chore(#4729): guard the retired-runtime name, and finish the locale residue (#4753)

* chore(#4729): guard the retired-runtime name, and finish the locale residue

Phase 5 of 5 on epic #4709, and the phase that closes it. Two parts, one
concern: make the tree clean, and keep it clean. The guard is inert until the
tree is clean, and shipping the cleanup without the guard is the
one-bug-at-a-time pattern this epic exists to end.

WHY A GUARD, AND WHY LAST

Nothing in CI answered "does any shipped surface still present a retired
runtime as live?", and the two gates that look like they should cannot.
checkReviewerDocsParity is one-directional: it asserts the PRESENCE of every
declared reviewer flag and never the ABSENCE of a retired one, so in #4716 it
reported 0 violations while all four locale mirrors still documented --gemini
as a live reviewer flag, with usage examples. And
tests/gemini-runtime-removed.test.cjs is scoped by construction - its own
docblock limits it to the installer CLI contract and the runtime-name-policy
exports; it never reads docs/**, gsd-core/workflows/**, commands/** or
agents/**. Every extension to it during this epic was a hand-added assertion
for a surface somebody had already noticed.

A guard written earlier would have red-flagged the very references phases
1b-4b were removing, which is why it lands last.

PART A - THE RESIDUE, INCLUDING WORK I SHIPPED INCOMPLETE

Each site was judged against its ENGLISH counterpart, not on its own:

  README.{ja-JP,ko-KR,pt-BR,zh-CN}.md :9 :24 :46  English README.md has ZERO
                                                  occurrences -> substituted
                                                  "Antigravity CLI, Kimi CLI"
  how-to/execute-a-phase.md:88  x4 locales        fixed in #4728 -> substitute
  how-to/verify-and-ship.md:89  x4 locales        fixed in #4728 -> substitute
  FEATURES.md cross-AI CLI list                   :1419 no Gemini -> DELETE
  FEATURES.md REQ-MULTI-RT-01                     :1709 -> substitute
  FEATURES.md REQ-SKILLS-03                       :1952 -> rewrite
  FEATURES.md REQ-QUOTA-02                        :3256 deleted upstream -> delete
  VERSIONING.md:133                               stale manifest -> see below

The twelve README occurrences were an adversarial reviewer's BLOCKER, and the
reason they survived my own sweep is structural: root-level *.md was outside
the guard's scan set, so the repo's most-read runtime-advertising surface was
invisible to the guard meant to police it. :46 is a live installer-runtime
claim - it tells the reader the installer will offer a runtime that no longer
exists. Checked for the duplicate-name trap before substituting: neither
Antigravity nor Kimi appears anywhere in those four files.

Two of these are mine to own: I fixed the ENGLISH execute-a-phase.md and
verify-and-ship.md in #4728 and left all four mirrors behind. Unfinished work,
not a deferral.

Two more show why "substitute Gemini -> Antigravity" is the wrong default: in
the cross-AI list and REQ-QUOTA-02 English DELETES the name, because
Antigravity was already in the list or the classifier had dropped it.
Substituting would have duplicated a name - the identical trap
ARCHITECTURE.md:24 set in #4728, where English holds Kimi CLI in that slot.

VERSIONING.md:133 is a different and worse defect than translation lag. Under
"Manifest Version Sync" it listed gemini-extension.json as a version-synced
manifest. That file is ABSENT from the repo, and
scripts/sync-manifest-versions.cjs says so in its own comment - "#1928:
gemini-extension.json was removed with the gemini runtime ... it is no longer
a registered manifest" - while VERSIONED_MANIFESTS holds plugin.json,
marketplace.json and vscode/package.json. So the doc named a manifest that
does not exist AND omitted the one that replaced it. Both fixed, verified
against the owning code rather than inferred from the name. The replacement
bullet cites #1942, the issue that actually registered vscode/package.json,
matching the convention of its neighbours.

pt-BR/FEATURES.md is a 77-line stub genuinely lacking two sites, and ko-KR has
no REQ-QUOTA-02 line. Skipped and recorded, never invented.

PART B - THE GUARD

scripts/lint-retired-runtime-name.cjs, modelled on
scripts/lint-legacy-dir-name.cjs - the repo's own precedent for this problem
shape (forbid a retired token, allowlist frozen content, self-exempt via a
split literal, a REPO_ROOT test seam, lib/cli-exit.cjs, exit 0/1).

Case sensitivity IS the mechanism, not an accident. The naive guard - "the
string gemini must not appear" - is WRONG, not merely noisy: that string is
load-bearing across Antigravity's real on-disk contract. A case-sensitive,
standalone, capitalised name works because every legitimate reference is
spelled differently and therefore cannot match: lowercase config homes
(~/.gemini/antigravity, ~/.gemini/config, #3738), lowercase hyphenated model
ids (gemini-2.5-flash-lite), uppercase env vars (GEMINI_API_KEY), and
GEMINI.md. Table-driven, so the next retired runtime costs one row.

THE ALLOWLIST IS THE ENTIRE RISK SURFACE, so it is three tiers, not one. Two
rounds of isolated adversarial review reshaped it; both are recorded in
.gsd/bug/chore-4729-gemini-drift-guard/60-review.json.

ROUND 2 FOUND ONE ROOT CAUSE BEHIND TWO SEPARATE HOLES, and it was mine: both
Tier-1 rules treated the ABSENCE of a runtime word as a GRANT. A veto list can
never be complete, so "no runtime word found" silently exempted every phrasing
nobody had enumerated. Demonstrated: `The installer now offers Gemini 3.`,
`Supported agents include Gemini 3, Kimi, and Cursor.` and three more exited 0,
as did `Suportamos Gemini, no estilo padrao, como runtime de instalacao.` and
`Gemini 兼容，并且是受支持的运行时之一。`, both of which literally contain `runtime`
or `运行时`. The fix was to stop enumerating exceptions and invert the evidence
direction:

  Tier 1(a) - the hook DIALECT Antigravity inherits. Position is
  language-dependent and MEASURED: en Gemini-style/-compatible, ja Gemini
  スタイル, ko Gemini 스타일/호환, zh Gemini 风格 / 与 Gemini 兼容的, pt "no estilo
  Gemini" / "compatível com Gemini" where the qualifier PRECEDES the name. The
  marker must now form an ADJACENT COMPOUND with the name, not merely sit in a
  +/-24-character window - that window let `| Antigravity | Gemini-style hooks
  | Gemini support is live |` exit 0, one legitimate reference licensing a
  fresh live claim 21 characters later. The runtime-word veto is now
  LINE-GLOBAL. Ten real lines legitimately pair a dialect compound with a
  runtime word (`~/.gemini/antigravity-cli` in a table cell, "runtime files"
  in the same sentence); each is an explicit pin rather than a reason to
  loosen the veto for everyone. Measured: widening it surfaced exactly those
  ten and no others.

  Tier 1(b) - the provider/model axis. A version optionally followed by a
  qualifier, including full-width digits and CJK punctuation, AND positive
  model-axis evidence on the line, AND no runtime word. The positive
  requirement is the part that matters: all eight real model-axis lines in the
  repo name a model explicitly, so requiring it costs nothing on the real tree
  while flagging every laundering attempt. It is also the honest resolution of
  the agent/target tension below - rather than guess at an exhaustive veto
  list, stop treating an empty veto as evidence.

  Tier 2 - PINNED OCCURRENCES, now SPAN-SCOPED. A pin excuses only a match
  falling INSIDE an occurrence of its own snippet. Line-level containment let
  `Known provider menu update: Gemini CLI is once again a selectable GSD
  runtime.` and `Install target: Google (Gemini) - choose Gemini CLI as your
  GSD runtime.` both exit 0, because a short snippet elsewhere on the line
  pre-approved a brand-new claim. Span scoping makes short snippets safe:
  `Google (Gemini)` can only ever excuse the match inside those 15 characters.
  A LOAD-TIME validator now requires every pin to contain a retired name, and
  it immediately caught five of MY OWN pins whose snippets sat BESIDE the name
  rather than covering it - each would have shipped permanently inert and
  permanently reported stale. All pins were then reconciled in one pass.

  A pin is also marked used by PRESENCE on the line now, rather than only on
  the Tier-2 branch. Previously a pinned line that a general rule also matched
  never marked its pin used, producing a provably FALSE "no line matches
  pinned snippet" whose printed remedy told the maintainer to delete a pin
  that was still needed.

  Tier 3 - blanket trust, and a new occurrence inside it IS invisible.
  CHANGELOG.md and `.changeset/` - the rendered changelog and its source, one
  surface - plus six append-only directories. All 21 `.changeset/` hits were
  measured to be fragments DESCRIBING the retirement or a fix to it, 464 of
  them under archived/; a fragment can only describe what already shipped and
  is deleted at release, so pinning them would be friction with no signal. The
  cost is stated in the guard's own header rather than hidden.

THE SCAN SET IS NOW EVERY TRACKED *.md FILE (1165 read). The original prefix
list left `.github/`, `.changeset/`, `capabilities/`, `playbooks/` and
`references/` invisible - and `.changeset/*.md` renders into CHANGELOG.md, so a
live claim introduced there was invisible at BOTH ends.

The escape hatch must now carry a justification
(`gsd-allow-retired-runtime-name: <reason>`). A bare marker is rejected: it is
checked first, excuses the whole line, and the failure message advertises it,
so an unexplained one is indistinguishable from a silenced defect.

Plus an anti-vacuity floor counting files actually READ, not files listed - a
candidate count stays healthy-looking even if every read failed.

A FALSE NEGATIVE I INTRODUCED, AND CLOSED

The model-display escape began as a blanket /^ \d/ - "space then a digit" -
which also matched "Install for Gemini 2.5 CLI as a supported runtime.",
laundering a genuine stale-runtime claim through an attached version number.

That was the THIRD appearance of one failure shape in this epic: an exclusion
added to suppress false positives creating a false negative. #4716's sweep
excluded lines matching gemini-[0-9] to spare Google's model ids, and thereby
hid a stale review.models.gemini row whose example value was "gemini-2.5-pro"
ON THE SAME LINE. Round 2 then produced the FOURTH and FIFTH instances, which
is why the fix this time was to invert the rule's evidence direction rather
than to enumerate more exceptions.

The veto is word-anchored for Latin terms - unanchored, case-insensitive "CLI"
matched inside "client" and would have vetoed legitimate model lists - and raw
for CJK terms, where \b is ASCII-word-based and would never fire beside an
ideograph, so anchoring them would silently disable the veto in ja/ko/zh.
"agent" and "target" were deliberately left OUT: both occur throughout
ordinary prose ("AI coding agents (Claude Code, Codex, Gemini 2.5 Pro)"), so
vetoing on them would red correct content instead of catching runtime claims.
The reasoning is in the guard's comment, not just the omission - and Tier
1(b)'s positive-evidence requirement is what makes that omission safe, since
the rule no longer depends on the veto list being complete.

COVERAGE

tests/lint-retired-runtime-name.test.cjs drives the guard through its
GSD_LINT_RETIRED_RUNTIME_REPO_ROOT seam against fixture repos, mirroring
tests/lint-legacy-dir-name.test.cjs. A guard never observed failing is not a
guard, and this epic already shipped one that was vacuous for 2 of its 5
files, so properties are paired against BOTH failure modes - too broad
silently absorbs a future defect, too narrow reds on legitimate content. Floor
boundaries are covered at 149/150/151.

The round-2 reviewer's sharpest point was about that claim, and it was right:
the first matrix's pairing was "true of the properties chosen, not of the
predicate's actual surface" - not one of its twenty properties could see the
dialect adjacency hole, a non-adjacent runtime word, pin shadowing, or an
over-broad pin colliding with a new line. Every one of those is now a
committed regression using the reviewer's own attack line verbatim, and the
local fixture harness went from 14 cases to 35 (PASS=35 FAIL=0).

That harness earned a finding of its own. Its first run reported PASS=2
FAIL=12 with BOTH passes VACUOUS: `git add` has no -q flag on this build, so
nothing staged, every fixture hit the empty-walk error path, and the two
checks that assert an ABSENCE passed off that error path rather than off real
guard logic. A staging failure is now fatal and every absence-asserting check
first proves the walk ran and the expected violation was flagged. Later, one
case failed because its fixture supplied only one of a pinned file's two
approved lines, so the stale-pin check fired correctly - the expectation was
wrong, not the guard. Telling those two apart is the whole value of running a
matrix rather than reasoning about one.

On the two orthogonal reviews: the isolated adversarial pass executed a great
deal of code, across two rounds, against its own fixture repos. The security
pass did NOT - it self-discloses that it verified by reading only, because
node --test is hard-blocked here. Saying so plainly, because "two orthogonal
reviews" without that caveat overstates what the second one established. It
also raised, and I cleared by measurement, a concern that importing
escapeRegex from a gitignored build artifact would break lint:ci on an unbuilt
clone: six other tracked scripts already require that exact path, three of
them already in lint:ci, and .github/workflows/test.yml:192-193 runs
`npm run build:lib` immediately before it for exactly this reason.

Part A has no new test deliberately - those edits are covered by the guard
itself inside lint:ci, and a separate per-locale assertion would duplicate it
and then drift from it. The one exception is the root README case, which IS
pinned: that residue was invisible to the guard rather than merely unasserted,
so the fix is a scan-set change and needs its own regression test.

No mode-bit read-failure fixture was added on purpose: the benches run as
root, where chmod-based IO injection is vacuous, so such a test would assert
nothing.

The test's fixture helpers write throwaway docs/ paths, which trips
lint-docs-guard-registration's reader-name heuristic. Resolved the way that
lint documents - a header `// docs-guard-exempt:` marker plus a baseline entry
- because the fixtures only WRITE scratch data and never read shipped docs;
the baseline was re-confirmed, not merely extended, each time locale and
adversarial fixtures were added. scripts/lib/macos-conformance-tier.generated.cjs
regenerated through its own --write path, since a new test file changes the
count lint:generated-sync reads.

Fixes #4729

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

* chore(#4729): backfill changeset PR number (#4753)

---------

Co-authored-by: sim <sim@local>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>

docs/ja-JP/FEATURES.md

@@ -1166,7 +1166,7 @@ fix(03-01): correct auth token expiry
 
 **コマンド:** `/gsd-review --phase N [--claude] [--codex] [--coderabbit] [--opencode] [--qwen] [--cursor] [--agy] [--antigravity] [--ollama] [--lm-studio] [--llama-cpp] [--kimi-code] [--all]`
 
-**目的:** 外部の AI CLI（Gemini、Claude、Codex、CodeRabbit、OpenCode、Qwen Code、Cursor、Antigravity、Kimi Code）とローカルの OpenAI 互換サーバー（Ollama、LM Studio、llama.cpp）を呼び出して、フェーズプランを独立してレビューします。レビュアーごとのフィードバックを含む構造化された REVIEWS.md を生成します。
+**目的:** 外部の AI CLI（Claude、Codex、CodeRabbit、OpenCode、Qwen Code、Cursor、Antigravity、Kimi Code）とローカルの OpenAI 互換サーバー（Ollama、LM Studio、llama.cpp）を呼び出して、フェーズプランを独立してレビューします。レビュアーごとのフィードバックを含む構造化された REVIEWS.md を生成します。
 
 **要件:**
 - REQ-REVIEW-01: システムはシステム上で利用可能な AI CLI を検出しなければならない
@@ -1430,7 +1430,7 @@ Claude が GSD ワークフローコンテキスト外でファイル編集を
 **目的:** 1回のインタラクティブなインストールセッションで複数のランタイムを選択します。
 
 **要件:**
-- REQ-MULTI-RT-01: インタラクティブプロンプトはマルチセレクトをサポートしなければならない（例: Claude Code + Gemini）
+- REQ-MULTI-RT-01: インタラクティブプロンプトはマルチセレクトをサポートしなければならない（例: Claude Code + Antigravity）
 - REQ-MULTI-RT-02: CLI フラグは非インタラクティブインストールで引き続き動作しなければならない
 
 **プロセス:**
@@ -1672,13 +1672,13 @@ Claude が GSD ワークフローコンテキスト外でファイル編集を
 **要件:**
 - REQ-SKILLS-01: インストーラーは Claude Code 2.1.88+ 向けに `skills/gsd-*/SKILL.md` を書き込まなければならない
 - REQ-SKILLS-02: インストーラーはレガシー `commands/gsd/` ディレクトリを自動クリーンしなければならない
-- REQ-SKILLS-03: Gemini パスを通じて古い Claude Code バージョンとの後方互換性を維持しなければならない
+- REQ-SKILLS-03: レガシー `commands/gsd/` パスを通じて古い Claude Code バージョンとの後方互換性を維持しなければならない
 
 **プロセス:**
 1. **検出** — Claude Code のバージョンをチェックしてスキルサポートを判定
 2. **マイグレーション** — 各 GSD コマンドに対して `skills/gsd-*/SKILL.md` ファイルを書き込み
 3. **クリーン** — スキルがインストールされた場合、レガシー `commands/gsd/` ディレクトリを削除
-4. **フォールバック** — 古い Claude Code バージョンのために Gemini パス互換性を維持
+4. **フォールバック** — 古い Claude Code バージョンのためにレガシー `commands/gsd/` パス互換性を維持
 
 ---
 
@@ -2952,7 +2952,7 @@ Source commit: abc1234 (3 commits behind HEAD)
 
 **要件:**
 - REQ-QUOTA-01: クォータ失敗は即時再試行を主要な回復として提供してはならない。
-- REQ-QUOTA-02: 分類は Claude、Copilot、Codex、Gemini、および汎用プロバイダーセンチネルをカバーしなければならない。
+- REQ-QUOTA-02: 分類は Claude、Copilot、Codex、および汎用プロバイダーセンチネルをカバーしなければならない。
 - REQ-QUOTA-03: 非クォータ失敗は通常の実行失敗パスを継続しなければならない。
 
 **参照:** [プロバイダーレート制限シグナル](../research/provider-rate-limit-signals.md)

docs/ja-JP/how-to/execute-a-phase.md

@@ -85,7 +85,7 @@ Git の履歴には、各エグゼキュータからのタスクごとのコミ
 
 ## クロス AI 実行
 
-`workflow.cross_ai_command` で設定された外部 AI CLI（Codex、Gemini など）に実行を委任するには:
+`workflow.cross_ai_command` で設定された外部 AI CLI（Codex、Antigravity など）に実行を委任するには:
 
 ```bash
 /gsd-execute-phase 2 --cross-ai

docs/ja-JP/how-to/verify-and-ship.md

@@ -86,7 +86,7 @@ PR の本文はプランニング成果物から自動的に組み立てられ
 /gsd-code-review 1 --depth=deep  # インポートグラフを含むクロスファイル分析
 ```
 
-サイクルの早い段階でのプランレビューに Gemini、Codex、その他のレビュアーを設定するには [クロス AI レビューの設定](set-up-cross-ai-review.md) を参照してください。
+サイクルの早い段階でのプランレビューに Antigravity、Codex、その他のレビュアーを設定するには [クロス AI レビューの設定](set-up-cross-ai-review.md) を参照してください。
 
 ---
 

docs/ko-KR/FEATURES.md

@@ -1070,7 +1070,7 @@ fix(03-01): correct auth token expiry
 
 **명령어:** `/gsd-review --phase N [--claude] [--codex] [--coderabbit] [--opencode] [--qwen] [--cursor] [--agy] [--antigravity] [--ollama] [--lm-studio] [--llama-cpp] [--kimi-code] [--all]`
 
-**목적:** 외부 AI CLI(Gemini, Claude, Codex, CodeRabbit, OpenCode, Qwen Code, Cursor, Antigravity, Kimi Code)와 로컬 OpenAI 호환 서버(Ollama, LM Studio, llama.cpp)를 호출하여 페이즈 계획을 독립적으로 검토합니다. 검토자별 피드백이 담긴 구조화된 REVIEWS.md를 생성합니다.
+**목적:** 외부 AI CLI(Claude, Codex, CodeRabbit, OpenCode, Qwen Code, Cursor, Antigravity, Kimi Code)와 로컬 OpenAI 호환 서버(Ollama, LM Studio, llama.cpp)를 호출하여 페이즈 계획을 독립적으로 검토합니다. 검토자별 피드백이 담긴 구조화된 REVIEWS.md를 생성합니다.
 
 **요구사항.**
 - REQ-REVIEW-01: 시스템에서 사용 가능한 AI CLI를 감지해야 합니다.
@@ -1334,7 +1334,7 @@ Claude가 GSD 워크플로우 컨텍스트 밖에서 파일 편집을 시도하
 **목적:** 단일 대화형 설치 세션에서 여러 런타임을 선택합니다.
 
 **요구사항.**
-- REQ-MULTI-RT-01: 대화형 프롬프트는 다중 선택을 지원해야 합니다(예: Claude Code + Gemini).
+- REQ-MULTI-RT-01: 대화형 프롬프트는 다중 선택을 지원해야 합니다(예: Claude Code + Antigravity).
 - REQ-MULTI-RT-02: CLI 플래그는 비대화형 설치에서 계속 작동해야 합니다.
 
 **프로세스.**
@@ -1576,13 +1576,13 @@ Claude가 GSD 워크플로우 컨텍스트 밖에서 파일 편집을 시도하
 **요구사항.**
 - REQ-SKILLS-01: 설치 프로그램은 Claude Code 2.1.88+ 용 `skills/gsd-*/SKILL.md`를 작성해야 합니다.
 - REQ-SKILLS-02: 설치 프로그램은 레거시 `commands/gsd/` 디렉토리를 자동 정리해야 합니다.
-- REQ-SKILLS-03: Gemini 경로를 통해 이전 Claude Code 버전과의 하위 호환성을 유지해야 합니다.
+- REQ-SKILLS-03: 레거시 `commands/gsd/` 경로를 통해 이전 Claude Code 버전과의 하위 호환성을 유지해야 합니다.
 
 **프로세스.**
 1. **감지** — Claude Code 버전을 확인하여 스킬 지원 여부 판단
 2. **마이그레이션** — 각 GSD 명령어에 대해 `skills/gsd-*/SKILL.md` 파일 작성
 3. **정리** — 스킬이 설치되면 레거시 `commands/gsd/` 디렉토리 제거
-4. **폴백** — 이전 Claude Code 버전을 위한 Gemini 경로 호환성 유지
+4. **폴백** — 이전 Claude Code 버전을 위한 레거시 `commands/gsd/` 경로 호환성 유지
 
 ---
 

docs/ko-KR/how-to/execute-a-phase.md

@@ -85,7 +85,7 @@ Git 히스토리에는 각 실행자의 태스크당 커밋 하나와 오케스
 
 ## 크로스 AI 실행
 
-`workflow.cross_ai_command`에 설정된 외부 AI CLI(Codex, Gemini 등)에 실행을 위임하려면:
+`workflow.cross_ai_command`에 설정된 외부 AI CLI(Codex, Antigravity 등)에 실행을 위임하려면:
 
 ```bash
 /gsd-execute-phase 2 --cross-ai

docs/ko-KR/how-to/verify-and-ship.md

@@ -86,7 +86,7 @@ PR 본문은 기획 산출물에서 자동으로 조합됩니다:
 /gsd-code-review 1 --depth=deep  # 임포트 그래프를 포함한 파일 간 분석
 ```
 
-주기 초반의 계획 리뷰를 위해 Gemini, Codex 또는 다른 리뷰어를 설정하려면 [크로스 AI 리뷰 설정](set-up-cross-ai-review.md)을 참고하세요.
+주기 초반의 계획 리뷰를 위해 Antigravity, Codex 또는 다른 리뷰어를 설정하려면 [크로스 AI 리뷰 설정](set-up-cross-ai-review.md)을 참고하세요.
 
 ---
 

docs/pt-BR/how-to/execute-a-phase.md

@@ -85,7 +85,7 @@ O histórico git exibirá um commit por tarefa (de cada executor), seguido de co
 
 ## Execução Cross-AI
 
-Para delegar a execução a uma CLI de IA externa (Codex, Gemini, etc.) configurada em `workflow.cross_ai_command`:
+Para delegar a execução a uma CLI de IA externa (Codex, Antigravity, etc.) configurada em `workflow.cross_ai_command`:
 
 ```bash
 /gsd-execute-phase 2 --cross-ai

docs/pt-BR/how-to/verify-and-ship.md

@@ -86,7 +86,7 @@ Não é necessário escrever o corpo manualmente.
 /gsd-code-review 1 --depth=deep  # Análise entre arquivos incluindo grafos de importação
 ```
 
-Consulte [Configurar revisão entre IAs](set-up-cross-ai-review.md) para configurar o Gemini, Codex ou outros revisores para revisão de planos mais cedo no ciclo.
+Consulte [Configurar revisão entre IAs](set-up-cross-ai-review.md) para configurar o Antigravity, Codex ou outros revisores para revisão de planos mais cedo no ciclo.
 
 ---
 

docs/zh-CN/FEATURES.md

@@ -1176,7 +1176,7 @@ GSD update available: 1.39.0 → 1.40.0. Run /gsd-update.
 
 **命令：** `/gsd-review --phase N [--claude] [--codex] [--coderabbit] [--opencode] [--qwen] [--cursor] [--agy] [--antigravity] [--ollama] [--lm-studio] [--llama-cpp] [--kimi-code] [--all]`
 
-**目的：** 调用外部 AI CLI（Gemini、Claude、Codex、CodeRabbit、OpenCode、Qwen Code、Cursor、Antigravity、Kimi Code）和本地 OpenAI 兼容服务器（Ollama、LM Studio、llama.cpp）独立审查阶段计划。生成包含每位审查者反馈的结构化 REVIEWS.md。
+**目的：** 调用外部 AI CLI（Claude、Codex、CodeRabbit、OpenCode、Qwen Code、Cursor、Antigravity、Kimi Code）和本地 OpenAI 兼容服务器（Ollama、LM Studio、llama.cpp）独立审查阶段计划。生成包含每位审查者反馈的结构化 REVIEWS.md。
 
 **需求：**
 - REQ-REVIEW-01：系统必须检测系统上可用的 AI CLI
@@ -1447,7 +1447,7 @@ PreToolUse 钩子，检测 Claude 在 GSD 工作流上下文之外尝试文件
 **目的：** 在单个交互式安装会话中选择多个运行时。
 
 **需求：**
-- REQ-MULTI-RT-01：交互式提示必须支持多选（例如 Claude Code + Gemini）
+- REQ-MULTI-RT-01：交互式提示必须支持多选（例如 Claude Code + Antigravity）
 - REQ-MULTI-RT-02：CLI 标志必须继续适用于非交互式安装
 
 **流程：**
@@ -1688,13 +1688,13 @@ PreToolUse 钩子，检测 Claude 在 GSD 工作流上下文之外尝试文件
 **需求：**
 - REQ-SKILLS-01：安装器必须为 Claude Code 2.1.88+ 写入 `skills/gsd-*/SKILL.md`
 - REQ-SKILLS-02：安装器必须自动清理旧版 `commands/gsd/` 目录
-- REQ-SKILLS-03：安装器必须通过 Gemini 路径维护与旧版 Claude Code 的向后兼容性
+- REQ-SKILLS-03：安装器必须通过旧版 `commands/gsd/` 路径维护与旧版 Claude Code 的向后兼容性
 
 **流程：**
 1. **检测** — 检查 Claude Code 版本以确定技能支持情况
 2. **迁移** — 为每个 GSD 命令写入 `skills/gsd-*/SKILL.md` 文件
 3. **清理** — 如果已安装技能，则删除旧版 `commands/gsd/` 目录
-4. **回退** — 为旧版 Claude Code 维护 Gemini 路径兼容性
+4. **回退** — 为旧版 Claude Code 维护旧版 `commands/gsd/` 路径兼容性
 
 ---
 
@@ -2968,7 +2968,7 @@ explicit reviewer flags -> --all -> review.default_reviewers -> all detected rev
 
 **需求：**
 - REQ-QUOTA-01：配额失败不得将立即重试作为主要恢复选项。
-- REQ-QUOTA-02：分类必须涵盖 Claude、Copilot、Codex、Gemini 和通用提供商哨兵。
+- REQ-QUOTA-02：分类必须涵盖 Claude、Copilot、Codex 和通用提供商哨兵。
 - REQ-QUOTA-03：非配额失败必须继续通过正常的执行失败路径。
 
 **参考：** [提供商速率限制信号](../research/provider-rate-limit-signals.md)

docs/zh-CN/how-to/execute-a-phase.md

@@ -85,7 +85,7 @@ Git 历史记录中每个任务会有一个提交（来自各执行器），随
 
 ## 跨 AI 执行
 
-要将执行委托给在 `workflow.cross_ai_command` 中配置的外部 AI CLI（Codex、Gemini 等）：
+要将执行委托给在 `workflow.cross_ai_command` 中配置的外部 AI CLI（Codex、Antigravity 等）：
 
 ```bash
 /gsd-execute-phase 2 --cross-ai

docs/zh-CN/how-to/verify-and-ship.md

@@ -86,7 +86,7 @@ PR 正文由规划产物自动组装：
 /gsd-code-review 1 --depth=deep  # 包含导入图的跨文件分析
 ```
 
-请参阅[配置跨 AI 审查](set-up-cross-ai-review.md)，了解如何在周期早期为计划审查配置 Gemini、Codex 或其他审查工具。
+请参阅[配置跨 AI 审查](set-up-cross-ai-review.md)，了解如何在周期早期为计划审查配置 Antigravity、Codex 或其他审查工具。
 
 ---