langchain-ai/langgraph
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraph.git synced 2026-07-15 12:35:43 -04:00
Code Issues 314 Packages Projects Releases 17 Wiki Activity

LangGraph Server not propagating Runtime Context when using SendAPI #1033

New Issue
Closed
opened 2026-02-20 17:42:49 -05:00 by yindo · 1 comment
yindo commented 2026-02-20 17:42:49 -05:00
Owner
Copy Link
Copy Source

Originally created by @LouisAuneau on GitHub (Oct 31, 2025).

Checked other resources

  • This is a bug, not a usage question. For questions, please use the LangChain Forum (https://forum.langchain.com/).
  • I added a clear and detailed title that summarizes the issue.
  • I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example).
  • I included a self-contained, minimal example that demonstrates the issue INCLUDING all the relevant imports. The code run AS IS to reproduce the issue.

Example Code

from langgraph.graph import StateGraph, START, END
from langgraph.runtime import Runtime
from langgraph.types import Send
from typing_extensions import TypedDict, Annotated
import operator

class OverallState(TypedDict):
    subjects: list[str]
    jokes: Annotated[list[str], operator.add]

class NestedState(TypedDict):
    subject: str

class ContextSchema(TypedDict):
    my_runtime_value: str

def generate_topics(state: OverallState, runtime: Runtime[ContextSchema]):
    return {"subjects": ["lions", "elephants", "penguins"]}

def generate_joke(state: NestedState, runtime: Runtime[ContextSchema]):
    if runtime.context is None:
        raise RuntimeError("Runtime context is not available")
    
    joke_map = {
        "lions": "Why don't lions like fast food? Because they can't catch it!",
        "elephants": "Why don't elephants use computers? They're afraid of the mouse!",
        "penguins": "Why don't penguins like talking to strangers at parties? Because they find it hard to break the ice."
    }

    return {"jokes": [joke_map[state["subject"]]]}

def continue_to_jokes(state: OverallState):
    return [Send("generate_joke", {"subject": s}) for s in state["subjects"]]

builder = StateGraph(OverallState, context_schema=ContextSchema)
builder.add_node("generate_topics", generate_topics)
builder.add_node("generate_joke", generate_joke)
builder.add_edge(START, "generate_topics")
builder.add_conditional_edges("generate_topics", continue_to_jokes, ["generate_joke"])
builder.add_edge("generate_joke", END)
graph = builder.compile()

Error Message and Stack Trace (if applicable)

Traceback (most recent call last):
  File ".../lib/python3.12/site-packages/langgraph_api/worker.py", line 142, in wrap_user_errors
    await consume(
  File ".../lib/python3.12/site-packages/langgraph_api/stream.py", line 516, in consume
    raise e
  File ".../lib/python3.12/site-packages/langgraph_api/stream.py", line 499, in consume
    async for mode, payload in stream:
  File ".../lib/python3.12/site-packages/langgraph_api/stream.py", line 384, in astream_state
    event = await wait_if_not_done(anext(stream, sentinel), done)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".../lib/python3.12/site-packages/langgraph_api/asyncio.py", line 89, in wait_if_not_done
    raise e.exceptions[0] from None
  File ".../lib/python3.12/site-packages/langgraph/pregel/main.py", line 3000, in astream
    async for _ in runner.atick(
  File ".../lib/python3.12/site-packages/langgraph/pregel/_runner.py", line 410, in atick
    _panic_or_proceed(
  File ".../lib/python3.12/site-packages/langgraph/pregel/_runner.py", line 520, in _panic_or_proceed
    raise exc
  File ".../lib/python3.12/site-packages/langgraph/pregel/_retry.py", line 137, in arun_with_retry
    return await task.proc.ainvoke(task.input, config)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".../lib/python3.12/site-packages/langgraph/_internal/_runnable.py", line 705, in ainvoke
    input = await asyncio.create_task(
            ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".../lib/python3.12/site-packages/langgraph/_internal/_runnable.py", line 473, in ainvoke
    ret = await self.afunc(*args, **kwargs)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".../lib/python3.12/site-packages/langchain_core/runnables/config.py", line 603, in run_in_executor
    return await asyncio.get_running_loop().run_in_executor(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".../lib/python3.12/concurrent/futures/thread.py", line 59, in run
    result = self.fn(*self.args, **self.kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".../lib/python3.12/site-packages/langchain_core/runnables/config.py", line 594, in wrapper
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File ".../graphs.py", line 30, in generate_joke
    raise RuntimeError("Runtime context is not available")
RuntimeError: Runtime context is not available
During task with name 'generate_joke' and id '00c19a65-f8fb-ad84-4128-9e286501516b'

Description

I am trying to run a graph that uses the map-reduce pattern (with Send API) and a runtime context at the same time.

This works perfectly fine when running the graph locally with graph.invoke(). The mapped node (generate_joke) does receive the runtime context.

However, when adding the exact same graph to a langgraph.json as follows:

{
  "dependencies": ["./"],
  "graphs": {
    "test": "graphs.py:graph"
  },
  "env": "./.env"
}

And running this graph from the server (I tried both starting the server with langgraph-dev and building it as a docker image), it seems the context is no-longer passed by the conditional edge into the mapped node (hence raising the error I set in generate_joke).

System Info

System Information

OS: Darwin
OS Version: Darwin Kernel Version 24.6.0: Mon Jul 14 11:29:54 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T8122
Python Version: 3.12.11 (main, Jul 29 2025, 20:45:17) [Clang 17.0.0 (clang-1700.0.13.5)]

Package Information

langchain_core: 1.0.0
langchain: 1.0.2
langchain_community: 0.4
langsmith: 0.4.8
langchain_chroma: 1.0.0
langchain_classic: 1.0.0
langchain_openai: 1.0.1
langchain_text_splitters: 1.0.0
langgraph_api: 0.4.48
langgraph_cli: 0.4.4
langgraph_runtime_inmem: 0.14.1
langgraph_sdk: 0.2.6

Optional packages not installed

langserve

Other Dependencies

aiohttp: 3.12.15
async-timeout: Installed. No version info available.
blockbuster: 1.5.25
chromadb: 1.2.2
click: 8.2.1
cloudpickle: 3.1.1
cryptography: 44.0.3
dataclasses-json: 0.6.7
grpcio: 1.76.0
grpcio-tools: 1.75.1
httpx: 0.28.1
httpx-sse: 0.4.1
jsonpatch: 1.33
jsonschema-rs: 0.29.1
langchain-anthropic: Installed. No version info available.
langchain-aws: Installed. No version info available.
langchain-deepseek: Installed. No version info available.
langchain-fireworks: Installed. No version info available.
langchain-google-genai: Installed. No version info available.
langchain-google-vertexai: Installed. No version info available.
langchain-groq: Installed. No version info available.
langchain-huggingface: Installed. No version info available.
langchain-mistralai: Installed. No version info available.
langchain-ollama: Installed. No version info available.
langchain-perplexity: Installed. No version info available.
langchain-together: Installed. No version info available.
langchain-xai: Installed. No version info available.
langgraph: 1.0.2
langgraph-checkpoint: 2.1.1
langsmith-pyo3: Installed. No version info available.
numpy: 1.26.4
openai: 2.6.1
openai-agents: Installed. No version info available.
opentelemetry-api: 1.38.0
opentelemetry-exporter-otlp-proto-http: 1.38.0
opentelemetry-sdk: 1.38.0
orjson: 3.11.1
packaging: 25.0
protobuf: 6.33.0
pydantic: 2.11.7
pydantic-settings: 2.10.1
pyjwt: 2.10.1
pytest: Installed. No version info available.
python-dotenv: 1.1.1
pyyaml: 6.0.2
PyYAML: 6.0.2
requests: 2.32.5
requests-toolbelt: 1.0.0
rich: 14.2.0
sqlalchemy: 2.0.41
SQLAlchemy: 2.0.41
sse-starlette: 2.1.3
starlette: 0.48.0
structlog: 25.4.0
tenacity: 9.1.2
tiktoken: 0.12.0
truststore: 0.10.4
typing-extensions: 4.14.1
uvicorn: 0.35.0
watchfiles: 1.1.0
zstandard: 0.23.0

Originally created by @LouisAuneau on GitHub (Oct 31, 2025). ### Checked other resources - [x] This is a bug, not a usage question. For questions, please use the LangChain Forum (https://forum.langchain.com/). - [x] I added a clear and detailed title that summarizes the issue. - [x] I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example). - [x] I included a self-contained, minimal example that demonstrates the issue INCLUDING all the relevant imports. The code run AS IS to reproduce the issue. ### Example Code ```python from langgraph.graph import StateGraph, START, END from langgraph.runtime import Runtime from langgraph.types import Send from typing_extensions import TypedDict, Annotated import operator class OverallState(TypedDict): subjects: list[str] jokes: Annotated[list[str], operator.add] class NestedState(TypedDict): subject: str class ContextSchema(TypedDict): my_runtime_value: str def generate_topics(state: OverallState, runtime: Runtime[ContextSchema]): return {"subjects": ["lions", "elephants", "penguins"]} def generate_joke(state: NestedState, runtime: Runtime[ContextSchema]): if runtime.context is None: raise RuntimeError("Runtime context is not available") joke_map = { "lions": "Why don't lions like fast food? Because they can't catch it!", "elephants": "Why don't elephants use computers? They're afraid of the mouse!", "penguins": "Why don't penguins like talking to strangers at parties? Because they find it hard to break the ice." } return {"jokes": [joke_map[state["subject"]]]} def continue_to_jokes(state: OverallState): return [Send("generate_joke", {"subject": s}) for s in state["subjects"]] builder = StateGraph(OverallState, context_schema=ContextSchema) builder.add_node("generate_topics", generate_topics) builder.add_node("generate_joke", generate_joke) builder.add_edge(START, "generate_topics") builder.add_conditional_edges("generate_topics", continue_to_jokes, ["generate_joke"]) builder.add_edge("generate_joke", END) graph = builder.compile() ``` ### Error Message and Stack Trace (if applicable) ```shell Traceback (most recent call last): File ".../lib/python3.12/site-packages/langgraph_api/worker.py", line 142, in wrap_user_errors await consume( File ".../lib/python3.12/site-packages/langgraph_api/stream.py", line 516, in consume raise e File ".../lib/python3.12/site-packages/langgraph_api/stream.py", line 499, in consume async for mode, payload in stream: File ".../lib/python3.12/site-packages/langgraph_api/stream.py", line 384, in astream_state event = await wait_if_not_done(anext(stream, sentinel), done) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File ".../lib/python3.12/site-packages/langgraph_api/asyncio.py", line 89, in wait_if_not_done raise e.exceptions[0] from None File ".../lib/python3.12/site-packages/langgraph/pregel/main.py", line 3000, in astream async for _ in runner.atick( File ".../lib/python3.12/site-packages/langgraph/pregel/_runner.py", line 410, in atick _panic_or_proceed( File ".../lib/python3.12/site-packages/langgraph/pregel/_runner.py", line 520, in _panic_or_proceed raise exc File ".../lib/python3.12/site-packages/langgraph/pregel/_retry.py", line 137, in arun_with_retry return await task.proc.ainvoke(task.input, config) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File ".../lib/python3.12/site-packages/langgraph/_internal/_runnable.py", line 705, in ainvoke input = await asyncio.create_task( ^^^^^^^^^^^^^^^^^^^^^^^^^^ File ".../lib/python3.12/site-packages/langgraph/_internal/_runnable.py", line 473, in ainvoke ret = await self.afunc(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File ".../lib/python3.12/site-packages/langchain_core/runnables/config.py", line 603, in run_in_executor return await asyncio.get_running_loop().run_in_executor( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File ".../lib/python3.12/concurrent/futures/thread.py", line 59, in run result = self.fn(*self.args, **self.kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File ".../lib/python3.12/site-packages/langchain_core/runnables/config.py", line 594, in wrapper return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File ".../graphs.py", line 30, in generate_joke raise RuntimeError("Runtime context is not available") RuntimeError: Runtime context is not available During task with name 'generate_joke' and id '00c19a65-f8fb-ad84-4128-9e286501516b' ``` ### Description I am trying to run a graph that uses the [map-reduce pattern](https://docs.langchain.com/oss/python/langgraph/use-graph-api#map-reduce-and-the-send-api) (with Send API) and a [runtime context](https://docs.langchain.com/oss/python/langgraph/use-graph-api#add-runtime-configuration) at the same time. This works perfectly fine when running the graph locally with `graph.invoke()`. The mapped node (`generate_joke`) does receive the runtime context. However, when adding the exact same graph to a `langgraph.json` as follows: ```json { "dependencies": ["./"], "graphs": { "test": "graphs.py:graph" }, "env": "./.env" } ``` And running this graph from the server (I tried both starting the server with `langgraph-dev` and building it as a docker image), it seems the context is no-longer passed by the conditional edge into the mapped node (hence raising the error I set in `generate_joke`). ### System Info System Information ------------------ > OS: Darwin > OS Version: Darwin Kernel Version 24.6.0: Mon Jul 14 11:29:54 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T8122 > Python Version: 3.12.11 (main, Jul 29 2025, 20:45:17) [Clang 17.0.0 (clang-1700.0.13.5)] Package Information ------------------- > langchain_core: 1.0.0 > langchain: 1.0.2 > langchain_community: 0.4 > langsmith: 0.4.8 > langchain_chroma: 1.0.0 > langchain_classic: 1.0.0 > langchain_openai: 1.0.1 > langchain_text_splitters: 1.0.0 > langgraph_api: 0.4.48 > langgraph_cli: 0.4.4 > langgraph_runtime_inmem: 0.14.1 > langgraph_sdk: 0.2.6 Optional packages not installed ------------------------------- > langserve Other Dependencies ------------------ > aiohttp: 3.12.15 > async-timeout: Installed. No version info available. > blockbuster: 1.5.25 > chromadb: 1.2.2 > click: 8.2.1 > cloudpickle: 3.1.1 > cryptography: 44.0.3 > dataclasses-json: 0.6.7 > grpcio: 1.76.0 > grpcio-tools: 1.75.1 > httpx: 0.28.1 > httpx-sse: 0.4.1 > jsonpatch: 1.33 > jsonschema-rs: 0.29.1 > langchain-anthropic: Installed. No version info available. > langchain-aws: Installed. No version info available. > langchain-deepseek: Installed. No version info available. > langchain-fireworks: Installed. No version info available. > langchain-google-genai: Installed. No version info available. > langchain-google-vertexai: Installed. No version info available. > langchain-groq: Installed. No version info available. > langchain-huggingface: Installed. No version info available. > langchain-mistralai: Installed. No version info available. > langchain-ollama: Installed. No version info available. > langchain-perplexity: Installed. No version info available. > langchain-together: Installed. No version info available. > langchain-xai: Installed. No version info available. > langgraph: 1.0.2 > langgraph-checkpoint: 2.1.1 > langsmith-pyo3: Installed. No version info available. > numpy: 1.26.4 > openai: 2.6.1 > openai-agents: Installed. No version info available. > opentelemetry-api: 1.38.0 > opentelemetry-exporter-otlp-proto-http: 1.38.0 > opentelemetry-sdk: 1.38.0 > orjson: 3.11.1 > packaging: 25.0 > protobuf: 6.33.0 > pydantic: 2.11.7 > pydantic-settings: 2.10.1 > pyjwt: 2.10.1 > pytest: Installed. No version info available. > python-dotenv: 1.1.1 > pyyaml: 6.0.2 > PyYAML: 6.0.2 > requests: 2.32.5 > requests-toolbelt: 1.0.0 > rich: 14.2.0 > sqlalchemy: 2.0.41 > SQLAlchemy: 2.0.41 > sse-starlette: 2.1.3 > starlette: 0.48.0 > structlog: 25.4.0 > tenacity: 9.1.2 > tiktoken: 0.12.0 > truststore: 0.10.4 > typing-extensions: 4.14.1 > uvicorn: 0.35.0 > watchfiles: 1.1.0 > zstandard: 0.23.0
yindo added the bugpending labels 2026-02-20 17:42:49 -05:00
yindo closed this issue 2026-02-20 17:42:49 -05:00
yindo commented 2026-02-20 17:42:50 -05:00
Author
Owner
Copy Link
Copy Source

@LouisAuneau commented on GitHub (Nov 6, 2025):

For people seeing this issue. It turns out that if in my case it wasn't related to the sendAPI at all. But when I invoked my assistant through the langgraph-sdk, and then hit an interrupt. I was resuming my graph from LangGraph Studio, which resets the context to None, while I should have resumed from the SDK and provide the context again.

@LouisAuneau commented on GitHub (Nov 6, 2025): For people seeing this issue. It turns out that if in my case it wasn't related to the sendAPI at all. But when I invoked my assistant through the `langgraph-sdk`, and then hit an `interrupt`. I was resuming my graph from LangGraph Studio, which resets the context to `None`, while I should have resumed from the SDK and provide the context again.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
agents
awaiting author revision
bug
change
chat models
checkpointer
ci
code quality
code quality
dependencies
documentation
drawing
duplicate
enhancement
good first issue
help wanted
invalid
maintainer
meta
missing information
not maintained by langchain
open-swe-auto
open-swe-max
open-swe-max-auto
pending
performance
pull-request
Mirrored from GitHub Pull Request
 question
requires design
sdk
server
stale
studio
tests
type checking
usage question
v0.5
v1.1
No Label bug pending
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/langgraph#1033
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?