vrr/qwen-code
2
0
Fork 0
mirror of https://github.com/QwenLM/qwen-code.git synced 2026-04-28 11:41:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 13

fix(review): address 5 Copilot comments

Browse source 
- Add error handling for git fetch and gh pr view failures in Step 1
- Skip worktree cleanup on autofix commit/push failure (preserve
  uncommitted fixes for manual recovery)
- Fix Agent 5 counting: it's 1 of the 5 LLM agents (not a separate
  zero-cost stage). Remove misleading "zero LLM" annotation and
  duplicate row from token efficiency table.
- Reverse audit skip-verification already implemented (comment #53
  was stale)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
wenshao 2026-04-07 03:42:20 +08:00
parent ccaab1779b
commit 09c95c44c8
2 changed files with 12 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

17
docs/users/features/code-review.md
View file

@ -37,7 +37,7 @@ Run deterministic analysis (linter, typecheck) [zero LLM cost]
|-- Agent 2: Code Quality
|-- Agent 3: Performance & Efficiency
|-- Agent 4: Undirected Audit
'-- Agent 5: Build & Test [zero LLM cost]
'-- Agent 5: Build & Test (runs shell commands)
|
Deduplicate --> Batch verify --> Aggregate [1 LLM call]
|
@ -231,14 +231,13 @@ For large diffs (>10 modified symbols), analysis prioritizes functions with sign
The review pipeline uses a fixed number of LLM calls regardless of how many findings are produced:
| Stage | LLM calls | Notes |
| --------------------------------- | --------- | ------------------------------------------ |
| Deterministic analysis (Step 1.5) | 0 | Shell commands only |
| Build & test (Agent 5) | 0 | Shell commands only |
| 5 review agents (Step 2) | 5 | Run in parallel |
| Batch verification (Step 2.5) | 1 | Single agent verifies all findings at once |
| Reverse audit (Step 2.6) | 1 | Finds coverage gaps |
| **Total** | **7** | Fixed, not proportional to finding count |
| Stage | LLM calls | Notes |
| --------------------------------- | --------- | ------------------------------------------------------- |
| Deterministic analysis (Step 1.5) | 0 | Shell commands only |
| 5 review agents (Step 2) | 5 | Run in parallel; Agent 5 runs build/test shell commands |
| Batch verification (Step 2.5) | 1 | Single agent verifies all findings at once |
| Reverse audit (Step 2.6) | 1 | Finds coverage gaps; findings skip verification |
| **Total** | **7** | Fixed, not proportional to finding count |
## What's NOT Flagged