/ship no longer reports zero blockers when the second-model review found one (GST-3075) (#4485)

When /ship stopped on a second-model review finding marked "Blocks:
yes", the record it left on the PR said no blockers were found; now the
finding is counted and /ship will not write that record until it is
fixed or ruled.

Why: `ready` and the merge step trust that record, so an undercount let
a blocked PR look clean.

Nothing to do: the next /ship run logs Step 11's findings and checks
them before writing.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Review-Finding: h2p1/red-team#1 reader=red-team
Review-Finding: h2p1/red-team#2 reader=red-team
Review-Finding: h2p1/red-team#3 reader=red-team
Review-Finding: v1/outside-voice#1 reader=outside-voice
This commit is contained in:
Garry Tanandcapy-ai[bot] authored and GitHub committed 2026-11-18 12:51:14 +00:00
1 parent bbf48aa7ef
commit 07611a00a7
19 files changed
+190 -16

No files matched your search

+7 -1
View File
@@ -260,7 +260,7 @@ its original token. If it never started because it was unavailable, disabled or
size-gated, omit `--finish PASS_START` and set completed/converged false.
Do not create or borrow a token just to save a result.
```bash
~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"adversarial-review","timestamp":"'"$(date -u +%Y-%m-%dT%H:%M:%SZ)"'","status":"STATUS","source":"SOURCE","host":"claude","outside_provider":"codex","outside_status":"OUTSIDE_STATUS","phase":"PHASE","tier":"always","gate":"GATE","commit":"'"$(git rev-parse --short HEAD)"'","completed":COMPLETED,"converged":CONVERGED}' --finish PASS_START
~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"adversarial-review","via":"ship","timestamp":"'"$(date -u +%Y-%m-%dT%H:%M:%SZ)"'","status":"STATUS","source":"SOURCE","host":"claude","outside_provider":"codex","outside_status":"OUTSIDE_STATUS","phase":"PHASE","tier":"always","gate":"GATE","commit":"'"$(git rev-parse --short HEAD)"'","completed":COMPLETED,"converged":CONVERGED,"findings":FINDINGS}' --finish PASS_START
```
PASS_START belongs to that attempt, not the parent's REVIEW_START. Each token is consumed once.
Fill fields from this attempt, not the parent's Step 9.4 result:
@@ -275,6 +275,12 @@ Fill fields from this attempt, not the parent's Step 9.4 result:
- GATE is "informational" for adversarial passes. For structured review, use
"pass" or "fail" from its completed result, "skipped" when size-gated, or
"informational" with completed:false when coverage is missing.
- FINDINGS is a JSON array, one record per finding this attempt raised, in Step 9.4's
shape (`fingerprint`, `severity`, `blocking`, `raised_by`, `ledger_id`) with ACTION
`"open"` for a blocker (CRITICAL, High or `Blocks: yes`) and `"noted"` below the floor;
`[]` when it raised none. The receipt counts these rows' blockers, and one still
`open` when the run stops (no later Step 9 row fixed or deferred it) makes
`gstack-ship-receipt write` refuse (`RECEIPT_BLOCKER_OPEN`).
---
+2 -1
View File
@@ -274,7 +274,8 @@ files under `review_exclude_paths` changed it, which `--docs-post` binds (`REVIE
The summary reads this branch's review log for the invocation's passes (its
`REVIEW_LOOP:` line is the one the Pre-Landing Review section carries). Here every
finding reaches a row through Step 9.4; a run whose readers were collected by
finding reaches a row through Step 9.4 or Step 11's own row; a blocker still `open` there
makes write refuse (`RECEIPT_BLOCKER_OPEN`). A run whose readers were collected by
`gstack-review-dispatch` (ship/DRIVER.md) passes `--run <run dir>` instead. The `&&`
matters: a summary that refuses (no pass matched `REVIEW_SINCE`) must not let `write`
record a stale or empty loop file.
+2 -1
View File
@@ -257,7 +257,8 @@ files under `review_exclude_paths` changed it, which `--docs-post` binds (`REVIE
The summary reads this branch's review log for the invocation's passes (its
`REVIEW_LOOP:` line is the one the Pre-Landing Review section carries). Here every
finding reaches a row through Step 9.4; a run whose readers were collected by
finding reaches a row through Step 9.4 or Step 11's own row; a blocker still `open` there
makes write refuse (`RECEIPT_BLOCKER_OPEN`). A run whose readers were collected by
`gstack-review-dispatch` (ship/DRIVER.md) passes `--run <run dir>` instead. The `&&`
matters: a summary that refuses (no pass matched `REVIEW_SINCE`) must not let `write`
record a stale or empty loop file.