feat: allow 'max' reasoning effort#261
Merged
Merged
Conversation
gpt-5.5 and the 'xhigh' choice already landed on pin-all-versions (via #254). This adds the remaining 'max' level so Claude Opus 4.x can run at max reasoning effort. reasoning_effort is passed straight through to LiteLLM, so no agent-side changes are required. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
zjwu0522
force-pushed
the
feat/reasoning-effort-xhigh-max
branch
from
f3f7155 to
db5bc7e
Compare
zjwu0522
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
openai/gpt-5.5(public OpenAI endpoint) inModelConfig.xhighandmaxas--reasoning-effortchoices.Why
We need to benchmark gpt-5.5 at
xhighand Claude Opus 4.x atmaxreasoning effort. The CLI previously capped the choices athigh.Notes
reasoning_effortis already passed straight through to LiteLLM (completion_kwargs["reasoning_effort"]), so no agent-side changes are required — this PR only widens the CLI allow-list and adds the public model entry. gpt-5's Responses API is handled internally by LiteLLM; no explicit Responses-API code is needed.🤖 Generated with Claude Code