docs(u6-plugin-docs-drift): plugin stage 文書の自動起動記述を advisory ladder の実挙動へ整合させる

[j5ik2o]

概要(Bolt: u6-plugin-docs-drift / intent 260807-autonomy-reachability)

plugins/formal-model-check/stages/formal-model-check.md:27 と plugins/pr-convergence/stages/pr-convergence.md:27 の「Amadeus never runs it automatically」を、#2318 で実装済みの advisory→question ルーティング(amadeus-advisory-choice.ts:521,:576-586)の実挙動へ整合させる(FR-6a)。

• autonomy none: 人間が起動判断(advisory は提示のみ)
• semi/full: advisory が question occurrence として autonomy ladder に掛かり、run-now 裁定で無人起動しうる(それ以外は human fallback)
• scopes: [](stock 非所属)の記述は不変。新 occurrence kind の追加なし(FR-6b)

検証

• 是正前 grep 各1件 → 是正後 両ファイル 0 件(repo 全域で pin するテスト・fixture なし)
• typecheck 0 / lint 0 / plugin 関連テスト8ファイル 79 pass / 0 fail
• conductor ツリー取込後の full CI(bash tests/run-tests.sh --ci)RESULT: PASS

レビュー

• FD(BR-U6-1〜4)は §12a reviewer READY(iteration 1)
• 文書のみの変更(コード変更なし)— TDD 適用外クラス、grep 対照の両側実測で検証

Refs #2378 (record: amadeus/spaces/default/intents/260807-autonomy-reachability)

---

Note

Low Risk
Markdown-only; no runtime, auth, or data-path changes.

Overview
Documentation-only update to formal-model-check and pr-convergence plugin stage docs so they match advisory→question routing in amadeus-advisory-choice.ts (FR-6a), instead of stating that Amadeus never runs these stages automatically.

Both files now describe how a run can start by Intent autonomy mode: under none, humans decide; under semi/full, engine advisories become question occurrences on the autonomy ladder, and a run-now decision can start the stage unattended, with other ladder outcomes falling back to a human. Opt-in boundaries (scopes: [], explicit --stage, no stock workflow membership) are unchanged.

^{Reviewed by Cursor Bugbot for commit 1d0fc40. Configure here.}

[coderabbitai]

Warning

Review limit reached

@j5ik2o, you've reached your PR review limit, so we couldn't start this review.

Next review available in: 38 minutes

Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available.
You're only billed for reviews past your plan's rate limits ($0.25/file).

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews.

How do review limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window.

Please refer docs for additional details.

Review details

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: ASSERTIVE

Plan: Pro Plus

Run ID: 34ad7520-32e8-4e9c-bf9a-634b4bb43ab9

📥 Commits

Reviewing files that changed from the base of the PR and between 062fbb0 and 1d0fc40.

📒 Files selected for processing (2)

• plugins/formal-model-check/stages/formal-model-check.md
• plugins/pr-convergence/stages/pr-convergence.md

---

_{Comment @coderabbitai help to get the list of available commands.}