Commit Graph
9 Commits
Author SHA1 Message Date
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] ddbf1c9a47 fix: /autoplan gate makes each phase publish in order after its report (GST-1814) (#4135)
* test: failing-first replays of the three E2 autoplan gate sequences (GST-1814)

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

* fix: /autoplan gate refuses a phase publish out of order or before its report; per-step Stop budget that never exhausts before the first report (GST-1814)

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

* fix: pre-landing review fixes

Before scope is known, CEO publishes first; an exhausted or released run no longer refuses publishes.

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

* fix: the publish check reads the transcript only up to the call it decides

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

* docs: changelog fragment notes that a released or exhausted run no longer refuses publishes

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 18:43:11 +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] ca5dbfc7e0 feat: opt-in /autoplan stop gate with GSTACK_GATE markers (GST-1666) (#4100)
* test: failing-first cases for the opt-in /autoplan stop gate (GST-1666)

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

* feat: opt-in /autoplan stop gate with GSTACK_GATE markers (GST-1666)

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

* fix: keep the ceo-only section name out of lib/autoplan-stop-gate.ts (carve guard)

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

* fix: pre-landing review fixes

Anchor the runner match to a command position, treat a failed background launch as not pending, and read --ceo-only from a Skill call's command/skill fields and from the prompt before a Read load.

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

* docs: name the /autoplan gate in skill-routing and the smoke section

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 00:57:41 +00:00
Garry Tanandcapy-ai[bot] bd36aa0b46 fix: skill gate hooks outlive the gate deadline, so a slow gate no longer fails open (#4072)
* skill gates: the hook timeout outlives the clamped gate deadline (GST-1615)

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

* test: #4045/#4047 narrow screens select the bin/gstack-config gate case once setup runs gstack-skill-gates (GST-1615)

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 13:22:18 +00:00
Garry Tanandcapy-ai[bot] 4743132ca0 plan-ceo-review gate: hold the final stop until ranked Findings are written (GST-1461) (#4047)
* investigate gate: undo gated commits on branches behind the baseline (GST-1461 fc#1)

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

* plan-ceo-review gate: hold Stop/SubagentStop until ranked Findings are written (GST-1461)

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

* test: unit-test rankedRisksGap so lib/ceo-review-gate.ts has a pregate lane (GST-1461)

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

* fix: plan-ceo-review gate never names or accepts a file inside a skills/ tree (GST-1461)

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

* fix: gstack-skill-gates settings quotes hook paths for the shell (GST-1461 ov#5)

Review-Finding: bin/gstack-skill-gates:60:outside-voice reader=outside-voice
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix: investigate gate restores raw bytes, index and mode; attributes come from the baseline (GST-1461 ov#1-4)

Review-Finding: lib/investigate-gate.ts:126:outside-voice reader=outside-voice
Review-Finding: lib/investigate-gate.ts:254:outside-voice reader=outside-voice
Review-Finding: lib/investigate-gate.ts:256:outside-voice reader=outside-voice
Review-Finding: lib/investigate-gate.ts:64:outside-voice reader=outside-voice
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix: investigate gate baseline includes staged-only changes so a rollback keeps them (GST-1461)

Review-Finding: p2/outside-voice#1 reader=outside-voice
Review-Finding: p2/adversarial-native#6 reader=adversarial-native
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix: plan-ceo-review gate judges skills/ paths from the repo root and filters the repo scan too (GST-1461)

Review-Finding: p2/outside-voice#2 reader=outside-voice
Review-Finding: p2/adversarial-native#2 reader=adversarial-native
Review-Finding: p2/adversarial-native#3 reader=adversarial-native
Review-Finding: p2/red-team#2 reader=red-team
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* docs: skill-gates restore modes and skills/ exclusion match the code (GST-1461)

Review-Finding: p2/adversarial-native#7 reader=adversarial-native
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* docs: changelog entry covers the investigate gate rollback fixes (GST-1461)

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

* ci: retrigger pull_request checks after stale dirty state

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 21:27:04 +00:00
Garry Tanandcapy-ai[bot] 9e809ab5b1 investigate: opt-in gate that holds root cause before fix, through Bash too (GST-1461) (#4045)
* investigate: opt-in gate that holds root cause before fix, through Bash too (GST-1461)

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

* investigate gate: posix paths in edit blocks, CI fixes (GST-1461)

- hook: the edit branch computes the repo-relative path once in posix form, so
  the marker and deny text read src/total.ts on Windows too
- lib/review-depth.ts is back to main's pinned bytes; lib/investigate-gate.ts
  keeps its own copy of TEST_PATH
- gstack-skill-gates report: destructure session_id (the pregate secrets scan
  read the old line as a secret-named assignment)
- tests: pin core.autocrlf=false in the git fixtures, skip the symlink swap on
  Windows, give setup-hook-syntax-gate's fixture the shared TypeScript entry a
  shim runs, unit-test excludedReason, and check the smoke's pinned Claude Code
  version against docs/skill-gates.md

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

* fix: pre-landing review fixes (GST-1461)

- checkTree saves the bytes a restore replaces in the session directory and
  the block names the copy, so a concurrent editor save is never lost
- a new commit is undone to its newest ancestor that existed before the
  baseline or that a remote-tracking ref holds, not to the baseline HEAD: a
  fix committed on another branch moves that branch back to its own tip,
  and pull/merge of fetched upstream commits is not undone; the block lists
  the commit's other changes left staged
- runGateHook takes the switch reading from its caller, so the
  investigate_gate config key has a literal reader (gstack-config-defaults)
- the slow checkout case gets an explicit 30 s test timeout

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

* fix: pre-landing review fixes, round 2 (GST-1461)

- an amend or rebase of commits from before the baseline on the same branch
  is undone to the baseline HEAD, not to its parent; on a different branch
  the gate blocks but leaves the commit in place
- existedBefore answers reachability with one rev-list call instead of one
  merge-base per ref, so a fix commit in a repo with hundreds of refs is
  still undone inside the 5 s hook deadline

Review-Finding: p2/specialist-batched#1 reader=testing
Review-Finding: p2/red-team#1 reader=red-team
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 20:46:19 +00:00
Garry Tanandcapy-ai[bot] 18d557d30c v1.94.33.0 fix(ship-queue, hooks): selector reads the checkout under review; one SWITCH_DEFAULT per hook switch; installs are not checks; timed agent deferral (GST-1088 follow-up) (#3933)
* fix(ship-queue, hooks): selector reads the checkout under review; config lists the hook switches; installs are not checks; one deferral per running agent set (GST-1088 follow-up)

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

* feat(hooks): one SWITCH_DEFAULT per hook switch, read by setup, the hooks, gstack-config and gstack-skill-route (GST-1088 follow-up)

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

* fix(hooks): option values are not the check verb, wrapper chains stay linear, agent stalls are timed, report re-checks deferred runs (GST-1088 follow-up review)

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

* fix(hooks): tests read SWITCH_DEFAULT instead of assuming off; an unreadable config turns both hooks off whatever the default (GST-1088 follow-up)

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>
2026-11-03 18:53:52 +00:00
Garry Tanandcapy-ai[bot] 6a370bd7ba v1.94.6.0 feat(hooks): opt-in skill routing and contract Stop hooks with gstack-skill-contract (GST-1088 lane A) (#3912)
* feat(hooks): opt-in skill routing and contract Stop hooks, gstack-skill-contract and gstack-skill-route (GST-1088 lane A)

Both switches default off. UserPromptSubmit routing hook scores prompts against installed triggers; Stop hook blocks once when a contract skill ends without its outputs, failing open on every state error. setup gains --[no-]skill-routing and --[no-]skill-contracts mirroring the timeline gate.

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

* test(hooks): stop-hook test imports the state error line it pins (test-of-test ratchet)

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

* fix(hooks): route only the four discovery targets; register the skill-contract fixture as free (GST-1088 lane A)

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

* fix(hooks): review round 1 on the contract Stop hook: record after stop_hook_active, read last_assistant_message, per-agent completion, met runs stay met, installed-only SKILL.md loads, program-based check commands, safe specialist names, report rechecks the saved run (GST-1088 lane A)

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

* fix(hooks): review round 2 notes: check commands behind wrappers count, the shell test builtin does not; met_after_block is final (GST-1088 lane A)

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

* feat(hooks): one DEFAULT_MATCHERS table for the checker markers; N = 0 selects no specialists (GST-1088 lane A)

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

* feat(hooks): lane C fixed markers: agent_dispatch prefers its marker line, parenthesized notes are not specialist names (GST-1088 lane A)

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

* feat(hooks): an early exit (STATUS: BLOCKED, Nothing to review) meets the contract (GST-1088 lane A)

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

* fix(hooks): early exit only from the final message, line-anchored (GST-1088 lane A)

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>
2026-11-03 06:31:35 +00:00