Commit Graph
242 Commits
Author SHA1 Message Date
Garry Tanandcapy-ai[bot] 07611a00a7 /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
2026-11-18 12:51:14 +00:00
Garry Tanandcapy-ai[bot] 44170d6791 Unattended /autoplan on Claude Code says its phase guard is on, and a report hidden in reasoning gets a clear fix (GST-3062) (#4481)
An unattended /autoplan run on Claude Code now says its phase guard is
on, instead of saying it is off while the guard blocks it. A phase
report written only in reasoning now gets a denial that says so and
names the exact command to send.

Why: in the day-one eval, two runs were blocked by a guard their own
record called off, and one run ended blocked after four publish attempts
whose report was invisible.

Nothing to do.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-18 08:47:07 +00:00
Garry Tanandcapy-ai[bot] f87d4325a3 A round grant at the review round cap buys the fix round it names (GST-2968) (#4479)
When /ship stops at a pull request's review round cap, a grant naming
that stop now buys one scoped review of the fix, in the same run or the
next, instead of another read-only full review.

Before, a grant recorded after the read-only review, or between /ship
runs, bought nothing, so teams paid for extra full reviews or second
grants (ghome#40: $8.78 against about $3).

Nothing to do: /ship prints the grant command when it stops.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Review-Finding: p1/specialist-batched#1 reader=security
Review-Finding: p1/specialist-batched#2 reader=state-machines
Review-Finding: p1/specialist-batched#3 reader=testing
Review-Finding: p1/red-team#1 reader=red-team
Review-Finding: p1/red-team#2 reader=red-team
Review-Finding: p1/red-team#3 reader=red-team
2026-11-18 08:34:39 +00:00
Garry Tanandcapy-ai[bot] 33b1a965ba /ship's push step ends with one line that says whether it pushed (GST-3053) (#4474)
/ship's push step now always ends with one line that says what happened:
`PUSH: pushed …`, `PUSH: already_pushed …` or `PUSH: failed reason=`,
with the remote, branch and full commit.

Why: an eval grader looked for a `git push` call and counted 48 real
/ship pushes as "no push"; scripts and graders can now match this one
line instead.

If a script of yours matched the old `PUSH: ALREADY_PUSHED ` or `PUSH:
pushed to origin/` lines, update it; the exit status is unchanged.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-18 03:56:41 +00:00
Garry Tanandcapy-ai[bot] 0a6bb42e74 Reused CI runs that passed only after a re-run are now marked instead of shown as clean passes (GST-3054) (#4473)
When /ship reuses a CI run that passed only after its failed jobs were
re-run, its CI line and its final summary line now add `rerun=
attempts=`.

Why: gbrain's CI now records which test files passed on a re-run
(gbrain#9690), and a pass on a re-run must read as flaky, never as
clean.

Nothing to do: runs without that record print as before; a malformed
record is refused with `CI_CARRY_RERUN_MALFORMED`.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Review-Finding: p1/outside-voice#1 reader=outside-voice
Review-Finding: p1/outside-voice#2 reader=outside-voice
Review-Finding: p1/adversarial-native#2 reader=adversarial-native
Review-Finding: p1/red-team#1 reader=red-team
2026-11-18 03:47:25 +00:00
Garry Tanandcapy-ai[bot] 237371474b Let autoplan revise accept a plan without section headings, as next does (GST-3050) (#4470)
`gstack-autoplan revise` now accepts a revised plan whenever the first
`next` accepted its shape, so a run no longer pays for a full review
round and then refuses the owner's edit.

Why: a plan with no section headings is reviewed whole by `next`, but
once the owner added one heading, `revise` stopped with
`PLAN_SECTIONS_INVALID`.

Nothing to do: runs already in progress pick this up too.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-18 02:21:31 +00:00
Garry Tanandcapy-ai[bot] c9b6fe0ab3 Second-model plan reviews in autoplan stop being reported unavailable; --help stops printing a fake refusal (GST-3051) (#4471)
A second-model plan review in `/autoplan` is no longer reported as
unavailable when it actually ran, and `gstack-outside-voice --help` no
longer prints a line that reads like a real consent refusal.

Why: sessions believed the false label and paid to re-run the review, or
closed the plan phase without its second-model review.

Nothing to do: the command autoplan already runs now picks the right
check by itself.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-18 02:12:43 +00:00
Garry Tanandcapy-ai[bot] dd4266dc4b Check each app build with an agent from another model family before its owner is asked to try it (GST-3025) (#4465)
Adds `gstack-first-use`: before an app build reaches its owner as "ready
to try", an agent from another model family plays that exact build, does
the plan's first five day-one actions with a screenshot or video of
each, and checks every link. Only then does it print the "try this
build" message.

Why: a recent app build passed every review and its owner still found
the first screen broken, because nothing tried the build the way the
owner would.

Nothing to do now; the first real use is that app's next build.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Review-Finding: p1/red-team#2 reader=red-team
Review-Finding: p1/red-team#4 reader=red-team
2026-11-17 23:19:24 +00:00
Garry Tanandcapy-ai[bot] 0b656a171d Check a question against the owner's earlier answers before asking it again (GST-3025) (#4467)
An agent can now check a draft question against the owner's earlier
answers before sending it, so the owner isn't asked again about
something they already said yes to.

Why: owners repeat "don't ask me, just do it" across threads, because
each new session forgets earlier answers. In a four-day sample, about 1%
of 444 asks were repeats this could skip, so a two-week pilot decides
whether it's kept.

Nothing to do: the new command is opt-in, and no existing command,
install output or factory rule changes.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Review-Finding: p1/specialist-batched#1 reader=testing
Review-Finding: p1/specialist-batched#2 reader=state-machines
Review-Finding: p1/red-team#1 reader=red-team
Review-Finding: p1/red-team#2 reader=red-team
Review-Finding: p3/outside-voice#1 reader=outside-voice
Review-Finding: p3/outside-voice#2 reader=outside-voice
2026-11-17 23:13:14 +00:00
Garry Tanandcapy-ai[bot] d3d35019a0 Tests and scratch repositories can no longer write approval rows into a real Capy Drive (GST-3027) (#4466)
Tests and scratch repositories in the temp directory can no longer write
approval rows into your real Capy Drive. When `gstack-approvals` runs
under `bun test`, or its state root or repository sits in the temp
directory, a Drive mirror that resolves outside the temp directory
(links followed) is refused with `APPROVAL_RECORD_WRITE_FAILED`; the
local row is kept.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Review-Finding: p1/red-team#1 reader=red-team
2026-11-17 22:56:51 +00:00
Garry Tanandcapy-ai[bot] da98d0a0eb /ship reuses CI's passing run when a base merge changed no file, and stops before long local test runs or an unknown base (GST-3019) (#4461)
/ship's preflight and its CI-run lookup now reuse a passing CI test run
when a base merge left the files unchanged, stop instead of quietly
starting an hour-long test suite on the local machine, and refuse a
`--base` that names no commit instead of reporting an empty diff.

Why: gbrain #9662 lost a green CI run to a no-op base merge, then ran a
50-minute suite on a 4-CPU box, and its audit read a commit sha as a
branch and saw zero changed files.

Nothing to do: `--run-uncarried-here` restores running an uncovered
suite locally under `--tests-only`.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Review-Finding: s11/outside-voice#1 reader=outside-voice
Review-Finding: s11/outside-voice#2 reader=outside-voice
2026-11-17 20:56:07 +00:00
Garry Tanandcapy-ai[bot] e671a531f4 Unattended /autoplan runs its configured second-model review in the foreground, and run ids no longer collide (GST-3015) (#4459)
Unattended `/autoplan --full` now runs the second-model review when
`codex_reviews: enabled` is set, runs it in the foreground with a
9-minute limit, and records a timeout with the standard failure line
instead of ending the session. Two runs started in the same second also
get different run ids now.

Why: in a planning test, Opus 5.5 skipped the second reviewer in 2 of 3
runs over consent the config had already given, and ended the third
session while the review ran in the background.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-17 19:54:16 +00:00
Garry Tanandcapy-ai[bot] c53b15c48d Open pull requests with three plain lines and land each one as a single commit (GST-2737) (#4438)
* WIP plain PR bodies and squash messages

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Fold PR bodies to three plain lines and land every PR as one plainly titled commit

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Expect the plain commit body in the train land tests

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Count the new policy keys in the floor tests and record the ship size change

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Let older, generated and Dependabot PRs pass the body check, and keep comments posting

The opening check now follows the same date and branch exemption as the rest of the body check, Dependabot branches are exempt, the exemption only counts for branches in this repository, a merge that cannot read the PR waits instead of refusing, and a broken policy file no longer stops comments.

Review-Finding: p1/specialist-batched#1 reader=testing
Review-Finding: p1/specialist-batched#2 reader=testing
Review-Finding: p1/red-team#1 reader=red-team
Review-Finding: p1/red-team#2 reader=red-team
Review-Finding: p1/red-team#4 reader=red-team
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Stop re-posted PR bodies from duplicating sections, and let file names through the word check

Posting an already-folded body now replaces each section once instead of keeping the old copy beside it, and listed words inside file paths or file names, such as a test file in the Tests section, no longer count as prose.

Review-Finding: v2/outside-voice#3 reader=outside-voice
Review-Finding: v2/adversarial-native#2 reader=adversarial-native
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Describe the folded three-line PR body in the skills guide and the prose lint help

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-17 13:14:33 +00:00
Garry Tanandcapy-ai[bot] aeb74eb00b /ship's test step says when it hits its time limit, and long test file lists no longer overflow the remote command (GST-2958) (#4429)
* Say when /ship's test step hit its time limit, and keep long file lists off the remote test command line

gstack-ship-preflight stopped gstack-pregate after a fixed hour and printed
'PREGATE: unreadable (exit 143)'. The whole step's budget is now
--step-timeout <s> (default 3600), and a stop at it prints
'PREGATE: time limit hit' with the way out: push and let CI's full run
carry the tests, or a larger budget.

The test_backend command pregate prints for a small machine put every
selected file into one argument, which Linux refuses past 128 KiB. The
files now reach the VM in a setup script named by its content.

Also adds an arg-limit troubleshooting entry and says the Windows job has
eight shards.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Read the small-machine file list from the setup script in the hidden-folder path test

The remote command now names a setup script instead of the files, so the
test checks that the script lists the ./-prefixed path.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Keep a test path with a newline out of the remote file list

A selected test path containing a newline, or equal to the list's end marker, could end the setup script's file list early and run the rest as shell on the test VM. Such paths now keep the quoted inline command.

Review-Finding: p1/outside-voice#1 reader=outside-voice
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Mark the preflight half of the Step 5 time limit to-do as done

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-17 13:13:19 +00:00
c5250dedc1 Keep reviewer product challenges open on the approval page (#4431)
* Keep reviewer product challenges open on the approval page

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Read the approvals record without writing the slug cache when building the gate

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Keep every reviewer challenge on the approval page, and ask again when the cut list changes

A challenge with no change kind and no real owner quote now becomes a proposal instead of vanishing. An ordinary finding that only mentions an earlier challenge no longer closes it. The cut list and confirm-direction items carry their content in their origin, so an earlier answer is not reused for a changed list.

Review-Finding: p1/specialist-batched#1 reader=specialist-batched
Review-Finding: p1/red-team#2 reader=red-team
Review-Finding: p1/red-team#3 reader=red-team
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Keep removed owner quotes redacted, and keep High proposals as blocking tasks when declined

Public exports now redact the Owner's words from every plan text the run kept, so a quote a revision removed stays hidden in earlier reviewer results. A paired proposal takes the heaviest change either reviewer named, so an ordering-plus-scope pair is re-reviewed instead of settled. A proposal behind a Critical or High finding offers b as keep the draft and carry it into the build as a blocking task, and only a settles it.

Review-Finding: p1v/outside-voice#1 reader=outside-voice
Review-Finding: p1v/outside-voice#2 reader=outside-voice
Review-Finding: p1v/adversarial-native#2 reader=adversarial-native
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Document owner's words, reviewer proposals and day-one items on the approval page

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* chore: changelog and TODOS

Co-Authored-By: Claude <noreply@anthropic.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
2026-11-17 12:02:11 +00:00
Garry Tanandcapy-ai[bot] 79f6012bbc v1.99.5.0 Give the head a pull request merges a full review when its removed lines changed or it was only re-checked (GST-2706) (#4365)
* Count review rounds per pull request across /ship runs (GST-2673)

/ship's two-round review cap was counted inside each run, so a pull request
shipped many times was reviewed again at every head. Step 1 now reads the
rounds the PR body's receipt history records, passes them to the review plan,
and sends later heads to the scoped re-check, with a lane or Captain round
grant for an extra round. Adds the no-loss replay preregistration.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Cap full review rounds per pull request and keep fix-checks to each run

The plan counts a PR's earlier full rounds (--prior-full) against the cap of
two, as the approved plan says, and prints every earlier round as pr_rounds=.
Renames the troubleshooting anchor to pr-round-cap, lists <SESSION_ID> as a
reviewed placeholder, and leaves ship/DRIVER.md at its size cap.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Point the ship driver's review pass at Step 9's plan flags, which carry the PR round count

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Give a pull request's final head a full review and make the diff-only re-check advice only (GST-2673)

A scoped re-check that reads only what changed since the last reviewed head
caught 22 of 24 planted faults but none of 8 real faults that full rounds had
caught, so it no longer carries a /ship receipt. A later head whose own lines
changed now gets a fresh full review, the PR's last before merge; a PR already
at two full rounds gets one read-only full review with no fix round, whose
blocker goes to the lane's Captain. carry prints RECHECK: advisory and refuses
--recheck. The drift threshold, the re-check blocker count and the
design-change grant kind are removed with the route they fed.

Repins lib/review-depth.ts and ship/sections/review-army.md under replay
GST-2673 (docs/evals/pr-round-count-results.md; deterministic grid against
main: 196,608 of 196,608 plans identical with no prior rounds).

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Keep a review round grant usable through its fix round and after a read-only review

A grant now holds after the fix round's commits move HEAD past it, counts only the rounds earlier heads spent, and a receipt written without a run keeps other runs' stubs.

Review-Finding: p1/specialist-batched#1 reader=state-machines
Review-Finding: p1/red-team#2 reader=red-team
Review-Finding: p1/red-team#3 reader=red-team
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Count every review round at a granted head again, so a grant can't reset the count

Reverts the history change that skipped rounds recorded at a round grant's head: the run that hit the cap is recorded at that same head, so skipping it wiped the count. A grant recorded after a read-only review still doesn't buy a fix round (fails closed).

Review-Finding: p2/adversarial-native#1 reader=adversarial-native
Review-Finding: p2/outside-voice#1 reader=outside-voice
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Give a merge head a full review when its removed lines changed or its receipt came from a re-check

A head whose removed lines changed with the base no longer carries on one scoped reader, a receipt an older gstack carried through a scoped re-check no longer carries on or lands, and a /ship body post keeps the run history. The read-only stop stops offering a round grant it can't honor, and the stamp-only-carry no-stop class is removed because a refused carry never stopped. (GST-2706)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Keep the run history inside Agent notes when the PR text quotes a receipt

Review-Finding: p1/red-team#1 reader=red-team
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Let a receipt write skip a retired no-stop entry left in an older branch ledger

Review-Finding: p3/outside-voice#1 reader=outside-voice
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Say in troubleshooting that the queue refuses a receipt carried through a re-check

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-17 12:01:00 +00:00
Garry Tanandcapy-ai[bot] eb54692427 Never let a later docs-audit line override an earlier blocked result (GST-2349) (#4434)
* Never let a later docs-audit line override an earlier blocked line (GST-2349)

A blocked documentation-audit result line followed by an unfenced "current"
JSON line for the same audit as the very last line was accepted as current,
and a last "current" line whose only fault was its format was repaired back to
current. The blocked verdict now carries: a last line that drops an earlier
blocked status or blocker for the audit is never accepted and gets the
one-way re-ask, whose reply must stay blocked and keep those blockers.

Step 2 of the docs audit section no longer says it parses only the last
line, and the changelog entry now claims only what the parser checks.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Leave the landed changelog entry alone and correct its claim in a new entry (GST-2349)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Split a run-on sentence in the changelog entry for the docs-audit fix

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-17 11:12:52 +00:00
Garry Tanandcapy-ai[bot] 83cc10acd2 Stop gstack-pr-wait, the land gate and the release cut from calling a head green while a check on it failed (GST-2252) (#4257)
* Make gstack-pr-wait, gstack-ci-gate and the release cut count a failed check hidden behind an empty rerun (GST-2252)

GitHub rollup and default check-runs list hold only each check suite latest attempt, so a rerun attempt with no jobs hid the failed run before it, and a workflow run that failed before any job never appeared. All three readers now add CI at the commit as the merge queue reads it (ciAtHead via lib/ci-head-checks.ts) and keep the worse bucket per check. Tests reuse the gstack-evals#303 recording from #4235.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Have the release cut read every check attempt only for commits that pass its named checks (GST-2252)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Say in the changelog that the release cut now counts failed commit statuses (GST-2252)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Let the release cut set its own jobs aside in the every-attempt check read too (GST-2252)

After #4297 the cut sets aside check runs from its own workflow and the Windows nightly by job id, but the rows from lib/ci-head-checks.ts skipped that filter, so the cut waited on its own run. headCheckRows now takes the set-aside check run and workflow run ids and removes them from every list before ciAtHead reads it.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-17 10:03:19 +00:00
Garry Tanandcapy-ai[bot] 2af3822f94 Stop /ship's docs audit halting when the child writes prose after its result (GST-2349) (#4285)
* Stop /ship's docs audit halting when the child writes prose after its result (GST-2349)

The Step 14.5 documentation audit read only the child's last nonempty line.
Children that ended with their JSON result and then restated the documentation
section in prose had a valid "current, no edits" audit rejected with no format
repair, which spent an attempt each time and, after two, stopped /ship for an
owner risk grant (founderstar #837, harness-evals #393).

gstack-docs-candidate result now reads the last line that opens a JSON object,
ignores prose after it and says so with TRAILING_PROSE:. A result missing only
documentation_section keeps the existing free re-ask, whose prompt now tells the
child to put the section inside the JSON and write nothing after the line; the
re-audit retry note says the same. Content failures still count.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Send any docs-audit result with text after it back for one free re-ask (GST-2349)

A cross-family audit of the previous commit showed that ignoring prose after
the result line let a contradicting verdict through: a blocked result followed
by a fenced "current" example was accepted as current, and a "Correction: the
audit is BLOCKED" after a current line became a repair that had to stay current.

Text after a JSON line carrying the audit id is no longer ignored and never
searched for another result. It is a format slip: FORMAT_REPAIR re-asks once
for the whole result line without spending an attempt, the re-ask counts
everything the audit wrote after its JSON line, and the reply is judged on its
own with nothing kept from the first line. A reply that itself has text after
its line counts as an attempt.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Keep a blocked docs audit blocked through the free re-ask (GST-2349)

Review of the previous change found that the free whole-line re-ask could
turn a blocked audit into a passing one: a blocked result line, then a fenced
"current" example, then a "current" reply was accepted as current.

The re-ask now works one way. It is offered only when every JSON line that
carries the audit id is free of content problems; a content problem such as a
missing status or "current" with edits still spends an attempt. If any of those
lines said blocked or listed a blocker, the reply must stay blocked and keep
every blocker (it may add more), and the re-ask prompt says so.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-17 09:36:21 +00:00
Garry Tanandcapy-ai[bot] bcece3fbcd Make gstack's shell locks hold when mkdir reports a race it lost (GST-2247) (#4262)
* Make gstack's shell locks hold when mkdir reports a race it lost (GST-2247)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Fix lock tests and fixtures for gstack_lock_take; trim setup-gbrain lock prose

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Ship the lock helper with every copied runtime and fixture that runs a lock

The Claude Code wrapper's copied runtime now includes bin/gstack-lock.sh, and
bin/gstack-render-claude.sh sources it beside itself, so gstack-config set
works in a copied runtime and the render lock is taken by every caller.
Test fixtures that copy single bin scripts now copy the helper too, and the
mkdir lock guard is registered as a repo-wide docs reader.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Release a lock whose owner file could not be fully written

gstack_lock_take created the owner file with a noclobber redirect and, when
that redirect failed, treated an existing file as a competing holder. If the
file was created but the write then failed (disk full, quota, ulimit -f), the
helper found its own empty file, returned 1 and left a lock nobody held;
freeze's state lock has no stale recovery, so it stayed busy until removed by
hand. The helper now tells "opened but write failed" from "already held",
removes its own file and directory, and returns 3. The inline copy in
gstack-ff-update is updated byte for byte, and a new test under ulimit -f 0
fails on the old helper.

Review-Finding: s11/outside-voice#1 reader=outside-voice
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Describe the lease lock as gstack_lock_take's O_EXCL owner file

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-17 09:05:25 +00:00
Garry Tanandcapy-ai[bot] e9f38d6fe1 Review a pull request's final head in full and count review rounds per PR (GST-2673) (#4360)
* Count review rounds per pull request across /ship runs (GST-2673)

/ship's two-round review cap was counted inside each run, so a pull request
shipped many times was reviewed again at every head. Step 1 now reads the
rounds the PR body's receipt history records, passes them to the review plan,
and sends later heads to the scoped re-check, with a lane or Captain round
grant for an extra round. Adds the no-loss replay preregistration.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Cap full review rounds per pull request and keep fix-checks to each run

The plan counts a PR's earlier full rounds (--prior-full) against the cap of
two, as the approved plan says, and prints every earlier round as pr_rounds=.
Renames the troubleshooting anchor to pr-round-cap, lists <SESSION_ID> as a
reviewed placeholder, and leaves ship/DRIVER.md at its size cap.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Point the ship driver's review pass at Step 9's plan flags, which carry the PR round count

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Give a pull request's final head a full review and make the diff-only re-check advice only (GST-2673)

A scoped re-check that reads only what changed since the last reviewed head
caught 22 of 24 planted faults but none of 8 real faults that full rounds had
caught, so it no longer carries a /ship receipt. A later head whose own lines
changed now gets a fresh full review, the PR's last before merge; a PR already
at two full rounds gets one read-only full review with no fix round, whose
blocker goes to the lane's Captain. carry prints RECHECK: advisory and refuses
--recheck. The drift threshold, the re-check blocker count and the
design-change grant kind are removed with the route they fed.

Repins lib/review-depth.ts and ship/sections/review-army.md under replay
GST-2673 (docs/evals/pr-round-count-results.md; deterministic grid against
main: 196,608 of 196,608 plans identical with no prior rounds).

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Keep a review round grant usable through its fix round and after a read-only review

A grant now holds after the fix round's commits move HEAD past it, counts only the rounds earlier heads spent, and a receipt written without a run keeps other runs' stubs.

Review-Finding: p1/specialist-batched#1 reader=state-machines
Review-Finding: p1/red-team#2 reader=red-team
Review-Finding: p1/red-team#3 reader=red-team
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Count every review round at a granted head again, so a grant can't reset the count

Reverts the history change that skipped rounds recorded at a round grant's head: the run that hit the cap is recorded at that same head, so skipping it wiped the count. A grant recorded after a read-only review still doesn't buy a fix round (fails closed).

Review-Finding: p2/adversarial-native#1 reader=adversarial-native
Review-Finding: p2/outside-voice#1 reader=outside-voice
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-17 08:39:43 +00:00
Garry Tanandcapy-ai[bot] fdf3f1e1b6 Make /eval-plan check judges, zeros, failure counts and decisions before results count (GST-2754) (#4384)
* Make /eval-plan check judges, zeros, failure counts and decisions before results count (GST-2754)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Check zeros in every results table, apply Decisions and Scoring with stack: none, count only valid judge labels (GST-2754)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Describe the /eval-plan result checks in the skills guide (GST-2754)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-16 02:55:19 +00:00
Garry Tanandcapy-ai[bot] 8837fda399 Bring back the standalone /plan-eng-review command (GST-2726) (#4375)
Garry, 2026-11-15: people rely on /plan-eng-review, so it returns as its own
command on every host that had it before GST-1698 (#4108). /autoplan's eng
phase is unchanged: external hosts still ship the same methodology beside
gstack-autoplan/SKILL.md, now rendered from the same pass as the standalone
skill, and the Kiro sibling copy and ownership guards from #4108 stay.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-15 02:11:18 +00:00
Garry Tanandcapy-ai[bot] 4bee369d4a Retry /ship's second-model review on Astra, then Gemini, when OpenAI refuses it as a cyber-security risk (GST-2649) (#4350)
* Retry /ship's outside voice on Astra, then Gemini, when OpenAI refuses it under cyber_policy (GST-2649)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Register the cyber_policy refusal fixtures as free test inputs (GST-2649)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Retry a refused second-model review only when it left no review (GST-2649)

A voice the host marks refused under cyber_policy but that still wrote findings is now collected as that review, with its own outside record, instead of starting a redundant retry and losing its record. The cyber_policy test header now matches what the classifier does with a host error.

Review-Finding: p1/red-team#2 reader=red-team
Review-Finding: p1/specialist-batched#1 reader=testing
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Skip the Gemini retry when the lane or native reviewer is already a Google model (GST-2649)

On a Google-family lane, Step 11 refuses a Gemini outside voice, so two OpenAI refusals used to plan a Gemini retry that stopped the pass on every resume. The retry chain now skips a step whose family the lane or native reviewer holds and records the second-family read as missing.

Review-Finding: p1/outside-voice#1 reader=outside-voice
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Say in troubleshooting that a retry is skipped when its model family is the lane's (GST-2649)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-14 02:23:48 +00:00
Garry Tanandcapy-ai[bot] 4414f4cc93 Stop /ship's docs audit from refusing Next.js bracketed route paths (GST-2554) (#4321)
* Stop /ship's docs audit from refusing Next.js bracketed route paths (GST-2554)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* List the bracketed route path rule in the docs audit troubleshooting entry (GST-2554)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-12 15:44:36 +00:00
Garry Tanandcapy-ai[bot] b1f78301db The lander must accept each owner-approved gate change before a PR merges (GST-2491) (#4304)
* Let an owner recorded approval close a gate finding in unattended ship (GST-2491)

An unattended /ship logs every gate finding open and nothing could close it, so a PR with an owner-approved gate change could never finish. gstack-approvals gate records the owner disposition outside the run; it closes only that fingerprint on a review row whose range holds the head, and finish, the receipt, the PR body and READY all carry it.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Keep the pinned review brief unchanged; document the resume steps for a dispositioned gate finding (GST-2491)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Bind a gate disposition to its gate change and show it as kept to the rest of /ship (GST-2491)

A disposition now names the finding's gate_id as well as its fingerprint, so a later loosening of the same line stays open. gstack-review-read shows a closed gate finding as kept with the disposition's approval id, so the existing --blocking-open, --gate-open, draft and Gate edits rules carry it without prose changes, and an unreadable approval record applies no disposition instead of failing the reader.

Review-Finding: p1/red-team#1 reader=red-team
Review-Finding: s11/outside-voice#1 reader=outside-voice
Review-Finding: s11/outside-voice#2 reader=outside-voice
Review-Finding: s11/adversarial-native#1 reader=adversarial-native
Review-Finding: s11/adversarial-native#2 reader=adversarial-native
Review-Finding: s11/adversarial-native#4 reader=adversarial-native
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* List the Gate disposition line in the receipt and prose troubleshooting entries (GST-2491)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Require the lander to accept each owner gate disposition before merging (GST-2491)

Land and a new read-only verify --pin re-derive the dispositions the approval store applies at the pin and merge only with --accept-gate-disposition for each one. The gate writer refuses while any worktree holds an open /ship run on the branch, under a lock; a row counts only in the writer's full shape with its digest; receipt write needs --body when a disposition applies; ready and land cross-check the receipt and body against the store. Supersedes #4299.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Regenerate the result-code anchors for the gate-disposition refusal (GST-2491)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Always record the receipt's gate dispositions and refuse a store that disagrees at merge (GST-2491)

The receipt always carries gate_dispositions (an empty list when none apply) and write refuses on an unreadable store or a git error. Land, verify and ready refuse a receipt id the merge-time store lacks, naming the likely wrong state root or mirror, and a field-less receipt beside an applied row. A git ancestry error while deriving dispositions refuses instead of reading as not applied.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Count a disposition whose head a rewrite removed as not applied, and expect the receipt to end with gate_dispositions (GST-2491)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Trim and check the gate disposition recorder name, and let a parked run's ended lease stop blocking it (GST-2491)

Review-Finding: s11/outside-voice#3 reader=outside-voice
Review-Finding: s11/outside-voice#2 reader=outside-voice
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-12 01:49:08 +00:00
Garry Tanandcapy-ai[bot] 842fef1f95 Let the sealed-output guard check pull requests larger than 256 MiB (GST-2494) (#4300)
* Let the sealed-output guard read pull requests larger than 256 MiB (GST-2494)

The guard's text check and landed-patch check buffered git diff-tree's whole output under spawnSync's 256 MiB maxBuffer, so a PR with millions of generated lines always refused with an empty-stderr error. Both now spool git's stdout to a private temp file and read it a line at a time after git exits 0; failures name the exit code, signal or timeout.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Accept the platform spawn error text in the missing-git test (Windows says Executable not found)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Reword the sealed guard changelog entry to pass the prose check

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-11 22:48:18 +00:00
Garry Tanandcapy-ai[bot] 6b327148e3 Stop gstack-uninstall deleting unpushed or kept work under any folder it removes (GST-2303) (#4282)
* Stop gstack-uninstall deleting unpushed or kept work under any folder it removes (GST-2303)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Keep repos behind a symlinked .gstack-worktrees, remove stable-channel installs, and read worktrees on git before 2.36 in gstack-uninstall (GST-2303)

Review-Finding: p1/red-team#1 reader=red-team
Review-Finding: p1/red-team#2 reader=red-team
Review-Finding: p1/red-team#3 reader=red-team
Review-Finding: p1/specialist-batched#1 reader=testing
Review-Finding: p1/specialist-batched#2 reader=testing
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Count a FETCH_HEAD commit as pushed only when it came from one of the checkout's remotes in gstack-uninstall (GST-2303)

Review-Finding: p2/specialist-batched#1 reader=security
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Read remote URLs with git remote get-url so url.insteadOf rewrites match FETCH_HEAD in gstack-uninstall (GST-2303)

Review-Finding: fc/fix-check#1 reader=fix-check
Review-Finding: fc/fix-check#2 reader=fix-check
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Refuse to uninstall on git older than 2.36 instead of reading worktrees without -z (GST-2303)

Review-Finding: v11/outside-voice#1 reader=outside-voice
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* List the git 2.36 uninstall refusal in troubleshooting (GST-2303)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-10 09:34:35 +00:00
Garry Tanandcapy-ai[bot] 4685fa9233 Warn when a branch-only run hides a red PR check, and make ready refuse when its note or base is missing (GST-2205) (#4270)
* Warn when a red check is replaced by a run from another suite, and refuse a plain ready whose note never reached origin (GST-2205)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Fetch the base before ready picks the train or plain path (GST-2205)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Let the train path report its own fetch failure when ready cannot refresh the base (GST-2205)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Give the no-origin/main routing test a complete pregate record (GST-2205)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Give the unpushed ready-note test a complete pregate record (GST-2205)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-10 06:36:56 +00:00
Garry Tanandcapy-ai[bot] 46d51496b4 Let an owner's ruling clear new blockers that an extra review round found, so /ship can finish (GST-2251) (#4260)
* Let an owner's ruling clear the new blockers a granted fix-check found (GST-2251)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Name every finding that still holds a fix-check open, with the full rule command (GST-2251)

Review-Finding: p1/adversarial-native#1 reader=adversarial-native
Review-Finding: p1/red-team#1 reader=red-team
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Describe the wider FIX_CHECK_OPEN list in the release note (GST-2251)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Keep a skipped blocking finding open until the owner rules it, even beside a ruled CRITICAL (GST-2251)

A ruled open CRITICAL could clear a fix-check row while an unruled non-CRITICAL finding logged skipped with blocking:true stayed unruled. Rulings now clear a row only when one covers every unresolved or blocking finding, and FIX_CHECK_OPEN names the rest.

Review-Finding: captain-audit/Q1 reader=outside-voice
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-10 01:43:01 +00:00
Garry Tanandcapy-ai[bot] 56c4e873b2 Stop the pre-merge check from accepting a half-finished run (GST-2194) (#4258)
* Make pregate verify refuse a record from a partial run (GST-2194)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Update pregate and queue test fixtures to complete records

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Document that verify needs every check and that a staged rerun keeps the rest

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Skip the partial-record pregate tests on Windows, where the fixture lane is a remote obligation

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Give the crew queue tests complete pregate records

The train, train-ops and wave tests wrote one-check pregate records, which verify now refuses as a partial run. They now write every registered check, as test/gstack-ship-queue.test.ts already does (CI free-suite run 42718782737).

Review-Finding: lib/pregate/index.ts:251:functional-contract reader=core
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Explain the missing-checks pregate refusal in troubleshooting

Documents that verify refuses a record missing registered checks, and that a fix commit needs a full gstack-pregate run (Step 14.5 docs audit).

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-10 01:33:31 +00:00
Garry Tanandcapy-ai[bot] 00cb80cce8 Make the ship queue fetch the latest main before it checks a pull request (GST-2232) (#4256)
* Make ship-queue ready fetch the base before it checks the receipt (GST-2232)

ready read origin/<base> as the clone last fetched it, so a lane a few landings behind measured the PR from an older merge base and refused a good receipt with a false RECEIPT_INVALID field=review_exclude. ready now fetches the base first and refuses QUEUE_BASE_UNFETCHED when it cannot; the stamp path of land refuses the same way instead of ignoring a failed fetch.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Regenerate the doctor component list for the new queue refusal code (GST-2232)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Keep the new ready test off the Windows-safe set and say which land path uses the new refusal (GST-2232)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-10 01:03:46 +00:00
Garry Tanandcapy-ai[bot] dfdaea2efd Make ship-queue ready refuse when its READY note doesn't reach origin (GST-2242) (#4254)
* Make ship-queue ready refuse when its READY note doesn't reach origin (GST-2242)

ready exited 0 and printed "notes pushed" even when the READY note never reached origin, so land refused the pin with QUEUE_NOT_READY (#4245). The notes writer now reads origin's ref back after each push, and train ready refuses with QUEUE_READY_NOTE_UNPUSHED when origin still lacks the note after three tries.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Name the changelog fragment for the branch (GST-2242)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Regenerate the doctor component list for the new ready result code (GST-2242)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Say that ready's notes check covers train policies, and how to rerun it with its gate flags (GST-2242)

Review-Finding: p1/red-team#2 reader=red-team
Review-Finding: p1/red-team#1 reader=red-team
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Skip the ready notes-push test on Windows, where the gh shim can't run (GST-2242)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-10 00:54:27 +00:00
Garry Tanandcapy-ai[bot] 3183120cec Stop a main merge from counting as the PR's own change, so a retake no longer needs a second full review (GST-2229) (#4259)
The receipt carry and finish scoped-review packet counted context lines, hunk headers and the base's change toward the 200-line section cap (founderstar#802). gstack-review-plan measured the fix range as --range-base..HEAD, so files a main merge brought counted as the PR's fix (harness-evals#354).

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-09 23:41:35 +00:00
Garry Tanandcapy-ai[bot] 1d91652764 Make the archive check refuse unknown PR states, cut-short issue rows and a missing title policy (GST-2241) (#4251)
* Make the archive check refuse unknown PR states, cut-short issue rows and a missing title policy (GST-2241)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Regenerate the doctor result-code table for the two new archive codes

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Document that the archive check refuses unknown PR states and needs the title policy on land

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-09 23:29:20 +00:00
Garry Tanandcapy-ai[bot] 83bfdc5177 Refuse to archive a thread that holds an open PR, and close a landed PR's issue (GST-2188) (#4244)
* Test that a Captain cannot archive a thread still holding open work (GST-2188)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Refuse to archive a thread that holds an open PR and close a landed PR's issue (GST-2188)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Clear the archive check's handoff file on a failed read and say plainly that long PR lists cannot be checked

Review-Finding: p1/specialist-batched#2 reader=testing
Review-Finding: p1/specialist-batched#3 reader=state-machines
Review-Finding: p1/red-team#1 reader=red-team
Review-Finding: p1/red-team#3 reader=red-team
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Refuse to archive on an issue list with no rows, and match tracker codes in any case when closing a landed PR's issues

Review-Finding: p3/outside-voice#1 reader=outside-voice
Review-Finding: p3/outside-voice#2 reader=outside-voice
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Say in the skills guide that a rotated thread is archived only once none of its PRs is open

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Shorten the runaway-stopper archive step so the skill fits its context budget after the rebase

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-09 21:50:58 +00:00
Garry Tanandcapy-ai[bot] f75ce6fdcc Stop the merge queue from landing a stacked PR's unreviewed parent commits (GST-2153) (#4229)
* Add failing tests: ready and land accept a stacked child's receipt reviewed against its open parent branch

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Refuse a receipt reviewed against another branch than the queue base at ready, land and train build (GST-2153)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Regenerate the doctor result anchors for the new receipt base mismatch code

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix: pre-landing review fixes

Train build now has a test that refuses a receipt reviewed against a parent branch.

Review-Finding: p1/specialist-batched#1 reader=specialist-batched
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix: pre-landing review fixes

Keep the base-contains-head diagnostic ahead of the receipt base check, normalize any remote's refs, and tell callers to merge the base in before the carry.

Review-Finding: v1/outside-voice#3 reader=outside-voice
Review-Finding: v1/outside-voice#1 reader=outside-voice
Review-Finding: v1/outside-voice#2 reader=outside-voice
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Say in the changelog entry that the base is merged into the child before the carry

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* List the receipt base mismatch refusal in the land refusal tables

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Leave the crew captain refusal table for a follow-up so this PR changes no agent instructions after review

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-09 18:34:34 +00:00
Garry Tanandcapy-ai[bot] 89856f3b3a Make the behind= trailer and rebase rules agree across gstack docs (GST-2136) (#4224)
* Make the behind= trailer and rebase rules agree across gstack docs (GST-2136)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Keep the Capy skill inside its context budget after the behind= rewrite (GST-2136)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Skip the unset fix for a pin with a recorded reason, and add the changelog fragment (GST-2136)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-09 15:46:09 +00:00
Garry Tanandcapy-ai[bot] c25580eb52 Let the docs audit repair a badly shaped final line without using an attempt (#4205)
* Let the docs audit repair a badly shaped final line without using an attempt

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Keep the audit id and outcome out of docs audit format repairs

A missing audit id or a missing or unknown status is now a content failure, a --repair-of that names a non-repairable output no longer uses up the audit's one repair, and the re-ask goes to a fresh agent with no tools instead of the writer child.

Review-Finding: p1/specialist-batched#1 reader=testing
Review-Finding: p1/specialist-batched#2 reader=testing
Review-Finding: p1/red-team#1 reader=red-team
Review-Finding: p1/red-team#2 reader=red-team
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Treat repeated identity keys and malformed outcome lists as failed docs audits

A repeated audit_id or status key, and a files_updated or blockers list that is present but malformed, are now content failures, so a format repair can no longer erase a reported blocker or choose the outcome. A missing list stays repairable.

Review-Finding: v1/outside-voice#1 reader=outside-voice
Review-Finding: v1/outside-voice#2 reader=outside-voice
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-09 10:32:29 +00:00
Garry Tanandcapy-ai[bot] 516435311d Refuse agent words on owner-only autoplan answers (#4201)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-09 09:14:58 +00:00
Garry Tanandcapy-ai[bot] a8e36b9815 Fewer false privacy holds when posting PRs and running pre-merge checks (GST-2047) (#4198)
* Stop flagging test run numbers in PR descriptions as phone numbers (GST-2047)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Let approval import record autoplan run ids that look like phone or card numbers (GST-2047)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Read versions beside a VERSION file or a semver as versions, not public IPs (GST-2047)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Say pre-merge checks in the changelog entry (GST-2047)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Keep the phone-number check on run-id fields that hold other text and on run id names (GST-2047)

Review-Finding: p1/red-team#1 reader=red-team
Review-Finding: p1/specialist-batched#1 reader=security
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Exempt only 11 to 20 digit run numbers in a ship summary block from the phone-number check (GST-2047)

Review-Finding: v1/adversarial-native#2 reader=adversarial-native
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-09 08:55:27 +00:00
Garry Tanandcapy-ai[bot] a229e25806 Let review exclusions handle big results PRs (GST-1967) (#4184)
* Let review exclusions handle big results PRs (GST-1967)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Keep the value rule in review-exclude so the pinned review-risk rules stay at their replayed bytes

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Reword the changelog entry so its credential sentence reads plainly

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-09 03:43:59 +00:00
Garry Tanandcapy-ai[bot] e077053c3c Let pull requests that only change human-facing docs skip the test suites (GST-1951) (#4178)
* Let pull requests that only change human-facing docs skip the test suites (GST-1951)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Quote the docs test list in the docs lane so shellcheck passes

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Keep the Windows smoke check green on docs-only pull requests and update the workflow contract tests

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Keep the merged test check when the base gained a reader of a changed doc, hold the land policy key until a release reads it, and register two more docs reader tests

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Check links in untracked docs and docs with quoted or spaced names, and report an undecodable anchor instead of crashing

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Point the flaky-exception anchor back at its section and test the link checker's exit codes

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-09 01:42:33 +00:00
Garry Tanandcapy-ai[bot] b6155921a5 Stop the pre-push check flagging real files whose names start with tmp or scratch (GST-1944) (#4177)
* Stop pregate flagging real files whose names start with tmp or scratch (GST-1944)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Make the stray-name test safe on case-insensitive disks and record the tmp-word tradeoff

Review-Finding: p1/specialist-batched#1 reader=testing
Review-Finding: p1/red-team#2 reader=red-team
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Describe the new scratch-name rule in the PREGATE_STRAYS troubleshooting entry

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-08 21:10:22 +00:00
Garry Tanandcapy-ai[bot] 6417abf7a6 Move the tools only Capy crews use into a crew/ folder (GST-1833) (#4145)
* Load the Capy crew skills only on Capy machines (GST-1833)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Add changelog entry for Capy-only crew skills (GST-1833)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Move the Capy-only crew tooling into crew/ and run its tests only when needed (GST-1833)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Test that the Capy launch file puts crew/bin on PATH

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Count any ~/.capy as a Capy machine, so a Mac running Capy keeps /captain

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Fix the tests and fixtures that broke when crew tooling moved into crew/

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Plan every crew test when a pull request's merge-base can't be read

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Add a test that checks each crew-only module left the root tree for crew/

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Run crew tests on pull requests that change bin/ commands or workflows they drive

Review-Finding: p1/specialist-batched#1 reader=testing
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Keep running every crew test on every pull request; the skip comes in a later change

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Keep copied installs and older release bisects working after the crew/ move

Setup now copies crew/lib into every host's runtime root beside bin and lib, so Windows installs (which copy instead of linking) can still start gstack-ship-receipt, gstack-pregate and the other commands that import it. The release bisect runs the train-gate script from wherever the checked-out commit has it, so a bisect over commits from before the move still gets a verdict.

Review-Finding: p1/outside-voice#1 reader=outside-voice
Review-Finding: p1/outside-voice#2 reader=outside-voice
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Say in the changelog that Windows installs keep working after the crew/ move

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Point the harness guide's merge-queue rows at crew/lib/ where those modules moved

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Point the plain-title test at the wave module's new home in crew/ (GST-1833)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-08 14:26:14 +00:00
Garry Tanandcapy-ai[bot] 6042f6ad48 Give a clear error when Chromium's sandbox can't start, and make design-build preflight launch the browser (GST-1906) (#4162)
* Give a clear error when Chromium's sandbox can't start, and make design-build preflight launch the browser (GST-1906)

On Linux hosts that deny unprivileged user namespaces (stock Ubuntu 23.10+ under AppArmor, non-root Docker), Chromium aborts with "No usable sandbox!". browse now fails with one error naming both fixes (allow user namespaces, or GSTACK_CHROMIUM_NO_SANDBOX=1 for trusted pages only) with Chromium's line below it, and never turns the sandbox off on its own. Docker's /.dockerenv now counts as a container, like CONTAINER. gstack-design-build preflight opens and closes one tab in the browser it found and stops with code=BROWSER_SANDBOX and the same error when that launch fails.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Reword the Chromium sandbox changelog entry (GST-1906)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-08 11:23:55 +00:00
Garry Tanandcapy-ai[bot] 1bdb1644d8 Stop /ship stalling on branches that merged in thousands of data files (GST-1855) (#4149)
* Stop /ship stalling on branches that merged in thousands of data files (GST-1855)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Still spot scripts in data files when git grep is set to fixed strings

Review-Finding: p1/red-team#1 reader=red-team
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Document that a review plan run by itself also stops at its time limit

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-08 01:46:06 +00:00
Garry Tanandcapy-ai[bot] 914e7b6fb3 Write PR titles, commit messages and branch names in plain English (GST-1825) (#4146)
* Add a check that keeps tracker codes and internal jargon out of PR titles and branch names

gstack-plain-title checks the readable front of a title, branch name, PR opening or changelog entry against the repository's .gstack/plain-titles.json; one trailing issue code stays allowed. A Plain title workflow runs it on every new pull request, and /ship's push refuses a never-pushed branch whose name fails it.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Move the PR body's machine-read lines into a closing Agent notes section

The ship receipt, its runs block and the Plan line now live in one collapsed section at the end of the body, and every reader looks there first while still accepting the old receipt-at-top layout. gstack-post refuses to post a title the plain-title check refuses, and land uses the checked PR title as main's commit title.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Teach /ship to write plain titles, PR openings, commit messages and changelog entries

The README now lists what gstack is for, so a PR opening can name the goal it serves.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Keep tests, size budgets and generated files in step with plain titles and Agent notes

Copy lists that install result-code modules now include the plain-title codes, the ship goldens and size ledger are refreshed, the new workflow is classified, and the pinned prose tests read the new title and body layout.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Record the test-profile list change as non-behavioral for the shared test harness

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Keep text people add below the PR notes, and fix three smaller review findings

The notes section now ends at its own closing tag, so a collapsible added after it survives the next post. The opening check splits the body the same way the notes reader does. Wave PR titles no longer name the area, which the plain-title check could refuse. The Capy line in the PR-body steps now puts Approvals in the notes.

Review-Finding: p1/specialist-batched#1 reader=testing
Review-Finding: p1/red-team#1 reader=red-team
Review-Finding: p1/red-team#2 reader=red-team
Review-Finding: p1/red-team#3 reader=red-team
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Mask credentials in refused-title lines and keep older PRs' plan lines readable

A refused title's printed match is masked by the secret scanner first. The Plan line reader falls back to the whole body when the Agent notes section has none, so a body written before this change keeps its plan when its first receipt lands. The notes section also ends at its own closing tag when its opener is split or marked open, or when a collapsible inside it is left unclosed.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Print a fixed placeholder when a credential in a refused title cannot be masked

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Keep a plain-title policy edit from scheduling every paid eval

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Record the paid-eval list change as non-behavioral for the shared test harness

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Recheck the PR title on every edit so a base change cannot turn a refused title green

Review-Finding: s11/targeted#1 reader=targeted
Review-Finding: s11/adversarial-native#1 reader=adversarial-native
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-08 00:59:38 +00:00
Garry Tanandcapy-ai[bot] aa46032f2b Stop /ship from stalling when the docs checker misspells a field in its reply (GST-1843) (#4147)
* Stop /ship from stalling when the docs checker misspells a field in its reply (GST-1843)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Make the docs reply check refuse hidden extra fields and keep old audit ids out of the retry

Review-Finding: p1/specialist-batched#1 reader=security
Review-Finding: p1/specialist-batched#2 reader=testing
Review-Finding: p1/red-team#1 reader=red-team
Review-Finding: p1/red-team#2 reader=red-team
Review-Finding: p1/red-team#3 reader=red-team
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Let the docs eval fixture run the new reply check, and keep odd audit ids and keys from escaping it

Review-Finding: v1/outside-voice#2 reader=outside-voice
Review-Finding: v1/adversarial-native#1 reader=adversarial-native
Review-Finding: fc1/fix-check#1 reader=fix-check
Review-Finding: v1/outside-voice#1 reader=outside-voice
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Add the changelog entry for the docs reply check

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* List every way a docs checker reply can be refused in the troubleshooting entry

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-07 22:27:38 +00:00
Garry Tanandcapy-ai[bot] 7cb151bff7 Count an outside review as clean only when it ends with a VERDICT line (#4140)
* Add failing tests: outside reviews read clean only from a last-line verdict

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Count an outside review as clean only from its last VERDICT line

Every outside-review prompt now asks the reviewer to end with exactly
VERDICT: CLEAN or VERDICT: FINDINGS, and the parser reads a pass only from
that line. Prose no-findings sentences are no longer evidence for clean.
Codex's structured review and /codex review run through codex exec, since
codex review --base takes no prompt and could never give the line.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Repin the outside reviewer briefs and fix the tests the verdict line broke (GST-1821)

The outside brief, both adversarial sections and the review-army prompt-file line now carry the last-line VERDICT request; their pins move under the preregistered no-loss replay GST-1821. Test fakes that wrote a clean reply now end it with VERDICT: CLEAN, the review carve marker follows the codex exec sentence, size pins drop where skills shrank, and the plan-review prompt-file line is shortened so /plan-eng-review stays at its pin.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Give the plan-review invocation test's fake reviewer the verdict line it now needs

CI's free-suite shard 5 failed at 1de52b0 with 18 cases in test/model-role-invocation.test.ts: the fake Codex reply had no VERDICT line, so it read unverified (exit 4), and the review-mode template now has one codex exec dispatch block instead of two. The fake reply now ends with VERDICT: FINDINGS and the block count expects one.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Stop the changelog correction from claiming the verdict line closes every false-clean case

Review-Finding: p1/red-team#2 reader=red-team
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Split the changelog correction's last sentence for readability

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Close the review fail-opens the fix-check found (GST-1821)

A /codex review whose git diff fails now stops before Codex runs instead of sending an empty diff. The verdict is read from the raw last line, so inline code after VERDICT: CLEAN no longer reads clean, and VERDICT: CLEAN beside numbered items with no severity reads unverified. Codex structured review gets the base-branch diff appended to its prompt, the way the Claude path does, so the scope no longer depends on the prompt the host writes.

Fix round granted by the Captain (a-aec3882c9d48). Review-section pins move under replay GST-1821: the free 681-input replay and the 54 scored probe replies are unchanged through the fixed parser.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Say in the changelog which numbered-list replies now read unverified, and that /codex review stops without its diff

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Say in the skills guide that /codex review now sends the diff through codex exec

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Check that the structured outside review appends the base-branch diff to its prompt

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-07 22:12:57 +00:00