fix(ci): make AI PR review bots concise and actionable#1601
Merged
imran-siddique merged 2 commits intoApr 29, 2026
Conversation
- Rewrite code-reviewer custom instructions to enforce TL;DR + table format - Reduce max-tokens from 4000 to 2000 for code-reviewer and test-generator - Add explicit word limits (200 words code-reviewer, 300 words test-generator) - Forbid essay-style output: no Conclusion sections, suggestion lists, or nits - Test-generator now lists only top 3-5 gaps instead of exhaustive file-by-file analysis - Update verdict parser to recognize 'Block' severity alongside 'Critical' - Add Review Output Style section to copilot-instructions.md for persistence Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
github-actions
Bot
added
documentation
🤖 AI Agent: code-reviewer — View detailsNo issues found. Clean change. |
🤖 AI Agent: docs-sync-checker — Docs SyncDocs Sync
|
🤖 AI Agent: breaking-change-detector — View detailsNo breaking changes detected. |
PR Review Summary
Verdict: |
🤖 AI Agent: security-scanner — View detailsNo security issues found. |
🤖 AI Agent: test-generator — View detailsTest coverage looks good. No gaps identified. |
MohammadHaroonAbuomar
pushed a commit
to MohammadHaroonAbuomar/agt-acs
that referenced
this pull request
Jun 1, 2026
- Rewrite code-reviewer custom instructions to enforce TL;DR + table format - Reduce max-tokens from 4000 to 2000 for code-reviewer and test-generator - Add explicit word limits (200 words code-reviewer, 300 words test-generator) - Forbid essay-style output: no Conclusion sections, suggestion lists, or nits - Test-generator now lists only top 3-5 gaps instead of exhaustive file-by-file analysis - Update verdict parser to recognize 'Block' severity alongside 'Critical' - Add Review Output Style section to copilot-instructions.md for persistence 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
Makes AI PR review bot output concise and scannable instead of verbose essay-style.
Changes
ai-pr-review.yml:
copilot-instructions.md:
Why
Bot reviews on PRs like #1594 produced 500+ word essays with multi-paragraph explanations, 8-item suggestion lists, and conclusion paragraphs. Contributors need scannable verdicts, not literature.
Type of Change