Commit Graph
557 Commits
Author SHA1 Message Date
Garry Tanandcapy-ai[bot] 2767d229fb gstack-artifact validate now refuses a run.json that gstack-autoplan never wrote (GST-3090) (#4494)
`gstack-artifact validate` and `ack` now refuse a run.json that
gstack-autoplan never wrote, so a hand-built run can no longer pass as a
finished review.

Why: a session skipped `gstack-autoplan next`, built run.json with a
script copied from the reference fixture, and got ARTIFACT_VALID.

Nothing to do unless you validate old or hand-made run directories:
rerun those through gstack-autoplan.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-18 16:45:06 +00:00
Garry Tanandcapy-ai[bot] 45f879b534 The Codex readiness check and the second-model review pick the same model for a custom Codex provider (GST-3089) (#4491)
With a custom Codex provider, `gstack-codex-probe role-ready` and
`gstack-outside-voice run --runner codex-cli` now resolve the
plan-review model the same way, so a session no longer skips a review
that would have run.

Why: the check refused a `config.toml` naming `gpt-6-astra` while the
runner ran it, and a day-one eval session dropped the second-model
review in every phase.

Nothing to do: a custom provider naming the frontier catalog ID just
works; any other name now says how to opt in.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-18 16:44:07 +00:00
Garry Tanandcapy-ai[bot] 782f4595ed Two owner-answer adds at once no longer collide, and three flaky tests get real fixes (GST-3084) (#4490)
Recording the same owner answer from two processes at once no longer
fails about one time in ten; the second add waits for the first to
finish writing.

Why: this was a daily flaky-test repair, and the owner-answers "two
processes adding at once" failure turned out to be a real race, not a
flaky test.

Nothing to do: tests only change, except the 11 lines in
`lib/owner-answers.ts`.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Review-Finding: p1/specialist-batched#1 reader=testing
2026-11-18 15:08:17 +00:00
Garry Tanandcapy-ai[bot] bf2c126b55 gstack-post no longer reads /ship's own run ids and commit ids as phone numbers (#4480) (#4488)
Posting a /ship PR body no longer stops on a phone-number warning for
the run id and commit ids that /ship writes into it.

Why: most /ship runs hit this confirm (#4480, and #4474), which turned a
privacy guard into noise people click past.

Nothing to do: the next /ship post goes through without `--confirm`.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Review-Finding: v1/outside-voice#1 reader=outside-voice
Review-Finding: v1/adversarial-native#1 reader=adversarial-native
2026-11-18 14:57:04 +00:00
Garry Tanandcapy-ai[bot] 3ecd7168b2 The token-capped /ship child on Claude Code now starts its prompt with the typed /ship command (GST-3078) (#4487)
The /ship child that `gstack-ship-budget launch` starts on Claude Code
now opens its prompt with `/ship --continue ` (or `/gstack-ship` under
`skill_prefix`), so Claude Code expands the skill instead of hoping the
model finds it.

Why: Claude Code expands a skill only when the prompt starts with the
typed command, and unattended Opus 5.5 found a skill from its
description in 0 of 60 sessions (gstack-evals#366).

Nothing to do: the rule for parents is now in docs/unattended.md.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-18 13:32:03 +00:00
Garry Tanandcapy-ai[bot] 0109703797 Security findings no longer show their file, line or reason in PR bodies (GST-3076) (#4486)
A security finding that an owner ruled a note, dispositioned, or that
review deferred now shows in a PR body only as an opaque id and
"security finding, details recorded privately".

Why: on a public repository the old lines named the file, line and
reason of a live exposure outside the PR's change.

Nothing to do: other findings print exactly as before, and the details
stay in the private approval record.

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/red-team#1 reader=red-team
2026-11-18 12:57:24 +00:00
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] 9222485040 Review planner sends Swift health, permission and on-device storage code to full review (GST-3052) (#4472)
/ship's review planner now sends Swift code that asks for a privacy
permission, reads HealthKit or calendar data, or writes, deletes or
protects users' files on the device to the full review panel.

Why: since #4469, iOS changes that asked for microphone permission,
wrote and deleted meeting transcript files, or read calendars got the
light, one-reader review. Reported from the GHome iOS app's PR review.

Nothing to do: plain SwiftUI views, UserDefaults settings and file reads
still plan light.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Review-Finding: p1/red-team#1 reader=red-team
Review-Finding: p1/red-team#2 reader=red-team
2026-11-18 03:55:13 +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] 29e950227b Review planner sorts Swift and Xcode files by risk instead of sending every iOS PR to the full panel (GST-3041) (#4469)
/ship's review planner now sorts Swift and Xcode files by risk, so a
plain iOS UI change gets the light review instead of the full
five-reader panel.

Why: `gstack-diff-scope` had no rule for `.swift`, so every all-Swift
diff printed `SCOPE_ERROR=unmatched` and the planner failed closed.
Reported from the GHome iOS app's PR review.

Nothing to do: unknown file types still fail closed exactly as before.

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: p2/red-team#1 reader=red-team
2026-11-18 01:28:22 +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] fc5c285035 /office-hours keeps its founder resources out of the skill file (GST-3024) (#4463)
/office-hours no longer carries its 34 founder videos and essays in the
skill file; the closing runs a new `gstack-founder-resources` command
that prints the ones a user hasn't been shown yet.

Why: the skill was 9 bytes from its size cap, and the approved
partner-session improvements need room. This frees about 8.6 KB.

Nothing to do as a reader.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Review-Finding: p1/specialist-batched#1 reader=testing
2026-11-17 22:47:26 +00:00
44c904fe9b Pre-push test selection finds tests in monorepo apps that use their own @/ alias (#4464)
/ship's pre-push test selection now finds the tests of a monorepo app
that imports through its own `@/` alias (for example `apps/mobile`
mapping `@/*` to `./src/*`).

Why: only the root tsconfig was read, so every touched file in such an
app failed with `PREGATE_NO_LANE` even with a test beside it. Rebuilt
from #4462 by @dtoelke, who found and fixed it; thank you.

Nothing to do: a repo whose only tsconfig is at the root (gstack itself)
resolves exactly as before.

Co-authored-by: stackpt-agent <348614618+stackpt-agent@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Review-Finding: p1/specialist-batched#1 reader=testing
Review-Finding: p2v/outside-voice#1 reader=outside-voice
2026-11-17 22:43:07 +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] 76535826f5 /ship stops asking owners to clear base-side merge text and reviewers' confirmation prose (GST-2975, GST-2972) (#4458)
/ship no longer stops for an owner's ruling when a base merge only
changes base-side text, such as the preamble hash in regenerated
SKILL.md files, and a reviewer's confirmation prose becomes a finding
the lead can lower with a reason.

Why: each of these cost a stopped /ship and an owner ruling on recent
PRs (#4383, ghome#16, #4431), which keeps unattended shipping from
finishing.

Nothing to do.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-17 20:08:56 +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] e1cfceae6a Secrets check stops flagging three code shapes and catches concatenated and commented secrets (GST-3004) (#4457)
The secrets check no longer stops a push on three kinds of ordinary code
that only look like secrets: TypeScript types with spaced generic
arguments, Python arguments that read a settings constant, and camelCase
dotted field paths.

It also catches two kinds of real secrets it used to miss, one built
with `+` from short pieces and one written in a comment, so pushes are
both quieter and safer.

Nothing to do; a secret in any of the loosened positions still fails the
check.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Review-Finding: p1/adversarial-native#1 reader=adversarial-native
Review-Finding: p1/outside-voice#1 reader=outside-voice
Review-Finding: p1/outside-voice#2 reader=outside-voice
2026-11-17 18:47:18 +00:00
Garry Tanandcapy-ai[bot] b1c32824fd Keep skill_prefix after updates, retire the ClawHub install route, and stop misreading cross-repo issue refs (GST-2967) (#4454)
Three small fixes: `skill_prefix=true` now survives updates when gbrain
is installed, the OpenClaw docs stop sending people to stale ClawHub
skills, and `gstack-issue-links` no longer reads other repositories'
issue numbers as gstack issues.

Why: each one misleads users or /ship today (wrong skill names after
every update, April 2026 skill builds, wrong `Refs #N` lines in PR
bodies).

Nothing to do as a reader. Thanks @fliaron (#4413) and @exGeni (#4421)
for the detailed reports.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-17 17:13:42 +00:00
Garry Tanandcapy-ai[bot] 0ee5914628 Run each driven /ship phase as one command, count its calls, and stop it at 100 minutes (GST-2984) (#4451)
A driven /ship now runs each ship/DRIVER.md phase as one command, shows
how many calls the run made, and stops itself with a printed line at 100
minutes.

Why: measured /ship runs made 121 to 308 calls where the driver plans 9
to 12, and 10 of 12 ran past the 100-minute stop while those limits were
only prose.

Nothing to do: older ship records without `calls=` still validate and
print.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Review-Finding: p1/outside-voice#1 reader=outside-voice
2026-11-17 16:44:06 +00:00
Garry Tanandcapy-ai[bot] 9c6e0a0f85 Token-capped /ship hands its child Claude Code session its prompt (#4448) (#4452)
A `/ship` with a token cap on Claude Code no longer stops at its first
handoff: the child `claude -p` session now gets its prompt.

Why: `--allowedTools` takes every argument after it, so the prompt was
read as one more tool name and the child exited at once. The launch now
puts `--` before the prompt.

Nothing to do. Thanks to @exGeni for the report and diagnosis.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-17 16:37:56 +00:00
Garry Tanandcapy-ai[bot] f000b6e0e3 Stop giving bug reports a special rule in gstack's router (GST-2873) (#4442)
gstack's router no longer gives bug reports a special check-the-cause,
fix-it-test-first rule, and its description no longer lists debugging,
so the model fixes a bug the way it would without gstack. This keeps
gstack to the parts that measurably help, and on 26 hard real bugs the
rule gave no clear gain.

Nothing to do.

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 14:37:34 +00:00
Garry Tanandcapy-ai[bot] b79843c5d7 Keep a pull request's review count intact when a posted description brings its own run history (GST-2707) (#4440)
When `/ship` posts a pull request's description, the count of earlier
review rounds now always comes from the PR's real history. Before this
fix, a description that brought extra history blocks of its own could
make gstack count one round where there were three.

Why: the per-PR round cap (R51) depends on that count, and it's the last
gap before crews can stop counting rounds by hand.

Nothing to do as a reader.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Review-Finding: p1/specialist-batched#1 reader=red-team
Review-Finding: p1/specialist-batched#2 reader=testing
2026-11-17 14:10:23 +00:00
Garry Tanandcapy-ai[bot] 169eb9c8a5 Approval page re-reviews two-reviewer scope changes and checks quotes only against this repository (#4441)
/autoplan's approval page now re-reviews a scope change both reviewers
raise, asks a plan with no Owner's words to confirm its direction, and
checks owner quotes only against this repository's approvals record.

This keeps the rule that only the owner's own words set a plan's
direction, and there is nothing for the reader to do.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Review-Finding: p1/red-team#1 reader=red-team
Review-Finding: p1/specialist-batched#1 reader=specialist-batched
Review-Finding: p1/specialist-batched#2 reader=specialist-batched
2026-11-17 13:22:10 +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
Garry Tanandcapy-ai[bot] e8c8625bd6 Keep checking custom skill contracts that still list the removed test-after-edit item (GST-2811) (#4439)
* Keep checking a custom skill's contract when it still lists the removed test-after-edit item

The Stop hook used to treat such a contract as invalid and check none of
its items. It now skips only that item, warns with a line naming the file
and item, and checks the rest.

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

* Move the changelog note to its own entry, since a landed entry is never edited

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

* fix: pre-landing review fixes

Test that gstack-skill-contract check warns about a removed-kind item and checks the rest.

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

* chore: changelog and TODOS

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 12:51:54 +00:00
Garry Tanandcapy-ai[bot] ab114c5308 Say when to use each gstack skill in Claude Code's skill list (GST-2774) (#4387)
* Say when to use each gstack skill in Claude Code's skill list (GST-2774)

Claude Code's listing of each gstack skill now keeps a short when-to-use
clause after its first sentence, so Opus 5.5 loads /review on "review my
changes" and /plan-eng-review on "plan this feature" (GSTA-558).

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

* Keep /review and /plan-eng-review within their size pins and refresh budgets

CI on the first head found five size and fact checks the new catalog
clause moved: the per-host SKILL.md size pins, the context-budget
ceilings, the deslop-shared-libs catalog byte pin, the Claude ship golden
and the catalog ceiling CLAUDE.md states. /review's and /plan-eng-review's
full descriptions are now shorter than before, so their pins go down, and
/plan-eng-review's scope gate is unchanged from main.

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

* Say which skills keep no when-to-use clause in the changelog entry

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

* Update the catalog budget and voice-trigger docs for the when-to-use clause

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

* Drop "deploy this" from /ship's Claude Code skill list line

Deploying belongs to /land-and-deploy, so /ship's when-to-use clause keeps
"ship it, create a pr, push to main" only. Budgets, the size ledger and the
Claude ship golden are re-measured.

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

* fix: pre-landing review fixes

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

* Re-measure the setup-gbrain size cap after merging main

Main grew setup-gbrain's always-loaded part to 38,621 bytes, and this
branch's when-to-use clause adds 55 more, so the cap measured on the old
base (38,637) is stale. The cap is now the merged measurement, 38,676.

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 12:23:35 +00:00
Garry Tanandcapy-ai[bot] 127bcd6d55 Accept a requested docs fix when the audit names the file with a line number (#4437)
finish --docs-requested refused a correct fix when the docs audit named the
file as path:line ("changelog.d/engine-parity-decisions.md:8: wording") or
path:line:column, because the match only allowed whitespace, quotes or
punctuation right after the path. It now also allows :<line> and
:<line>:<column> before those, while a different file sharing the path's
prefix still doesn't match. Reported by Vorflux via FOUN-32.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-17 12:22:11 +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] 800a9269fd gstack-runaway prices each wake and marks it cold or warm (GST-2770) (#4385)
* gstack-runaway prices each wake and marks it cold or warm (GST-2770)

Each wake read is priced in warm model calls, with a cold call (after the 5-minute prompt cache lapsed) at 19.4. The scan line reports cold and empty wakes' share of spend, and scan --wakes lists each wake. A message sent to another thread now counts as action.

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

* Document gstack-runaway wake pricing in the /runaway-stopper reference

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

* gstack-runaway charges a lapsed cache to the call after a long tool and ignores a null message target

A cold wake no longer counts its first call twice, a call issued more than 5 minutes after the previous model call is cold whether or not an inbound item was recorded, and a report to the parent with an explicit null target stays a report.

Review-Finding: p1/outside-voice#1 reader=outside-voice
Review-Finding: p1/outside-voice#3 reader=outside-voice
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>

* Describe gstack-runaway's cold_extra_spend and empty_spend as shares of spend in docs/skills.md

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 11:28:47 +00:00
Garry Tanandcapy-ai[bot] 99256a8631 Stop the optional Stop hook checking for a test after the last edit (GST-2811) (#4428)
* Stop the optional Stop hook checking for a test after the last edit (GST-2811)

Models already run a test after their last edit when /verify asks (Opus 5.5
96%, GPT-6.1 Sol 89%), and the hook's check added no measurable gain. Remove
the check_after_last_edit contract item and its shell-write parser, keep the
rule as /verify prose, and stop /verify telling models never to edit CHANGELOG.

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

* Point the removed shell-write parser at the contract checker's test so the pre-merge check accepts its removal

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

* Say in the changelog entry that a custom contract with the removed item stops being checked

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 11:13:47 +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] 5b4fa9ea33 Run large unit suites on Linux instead of failing with argument list too long (#4424) (#4426)
* Run large unit suites on Linux instead of failing with argument list too long

A lane passed every unit file in one bash -c argument; Linux caps one
argument at 128 KiB, so thousands of files failed with E2BIG. Split the
file list into byte-bounded chunks run in sequence and read back as one
run, and classify E2BIG as its own arg-limit cause.

Fixes #4424

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

* fix: pre-landing review fixes

Put the failing fixture file last after sorting so the arg-limit test really checks a failure in the final chunk.

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

* docs: note the Windows chunk size for split lane file lists

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 06:09:13 +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] 3b650356f3 /ship reviewers state their blocker count in one line, and gstack checks it against their findings (GST-2495) (#4353)
* Reviewers state their blocker count in one line, and gstack checks it against the findings it parsed

Every blocking /ship reader's brief now asks for REVIEW_VERDICT: blocking=<n>. collect adds a CRITICAL row for each
declared blocker it did not parse, marks word-only CRITICAL rows as summary candidates when the count is lower, and
never lowers a row on its own except the native voice's unanchored FIXABLE raise. Ledgers rendered before this change
replay unchanged. Includes the preregistration for the no-loss replay.

Refs: GST-2495
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Add the verdict-line no-loss replay results

Refs: GST-2495
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Keep a finding line that mentions REVIEW_VERDICT instead of stripping it

Only a well-formed verdict line is removed before findings are parsed; prose that names the token, or a malformed attempt, stays in the text so its finding is still collected.

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

* Check a stored summary flag against the reply on every ledger, not only ones that asked for the verdict line

verify now re-derives summary_candidate for every merged row, so a flag edited onto a real CRITICAL in an older ledger can no longer let judgment lower it while verify reports clean.

Review-Finding: v2/outside-voice#1 reader=outside-voice
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Never lower a finding automatically when a reviewer's blocker count is lower than the parse

A valid verdict line used to relabel the native voice's unanchored FIXABLE prose to its own label. Beside a
denial line such as 'No other CRITICAL issues.' that let a real blocker drop to FIXABLE while the count still
agreed. Those rows now stay CRITICAL and become summary candidates the lead lowers with a written reason.

Review-Finding: v3/adversarial-native#1 reader=adversarial-native
Refs: GST-2495
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Split a run-on sentence in the verdict-line changelog 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>
2026-11-14 07:31:35 +00:00
Garry Tanandcapy-ai[bot] 89be362eb2 Exclude a data file from /ship's review when the base policy names it by file name (GST-2674) (#4356)
* Exclude a data file from /ship's review when the base policy names it by file name (GST-2674)

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

* Split a run-on sentence in the review-exclude changelog 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>
2026-11-14 06:31:25 +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