x

fix(docs): clarify value of context (#5689 )
Merge branch 'sr/more-context-for-context' of https://github.com/langchain-ai/langgraph into sr/more-context-for-context
2026-08-18 13:45:44 +02:00 · 2025-07-28 14:21:55 -07:00 · 2025-07-28 16:38:02 -04:00 · 2025-07-28 16:34:54 -04:00 · 2025-07-28 16:34:13 -04:00 · 2025-07-28 16:22:16 -04:00
22 changed files with 747 additions and 74 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 }}
@@ -310,6 +310,12 @@ def _highlight_code_blocks(markdown: str) -> str:
    return markdown


+TARGET_LANGUAGE = os.environ.get("TARGET_LANGUAGE", "python")
+
+if TARGET_LANGUAGE not in {"python", "js"}:
+    raise ValueError(f"TARGET_LANGUAGE must be 'python' or 'js', got {TARGET_LANGUAGE}")
+
+
 def _on_page_markdown_with_config(
    markdown: str,
    page: Page,
@@ -332,16 +338,15 @@ def _on_page_markdown_with_config(
    markdown = _highlight_code_blocks(markdown)

    # Apply conditional rendering for code blocks
-    target_language = kwargs.get("target_language", "python")
-    markdown = _apply_conditional_rendering(markdown, target_language)
-    if target_language == "js":
+    markdown = _apply_conditional_rendering(markdown, TARGET_LANGUAGE)
+    if TARGET_LANGUAGE == "js":
        markdown = _resolve_cross_references(markdown, JS_LINK_MAP)
-    elif target_language == "python":
+    elif TARGET_LANGUAGE == "python":
        # Via a dedicated plugin
        pass
    else:
        raise ValueError(
-            f"Unsupported target language: {target_language}. "
+            f"Unsupported target language: {TARGET_LANGUAGE}. "
            "Supported languages are 'python' and 'js'."
        )

@@ -8,7 +8,7 @@ Context includes *any* data outside the message list that can shape behavior. Th
 - Internal state updated during a multi-step reasoning process.
 - Persistent memory or facts from previous interactions.

-LangGraph provides **three** primary ways to supply context:
+LangGraph provides **three** primary ways to manage context:

 | Type                                                                         | Description                                   | Mutable? | Lifetime                |
 |------------------------------------------------------------------------------|-----------------------------------------------|----------|-------------------------|
@@ -18,14 +18,21 @@ LangGraph provides **three** primary ways to supply context:

 ### Runtime Context

-!!! note "`config['configurable']` -> `runtime.context`"
+Runtime context is for immutable data like user metadata, tools, db connections, etc. Use this when you have values that don't change mid-run.

-    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.
+!!! version-added "New in LangGraph v0.6: `Runtime.context` replaces `config['configurable']`"

-    As of LangGraph v1.0, the Runtime object is recommended to access static context and runtime-specific information like the store and stream writer.
+    The `Runtime` object is recommended to access static context and runtime-specific information like the store and stream writer.

-Runtime context is for immutable data like user metadata or API keys. Use this when you have values that don't change mid-run.
+!!! note 
+
+    Runtime context refers to local context: data and dependencies your code needs to run. It does not refer to:
+
+    * 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.
+
+    You likely want to use the local context to optimize the LLM's context window. For example, you
+    could use a user id to fetch a user's name and information from a database to populate the context window with relevant memories.

 Specify static context via the `context` argument to `invoke` / `stream`, which is reserved for this purpose:

@@ -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.

@@ -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" },
@@ -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"
@@ -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
Eugene YurtsevandHunter Lovell	d1d4abf70e	x	2025-07-28 14:21:55 -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."""`