fix(code-review): Calibrate config severity#319
Merged
Conversation
Treat high-impact public metadata and routing config breakages as high severity, even when found through tests or golden fixtures. Make eval severity expectations strict so future regressions cannot pass at the wrong level. Fixes #317 Co-Authored-By: GPT-5 <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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Calibrate the bundled
code-reviewskill so high-impact public metadata and routing config breakages are treated by blast radius, even when the evidence appears in tests or golden fixtures.This also makes eval severity expectations strict when a severity is specified, then adds a regression eval for the robots.txt prefix case from issue #317. A finding that catches
/mcpblocking/mcp.jsonnow has to land as high severity to pass.Fixes #317