Skip to content

feat(review): moderate-explanation style in findings prompt #527

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ajianaz merged 1 commit into from
Aug 25, 2026
Merged

feat(review): moderate-explanation style in findings prompt #527

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions src/engine/llm.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -226,6 +226,14 @@ Return a JSON array of objects with these fields:
- "body": string — detailed explanation with specific code reference
- "suggested_fix": string or null — optional fix suggestion

EXPLANATION STYLE (moderate-explanation principle, arXiv:2607.24601):
Keep each finding at moderate depth: severity + a short reason (1-3
sentences) + the specific code evidence it points to. Do NOT include
long reasoning chains, step-by-step derivations, or exhaustive
justifications — overly long explanations reduce agreement with the
finding without adding value. Trust the reader to reason from the
evidence.

If no issues are found, return: []

Return ONLY the JSON array. No markdown code fences, no explanation, no conversational text.
Expand Down
Loading