evalbuff: Codebuff SDK integration, direct LLM API, and quality improvements#486
Merged
evalbuff: Codebuff SDK integration, direct LLM API, and quality improvements#486
Conversation
Replace CLI spawning with Codebuff SDK for agent execution and Vercel AI SDK for LLM calls (5x faster prompt generation). Add base2-free-evals agent with noAskUser. Use local git clones with hardlinks for near-instant repo setup. Filter trivial commits, use average reviewer scores, inline traces into doc writer prompts, and add adaptive improvement thresholds. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Delete all docs/patterns/** files generated by evalbuff — they overfit to specific commits rather than teaching generalizable principles. Simplify compareScores now that parallelism is always 5. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Fixes RunState type mismatches: sessionState: null → undefined, fake session state objects cast as any, StreamStatus narrowing. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
CodebuffClient+CodebuffRunner) instead of spawning CLI processes, with trace storage as JSON lines ofPrintModeEventstepsbase2-free-evalsagent (free tier +noAskUser: true) for evalbuff runs@ai-sdk/anthropic+ai), ~2-5x fasterclaude-sonnet-4-6) as default model for LLM calls, no maxOutputTokens or temperature overridesTest plan
tsc --noEmitpasses for evalbuff and root🤖 Generated with Claude Code