CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-09-16 09:55:29 +02:00
Code Issues Packages Projects Releases Wiki Activity

v1.87.3.0 fix: bind review evidence to the reviewed tree (#2875)

Browse Source 
* fix(review): bind evidence to completed unchanged review passes

* fix(review): keep unresolved Codex findings unverified

* docs: update review evidence documentation for v1.87.3.0

* test(cso): let Windows integration finish within subprocess budgets

* docs: update project documentation for v1.87.3.0

---------

Co-authored-by: garrytan <19957+garrytan@users.noreply.github.com>
This commit is contained in:
Garry Tan
2026-09-15 20:53:58 +00:00
committed by GitHub
co-authored by garrytan
parent 43c9e45ea7
commit 85b8c038fc
37 changed files with 640 additions and 166 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/fixtures/golden/claude-ship-SKILL.md
Vendored
+7 -7
View File
@@ -620,17 +620,17 @@ Display:
- **Outside Voice (default-on):** Independent plan review through the host-selected provider after /plan-ceo-review and /plan-eng-review. The codex_reviews switch disables the entire extra step. Provider failure uses the existing native fallback and reports missing outside coverage. Never gates shipping.
**Verdict logic:**
- **CLEARED**: Eng Review has >= 1 entry within 7 days from either \`review\` or \`plan-eng-review\` with status "clean" (or \`skip_eng_review\` is \`true\`)
- **CLEARED**: Eng Review has >= 1 entry within 7 days from either \`review\` or \`plan-eng-review\` with status "clean"; diff review must also grade CURRENT below (or \`skip_eng_review\` is \`true\`)
- **NOT CLEARED**: Eng Review missing, stale (>7 days), or has open issues
- CEO, Design, and outside reviews are shown for context but never block shipping
- If \`skip_eng_review\` config is \`true\`, Eng Review shows "SKIPPED (global)" and verdict is CLEARED
**Staleness detection:** After displaying the dashboard, check if any existing reviews may be stale:
- **Content-first rule (diff-scoped rows only: \`review\`, \`adversarial-review\`, \`codex-review\`, ship-stage entries).** Parse the \`---WTREE---\` and \`---DIRTY---\` sections from the bash output. If an entry has a \`wtree\` field AND it equals the current \`---WTREE---\` value, the review is CURRENT — identical content, regardless of commit count, rebase, amend, or whether it was committed yet (wtree equality alone proves identical content; that is the keystone property). Skip the commit-count heuristic for that entry and show no staleness note.
- Plan-tier rows (plan-ceo-review, plan-eng-review, plan-design-review) grade a plan file, not the repo tree — never apply the wtree rule to them; they keep the 7-day freshness logic. If such an entry carries a \`plan_sha256\` field, you MAY compare it against the current plan file's sha256 and note "plan changed since review" on mismatch.
- Fallback (no \`wtree\` on the entry, or wtree mismatch): parse the \`---HEAD---\` section to get the current HEAD commit hash. For each review entry that has a \`commit\` field: compare it against the current HEAD. If different, count elapsed commits: \`git rev-list --count STORED_COMMIT..HEAD\`. If that command FAILS (the stored commit was rebased away), grade UNKNOWN and treat as stale — do not error. Display: "Note: {skill} review from {date} may be stale — {N} commits since review"
- For entries without a \`commit\` field (legacy entries): display "Note: {skill} review from {date} has no commit tracking — consider re-running for accurate staleness detection"
- If all reviews grade CURRENT (wtree match or HEAD match), do not display any staleness notes
**Staleness detection:** Grade before deciding CLEARED:
- Ship telemetry reports metrics, not review coverage; it never satisfies a review row.
- **Content-first rule (diff-scoped rows only: `review`, `adversarial-review`, `codex-review`, ship-stage entries, `design-review-lite`).** Use the helper's computed `review_freshness.status` and show its `reason`. CURRENT requires a completed clean pass with captured start/end wtree equal to the current `---WTREE---`. STALE or UNVERIFIED never clears Eng Review. Missing `review_freshness` is UNVERIFIED, including legacy log-only rows. Never fall back to HEAD equality or commit distance for diff evidence, even at 0 commits. Show recorded cycles, completed/converged state, and missing per-source/phase coverage; unknown is not a pass.
- Plan-tier rows (plan-ceo-review, plan-eng-review, plan-design-review, codex-plan-review) grade a plan file, not the repo tree — never apply the wtree rule to them; they keep the 7-day freshness logic. If an entry carries `plan_sha256`, you MAY compare it with the plan file and note "plan changed since review" on mismatch.
- Plan-tier fallback only: parse `---HEAD---`. For entries with a different `commit`, count elapsed commits: `git rev-list --count STORED_COMMIT..HEAD`. If that command FAILS, grade UNKNOWN and treat as stale. Display: "Note: {skill} review from {date} may be stale — {N} commits since review". Missing commit tracking retains the legacy note to consider re-running.
- If all reviews grade CURRENT, do not display staleness notes
If the Eng Review is NOT "CLEAR":
test/fixtures/golden/codex-ship-SKILL.md
Vendored
+21 -13
View File
@@ -613,17 +613,17 @@ Display:
- **Outside Voice (default-on):** Independent plan review through the host-selected provider after /plan-ceo-review and /plan-eng-review. The codex_reviews switch disables the entire extra step. Provider failure uses the existing native fallback and reports missing outside coverage. Never gates shipping.
**Verdict logic:**
- **CLEARED**: Eng Review has >= 1 entry within 7 days from either \`review\` or \`plan-eng-review\` with status "clean" (or \`skip_eng_review\` is \`true\`)
- **CLEARED**: Eng Review has >= 1 entry within 7 days from either \`review\` or \`plan-eng-review\` with status "clean"; diff review must also grade CURRENT below (or \`skip_eng_review\` is \`true\`)
- **NOT CLEARED**: Eng Review missing, stale (>7 days), or has open issues
- CEO, Design, and outside reviews are shown for context but never block shipping
- If \`skip_eng_review\` config is \`true\`, Eng Review shows "SKIPPED (global)" and verdict is CLEARED
**Staleness detection:** After displaying the dashboard, check if any existing reviews may be stale:
- **Content-first rule (diff-scoped rows only: \`review\`, \`adversarial-review\`, \`codex-review\`, ship-stage entries).** Parse the \`---WTREE---\` and \`---DIRTY---\` sections from the bash output. If an entry has a \`wtree\` field AND it equals the current \`---WTREE---\` value, the review is CURRENT — identical content, regardless of commit count, rebase, amend, or whether it was committed yet (wtree equality alone proves identical content; that is the keystone property). Skip the commit-count heuristic for that entry and show no staleness note.
- Plan-tier rows (plan-ceo-review, plan-eng-review, plan-design-review) grade a plan file, not the repo tree — never apply the wtree rule to them; they keep the 7-day freshness logic. If such an entry carries a \`plan_sha256\` field, you MAY compare it against the current plan file's sha256 and note "plan changed since review" on mismatch.
- Fallback (no \`wtree\` on the entry, or wtree mismatch): parse the \`---HEAD---\` section to get the current HEAD commit hash. For each review entry that has a \`commit\` field: compare it against the current HEAD. If different, count elapsed commits: \`git rev-list --count STORED_COMMIT..HEAD\`. If that command FAILS (the stored commit was rebased away), grade UNKNOWN and treat as stale — do not error. Display: "Note: {skill} review from {date} may be stale — {N} commits since review"
- For entries without a \`commit\` field (legacy entries): display "Note: {skill} review from {date} has no commit tracking — consider re-running for accurate staleness detection"
- If all reviews grade CURRENT (wtree match or HEAD match), do not display any staleness notes
**Staleness detection:** Grade before deciding CLEARED:
- Ship telemetry reports metrics, not review coverage; it never satisfies a review row.
- **Content-first rule (diff-scoped rows only: `review`, `adversarial-review`, `codex-review`, ship-stage entries, `design-review-lite`).** Use the helper's computed `review_freshness.status` and show its `reason`. CURRENT requires a completed clean pass with captured start/end wtree equal to the current `---WTREE---`. STALE or UNVERIFIED never clears Eng Review. Missing `review_freshness` is UNVERIFIED, including legacy log-only rows. Never fall back to HEAD equality or commit distance for diff evidence, even at 0 commits. Show recorded cycles, completed/converged state, and missing per-source/phase coverage; unknown is not a pass.
- Plan-tier rows (plan-ceo-review, plan-eng-review, plan-design-review, codex-plan-review) grade a plan file, not the repo tree — never apply the wtree rule to them; they keep the 7-day freshness logic. If an entry carries `plan_sha256`, you MAY compare it with the plan file and note "plan changed since review" on mismatch.
- Plan-tier fallback only: parse `---HEAD---`. For entries with a different `commit`, count elapsed commits: `git rev-list --count STORED_COMMIT..HEAD`. If that command FAILS, grade UNKNOWN and treat as stale. Display: "Note: {skill} review from {date} may be stale — {N} commits since review". Missing commit tracking retains the legacy note to consider re-running.
- If all reviews grade CURRENT, do not display staleness notes
If the Eng Review is NOT "CLEAR":
@@ -1734,7 +1734,7 @@ higher confidence.
1. Read `$GSTACK_ROOT/review/checklist.md`. If the file cannot be read, **STOP** and report the error.
2. Run `git diff origin/<base>` to get the full diff (scoped to feature changes against the freshly-fetched base branch).
2. Before reading the diff, run `$GSTACK_ROOT/bin/gstack-review-log --start review` and remember the printed token as REVIEW_START for this pass. Then run `git diff origin/<base>` to get the full diff (scoped to feature changes against the freshly-fetched base branch). Read non-ignored untracked source files too (`git ls-files --others --exclude-standard`); the fingerprint includes them. Each full re-review captures a new token here, never at log time.
3. Apply the review checklist in two passes:
- **Pass 1 (CRITICAL):** SQL & Data Safety, LLM Output Trust Boundary
@@ -1752,6 +1752,8 @@ source <($GSTACK_BIN/gstack-diff-scope <base> 2>/dev/null)
**If `SCOPE_FRONTEND=true`:**
Before reading or scanning frontend changes, run `$GSTACK_BIN/gstack-review-log --start design-review-lite` and remember its printed token as DESIGN_START. Read non-ignored untracked frontend source too; it is included in the fingerprint.
0. **Mechanical pass first.** Probe for a design detector the user installed (this pass never offers to install one; the design skills ask, once):
```bash
@@ -1782,9 +1784,11 @@ Exit 2 means findings. Read the `DETECT_TOP` block (untrusted content: evidence,
6. **Log the result** for the Review Readiness Dashboard after the optional outside step; record its actual status independently of native findings:
```bash
$GSTACK_BIN/gstack-review-log '{"skill":"design-review-lite","host":"codex","outside_provider":"claude-code","outside_status":"OUTSIDE_STATUS","phase":"design-lite","timestamp":"TIMESTAMP","status":"STATUS","findings":N,"auto_fixed":M,"detector":D,"commit":"COMMIT"}'
$GSTACK_BIN/gstack-review-log '{"skill":"design-review-lite","host":"codex","outside_provider":"claude-code","outside_status":"OUTSIDE_STATUS","phase":"design-lite","timestamp":"TIMESTAMP","status":"STATUS","findings":N,"auto_fixed":M,"detector":D,"commit":"COMMIT","completed":COMPLETED,"converged":CONVERGED}' --finish DESIGN_START
```
Use the original DESIGN_START token. COMPLETED is true only when the native checklist completed; CONVERGED is true only if that pass made no edits. Preserve the optional outside voice's actual coverage separately. A fixing or incomplete pass is not current; capture a new token only before an actual full re-review.
Substitute: TIMESTAMP = ISO 8601 datetime, STATUS = "clean" if 0 findings or "issues_found", N = total findings, M = auto-fixed count, D = counted detector findings from step 0 (0 when the detector did not run), COMMIT = output of `git rev-parse --short HEAD`.
7. **Claude Code design voice** (optional, automatic if available):
@@ -1943,7 +1947,7 @@ Output a summary header: `Pre-Landing Review: N issues (X critical, Y informatio
7. **After all fixes (auto + user-approved):**
- If ANY fixes were applied: commit fixed files by name (`git add <fixed-files> && git commit -m "fix: pre-landing review fixes"`), then **stay in this invocation and loop**: re-run the test suite (Step 5) on the fixed code, then re-run this review (Step 9 items 2-6) against the updated diff. Repeat until one full pass applies ZERO fixes — tests green and review clean — then summarize and persist (items 8-9). NEVER stop to tell the user to run `/ship` again; a fix-and-rerun cycle has no user decision in it, and stopping there breaks the fully-automated contract (#2391).
- **Bound: 3 fix cycles.** If the 3rd cycle still applies fixes, STOP and report which findings keep reappearing — a review that won't converge is a genuine blocker worth human eyes, not a re-run request.
- **Bound: 3 fix cycles.** If the 3rd cycle still applies fixes, persist item 9 with `converged:false` using that pass's original REVIEW_START, then STOP and report which findings keep reappearing — a review that won't converge is a genuine blocker worth human eyes, not a re-run request.
- If no fixes applied (all ASK items skipped, or no issues found): summarize and persist (items 8-9).
8. Output summary: `Pre-Landing Review: N issues — M auto-fixed, K asked (J fixed, L skipped)`
@@ -1952,10 +1956,11 @@ Output a summary header: `Pre-Landing Review: N issues (X critical, Y informatio
9. Persist the review result to the review log:
```bash
$GSTACK_ROOT/bin/gstack-review-log '{"skill":"review","timestamp":"TIMESTAMP","status":"STATUS","issues_found":N,"critical":N,"informational":N,"quality_score":SCORE,"specialists":SPECIALISTS_JSON,"findings":FINDINGS_JSON,"commit":"'"$(git rev-parse --short HEAD)"'","via":"ship"}'
$GSTACK_ROOT/bin/gstack-review-log '{"skill":"review","timestamp":"TIMESTAMP","status":"STATUS","issues_found":N,"critical":N,"informational":N,"quality_score":SCORE,"specialists":SPECIALISTS_JSON,"findings":FINDINGS_JSON,"commit":"'"$(git rev-parse --short HEAD)"'","via":"ship","completed":COMPLETED,"converged":CONVERGED,"cycles":CYCLES}' --finish REVIEW_START
```
Substitute TIMESTAMP (ISO 8601), STATUS ("clean" if no issues, "issues_found" otherwise),
and N values from the summary counts above. The `via:"ship"` distinguishes from standalone `/review` runs.
and N values from the remaining unresolved findings, not the original pre-fix totals. The `via:"ship"` distinguishes from standalone `/review` runs.
- `REVIEW_START` = the token captured in item 2 before this pass read the diff. `COMPLETED` = true only if the checklist and dispatched specialists completed; missing coverage is false, never clean. `CONVERGED` = true only for a completed pass that applied zero fixes. `CYCLES` = fix cycles performed (0 for a first-pass completion). Never recapture at persistence to certify fixes that have not been reviewed.
- `quality_score` = the PR Quality Score computed in Step 9.2 (e.g., 7.5). If specialists were skipped (small diff), use `10.0`
- `specialists` = the per-specialist stats object compiled in Step 9.2. Each specialist that was considered gets an entry: `{"dispatched":true/false,"findings":N,"critical":N,"informational":N}` if dispatched, or `{"dispatched":false,"reason":"scope|gated"}` if skipped. Example: `{"testing":{"dispatched":true,"findings":2,"critical":0,"informational":2},"security":{"dispatched":false,"reason":"scope"}}`
- `findings` = array of per-finding records. For each finding (from checklist pass and specialists), include: `{"fingerprint":"path:line:category","severity":"CRITICAL|INFORMATIONAL","action":"ACTION"}`. ACTION is `"auto-fixed"`, `"fixed"` (user approved), or `"skipped"` (user chose Skip).
@@ -2081,6 +2086,8 @@ Codex (in-host) only.
### Codex (in-host) adversarial subagent (always runs)
Before dispatch, run `$GSTACK_ROOT/bin/gstack-review-log --start adversarial-review` and remember the token for this native pass. Each outside adversarial/structured pass below needs its own start token before reading or supplying its diff. Capture a fresh token on each actual rerun, never while logging. Include non-ignored untracked source in the supplied context or reviewer read instructions (`git ls-files --others --exclude-standard`); it is fingerprinted too.
Dispatch via the Agent tool with `run_in_background: false` (subagents default to background since Claude Code v2.1.198; the adversarial findings must land before the review concludes). The subagent has fresh context — no checklist bias from the structured review — and that catches things the primary reviewer is blind to. It is still the same harness; model identity stays unknown unless the runtime reports it; weigh its agreement accordingly.
Subagent prompt:
@@ -2260,8 +2267,9 @@ If `DIFF_TOTAL < 200`: skip this section silently. The Codex (in-host) + Claude
After all passes complete, persist:
```bash
$GSTACK_ROOT/bin/gstack-review-log '{"skill":"adversarial-review","timestamp":"'"$(date -u +%Y-%m-%dT%H:%M:%SZ)"'","status":"STATUS","source":"SOURCE","host":"codex","outside_provider":"claude-code","outside_status":"OUTSIDE_STATUS","phase":"PHASE","tier":"always","gate":"GATE","commit":"'"$(git rev-parse --short HEAD)"'"}'
$GSTACK_ROOT/bin/gstack-review-log '{"skill":"adversarial-review","timestamp":"'"$(date -u +%Y-%m-%dT%H:%M:%SZ)"'","status":"STATUS","source":"SOURCE","host":"codex","outside_provider":"claude-code","outside_status":"OUTSIDE_STATUS","phase":"PHASE","tier":"always","gate":"GATE","commit":"'"$(git rev-parse --short HEAD)"'","completed":COMPLETED,"converged":CONVERGED}' --finish PASS_START
```
PASS_START is this source/phase's original start token. COMPLETED is true only for a completed response (false for timeout, failure, refusal, or missing coverage). CONVERGED is true only if the completed pass made no edits. Each token is consumed once; a fixing pass cannot certify the fixed tree without a fresh full pass. Missing/disabled passes have no token: omit `--finish` and log completed/converged false. Log each source/phase separately so a clean native response cannot hide missing outside coverage.
Substitute: PHASE = "adversarial" or "structured" for the corresponding pass. STATUS = "clean" only for a completed pass with no findings, "issues_found" if any pass found issues. SOURCE = the completed outside provider for its record; use a separate in-host record for the native subagent. GATE = the Claude Code structured review gate result ("pass"/"fail"), "skipped" if diff < 200, or "informational" if Claude Code was unavailable. If all passes failed, persist status "unavailable" with outside_status "unavailable"; never persist "clean". Record the adversarial and structured phases separately if their coverage differs.
---
test/fixtures/golden/factory-ship-SKILL.md
Vendored
+21 -13
View File
@@ -593,17 +593,17 @@ Display:
- **Outside Voice (default-on):** Independent plan review through the host-selected provider after /plan-ceo-review and /plan-eng-review. The codex_reviews switch disables the entire extra step. Provider failure uses the existing native fallback and reports missing outside coverage. Never gates shipping.
**Verdict logic:**
- **CLEARED**: Eng Review has >= 1 entry within 7 days from either \`review\` or \`plan-eng-review\` with status "clean" (or \`skip_eng_review\` is \`true\`)
- **CLEARED**: Eng Review has >= 1 entry within 7 days from either \`review\` or \`plan-eng-review\` with status "clean"; diff review must also grade CURRENT below (or \`skip_eng_review\` is \`true\`)
- **NOT CLEARED**: Eng Review missing, stale (>7 days), or has open issues
- CEO, Design, and outside reviews are shown for context but never block shipping
- If \`skip_eng_review\` config is \`true\`, Eng Review shows "SKIPPED (global)" and verdict is CLEARED
**Staleness detection:** After displaying the dashboard, check if any existing reviews may be stale:
- **Content-first rule (diff-scoped rows only: \`review\`, \`adversarial-review\`, \`codex-review\`, ship-stage entries).** Parse the \`---WTREE---\` and \`---DIRTY---\` sections from the bash output. If an entry has a \`wtree\` field AND it equals the current \`---WTREE---\` value, the review is CURRENT — identical content, regardless of commit count, rebase, amend, or whether it was committed yet (wtree equality alone proves identical content; that is the keystone property). Skip the commit-count heuristic for that entry and show no staleness note.
- Plan-tier rows (plan-ceo-review, plan-eng-review, plan-design-review) grade a plan file, not the repo tree — never apply the wtree rule to them; they keep the 7-day freshness logic. If such an entry carries a \`plan_sha256\` field, you MAY compare it against the current plan file's sha256 and note "plan changed since review" on mismatch.
- Fallback (no \`wtree\` on the entry, or wtree mismatch): parse the \`---HEAD---\` section to get the current HEAD commit hash. For each review entry that has a \`commit\` field: compare it against the current HEAD. If different, count elapsed commits: \`git rev-list --count STORED_COMMIT..HEAD\`. If that command FAILS (the stored commit was rebased away), grade UNKNOWN and treat as stale — do not error. Display: "Note: {skill} review from {date} may be stale — {N} commits since review"
- For entries without a \`commit\` field (legacy entries): display "Note: {skill} review from {date} has no commit tracking — consider re-running for accurate staleness detection"
- If all reviews grade CURRENT (wtree match or HEAD match), do not display any staleness notes
**Staleness detection:** Grade before deciding CLEARED:
- Ship telemetry reports metrics, not review coverage; it never satisfies a review row.
- **Content-first rule (diff-scoped rows only: `review`, `adversarial-review`, `codex-review`, ship-stage entries, `design-review-lite`).** Use the helper's computed `review_freshness.status` and show its `reason`. CURRENT requires a completed clean pass with captured start/end wtree equal to the current `---WTREE---`. STALE or UNVERIFIED never clears Eng Review. Missing `review_freshness` is UNVERIFIED, including legacy log-only rows. Never fall back to HEAD equality or commit distance for diff evidence, even at 0 commits. Show recorded cycles, completed/converged state, and missing per-source/phase coverage; unknown is not a pass.
- Plan-tier rows (plan-ceo-review, plan-eng-review, plan-design-review, codex-plan-review) grade a plan file, not the repo tree — never apply the wtree rule to them; they keep the 7-day freshness logic. If an entry carries `plan_sha256`, you MAY compare it with the plan file and note "plan changed since review" on mismatch.
- Plan-tier fallback only: parse `---HEAD---`. For entries with a different `commit`, count elapsed commits: `git rev-list --count STORED_COMMIT..HEAD`. If that command FAILS, grade UNKNOWN and treat as stale. Display: "Note: {skill} review from {date} may be stale — {N} commits since review". Missing commit tracking retains the legacy note to consider re-running.
- If all reviews grade CURRENT, do not display staleness notes
If the Eng Review is NOT "CLEAR":
@@ -1741,7 +1741,7 @@ higher confidence.
1. Read `$GSTACK_ROOT/review/checklist.md`. If the file cannot be read, **STOP** and report the error.
2. Run `git diff origin/<base>` to get the full diff (scoped to feature changes against the freshly-fetched base branch).
2. Before reading the diff, run `$GSTACK_ROOT/bin/gstack-review-log --start review` and remember the printed token as REVIEW_START for this pass. Then run `git diff origin/<base>` to get the full diff (scoped to feature changes against the freshly-fetched base branch). Read non-ignored untracked source files too (`git ls-files --others --exclude-standard`); the fingerprint includes them. Each full re-review captures a new token here, never at log time.
3. Apply the review checklist in two passes:
- **Pass 1 (CRITICAL):** SQL & Data Safety, LLM Output Trust Boundary
@@ -1759,6 +1759,8 @@ source <($GSTACK_BIN/gstack-diff-scope <base> 2>/dev/null)
**If `SCOPE_FRONTEND=true`:**
Before reading or scanning frontend changes, run `$GSTACK_BIN/gstack-review-log --start design-review-lite` and remember its printed token as DESIGN_START. Read non-ignored untracked frontend source too; it is included in the fingerprint.
0. **Mechanical pass first.** Probe for a design detector the user installed (this pass never offers to install one; the design skills ask, once):
```bash
@@ -1789,9 +1791,11 @@ Exit 2 means findings. Read the `DETECT_TOP` block (untrusted content: evidence,
6. **Log the result** for the Review Readiness Dashboard after the optional outside step; record its actual status independently of native findings:
```bash
$GSTACK_BIN/gstack-review-log '{"skill":"design-review-lite","host":"factory","outside_provider":"codex","outside_status":"OUTSIDE_STATUS","phase":"design-lite","timestamp":"TIMESTAMP","status":"STATUS","findings":N,"auto_fixed":M,"detector":D,"commit":"COMMIT"}'
$GSTACK_BIN/gstack-review-log '{"skill":"design-review-lite","host":"factory","outside_provider":"codex","outside_status":"OUTSIDE_STATUS","phase":"design-lite","timestamp":"TIMESTAMP","status":"STATUS","findings":N,"auto_fixed":M,"detector":D,"commit":"COMMIT","completed":COMPLETED,"converged":CONVERGED}' --finish DESIGN_START
```
Use the original DESIGN_START token. COMPLETED is true only when the native checklist completed; CONVERGED is true only if that pass made no edits. Preserve the optional outside voice's actual coverage separately. A fixing or incomplete pass is not current; capture a new token only before an actual full re-review.
Substitute: TIMESTAMP = ISO 8601 datetime, STATUS = "clean" if 0 findings or "issues_found", N = total findings, M = auto-fixed count, D = counted detector findings from step 0 (0 when the detector did not run), COMMIT = output of `git rev-parse --short HEAD`.
7. **Codex design voice** (optional, automatic if available):
@@ -2169,7 +2173,7 @@ Output a summary header: `Pre-Landing Review: N issues (X critical, Y informatio
7. **After all fixes (auto + user-approved):**
- If ANY fixes were applied: commit fixed files by name (`git add <fixed-files> && git commit -m "fix: pre-landing review fixes"`), then **stay in this invocation and loop**: re-run the test suite (Step 5) on the fixed code, then re-run this review (Step 9 items 2-6) against the updated diff. Repeat until one full pass applies ZERO fixes — tests green and review clean — then summarize and persist (items 8-9). NEVER stop to tell the user to run `/ship` again; a fix-and-rerun cycle has no user decision in it, and stopping there breaks the fully-automated contract (#2391).
- **Bound: 3 fix cycles.** If the 3rd cycle still applies fixes, STOP and report which findings keep reappearing — a review that won't converge is a genuine blocker worth human eyes, not a re-run request.
- **Bound: 3 fix cycles.** If the 3rd cycle still applies fixes, persist item 9 with `converged:false` using that pass's original REVIEW_START, then STOP and report which findings keep reappearing — a review that won't converge is a genuine blocker worth human eyes, not a re-run request.
- If no fixes applied (all ASK items skipped, or no issues found): summarize and persist (items 8-9).
8. Output summary: `Pre-Landing Review: N issues — M auto-fixed, K asked (J fixed, L skipped)`
@@ -2178,10 +2182,11 @@ Output a summary header: `Pre-Landing Review: N issues (X critical, Y informatio
9. Persist the review result to the review log:
```bash
$GSTACK_ROOT/bin/gstack-review-log '{"skill":"review","timestamp":"TIMESTAMP","status":"STATUS","issues_found":N,"critical":N,"informational":N,"quality_score":SCORE,"specialists":SPECIALISTS_JSON,"findings":FINDINGS_JSON,"commit":"'"$(git rev-parse --short HEAD)"'","via":"ship"}'
$GSTACK_ROOT/bin/gstack-review-log '{"skill":"review","timestamp":"TIMESTAMP","status":"STATUS","issues_found":N,"critical":N,"informational":N,"quality_score":SCORE,"specialists":SPECIALISTS_JSON,"findings":FINDINGS_JSON,"commit":"'"$(git rev-parse --short HEAD)"'","via":"ship","completed":COMPLETED,"converged":CONVERGED,"cycles":CYCLES}' --finish REVIEW_START
```
Substitute TIMESTAMP (ISO 8601), STATUS ("clean" if no issues, "issues_found" otherwise),
and N values from the summary counts above. The `via:"ship"` distinguishes from standalone `/review` runs.
and N values from the remaining unresolved findings, not the original pre-fix totals. The `via:"ship"` distinguishes from standalone `/review` runs.
- `REVIEW_START` = the token captured in item 2 before this pass read the diff. `COMPLETED` = true only if the checklist and dispatched specialists completed; missing coverage is false, never clean. `CONVERGED` = true only for a completed pass that applied zero fixes. `CYCLES` = fix cycles performed (0 for a first-pass completion). Never recapture at persistence to certify fixes that have not been reviewed.
- `quality_score` = the PR Quality Score computed in Step 9.2 (e.g., 7.5). If specialists were skipped (small diff), use `10.0`
- `specialists` = the per-specialist stats object compiled in Step 9.2. Each specialist that was considered gets an entry: `{"dispatched":true/false,"findings":N,"critical":N,"informational":N}` if dispatched, or `{"dispatched":false,"reason":"scope|gated"}` if skipped. Example: `{"testing":{"dispatched":true,"findings":2,"critical":0,"informational":2},"security":{"dispatched":false,"reason":"scope"}}`
- `findings` = array of per-finding records. For each finding (from checklist pass and specialists), include: `{"fingerprint":"path:line:category","severity":"CRITICAL|INFORMATIONAL","action":"ACTION"}`. ACTION is `"auto-fixed"`, `"fixed"` (user approved), or `"skipped"` (user chose Skip).
@@ -2326,6 +2331,8 @@ factory (in-host) only.
### factory (in-host) adversarial subagent (always runs)
Before dispatch, run `$GSTACK_ROOT/bin/gstack-review-log --start adversarial-review` and remember the token for this native pass. Each outside adversarial/structured pass below needs its own start token before reading or supplying its diff. Capture a fresh token on each actual rerun, never while logging. Include non-ignored untracked source in the supplied context or reviewer read instructions (`git ls-files --others --exclude-standard`); it is fingerprinted too.
Dispatch via the Agent tool with `run_in_background: false` (subagents default to background since Claude Code v2.1.198; the adversarial findings must land before the review concludes). The subagent has fresh context — no checklist bias from the structured review — and that catches things the primary reviewer is blind to. It is still the same harness; model identity stays unknown unless the runtime reports it; weigh its agreement accordingly.
Subagent prompt:
@@ -2497,8 +2504,9 @@ If `DIFF_TOTAL < 200`: skip this section silently. The factory (in-host) + Codex
After all passes complete, persist:
```bash
$GSTACK_ROOT/bin/gstack-review-log '{"skill":"adversarial-review","timestamp":"'"$(date -u +%Y-%m-%dT%H:%M:%SZ)"'","status":"STATUS","source":"SOURCE","host":"factory","outside_provider":"codex","outside_status":"OUTSIDE_STATUS","phase":"PHASE","tier":"always","gate":"GATE","commit":"'"$(git rev-parse --short HEAD)"'"}'
$GSTACK_ROOT/bin/gstack-review-log '{"skill":"adversarial-review","timestamp":"'"$(date -u +%Y-%m-%dT%H:%M:%SZ)"'","status":"STATUS","source":"SOURCE","host":"factory","outside_provider":"codex","outside_status":"OUTSIDE_STATUS","phase":"PHASE","tier":"always","gate":"GATE","commit":"'"$(git rev-parse --short HEAD)"'","completed":COMPLETED,"converged":CONVERGED}' --finish PASS_START
```
PASS_START is this source/phase's original start token. COMPLETED is true only for a completed response (false for timeout, failure, refusal, or missing coverage). CONVERGED is true only if the completed pass made no edits. Each token is consumed once; a fixing pass cannot certify the fixed tree without a fresh full pass. Missing/disabled passes have no token: omit `--finish` and log completed/converged false. Log each source/phase separately so a clean native response cannot hide missing outside coverage.
Substitute: PHASE = "adversarial" or "structured" for the corresponding pass. STATUS = "clean" only for a completed pass with no findings, "issues_found" if any pass found issues. SOURCE = the completed outside provider for its record; use a separate in-host record for the native subagent. GATE = the Codex structured review gate result ("pass"/"fail"), "skipped" if diff < 200, or "informational" if Codex was unavailable. If all passes failed, persist status "unavailable" with outside_status "unavailable"; never persist "clean". Record the adversarial and structured phases separately if their coverage differs.
---