Add reasoningEffort/reasoning_effort parameter support#165
Merged
Conversation
Implements support for the `reasoningEffort` parameter for o-series models like o3-mini, as requested in issue #132. Changes: - TypeScript: Added `reasoningEffort` to LLMArgs type - TypeScript: Import and use OpenAI's ReasoningEffort type - Python: Added `reasoning_effort` parameter to LLMClassifier - Both: Parameter flows through to OpenAI API as `reasoning_effort` - Both: Added comprehensive test coverage The parameter accepts values: "minimal", "low", "medium", "high", or null and allows fine-grained control over model reasoning capabilities. Fixes #132 Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
ibolmo
approved these changes
Jan 14, 2026
Collaborator
ibolmo
left a comment
ibolmo
left a comment
There was a problem hiding this comment.
approving since the _enabled and _budget may be added later
- Add reasoningEnabled and reasoningBudget optional parameters to TypeScript LLMArgs - Add reasoning_enabled and reasoning_budget optional parameters to Python LLMClassifier - These parameters support Braintrust AI proxy's extended reasoning capabilities - Particularly useful for Claude (via reasoning_enabled/reasoning_budget) and Gemini models - Change ReasoningEffort import to use type-only import for better TypeScript optimization - Add comprehensive tests for new parameters in both TypeScript and Python Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Braintrust eval reportAutoevals (reasoning-effort-support-1768445948)
|
Braintrust eval report
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Implements support for the
reasoningEffortparameter for o-series models like o3-mini, as requested in issue #132.Changes:
reasoningEffortto LLMArgs typereasoning_effortparameter to LLMClassifierreasoning_effortThe parameter accepts values: "minimal", "low", "medium", "high", or null and allows fine-grained control over model reasoning capabilities.
Fixes #132