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

No custom messages in stream_mode='custom' in agent called by Supervisor #825

New Issue
Closed
opened 2026-02-20 17:41:57 -05:00 by yindo · 2 comments
yindo commented 2026-02-20 17:41:57 -05:00
Owner
Copy Link
Copy Source

Originally created by @adil2604 on GitHub (Jul 21, 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 langchain_openai import ChatOpenAI
from langgraph.prebuilt import create_react_agent
from langgraph_supervisor import create_supervisor
from langgraph.config import get_stream_writer

def book_hotel(hotel_name: str):
    """Book a hotel"""
    writer = get_stream_writer()
    writer("Booking hotel")
    return f"Successfully booked a stay at {hotel_name}."

def book_flight(from_airport: str, to_airport: str):
    """Book a flight"""
    writer = get_stream_writer()
    writer("Booking flight")
    return f"Successfully booked a flight from {from_airport} to {to_airport}."

flight_assistant = create_react_agent(
    model=ChatOpenAI(model='gpt-4.1-mini'),
    tools=[book_flight],
    prompt="You are a flight booking assistant",
    name="flight_assistant"
)

hotel_assistant = create_react_agent(
    model=ChatOpenAI(model='gpt-4.1-mini'),
    tools=[book_hotel],
    prompt="You are a hotel booking assistant",
    name="hotel_assistant"
)

supervisor = create_supervisor(
    agents=[flight_assistant, hotel_assistant],
    model=ChatOpenAI(model="gpt-4o"),
    prompt=(
        "You manage a hotel booking assistant and a"
        "flight booking assistant. Assign work to them."
    )
).compile()

for chunk in supervisor.stream(
    {
        "messages": [
            {
                "role": "user",
                "content": "book a flight from BOS to JFK and a stay at McKittrick Hotel"
            }
        ]
    },
    stream_mode=['debug', 'custom']
):
    print(chunk)
    print("\n")

Error Message and Stack Trace (if applicable)

Description

I wanted to receive real time updates from the tools, but if the agent is called by the supervisor, then there are no custom messages in the streaming
When I call agent directly, there are custom data in streaming

System Info

System Information

OS: Darwin
OS Version: Darwin Kernel Version 24.3.0: Thu Jan 2 20:31:46 PST 2025; root:xnu-11215.81.4~4/RELEASE_ARM64_T8132
Python Version: 3.11.4 (main, Jul 5 2023, 08:40:20) [Clang 14.0.6 ]

Package Information

langchain_core: 0.3.69
langchain: 0.1.20
langchain_community: 0.0.38
langsmith: 0.3.45
langchain_anthropic: 0.1.13
langchain_chroma: 0.1.4
langchain_google_vertexai: 1.0.4
langchain_openai: 0.3.27
langchain_robocorp: 0.0.8
langchain_text_splitters: 0.0.2
langgraph_api: 0.2.51
langgraph_cli: 0.3.3
langgraph_license: Installed. No version info available.
langgraph_runtime: Installed. No version info available.
langgraph_runtime_inmem: 0.2.1
langgraph_sdk: 0.1.70
langgraph_supervisor: 0.0.27

Optional packages not installed

langserve

Originally created by @adil2604 on GitHub (Jul 21, 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 langchain_openai import ChatOpenAI from langgraph.prebuilt import create_react_agent from langgraph_supervisor import create_supervisor from langgraph.config import get_stream_writer def book_hotel(hotel_name: str): """Book a hotel""" writer = get_stream_writer() writer("Booking hotel") return f"Successfully booked a stay at {hotel_name}." def book_flight(from_airport: str, to_airport: str): """Book a flight""" writer = get_stream_writer() writer("Booking flight") return f"Successfully booked a flight from {from_airport} to {to_airport}." flight_assistant = create_react_agent( model=ChatOpenAI(model='gpt-4.1-mini'), tools=[book_flight], prompt="You are a flight booking assistant", name="flight_assistant" ) hotel_assistant = create_react_agent( model=ChatOpenAI(model='gpt-4.1-mini'), tools=[book_hotel], prompt="You are a hotel booking assistant", name="hotel_assistant" ) supervisor = create_supervisor( agents=[flight_assistant, hotel_assistant], model=ChatOpenAI(model="gpt-4o"), prompt=( "You manage a hotel booking assistant and a" "flight booking assistant. Assign work to them." ) ).compile() for chunk in supervisor.stream( { "messages": [ { "role": "user", "content": "book a flight from BOS to JFK and a stay at McKittrick Hotel" } ] }, stream_mode=['debug', 'custom'] ): print(chunk) print("\n") ``` ### Error Message and Stack Trace (if applicable) ```shell ``` ### Description I wanted to receive real time updates from the tools, but if the agent is called by the supervisor, then there are no custom messages in the streaming When I call agent directly, there are custom data in streaming ### System Info System Information ------------------ > OS: Darwin > OS Version: Darwin Kernel Version 24.3.0: Thu Jan 2 20:31:46 PST 2025; root:xnu-11215.81.4~4/RELEASE_ARM64_T8132 > Python Version: 3.11.4 (main, Jul 5 2023, 08:40:20) [Clang 14.0.6 ] Package Information ------------------- > langchain_core: 0.3.69 > langchain: 0.1.20 > langchain_community: 0.0.38 > langsmith: 0.3.45 > langchain_anthropic: 0.1.13 > langchain_chroma: 0.1.4 > langchain_google_vertexai: 1.0.4 > langchain_openai: 0.3.27 > langchain_robocorp: 0.0.8 > langchain_text_splitters: 0.0.2 > langgraph_api: 0.2.51 > langgraph_cli: 0.3.3 > langgraph_license: Installed. No version info available. > langgraph_runtime: Installed. No version info available. > langgraph_runtime_inmem: 0.2.1 > langgraph_sdk: 0.1.70 > langgraph_supervisor: 0.0.27 Optional packages not installed ------------------------------- > langserve
yindo added the bugpending labels 2026-02-20 17:41:57 -05:00
yindo closed this issue 2026-02-20 17:41:57 -05:00
yindo commented 2026-02-20 17:41:57 -05:00
Author
Owner
Copy Link
Copy Source

@shivampkumar commented on GitHub (Jul 29, 2025):

I Started facing the same after making the following upgrades:

langgraph=^0.4.10 -> langgraph = "^0.6.0"
langgraph-supervisor = "^0.0.27" -> langgraph-supervisor = "^0.0.29"

@shivampkumar commented on GitHub (Jul 29, 2025): I Started facing the same after making the following upgrades: langgraph=^0.4.10 -> langgraph = "^0.6.0" langgraph-supervisor = "^0.0.27" -> langgraph-supervisor = "^0.0.29"
yindo commented 2026-02-20 17:41:57 -05:00
Author
Owner
Copy Link
Copy Source

@adil2604 commented on GitHub (Jul 31, 2025):

Resolved

Need set to subgraphs=True flag while streaming

async for message in router_workflow.astream(
    state,
    config,
    stream_mode=["updates", "custom"],
    subgraphs=True,
):
    logger.info(f"Message: {message}")
@adil2604 commented on GitHub (Jul 31, 2025): Resolved Need set to `subgraphs=True` flag while streaming ``` async for message in router_workflow.astream( state, config, stream_mode=["updates", "custom"], subgraphs=True, ): logger.info(f"Message: {message}") ```
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#825
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?