren@langchain.dev>	2025-07-28 16:22:16 -04:00
Sydney Runkle	3af857922a	formatting for bullets	2025-07-28 16:19:27 -04:00
Sydney Runkle	7ec049e0c7	note on window	2025-07-28 16:15:56 -04:00
Sydney Runkle	1923ff8d85	first pass	2025-07-28 16:15:14 -04:00
Sydney RunkleandGitHub	4b9b7d0b1c	fix(docs): better docs for resuming multiple interrupts (#5688 )	2025-07-28 16:05:22 -04:00
Sydney Runkle GitHub Eugene Yurtsev	624247a51f	Update docs/docs/agents/context.md Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	2025-07-28 15:31:36 -04:00
Sydney Runkle	b21b595927	Merge branch 'sr/more-docs' of https://github.com/langchain-ai/langgraph into sr/more-docs	2025-07-28 15:21:24 -04:00
Sydney Runkle	f4633a0015	single example	2025-07-28 15:20:32 -04:00
Sam CrowderandGitHub	86017c010c	docs: [LangGraph Server Changelog Bot] Changelog updates for new version(s) (#5686 )	2025-07-28 12:17:20 -07:00
Sydney Runkle	2115cffc94	notes on context	2025-07-28 15:17:05 -04:00
Sydney Runkle GitHub Eugene Yurtsev	03726f9bc6	Update docs/docs/how-tos/human_in_the_loop/add-human-in-the-loop.md Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	2025-07-28 15:14:37 -04:00
Sydney Runkle	509dfd1f21	better hitl multi interrupt resume docs	2025-07-28 15:05:57 -04:00
Sam Crowder	efca21070d	Update changelog via LangGraph Server Changelog Bot	2025-07-28 10:10:50 -07:00
Sam CrowderandGitHub	dba20d0577	docs: [LangGraph Server Changelog Bot] Changelog updates for new version(s) (#5680 )	2025-07-28 07:51:52 -07:00
Sam Crowder	5145dac12b	Update changelog via LangGraph Server Changelog Bot	2025-07-28 07:39:31 -07:00
Sydney RunkleandGitHub	440c7ff12a	release(langgraph): v0.6.0 (#5684 )	2025-07-28 09:11:43 -04:00
Sydney RunkleandGitHub	5eef290c4e	fix(langgraph): backwards compat config utils (#5683 )	2025-07-28 09:06:38 -04:00
Sydney Runkle	a8b3746356	release prep v0.6	2025-07-28 09:05:23 -04:00
Sydney Runkle	7541331643	no top level file	2025-07-28 09:00:09 -04:00
Sydney Runkle	76814676c2	finalize utils	2025-07-28 08:57:46 -04:00
Sydney RunkleandGitHub	0804984f9d	Merge branch 'main' into sr/config-utils	2025-07-28 08:54:49 -04:00
Sydney Runkle	8f11b6a003	ensure_config and patch_configurable	2025-07-28 08:53:10 -04:00
Sam Crowder	aa6b122e4c	Update changelog via LangGraph Server Changelog Bot	2025-07-27 08:43:43 -07:00
Sam Crowder GitHub William FH	23491e5c9a	docs: [LangGraph Server Changelog Bot] Changelog updates for new version(s) (#5676 ) Automated changelog update created by the LangGraph Server Changelog Bot. Feel free to merge anytime. --------- Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com>	2025-07-27 13:38:15 +00:00
Sydney Runkle	1491f30a07	ensure config also	2025-07-25 16:23:28 -04:00
Sydney RunkleandGitHub	f63635d3c8	release: langgraph v0.6.0a1, langgraph-prebuilt v0.6.0a1 (#5671 )	2025-07-25 15:53:08 -04:00
Sydney RunkleandGitHub	6672032568	chore: add backwards compat utils imports to make v0.6 migration easier (#5670 )	2025-07-25 15:44:02 -04:00
Sydney Runkle	311ce7b04f	alpha bumps	2025-07-25 15:41:51 -04:00
Sydney Runkle	14b732740e	removal notice	2025-07-25 15:37:41 -04:00
Sydney Runkle	370825a48a	lint	2025-07-25 15:36:56 -04:00
Sydney Runkle	264bae5a7e	adding backwards compat utils imports to make my life easier	2025-07-25 15:35:48 -04:00
Eugene Yurtsev GitHub Sydney Runkle	f6aa19709e	feat(prebuilt): Add dynamic model to create_react_agent (#5651 ) This PR allows a developer to change the model configuration at run time based on context. This includes that list of tools available to the model to call. ```python def create_react_agent( model: Union[ str, LanguageModelLike, Callable[[SateLike, Runtime...], BaseChatModel], # <--- New ], tools: Union[ Sequence[Union[BaseTool, Callable, dict[str, Any]]], ToolNode] ], *, .... llm = init_chat_model(...) def prepare_model(state, runtime): selected_tool_names = func(state, context) return llm.bind(tools=selected_tool_names) create_react_agent( prepare_model, tools=all_known_tools ) ``` ## Semantics 1. `tools` = are the known tools, used to configure ToolNode and will configure: 1. model provided as string 2. model provided as BaseChatModel (if it has no tools bound to it) 2. If a user provides a dynamic model (callable), the user is responsible for binding tools Alternative considered: 1. Passing `Callable[[SateLike, Config...], list[BaseTool]]` to tools 2. Passing `Callable[[SateLike, Config...], list[str]]` to a tool selector Both have the issue that there's non obvious interplay between tool selection and dynamic models. (i.e., if we want to introduce dynamic models at in the future, the API will become tricky to explain) --------- Co-authored-by: Sydney Runkle <54324534+sydney-runkle@users.noreply.github.com>	2025-07-25 14:48:15 -04:00
Sydney RunkleandGitHub	8495f6f95d	chore(ci): harden release workflow (#5669 )	2025-07-25 14:45:18 -04:00
Eugene Yurtsev	6710908d40	x	2025-07-25 14:37:03 -04:00
Eugene Yurtsev	d24ad3d980	x	2025-07-25 14:34:49 -04:00
Eugene Yurtsev	2d8288fd0f	reduce permissions	2025-07-25 14:14:07 -04:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	c1ef10a0ec	chore: bump form-data from 4.0.1 to 4.0.4 in /docs (#5615 ) Bumps [form-data](https://github.com/form-data/form-data) from 4.0.1 to 4.0.4. <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/form-data/form-data/blob/master/CHANGELOG.md">form-data's changelog</a>.</em></p> <blockquote> <h2><a href="https://github.com/form-data/form-data/compare/v4.0.3...v4.0.4">v4.0.4</a> - 2025-07-16</h2> <h3>Commits</h3> <ul> <li>[meta] add <code>auto-changelog</code> <a href="https://github.com/form-data/form-data/commit/811f68282fab0315209d0e2d1c44b6c32ea0d479"><code>811f682</code></a></li> <li>[Tests] handle predict-v8-randomness failures in node < 17 and node > 23 <a href="https://github.com/form-data/form-data/commit/1d11a76434d101f22fdb26b8aef8615f28b98402"><code>1d11a76</code></a></li> <li>[Fix] Switch to using <code>crypto</code> random for boundary values <a href="https://github.com/form-data/form-data/commit/3d1723080e6577a66f17f163ecd345a21d8d0fd0"><code>3d17230</code></a></li> <li>[Tests] fix linting errors <a href="https://github.com/form-data/form-data/commit/5e340800b5f8914213e4e0378c084aae71cfd73a"><code>5e34080</code></a></li> <li>[meta] actually ensure the readme backup isn’t published <a href="https://github.com/form-data/form-data/commit/316c82ba93fd4985af757b771b9a1f26d3b709ef"><code>316c82b</code></a></li> <li>[Dev Deps] update <code>@ljharb/eslint-config</code> <a href="https://github.com/form-data/form-data/commit/58c25d76406a5b0dfdf54045cf252563f2bbda8d"><code>58c25d7</code></a></li> <li>[meta] fix readme capitalization <a href="https://github.com/form-data/form-data/commit/2300ca19595b0ee96431e868fe2a40db79e41c61"><code>2300ca1</code></a></li> </ul> <h2><a href="https://github.com/form-data/form-data/compare/v4.0.2...v4.0.3">v4.0.3</a> - 2025-06-05</h2> <h3>Fixed</h3> <ul> <li>[Fix] <code>append</code>: avoid a crash on nullish values <a href="https://redirect.github.com/form-data/form-data/issues/577"><code>[#577](https://github.com/form-data/form-data/issues/577)</code></a></li> </ul> <h3>Commits</h3> <ul> <li>[eslint] use a shared config <a href="https://github.com/form-data/form-data/commit/426ba9ac440f95d1998dac9a5cd8d738043b048f"><code>426ba9a</code></a></li> <li>[eslint] fix some spacing issues <a href="https://github.com/form-data/form-data/commit/20941917f0e9487e68c564ebc3157e23609e2939"><code>2094191</code></a></li> <li>[Refactor] use <code>hasown</code> <a href="https://github.com/form-data/form-data/commit/81ab41b46fdf34f5d89d7ff30b513b0925febfaa"><code>81ab41b</code></a></li> <li>[Fix] validate boundary type in <code>setBoundary()</code> method <a href="https://github.com/form-data/form-data/commit/8d8e4693093519f7f18e3c597d1e8df8c493de9e"><code>8d8e469</code></a></li> <li>[Tests] add tests to check the behavior of <code>getBoundary</code> with non-strings <a href="https://github.com/form-data/form-data/commit/837b8a1f7562bfb8bda74f3fc538adb7a5858995"><code>837b8a1</code></a></li> <li>[Dev Deps] remove unused deps <a href="https://github.com/form-data/form-data/commit/870e4e665935e701bf983a051244ab928e62d58e"><code>870e4e6</code></a></li> <li>[meta] remove local commit hooks <a href="https://github.com/form-data/form-data/commit/e6e83ccb545a5619ed6cd04f31d5c2f655eb633e"><code>e6e83cc</code></a></li> <li>[Dev Deps] update <code>eslint</code> <a href="https://github.com/form-data/form-data/commit/4066fd6f65992b62fa324a6474a9292a4f88c916"><code>4066fd6</code></a></li> <li>[meta] fix scripts to use prepublishOnly <a href="https://github.com/form-data/form-data/commit/c4bbb13c0ef669916657bc129341301b1d331d75"><code>c4bbb13</code></a></li> </ul> <h2><a href="https://github.com/form-data/form-data/compare/v4.0.1...v4.0.2">v4.0.2</a> - 2025-02-14</h2> <h3>Merged</h3> <ul> <li>[Fix] set <code>Symbol.toStringTag</code> when available <a href="https://redirect.github.com/form-data/form-data/pull/573"><code>[#573](https://github.com/form-data/form-data/issues/573)</code></a></li> <li>[Fix] set <code>Symbol.toStringTag</code> when available <a href="https://redirect.github.com/form-data/form-data/pull/573"><code>[#573](https://github.com/form-data/form-data/issues/573)</code></a></li> <li>fix (npmignore): ignore temporary build files <a href="https://redirect.github.com/form-data/form-data/pull/532"><code>[#532](https://github.com/form-data/form-data/issues/532)</code></a></li> <li>fix (npmignore): ignore temporary build files <a href="https://redirect.github.com/form-data/form-data/pull/532"><code>[#532](https://github.com/form-data/form-data/issues/532)</code></a></li> </ul> <h3>Fixed</h3> <ul> <li>[Fix] set <code>Symbol.toStringTag</code> when available (<a href="https://redirect.github.com/form-data/form-data/issues/573">#573</a>) <a href="https://redirect.github.com/form-data/form-data/issues/396"><code>[#396](https://github.com/form-data/form-data/issues/396)</code></a></li> <li>[Fix] set <code>Symbol.toStringTag</code> when available (<a href="https://redirect.github.com/form-data/form-data/issues/573">#573</a>) <a href="https://redirect.github.com/form-data/form-data/issues/396"><code>[#396](https://github.com/form-data/form-data/issues/396)</code></a></li> <li>[Fix] set <code>Symbol.toStringTag</code> when available <a href="https://redirect.github.com/form-data/form-data/issues/396"><code>[#396](https://github.com/form-data/form-data/issues/396)</code></a></li> </ul> <h3>Commits</h3> <ul> <li>Merge tags v2.5.3 and v3.0.3 <a href="https://github.com/form-data/form-data/commit/92613b9208556eb4ebc482fdf599fae111626fb6"><code>92613b9</code></a></li> <li>[Tests] migrate from travis to GHA <a href="https://github.com/form-data/form-data/commit/806eda77740e6e3c67c7815afb216f2e1f187ba5"><code>806eda7</code></a></li> <li>[Tests] migrate from travis to GHA <a href="https://github.com/form-data/form-data/commit/8fdb3bc6b5d001f8909a9fca391d1d1d97ef1d79"><code>8fdb3bc</code></a></li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/form-data/form-data/commit/41996f5ac73a867046d48512cab62e64fc846dad"><code>41996f5</code></a> v4.0.4</li> <li><a href="https://github.com/form-data/form-data/commit/316c82ba93fd4985af757b771b9a1f26d3b709ef"><code>316c82b</code></a> [meta] actually ensure the readme backup isn’t published</li> <li><a href="https://github.com/form-data/form-data/commit/2300ca19595b0ee96431e868fe2a40db79e41c61"><code>2300ca1</code></a> [meta] fix readme capitalization</li> <li><a href="https://github.com/form-data/form-data/commit/811f68282fab0315209d0e2d1c44b6c32ea0d479"><code>811f682</code></a> [meta] add <code>auto-changelog</code></li> <li><a href="https://github.com/form-data/form-data/commit/5e340800b5f8914213e4e0378c084aae71cfd73a"><code>5e34080</code></a> [Tests] fix linting errors</li> <li><a href="https://github.com/form-data/form-data/commit/1d11a76434d101f22fdb26b8aef8615f28b98402"><code>1d11a76</code></a> [Tests] handle predict-v8-randomness failures in node < 17 and node > 23</li> <li><a href="https://github.com/form-data/form-data/commit/58c25d76406a5b0dfdf54045cf252563f2bbda8d"><code>58c25d7</code></a> [Dev Deps] update <code>@ljharb/eslint-config</code></li> <li><a href="https://github.com/form-data/form-data/commit/3d1723080e6577a66f17f163ecd345a21d8d0fd0"><code>3d17230</code></a> [Fix] Switch to using <code>crypto</code> random for boundary values</li> <li><a href="https://github.com/form-data/form-data/commit/d8d67dc8ac79285154edf7d3f57dbab593b9a146"><code>d8d67dc</code></a> v4.0.3</li> <li><a href="https://github.com/form-data/form-data/commit/e6e83ccb545a5619ed6cd04f31d5c2f655eb633e"><code>e6e83cc</code></a> [meta] remove local commit hooks</li> <li>Additional commits viewable in <a href="https://github.com/form-data/form-data/compare/v4.0.1...v4.0.4">compare view</a></li> </ul> </details> <br /> [![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=form-data&package-manager=npm_and_yarn&previous-version=4.0.1&new-version=4.0.4)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) You can disable automated security fix PRs for this repo from the [Security Alerts page](https://github.com/langchain-ai/langgraph/network/alerts). </details> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2025-07-25 13:31:18 -04:00
Eugene YurtsevandGitHub	a3d7b6f44e	chore(checkpoint-sqlite): Release 2.0.11 (#5667 ) Release new version	2025-07-25 17:26:26 +00:00
				`@@ -0,0 +1 @@`
				`"""Legacy utilities module, to be removed in v1."""`