fix(provider): support Kimi K3 reasoning effort#37514
Closed
BiuBiu2015 wants to merge 1 commit into
Closed
Conversation
Kimi K3 models using Anthropic-compatible endpoint derive adaptive low/high/max variants from models.dev, preventing budget-token fallback. Includes unit and provider regression coverage.
github-actions
Bot
added
needs:compliance
Contributor
|
Thanks for updating your PR! It now meets our contributing guidelines. 👍 |
Author
|
Superseded by #37519, which fixes the issue with a more general reasoning-options implementation. |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Issue for this PR
Closes #37418
Type of change
What does this PR do?
Kimi K3 declares
low,high, andmaxeffort levels in models.dev, but the Anthropic-compatible provider did not recognize thekimi-k3family. The effort conversion returned no variants and OpenCode fell back to Anthropic budget-token variants.This change maps Kimi K3 effort metadata to adaptive thinking options so the Anthropic SDK sends
thinking.type = adaptivewith the selectedoutput_config.effort. It also adds transform and provider regression coverage for all three levels.How did you verify your code works?
cd packages/opencode && bun test test/provider/transform.test.ts test/provider/provider.test.ts: 445 passed, 0 failedcd packages/opencode && bun run typecheck: passedlow,high, andmax; each request used adaptive thinking with the matching effort and was acceptedScreenshots / recordings
Not applicable; this change only affects provider request options.
Checklist