Include low-severity findings in PR Review benchmarks - #885
Open
Wenjie Fan (gggdttt) wants to merge 1 commit into
Open
Wenjie Fan (gggdttt) wants to merge 1 commit into
Wenjie Fan (gggdttt) wants to merge 1 commit into
Conversation
Apply the configured severity to both engine gates and default to Low so low-severity gold findings remain eligible. Bump the benchmark to 0.14.0 for the changed review scope. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Sun Haoran (haoranpb)
added a commit
that referenced
this pull request
Sep 15, 2026
Force GitHub Actions to index an experiment ref with the exact PR #885 tree. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Default the BC PR Review benchmark to
Lowinstead ofMedium, so its review scope includes low-severity gold findings.Pass the configured floor to both
MINIMUM_SEVERITYandAGENT_MINIMUM_SEVERITY. Previously, the adapter set only the latter, leaving the pinned engine's prompt and knowledge-backed findings at its defaultMediumfloor. Both gates now honor the benchmark configuration or explicit local override, regardless of inherited severity environment variables.Update the CLI help and code-review documentation, and cover the default, explicit overrides, ambient environment values, and Low output mapping with regression tests. Bump BC-Bench from
0.13.0to0.14.0because the default review behavior changes.Scope
No changes to the dataset, scoring, historical results, or engine/BCQuality pins. Production BC-ALAgents configuration is handled separately. This PR does not claim a measured score improvement.