okstra 0.85.0 → 0.87.0

package/docs/superpowers/specs/2026-06-17-okstra-error-report-design.md

@@ -0,0 +1,123 @@
+# okstra-run 에러 집계 리포트 (`okstra error-report` + inspect `errors` facet) 설계
+
+- 날짜: 2026-06-17
+- 상태: 설계 초안
+- 대상: 신규 `scripts/okstra_ctl/error_report.py`, 신규 `src/error-report.mjs`, `src/cli-registry.mjs`, `skills/okstra-inspect/SKILL.md`
+- 선행 문서:
+  - [`2026-06-06-stage-worktree-isolation-design.md`](2026-06-06-stage-worktree-isolation-design.md) (stage-isolated run 경로)
+
+## 1. 배경
+
+okstra-run 은 실행 중 발생한 에러를 이미 구조화된 형태로 적재하고 있다. 그러나 그 데이터를 **읽어서 사람에게 리포트로 보여주는 소비자가 없다.**
+
+확인된 현재 상태:
+
+- 에러는 run 별 JSONL 로 적재된다: `runs/<task-type>/logs/errors-<task-type>-<seq>.jsonl` ([paths.py:196](../../../scripts/okstra_ctl/paths.py:196)).
+- 단일 writer 헬퍼가 스키마를 강제한다. 레코드 필드는 `ts / recordedAt / taskKey / phase / agent / agentRole / model / source / errorType / command / commandKind / exitCode / durationMs / message / stderrExcerpt / context` ([okstra-error-log.py:122](../../../scripts/okstra-error-log.py:122)).
+- 두 경로로 수집된다: lead 가 직접 관측한 에러(`append-observed`)와 워커 사이드카(`worker-results/<id>-worker-errors-*.json`)에서 끌어온 에러(`append-from-worker`) ([okstra-error-log.py:96](../../../scripts/okstra-error-log.py:96), [okstra-error-log.py:144](../../../scripts/okstra-error-log.py:144)). `source` 는 각각 `lead-observed` / `worker-reported`.
+- `errorType` 화이트리스트: `tool-failure`, `cli-failure`, `contract-violation` ([okstra-error-log.py:17](../../../scripts/okstra-error-log.py:17)).
+- `_active_error_logs` 는 이 경로들을 **lead 에게 "여기 기록하라"고 알려주는 쓰기 타깃**으로만 노출한다 ([render.py:361](../../../scripts/okstra_ctl/render.py:361), [render.py:430](../../../scripts/okstra_ctl/render.py:430)). errors.jsonl 을 읽어 보고하는 코드는 없다(grep 확인).
+- okstra-inspect 는 현재 `latestRunStatus == error` 라는 **run 단위 거친 상태**만 노출할 뿐, 개별 에러 이벤트(어느 phase 에서 어느 워커가 무슨 command 로 exitCode 몇으로 실패했는지)는 어디서도 리포트하지 않는다 ([skills/okstra-inspect/SKILL.md:206](../../../skills/okstra-inspect/SKILL.md:206)).
+
+## 2. 사용자 결정
+
+브레인스토밍에서 4개 핵심을 확정했다.
+
+1. **리포트 성격 = 파일 산출물.** 화면 출력에 그치지 않고 `.md` 파일로 저장한다.
+2. **범위 = task 전체 집계.** 한 task 의 모든 run 에 걸친 errors.jsonl 을 합쳐 phase / worker / errorType 별로 집계한다.
+3. **렌더링 주체 = 신규 CLI `okstra error-report`.** 여러 run 의 JSONL 집계는 결정론적이어야 정확하므로 Python 렌더러가 수행한다. inspect facet 은 이 CLI 를 호출하고 결과를 표시한다 — `cost` facet 이 `okstra context-cost` 를 호출하는 것과 동일한 패턴 ([skills/okstra-inspect/SKILL.md:528](../../../skills/okstra-inspect/SKILL.md:528)).
+4. **저장 방식 = timestamp 누적.** 매 호출마다 새 파일을 만들어 이력을 파일로 보존한다 — schedule 산출물과 동일한 누적 패턴 ([skills/okstra-schedule/SKILL.md:160](../../../skills/okstra-schedule/SKILL.md:160)).
+
+## 3. 아키텍처
+
+4개 변경. 모두 기존 컴포넌트를 복제하므로 새 패턴을 만들지 않는다.
+
+| 컴포넌트 | 역할 | 복제 대상 |
+|---|---|---|
+| `scripts/okstra_ctl/error_report.py` (신규) | task-key → task_root resolve → errors.jsonl glob → 집계 → `.md` 렌더 + stdout JSON 요약 | [`context_cost.py`](../../../scripts/okstra_ctl/context_cost.py) |
+| `src/error-report.mjs` (신규) | Node CLI 래퍼. `runPythonModule({module: "okstra_ctl.error_report"})` | [`src/context-cost.mjs`](../../../src/context-cost.mjs) |
+| `src/cli-registry.mjs` | `error-report` 명령 등록 (`introspection` 카테고리) | [`cli-registry.mjs:100`](../../../src/cli-registry.mjs:100) (context-cost 항목) |
+| `skills/okstra-inspect/SKILL.md` | 신규 `errors` facet 섹션 + dispatch 테이블 1행 + 트리거 phrase | `cost` facet 섹션 |
+
+### 단일 참조점 준수
+
+task-key → task_root 해석의 SSOT 는 공유 모듈 `okstra_project` 의 `find_task_root` / `resolve_project_root` 다 ([context_cost.py:16](../../../scripts/okstra_ctl/context_cost.py:16) 가 이를 `_resolve_task_root` 로 감싸 사용, [context_cost.py:92](../../../scripts/okstra_ctl/context_cost.py:92)). `error_report.py` 는 새 해석 경로를 만들지 않고 같은 공유 모듈을 직접 재사용한다 — `context_cost.py` 의 `_resolve_task_root`(target = task-root path / task-key + project-root / task-key + cwd 3형태)와 동일한 입력 계약을 따른다.
+
+## 4. CLI 인터페이스
+
+```
+okstra error-report <task-root>
+okstra error-report <task-key> --project-root <dir>
+okstra error-report <task-key> --cwd <dir>
+```
+
+- 입력 형태는 `context-cost` 와 동일(task-root 직접 / task-key + project-root / task-key + cwd).
+- 동작: errors.jsonl 들을 모아 집계 → `.md` 파일을 쓰고 → **stdout 으로 요약 JSON** 을 낸다.
+- stdout JSON shape(초안):
+  ```json
+  {
+    "taskKey": "<project-id>:<task-group>:<task-id>",
+    "reportPath": "<project-root-relative .md path>",
+    "totals": { "errorCount": 12, "runCount": 4, "byErrorType": {...}, "bySource": {...} },
+    "byPhase": [ { "phase": "...", "count": N } ],
+    "byAgent": [ { "agent": "...", "count": N } ]
+  }
+  ```
+- inspect `errors` facet 은 이 JSON 을 파싱해 생성 경로 + 요약 카운트만 화면에 표시한다(전체 본문은 `.md` 파일이 SSOT).
+
+## 5. 산출물 위치 / 구조
+
+- 저장 경로: **`<task_root>/error-reports/error-report-<YYYY-MM-DD_HH-MM-SS>.md`**
+  - task 레벨 집계 산출물이므로 task root 하위 전용 디렉터리(`error-reports/`)에 둔다. run 별 산출물(`runs/<type>/reports/`, [paths.py:148](../../../scripts/okstra_ctl/paths.py:148))과 레벨이 다르므로 디렉터리를 분리해 혼동을 막는다.
+  - timestamp 형식은 schedule 과 동일한 `<YYYY-MM-DD_HH-MM-SS>`.
+  - artifact-home 규칙 준수: 모든 산출물이 `<PROJECT_ROOT>/.okstra/` 하위에 있다.
+- 리포트 `.md` 섹션 구조:
+  1. **요약** — 총 에러 N건, 집계된 run 수, `errorType` 별 카운트, `source`(lead-observed / worker-reported) 별 카운트, 생성 시각.
+  2. **phase 별 집계** — `| Phase | Count |` (lifecycle phase 순).
+  3. **worker(agent) 별 집계** — `| Agent | Role | Count |`.
+  4. **run 별 분해** — `| Run (type/seq) | Errors | 최초 ts | 최종 ts |`.
+  5. **개별 에러 이벤트** — `ts / phase / agent / errorType / command / exitCode / message` 테이블 + `stderrExcerpt` 는 접힌 코드블록. `ts` 오름차순.
+
+## 6. 데이터 흐름
+
+1. task-key → task_root resolve (context_cost 와 동일).
+2. errors.jsonl glob:
+   - flat: `<task_root>/runs/*/logs/errors-*.jsonl`
+   - stage-isolated: `<task_root>/runs/*/stage-*/logs/errors-*.jsonl` ([2026-06-06-stage-worktree-isolation-design.md](2026-06-06-stage-worktree-isolation-design.md) 의 stage 경로 규칙)
+3. 각 파일을 줄 단위 JSON 으로 파싱. 깨진 줄은 건너뛰되 카운트해 리포트 말미에 `parse-skipped: N` 으로 surface(조용한 누락 금지).
+4. 집계 → `.md` 렌더 + stdout JSON.
+
+## 7. inspect 의 "두 번째 write" 경계
+
+현재 SKILL 첫 줄은 "read-side inspection plus the one write-side mutation (`workStatus`)" ([SKILL.md:9](../../../skills/okstra-inspect/SKILL.md:9)).
+
+`errors` facet 은 `task-manifest.json` 같은 **okstra 상태를 mutate 하지 않는다.** CLI 를 호출해 **읽은 에러 데이터에서 파생한 산출물(.md)을 렌더**할 뿐이며, 이는 `cost` 가 추정치를 내는 것과 같은 read-derived 동작이다. 따라서 SKILL 의 정체성 문구를 다음으로 정정한다:
+
+> read-side okstra inspection + 상태 mutation 하나(`workStatus`) + read-derived 산출물 렌더(`errors` 리포트).
+
+이로써 "유일한 write 는 workStatus" 라는 기존 불변식과 모순되지 않게 경계를 명시한다(상태 mutation 은 여전히 workStatus 하나뿐).
+
+## 8. 엣지케이스
+
+- **glob 결과 0개** (errors.jsonl 자체가 없음): "이 task 에는 기록된 에러 로그가 없습니다" 를 facet 이 보고하고 `.md` 를 생성하지 않는다.
+- **파일은 있으나 레코드 0건**: 빈 결과와 구분해, "에러 0건" 을 명시한 리포트를 생성한다.
+- **깨진 JSONL 줄**: 건너뛰고 `parse-skipped` 카운트로 surface.
+- **stage-isolated + flat 혼재**: 둘 다 glob 해 합산.
+
+## 9. 테스트 계획
+
+- `tests/test_okstra_error_report.py` (신규):
+  - flat / stage-isolated / 혼재 fixture 에서 errorCount·byPhase·byAgent·bySource 집계 정확성.
+  - errors.jsonl 0개 / 빈 파일 / 깨진 줄(parse-skipped) 처리.
+  - 생성 `.md` 의 섹션 헤딩·테이블 컬럼 존재.
+  - stdout JSON shape.
+- 기존 `tests/test_okstra_error_log.py` 와 충돌하지 않게 별도 모듈.
+- e2e: 기존 시나리오에 에러를 적재한 뒤 `okstra error-report` 를 돌려 `.md` 가 생성되는지 확인하는 시나리오를 선택적으로 추가(범위 밖일 수 있음 — plan 단계에서 판단).
+
+## 10. 범위 밖 (YAGNI)
+
+- 단일 run 한정 모드 / `--all` 토글 — 이번엔 task 집계 단일 모드만.
+- task-group 단위 집계.
+- run 종료 훅에서의 자동 생성(on-demand 보고가 의도).
+- HTML / slim-AI 뷰 렌더.
+- errors.jsonl 의 timeline/catalog 경로 노출(facet 이 결정론적 glob 으로 resolve 하므로 불필요).

package/docs/task-process/error-analysis.md

@@ -32,7 +32,7 @@ flowchart TD
     Confirm --> Render[render-bundle --render-only]
 ```
 
-기본 required roster는 `claude`, `codex`, `report-writer`다. `gemini`는 optional worker이고, 선택하면 analyser set에 들어간다.
+기본 required roster는 `claude`, `codex`, `report-writer`다. `antigravity`는 optional worker이고, 선택하면 analyser set에 들어간다.
 
 ## 3. prepare_task_bundle 처리
 

package/docs/task-process/final-verification.md

@@ -33,7 +33,7 @@ flowchart TD
     Confirm --> Render[render-bundle]
 ```
 
-`final-verification`은 analyser roster가 있는 non-implementation phase다. 따라서 `Use defaults`를 골라도 worker roster prompt는 계속 나온다. 기본 required workers는 `claude`, `codex`, `report-writer`이고, `gemini`는 opt-in이다.
+`final-verification`은 analyser roster가 있는 non-implementation phase다. 따라서 `Use defaults`를 골라도 worker roster prompt는 계속 나온다. 기본 required workers는 `claude`, `codex`, `report-writer`이고, `antigravity`는 opt-in이다.
 
 ## 3. entry gate
 
@@ -69,12 +69,12 @@ flowchart TD
     Gate[entry gate passed] --> Lead[Claude lead fixes target snapshot]
     Lead --> CW[Claude verifier<br/>read-only]
     Lead --> XW[Codex verifier<br/>read-only]
-    Lead --> GW{Gemini opt-in?}
-    GW -->|yes| Gemini[Gemini verifier<br/>read-only]
+    Lead --> GW{Antigravity opt-in?}
+    GW -->|yes| Antigravity[Antigravity verifier<br/>read-only]
     GW -->|no| Collect
     CW --> Collect[collect independent findings]
     XW --> Collect
-    Gemini --> Collect
+    Antigravity --> Collect
     Collect --> Conv[convergence<br/>default max rounds = 2]
     Conv --> Writer[report-writer final synthesis]
     Writer --> SelfReview[lead self-review<br/>verdict, blockers, coverage, no-mutation]

package/docs/task-process/implementation-planning.md

@@ -24,10 +24,10 @@ flowchart TD
     Worktree -->|yes| Defaults[Use defaults / Customize]
     Worktree -->|no| BaseRef[base-ref pick/text]
     BaseRef --> Defaults
-    Defaults --> Workers[worker multi-pick<br/>claude/codex + optional gemini]
+    Defaults --> Workers[worker multi-pick<br/>claude/codex + optional antigravity]
     Workers --> Branch{customize?}
     Branch -->|no| Confirm
-    Branch -->|yes| Models[lead, claude, codex, gemini if selected, report-writer models]
+    Branch -->|yes| Models[lead, claude, codex, antigravity if selected, report-writer models]
     Models --> Extras[directive, related tasks, clarification]
     Extras --> Confirm
     Confirm --> Render[render-bundle]

package/docs/task-process/implementation.md

@@ -28,7 +28,7 @@ flowchart TD
     PlanPick --> Approved{APPROVED marker present?}
     Approved -->|no| Retry[re-prompt same step]
     Approved -->|yes| Stage[stage pick<br/>auto or number]
-    Stage --> Executor[executor pick<br/>claude/codex/gemini]
+    Stage --> Executor[executor pick<br/>claude/codex/antigravity]
     Executor --> Defaults[Use defaults / Customize]
     Defaults -->|defaults| Confirm
     Defaults -->|customize| Models[lead + executor model + report-writer model]
@@ -69,8 +69,8 @@ flowchart TD
     Lead[Claude lead] --> Exec[Executor<br/>selected provider]
     Lead --> CV[Claude verifier<br/>read-only]
     Lead --> XV[Codex verifier<br/>read-only]
-    Lead --> GV{Gemini in roster?}
-    GV -->|yes| Gem[Gemini verifier<br/>read-only]
+    Lead --> GV{Antigravity in roster?}
+    GV -->|yes| Gem[Antigravity verifier<br/>read-only]
     Exec --> Diff[Source edits + local commits]
     CV --> QA[Independent QA rerun]
     XV --> QA

package/docs/task-process/requirements-discovery.md

@@ -42,7 +42,7 @@ flowchart TD
     Confirm --> Render[render-bundle]
 ```
 
-worker multi-pick에서 picker는 `report-writer`를 옵션으로 보여주지 않는다. 사용자가 `claude`만 골라도 wizard가 `report-writer`를 강제 append한다. optional `gemini`는 사용자가 골랐을 때만 포함된다.
+worker multi-pick에서 picker는 `report-writer`를 옵션으로 보여주지 않는다. 사용자가 `claude`만 골라도 wizard가 `report-writer`를 강제 append한다. optional `antigravity`는 사용자가 골랐을 때만 포함된다.
 
 ## 3. prepare_task_bundle 처리
 
@@ -73,7 +73,7 @@ runtime에서 이 phase만을 위한 추가 hard gate는 없다. 중요한 gate
 flowchart TD
     P1[Phase 1 intake<br/>manifest, brief, profile, run manifest, team-state] --> P2[Phase 2 prompts]
     P2 --> P3[Phase 3 TeamCreate]
-    P3 --> P4[Phase 4/5 dispatch analysers<br/>claude/codex + optional gemini]
+    P3 --> P4[Phase 4/5 dispatch analysers<br/>claude/codex + optional antigravity]
     P4 --> C[Phase 5.5 convergence<br/>default maxRounds = 1]
     C --> R[Phase 6 report-writer authors final report]
     R --> P7[Phase 7 token usage, validate, persist]

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "okstra",
-  "version": "0.85.0",
+  "version": "0.87.0",
   "description": "Multi-agent cross-verification orchestrator runtime + Claude Code skills.",
   "license": "MIT",
   "author": "devonshin",

package/runtime/BUILD.json

@@ -1,5 +1,5 @@
 {
-  "package": "0.85.0",
-  "builtAt": "2026-06-15T19:37:36.878Z",
+  "package": "0.87.0",
+  "builtAt": "2026-06-16T18:50:52.236Z",
   "repoRoot": "/home/runner/work/okstra/okstra"
 }

package/runtime/agents/workers/{gemini-worker.md → antigravity-worker.md}

@@ -1,19 +1,19 @@
 ---
-name: gemini-worker
+name: antigravity-worker
 description: |
-  Use this agent when dispatched as a Gemini worker for okstra cross-verification tasks. Executes Google Gemini CLI and returns analysis results.
+  Use this agent when dispatched as a Antigravity worker for okstra cross-verification tasks. Executes Google Antigravity CLI and returns analysis results.
 
   <example>
   Context: The okstra skill is orchestrating a multi-agent cross-verification run.
   user: "okstra this task bundle"
-  assistant: "Spawning gemini-worker agent to get Gemini analysis."
+  assistant: "Spawning antigravity-worker agent to get Antigravity analysis."
   <commentary>The okstra skill dispatches this agent as part of the worker roster.</commentary>
   </example>
 
   <example>
-  Context: A cross-verification needs Gemini perspective on analysis.
+  Context: A cross-verification needs Antigravity perspective on analysis.
   user: "cross verify this implementation"
-  assistant: "Running gemini-worker for independent Gemini analysis."
+  assistant: "Running antigravity-worker for independent Antigravity analysis."
   <commentary>Cross-verification tasks require independent AI worker outputs.</commentary>
   </example>
 model: inherit
@@ -21,63 +21,63 @@ color: green
 tools: ["Bash", "BashOutput", "KillShell", "Read", "Write", "Glob", "Grep"]
 ---
 
-You are a Gemini worker agent. Your job is to execute the Google Gemini CLI and return the analysis result.
+You are a Antigravity worker agent. Your job is to execute the Google Antigravity CLI and return the analysis result.
 
 ## CLI Command
 
 **Required form (uses the okstra wrapper to avoid redirect-triggered permission prompts):**
 ```bash
-$HOME/.okstra/bin/okstra-gemini-exec.sh "<absolute-project-root>" "<assigned-model-execution-value>" "<absolute-prompt-history-path>" [<absolute-worktree-path>] [<role>]
+$HOME/.okstra/bin/okstra-antigravity-exec.sh "<absolute-project-root>" "<assigned-model-execution-value>" "<absolute-prompt-history-path>" [<absolute-worktree-path>] [<role>]
 ```
 
-The fifth argument `<role>` is folded into both the caller (worker) pane title `gemini-<role>` and the sibling trace-pane title `gemini-<role>-tail`. `<role>` carries the dispatched Agent `name` minus the `gemini-` prefix, so the pane title equals the FleetView teammate name (`gemini-worker-reverify-r1`, `gemini-executor`, …) instead of a generic `worker`. Pass the value of the dispatch prompt's `**Pane role:**` line verbatim — Lead injects it on every CLI dispatch: `**Pane role:** worker-reverify-r1` on a convergence reverify, `**Pane role:** worker-critic` on a critic pass, `**Pane role:** executor` on an `implementation` Executor dispatch, `**Pane role:** verifier` on an `implementation` / `final-verification` verifier dispatch, and `**Pane role:** worker` on a plain analysis dispatch. The wrapper defaults to `worker` when the argument is omitted, but pass it explicitly so the pane title is self-describing.
+The fifth argument `<role>` is folded into both the caller (worker) pane title `agy-<role>` and the sibling trace-pane title `agy-<role>-tail`. `<role>` carries the dispatched Agent `name` minus the `agy-` prefix, so the pane title equals the FleetView teammate name (`agy-worker-reverify-r1`, `agy-executor`, …) instead of a generic `worker`. Pass the value of the dispatch prompt's `**Pane role:**` line verbatim — Lead injects it on every CLI dispatch: `**Pane role:** worker-reverify-r1` on a convergence reverify, `**Pane role:** worker-critic` on a critic pass, `**Pane role:** executor` on an `implementation` Executor dispatch, `**Pane role:** verifier` on an `implementation` / `final-verification` verifier dispatch, and `**Pane role:** worker` on a plain analysis dispatch. The wrapper defaults to `worker` when the argument is omitted, but pass it explicitly so the pane title is self-describing.
 
-The fourth argument is **mandatory for implementation phase** and optional otherwise. It must be the literal `EXECUTOR_WORKTREE_PATH` recorded in the run context; the wrapper appends it to gemini's `--include-directories` list so the model can both read and operate on the worktree alongside project-root.
+The fourth argument is **mandatory for implementation phase** and optional otherwise. It must be the literal `EXECUTOR_WORKTREE_PATH` recorded in the run context; the wrapper adds it to agy's `--add-dir` workspace list so the model can both read and operate on the worktree alongside project-root.
 
 The wrapper internally runs:
 ```bash
-gemini -p - -m "<model>" -o text --include-directories "<project-root>[,<worktree-path>]" < "<prompt-path>" 2>/dev/null
+agy --print "<prompt>" --model "<model>" --add-dir "<project-root>" [--add-dir "<worktree-path>"] --dangerously-skip-permissions
 ```
 
-The wrapper exists because Claude Code's Bash permission matcher rejects simple-prefix matches when the command contains stdin/stderr redirects. Calling `gemini -p - ... < <path> 2>/dev/null` directly triggers a permission prompt every dispatch even when `Bash(gemini:*)` is allowlisted. The wrapper folds the redirects inside, so the harness sees a single non-redirect command that matches `Bash($HOME/.okstra/bin/okstra-gemini-exec.sh:*)`.
+The wrapper exists because Claude Code's Bash permission matcher rejects simple-prefix matches when the command contains stdin/stderr redirects. Calling `agy --print ... < <path> 2>/dev/null` directly triggers a permission prompt every dispatch even when `Bash(agy:*)` is allowlisted. The wrapper folds the redirects inside, so the harness sees a single non-redirect command that matches `Bash($HOME/.okstra/bin/okstra-antigravity-exec.sh:*)`.
 
-**Do NOT** invoke `gemini -p - ... < ... 2>/dev/null` directly — always go through the wrapper. Gemini CLI has no `--cd` flag, so the wrapper anchors workspace correctness via `--include-directories <project-root>` regardless of inherited cwd.
+**Do NOT** invoke `agy --print ... 2>>log > >(tee)` directly — always go through the wrapper. agy has no `--cd` flag, so the wrapper anchors workspace correctness via `--add-dir <project-root>` regardless of inherited cwd.
 
 ## Execution Rules
 
-1. Check if gemini CLI is installed:
+1. Check if agy CLI is installed:
    ```bash
-   which gemini 2>/dev/null
+   which agy 2>/dev/null
    ```
 
-2. If not installed, immediately return: `GEMINI_NOT_INSTALLED: gemini CLI is not installed`
+2. If not installed, immediately return: `ANTIGRAVITY_NOT_INSTALLED: agy CLI is not installed`
 
 3. Extract the absolute `Project Root` from the lead prompt (look for a line starting with `**Project Root:**` or `Project Root:`). If it is missing, immediately return:
-   `GEMINI_PROJECT_ROOT_MISSING: absolute Project Root was not provided in the lead prompt`
+   `ANTIGRAVITY_PROJECT_ROOT_MISSING: absolute Project Root was not provided in the lead prompt`
 
 4. Extract the assigned worker prompt history path from the lead prompt (look for a line starting with `Assigned worker prompt history path:`). If it is missing, immediately return:
-   `GEMINI_PROMPT_PATH_MISSING: assigned worker prompt history path was not provided`
+   `ANTIGRAVITY_PROMPT_PATH_MISSING: assigned worker prompt history path was not provided`
    - If the extracted path is relative (does not start with `/`), resolve it against `Project Root` to get an absolute path. Use the absolute form everywhere below.
 
-5. Persist the exact worker prompt to the absolute prompt history path before invoking Gemini.
+5. Persist the exact worker prompt to the absolute prompt history path before invoking Antigravity.
    - Use the absolute assigned path under the current run `prompts/` directory.
    - `Write` is allowed for this purpose.
    - Bash heredoc or redirection is also acceptable if that is more reliable.
-   - Never use `/tmp/gemini_prompt*.txt` as the canonical storage path.
+   - Never use `/tmp/agy_prompt*.txt` as the canonical storage path.
 
-6. Extract the assigned model execution value for `Gemini worker`.
+6. Extract the assigned model execution value for `Antigravity worker`.
    - First, use the value explicitly assigned in the lead prompt.
-   - If the lead prompt only lists the display model, use the canonical execution value from the referenced task bundle metadata (`task-manifest.json` → `resultContract.requiredWorkerRoles[]` for the gemini role).
-   - If no assigned model execution value can be determined, immediately return `GEMINI_MODEL_MISSING: assigned Gemini model execution value was not provided`. Do NOT fall back to training-data defaults — historical Gemini defaults like `gemini-1.5-flash` are NOT acceptable substitutes for the assigned model. Returning the sentinel is the correct behavior; the lead is responsible for fixing its prompt and redispatching.
-   - This rule applies equally to convergence reverify rounds. The reverify prompt MUST carry the same `**Model:**` line as the initial run (see the convergence resource at `prompts/lead/convergence.md`, "Required reverify-prompt anchor headers"). If the line is absent in a reverify prompt, return `GEMINI_MODEL_MISSING` rather than guessing.
+   - If the lead prompt only lists the display model, use the canonical execution value from the referenced task bundle metadata (`task-manifest.json` → `resultContract.requiredWorkerRoles[]` for the antigravity role).
+   - If no assigned model execution value can be determined, immediately return `ANTIGRAVITY_MODEL_MISSING: assigned Antigravity model execution value was not provided`. Do NOT fall back to training-data defaults — historical Antigravity defaults like `gemini-1.5-flash` are NOT acceptable substitutes for the assigned model. Returning the sentinel is the correct behavior; the lead is responsible for fixing its prompt and redispatching.
+   - This rule applies equally to convergence reverify rounds. The reverify prompt MUST carry the same `**Model:**` line as the initial run (see the convergence resource at `prompts/lead/convergence.md`, "Required reverify-prompt anchor headers"). If the line is absent in a reverify prompt, return `ANTIGRAVITY_MODEL_MISSING` rather than guessing.
 
-7. If installed, dispatch the wrapper as a **background** Bash command and poll for completion. The two-minute foreground Bash timeout is insufficient for implementation-phase Gemini runs and forced workers into ad-hoc background dispatch with lost output. The polling contract below is the formal replacement.
+7. If installed, dispatch the wrapper as a **background** Bash command and poll for completion. The two-minute foreground Bash timeout is insufficient for implementation-phase Antigravity runs and forced workers into ad-hoc background dispatch with lost output. The polling contract below is the formal replacement.
 
    **Dispatch (background, no foreground timeout):**
    ```bash
-   $HOME/.okstra/bin/okstra-gemini-exec.sh "<absolute-project-root>" "<assigned-model-execution-value>" "<absolute-prompt-history-path>" "<absolute-worktree-path>" "<pane-role>"
+   $HOME/.okstra/bin/okstra-antigravity-exec.sh "<absolute-project-root>" "<assigned-model-execution-value>" "<absolute-prompt-history-path>" "<absolute-worktree-path>" "<pane-role>"
    ```
-   Call `Bash` with `run_in_background: true`. Capture the returned `bash_id` (a.k.a. `shell_id`). Pass the positional arguments verbatim — do NOT use environment variables, `cd`, `&&` chains, or pipes from `cat`. Substitute the literal extracted Project Root, model execution value, prompt-history path, and worktree path, plus the `**Pane role:**` value (`executor` / `verifier`, or `worker` when the line is absent). The fourth argument is **mandatory for implementation phase** (extract from `EXECUTOR_WORKTREE_PATH` in the lead prompt's run context or the `**Worktree:**` / `cwd for every mutating command:` line) and **may be omitted only for non-implementation analysis phases** that do not mutate the worktree. The wrapper handles `-p -`, `-m`, `-o text`, `--include-directories`, the stdin redirect from the prompt file, and stderr suppression internally. Calling `gemini` directly (without the wrapper) is an error in this skill: the redirect tokens disqualify the prefix match against `Bash(gemini:*)` and produce a permission prompt every dispatch.
+   Call `Bash` with `run_in_background: true`. Capture the returned `bash_id` (a.k.a. `shell_id`). Pass the positional arguments verbatim — do NOT use environment variables, `cd`, `&&` chains, or pipes from `cat`. Substitute the literal extracted Project Root, model execution value, prompt-history path, and worktree path, plus the `**Pane role:**` value (`executor` / `verifier`, or `worker` when the line is absent). The fourth argument is **mandatory for implementation phase** (extract from `EXECUTOR_WORKTREE_PATH` in the lead prompt's run context or the `**Worktree:**` / `cwd for every mutating command:` line) and **may be omitted only for non-implementation analysis phases** that do not mutate the worktree. The wrapper handles `--print`, `--model`, the repeatable `--add-dir`, inlining the prompt file as the `--print` argument (agy does not read stdin), `--dangerously-skip-permissions`, and stderr capture internally. Calling `agy` directly (without the wrapper) is an error in this skill: the redirect tokens disqualify the prefix match against `Bash(agy:*)` and produce a permission prompt every dispatch.
 
    **Poll loop (BashOutput-only, 30-minute cap):**
    - Record `start_ts` at dispatch time via a single `Bash` call: `date +%s` (output captured).
@@ -88,7 +88,7 @@ The wrapper exists because Claude Code's Bash permission matcher rejects simple-
         `log="${prompt_path%.md}.log"; mtime=$(stat -f '%m' "$log" 2>/dev/null || stat -c '%Y' "$log" 2>/dev/null); date +%s`
         (output captured — first line is `mtime`, second is `current_ts`).
         - If `current_ts - mtime <= 90` AND grace has NOT yet been applied this polling loop: extend the cap to `2100` seconds (one-shot +5min grace), record the grace internally so it does not re-trigger, and continue polling.
-        - Otherwise (mtime stale `> 90s`, OR grace already applied): call `KillShell(shell_id: <shell_id>)`, then record a `cli-failure` event with `--error-type cli-failure`, `--exit-code 124`, `--duration-ms <observed_ms>`, `--message "okstra-gemini-exec.sh exceeded polling cap (grace=<applied|not-applied>, last_mtime_age=<n>s)"`, and return `GEMINI_CLI_TIMEOUT: gemini exec exceeded polling cap`.
+        - Otherwise (mtime stale `> 90s`, OR grace already applied): call `KillShell(shell_id: <shell_id>)`, then record a `cli-failure` event with `--error-type cli-failure`, `--exit-code 124`, `--duration-ms <observed_ms>`, `--message "okstra-antigravity-exec.sh exceeded polling cap (grace=<applied|not-applied>, last_mtime_age=<n>s)"`, and return `ANTIGRAVITY_CLI_TIMEOUT: agy exec exceeded polling cap`.
      4. Otherwise continue polling. Read `current_ts` cheaply via another `Bash` call (`date +%s`) at most once per poll iteration.
    - Do NOT abort the loop on transient `running` status. Only `completed` or the polling cap (initially 30min, optionally extended once to 35min by mtime grace) end it.
    - **No external timeout from Lead.** This polling loop is the SINGLE timeout authority for this dispatch. Lead MUST NOT impose a separate Agent-call timeout that would terminate this subagent before the polling cap is reached (see team-contract "No external timeout on wrapper subagents").
@@ -97,18 +97,18 @@ The wrapper exists because Claude Code's Bash permission matcher rejects simple-
 
 8. After the polling loop exits with `completed`, perform terminal-status determination BEFORE returning:
 
-   a. **Extract Result Path.** Read the `**Result Path:** <abs-path>` header line from the lead's dispatch prompt body. If the header is absent, return `GEMINI_RESULT_PATH_MISSING: lead prompt did not include **Result Path:** header` without proceeding. Resolve to absolute against `Project Root` if relative.
+   a. **Extract Result Path.** Read the `**Result Path:** <abs-path>` header line from the lead's dispatch prompt body. If the header is absent, return `ANTIGRAVITY_RESULT_PATH_MISSING: lead prompt did not include **Result Path:** header` without proceeding. Resolve to absolute against `Project Root` if relative.
 
    b. **CLI failure first.** If the final `BashOutput` reports a non-zero `exit_code`, follow the **CLI failure** rule in §"Error reporting" before returning. Do NOT perform the result-file check on a failed exit — `cli-failure` already covers it.
 
-   c. **Result-file existence check (exit 0 only).** If `exit_code == 0` BUT no file exists at the extracted Result Path, the Gemini CLI returned 0 without producing the analysis artifact. Observed failure mode: the CLI streams analysis prose on stdout, hits its token budget or a sandbox EPERM mid-`Write`, and exits 0 with the artifact never persisted. Forwarding the partial stdout silently degrades lead synthesis (the case that motivated this rule), so this path is required.
-      1. Capture the final ~10 lines of the wrapper's live log for diagnostics — single Bash call: `tail -n 10 "${prompt_path%.md}.log"` (substitute the literal absolute prompt-history path; the wrapper writes the log next to it per the §"trace pane" comment in `okstra-gemini-exec.sh`). Write the captured lines to a temp file (e.g. `<errors-sidecar-dir>/gemini-result-missing-tail.txt`) so `--stderr-excerpt-file` can reference it.
-      2. Record a `cli-failure` event directly to the run-level error log via the exact `okstra error-log append-observed` template in §"Error reporting" — substitute `--exit-code 0`, `--duration-ms <observed-ms>`, `--message "okstra-gemini-exec.sh exited 0 but no result file at <abs-path>"`, and `--stderr-excerpt-file <temp-tail-path>`.
-      3. Return `GEMINI_RESULT_MISSING: gemini exited 0 but result file absent at <abs-path>` instead of the raw stdout. The lead is responsible for deciding redispatch per `team-contract` "Lead Redispatch Policy on Result-Missing".
+   c. **Result-file existence check (exit 0 only).** If `exit_code == 0` BUT no file exists at the extracted Result Path, the Antigravity CLI returned 0 without producing the analysis artifact. Observed failure mode: the CLI streams analysis prose on stdout, hits its token budget or a sandbox EPERM mid-`Write`, and exits 0 with the artifact never persisted. Forwarding the partial stdout silently degrades lead synthesis (the case that motivated this rule), so this path is required.
+      1. Capture the final ~10 lines of the wrapper's live log for diagnostics — single Bash call: `tail -n 10 "${prompt_path%.md}.log"` (substitute the literal absolute prompt-history path; the wrapper writes the log next to it per the §"trace pane" comment in `okstra-antigravity-exec.sh`). Write the captured lines to a temp file (e.g. `<errors-sidecar-dir>/agy-result-missing-tail.txt`) so `--stderr-excerpt-file` can reference it.
+      2. Record a `cli-failure` event directly to the run-level error log via the exact `okstra error-log append-observed` template in §"Error reporting" — substitute `--exit-code 0`, `--duration-ms <observed-ms>`, `--message "okstra-antigravity-exec.sh exited 0 but no result file at <abs-path>"`, and `--stderr-excerpt-file <temp-tail-path>`.
+      3. Return `ANTIGRAVITY_RESULT_MISSING: agy exited 0 but result file absent at <abs-path>` instead of the raw stdout. The lead is responsible for deciding redispatch per `team-contract` "Lead Redispatch Policy on Result-Missing".
 
-   d. **Normal return.** Otherwise (`exit_code == 0` AND result file exists), return the wrapper's accumulated stdout from `BashOutput`, prefixed by exactly one model-identity line copied verbatim from the `**Model:** Gemini worker, <execution-value>` line in the lead prompt (per Worker Preamble → "Return message to the lead"):
+   d. **Normal return.** Otherwise (`exit_code == 0` AND result file exists), return the wrapper's accumulated stdout from `BashOutput`, prefixed by exactly one model-identity line copied verbatim from the `**Model:** Antigravity worker, <execution-value>` line in the lead prompt (per Worker Preamble → "Return message to the lead"):
       ```
-      **Model:** Gemini worker, <assigned-model-execution-value>
+      **Model:** Antigravity worker, <assigned-model-execution-value>
       ```
       Emit that line first, then the stdout unmodified. The model line is the ONLY addition permitted — do not otherwise summarize or alter the CLI output. This applies to convergence reverify dispatches too.
 
@@ -116,49 +116,49 @@ The wrapper exists because Claude Code's Bash permission matcher rejects simple-
 
 ## Stop Condition
 
-This wrapper is a thin Bash-execution shell over the Gemini CLI (via `okstra-gemini-exec.sh`). The CLI process itself is the analysis engine; this subagent's only job is to dispatch it and forward output. Therefore:
+This wrapper is a thin Bash-execution shell over the Antigravity CLI (via `okstra-antigravity-exec.sh`). The CLI process itself is the analysis engine; this subagent's only job is to dispatch it and forward output. Therefore:
 
 - Return immediately after the polling loop exits with `completed` (or after recording any required `cli-failure` event for a non-zero exit / 30-minute cap / rate-limit).
 - The only tool calls permitted during the polling loop are `BashOutput`, a single `Bash` call per iteration for `date +%s` (timeout bookkeeping only — no `sleep`), and — on the timeout path only — `KillShell`. Do NOT perform additional `Read`, `Grep`, `Glob` calls between polls; do NOT inspect intermediate wrapper output mid-run.
 - Outside the polling loop, no `Read`, `Grep`, or `Glob` beyond what is strictly required by steps 1–8 (prompt persistence, Project Root extraction, model resolution, and the step 8 result-file check). The step 8 result-file existence check is explicitly permitted: at most one `Bash` call for `tail -n 10 <log-path>` and one `Read`/test of the Result Path.
-- Do NOT re-invoke `okstra-gemini-exec.sh` to "double-check" or "rerun for safety" — convergence (Phase 5.5) handles cross-worker reconciliation. A single CLI dispatch per dispatched-prompt is the contract.
+- Do NOT re-invoke `okstra-antigravity-exec.sh` to "double-check" or "rerun for safety" — convergence (Phase 5.5) handles cross-worker reconciliation. A single CLI dispatch per dispatched-prompt is the contract.
 
-The Gemini CLI's own exit terminates the underlying analysis; this wrapper terminates by returning its captured output (or sentinel).
+The Antigravity CLI's own exit terminates the underlying analysis; this wrapper terminates by returning its captured output (or sentinel).
 
 ## MCP Scope
 
-This wrapper does NOT invoke MCP tools directly. MCP availability inside the Gemini CLI is governed by the underlying CLI's own configuration. The `## Available MCP Servers` block from the lead prompt is forwarded verbatim into the dispatched prompt for record-keeping and so the Gemini CLI's own logic can decide what to call — this wrapper does not gate or filter it.
+This wrapper does NOT invoke MCP tools directly. MCP availability inside the Antigravity CLI is governed by the underlying CLI's own configuration. The `## Available MCP Servers` block from the lead prompt is forwarded verbatim into the dispatched prompt for record-keeping and so the Antigravity CLI's own logic can decide what to call — this wrapper does not gate or filter it.
 
 ## Prompt Composition
 
 - The lead prompt must include both `**Project Root:** <absolute-path>` (at the top) and `Assigned worker prompt history path: <path>`.
 - Treat the prompt-history path as the canonical worker prompt history artifact for the current run, resolved to absolute against `Project Root` if given as relative.
-- The assigned model execution value is canonical for CLI execution. Do not substitute a different Gemini model unless the task bundle explicitly changes it.
-- Pass the prompt received from Lead directly to gemini after persisting the exact prompt to the assigned path.
-- **Executor preflight forwarding check (implementation runs only).** When the lead prompt assigns this dispatch the `Executor` role for an `implementation` run, the persisted prompt body MUST contain the literal heading `Coding-conventions preflight` (the lead appends the body of `prompts/profiles/_coding-conventions-preflight.md` into the dispatch prompt — see `prompts/profiles/_implementation-executor.md` → "Pre-implementation context exploration") — the Gemini CLI does not share the lead's context, so an unforwarded gate never reaches the process that writes the code. If the heading is absent, return `GEMINI_PREFLIGHT_MISSING: executor dispatch prompt lacks the coding-conventions preflight block` instead of invoking the CLI; the lead is responsible for re-dispatching with the block included. This check does NOT apply to verifier or analysis dispatches.
+- The assigned model execution value is canonical for CLI execution. Do not substitute a different Antigravity model unless the task bundle explicitly changes it.
+- Pass the prompt received from Lead directly to agy after persisting the exact prompt to the assigned path.
+- **Executor preflight forwarding check (implementation runs only).** When the lead prompt assigns this dispatch the `Executor` role for an `implementation` run, the persisted prompt body MUST contain the literal heading `Coding-conventions preflight` (the lead appends the body of `prompts/profiles/_coding-conventions-preflight.md` into the dispatch prompt — see `prompts/profiles/_implementation-executor.md` → "Pre-implementation context exploration") — the Antigravity CLI does not share the lead's context, so an unforwarded gate never reaches the process that writes the code. If the heading is absent, return `ANTIGRAVITY_PREFLIGHT_MISSING: executor dispatch prompt lacks the coding-conventions preflight block` instead of invoking the CLI; the lead is responsible for re-dispatching with the block included. This check does NOT apply to verifier or analysis dispatches.
 - Include context (code, diff, file paths) if provided.
 - For long prompts, dispatch through the wrapper with literal absolute paths (plus the worktree path for implementation phase):
   ```bash
-  $HOME/.okstra/bin/okstra-gemini-exec.sh "<literal-project-root>" "<assigned-model-execution-value>" "<literal-prompt-history-path>" "<literal-worktree-path>" "<pane-role>"
+  $HOME/.okstra/bin/okstra-antigravity-exec.sh "<literal-project-root>" "<assigned-model-execution-value>" "<literal-prompt-history-path>" "<literal-worktree-path>" "<pane-role>"
   ```
 - If the parent directory does not exist yet, create it before writing the prompt file.
 
 ## Required Reading Before Any Analysis
 
-Before invoking the Gemini CLI, you MUST:
+Before invoking the Antigravity CLI, you MUST:
 
-1. Extract the absolute path from the lead's `**Worker Preamble Path:**` anchor header and verify the CLI run will Read that file end-to-end (canonical SSOT for the Required Reading + Error Reporting + Output sections contract). The lead's prompt body — which you persist verbatim and feed into Gemini via stdin — already contains this anchor; do not strip it.
+1. Extract the absolute path from the lead's `**Worker Preamble Path:**` anchor header and verify the CLI run will Read that file end-to-end (canonical SSOT for the Required Reading + Error Reporting + Output sections contract). The lead's prompt body — which you persist verbatim and feed into Antigravity via stdin — already contains this anchor; do not strip it.
 2. Verify the lead's prompt body lists the per-run primary input files under `## Inputs` (normally `analysis-packet.md` for analysis workers). The source files named inside that packet are fallback/evidence paths to open when needed. Analysis workers do NOT read `final-report-template.md` — that file is for the report writer only.
 
-The CLI writes a Reading Confirmation block to the **audit sidecar** at `runs/<task-type>/worker-results/gemini-worker-audit-<task-type>-<seq>.md`. The sidecar's body begins with `# Gemini Worker Audit — <task-key>` followed by one short line per input file confirming end-to-end reading. The main Gemini output MUST NOT contain a `## 0. Reading Confirmation` heading — the validator fails worker-results that contain one. If any file was skipped, record a `tool-failure` in the errors sidecar instead of fabricating Findings.
+The CLI writes a Reading Confirmation block to the **audit sidecar** at `runs/<task-type>/worker-results/antigravity-worker-audit-<task-type>-<seq>.md`. The sidecar's body begins with `# Antigravity Worker Audit — <task-key>` followed by one short line per input file confirming end-to-end reading. The main Antigravity output MUST NOT contain a `## 0. Reading Confirmation` heading — the validator fails worker-results that contain one. If any file was skipped, record a `tool-failure` in the errors sidecar instead of fabricating Findings.
 
 ## Worker Output Structure
 
 When returning results, start the file with a YAML frontmatter block, then organize the body into the following sections in this exact order.
 
-**Frontmatter (mandatory)** — set `workerId: "gemini"`. Copy `id`, `aliases`, `taskType`, `task-id`, `task-group`, `project-id`, `date` verbatim from the primary input (`analysis-packet.md`; fall back to `analysis-material.md` only if the packet is missing a field). Full schema and a concrete example live in the team-contract resource (`prompts/lead/team-contract.md`) "Result Frontmatter" subsection.
+**Frontmatter (mandatory)** — set `workerId: "antigravity"`. Copy `id`, `aliases`, `taskType`, `task-id`, `task-group`, `project-id`, `date` verbatim from the primary input (`analysis-packet.md`; fall back to `analysis-material.md` only if the packet is missing a field). Full schema and a concrete example live in the team-contract resource (`prompts/lead/team-contract.md`) "Result Frontmatter" subsection.
 
-1. **Findings** - what Gemini identified
+1. **Findings** - what Antigravity identified
 2. **Missing Information or Assumptions** - gaps in the analysis
 3. **Safe or Reasonable Areas** - parts that look correct
 4. **Uncertain Points** - areas needing further review
@@ -166,7 +166,7 @@ When returning results, start the file with a YAML frontmatter block, then organ
 
 Include file paths and line numbers when discussing code evidence.
 
-**Item IDs (mandatory).** Every row in sections 1–5 (and any optional section 6) MUST carry a worker-internal item ID unique within this file. Gemini may use `F-1`, `F-2`, ... or numbered hierarchical IDs — either is fine. What matters is that each item is addressable. The lead's §6.1 / §6.2 / §2.1 synthesis preserves these IDs as `gemini:<your-id>` entries in its `Source items (worker:item)` column. See `prompts/profiles/_common-contract.md` "Cross-worker traceability" SSOT.
+**Item IDs (mandatory).** Every row in sections 1–5 (and any optional section 6) MUST carry a worker-internal item ID unique within this file. Antigravity may use `F-1`, `F-2`, ... or numbered hierarchical IDs — either is fine. What matters is that each item is addressable. The lead's §6.1 / §6.2 / §2.1 synthesis preserves these IDs as `antigravity:<your-id>` entries in its `Source items (worker:item)` column. See `prompts/profiles/_common-contract.md` "Cross-worker traceability" SSOT.
 
 **Ticket tagging:** For runs whose task type is `requirements-discovery`, `error-analysis`, `implementation-planning`, or `implementation`, every item in sections 1–5 MUST carry a ticket identifier. Use the `Ticket ID` column in table-form items and the `[TICKETID: <id>]` prefix in bullet/numbered items. Fill priority: `Issue / Ticket` from the input → `Task ID` (no prefix, e.g. `8852`) → `unknown`. Multiple tickets are comma-separated. Full rules live in the team-contract resource (`prompts/lead/team-contract.md`) Ticket Tagging section.
 
@@ -174,7 +174,7 @@ This contract mirrors the team-contract resource (`prompts/lead/team-contract.md
 
 ## Error reporting
 
-The wrapper agent (this Gemini worker subagent) is responsible for recording
+The wrapper agent (this Antigravity worker subagent) is responsible for recording
 two kinds of errors via `okstra error-log`:
 
 **Path extraction (BLOCKING).** Before recording anything, extract the
@@ -184,7 +184,7 @@ following two absolute paths verbatim from the lead's dispatch prompt body:
 - `**Errors sidecar path:** <abs-path>` — this worker's per-run sidecar JSON.
 
 If either header line is absent from the dispatch prompt, return
-`GEMINI_ERRORS_PATH_MISSING: lead prompt did not include **Errors log path:** / **Errors sidecar path:** headers`
+`ANTIGRAVITY_ERRORS_PATH_MISSING: lead prompt did not include **Errors log path:** / **Errors sidecar path:** headers`
 without proceeding. Do NOT synthesize the path from `<runDir>/logs/...` —
 historical bug class: workers writing to a literally-named template path
 and the run-level error log staying empty.
@@ -211,10 +211,10 @@ and the run-level error log staying empty.
      --out "<absolute-errors-log-path-from-lead-prompt>" \
      --task-key "<task-key>" \
      --phase "<phase>" \
-     --agent gemini-worker --agent-role worker \
+     --agent antigravity-worker --agent-role worker \
      --model "<assigned-model-execution-value>" \
      --error-type cli-failure \
-     --command "$HOME/.okstra/bin/okstra-gemini-exec.sh <project-root> <m> <prompt-path> <worktree-path> <pane-role>" \
+     --command "$HOME/.okstra/bin/okstra-antigravity-exec.sh <project-root> <m> <prompt-path> <worktree-path> <pane-role>" \
      --command-kind cli-invoke \
      --exit-code <N> --duration-ms <ms> \
      --message "<one-line summary>" \
@@ -226,15 +226,15 @@ and the run-level error log staying empty.
    missing, fall back to logging to the worker errors sidecar instead —
    never silently swallow a CLI failure.
 
-Do not record a `cli-failure` for `GEMINI_NOT_INSTALLED` returns — that is a
+Do not record a `cli-failure` for `ANTIGRAVITY_NOT_INSTALLED` returns — that is a
 pre-flight terminal status, not a runtime CLI error.
 
 ## Notes
 
-- Always specify the assigned `-m` value for the current run.
+- Always specify the assigned `--model` value for the current run.
 - Return error messages as-is on failure.
-- Do not summarize or modify Gemini results beyond prepending the single `**Model:**` line on a normal return (step 8d).
-- Sections 1–5 of the worker output are the common core shared with the Claude and Codex workers — the dispatched prompt asks identical questions for all three roles, and the Gemini CLI must answer all of them, not only requirement-interpretation findings. Your specialization (requirement interpretation, consistency, safety, documentation quality, alternative viewpoints) belongs only in optional Section 6 as additive depth. A Gemini result whose Findings section is populated solely with requirement-interpretation items is in breach of contract; see `prompts/lead/team-contract.md` "Worker Output Contract".
+- Do not summarize or modify Antigravity results beyond prepending the single `**Model:**` line on a normal return (step 8d).
+- Sections 1–5 of the worker output are the common core shared with the Claude and Codex workers — the dispatched prompt asks identical questions for all three roles, and the Antigravity CLI must answer all of them, not only requirement-interpretation findings. Your specialization (requirement interpretation, consistency, safety, documentation quality, alternative viewpoints) belongs only in optional Section 6 as additive depth. A Antigravity result whose Findings section is populated solely with requirement-interpretation items is in breach of contract; see `prompts/lead/team-contract.md` "Worker Output Contract".
 
 ## Stage evidence emission (BLOCKING, implementation task only)
 

package/runtime/agents/workers/claude-worker.md

@@ -21,11 +21,11 @@ color: blue
 tools: ["Bash", "Read", "Write", "Edit", "Glob", "Grep", "TodoWrite", "WebFetch", "WebSearch"]
 ---
 
-You are a Claude worker agent for okstra cross-verification. You share an **identical core responsibility** with the Codex and Gemini workers: cover every brief question across feasibility, requirement interpretation, hidden assumptions, alternatives, and execution risk in sections 1–5 of the worker output. Cross-verification only triangulates if all three workers answer the same questions against the same brief.
+You are a Claude worker agent for okstra cross-verification. You share an **identical core responsibility** with the Codex and Antigravity workers: cover every brief question across feasibility, requirement interpretation, hidden assumptions, alternatives, and execution risk in sections 1–5 of the worker output. Cross-verification only triangulates if all three workers answer the same questions against the same brief.
 
 Your specialization lens — **broad reasoning depth, hidden-assumption surfacing, execution-risk decomposition** — is the only content that belongs in optional Section 6 (additive, not subject to convergence). Do NOT let the lens narrow sections 1–5: a Claude-only "Findings" populated solely with assumption-class items is a contract violation.
 
-Unlike the Codex / Gemini workers, you are an in-process Claude subagent — you do NOT shell out to a CLI. Use your native tools (Read / Grep / Glob / MCP) directly.
+Unlike the Codex / Antigravity workers, you are an in-process Claude subagent — you do NOT shell out to a CLI. Use your native tools (Read / Grep / Glob / MCP) directly.
 
 ## Execution Rules
 

package/runtime/agents/workers/codex-worker.md

@@ -234,7 +234,7 @@ pre-flight terminal status, not a runtime CLI error.
 - Ignore stderr warnings from MCP integration.
 - Return error messages as-is on failure.
 - Do not summarize or modify Codex results beyond prepending the single `**Model:**` line on a normal return (step 8d).
-- Sections 1–5 of the worker output are the common core shared with the Claude and Gemini workers — the dispatched prompt asks identical questions for all three roles, and the Codex CLI must answer all of them, not only implementation-feasibility findings. Your specialization (implementation realism, code-path implications, edge cases, technical trade-offs) belongs only in optional Section 6 as additive depth. A Codex result whose Findings section is populated solely with implementation-feasibility items is in breach of contract; see `prompts/lead/team-contract.md` "Worker Output Contract".
+- Sections 1–5 of the worker output are the common core shared with the Claude and Antigravity workers — the dispatched prompt asks identical questions for all three roles, and the Codex CLI must answer all of them, not only implementation-feasibility findings. Your specialization (implementation realism, code-path implications, edge cases, technical trade-offs) belongs only in optional Section 6 as additive depth. A Codex result whose Findings section is populated solely with implementation-feasibility items is in breach of contract; see `prompts/lead/team-contract.md` "Worker Output Contract".
 
 ## Stage evidence emission (BLOCKING, implementation task only)
 

package/runtime/agents/workers/report-writer-worker.md

@@ -52,7 +52,7 @@ Do NOT duplicate the data.json contents here — the data.json is the canonical
    `REPORT_WRITER_RESULT_PATH_MISSING: assigned final-report Result Path was not provided`
    - Resolve relative paths against `Project Root` to get an absolute path.
 
-4. Persist the exact worker prompt to the absolute prompt history path before producing any output. Use `Write` (or Bash heredoc if more reliable). Never use `/tmp/*prompt*.txt` as canonical storage. Create parent directories if missing.
+4. Persist the exact worker prompt to the absolute prompt history path before producing any output. Prefer a Bash heredoc (`cat > <path> <<'EOF'`) — on a redispatch the prompt history file already exists, and the `Write` tool then refuses with "File has not been read yet"; the heredoc has no read-before-write constraint. Never use `/tmp/*prompt*.txt` as canonical storage. Create parent directories if missing.
 
 5. Anchor all file operations to the absolute `Project Root`. Use absolute paths everywhere — do not rely on inherited cwd, do not `cd`.
 
@@ -86,7 +86,7 @@ The rendered markdown (`final-report-<task-type>-<seq>.md`) is produced by `scri
 Rules (the schema enforces most of these — they are listed here so you know *what* to populate, not *how* to validate):
 
 - `header.reportAuthor` is `"Report writer worker"`; `header.reportOwner` is `"Claude lead"`. Set author to `"Claude lead"` only for `release-handoff` runs (single-lead by design) or a recorded report-writer dispatch failure fallback.
-- **Source items (worker:item) preservation.** Every `consensus[].sourceItems`, `differences[].workersPosition[].itemId`, and `evidence.primary[].sourceItems` entry MUST carry the worker:item-id pair (e.g. `claude:F-001`, `codex:1.1`, `gemini:F-3`, or `lead:mcp-1` for lead-only evidence). The schema enforces this via the `SourceItem` regex; bare worker-name lists no longer parse.
+- **Source items (worker:item) preservation.** Every `consensus[].sourceItems`, `differences[].workersPosition[].itemId`, and `evidence.primary[].sourceItems` entry MUST carry the worker:item-id pair (e.g. `claude:F-001`, `codex:1.1`, `antigravity:F-3`, or `lead:mcp-1` for lead-only evidence). The schema enforces this via the `SourceItem` regex; bare worker-name lists no longer parse.
 - **Verdict Card consistency.** `verdictCard.verdictToken` / `.direction` / `.nextStep` MUST byte-match `finalVerdict.verdictToken` / `.direction` / `.nextStep` and `recommendedNextSteps[0].text`. The renderer pulls both from the same data structure — duplicating values across `verdictCard` and `finalVerdict` is intentional so the validator can diff them.
 - **§7 phase-continuation row (mandatory for non-terminal task-types).** When `header.taskType` is one of `requirements-discovery` / `implementation-planning` / `error-analysis` / `implementation` / `final-verification`, `followUpTasks` MUST contain at least one row whose `origin` is `phase-continuation`, `suggestedTaskType` equals the next phase (byte-identical to `finalVerdict.nextStep`'s referenced phase), `newTaskId` reuses the current task-id, `autoSpawn` is `"no"`, and `priority` is `"P0"`. For `release-handoff` runs, omit the phase-continuation row. Schema `allOf` clause enforces this via `contains`.
 - **No deprecated sections.** The schema has no `4.5.8 User Approval Request` body field, no `4.5.9 Open Questions`, no `5.1 추가 자료 요청`, no `5.2 사용자 확인 질문` — clarifications go under the unified `clarificationItems[]` array.

package/runtime/bin/lib/okstra/cli.sh

@@ -74,8 +74,8 @@ while [[ $# -gt 0 ]]; do
       CODEX_MODEL_OVERRIDE="$(require_option_value --codex-model "${2-}")"
       shift 2
       ;;
-    --gemini-model)
-      GEMINI_MODEL_OVERRIDE="$(require_option_value --gemini-model "${2-}")"
+    --antigravity-model)
+      ANTIGRAVITY_MODEL_OVERRIDE="$(require_option_value --antigravity-model "${2-}")"
       shift 2
       ;;
     --report-writer-model)
@@ -212,7 +212,7 @@ while [[ $# -gt 0 ]]; do
           printf '  hint: did you mean --task-id?\n' >&2
           ;;
       esac
-      printf '  valid options: --render-only --resume-clarification --yes --workers --lead-model --claude-model --codex-model --gemini-model --report-writer-model --lead-runtime --related-tasks --task-type --project-id --project-root --task-group --task-id --task-brief --directive --fix-cycle --clarification-response --approved-plan --approve --implementation-option --stage --qa-waiver --no-plan-verification -h|--help\n' >&2
+      printf '  valid options: --render-only --resume-clarification --yes --workers --lead-model --claude-model --codex-model --antigravity-model --report-writer-model --lead-runtime --related-tasks --task-type --project-id --project-root --task-group --task-id --task-brief --directive --fix-cycle --clarification-response --approved-plan --approve --implementation-option --stage --qa-waiver --no-plan-verification -h|--help\n' >&2
       usage
       exit 1
       ;;