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

create_agent In "astream" with stream_mode="messages" does not output tokens incrementally. #1060

New Issue
Closed
opened 2026-02-20 17:42:55 -05:00 by yindo · 3 comments
yindo commented 2026-02-20 17:42:55 -05:00
Owner
Copy Link
Copy Source

Originally created by @nswsnb on GitHub (Nov 14, 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

import asyncio

from langchain.agents import create_agent
from langchain_openai import ChatOpenAI


modelOpenAI = ChatOpenAI(
        model="***",
        base_url="***",
        api_key="***", 
    )

agent = create_agent(
    model=modelOpenAI,
    system_prompt="You are a helpful assistant",

)

async def main():
    async for token, metadata in agent.astream(
            {"messages": [{"role": "user", "content": "hello who are you?"}]},
            stream_mode="messages",
            stream_subgraphs=True
    ):
        print(token.content)


if __name__ == '__main__':
    asyncio.run(main())

Error Message and Stack Trace (if applicable)

Output:
Hello! I’m your AI assistant, here to help answer your questions, provide information, or assist with tasks. You can think of me as a friendly digital helper. How can I assist you today? 😊

Description

I'm trying to use create_agent in astream with stream_mode="messages", but the output is not generated token by token.

System Info

version:

Image
Originally created by @nswsnb on GitHub (Nov 14, 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 import asyncio from langchain.agents import create_agent from langchain_openai import ChatOpenAI modelOpenAI = ChatOpenAI( model="***", base_url="***", api_key="***", ) agent = create_agent( model=modelOpenAI, system_prompt="You are a helpful assistant", ) async def main(): async for token, metadata in agent.astream( {"messages": [{"role": "user", "content": "hello who are you?"}]}, stream_mode="messages", stream_subgraphs=True ): print(token.content) if __name__ == '__main__': asyncio.run(main()) ``` ### Error Message and Stack Trace (if applicable) ```shell Output: Hello! I’m your AI assistant, here to help answer your questions, provide information, or assist with tasks. You can think of me as a friendly digital helper. How can I assist you today? 😊 ``` ### Description I'm trying to use create_agent in astream with stream_mode="messages", but the output is not generated token by token. ### System Info version: <img width="642" height="680" alt="Image" src="https://github.com/user-attachments/assets/a9fe9581-8ffa-4249-aa3d-5992de559add" />
yindo added the bugpending labels 2026-02-20 17:42:55 -05:00
yindo closed this issue 2026-02-20 17:42:55 -05:00
yindo commented 2026-02-20 17:42:56 -05:00
Author
Owner
Copy Link
Copy Source

@yashsonawane15 commented on GitHub (Nov 15, 2025):

I think this should be in the langchain repository instead of langgraph.

@yashsonawane15 commented on GitHub (Nov 15, 2025): I think this should be in the langchain repository instead of langgraph.
yindo commented 2026-02-20 17:42:56 -05:00
Author
Owner
Copy Link
Copy Source

@le-codeur-rapide commented on GitHub (Nov 16, 2025):

Hello @nswsnb I ran your code and it worked as expected:
I just replaced print(token.content) by print(token.content + "|", end="") and got output:

|Hello|!| I'm| an| AI| language| model| here| to| assist| you|.| How| can| I| help| today|?||||

I am using same version of langgraph and langchain as you 1.0.3 and 1.0.7

What model are you using ?

@le-codeur-rapide commented on GitHub (Nov 16, 2025): Hello @nswsnb I ran your code and it worked as expected: I just replaced `print(token.content)` by `print(token.content + "|", end="")` and got output: ``` |Hello|!| I'm| an| AI| language| model| here| to| assist| you|.| How| can| I| help| today|?|||| ``` I am using same version of langgraph and langchain as you 1.0.3 and 1.0.7 What model are you using ?
yindo commented 2026-02-20 17:42:56 -05:00
Author
Owner
Copy Link
Copy Source

@casparb commented on GitHub (Nov 24, 2025):

Hi @nswsnb, I am closing as I cannot reproduce. Your code is functioning as expected. If you're still having issues please be more descriptive about what's going wrong.

@casparb commented on GitHub (Nov 24, 2025): Hi @nswsnb, I am closing as I cannot reproduce. Your code is functioning as expected. If you're still having issues please be more descriptive about what's going wrong.
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#1060
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?