Skip to content

feat(review): adopt a round-aware convergence posture for posted findings #9118

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
wenshao merged 15 commits into from
Aug 15, 2026
Merged

feat(review): adopt a round-aware convergence posture for posted findings #9118

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
15 commits
Select commit Hold shift + click to select a range
2794cef
feat(review): adopt a round-aware convergence posture for posted find…
wenshao Aug 14, 2026
0b1ad5b
chore(review): regenerate settings.schema.json for review.severityFloor
wenshao Aug 14, 2026
fae401a
fix(review): close the round-1 review findings on the convergence pos…
wenshao Aug 14, 2026
60c9eb1
fix(review): carry deferredCount through the persisted verdict
wenshao Aug 14, 2026
2b6b229
test(review): pin deferredCount passthrough and the pre-posture defau…
wenshao Aug 14, 2026
defc687
fix(review): close the round-2 findings — deterministic deferrals and…
wenshao Aug 14, 2026
8355d2a
fix(review): close the round-3 findings — source-position tags, a Cri…
wenshao Aug 14, 2026
4d171d9
fix(review): close the round-4 findings — licence the deferral channe…
wenshao Aug 14, 2026
1524c6d
fix(review): close the round-5 findings — carry the floor unresolved,…
wenshao Aug 14, 2026
df6dd45
fix(review): close the round-6 Criticals — relocate stray Criticals, …
wenshao Aug 14, 2026
662d98f
fix(review): close the round-7 findings — kebab paths, the equals-for…
wenshao Aug 15, 2026
b29a494
fix(review): close the round-8 Criticals — one entry grammar, one res…
wenshao Aug 15, 2026
6118109
feat(review): type the deferral channel — carry the fields, stop re-p…
wenshao Aug 15, 2026
58aae46
Merge branch 'main' into feat/review-convergence-posture
wenshao Aug 15, 2026
b0b7abb
fix(review): bound the relocation exit and dedupe rescued targets by …
wenshao Aug 15, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 6 additions & 5 deletions docs/users/configuration/settings.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -109,11 +109,12 @@ Settings are organized into categories. Most settings should be placed within th

#### review

| Setting | Type | Description | Default |
| -------------------- | ------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- |
| `review.attribution` | boolean | Append the attribution footer naming the model and CLI version (e.g. `_— qwen3-coder via Qwen Code /review (v0.21.2)_`) to review bodies and inline comments posted by `/review`. Disable to post reviews without AI attribution. With the footer off, presubmit duplicate detection still recognizes earlier posts by the same GitHub account, but footer-less posts from other accounts escape it. | `true` |
| `review.effort` | enum | Default effort for `/review` when `--effort` is not given: `"low"`, `"medium"`, `"high"`, or `"auto"` (the built-in rule: high for PRs, medium for local changes). An explicit `--effort` wins; an effective `--comment` still forces high and `--fix` still floors at medium. | `"auto"` |
| `review.comment` | boolean | Treat every PR `/review` as if `--comment` was passed: findings are posted to the pull request without the flag. The post still binds to the PR named in the invocation. Enable only if you always want reviews published. | `false` |
| Setting | Type | Description | Default |
| ---------------------- | ------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- |
| `review.attribution` | boolean | Append the attribution footer naming the model and CLI version (e.g. `_— qwen3-coder via Qwen Code /review (v0.21.2)_`) to review bodies and inline comments posted by `/review`. Disable to post reviews without AI attribution. With the footer off, presubmit duplicate detection still recognizes earlier posts by the same GitHub account, but footer-less posts from other accounts escape it. | `true` |
| `review.effort` | enum | Default effort for `/review` when `--effort` is not given: `"low"`, `"medium"`, `"high"`, or `"auto"` (the built-in rule: high for PRs, medium for local changes). An explicit `--effort` wins; an effective `--comment` still forces high and `--fix` still floors at medium. | `"auto"` |
| `review.comment` | boolean | Treat every PR `/review` as if `--comment` was passed: findings are posted to the pull request without the flag. The post still binds to the PR named in the invocation. Enable only if you always want reviews published. | `false` |
| `review.severityFloor` | enum | The lowest severity a PR `/review` posts when `--severity-floor` is not given: `"auto"` (the round-adaptive default — Suggestions post through round 5, only Criticals from round 6, with otherwise-postable high-confidence Suggestions recorded and deferred, and rounds 2–5 deferring new Suggestions on code unchanged since the previous round; low-confidence and Nice-to-have findings stay terminal-only), `"critical"` (that posture from round 1), or `"suggestion"` (Suggestions post at every round; turns the convergence posture off). Non-PR targets have no rounds and ignore this. | `"auto"` |

@wenshao wenshao Aug 15, 2026

Copy link
Copy Markdown
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

[Nice to have] The user-facing feature doc never learns about any of this.

docs/users/features/code-review.md is the page that documents /review's flags (--effort, --comment, --fix, each with its own section and its forcing rules) and it is untouched by this PR. Two user-visible things are therefore undocumented where a user would look for them:

  • the new --severity-floor critical|suggestion|auto flag (and that it warns-and-is-ignored on non-PR targets, mirroring --comment);
  • the default change — from round 6 onward a PR re-review stops posting Suggestions and lists them as deferrals instead, and rounds 2–5 defer new Suggestions on unchanged code. A contributor who reads only this page will see a round-6 review that "found nothing" and have no way to know why.

docs/users/configuration/settings.md covers the review.severityFloor setting, but nothing covers the flag or the behavior change.


These settings are read from operator scopes only (User, System, and SystemDefaults); values in a workspace `.qwen/settings.json` are ignored, so a repository cannot set review policy for its reviewers.

Expand Down
Loading
Loading