Skip to content

Conversation

HERIUN
Copy link

@HERIUN HERIUN commented Oct 1, 2025

support for including reasoning_content from model responses in AIMessage

it's simliar with pr : #32982 ,
same as #32859

I use GPT_OSS_20B with llama-cpp with local server like

llama-server -m "$llm_model_path" \
    --host "localhost" \
    --port "$llm_port" \
    --n-cpu-moe 9 \
    --n-gpu-layers 999 \
    -c 0 \
    -n -1 \
    -fa on \
    --jinja \
    --chat-template-kwargs '{"reasoning_effort": "high"}'

and make llm and agent like

from langchain.chat_models import init_chat_model
from langgraph.prebuilt import create_react_agent

llm= init_chat_model(
                model = model_path,
                model_provider = "openai",
                base_url = f"http://{host}:{port}/v1",
                api_key = "EMPTY", # no auth
            )
agent = create_react_agent(
                llm, 
                tools = self.available_tools,
            )

It could be open_ai right?

@ccurme

Add support for including reasoning_content from model responses in AIMessage
Copy link

vercel bot commented Oct 1, 2025

The latest updates on your projects. Learn more about Vercel for GitHub.

1 Skipped Deployment
Project Deployment Preview Comments Updated (UTC)
langchain Ignored Ignored Preview Oct 1, 2025 8:01am

@github-actions github-actions bot added the integration Related to a provider partner package integration label Oct 1, 2025
@HERIUN HERIUN changed the title feat(openai) : support for including reasoning_content from model responses in AIMessage feat(openai) : support for including reasoning_content from model responses Oct 1, 2025
@github-actions github-actions bot removed the integration Related to a provider partner package integration label Oct 1, 2025
@HERIUN HERIUN changed the title feat(openai) : support for including reasoning_content from model responses feat(openai): support for including reasoning_content from model responses Oct 1, 2025
@github-actions github-actions bot added feature integration Related to a provider partner package integration labels Oct 1, 2025
Copy link

codspeed-hq bot commented Oct 1, 2025

CodSpeed Instrumentation Performance Report

Merging #33180 will not alter performance

Comparing HERIUN:patch-1 (d2b30bc) with master (aac6983)1

Summary

✅ 6 untouched
⏩ 15 skipped2

Footnotes

  1. No successful run was found on master (34f8031) during the generation of this report, so aac6983 was used instead as the comparison base. There might be some changes unrelated to this pull request in this report.

  2. 15 benchmarks were skipped, so the baseline results were used instead. If they were deleted from the codebase, click here and archive them to remove them from the performance reports.

@github-actions github-actions bot removed the integration Related to a provider partner package integration label Oct 1, 2025
Copy link
Collaborator

@ccurme ccurme left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Closing as duplicated with #32982 (let me know if I misunderstood your intent with this)

@ccurme ccurme closed this Oct 1, 2025
@HERIUN
Copy link
Author

HERIUN commented Oct 2, 2025

#32982 only care OpenRouter case.. this pr and #32859 care general invoke, ainvoke case i think @ccurme

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants