vrr/qwen-code
2
0
Fork 0
mirror of https://github.com/QwenLM/qwen-code.git synced 2026-05-05 23:42:03 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 11

feat(review): add "fix these issues" follow-up tip

Browse source 
After review with unfixed findings (autofix declined/partial/N/A),
suggest "type fix these issues" so the LLM can interactively fix
each finding using the edit tool without re-running the review.

Follow-up tips now cover the complete post-review flow:
- Unfixed findings → "fix these issues"
- PR with findings → "post comments"
- Local all clear → "commit"

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
wenshao 2026-04-07 00:38:15 +08:00
parent 5ff22dcd4f
commit fe83b82dab
1 changed files with 6 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

9
packages/core/src/skills/bundled/review/SKILL.md
View file

@ -290,10 +290,13 @@ One of:
- **Request changes** — Has critical issues that need fixing
- **Comment** — Has suggestions but no blockers
Append a follow-up tip after the verdict based on the review target:
Append a follow-up tip after the verdict (and after Step 3.5 Autofix if applicable). Choose based on remaining state:
- **PR review with confirmed findings**: "Tip: type `post comments` to publish these findings as PR inline comments."
- **Local review with Approve verdict**: "Tip: type `commit` to commit your changes."
- **Unfixed findings remain** (autofix declined, partial, or not applicable): "Tip: type `fix these issues` to apply fixes interactively."
- **PR review with findings** (whether fixed or not): also append "Type `post comments` to publish findings as PR inline comments."
- **Local review, all clear** (Approve or all issues fixed): "Tip: type `commit` to commit your changes."
If the user responds with "fix these issues" (or similar intent), use the `edit` tool to fix each remaining finding interactively based on the suggested fixes from the review — do NOT re-run Steps 1-3.5.
If the user responds with "post comments" (or similar intent like "yes post them", "publish comments"), proceed directly to Step 4 using the findings already collected — do NOT re-run Steps 1-3.5.