fix: teach grippy LLM to use finding_type note for praise#92
Merged
Conversation
Add Step 4 (Classify Finding Types) to system-core.md prompt chain. Without explicit guidance, the LLM emits all findings as "issue" even when describing good practices, causing praise to tank scores. Coding-Agent: claude-code Model: claude-opus-4-6
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
Contributor
✅ Grippy Review — PASSScore: 100/100 | Findings: 0 Commit: 34cda50 |
Navi Bot (project-navi-bot)
approved these changes
Apr 5, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
system-core.mdprompt chain"issue"for problems,"note"for positive observationsBug
PR #91 added
finding_typeto the schema and scoring logic, but the LLM wasn't told when to use it. Without prompt guidance, all findings remained"issue"— praise still tanked scores. PR #90 scored 68/100 FAIL on the rebased run despite all findings being compliments.Test plan