fix(review): skip Agent 5 in cross-repo mode, update token counts

Cross-repo lightweight mode has no local codebase — Agent 5 (build/test)
is pointless. Now launches 4 agents instead of 5 in cross-repo mode.

Updated token count tables in SKILL.md, user doc, and DESIGN.md:
same-repo = 7 LLM calls, cross-repo = 6.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
wenshao 2026-04-07 09:24:59 +08:00
parent 608550f2fc
commit c826c24f6e
3 changed files with 15 additions and 15 deletions

View file

@ -246,13 +246,13 @@ 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 3) | 0 | Shell commands only |
| 5 review agents (Step 4) | 5 | Run in parallel; Agent 5 runs build/test shell commands |
| Batch verification (Step 5) | 1 | Single agent verifies all findings at once |
| Reverse audit (Step 6) | 1 | Finds coverage gaps; findings skip verification |
| **Total** | **7** | Fixed, not proportional to finding count |
| Stage | LLM calls | Notes |
| ------------------------------- | ---------- | --------------------------------------------------- |
| Deterministic analysis (Step 3) | 0 | Shell commands only |
| Review agents (Step 4) | 5 (or 4) | Run in parallel; Agent 5 skipped in cross-repo mode |
| Batch verification (Step 5) | 1 | Single agent verifies all findings at once |
| Reverse audit (Step 6) | 1 | Finds coverage gaps; findings skip verification |
| **Total** | **7 or 6** | Same-repo: 7; cross-repo: 6 (no Agent 5) |
## What's NOT Flagged