release: langgraph v0.6.0a1, langgraph-prebuilt v0.6.0a1 (#5671 )

chore: add backwards compat utils imports to make v0.6 migration easier (#5670 )
alpha bumps
2026-08-27 01:52:25 +02:00 · 2025-07-25 15:53:08 -04:00 · 2025-07-25 15:44:02 -04:00 · 2025-07-25 15:41:51 -04:00 · 2025-07-25 15:37:41 -04:00 · 2025-07-25 15:36:56 -04:00
39 changed files with 1685 additions and 90 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 }}
@@ -4,6 +4,31 @@

 ---

+## v0.2.103 (2025-07-25)
+- Corrected the metadata endpoint to ensure accurate data retrieval.
+
+## v0.2.102 (2025-07-24)
+- Captured interrupt events in the wait method to preserve legacy behavior and stream updates by default.
+- Added support for SDK structlog in the JavaScript environment, enhancing logging capabilities.
+
+## v0.2.101 (2025-07-24)
+- Used the correct metadata endpoint for self-hosted environments, resolving an access issue.
+
+## v0.2.99 (2025-07-22)
+- Improved license validation by adding an in-memory cache and handling Redis connection errors more effectively.
+- Automatically remove agents from memory that are removed from `langgraph.json` to prevent persistence issues.
+- Ensured the UI namespace for generated UI is a valid JavaScript property name to prevent errors.
+- Raised a 422 error for improved request validation feedback.
+
+## v0.2.98 (2025-07-19)
+- Added langgraph node context for improved log filtering and trace visibility.
+
+## v0.2.97 (2025-07-19)
+- Fixed scheduling issue with ckpt ingestion worker that occurred on isolated background loops.
+- Ensured queue worker starts only after all migrations have completed.
+- Added more detailed error messages for thread state issues and improved response handling when state updates fail.
+- Exposed interrupt ID while retrieving thread state for enhanced API response details.
+
 ## v0.2.96 (2025-07-17)
 - Added a fallback mechanism for configurable header patterns to handle exclude/include settings more effectively.

@@ -23,7 +23,7 @@ To review, edit, and approve tool calls in an agent or workflow, [use LangGraph'

 ## Key capabilities

-* **Persistent execution state**: Interrupts use LangGraph's [persistence](../../concepts/persistence.md) layer, which saves the graph state, to indefinitely pause graph execution until you resume. This is possible because LangGraph checkpoints the graph state after each step, which allows the system to persist execution context and later resume the workflow, continuing from where it left off. This supports asynchronous human review or input without time constraints.
+* **Persistent execution state**: Interrupts use LangGraph's [persistence](./persistence.md) layer, which saves the graph state, to indefinitely pause graph execution until you resume. This is possible because LangGraph checkpoints the graph state after each step, which allows the system to persist execution context and later resume the workflow, continuing from where it left off. This supports asynchronous human review or input without time constraints.

    There are two ways to pause a graph:

@@ -119,6 +119,11 @@ These metrics are displayed as charts in the Control Plane UI.

 ### LangSmith Integration

-A [LangSmith](https://docs.smith.langchain.com/) tracing project is automatically created for each deployment. The tracing project has the same name as the deployment. When creating a deployment, the `LANGCHAIN_TRACING` and `LANGSMITH_API_KEY`/`LANGCHAIN_API_KEY` environment variables do not need to be specified; they are set automatically by the control plane.
+A [LangSmith](https://docs.smith.langchain.com/) tracing project and LangSmith API key are automatically created for each deployment. The deployment uses the API key to automatically send traces to LangSmith.

-When a deployment is deleted, the traces and the tracing project are not deleted.
+- The tracing project has the same name as the deployment.
+- The API key has the description `LangGraph Platform: <deployment_name>`.
+- The API key is never revealed and cannot be deleted manually.
+- When creating a deployment, the `LANGCHAIN_TRACING` and `LANGSMITH_API_KEY`/`LANGCHAIN_API_KEY` environment variables do not need to be specified; they are set automatically by the control plane.
+
+When a deployment is deleted, the traces and the tracing project are not deleted. However, the API will be deleted when the deployment is deleted.
@@ -0,0 +1,18 @@
+# Runtime
+
+::: langgraph.runtime.Runtime
+    options:
+      show_root_heading: true
+      show_root_full_path: false
+      members:
+        - context
+        - store
+        - stream_writer
+        - previous
+
+::: langgraph.runtime
+    options:
+      members:
+        - get_runtime
+
+
@@ -250,6 +250,7 @@ nav:
      - Storage: reference/store.md
      - Caching: reference/cache.md
      - Types: reference/types.md
+      - Runtime: reference/runtime.md
      - Config: reference/config.md
      - Errors: reference/errors.md
      - Constants: reference/constants.md
@@ -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"
@@ -3,6 +3,7 @@ from __future__ import annotations
 import concurrent.futures
 import datetime
 import logging
+import re
 import sqlite3
 import threading
 from collections import defaultdict
@@ -107,6 +108,23 @@ def _decode_ns_text(namespace: str) -> tuple[str, ...]:
    return tuple(namespace.split("."))


+def _validate_filter_key(key: str) -> None:
+    """Validate that a filter key is safe for use in SQL queries.
+
+    Args:
+        key: The filter key to validate
+
+    Raises:
+        ValueError: If the key contains invalid characters that could enable SQL injection
+    """
+    # Allow alphanumeric characters, underscores, dots, and hyphens
+    # This covers typical JSON property names while preventing SQL injection
+    if not re.match(r"^[a-zA-Z0-9_.-]+$", key):
+        raise ValueError(
+            f"Invalid filter key: '{key}'. Filter keys must contain only alphanumeric characters, underscores, dots, and hyphens."
+        )
+
+
 def _json_loads(content: bytes | str | orjson.Fragment) -> Any:
    if isinstance(content, orjson.Fragment):
        if hasattr(content, "buf"):
@@ -372,6 +390,8 @@ class BaseSqliteStore:
            filter_conditions = []
            if op.filter:
                for key, value in op.filter.items():
+                    _validate_filter_key(key)
+
                    if isinstance(value, dict):
                        for op_name, val in value.items():
                            condition, filter_params_ = self._get_filter_condition(
@@ -622,6 +642,8 @@ class BaseSqliteStore:

    def _get_filter_condition(self, key: str, op: str, value: Any) -> tuple[str, list]:
        """Helper to generate filter conditions."""
+        _validate_filter_key(key)
+
        # We need to properly format values for SQLite JSON extraction comparison
        if op == "$eq":
            if isinstance(value, str):
@@ -858,6 +880,8 @@ class SqliteStore(BaseSqliteStore, BaseStore):

    def _get_filter_condition(self, key: str, op: str, value: Any) -> tuple[str, list]:
        """Helper to generate filter conditions."""
+        _validate_filter_key(key)
+
        # We need to properly format values for SQLite JSON extraction comparison
        if op == "$eq":
            if isinstance(value, str):
@@ -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"
@@ -1047,3 +1047,23 @@ def test_search_items(
        for ns in test_namespaces:
            key = f"item_{ns[-1]}"
            store.delete(ns, key)
+
+
+def test_sql_injection_vulnerability(store: SqliteStore) -> None:
+    """Test that SQL injection via malicious filter keys is prevented."""
+    # Add public and private documents
+    store.put(("docs",), "public", {"access": "public", "data": "public info"})
+    store.put(
+        ("docs",), "private", {"access": "private", "data": "secret", "password": "123"}
+    )
+
+    # Normal query - returns 1 public document
+    normal = store.search(("docs",), filter={"access": "public"})
+    assert len(normal) == 1
+    assert normal[0].value["access"] == "public"
+
+    # SQL injection attempt via malicious key should raise ValueError
+    malicious_key = "access') = 'public' OR '1'='1' OR json_extract(value, '$."
+
+    with pytest.raises(ValueError, match="Invalid filter key"):
+        store.search(("docs",), filter={malicious_key: "dummy"})
@@ -346,7 +346,7 @@ dev = [

 [[package]]
 name = "langgraph-checkpoint-sqlite"
-version = "2.0.10"
+version = "2.0.11"
 source = { editable = "." }
 dependencies = [
    { name = "aiosqlite" },
@@ -153,6 +153,12 @@ OPT_POSTGRES_URI = click.option(
    help="Postgres URI to use for the database. Defaults to launching a local database",
 )

+OPT_API_VERSION = click.option(
+    "--api-version",
+    type=str,
+    help="API server version to use for the base image. If unspecified, the latest version will be used.",
+)
+

@click.group()
@click.version_option(version=__version__, prog_name="LangGraph CLI")
@@ -170,6 +176,7 @@ def cli():
@OPT_DEBUGGER_BASE_URL
@OPT_WATCH
@OPT_POSTGRES_URI
+@OPT_API_VERSION
@click.option(
    "--image",
    type=str,
@@ -203,6 +210,7 @@ def up(
    debugger_port: Optional[int],
    debugger_base_url: Optional[str],
    postgres_uri: Optional[str],
+    api_version: Optional[str],
    image: Optional[str],
    base_image: Optional[str],
 ):
@@ -225,6 +233,7 @@ For production use, requires a license key in env var LANGGRAPH_CLOUD_LICENSE_KE
            debugger_port=debugger_port,
            debugger_base_url=debugger_base_url,
            postgres_uri=postgres_uri,
+            api_version=api_version,
            image=image,
            base_image=base_image,
        )
@@ -290,6 +299,7 @@ def _build(
    config: pathlib.Path,
    config_json: dict,
    base_image: Optional[str],
+    api_version: Optional[str],
    pull: bool,
    tag: str,
    passthrough: Sequence[str] = (),
@@ -300,7 +310,7 @@ def _build(
            subp_exec(
                "docker",
                "pull",
-                langgraph_cli.config.docker_tag(config_json, base_image),
+                langgraph_cli.config.docker_tag(config_json, base_image, api_version),
                verbose=True,
            )
        )
@@ -314,7 +324,7 @@ def _build(
    ]
    # apply config
    stdin, additional_contexts = langgraph_cli.config.config_to_docker(
-        config, config_json, base_image
+        config, config_json, base_image, api_version
    )
    # add additional_contexts
    if additional_contexts:
@@ -355,6 +365,7 @@ def _build(
    "\n\n    \b\nExamples:\n    --base-image langchain/langgraph-server:0.2.18  # Pin to a specific patch version"
    "\n    --base-image langchain/langgraph-server:0.2  # Pin to a minor version (Python)",
 )
+@OPT_API_VERSION
@click.argument("docker_build_args", nargs=-1, type=click.UNPROCESSED)
@cli.command(
    help="📦 Build LangGraph API server Docker image.",
@@ -367,6 +378,7 @@ def build(
    config: pathlib.Path,
    docker_build_args: Sequence[str],
    base_image: Optional[str],
+    api_version: Optional[str],
    pull: bool,
    tag: str,
 ):
@@ -376,7 +388,15 @@ def build(
        config_json = langgraph_cli.config.validate_config_file(config)
        warn_non_wolfi_distro(config_json)
        _build(
-            runner, set, config, config_json, base_image, pull, tag, docker_build_args
+            runner,
+            set,
+            config,
+            config_json,
+            base_image,
+            api_version,
+            pull,
+            tag,
+            docker_build_args,
        )


@@ -456,12 +476,14 @@ tests
    "\n\n    \b\nExamples:\n    --base-image langchain/langgraph-server:0.2.18  # Pin to a specific patch version"
    "\n    --base-image langchain/langgraph-server:0.2  # Pin to a minor version (Python)",
 )
+@OPT_API_VERSION
@log_command
 def dockerfile(
    save_path: str,
    config: pathlib.Path,
    add_docker_compose: bool,
    base_image: Optional[str] = None,
+    api_version: Optional[str] = None,
 ) -> None:
    save_path = pathlib.Path(save_path).absolute()
    secho(f"🔍 Validating configuration at path: {config}", fg="yellow")
@@ -474,6 +496,7 @@ def dockerfile(
        config,
        config_json,
        base_image=base_image,
+        api_version=api_version,
    )
    with open(str(save_path), "w", encoding="utf-8") as f:
        f.write(dockerfile)
@@ -739,6 +762,7 @@ def prepare_args_and_stdin(
    debugger_port: Optional[int] = None,
    debugger_base_url: Optional[str] = None,
    postgres_uri: Optional[str] = None,
+    api_version: Optional[str] = None,
    # Like "my-tag" (if you already built it locally)
    image: Optional[str] = None,
    # Like "langchain/langgraphjs-api" or "langchain/langgraph-api
@@ -754,6 +778,7 @@ def prepare_args_and_stdin(
        postgres_uri=postgres_uri,
        image=image,  # Pass image to compose YAML generator
        base_image=base_image,
+        api_version=api_version,
    )
    args = [
        "--project-directory",
@@ -769,6 +794,7 @@ def prepare_args_and_stdin(
        config,
        watch=watch,
        base_image=langgraph_cli.config.default_base_image(config),
+        api_version=api_version,
        image=image,
    )
    return args, stdin
@@ -787,6 +813,7 @@ def prepare(
    debugger_port: Optional[int] = None,
    debugger_base_url: Optional[str] = None,
    postgres_uri: Optional[str] = None,
+    api_version: Optional[str] = None,
    image: Optional[str] = None,
    base_image: Optional[str] = None,
 ) -> tuple[list[str], str]:
@@ -799,7 +826,7 @@ def prepare(
            subp_exec(
                "docker",
                "pull",
-                langgraph_cli.config.docker_tag(config_json, base_image),
+                langgraph_cli.config.docker_tag(config_json, base_image, api_version),
                verbose=verbose,
            )
        )
@@ -814,6 +841,7 @@ def prepare(
        debugger_port=debugger_port,
        debugger_base_url=debugger_base_url or f"http://127.0.0.1:{port}",
        postgres_uri=postgres_uri,
+        api_version=api_version,
        image=image,
        base_image=base_image,
    )
@@ -1213,6 +1213,7 @@ def python_config_to_docker(
    config_path: pathlib.Path,
    config: Config,
    base_image: str,
+    api_version: Optional[str] = None,
 ) -> tuple[str, dict[str, str]]:
    """Generate a Dockerfile from the configuration."""
    pip_installer = config.get("pip_installer", "auto")
@@ -1360,7 +1361,7 @@ ADD {relpath} /deps/{name}
                "# -- End of JS dependencies install --",
            ]
        )
-    image_str = docker_tag(config, base_image)
+    image_str = docker_tag(config, base_image, api_version)
    docker_file_contents = [
        f"FROM {image_str}",
        "",
@@ -1402,10 +1403,11 @@ def node_config_to_docker(
    config_path: pathlib.Path,
    config: Config,
    base_image: str,
+    api_version: Optional[str] = None,
 ) -> tuple[str, dict[str, str]]:
    faux_path = f"/deps/{config_path.parent.name}"
    install_cmd = _get_node_pm_install_cmd(config_path, config)
-    image_str = docker_tag(config, base_image)
+    image_str = docker_tag(config, base_image, api_version)

    env_vars: list[str] = []

@@ -1461,6 +1463,7 @@ def default_base_image(config: Config) -> str:
 def docker_tag(
    config: Config,
    base_image: Optional[str] = None,
+    api_version: Optional[str] = None,
 ) -> str:
    base_image = base_image or default_base_image(config)

@@ -1473,28 +1476,43 @@ def docker_tag(
    if "/langgraph-server" in base_image:
        return f"{base_image}-py{config['python_version']}"

+    # Build the standard tag format
+    language, version = None, None
    if config.get("node_version") and not config.get("python_version"):
-        return f"{base_image}:{config['node_version']}{distro_tag}"
-    return f"{base_image}:{config['python_version']}{distro_tag}"
+        language, version = "node", config["node_version"]
+    else:
+        language, version = "py", config["python_version"]
+
+    version_distro_tag = f"{version}{distro_tag}"
+
+    # Prepend API version if provided
+    if api_version:
+        full_tag = f"{api_version}-{language}{version_distro_tag}"
+    else:
+        full_tag = version_distro_tag
+
+    return f"{base_image}:{full_tag}"


 def config_to_docker(
    config_path: pathlib.Path,
    config: Config,
    base_image: Optional[str] = None,
+    api_version: Optional[str] = None,
 ) -> tuple[str, dict[str, str]]:
    base_image = base_image or default_base_image(config)

    if config.get("node_version") and not config.get("python_version"):
-        return node_config_to_docker(config_path, config, base_image)
+        return node_config_to_docker(config_path, config, base_image, api_version)

-    return python_config_to_docker(config_path, config, base_image)
+    return python_config_to_docker(config_path, config, base_image, api_version)


 def config_to_compose(
    config_path: pathlib.Path,
    config: Config,
    base_image: Optional[str] = None,
+    api_version: Optional[str] = None,
    image: Optional[str] = None,
    watch: bool = False,
 ) -> str:
@@ -1531,7 +1549,7 @@ def config_to_compose(

    else:
        dockerfile, additional_contexts = config_to_docker(
-            config_path, config, base_image
+            config_path, config, base_image, api_version
        )

        additional_contexts_str = "\n".join(
@@ -147,6 +147,8 @@ def compose_as_dict(
    image: Optional[str] = None,
    # Base image to use for the LangGraph API server
    base_image: Optional[str] = None,
+    # API version of the base image
+    api_version: Optional[str] = None,
 ) -> dict:
    """Create a docker compose file as a dictionary in YML style."""
    if postgres_uri is None:
@@ -252,6 +254,7 @@ def compose(
    postgres_uri: Optional[str] = None,
    image: Optional[str] = None,
    base_image: Optional[str] = None,
+    api_version: Optional[str] = None,
 ) -> str:
    """Create a docker compose file as a string."""
    compose_content = compose_as_dict(
@@ -262,6 +265,7 @@ def compose(
        postgres_uri=postgres_uri,
        image=image,
        base_image=base_image,
+        api_version=api_version,
    )
    compose_str = dict_to_yaml(compose_content)
    return compose_str
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"

 [project]
 name = "langgraph-cli"
-version = "0.3.5"
+version = "0.3.6"
 description = "CLI for interacting with LangGraph API"
 authors = []
 requires-python = ">=3.9"
@@ -574,3 +574,248 @@ def test_build_generate_proper_build_context():
        assert len(build_contexts) == 2, (
            f"Expected 2 build contexts, but found {len(build_contexts)}"
        )
+
+
+def test_dockerfile_command_with_api_version() -> None:
+    """Test the 'dockerfile' command with --api-version flag."""
+    runner = CliRunner()
+    config_content = {
+        "python_version": "3.11",
+        "graphs": {"agent": "agent.py:graph"},
+        "dependencies": ["."],
+    }
+
+    with temporary_config_folder(config_content) as temp_dir:
+        save_path = temp_dir / "Dockerfile"
+        agent_path = temp_dir / "agent.py"
+        agent_path.touch()
+
+        result = runner.invoke(
+            cli,
+            [
+                "dockerfile",
+                str(save_path),
+                "--config",
+                str(temp_dir / "config.json"),
+                "--api-version",
+                "0.2.74",
+            ],
+        )
+
+        # Assert command was successful
+        assert result.exit_code == 0, result.output
+        assert "✅ Created: Dockerfile" in result.output
+
+        # Check if Dockerfile was created and contains correct FROM line
+        assert save_path.exists()
+        with open(save_path) as f:
+            dockerfile = f.read()
+            assert "FROM langchain/langgraph-api:0.2.74-py3.11" in dockerfile
+
+
+def test_dockerfile_command_with_api_version_and_base_image() -> None:
+    """Test the 'dockerfile' command with both --api-version and --base-image flags."""
+    runner = CliRunner()
+    config_content = {
+        "python_version": "3.12",
+        "graphs": {"agent": "agent.py:graph"},
+        "dependencies": ["."],
+        "image_distro": "wolfi",
+    }
+
+    with temporary_config_folder(config_content) as temp_dir:
+        save_path = temp_dir / "Dockerfile"
+        agent_path = temp_dir / "agent.py"
+        agent_path.touch()
+
+        result = runner.invoke(
+            cli,
+            [
+                "dockerfile",
+                str(save_path),
+                "--config",
+                str(temp_dir / "config.json"),
+                "--api-version",
+                "1.0.0",
+                "--base-image",
+                "my-registry/custom-api",
+            ],
+        )
+
+        # Assert command was successful
+        assert result.exit_code == 0, result.output
+        assert "✅ Created: Dockerfile" in result.output
+
+        # Check if Dockerfile was created and contains correct FROM line
+        assert save_path.exists()
+        with open(save_path) as f:
+            dockerfile = f.read()
+            assert "FROM my-registry/custom-api:1.0.0-py3.12-wolfi" in dockerfile
+
+
+def test_dockerfile_command_with_api_version_nodejs() -> None:
+    """Test the 'dockerfile' command with --api-version flag for Node.js config."""
+    runner = CliRunner()
+    config_content = {
+        "node_version": "20",
+        "graphs": {"agent": "agent.js:graph"},
+    }
+
+    with temporary_config_folder(config_content) as temp_dir:
+        save_path = temp_dir / "Dockerfile"
+        agent_path = temp_dir / "agent.js"
+        agent_path.touch()
+
+        result = runner.invoke(
+            cli,
+            [
+                "dockerfile",
+                str(save_path),
+                "--config",
+                str(temp_dir / "config.json"),
+                "--api-version",
+                "0.2.74",
+            ],
+        )
+
+        # Assert command was successful
+        assert result.exit_code == 0, result.output
+        assert "✅ Created: Dockerfile" in result.output
+
+        # Check if Dockerfile was created and contains correct FROM line
+        assert save_path.exists()
+        with open(save_path) as f:
+            dockerfile = f.read()
+            assert "FROM langchain/langgraphjs-api:0.2.74-node20" in dockerfile
+
+
+def test_build_command_with_api_version() -> None:
+    """Test the 'build' command with --api-version flag."""
+    runner = CliRunner()
+    config_content = {
+        "python_version": "3.11",
+        "graphs": {"agent": "agent.py:graph"},
+        "dependencies": ["."],
+        "image_distro": "wolfi",  # Use wolfi to avoid warning messages
+    }
+
+    with temporary_config_folder(config_content) as temp_dir:
+        agent_path = temp_dir / "agent.py"
+        agent_path.touch()
+
+        # Mock docker command since we don't want to actually build
+        with runner.isolated_filesystem():
+            result = runner.invoke(
+                cli,
+                [
+                    "build",
+                    "--tag",
+                    "test-image",
+                    "--config",
+                    str(temp_dir / "config.json"),
+                    "--api-version",
+                    "0.2.74",
+                    "--no-pull",  # Avoid pulling non-existent images
+                ],
+                catch_exceptions=True,
+            )
+
+        # Check that the build command is called with the correct tag
+        # The output should contain the docker build command with the api_version tag
+        assert "langchain/langgraph-api:0.2.74-py3.11-wolfi" in result.output
+
+
+def test_build_command_with_api_version_and_base_image() -> None:
+    """Test the 'build' command with both --api-version and --base-image flags."""
+    runner = CliRunner()
+    config_content = {
+        "python_version": "3.12",
+        "graphs": {"agent": "agent.py:graph"},
+        "dependencies": ["."],
+        "image_distro": "wolfi",  # Use wolfi to avoid warning messages
+    }
+
+    with temporary_config_folder(config_content) as temp_dir:
+        agent_path = temp_dir / "agent.py"
+        agent_path.touch()
+
+        # Mock docker command since we don't want to actually build
+        with runner.isolated_filesystem():
+            result = runner.invoke(
+                cli,
+                [
+                    "build",
+                    "--tag",
+                    "test-image",
+                    "--config",
+                    str(temp_dir / "config.json"),
+                    "--api-version",
+                    "1.0.0",
+                    "--base-image",
+                    "my-registry/custom-api",
+                    "--no-pull",  # Avoid pulling non-existent images
+                ],
+                catch_exceptions=True,
+            )
+
+        # Check that the build command includes the api_version
+        assert "my-registry/custom-api:1.0.0-py3.12-wolfi" in result.output
+
+
+def test_prepare_args_and_stdin_with_api_version() -> None:
+    """Test prepare_args_and_stdin function with api_version parameter."""
+    config_path = pathlib.Path(__file__).parent / "langgraph.json"
+    config = validate_config(
+        Config(dependencies=["."], graphs={"agent": "agent.py:graph"})
+    )
+    port = 8000
+    api_version = "0.2.74"
+
+    actual_args, actual_stdin = prepare_args_and_stdin(
+        capabilities=DEFAULT_DOCKER_CAPABILITIES,
+        config_path=config_path,
+        config=config,
+        docker_compose=None,
+        port=port,
+        watch=False,
+        api_version=api_version,
+    )
+
+    expected_args = [
+        "--project-directory",
+        str(pathlib.Path(__file__).parent.absolute()),
+        "-f",
+        "-",
+    ]
+
+    # Check that the args are correct
+    assert actual_args == expected_args
+
+    # Check that the stdin contains the correct FROM line with api_version
+    assert "FROM langchain/langgraph-api:0.2.74-py3.11" in actual_stdin
+
+
+def test_prepare_args_and_stdin_with_api_version_and_image() -> None:
+    """Test prepare_args_and_stdin function with both api_version and image parameters."""
+    config_path = pathlib.Path(__file__).parent / "langgraph.json"
+    config = validate_config(
+        Config(dependencies=["."], graphs={"agent": "agent.py:graph"})
+    )
+    port = 8000
+    api_version = "0.2.74"
+    image = "my-custom-image:latest"
+
+    actual_args, actual_stdin = prepare_args_and_stdin(
+        capabilities=DEFAULT_DOCKER_CAPABILITIES,
+        config_path=config_path,
+        config=config,
+        docker_compose=None,
+        port=port,
+        watch=False,
+        api_version=api_version,
+        image=image,
+    )
+
+    # When image is provided, api_version should be ignored for the image
+    # but the stdin should not contain a build section (since image is provided)
+    assert "pull_policy: build" not in actual_stdin
@@ -1337,3 +1337,195 @@ def test_docker_tag_different_node_versions_with_distro():
        )
        tag = docker_tag(config)
        assert tag == expected_tag, f"Failed for Node.js {node_version}"
+
+
+def test_docker_tag_with_api_version():
+    """Test docker_tag function with api_version parameter."""
+
+    # Test 1: Python config with api_version and default distro
+    config = validate_config(
+        {
+            "python_version": "3.11",
+            "dependencies": ["."],
+            "graphs": {"agent": "./agent.py:graph"},
+        }
+    )
+    tag = docker_tag(config, api_version="0.2.74")
+    assert tag == "langchain/langgraph-api:0.2.74-py3.11"
+
+    # Test 2: Python config with api_version and wolfi distro
+    config = validate_config(
+        {
+            "python_version": "3.12",
+            "dependencies": ["."],
+            "graphs": {"agent": "./agent.py:graph"},
+            "image_distro": "wolfi",
+        }
+    )
+    tag = docker_tag(config, api_version="0.2.74")
+    assert tag == "langchain/langgraph-api:0.2.74-py3.12-wolfi"
+
+    # Test 3: Node.js config with api_version and default distro
+    config = validate_config(
+        {
+            "node_version": "20",
+            "graphs": {"agent": "./agent.js:graph"},
+        }
+    )
+    tag = docker_tag(config, api_version="0.2.74")
+    assert tag == "langchain/langgraphjs-api:0.2.74-node20"
+
+    # Test 4: Node.js config with api_version and wolfi distro
+    config = validate_config(
+        {
+            "node_version": "20",
+            "graphs": {"agent": "./agent.js:graph"},
+            "image_distro": "wolfi",
+        }
+    )
+    tag = docker_tag(config, api_version="0.2.74")
+    assert tag == "langchain/langgraphjs-api:0.2.74-node20-wolfi"
+
+    # Test 5: Custom base image with api_version
+    config = validate_config(
+        {
+            "python_version": "3.11",
+            "dependencies": ["."],
+            "graphs": {"agent": "./agent.py:graph"},
+            "base_image": "my-registry/custom-image",
+        }
+    )
+    tag = docker_tag(config, base_image="my-registry/custom-image", api_version="1.0.0")
+    assert tag == "my-registry/custom-image:1.0.0-py3.11"
+
+    # Test 6: api_version with different Python versions
+    for python_version in ["3.11", "3.12", "3.13"]:
+        config = validate_config(
+            {
+                "python_version": python_version,
+                "dependencies": ["."],
+                "graphs": {"agent": "./agent.py:graph"},
+            }
+        )
+        tag = docker_tag(config, api_version="0.2.74")
+        assert tag == f"langchain/langgraph-api:0.2.74-py{python_version}"
+
+    # Test 7: Without api_version should work as before
+    config = validate_config(
+        {
+            "python_version": "3.11",
+            "dependencies": ["."],
+            "graphs": {"agent": "./agent.py:graph"},
+        }
+    )
+    tag = docker_tag(config)
+    assert tag == "langchain/langgraph-api:3.11"
+
+    # Test 8: api_version with multiplatform config (should default to Python)
+    config = validate_config(
+        {
+            "python_version": "3.11",
+            "node_version": "20",
+            "dependencies": ["."],
+            "graphs": {"python": "./agent.py:graph", "js": "./agent.js:graph"},
+        }
+    )
+    tag = docker_tag(config, api_version="0.2.74")
+    assert tag == "langchain/langgraph-api:0.2.74-py3.11"
+
+    # Test 9: api_version with _INTERNAL_docker_tag should ignore api_version
+    config = validate_config(
+        {
+            "python_version": "3.11",
+            "dependencies": ["."],
+            "graphs": {"agent": "./agent.py:graph"},
+            "_INTERNAL_docker_tag": "internal-tag",
+        }
+    )
+    tag = docker_tag(config, api_version="0.2.74")
+    assert tag == "langchain/langgraph-api:internal-tag"
+
+    # Test 10: api_version with langgraph-server base image should follow special format
+    config = validate_config(
+        {
+            "python_version": "3.11",
+            "dependencies": ["."],
+            "graphs": {"agent": "./agent.py:graph"},
+        }
+    )
+    tag = docker_tag(
+        config, base_image="langchain/langgraph-server:0.2", api_version="0.2.74"
+    )
+    assert tag == "langchain/langgraph-server:0.2-py3.11"
+
+
+def test_config_to_docker_with_api_version():
+    """Test config_to_docker function with api_version parameter."""
+
+    # Test Python config with api_version
+    graphs = {"agent": "./agent.py:graph"}
+    actual_docker_stdin, additional_contexts = config_to_docker(
+        PATH_TO_CONFIG,
+        validate_config({"dependencies": ["."], "graphs": graphs}),
+        "langchain/langgraph-api",
+        api_version="0.2.74",
+    )
+
+    # Check that the FROM line uses the api_version
+    lines = actual_docker_stdin.split("\n")
+    from_line = lines[0]
+    assert from_line == "FROM langchain/langgraph-api:0.2.74-py3.11"
+
+    # Test Node.js config with api_version
+    graphs = {"agent": "./agent.js:graph"}
+    actual_docker_stdin, additional_contexts = config_to_docker(
+        PATH_TO_CONFIG,
+        validate_config({"node_version": "20", "graphs": graphs}),
+        "langchain/langgraphjs-api",
+        api_version="0.2.74",
+    )
+
+    # Check that the FROM line uses the api_version
+    lines = actual_docker_stdin.split("\n")
+    from_line = lines[0]
+    assert from_line == "FROM langchain/langgraphjs-api:0.2.74-node20"
+
+
+def test_config_to_compose_with_api_version():
+    """Test config_to_compose function with api_version parameter."""
+
+    # Test Python config with api_version
+    config = validate_config(
+        {
+            "dependencies": ["."],
+            "graphs": {"agent": "./agent.py:graph"},
+        }
+    )
+
+    actual_compose_str = config_to_compose(
+        PATH_TO_CONFIG,
+        config,
+        "langchain/langgraph-api",
+        api_version="0.2.74",
+    )
+
+    # Check that the compose file includes the correct FROM line with api_version
+    assert "FROM langchain/langgraph-api:0.2.74-py3.11" in actual_compose_str
+
+    # Test Node.js config with api_version
+    config = validate_config(
+        {
+            "node_version": "20",
+            "graphs": {"agent": "./agent.js:graph"},
+        }
+    )
+
+    actual_compose_str = config_to_compose(
+        PATH_TO_CONFIG,
+        config,
+        "langchain/langgraphjs-api",
+        api_version="0.2.74",
+    )
+
+    # Check that the compose file includes the correct FROM line with api_version
+    assert "FROM langchain/langgraphjs-api:0.2.74-node20" in actual_compose_str
@@ -146,3 +146,220 @@ services:
            REDIS_URI: redis://langgraph-redis:6379
            POSTGRES_URI: {DEFAULT_POSTGRES_URI}"""
    assert clean_empty_lines(actual_compose_str) == expected_compose_str
+
+
+def test_compose_with_api_version():
+    """Test compose function with api_version parameter."""
+    port = 8123
+    api_version = "0.2.74"
+
+    actual_compose_str = compose(
+        DEFAULT_DOCKER_CAPABILITIES, port=port, api_version=api_version
+    )
+
+    # The compose function should generate a compose file that doesn't directly
+    # reference the api_version, since it's handled in the docker tag creation
+    # when building the image. The compose function mainly sets up services.
+    expected_compose_str = f"""volumes:
+    langgraph-data:
+        driver: local
+services:
+    langgraph-redis:
+        image: redis:6
+        healthcheck:
+            test: redis-cli ping
+            interval: 5s
+            timeout: 1s
+            retries: 5
+    langgraph-postgres:
+        image: pgvector/pgvector:pg16
+        ports:
+            - "5433:5432"
+        environment:
+            POSTGRES_DB: postgres
+            POSTGRES_USER: postgres
+            POSTGRES_PASSWORD: postgres
+        command:
+            - postgres
+            - -c
+            - shared_preload_libraries=vector
+        volumes:
+            - langgraph-data:/var/lib/postgresql/data
+        healthcheck:
+            test: pg_isready -U postgres
+            start_period: 10s
+            timeout: 1s
+            retries: 5
+            interval: 5s
+    langgraph-api:
+        ports:
+            - "{port}:8000"
+        depends_on:
+            langgraph-redis:
+                condition: service_healthy
+            langgraph-postgres:
+                condition: service_healthy
+        environment:
+            REDIS_URI: redis://langgraph-redis:6379
+            POSTGRES_URI: {DEFAULT_POSTGRES_URI}"""
+    assert clean_empty_lines(actual_compose_str) == expected_compose_str
+
+
+def test_compose_with_api_version_and_base_image():
+    """Test compose function with both api_version and base_image parameters."""
+    port = 8123
+    api_version = "1.0.0"
+    base_image = "my-registry/custom-api"
+
+    actual_compose_str = compose(
+        DEFAULT_DOCKER_CAPABILITIES,
+        port=port,
+        api_version=api_version,
+        base_image=base_image,
+    )
+
+    # Similar to the previous test - the compose function doesn't directly embed
+    # the api_version or base_image into the compose file since those are handled
+    # during the docker build process
+    expected_compose_str = f"""volumes:
+    langgraph-data:
+        driver: local
+services:
+    langgraph-redis:
+        image: redis:6
+        healthcheck:
+            test: redis-cli ping
+            interval: 5s
+            timeout: 1s
+            retries: 5
+    langgraph-postgres:
+        image: pgvector/pgvector:pg16
+        ports:
+            - "5433:5432"
+        environment:
+            POSTGRES_DB: postgres
+            POSTGRES_USER: postgres
+            POSTGRES_PASSWORD: postgres
+        command:
+            - postgres
+            - -c
+            - shared_preload_libraries=vector
+        volumes:
+            - langgraph-data:/var/lib/postgresql/data
+        healthcheck:
+            test: pg_isready -U postgres
+            start_period: 10s
+            timeout: 1s
+            retries: 5
+            interval: 5s
+    langgraph-api:
+        ports:
+            - "{port}:8000"
+        depends_on:
+            langgraph-redis:
+                condition: service_healthy
+            langgraph-postgres:
+                condition: service_healthy
+        environment:
+            REDIS_URI: redis://langgraph-redis:6379
+            POSTGRES_URI: {DEFAULT_POSTGRES_URI}"""
+    assert clean_empty_lines(actual_compose_str) == expected_compose_str
+
+
+def test_compose_with_api_version_and_custom_postgres():
+    """Test compose function with api_version and custom postgres URI."""
+    port = 8123
+    api_version = "0.2.74"
+    custom_postgres_uri = "postgresql://user:pass@external-db:5432/mydb"
+
+    actual_compose_str = compose(
+        DEFAULT_DOCKER_CAPABILITIES,
+        port=port,
+        api_version=api_version,
+        postgres_uri=custom_postgres_uri,
+    )
+
+    expected_compose_str = f"""services:
+    langgraph-redis:
+        image: redis:6
+        healthcheck:
+            test: redis-cli ping
+            interval: 5s
+            timeout: 1s
+            retries: 5
+    langgraph-api:
+        ports:
+            - "{port}:8000"
+        depends_on:
+            langgraph-redis:
+                condition: service_healthy
+        environment:
+            REDIS_URI: redis://langgraph-redis:6379
+            POSTGRES_URI: {custom_postgres_uri}"""
+    assert clean_empty_lines(actual_compose_str) == expected_compose_str
+
+
+def test_compose_with_api_version_and_debugger():
+    """Test compose function with api_version and debugger port."""
+    port = 8123
+    debugger_port = 8001
+    api_version = "0.2.74"
+
+    actual_compose_str = compose(
+        DEFAULT_DOCKER_CAPABILITIES,
+        port=port,
+        api_version=api_version,
+        debugger_port=debugger_port,
+    )
+
+    expected_compose_str = f"""volumes:
+    langgraph-data:
+        driver: local
+services:
+    langgraph-redis:
+        image: redis:6
+        healthcheck:
+            test: redis-cli ping
+            interval: 5s
+            timeout: 1s
+            retries: 5
+    langgraph-postgres:
+        image: pgvector/pgvector:pg16
+        ports:
+            - "5433:5432"
+        environment:
+            POSTGRES_DB: postgres
+            POSTGRES_USER: postgres
+            POSTGRES_PASSWORD: postgres
+        command:
+            - postgres
+            - -c
+            - shared_preload_libraries=vector
+        volumes:
+            - langgraph-data:/var/lib/postgresql/data
+        healthcheck:
+            test: pg_isready -U postgres
+            start_period: 10s
+            timeout: 1s
+            retries: 5
+            interval: 5s
+    langgraph-debugger:
+        image: langchain/langgraph-debugger
+        restart: on-failure
+        depends_on:
+            langgraph-postgres:
+                condition: service_healthy
+        ports:
+            - "{debugger_port}:3968"
+    langgraph-api:
+        ports:
+            - "{port}:8000"
+        depends_on:
+            langgraph-redis:
+                condition: service_healthy
+            langgraph-postgres:
+                condition: service_healthy
+        environment:
+            REDIS_URI: redis://langgraph-redis:6379
+            POSTGRES_URI: {DEFAULT_POSTGRES_URI}"""
+    assert clean_empty_lines(actual_compose_str) == expected_compose_str
@@ -531,7 +531,7 @@ wheels = [

 [[package]]
 name = "langgraph-cli"
-version = "0.3.5"
+version = "0.3.6"
 source = { editable = "." }
 dependencies = [
    { name = "click", version = "8.1.8", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.10'" },
@@ -262,6 +262,11 @@ class entrypoint(Generic[ContextT]):
        cache_policy: A cache policy to use for caching the results of the workflow.
        retry_policy: A retry policy (or list of policies) to use for the workflow in case of a failure.

+    !!! warning "`config_schema` Deprecated"
+        The `config_schema` parameter is deprecated in v0.6.0 and support will be removed in v2.0.0.
+        Please use `context_schema` instead to specify the schema for run-scoped context.
+
+
    Example: Using entrypoint and tasks
        ```python
        import time
@@ -129,6 +129,10 @@ class StateGraph(Generic[StateT, ContextT, InputT, OutputT]):
        input_schema: The schema class that defines the input to the graph.
        output_schema: The schema class that defines the output from the graph.

+    !!! warning "`config_schema` Deprecated"
+        The `config_schema` parameter is deprecated in v0.6.0 and support will be removed in v2.0.0.
+        Please use `context_schema` instead to specify the schema for run-scoped context.
+
    Example:
        ```python
        from langchain_core.runnables import RunnableConfig
@@ -602,6 +602,7 @@ class Pregel(
    Defaults to None."""

    context_schema: type[ContextT] | None = None
+    """Specifies the schema for the context object that will be passed to the workflow."""

    config: RunnableConfig | None = None

@@ -2438,6 +2439,8 @@ class Pregel(
        Args:
            input: The input to the graph.
            config: The configuration to use for the run.
+            context: The static context to use for the run.
+                !!! version-added "Added in version 0.6.0."
            stream_mode: The mode to stream output, defaults to `self.stream_mode`.
                Options are:

@@ -2694,6 +2697,8 @@ class Pregel(
        Args:
            input: The input to the graph.
            config: The configuration to use for the run.
+            context: The static context to use for the run.
+                !!! version-added "Added in version 0.6.0."
            stream_mode: The mode to stream output, defaults to `self.stream_mode`.
                Options are:

@@ -2981,6 +2986,8 @@ class Pregel(
        Args:
            input: The input data for the graph. It can be a dictionary or any other type.
            config: Optional. The configuration for the graph run.
+            context: The static context to use for the run.
+                !!! version-added "Added in version 0.6.0."
            stream_mode: Optional[str]. The stream mode for the graph run. Default is "values".
            print_mode: Accepts the same values as `stream_mode`, but only prints the output to the console, for debugging purposes. Does not affect the output of the graph in any way.
            output_keys: Optional. The output keys to retrieve from the graph run.
@@ -3058,6 +3065,8 @@ class Pregel(
        Args:
            input: The input data for the computation. It can be a dictionary or any other type.
            config: Optional. The configuration for the computation.
+            context: The static context to use for the run.
+                !!! version-added "Added in version 0.6.0."
            stream_mode: Optional. The stream mode for the computation. Default is "values".
            print_mode: Accepts the same values as `stream_mode`, but only prints the output to the console, for debugging purposes. Does not affect the output of the graph in any way.
            output_keys: Optional. The output keys to include in the result. Default is None.
@@ -8,6 +8,7 @@ from typing import (
    cast,
 )

+import langsmith as ls
 from langchain_core.runnables import RunnableConfig
 from langchain_core.runnables.graph import (
    Edge as DrawableEdge,
@@ -118,6 +119,7 @@ class RemoteGraph(PregelProtocol):
        sync_client: SyncLangGraphClient | None = None,
        config: RunnableConfig | None = None,
        name: str | None = None,
+        distributed_tracing: bool = False,
    ):
        """Specify `url`, `api_key`, and/or `headers` to create default sync and async clients.

@@ -136,6 +138,7 @@ class RemoteGraph(PregelProtocol):
            name: Human-readable name to attach to the RemoteGraph instance.
                This is useful for adding `RemoteGraph` as a subgraph via `graph.add_node(remote_graph)`.
                If not provided, defaults to the assistant ID.
+            distributed_tracing: Whether to enable sending LangSmith distributed tracing headers.
        """
        self.assistant_id = assistant_id
        if name is None:
@@ -143,6 +146,7 @@ class RemoteGraph(PregelProtocol):
        else:
            self.name = name
        self.config = config
+        self.distributed_tracing = distributed_tracing

        if client is None and url is not None:
            client = get_client(url=url, api_key=api_key, headers=headers)
@@ -629,6 +633,7 @@ class RemoteGraph(PregelProtocol):
        interrupt_before: All | Sequence[str] | None = None,
        interrupt_after: All | Sequence[str] | None = None,
        subgraphs: bool = False,
+        headers: dict[str, str] | None = None,
        **kwargs: Any,
    ) -> Iterator[dict[str, Any] | Any]:
        """Create a run and stream the results.
@@ -644,6 +649,7 @@ class RemoteGraph(PregelProtocol):
            interrupt_before: Interrupt the graph before these nodes.
            interrupt_after: Interrupt the graph after these nodes.
            subgraphs: Stream from subgraphs.
+            headers: Additional headers to pass to the request.
            **kwargs: Additional params to pass to client.runs.stream.

        Yields:
@@ -672,6 +678,9 @@ class RemoteGraph(PregelProtocol):
            interrupt_after=interrupt_after,
            stream_subgraphs=subgraphs or stream is not None,
            if_not_exists="create",
+            headers=_merge_tracing_headers(headers)
+            if self.distributed_tracing
+            else headers,
            **kwargs,
        ):
            # split mode and ns
@@ -731,6 +740,7 @@ class RemoteGraph(PregelProtocol):
        interrupt_before: All | Sequence[str] | None = None,
        interrupt_after: All | Sequence[str] | None = None,
        subgraphs: bool = False,
+        headers: dict[str, str] | None = None,
        **kwargs: Any,
    ) -> AsyncIterator[dict[str, Any] | Any]:
        """Create a run and stream the results.
@@ -746,6 +756,7 @@ class RemoteGraph(PregelProtocol):
            interrupt_before: Interrupt the graph before these nodes.
            interrupt_after: Interrupt the graph after these nodes.
            subgraphs: Stream from subgraphs.
+            headers: Additional headers to pass to the request.
            **kwargs: Additional params to pass to client.runs.stream.

        Yields:
@@ -774,6 +785,9 @@ class RemoteGraph(PregelProtocol):
            interrupt_after=interrupt_after,
            stream_subgraphs=subgraphs or stream is not None,
            if_not_exists="create",
+            headers=_merge_tracing_headers(headers)
+            if self.distributed_tracing
+            else headers,
            **kwargs,
        ):
            # split mode and ns
@@ -847,6 +861,7 @@ class RemoteGraph(PregelProtocol):
        *,
        interrupt_before: All | Sequence[str] | None = None,
        interrupt_after: All | Sequence[str] | None = None,
+        headers: dict[str, str] | None = None,
        **kwargs: Any,
    ) -> dict[str, Any] | Any:
        """Create a run, wait until it finishes and return the final state.
@@ -856,6 +871,7 @@ class RemoteGraph(PregelProtocol):
            config: A `RunnableConfig` for graph invocation.
            interrupt_before: Interrupt the graph before these nodes.
            interrupt_after: Interrupt the graph after these nodes.
+            headers: Additional headers to pass to the request.
            **kwargs: Additional params to pass to RemoteGraph.stream.

        Returns:
@@ -866,6 +882,7 @@ class RemoteGraph(PregelProtocol):
            config=config,
            interrupt_before=interrupt_before,
            interrupt_after=interrupt_after,
+            headers=headers,
            stream_mode="values",
            **kwargs,
        ):
@@ -882,6 +899,7 @@ class RemoteGraph(PregelProtocol):
        *,
        interrupt_before: All | Sequence[str] | None = None,
        interrupt_after: All | Sequence[str] | None = None,
+        headers: dict[str, str] | None = None,
        **kwargs: Any,
    ) -> dict[str, Any] | Any:
        """Create a run, wait until it finishes and return the final state.
@@ -891,6 +909,7 @@ class RemoteGraph(PregelProtocol):
            config: A `RunnableConfig` for graph invocation.
            interrupt_before: Interrupt the graph before these nodes.
            interrupt_after: Interrupt the graph after these nodes.
+            headers: Additional headers to pass to the request.
            **kwargs: Additional params to pass to RemoteGraph.astream.

        Returns:
@@ -901,6 +920,7 @@ class RemoteGraph(PregelProtocol):
            config=config,
            interrupt_before=interrupt_before,
            interrupt_after=interrupt_after,
+            headers=headers,
            stream_mode="values",
            **kwargs,
        ):
@@ -909,3 +929,17 @@ class RemoteGraph(PregelProtocol):
            return chunk
        except UnboundLocalError:
            return None
+
+
+def _merge_tracing_headers(headers: dict[str, str] | None) -> dict[str, str] | None:
+    if rt := ls.get_current_run_tree():
+        tracing_headers = rt.to_headers()
+        baggage = tracing_headers.pop("baggage")
+        if headers:
+            if "baggage" in headers:
+                baggage = headers["baggage"] + "," + baggage
+            tracing_headers["baggage"] = baggage
+            headers.update(tracing_headers)
+        else:
+            headers = tracing_headers
+    return headers
@@ -11,6 +11,8 @@ from langgraph.store.base import BaseStore
 from langgraph.types import _DC_KWARGS, StreamWriter
 from langgraph.typing import ContextT

+__all__ = ("Runtime", "get_runtime")
+

 def _no_op_stream_writer(_: Any) -> None: ...

@@ -24,9 +26,61 @@ class _RuntimeOverrides(TypedDict, Generic[ContextT], total=False):

@dataclass(**_DC_KWARGS)
 class Runtime(Generic[ContextT]):
-    """Convenience class that bundles run-scoped context and graph configuration.
+    """Convenience class that bundles run-scoped context and other runtime utilities.

-    !!! version-added "Added in version 1.0.0."
+    !!! version-added "Added in version v0.6.0"
+
+    Example:
+
+    ```python
+    from typing import TypedDict
+    from langgraph.graph import StateGraph
+    from dataclasses import dataclass
+    from langgraph.runtime import Runtime
+    from langgraph.store.memory import InMemoryStore
+
+
+    @dataclass
+    class Context:  # (1)!
+        user_id: str
+
+
+    class State(TypedDict, total=False):
+        response: str
+
+
+    store = InMemoryStore()  # (2)!
+    store.put(("users",), "user_123", {"name": "Alice"})
+
+
+    def personalized_greeting(state: State, runtime: Runtime[Context]) -> State:
+        '''Generate personalized greeting using runtime context and store.'''
+        user_id = runtime.context.user_id  # (3)!
+        name = "unknown_user"
+        if runtime.store:
+            if memory := runtime.store.get(("users",), user_id):
+                name = memory.value["name"]
+
+        response = f"Hello {name}! Nice to see you again."
+        return {"response": response}
+
+
+    graph = (
+        StateGraph(state_schema=State, context_schema=Context)
+        .add_node("personalized_greeting", personalized_greeting)
+        .set_entry_point("personalized_greeting")
+        .set_finish_point("personalized_greeting")
+        .compile(store=store)
+    )
+
+    result = graph.invoke({}, context=Context(user_id="user_123"))
+    print(result)
+    # > {'response': 'Hello Alice! Nice to see you again.'}
+    ```
+
+    1. Define a schema for the runtime context.
+    2. Create a store to persist memories and other information.
+    3. Use the runtime context to access the user_id.
    """

    context: ContextT = field(default=None)  # type: ignore[assignment]
@@ -76,7 +130,14 @@ DEFAULT_RUNTIME = Runtime(


 def get_runtime(context_schema: type[ContextT] | None = None) -> Runtime[ContextT]:
-    """Get the runtime for the current graph run."""
+    """Get the runtime for the current graph run.
+
+    Args:
+        context_schema: Optional schema used for type hinting the return type of the runtime.
+
+    Returns:
+        The runtime for the current graph run.
+    """

    # TODO: in an ideal world, we would have a context manager for
    # the runtime that's independent of the config. this will follow
@@ -149,10 +149,25 @@ class Interrupt:
    """Information about an interrupt that occurred in a node.

    !!! version-added "Added in version 0.2.24."
+
+    !!! version-changed "Changed in version v0.4.0"
+        * `interrupt_id` was introduced as a property
+
+    !!! version-changed "Changed in version v0.6.0"
+
+        The following attributes have been removed:
+
+        * `ns`
+        * `when`
+        * `resumable`
+        * `interrupt_id`, deprecated in favor of `id`
    """

    value: Any
+    """The value associated with the interrupt."""
+
    id: str
+    """The ID of the interrupt. Can be used to resume the interrupt directly."""

    def __init__(
        self,
@@ -0,0 +1 @@
+"""Legacy utilities module, to be removed in v1."""
@@ -0,0 +1,3 @@
+"""Backwards compat imports for config utilities, to be removed in v1."""
+
+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 = "0.6.0a2"
 description = "Building stateful, multi-actor applications with LLMs"
 authors = []
 requires-python = ">=3.9"
@@ -15,7 +15,7 @@ dependencies = [
    "langchain-core>=0.1",
    "langgraph-checkpoint>=2.1.0,<3.0.0",
    "langgraph-sdk>=0.2.0,<0.3.0",
-    "langgraph-prebuilt>=0.5.0,<0.6.0",
+    "langgraph-prebuilt==0.6.0a1",
    "xxhash>=3.5.0",
    "pydantic>=2.7.4",
 ]
@@ -3,6 +3,7 @@ import sys
 from typing import Annotated, Union
 from unittest.mock import AsyncMock, MagicMock

+import langsmith as ls
 import pytest
 from langchain_core.messages import AnyMessage, BaseMessage
 from langchain_core.runnables import RunnableConfig
@@ -899,21 +900,20 @@ async def test_langgraph_cloud_integration():
    }

    # test invoke
-    response = app.invoke(
+    app.invoke(
        input,
        config={"configurable": {"thread_id": "39a6104a-34e7-4f83-929c-d9eb163003c9"}},
        interrupt_before=["agent"],
    )
-    print("response:", response["messages"][-1].content)

    # test stream
-    async for chunk in app.astream(
+    async for _ in app.astream(
        input,
        config={"configurable": {"thread_id": "2dc3e3e7-39ac-4597-aa57-4404b944e82a"}},
        subgraphs=True,
        stream_mode=["debug", "messages"],
    ):
-        print("chunk:", chunk)
+        pass

    # test stream events
    async for chunk in remote_pregel.astream_events(
@@ -923,17 +923,16 @@ async def test_langgraph_cloud_integration():
        subgraphs=True,
        stream_mode=[],
    ):
-        print("chunk:", chunk)
+        pass

    # test get state
-    state_snapshot = await remote_pregel.aget_state(
+    await remote_pregel.aget_state(
        config={"configurable": {"thread_id": "2dc3e3e7-39ac-4597-aa57-4404b944e82a"}},
        subgraphs=True,
    )
-    print("state snapshot:", state_snapshot)

    # test update state
-    response = await remote_pregel.aupdate_state(
+    await remote_pregel.aupdate_state(
        config={"configurable": {"thread_id": "6645e002-ed50-4022-92a3-d0d186fdf812"}},
        values={
            "messages": [
@@ -944,18 +943,16 @@ async def test_langgraph_cloud_integration():
            ]
        },
    )
-    print("response:", response)

    # test get history
    async for state in remote_pregel.aget_state_history(
        config={"configurable": {"thread_id": "2dc3e3e7-39ac-4597-aa57-4404b944e82a"}},
    ):
-        print("state snapshot:", state)
+        pass

    # test get graph
    remote_pregel.graph_id = "fe096781-5601-53d2-b2f6-0d3403f7e9ca"  # must be UUID
-    graph = await remote_pregel.aget_graph(xray=True)
-    print("graph:", graph)
+    await remote_pregel.aget_graph(xray=True)


 def test_sanitize_config():
@@ -1181,3 +1178,73 @@ async def test_remote_graph_stream_messages_tuple(
    assert coerced_events == coerced_inmem_events
    # TODO: Fix the namespace matching in the next api release.
    # assert namespaces == inmem_namespaces
+
+
+@pytest.mark.anyio
+@pytest.mark.parametrize("distributed_tracing", [False, True])
+@pytest.mark.parametrize("stream", [False, True])
+async def test_include_headers(distributed_tracing: bool, stream: bool):
+    mock_async_client = MagicMock()
+    async_iter = MagicMock()
+    return_value = [
+        StreamPart(event="values", data={"chunk": "data1"}),
+    ]
+    async_iter.__aiter__.return_value = return_value
+    astream_mock = mock_async_client.runs.stream
+    astream_mock.return_value = async_iter
+
+    mock_sync_client = MagicMock()
+    sync_iter = MagicMock()
+    sync_iter.__iter__.return_value = return_value
+    stream_mock = mock_sync_client.runs.stream
+    stream_mock.return_value = async_iter
+
+    remote_pregel = RemoteGraph(
+        "test_graph_id",
+        client=mock_async_client,
+        sync_client=mock_sync_client,
+        distributed_tracing=distributed_tracing,
+    )
+
+    config = {"configurable": {"thread_id": "thread_1"}}
+    with ls.tracing_context(enabled=True, client=MagicMock()):
+        with ls.trace("foo"):
+            if stream:
+                async for _ in remote_pregel.astream(
+                    {"input": {"messages": [{"type": "human", "content": "hello"}]}},
+                    config,
+                    headers={"foo": "bar"},
+                ):
+                    pass
+
+            else:
+                await remote_pregel.ainvoke(
+                    {"input": {"messages": [{"type": "human", "content": "hello"}]}},
+                    config,
+                    headers={"foo": "bar"},
+                )
+    expected = {"foo": "bar"}
+    if distributed_tracing:
+        expected["langsmith-trace"] = AnyStr()
+        expected["baggage"] = AnyStr()
+
+    assert astream_mock.call_args.kwargs["headers"] == expected
+    stream_mock.assert_not_called()
+
+    with ls.tracing_context(enabled=True, client=MagicMock()):
+        with ls.trace("foo"):
+            if stream:
+                for _ in remote_pregel.stream(
+                    {"input": {"messages": [{"type": "human", "content": "hello"}]}},
+                    config,
+                    headers={"foo": "bar"},
+                ):
+                    pass
+
+            else:
+                remote_pregel.invoke(
+                    {"input": {"messages": [{"type": "human", "content": "hello"}]}},
+                    config,
+                    headers={"foo": "bar"},
+                )
+    assert stream_mock.call_args.kwargs["headers"] == expected
@@ -1192,7 +1192,7 @@ wheels = [

 [[package]]
 name = "langgraph"
-version = "0.6.0a1"
+version = "0.6.0a2"
 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" },
@@ -1394,7 +1394,7 @@ dev = [

 [[package]]
 name = "langgraph-cli"
-version = "0.3.5"
+version = "0.3.6"
 source = { editable = "../cli" }
 dependencies = [
    { name = "click", version = "8.1.8", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.10'" },
@@ -1433,7 +1433,7 @@ dev = [

 [[package]]
 name = "langgraph-prebuilt"
-version = "0.5.2"
+version = "0.6.0a1"
 source = { editable = "../prebuilt" }
 dependencies = [
    { name = "langchain-core" },
@@ -1481,7 +1481,7 @@ wheels = [

 [[package]]
 name = "langgraph-sdk"
-version = "0.2.0a1"
+version = "0.2.0"
 source = { editable = "../sdk-py" }
 dependencies = [
    { name = "httpx" },
@@ -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:
@@ -364,6 +408,11 @@ def create_react_agent(
            This name will be automatically used when adding ReAct agent graph to another graph as a subgraph node -
            particularly useful for building multi-agent systems.

+    !!! warning "`config_schema` Deprecated"
+        The `config_schema` parameter is deprecated in v0.6.0 and support will be removed in v2.0.0.
+        Please use `context_schema` instead to specify the schema for run-scoped context.
+
+
    Returns:
        A compiled LangChain runnable that can be used for chat interactions.

@@ -447,32 +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 = (
@@ -517,9 +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

@@ -535,9 +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):
@@ -574,22 +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
@@ -597,7 +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)
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"

 [project]
 name = "langgraph-prebuilt"
-version = "0.5.2"
+version = "0.6.0a1"
 description = "Library with high-level APIs for creating and executing LangGraph agents and tools."
 authors = []
 requires-python = ">=3.9"
@@ -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 = "0.6.0a2"
 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" },
@@ -460,7 +460,7 @@ dev = [

 [[package]]
 name = "langgraph-prebuilt"
-version = "0.5.2"
+version = "0.6.0a1"
 source = { editable = "." }
 dependencies = [
    { name = "langchain-core" },
@@ -507,7 +507,7 @@ dev = [

 [[package]]
 name = "langgraph-sdk"
-version = "0.2.0a1"
+version = "0.2.0"
 source = { editable = "../sdk-py" }
 dependencies = [
    { name = "httpx" },
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"

 [project]
 name = "langgraph-sdk"
-version = "0.2.0a1"
+version = "0.2.0"
 description = "SDK for interacting with LangGraph API"
 authors = []
 requires-python = ">=3.9"
@@ -119,7 +119,7 @@ wheels = [

 [[package]]
 name = "langgraph-sdk"
-version = "0.2.0a1"
+version = "0.2.0"
 source = { editable = "." }
 dependencies = [
    { name = "httpx" },
Author	SHA1	Message	Date
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
Eugene YurtsevandGitHub	bc9d45b476	fix(checkpoint-sqlite): add validation to filter keys in sql store (#5666 ) This PR adds validation to keys used in filtering logic in the SQLite store implementation.	2025-07-25 13:01:13 -04:00
Sydney RunkleandGitHub	7d3f0089aa	docs: more thorough notes on v0.6 features and changes (#5623 )	2025-07-25 09:33:53 -04:00
Sydney RunkleandGitHub	ed678f4701	Merge branch 'main' into sr/version-added-for-context	2025-07-25 09:27:52 -04:00
Sydney Runkle	22411ba0fd	lint	2025-07-25 09:27:34 -04:00
Sydney Runkle	5b9021ff37	typo	2025-07-25 09:25:26 -04:00
Sydney Runkle	aaff464115	move deprecation note for config_schema	2025-07-25 09:23:59 -04:00
Sam CrowderandGitHub	3a23a256e2	docs: [LangGraph Server Changelog Bot] Changelog updates for new version(s) (#5657 )	2025-07-24 20:37:10 -07:00
Sam Crowder	f6857395b9	Update changelog via LangGraph Server Changelog Bot	2025-07-24 20:19:17 -07:00
William FHandGitHub	cdaa7ba003	chore: typing for headers in remote graph (#5653 )	2025-07-24 18:00:44 -07:00
Sydney Runkle	39745ed794	Merge branch 'sr/version-added-for-context' of https://github.com/langchain-ai/langgraph into sr/version-added-for-context	2025-07-24 17:31:25 -04:00
Sydney Runkle	738bb8a343	Merge branch 'sr/fixes-for-v6' into sr/version-added-for-context	2025-07-24 17:31:21 -04:00
Sydney RunkleandGitHub	b2dde8d9af	Merge branch 'main' into sr/version-added-for-context	2025-07-24 17:29:54 -04:00
Sydney Runkle	5312edc830	more runtime details	2025-07-24 17:28:58 -04:00
Sydney Runkle	276310e116	fix and interrupt	2025-07-24 16:54:20 -04:00
Sydney Runkle	39977ded8c	runtime api ref	2025-07-24 16:36:51 -04:00
Sydney Runkle	439038fc3a	deprecation for config_schema in docs	2025-07-24 16:23:42 -04:00
Sam CrowderandGitHub	2e5445c565	docs: [LangGraph Server Changelog Bot] Changelog updates for new version(s) (#5650 )	2025-07-24 11:35:22 -07:00
Sam Crowder	d38510ad03	Update changelog via LangGraph Server Changelog Bot	2025-07-24 09:18:21 -07:00
Sydney RunkleandGitHub	951486d107	release(prebuilt): 0.6.0 (#5648 )	2025-07-24 10:38:24 -04:00
Sydney Runkle	745a1e7a29	bumping required prebuilt version	2025-07-24 10:27:20 -04:00
Sam CrowderandGitHub	24731d6a28	docs: [LangGraph Server Changelog Bot] Changelog updates for new version(s) (#5625 )	2025-07-23 20:06:22 -07:00
Sam Crowder	a4689a5d10	Update changelog via LangGraph Server Changelog Bot	2025-07-23 18:59:50 -07:00
langchain-infraandGitHub	b05ce0bf60	release(cli): Release new CLI version with support for api-version flag (#5640 )	2025-07-23 19:47:25 -04:00
David Asamu	4501e41991	uv sync	2025-07-24 00:36:02 +01:00
Asamu DavidandGitHub	bc83287fc8	bump version number new CLI version with support for api-version flag	2025-07-24 00:19:57 +01:00
Andrew NguonlyandGitHub	11547e1990	docs: Add more clarification about the LangSmith API key for LangGraph Platform deployments (#5635 )	2025-07-23 11:39:39 -07:00
langchain-infraandGitHub	fadd9c4577	feat(cli): add support for api-version (#5584 )	2025-07-23 12:33:04 -04:00
Asamu DavidandGitHub	fd2933a792	Merge branch 'main' into david/30-06/support-base-image-tag	2025-07-23 15:42:24 +01:00
David Asamu	40fa69f8ee	lint and format fixes	2025-07-23 15:39:34 +01:00
Sam Crowder	0824161984	Update changelog via LangGraph Server Changelog Bot	2025-07-22 13:47:31 -07:00
Sam CrowderandGitHub	b028f502e1	docs: [LangGraph Server Changelog Bot] Changelog updates for new version(s) (#5611 )	2025-07-22 12:47:33 -07:00
William FHandGitHub	9dc3fed6b8	feat(langgraph): Support sending distributed tracing headers (#5619 )	2025-07-22 12:47:23 -07:00
Sydney Runkle	0232201b7b	improving docs for context	2025-07-22 13:28:27 -04:00
Sydney RunkleandGitHub	869b0f2de4	release(sdk-py): 0.2.0 (#5622 )	2025-07-22 13:27:04 -04:00
Sydney Runkle	90e3adcd71	bump sdk version	2025-07-22 13:20:55 -04:00
Sam Crowder	aa1bbe3d01	Update changelog via LangGraph Server Changelog Bot	2025-07-21 17:41:55 -07:00
David Asamu	ec0a30008c	more semantic variable name	2025-07-19 03:30:29 +01:00
Asamu DavidandGitHub	00c7909c27	Merge branch 'main' into david/30-06/support-base-image-tag	2025-07-19 03:20:09 +01:00
David Asamu	58d396fcf1	merge main	2025-07-19 03:17:17 +01:00
David Asamu	9f0abf014d	format changed files	2025-07-19 03:06:17 +01:00
David Asamu	8d6cd15669	add api-version option	2025-07-19 02:55:47 +01:00
				`@@ -0,0 +1 @@`
				`"""Legacy utilities module, to be removed in v1."""`