Skip to content

fix: sonnet 3.5 should not report support of reasoning_effort #12836

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

Closed

Conversation

aholmberg
Copy link
Contributor

fixes #12833

  • I have Added testing in the tests/litellm/ directory, Adding at least 1 test is a hard requirement - see details
  • I have added a screenshot of my new test passing locally
image - [x] My PR passes all unit tests on [`make test-unit`](https://docs.litellm.ai/docs/extras/contributing_code) - [x] My PR's scope is as isolated as possible, it only solves 1 specific problem

Type

🐛 Bug Fix
✅ Test

Copy link

vercel bot commented Jul 21, 2025

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

Name Status Preview Comments Updated (UTC)
litellm ✅ Ready (Inspect) Visit Preview 💬 Add feedback Jul 21, 2025 9:28pm

Copy link
Contributor

@ishaan-jaff ishaan-jaff left a comment

Choose a reason for hiding this comment

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

lgtm, one change

"web_search_options",
]

if "claude-3-7-sonnet" in model or supports_reasoning(
Copy link
Contributor

Choose a reason for hiding this comment

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

please keep the "if "claude-3-7-sonnet" LOC here

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Doesn't that basically override what someone might have configured with supports_reasoning in their config file?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

This change as-is retains the default behavior because that model has "supports_reasoning": true in the config map.

"supports_reasoning": true

@aholmberg
Copy link
Contributor Author

fix with no test cherry-picked to #12847

@aholmberg aholmberg closed this Jul 22, 2025
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.

[Bug]: Sonnet 3.5 incorrectly reporting support of reasoning_effort
2 participants