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

[nswsnb]

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

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:

[yashsonawane15]

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

[le-codeur-rapide]

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 ?

[casparb]

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.