feat: two-phase parallel candidate evaluator and batch_refine API#2125
Closed
KRRT7 wants to merge 3 commits into
Closed
feat: two-phase parallel candidate evaluator and batch_refine API#2125KRRT7 wants to merge 3 commits into
KRRT7 wants to merge 3 commits into
Conversation
This was referenced May 7, 2026
Closed
Phase 1 (concurrent): behavioral correctness tests run in parallel. Failed candidates release their worktree slot immediately. Phase 2 (sequential): only passing candidates get benchmarked, one at a time, for accurate timing without CPU contention. EvalFailure carries test diffs for repair context.
Adds the API method for submitting multiple candidates for refinement in a single request — used by the parallel evaluator to dispatch refinement/repair after evaluation completes.
dataclass(slots=True) requires Python 3.10+.
KRRT7
force-pushed
the
parallel-eval/02-evaluator
branch
from
ec123fd to
22736d3
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
the core evaluation algorithm. adds:
ParallelCandidateEvaluatorwith two-phase design: Phase 1 runs behavioral correctness tests concurrently (one worktree slot per candidate), Phase 2 runs benchmarks sequentially (no CPU contention for accurate timing)batch_refineendpoint onAiServiceClientdepends on #2124 (infrastructure).
this is PR 2/4 in a stack. review and merge in order: