reimpl: prevent orchestrator re-evaluation#378
Merged
Nicola Franco (franconicola) merged 2 commits intoMay 22, 2026
Merged
Conversation
Add _already_evaluated guard to run_full_evaluation that detects when input data already carries evaluation scores (eval_jb, eval_hb, best_score, etc.) and skips redundant re-evaluation steps 1-6 while preserving metrics summary generation (steps 7-8). This fixes the AdvPrefix bug where aggregated rows lack the completion field, causing judges to evaluate empty strings and overwrite correct statuses with FAILED_JAILBREAK. Fixes #342
Nicola Franco (franconicola)
temporarily deployed
to
reimpl/prevent-orchestrator-re-evaluation - Docs PR #378
Render
Destroyed
Codecov Report❌ Patch coverage is
📢 Thoughts on this report? Let us know! |
Nicola Franco (franconicola)
deleted the
reimpl/prevent-orchestrator-re-evaluation
branch
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add _already_evaluated guard to run_full_evaluation that detects when input data already carries evaluation scores (eval_jb, eval_hb, best_score, etc.) and skips redundant re-evaluation steps 1-6 while preserving metrics summary generation (steps 7-8).
Fixes #342