Commit Graph
287 Commits
Author SHA1 Message Date
Garry Tanandcapy-ai[bot] 9ea26ecc42 Telemetry records why skill runs end, which host and model ran them, and how upgrades went (GST-3234) (#4542)
gstack's anonymous usage telemetry now records nine more fields: the
host and model family, how a skill was started, why it ended, whether
checks passed, how skill routing is set up, a random per-session id, and
for upgrades the version left and any error.

This tells us where skills stop working and which setups break upgrades,
which the current outcome-only data can't show.

Deploy in order after merge: apply migration 009, deploy the
telemetry-ingest function, then release the client; apply migration 007
after that.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Review-Finding: p1/specialist-batched#2 reader=specialist-batched
Review-Finding: p1/specialist-batched#3 reader=specialist-batched
Review-Finding: p1/adversarial-native#1 reader=adversarial-native
Review-Finding: p1/outside-voice#2 reader=outside-voice
Review-Finding: v1/outside-voice#1 reader=outside-voice
Review-Finding: v1/outside-voice#2 reader=outside-voice
2026-11-19 23:10:19 +00:00
Garry Tanandcapy-ai[bot] 7f9c1bc52a Claude Code skills run their start step as they load, so it can't be skipped (GST-3157) (#4509)
In Claude Code, every gstack skill now runs its start command and loads
the shared preamble while the skill loads, so the model starts with
their output instead of an instruction it can skip.

Why: in test runs, loaded skills' steps were followed in only 45% to 62%
of sessions, and /autoplan's start command never ran in 5 of 10.

Nothing to do: other hosts keep today's instructions, and if Claude Code
can't run the step, the skill says so and the model runs it as before.

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#3 reader=testing
Review-Finding: p1/red-team#1 reader=red-team
Review-Finding: p1/red-team#2 reader=red-team
2026-11-19 22:05:07 +00:00
5df6b5a8cf The prompt-routing hook names your installed bug-fix skill on bug reports, and never puts /verify first (GST-3237) (#4539)
On a bug report, the routing hook now names the installed bug-fix skill
(prove-it, or any skill whose triggers claim bug fixing) alone, so
/verify is never ranked ahead of it.

Why: in B1d, Opus 5.5 loaded prove-it in 29 of 33 sessions when the hook
named it alone and 0 of 20 when it didn't; the old matcher named it on
only 40 of B1's 60 prompts.

Nothing to do: the hook line's wording is unchanged.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Co-authored-by: Lubos Buracinsky <159481718+lubosxyz@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#1 reader=adversarial-native
Review-Finding: p1/adversarial-native#4 reader=adversarial-native
Review-Finding: p1/specialist-batched#1 reader=testing
Review-Finding: p2/red-team#1 reader=red-team
Review-Finding: p2/specialist-batched#1 reader=testing
2026-11-19 22:04:13 +00:00
Garry Tanandcapy-ai[bot] b23e1b01a7 Codex picker prompts and docs name skills the way Codex lists them (GST-3196) (#4524)
On Codex, the suggested prompts for nine gstack skills and the README
now say `$office-hours`, `$review` and so on, which load the skill;
`$gstack-office-hours` loaded nothing.

Why: Codex lists each skill by the `name:` in its SKILL.md, not the
`gstack-` folder, and skill_prefix never changes that name on Codex.

Nothing to do: the next `./setup --host codex` picks it up.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-19 13:10:18 +00:00
Garry Tanandcapy-ai[bot] e95cea8404 On Capy, /ship hands its pull request edits and comments to Capy's PR tool, always naming the right repository (GST-3183) (#4518)
On Capy, /ship's PR body edits, comments and new PRs no longer go out
through `gh` under the machine owner's GitHub account.

Each write runs its checks, saves the exact text to a private file and
prints a `HOST_PUBLISH:` line that names the repository (and host, off
github.com) it belongs to, so Capy's PR tool sends it to the same place
`gh` would have.

Nothing changes outside Capy (`GSTACK_CAPY` unset).

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Review-Finding: p1/specialist-batched#1 reader=specialist-batched
Review-Finding: p1/specialist-batched#3 reader=specialist-batched
Review-Finding: p1/red-team#6 reader=red-team
Review-Finding: p1/specialist-batched#1 reader=testing
Review-Finding: p1/specialist-batched#2 reader=testing
2026-11-19 11:30:53 +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] 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] 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] 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] 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] 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] a141e94388 Ask each question once and check every handed-over file, in every skill that loads the shared preamble (GST-2756) (#4383)
* Load the never-print-secrets rule in every skill on every host, with the commands it missed (GST-2753)

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

* Ask each question once and check every handed-over file, in every skill on every host (GST-2756)

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

* Point the shared CI-wait rule at gstack-pr-wait and name the missed secret-printing commands

The Ground Rules section told every skill to wait with gh pr checks --watch, which spends the shared GitHub GraphQL quota gstack moved off; it now names gstack-pr-wait. The banned list also covers ps aux and ps -ef, set -x, git config -l and an export $(...) that expands to a bare export. Size caps raised to the measured +70 bytes.

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>

* Say which skills carry the new rule in its release note

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

* Say the new rules reach only skills that load the shared preamble

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

* List all four shared Ground Rules in the loadouts guide

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 12:05:52 +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] 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] 76fad3edd9 Make gstack agents lead every report with what failed, what's unverified and what else changed (GST-1455) (#4273)
* Make gstack agents lead every report with what failed, what's unverified and what else changed (GST-1455)

The shared closer asks a status report to stay under 250 words and open with Failed or skipped:, Unverified: and Also changed: lines, each naming every item or none; lists past 10 give the top 10 and a count. Capy's factory.md point 10, the lane report Outcome and READY's lane lines carry the same lines, and point 10 points findings write-ups at ETHOS.md section 8. The wording is GEVA-2's round-3 candidate f83eba4, ported without the retired /investigate rows. factory.md is 4,396 B, so its budget rises from 4,200 to 4,400.

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

* Update the ship skill golden files for the new shared preamble id (GST-1455)

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 09:00:55 +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] 28822af38c Load the never-print-secrets rule in every skill on every host, with the commands it missed (GST-2753) (#4382)
* Load the never-print-secrets rule in every skill on every host, with the commands it missed (GST-2753)

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

* Point the shared CI-wait rule at gstack-pr-wait and name the missed secret-printing commands

The Ground Rules section told every skill to wait with gh pr checks --watch, which spends the shared GitHub GraphQL quota gstack moved off; it now names gstack-pr-wait. The banned list also covers ps aux and ps -ef, set -x, git config -l and an export $(...) that expands to a bare export. Size caps raised to the measured +70 bytes.

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>

* Say which skills carry the new rule in its release note

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 02:57:22 +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] 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] a7968dc77d Keep deferred review findings on the PR instead of filing issues (#4208)
* Keep deferred review findings on the PR instead of filing issues

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

* Repin the ship review section after the deferred-findings lead edit

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

* Keep the deferred record's severity as the plain label

The reviewer's stated severity and Blocks text now sit in their own field, so a review-log row built from a deferred record keeps a severity the ledger can rank. The PR body renders the same line as before.

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

* Say deferred findings stay on the PR in the unattended docs

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 11:28:20 +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] 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] 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
Garry Tanandcapy-ai[bot] fb663a2bdd feat: the plan check works on public repos: a machine-local plan_record and a record-keyed Plan line (GST-1774) (#4133)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-07 18:02:40 +00:00
Garry Tanandcapy-ai[bot] 901f246d74 feat: crew PRs carry their brief's Plan line; ship-queue ready and land check it (GST-1751) (#4118)
* feat: crew PRs carry their brief's Plan line; ship-queue ready and land check it (GST-1751)

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

* feat: /ship finish and train ready/land check the Plan line (GST-1751)

finish --plan resolves the brief's Plan line before stage 1; train ready,
base-red ready, train land and stamp land read and write the READY note's
plan record like direct ready and land. Review fixes: grant and exception
rows never pass as plan approvals, render --plan stays short when redacted,
no explicit changelog-only exemption, off mode still records a resolved line.

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

* fix: pre-landing review fixes

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: bin/gstack-approvals:56:functional-contract reader=qa
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* test: cover the plan check at ready, train ready, land-direct, finish and the policy key (GST-1751)

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

* fix: the Plan line stands for the gate's real state, and a broken store never throws (GST-1751)

A row id from an autoplan run resolves to that run's newest gate revision; a
run id needs the plan approval answered and no decision left unanswered.
readStore skips malformed rows and unreadable files; with the key off the
check never throws or prints. Train land rechecks the Plan line before its
merge on every path. /ship's Step 19-C renders Approvals with --plan;
DRIVER.md back under its size limit.

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

* test: train land refuses a slot with no plan record under require (GST-1751)

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

* fix: pre-landing review fixes

Step 8 plan discovery (lib/ship-audit.ts and the plan-completion sections) skips the Plan record line, so a later Plan: <path> binding is still found; render --plan refuses a line it cannot parse. The review skill's pins drop by 4 bytes.

Review-Finding: p1/red-team#1 reader=red-team
Review-Finding: scripts/resolvers/plan-gates.ts:206:functional-contract reader=qa
Review-Finding: p1/red-team#3 reader=red-team
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* docs: changelog fragment passes the prose lint (GST-1751)

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

* docs: captain.md describes the READY PLAN: line (GST-1751)

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

* fix: plan discovery splits the Plan line on whitespace and skips record kinds in any case (GST-1751)

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

* test: lower the gstack-review size pins after the Step 8 binding shrank 4 bytes (GST-1751)

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 09:53:38 +00:00
Garry Tanandcapy-ai[bot] ef99eb5a55 feat: retire /investigate after a no-gain eval (GST-1717) (#4110)
* feat: retire /investigate after a no-gain eval (GST-1717)

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

* fix(skill-start): core routing offer drops every non-core rule line (GST-1717)

The retired /investigate rule became 'Bugs/errors → fix them directly', which no
longer matches '→ invoke /', so proactive=core leaked it into the offered section.
Match any '- … → ' rule line.

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

* revert(review): keep review/checklist.md at its no-loss-pinned bytes (GST-1717)

The pin names replay GSTA-224 H1; a reviewer checklist edit merges only after a
passing no-loss replay (crew rule 15). The /investigate flake line stays until a
replayed repin.

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

* test: repair free-suite fallout from retiring /investigate (GST-1717)

CI run 42340956269 at 83a8a9a: drop fixtures, ledger rows, allowlist entries and
counts for the retired skill and its deleted paid files; record the harness
change as non-behavioral; the test-of-test detector accepts path.join(ROOT, 'bin');
uncovered-prompt fixtures use a tracked prompt, since an untracked path now
reads as a deleted one.

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

* fix(relink): back up a retired skill's real SKILL.md before cleaning it (GST-1717)

With the skill's source gone, the customized-file check never ran, so a
banner-carrying local copy of investigate/SKILL.md was deleted instead of moved
to the backup root (red-team review, pass 1).

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

* fix(qm): restore the review checklist's flake-line rewrite (GST-1717)

review/checklist.md keeps its pinned /investigate line, so the QM edition needs
its replaceText rule back; qm/ stays fresh against the generator.

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

* docs(changelog): name the setup flag break, the relink backup and the pinned checklist line (GST-1717)

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

* fix(setup,relink): back up a retired skill's real SKILL.md instead of deleting it (GST-1717)

Scoped fix round under grant a-360dd62bd46a (outside-voice blocking finding and
adversarial #1, #4). setup's prune compares a copied host entry with the render
before removing that render, and backs up a copy that differs or whose render is
gone; relink no longer takes the marker's rm -rf for a skill whose source is
gone, so a real SKILL.md is backed up and the user's files stay. setup reports a
failed remove-source of the retired gate hooks on stderr.

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

* fix(pr-profile): a changed prompt counts as deleted only when it is gone from disk (GST-1717)

An untracked prompt file on disk still needs prompt validation (targeted review
finding); harness change recorded as non-behavioral.

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

* docs(changelog): exact backup wording, the hook-removal warning and GST-1744 (GST-1717)

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

* fix(setup): one backup folder per host for a retired skill's copies (GST-1717)

Under grant a-c95576b8b1f9 (fix-check#1): every copy host moved its
gstack-investigate/SKILL.md to the same backup path, so a later host's copy
overwrote an earlier host's edits. A sandboxed ./setup --host factory run showed
gen-skill-docs removes the retired render before the prune, so every real copy
is backed up; each host now gets its own folder.

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

* docs(changelog): say exactly what setup backs up for a retired skill (GST-1717)

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

* docs(changelog): end the two colon sentences prose-lint flagged (GST-1717)

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

* test(retired-skills): name plan-eng-review once behind a pregate-literal waiver (GST-1717)

pregate's literals check read the GSTACK_RETIRED_SKILLS change as an old
value still in the tests. plan-eng-review is still retired; investigate was
appended. The fixture names it once, with the waiver.

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 06:52:04 +00:00
Garry Tanandcapy-ai[bot] 5862765a20 feat(diff-scope): template UI in .ts/.js counts as frontend; receipt records the static design pass (GST-1718) (#4112)
* feat(diff-scope): template UI in .ts/.js counts as frontend; receipt records the static design pass (GST-1718)

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

* test: regenerate ship goldens for the static design-review line (GST-1718)

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

* fix: count edits inside tagged templates and spaced template tags as frontend

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

* fix: one set comparison per template file instead of a grep per changed line

Review-Finding: p2/red-team#2 reader=red-team
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* docs(changelog): GST-1718 fragment covers edits inside tagged templates

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

* docs(ship-policy): design record wording matches the in-template rule

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 06:39:20 +00:00
Garry Tanandcapy-ai[bot] 3742ee9527 feat: cut standalone /plan-eng-review; /autoplan keeps its eng phase (GST-1698) (#4108)
* feat: cut standalone /plan-eng-review; /autoplan keeps its eng phase (GST-1698)

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

* test: lower shrunk SKILL.md size pins; keep the retired methodology's pins measured beside /autoplan

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

* fix: carry /autoplan's plan-eng-review.md into Kiro installs

Kiro's per-skill loop copied only SKILL.md and sections, so ~/.kiro/skills/gstack-autoplan lacked the Phase 3 methodology file its SKILL.md reads. Generated sibling *.md files now travel with SKILL.md under the same ownership guards.

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

* docs: file /plan-eng-review retirement follow-ups; scope the changelog claim to ./setup

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

* fix: route architecture-review requests to /autoplan by its description (journey-plan-eng)

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 04:17:35 +00:00
Garry Tanandcapy-ai[bot] 10770954f0 ship-receipt write: every docs audit in one /ship run binds the reviewed digest (GST-1616) (#4071)
* fix(ship-receipt): write honors every docs audit in one /ship run (GST-1616)

When Step 14.5 audits twice in one /ship run (an audit, then a base merge and
restamp, then the re-audit), receipt write reset only the last audit's files,
so a file the first audit edited and committed stayed in the review_exclude
selection and write refused the reviewed digest (gbrain #8678).

gstack-docs-candidate snapshot now takes --run (the invocation record), --pre
on a post snapshot (records the files the audit edited, before and after) and
--carry (the run's earlier post snapshot, refused from another run). Write
resets every file the run's audits edited to its content before them when HEAD
holds what the last of them left; a file no audit edited, an edit after an
audit and a carried audit of another run still refuse.

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

* test(docs-candidate): cover --run/--pre/--carry refusals and a three-audit chain (Step 7 coverage, GST-1616)

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

* fix: pre-landing review fixes

Review-Finding: review-p1r/specialist-batched#1 reader=testing
Review-Finding: review-p1r/red-team#1 reader=red-team
Review-Finding: review-p1r/red-team#2 reader=red-team
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(ship-receipt): a carried-audit retry never drops an integrity refusal (GST-1616)

918ab93 retried writeExcludeBinds with shorter carried-audit lists on any
failure, so an unreviewed edit to a file a carried audit edited (one code
names, so the selection digest did not move) bound once that audit was
dropped (outside voice on #4071). Only the reconstruction digest mismatch
retries now; an edit after an audit, a file changed between audits and a
foreign HEAD end the check. The repro is a test that must refuse.

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

* review: record the outside-voice finding b9c5fa8 fixed (GST-1616)

Review-Finding: review-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>
2026-11-06 15:04:30 +00:00
Garry Tanandcapy-ai[bot] 1a06afdc19 ship finish: a Godot UID sidecar added after review binds with no reader; base-declared test_code (GST-1604) (#4063)
* ship finish: a Godot UID sidecar added after review binds with no reader; base-declared test_code globs (GST-1604)

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

* windows-curation: exclude test/ship-uid-sidecar.test.ts (bin shebang spawns fail on windows-latest, run 42205201312)

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

* fix: pre-landing review fixes

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

* fix: pre-landing review fixes (Step 11: unique UID proof, protected paths never declared test code)

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>

* ship sidecar: only another declaration of the UID refuses a sidecar, never a scene that references the script (GST-1604)

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

* changelog: cover the review fixes and the UID-holder narrowing (GST-1604)

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

* docs: the UID sidecar proof counts only another declaration of the UID (GST-1604)

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

* ship pr-body: name the Godot UID sidecar line the receipt requires (GST-1604)

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>
2026-11-06 13:52:51 +00:00
Garry Tanandcapy-ai[bot] 2305526774 review-plan: a granted fix round after the targeted read plans one targeted-only reader (GST-1607) (#4064)
* review-plan: a granted fix round after the targeted read plans one targeted-only reader (GST-1607)

After the owner granted a fix round past the loop cap, the granted round's
fix moved the product patch the targeted record names, so the receipt asked
for a fresh targeted read while the plan printed done (harness-evals #271).
With that --grant (checked against the approval record as before), any
change since the read except plain docs now plans NEXT: targeted on the
GST-1598 route: one targeted reader on HEAD for the head classes. A head
with no targeted class adds no reader; no grant keeps done.

The Capy pass program now runs a targeted manifest's voices stage, so a
NEXT: targeted pass driven through it creates its reader (it activated
voices only for fix-check).

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

* docs: changelog fragment for GST-1607

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

* docs: review-policy names the granted case in the targeted-only skip list (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>
2026-11-06 12:33:37 +00:00
Garry Tanandcapy-ai[bot] 937b360fed review-plan: a docs claim added after the loop plans one targeted-only reader (GST-1598) (#4062)
* test: failing-first repro for GST-1598 (post-review docs money delta has no targeted-only reader)

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

* review-plan: a docs claim added after the loop plans one targeted-only reader (GST-1598)

After a finished review loop, a docs change with a money, security or numeric
claim left the receipt unable to carry the targeted record and the plan at
done, so nothing could dispatch the reader the receipt asks for (harness-evals
#225). With --range-base naming the commit the targeted reader read and
--targeted-ran its patch, a docs-only change since then now plans NEXT:
targeted: one targeted reader on HEAD for the head classes, with
TARGETED_DELTA printed. Code changes keep done; --force targeted refuses and
names the route; gstack-review-dispatch pass builds the one-reader manifest.

Repins lib/review-depth.ts under replay GST-1598 (one Step union member;
the GST-967 and GST-972 grids hash unchanged).

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

* review-targeted-delta: pass the base to plainDocsSince (GST-1598 after #4058)

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

* fix: pre-landing review fixes

targetedDelta counts a path whose branch hunks are unchanged and only the base moved lines beside them (comparePath context) as unchanged, so a main merge next to a reviewed hunk no longer hides the targeted-only read (GST-1598).

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

* changelog: GST-1598 targeted-only read fragment

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>
2026-11-06 11:27:58 +00:00
Garry Tanandcapy-ai[bot] 8d712d63dd ship finish: a declared mechanical version retake after a base merge binds without a new review (GST-1560) (#4053)
* test: failing-first founderstar#563 retake shape, refusals and planner agreement at the cap (GST-1560)

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

* feat(ship): finish routes a declared mechanical retake with no review; --post-review plans the inserted Step 9 (GST-1560)

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

* docs(ship): mechanical_retake, ROUTE_MECHANICAL_REFUSED and the Step 16 planner line (GST-1560)

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

* test: keep ship-mechanical-retake.test.ts off the Windows scoped lane (bin shebang spawns) (GST-1560)

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

* fix: pre-landing review fixes

finish dropped a post-review path named like an Object.prototype key (constructor, toString, __proto__) from behavior through 'p in proven' on a plain object; proven is now a null-prototype map read with Object.hasOwn, with a regression test.

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

* docs: changelog fragment prose lint (GST-1560)

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>
2026-11-06 04:33:54 +00:00
Garry Tanandcapy-ai[bot] cf21a7fbef ship finish: an owner-ruled note closes its finding, and every ruling is listed (GST-1537) (#4050)
* ship finish: an owner-ruled note closes its finding, and every ruling is listed (GST-1537)

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

* test(windows): exclude ship-finish-ruled-notes from the Windows lanes like its ship-bin-fixture siblings (GST-1537)

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

* ship: keep the pinned Step 9 brief unchanged; the PR body's Pre-Landing Review lists ruled notes (GST-1537)

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

* fix: pre-landing review fixes

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

* fix: bind each ruled note to the stop head it was ruled at (GST-1537)

Review-Finding: p2/red-team#1 reader=red-team
Review-Finding: s11/outside-voice#1 reader=outside-voice
Review-Finding: p1/specialist-batched#2 reader=testing
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>
2026-11-06 02:08:16 +00:00
Garry Tanandcapy-ai[bot] 37d55328b0 fix(ship): Steps 7 and 8 audits default to the owner's agent_model (GST-1449) (#4042)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-05 17:12:15 +00:00
Garry Tanandcapy-ai[bot] 641d62291c fix(ship): Step 14.5 docs audit defaults to the owner's agent_model (GST-1439) (#4038)
* fix(ship): Step 14.5 docs audit defaults to the owner's agent_model (GST-1439)

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

* fix(ship): keep the driver and Capy skill inside their size budgets; cover host and bad agent_model (GST-1439)

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>
2026-11-05 16:17:14 +00:00
Garry Tanandcapy-ai[bot] 467be16ab2 fix(ship-receipt): a docs audit after the review no longer forces another review (GST-1429) (#4034)
* fix(ship-receipt): a docs audit after the review no longer voids the review_exclude binding (GST-1429)

Step 14.5's docs audit runs after the review. When it edits, adds or removes a
file under review_exclude_paths, HEAD's selection digest moves and receipt
write refused the reviewed digest. write --docs-post <audit-id>-post.json now
binds the reviewed digest when it is HEAD's selection with the files under a
pattern that changed since the snapshot's HEAD reset to it, each named by the
snapshot with the content HEAD holds and excluded or kept only because code
names it, and every other file selected alike. Anything else still refuses.

The ship driver's Step 19 write omitted --review-exclude, so gbrain #8627
wrote recorded=none; it now passes it, and the refusal says when the flag was
left out.

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

* test(review-exclude): keep the GST-1429 in-process receipt read off the real state root

The #8627-shape test called receiptReviewAtHead in-process with the runner's
GSTACK_STATE_ROOT, so its gate scan wrote gate-diff and slug-cache entries
under the real ~/.gstack and CI rejected free-suite shard 9
(FREE_SUBSHARD_REJECTED, run 42017628509). It now points GSTACK_STATE_ROOT at
the fixture like the docs-only gate-tagged test does.

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

* fix: pre-landing review fixes

The docs-audit exception reset every changed file under review_exclude_paths
to the post snapshot's HEAD, so a docs edit the review read while it was still
uncommitted was reverted and write refused a normal /ship run. --docs-pre
<Prepare snapshot> now narrows the reset to the files the audit changed, back
to their Prepare content. Snapshot hashes of working-tree bytes also compare
against HEAD's content as it checks out, so autocrlf or a clean filter no
longer reads as an edit after the audit.

Review-Finding: s11/outside-voice#1 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>

* chore: changelog and TODOS

gstack: ok 1.96.0.0 for=ship
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>
2026-11-05 12:25:45 +00:00
Garry Tanandcapy-ai[bot] e4f2930812 fix(ship): a required edit after review takes one scoped reader, not another review round (GST-1276, GST-1311) (#4020)
* feat(ship): bounded post-review edits take one scoped reader, not a third review round (GST-1276, GST-1311)

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

* docs(ship): a scoped-review STOP takes one reader, not a fix-check round (GST-1276)

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

* test: bound the diff-scope spawn and record the ship size ledger (GST-1276)

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

* test: repin lib/review-depth.ts on the GST-1276 no-loss replay

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/specialist-batched#2 reader=specialist-batched
Review-Finding: p1/specialist-batched#3 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>

* fix: a blank line or a template literal no longer hides a changed expected value (review fix-check)

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

* fix(ship): a bounded lanes edit changes only dependencies; any other pregate key stops (GST-1276)

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

* ship: take the receipt-write targeted rebind out of GST-1276 (follow-up); document the lanes key check

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

* docs: list always-run.json as a gate path and finish's bounded=N stop

Step 14.5 audit da1-gst1276 corrections.

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

* docs: keep review-policy.md at its reviewed bytes

main's finish reads docs/review-policy.md as agent prose (behavior); the gate-path list omission of .gstack/always-run.json is recorded as doc debt in the PR body.

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>
2026-11-05 04:16:06 +00:00
Garry Tanandcapy-ai[bot] 15dac66e33 fix(ship): make the five judge-flagged workflow spots match the code (GST-1346) (#4004)
* fix(ship): make the five judge-flagged workflow spots match the code (GST-1346)

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

* fix(ship): carry runs the pregate before its push (review fix)

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

* fix(ship): carry pushes early, waits for CI, then pregates; restore stage 1 wording (fix-check)

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

* docs: diff-plus-blocking stops at the third fix cycle; carry order matches ship Step 1 (Step 14.5)

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

* chore: changelog and TODOS

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

* Revert "docs: diff-plus-blocking stops at the third fix cycle; carry order matches ship Step 1 (Step 14.5)"

This reverts commit 5151144c04.

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-04 23:50:18 +00:00
622e8b1f76 fix(ship): one answer per ship-workflow question the judge flagged (GST-1346) (#3996)
* fix(ship): one answer per ship-workflow question the judge flagged (GST-1346)

The ship/SKILL.md workflow judge failed twice on main b244e6d (run 41817566885,
actionability 4/3/3 in both panels) on prose no landed PR changed. Every sample
cited the same conflicts; resolve them without growing the skill:
- Step 11: Codex-mode branches keep only the Claude pass the plan dispatched;
  both Codex passes run on DISPATCH: outside-voice.
- Steps 12/16: item and stage commands serve only a STOP:.
- CI carry: names the draft-PR command; Step 6.5's question covers only Greptile;
  accept runs after Step 17's push.
- Step 19 exit 3 ends Step 22 with status=refused run=-.
Ship union -8 bytes (size ledger), skeleton within its cap.

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

* fix(ship): drop the Step 11 wording; keep the three no-loss-free repairs (GST-1346)

ship/sections/adversarial.md is pinned to a no-loss replay (GSTA-258-C) and its
headings anchor lib/ship-parts.ts, so its rewording needs a replay first; it moves
to a follow-up. A local single-case judge panel without it passed 3/4/4 on all
three samples. Trims the CI_CARRY reason list (the tool prints the reason) to keep
the ship union under its ledger (-11 bytes).

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

* fix(ship): stage 1 builds go to finish as --build, stage 5 commits only regenerated outputs, full draft-PR command (GST-1346)

Step 11 review findings: the bare 'gstack-post pr-create --draft' exits 64
without --base/--title-file/--body-file (outside voice), and '1-4's commands are
only STOP recoveries' read as skipping stage 1's build discovery (native).
Folds #3951's stage 5 commit-owner wording. Ship union -39 bytes.

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

* fix(ship): keep pr-body byte-neutral after the exit-3 status=refused line (GST-1346)

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>
2026-11-04 17:09:00 +00:00
Garry Tanandcapy-ai[bot] c07eddb5af feat(ship,autoplan): five routine stops record a no_stop and keep going (GSTA-258 L5, K1) (#3976)
* feat(ship,autoplan): five routine stops record a no_stop and keep going (GSTA-258 L5, K1)

gstack-no-stop record checks scoped-fix-check, test-timeout-fix,
pregate-flake-rerun and stamp-only-carry against lib/no-stop.ts and
appends {class, reason, evidence} to the branch ledger the receipt
write passes as --no-stop. A scoped fix-check records the standing
grant for gstack-review-plan --grant. gstack-autoplan carries a plan
edit after the owner answered when its changed words name no spend,
cap, arm or verdict, and writes <run>/no-stop.json. Anything that does
not qualify, and every other stop, still stops.

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

* fix(no-stop): review pass 1: drift stays refused, timeout values only, range-base bound to the last pass, word-by-word re-gate, hunk-aware diff parse

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

* fix: pre-landing review fixes

Review pass 2 (below floor): import takes only autoplan-regate records with autoplan:<run>@gate_rev=N evidence; record diffs with --no-renames so a rename is a delete plus an add; a scoped-fix-check also checks the approval record for the branch's K1 grant, so a fresh checkout with an empty ledger still stops; a trailing }, N) counts as a timeout only where it closes a test callback; the re-gate words add paid, eval and model names; Step 19 sets NS on its own line so a path with spaces survives. Also launches gstack-review-read through runScriptSync (free-tests #3197 tripwire, run 41746166882).

Review-Finding: specialist-batched#1 reader=specialist-batched
Review-Finding: specialist-batched#3 reader=specialist-batched
Review-Finding: specialist-batched#4 reader=specialist-batched
Review-Finding: red-team#1 reader=red-team
Review-Finding: red-team#2 reader=red-team
Review-Finding: red-team#3 reader=red-team
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix: autoplan-regate carries only ELI5 additions; timeout and ref checks fail closed

Step 11 voices (round 2): the autoplan-regate word filter failed open on markup, spelled-out counts and reworded verdicts. A plan-file edit now carries only when it adds lines inside ## ELI5 that hold no number and no spend, cap, arm, model or verdict word; any removed or reworded line goes to the owner, and the carry still exports the reviewed plan. A trailing }, N) counts as a timeout only on a line that opens the test call. --range-base and --base resolve to commits with --end-of-options before git sees them.

Review-Finding: targeted#1 reader=targeted
Review-Finding: outside-voice#1 reader=outside-voice
Review-Finding: outside-voice#2 reader=outside-voice
Review-Finding: outside-voice#3 reader=outside-voice
Review-Finding: adversarial-native#1 reader=adversarial-native
Review-Finding: adversarial-native#6 reader=adversarial-native
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* docs: test-timeout-fix counts a trailing timeout only on the line that opens the test call

Step 14.5 docs audit l5-docs-1.

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

* fix(ship): keep ship/DRIVER.md under its 12 KB cap after the main merge

Main brought the driver to exactly 12288 bytes, so the K1 'except gstack-no-stop' clause put it 20 bytes over (quick-bun-default run on ca43af4). Trim two phrases; the pinned fallback sentence is unchanged.

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>
2026-11-04 03:03:39 +00:00
Garry Tanandcapy-ai[bot] 56a800da98 feat: /runaway-stopper — detect, stop and prevent runaway threads and subagents (GST-1279) (#3975)
* feat(runaway-stopper): detect, stop and prevent runaway threads and subagents (GST-1279)

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

* fix(runaway-stopper): autoplan review fixes: input validation, exact /ship task-row meter at 100M, rotation hand-off of subagents and PR watches, bounded fetch program

Skill-Size: 0→6747 bytes (SKILL.md.tmpl)
Evidence: plan docs/evals/runaway-stopper-prereg.md measure_by 2026-11-24
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* docs(ship-budget): describe the task-row reading without a literal thread_id this

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

* fix(runaway-stopper): ship review pass 1: DEFER holds rotation and a self-stop only, working-only defer, subagents file validation, scan exit kept, DRIVER and factory.md within their size budgets

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

* fix(runaway-stopper): ship voices: list limit clamp, allSettled fetch, waiting /ship and shipping descendants defer, unknown flags refused, GSTACK_SHIP_TASK_TITLE implies the task-row meter

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

* fix(ship): leave DRIVER.md unchanged; main left 21 bytes under its 12 KB cap

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>
2026-11-04 02:59:50 +00:00
Garry Tanandcapy-ai[bot] ad6e1db159 fix(ship): trim DRIVER.md back under its 12 KB cap (main red since #3886) (#3981)
* fix(ship): trim DRIVER.md back under its 12 KB cap (main red since #3886)

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

* fix(ship): keep "finish there" in the SKILL.md fallback line

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>
2026-11-04 02:23:11 +00:00
Garry Tanandcapy-ai[bot] 33d83412c6 docs(pregate): after a restart, rerun the remote pregate to reattach (GST-1028) (#3886)
* docs(pregate): after a machine restart, rerun the same remote pregate so it reattaches (GST-1028)

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

* test(ship-driver): pin the restart rerun line (GST-1028)

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

* fix: pre-landing review fixes (name the full reattach key; destroy the old VM when a rerun does not reattach)

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

* docs(changelog): GST-1028 pregate reattach fragment

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

* docs(pregate): the run key hashes the runner script and setup, not a gstack version

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

* docs(changelog): GST-1028 fragment matches the merged driver text

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>
2026-11-04 01:40:51 +00:00
Garry Tanandcapy-ai[bot] e09ea409f0 fix(ship): a second full preflight stops while this checkout's /ship run is open (GST-1204) (#3950)
* fix(ship-preflight): forward --timeout to Step 5's pregate (GST-1196)

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

* fix(ship): a second full preflight stops while this checkout's /ship run is open (GST-1204)

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

* fix(ship): a new /ship from the same harness replaces a stopped run's marker; a run the lease can't record stops (GST-1204 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>
2026-11-04 01:32:57 +00:00