mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-10 02:30:39 +01:00
3dfbf2ea2a76028655792fc89a4d496dff90b8ff
13
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Garry Tanandcapy-ai[bot]
|
6417abf7a6 |
Move the tools only Capy crews use into a crew/ folder (GST-1833) (#4145)
* Load the Capy crew skills only on Capy machines (GST-1833) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Add changelog entry for Capy-only crew skills (GST-1833) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Move the Capy-only crew tooling into crew/ and run its tests only when needed (GST-1833) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Test that the Capy launch file puts crew/bin on PATH Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Count any ~/.capy as a Capy machine, so a Mac running Capy keeps /captain Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Fix the tests and fixtures that broke when crew tooling moved into crew/ Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Plan every crew test when a pull request's merge-base can't be read Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Add a test that checks each crew-only module left the root tree for crew/ Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Run crew tests on pull requests that change bin/ commands or workflows they drive Review-Finding: p1/specialist-batched#1 reader=testing Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Keep running every crew test on every pull request; the skip comes in a later change Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Keep copied installs and older release bisects working after the crew/ move Setup now copies crew/lib into every host's runtime root beside bin and lib, so Windows installs (which copy instead of linking) can still start gstack-ship-receipt, gstack-pregate and the other commands that import it. The release bisect runs the train-gate script from wherever the checked-out commit has it, so a bisect over commits from before the move still gets a verdict. Review-Finding: p1/outside-voice#1 reader=outside-voice Review-Finding: p1/outside-voice#2 reader=outside-voice Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Say in the changelog that Windows installs keep working after the crew/ move Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Point the harness guide's merge-queue rows at crew/lib/ where those modules moved Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Point the plain-title test at the wave module's new home in crew/ (GST-1833) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --------- Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> |
||
|
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> |
||
|
Garry Tanandcapy-ai[bot]
|
52d6c46957 |
test(flaky): marathon census reds on 297f50c7 (gh telemetry in fixture HOME, /autoplan handoff) and two free flakes (GST-1793) (#4128)
* test: pin GH_TELEMETRY=0 in hermetic eval env; office-hours handoff accepts /autoplan (flaky pass 2026-11-07) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: release-cut slow cases get the 30 s free-suite timeout; ruled-notes grant names both shas after review_loop_grant (flaky pass 2026-11-07) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * changelog: flaky pass 2026-11-07 fragment Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: record the hermetic-env.ts GH_TELEMETRY pin as non-behavioral at HARNESS_VERSION 6 (flaky pass 2026-11-07) 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=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> |
||
|
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
|
||
|
Garry Tanandcapy-ai[bot]
|
94392a61ec |
test: harness targets skip retired skills; record the standalone /plan-eng-review paid cases' fates (GST-1698) (#4111)
* test: harness targets skip retired skills; record each standalone /plan-eng-review paid case's fate (GST-1698) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: mark retired /plan-eng-review cases in the detector inventory and TODOS (GST-1698) 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> |
||
|
Garry Tanandcapy-ai[bot]
|
3cf4bc9181 |
fix: test fixtures stop tripping /ship's fetch sweep (GST-1695) (#4105)
* test: leftover test fixtures must not quarantine a /ship review pass (GST-1695) Failing first: a marked fixture root and ship-bin's insteadOf-local clone are printed as ignored and never block the rerun, an unmarked network clone still does, and every test process keeps its temp paths under one marked root that is removed after a timeout. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: test fixtures live under a marked per-process root and the fetch sweep ignores them (GST-1695) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes The macOS named regressions re-host a captured 120-column Claude screen at the run's temp path; under the per-process marked root that path is 11 characters longer, so the permission row overran 120 columns, the PTY split '(shift+tab)' mid-word and the guard never granted (CI run 42326005642). The fake now word-wraps an overlong row at its last space, as Claude Code's renderer does. test-setup.ts, the changelog fragment and docs/review-policy.md now say a Bun.spawn child given no env keeps the original temp dir, and the policy names the exemptions a reader could forge. Review-Finding: test/plan-count-file-permission.test.ts:101:functional-contract reader=qa Review-Finding: p1/red-team#1 reader=red-team Review-Finding: p1/specialist-batched#1 reader=security Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: shard sandboxes carry the fixture marker so a runner-provided TMPDIR stays as handed (GST-1695) The narrow screen (evals run 42333856900) went red on qa-bootstrap: the preload nested gst-XXXXXX under the paid shard's private TMPDIR, so the case's mkdtemp(os.tmpdir()) landed below the bootstrap retention scope's temporary dir and registerBootstrapRetention refused it. createShardSandbox now writes the marker into the shard state dir beside tmp/, and the preload keeps any TMPDIR under a marked directory. Harness pin recorded as non-behavioral. 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> |
||
|
Garry Tanandcapy-ai[bot]
|
12d18a2e10 |
paid screens: narrow screens derive setup instead of running the full gate (GST-1575) (#4056)
* paid screens: narrow screens derive setup; modules/loadouts.json derives through its reader (GST-1575) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * changelog: name the fragment after the branch (GST-1575) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * harness pins: test-pr-profile.ts change is non-behavioral (case selection only) (GST-1575) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * changelog: setup reaches its cases through touchfiles; loadouts-only edits wait for the train census (GST-1575) 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> |
||
|
Garry Tanandcapy-ai[bot]
|
eaf1701da2 |
QM edition: three gstack skills QM loads on demand (GST-1492) (#4049)
* QM edition: three gstack skills QM loads on demand (GST-1492)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: name the QM edition's manifest and shipped script
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* paid lane: classify the QM edition as free-only (no paid case reads qm/)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes
diff-base.sh names the untracked files past the first 30 (UNTRACKED_MORE) instead of dropping them silently; the gstack-review first step tells QM to read every untracked file.
Review-Finding: p1/outside-voice#1 reader=outside-voice
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: point the QM row in docs/hosts.md at the QM edition
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: record the non-behavioral HARNESS_VERSION decision for the qm/** free-only row
CI run 42135033713 failed test/harness-version.test.ts: scripts/test-pr-profile.ts is a pinned shared-harness file and
|
||
|
Garry Tanandcapy-ai[bot]
|
55637db835 |
test: cut the last two behavior-guessing LLM judges; check review-bot history facts for free (GST-1403) (#4014)
* test: cut the qa anti-refusal and voice-tone judges; check review-bot history facts for free (GST-1403) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: count assertions follow the deleted judge file (GST-1403) 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> |
||
|
Garry Tanandcapy-ai[bot]
|
91ddd3bdb1 |
fix(evals): the Codex removed-rule arm really removes the rule from installed skills (GST-840) (#3816)
* fix(evals): Codex removed-rule arm strips the rule from the installed skills (GST-840)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(evals): copy linked directories inside a skill before stripping the rule; record the harness decision (GST-840)
/ship review found readdirSync({ recursive: true }) follows linked
subdirectories, so a rule file under a linked directory inside a real
skill directory would have been deleted and rewritten in the checkout.
Every linked directory on the way to a rule file is now copied first,
with a failing-first test row. The harness-version manifest records
codex-host-runner.ts as non-behavioral: only the manual removed arm
on the Codex host changes.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: keep the Codex safety-arm test off Windows, and spawn its probe with bunIsolationArgs (GST-840)
windows-free-shard 3 (run 41336347706) failed every case: native Bun on
Windows cannot open --config=/dev/null, and the test builds a symlinked
~/.codex/skills install that needs Developer Mode the runners lack.
./setup --host codex copies instead of linking on Windows, so the strip
only matters on POSIX. The probe now uses bunIsolationArgs().
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>
|
||
|
Garry Tanandcapy-ai[bot]
|
781f928ccf |
test: remove the AI scorer that grades skill prose for clarity (freeze repair, GST-1371) (#4009)
* test: remove the skill-prose clarity LLM judges (GST-1371) Removes the 21 eval cases where an LLM scored a skill's instruction text for clarity, completeness and actionability, with their registrations, input builders, response cache, calibration corpora, the cookie-workflow manual-review approval and scripts/judge-controls.ts. The three remaining skill-llm-eval judges keep their prompts, thresholds and samples; the file's supervision wall shrinks to fit them. Outcome judges are untouched. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: pin the retired judge-control script and cookie manual-review record as deleted (GST-1371) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: register the manual-review fixture as free (GST-1371) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: keep the orphaned clarity-judge calibration corpora for a follow-up deletion (GST-1371) Deleting the four corpus directories alone puts the diff over the /ship review ceiling; they serve no configuration now and go in a follow-up. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(todos): file the clarity-judge removal follow-ups (GST-1371) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: keep skill-bundle section paths POSIX so references dedupe on Windows (GST-1371) windows-scoped-shard (run 41918796523) failed 'cross-skill references retain complete bytes once': path.join gave the section entry a backslash path, so a reference to the same section was not recognized as already bundled. 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> |
||
|
Garry Tanandcapy-ai[bot]
|
cff1de2039 |
v1.95.0.0 feat(release-gate): gate main every 8 hours and feed the stable release (inert until adopted) (#3917)
* feat(release-gate): gate main every 8 hours and feed the stable release (inert until adopted) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(release-gate): exit codes match the bin Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(release-gate): blobless checkout and free-only workflow classification Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (finish an open gate before a new head; neutral check for an unfinished gate) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes, pass 2 (the workflow reads main head itself; an open gate on stable or older than three cadences) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: Step 11 review fixes (no paid dispatch without the record on origin; held or failed leaves the gate job green) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(release-gate): re-pin the key to 1.95.0.0 above main; move assertInsideRoot to lib/path-containment.ts to keep ship-policy.ts under 800 lines Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(release-gate): type the narrow fixture rows (test typecheck ratchet) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(release-gate): charge the trial reservation for a null or missing bisect prefix cost so the cap holds across rounds Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(capy-install): wrapper 4 follows the update channel (Step 14.5 audit) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(pregate-selection): mark the fixture wrapper bump as a deliberate old literal Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(pregate-selection): put the literal marker on its own comment line Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(release-gate-workflow): run policy steps with Git Bash argument conversion off, as on the Linux runners (windows-scoped-shard) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: release gate evidence and hold in releases.md, release_gate row in the policy key table (Step 14.5 audit) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(ship-policy): defer the release_gate key-table row to the adoption PR (named documentation risk, GSTA-258) 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> |
||
|
Garry Tanandcapy-ai[bot]
|
a1da77e6d4 |
v1.94.20.0 test(review): one file per review and harness pin, so independent repins merge cleanly (GST-1084) (#3903)
* test(review): one file per review and harness pin, so independent repins merge cleanly (GST-1084)
The reviewer-brief pins move from the table in test/review-packets-removed.test.ts to
test/fixtures/review-pins/{files,replays,brief-bodies}/*.json, and the harness pins from
scripts/harness-version.json to scripts/harness-pins/<path>.json. Every entry is ported
unchanged. New tests prove a stale pin still fails and that two repins of different pins
merge cleanly with a real git merge-tree.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes (GST-1084)
- unadmitted() and the specialist coverage use Object.hasOwn, so an inherited name such as toString is not an admitted replay
- MUST_PIN names every non-specialist reviewer source; deleting one of those pins now fails
- writeManifest writes the pins before the manifest head; pin parse errors name the file
- mergePinEdits removes its repository when setup throws, and the merge tests clean up every merge they made
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: name the changelog fragment for the branch (GST-1084)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: the harness guard pins one file per harness file (GST-1084)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(ship-release): GST-1031 re-pin route reads per-file harness pins (GST-1084)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* changelog: GST-1031 route reads per-file harness pins
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(test-audit): harness guard pins 42 files
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(harness-version): a pin ahead of the manifest version counts as drift (GST-1084)
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>
|