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

adispatch_custom_event not emitted in time when run via langgraph up (works on LangGraph cloud) #327

New Issue
Closed
opened 2026-02-20 17:36:43 -05:00 by yindo · 1 comment
yindo commented 2026-02-20 17:36:43 -05:00
Owner
Copy Link
Copy Source

Originally created by @mme on GitHub (Nov 28, 2024).

Originally assigned to: @eyurtsev on GitHub.

Checked other resources

  • I added a very descriptive title to this issue.
  • I searched the LangGraph/LangChain documentation with the integrated search.
  • I used the GitHub search to find a similar question and didn't find it.
  • I am sure that this is a bug in LangGraph/LangChain rather than my code.
  • I am sure this is better as an issue rather than a GitHub discussion, since this is a LangGraph bug and not a design question.

Example Code

# This snippet is from the CopilotKit <> LangGraph integration
# We are using copilotkit_emit_state to send state updates to CopilotKit while
# a node is running.
# copilotkit_emit_state is just a thin wrapper around adispatch_custom_event:
# https://github.com/CopilotKit/CopilotKit/blob/3b362e5858f193c56e0e3baf184451eb1d6170fe/sdk-python/copilotkit/langchain.py#L120

async def search_node(state: AgentState, config: RunnableConfig):
    """
    The search node is responsible for searching the internet for resources.
    """
    ai_message = cast(AIMessage, state["messages"][-1])

    state["resources"] = state.get("resources", [])
    state["logs"] = state.get("logs", [])
    queries = ai_message.tool_calls[0]["args"]["queries"]

    for query in queries:
        state["logs"].append({
            "message": f"Search for {query}",
            "done": False
        })

    await copilotkit_emit_state(config, state)

    search_results = []

    for i, query in enumerate(queries):
        response = tavily_client.search(query)
        search_results.append(response)
        state["logs"][i]["done"] = True
        await copilotkit_emit_state(config, state)

    config = copilotkit_customize_config(
        config,
        emit_intermediate_state=[{
            "state_key": "resources",
            "tool": "ExtractResources",
            "tool_argument": "resources",
        }],
    )

    model = get_model(state)
    ainvoke_kwargs = {}
    if model.__class__.__name__ in ["ChatOpenAI"]:
        ainvoke_kwargs["parallel_tool_calls"] = False

    # figure out which resources to use
    response = await model.bind_tools(
        [ExtractResources],
        tool_choice="ExtractResources",
        **ainvoke_kwargs
    ).ainvoke([
        SystemMessage(
            content="""
            You need to extract the 3-5 most relevant resources from the following search results.
            """
        ),
        *state["messages"],
        ToolMessage(
        tool_call_id=ai_message.tool_calls[0]["id"],
        content=f"Performed search: {search_results}"
    )
    ], config)

    state["logs"] = []
    await copilotkit_emit_state(config, state)

Error Message and Stack Trace (if applicable)

No response

Description

On cloud, the custom event is immediately sent. With the local setup via langgraph up, the events are sent with a delay and arrive in the wrong order (so the user can see the current status of the searches being performed)

System Info

CLI

$ langgraph --version
LangGraph CLI, version 0.1.60

System Information

OS: Darwin
OS Version: Darwin Kernel Version 23.0.0: Fri Sep 15 14:41:43 PDT 2023; root:xnu-10002.1.13~1/RELEASE_ARM64_T6000
Python Version: 3.11.9 (main, Apr 2 2024, 08:25:04) [Clang 15.0.0 (clang-1500.3.9.4)]

Package Information

langchain_core: 0.3.19
langchain: 0.3.7
langsmith: 0.1.143
langchain_openai: 0.2.9
langchain_text_splitters: 0.3.2
langgraph: 0.2.52
langserve: 0.0.41

Other Dependencies

aiohttp: 3.10.5
async-timeout: 4.0.2
fastapi: 0.115.0
httpx: 0.27.2
httpx-sse: 0.4.0
jsonpatch: 1.33
langgraph-checkpoint: 2.0.5
langgraph-sdk: 0.1.36
numpy: 1.26.4
openai: 1.54.5
orjson: 3.10.7
packaging: 24.1
pydantic: 2.9.2
PyYAML: 6.0.2
requests: 2.32.3
requests-toolbelt: 1.0.0
SQLAlchemy: 2.0.35
sse-starlette: 2.1.3
tenacity: 8.5.0
tiktoken: 0.7.0
typing-extensions: 4.12.2

Originally created by @mme on GitHub (Nov 28, 2024). Originally assigned to: @eyurtsev on GitHub. ### Checked other resources - [X] I added a very descriptive title to this issue. - [X] I searched the [LangGraph](https://langchain-ai.github.io/langgraph/)/LangChain documentation with the integrated search. - [X] I used the GitHub search to find a similar question and didn't find it. - [X] I am sure that this is a bug in LangGraph/LangChain rather than my code. - [X] I am sure this is better as an issue [rather than a GitHub discussion](https://github.com/langchain-ai/langgraph/discussions/new/choose), since this is a LangGraph bug and not a design question. ### Example Code ```python # This snippet is from the CopilotKit <> LangGraph integration # We are using copilotkit_emit_state to send state updates to CopilotKit while # a node is running. # copilotkit_emit_state is just a thin wrapper around adispatch_custom_event: # https://github.com/CopilotKit/CopilotKit/blob/3b362e5858f193c56e0e3baf184451eb1d6170fe/sdk-python/copilotkit/langchain.py#L120 async def search_node(state: AgentState, config: RunnableConfig): """ The search node is responsible for searching the internet for resources. """ ai_message = cast(AIMessage, state["messages"][-1]) state["resources"] = state.get("resources", []) state["logs"] = state.get("logs", []) queries = ai_message.tool_calls[0]["args"]["queries"] for query in queries: state["logs"].append({ "message": f"Search for {query}", "done": False }) await copilotkit_emit_state(config, state) search_results = [] for i, query in enumerate(queries): response = tavily_client.search(query) search_results.append(response) state["logs"][i]["done"] = True await copilotkit_emit_state(config, state) config = copilotkit_customize_config( config, emit_intermediate_state=[{ "state_key": "resources", "tool": "ExtractResources", "tool_argument": "resources", }], ) model = get_model(state) ainvoke_kwargs = {} if model.__class__.__name__ in ["ChatOpenAI"]: ainvoke_kwargs["parallel_tool_calls"] = False # figure out which resources to use response = await model.bind_tools( [ExtractResources], tool_choice="ExtractResources", **ainvoke_kwargs ).ainvoke([ SystemMessage( content=""" You need to extract the 3-5 most relevant resources from the following search results. """ ), *state["messages"], ToolMessage( tool_call_id=ai_message.tool_calls[0]["id"], content=f"Performed search: {search_results}" ) ], config) state["logs"] = [] await copilotkit_emit_state(config, state) ``` ### Error Message and Stack Trace (if applicable) _No response_ ### Description On cloud, the custom event is immediately sent. With the local setup via `langgraph up`, the events are sent with a delay and arrive in the wrong order (so the user can see the current status of the searches being performed) ### System Info CLI ------------------ > $ langgraph --version > LangGraph CLI, version 0.1.60 System Information ------------------ > OS: Darwin > OS Version: Darwin Kernel Version 23.0.0: Fri Sep 15 14:41:43 PDT 2023; root:xnu-10002.1.13~1/RELEASE_ARM64_T6000 > Python Version: 3.11.9 (main, Apr 2 2024, 08:25:04) [Clang 15.0.0 (clang-1500.3.9.4)] Package Information ------------------- > langchain_core: 0.3.19 > langchain: 0.3.7 > langsmith: 0.1.143 > langchain_openai: 0.2.9 > langchain_text_splitters: 0.3.2 > langgraph: 0.2.52 > langserve: 0.0.41 Other Dependencies ------------------ > aiohttp: 3.10.5 > async-timeout: 4.0.2 > fastapi: 0.115.0 > httpx: 0.27.2 > httpx-sse: 0.4.0 > jsonpatch: 1.33 > langgraph-checkpoint: 2.0.5 > langgraph-sdk: 0.1.36 > numpy: 1.26.4 > openai: 1.54.5 > orjson: 3.10.7 > packaging: 24.1 > pydantic: 2.9.2 > PyYAML: 6.0.2 > requests: 2.32.3 > requests-toolbelt: 1.0.0 > SQLAlchemy: 2.0.35 > sse-starlette: 2.1.3 > tenacity: 8.5.0 > tiktoken: 0.7.0 > typing-extensions: 4.12.2
yindo closed this issue 2026-02-20 17:36:43 -05:00
yindo commented 2026-02-20 17:36:43 -05:00
Author
Owner
Copy Link
Copy Source

@mme commented on GitHub (Dec 2, 2024):

Closing. The issue was that response = tavily_client.search(query) is a blocking call. Switching to an async call fixed the issue.

@mme commented on GitHub (Dec 2, 2024): Closing. The issue was that `response = tavily_client.search(query)` is a blocking call. Switching to an async call fixed the issue.
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
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#327
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?