Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add reasoning_effort parameter to ModelSettings Fixes #189 #235

Open
wants to merge 7 commits into
base: main
Choose a base branch
from

Conversation

askmuhsin
Copy link

Description

This PR adds the reasoning_effort parameter to ModelSettings to allow configuration of reasoning effort as described in the OpenAI API docs.

Changes

  • Added reasoning_effort parameter to ModelSettings class with Literal type for "low", "medium", "high" values
  • Updated the resolve method to include the new parameter
  • Added appropriate documentation

Related Issues

Fixes #189

Testing

  • Verified the parameter can be set and passed through the resolve method
  • Ran linting and type checking.

Copy link
Collaborator

@rm-openai rm-openai left a comment

Choose a reason for hiding this comment

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

Thank you! Can you also add this to openai_responses.py and openai_chatcompletions.py? Otherwise it's not actually used.

@askmuhsin askmuhsin requested a review from rm-openai March 20, 2025 04:28
@askmuhsin
Copy link
Author

hi @rm-openai the additions have been made, thank you!

  • openai_responses.py
  • openai_chatcompletions.py
  • model_settings.py

@rm-openai
Copy link
Collaborator

Typechecking is failing I dont think Response has reasonign_effort, it has reasoning

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Allow configuration of Reasoning_Effort on modelSettings
3 participants