Add reasoning effort to OpenAI CUA and Claude Computer Use - #124
Merged
Conversation
Expose the new reasoningEffort request field on both agents, matching the API and the existing Grok/Meta Computer Use pattern. Co-authored-by: nikhil <nikhil@metlo.com>
NikhilShahi
marked this pull request as ready for review
September 10, 2026 18:01
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
There was a problem hiding this comment.
NikhilShahi has reached the 50-credit limit for trial accounts. To continue receiving code reviews, upgrade your plan.
Co-authored-by: nikhil <nikhil@metlo.com>
There was a problem hiding this comment.
NikhilShahi has reached the 50-credit limit for trial accounts. To continue receiving code reviews, upgrade your plan.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Add the new
reasoning_effortrequest field to OpenAI CUA and Claude Computer Use so the Python SDK can send the samereasoningEffortvalues the API now accepts.Changes
CuaReasoningEffort(none,low,medium,high,xhigh,max) andClaudeComputerUseReasoningEffort(low,medium,high,xhigh,max)reasoning_efforton both TypedDict and legacy Pydantic start-task paramsValidation
poetry run pytest tests --ignore=tests/sandbox/e2e— 343 passed, 4 skippedpoetry run ruff checkon the changed files — all checks passeddump_requestserializesreasoning_efforttoreasoningEffortfor both agentsThe SDKs only declare the allowed values. Model-specific combinations are validated server-side.