mirror of
https://github.com/QwenLM/qwen-code.git
synced 2026-04-28 11:41:04 +00:00
docs: update user doc with token efficiency, fix follow-up table
- Add Token Efficiency section showing fixed 7 LLM calls breakdown - Fix follow-up table: "fix these issues" is local-only (worktree cleaned up after PR review) - Update PR description with worktree, batch verification, cross-model review, PR comment dedup, and expanded test plan Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
parent
e65e5bd353
commit
9b9bccd27d
1 changed files with 20 additions and 5 deletions
|
|
@ -129,11 +129,13 @@ Or, after running `/review 123`, type `post comments` to publish findings withou
|
|||
|
||||
After the review, context-aware tips appear as ghost text. Press Tab to accept:
|
||||
|
||||
| State after review | Tip | What happens |
|
||||
| ----------------------- | ------------------ | --------------------------------------- |
|
||||
| Unfixed findings remain | `fix these issues` | LLM interactively fixes each finding |
|
||||
| PR review with findings | `post comments` | Posts PR inline comments (no re-review) |
|
||||
| Local review, all clear | `commit` | Commits your changes |
|
||||
| State after review | Tip | What happens |
|
||||
| ---------------------------------- | ------------------ | --------------------------------------- |
|
||||
| Local review with unfixed findings | `fix these issues` | LLM interactively fixes each finding |
|
||||
| PR review with findings | `post comments` | Posts PR inline comments (no re-review) |
|
||||
| Local review, all clear | `commit` | Commits your changes |
|
||||
|
||||
Note: `fix these issues` is only available for local reviews. For PR reviews, use Autofix (Step 3.5) — the worktree is cleaned up after the review, so post-review interactive fixing is not possible.
|
||||
|
||||
## Project Review Rules
|
||||
|
||||
|
|
@ -209,6 +211,19 @@ When code changes modify exported functions, classes, or interfaces, the review
|
|||
|
||||
For large diffs (>10 modified symbols), analysis prioritizes functions with signature changes.
|
||||
|
||||
## Token Efficiency
|
||||
|
||||
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 |
|
||||
|
||||
## What's NOT Flagged
|
||||
|
||||
The review intentionally excludes:
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue