mirror of
https://github.com/garrytan/gstack.git
synced 2026-10-31 22:14:25 +01:00
8b4f5aaf5c8792d9cf9cbc48ff7aed674d4df7a0
677
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Garry Tanandcapy-ai[bot]
|
8b4f5aaf5c |
v1.91.302.0 fix: repair three flaky gate cases from the 2026-10-28 flaky pass (index flags, exploratory QA, cookie auth) (#3553)
* fix(review): shared-code evidence gathering is read-only (index-flags flaky, gate 40619718717)
The failing assume-unchanged trial ran git update-index --really-refresh while gathering evidence, which cleared the flag the checker reads. Step 1 now says the read is read-only and names that command; nearby prose tightened so the section stays byte-identical in size (no pin or ledger move).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(qa-callers): admit ship Step 9's review-plan helper and place its Step 11 voices (late-input 40664336141, plan-checks 40707142223)
Gate edit: the caller interface admits the gstack-review-plan forms Step 9 names at the exact installed path; the ship prompt says the plan's adversarial-native and outside-voice lines are Step 11's, outside the Steps 8-9 excerpt. Free replays of both 40707142223 captures and the real plan for all four ship cases.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(browse): real-Chromium cookie-auth positive and early-return rejection cases use the product default timeout
Gate edit approved by GStack Minder. The shared 400 ms came from
|
||
|
Garry Tanandcapy-ai[bot]
|
29f8ca053e |
v1.91.301.0 fix(flaky): four paid rule cases stop failing correct runs (2026-10-28 pass) (#3547)
* fix(flaky): repair four paid rule fixtures and detectors from the 2026-10-28 pass (GSTA-139 S2)
- plan-design-with-ui-scope: the focus detector accepts the all-7 offer in the
rated title line; issue-numbered options never count as Step 0D (gate edit).
- plan-review-report: the fixture state uses codex_reviews disabled so the
default-on outside voice no longer spends the 20-turn budget (gate edit).
- shared-libs-review-path-eligibility: an errored multi-command Bash read counts
when its output holds the exact evidence source (gate edit).
- office-hours-brain-writeback: the fake gbrain accepts the page on stdin, the
SAVE_RESULTS template form.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(changelog): note the 2026-10-28 S2 flaky repairs under Unreleased
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(evals): re-pin two detector-inventory line ranges moved by the S2 repairs
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes (Git Bash path for the preflight probe; empty-source control)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(fixtures): register the two S2 replay fixtures as free fixtures
The remote pregate at
|
||
|
Garry Tanandcapy-ai[bot]
|
766093df3e |
v1.91.300.0 test(flaky): 2026-10-28 free Linux timing pass: ubicloud fake ssh, coordinator clone, qa-fix-loop late clock (GSTA-139 S4) (#3543)
* test(flaky): ubicloud fake ssh dispatches on the remote command, not on a '-O' in the checkout name (GSTA-139) The fake ssh's *-O* arm, meant for 'ssh -O exit' (whose last argument is the host, so it never matched), caught any remote command whose path held '-O': dest work/ubi-run-O????? whenever mkdtemp's first random character was O. Sync then failed with exit 2 (tar child 141) or every phase exited 0, in about 1.3 s, before UBI_RUN_TIMEOUT could fire: Free Tests 40534568946 (:417, 2) and 40638411165 (:454, 0). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(flaky): the coordinator clone reads the fixture origin through git, not by copying its objects directory (GSTA-139) Every push into the fixture origin leaves a detached 'git maintenance run --auto' there (local transport drops the shard's GIT_CONFIG_COUNT backstop), which creates and deletes objects/maintenance.lock after the push returns. A local clone copies origin.git/objects entry by entry, so an entry appearing or vanishing mid-copy fails it; --no-local never lists that directory. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(flaky): qa-fix-loop late-timeout freezes its clock through setup and registers the outer budget (GSTA-139) The #3413 qa-only template: the late scenario's real setup ran inside its 1000 ms mocked work budget and a 1160 ms native deadline, so under load the attempt never started (0/10 under 24 busy loops, attempts length 0). The clock now stands still from the body's start until the capture begins, the capture gets exactly 1000 ms, and the native deadline is the registered 6080 ms outer budget. Gate edit: captureBudgetMs is asserted equal to 1000. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(flaky): keep run ids out of the coordinator-clone regression comment (GSTA-139) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (qa-fix-loop slow-setup keeps the setup-subtraction check the late clock freeze dropped) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: GSTA-139 S4 CHANGELOG entry and the local-push maintenance gap in TESTING_INTERNALS 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]
|
4c745eec10 |
v1.91.299.0 fix(owner-brief): Captain brief resolves rec like gstack-gate render when a gate carries decisions (#3546) (#3549)
* fix(owner-brief): the Captain brief resolves rec through parseReply, so carried decisions match gstack-gate render (#3546) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(owner-brief): the Captain brief keeps answers already recorded at this gate, as answer --reply rec does Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(owner-brief): the do-it line says every choice when rec keeps earlier answers 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]
|
415e343b52 |
v1.91.298.0 chore: remove Dia from gstack (cookie source and qualification harness) (#3551)
* chore: remove Dia from gstack (cookie source and qualification harness) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: pin the removed Dia harness so pregate selects a lane for its deleted scripts Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: CHANGELOG names every doc the Dia removal touched 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]
|
fb30ed1047 |
v1.91.297.0 fix(browse): read Windows process start times in-process so the terminal agent boots without PowerShell (GSTA-139 flaky pass) (#3545)
* fix(browse): read Windows process start times in-process; drop PowerShell from two flaky test paths (GSTA-139 S5)
The terminal agent's identity probe launched powershell.exe Get-CimInstance
with a 2 s timeout on every boot (twice when started standalone). On loaded
Windows runners a launch takes ~0.94 s at p50 and up to 10.8 s, so the agent
missed the watchdog test's 5 s window and a stalled launch returned an empty
identity. Under Bun the start time now comes from GetProcessTimes in the
same /Date(ms)/ form PowerShell's CreationDate serialises to, so records,
the Node daemon (which keeps the PowerShell reader) and earlier releases
agree. The kill-time command-line check still uses PowerShell.
path-security-realpath builds its 8.3 alias with GetShortPathNameW instead
of a PowerShell launch that stalled for 30 s and was reported as '8.3
disabled'. cookie-import-native-job prints the Restart Manager receipt when
its owner assertion fails.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(browse): scope test 5's PowerShell assertion to the owner; identify a win32 agent by generation when readers disagree
Review of
|
||
|
Garry Tanandcapy-ai[bot]
|
98dd72ffc3 |
v1.91.296.0 fix(flaky): ship-docsync gates accept the docs helper's --help and git tag listings in a line of reads (GSTA-139 S1) (#3542)
* fix(flaky): docsync detectors admit the candidate's --help and git tag listings in a line of reads (GSTA-139 S1) Gate edit. Five red ship-docsync-current/store parents (screen 40558235014, gates 40600731931 and 40643690306, screen 40627127462 and its rerun) each had exactly one refused Bash line: four joined gstack-docs-candidate --help onto a line of reads, one put git tag in one. v1.91.185.0 tried prompt clarity for the --help join and the slip recurred four times. The --help path prints usage and returns before touching Git or a file, so it now stands in a line of reads like a Git read (never pipe-fed, never after cd); operand-free git tag listings join the branch listings #3516 admitted. The fixture interface states both. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(changelog): docsync gate accepts the candidate's --help and git tag listings in a line of reads 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]
|
61e201ec08 |
v1.91.295.0 fix(pregate): deleting or renaming a test no longer fails lanes (#3534)
* fix(pregate): removed paths owe no lane instead of failing PREGATE_NO_LANE A deleted file or a rename's old name that no remaining test selects now prints 'removed (no lane owed): <path> — <why>' in lanes: a deleted test runs its owning suite or names the files that lost their last test; a modified file whose only test was deleted still fails, and an unreadable deleted test fails closed. Fixes: #3529 Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(pregate): pre-landing review fixes for removed paths A removal owes what an edit owes: manifests, lockfiles, config, fixtures, goldens, workflows and files a config still names keep PREGATE_NO_LANE. A test reading a fully deleted directory is selected again, a deleted Rust module selects its crate's tests, a test renamed to a non-test path is accounted as deleted, and the owning suite is the tests that directly exercise the same files. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(pregate): a removed file remaining code still imports fails closed Pass-2 red-team: namedBy matched only full repo paths, so a deleted module imported by a relative, extensionless or dotted specifier from untested code was waived. removedPath now refuses when the import graph shows a remaining dependent. Stale headers updated to say other removals owe what an edit owes. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(pregate): removals the graph cannot see stay fail-closed Step 11 adversarial and outside-voice findings: the waiver trusted SOURCE_EXT, so Go, Ruby, shell, Rust and bin removals, files loaded by name and files a nested config names relative to itself passed with no test; a rename's old name skipped every check. Now every removed path is refused while a remaining file imports it (directory references included); only JS, TS, Python and Dart code is waived, never a file loaded by name; namedBy also matches paths relative to each ancestor directory; Go and Ruby tests are refused; a rename's old name goes through the same checks unless it is a test renamed to a test. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(pregate): basename mentions and Go/Ruby test renames fail closed Fix-check 2 (cycle 4, rule 23 grant from GStack Minder): a deleted file a tested loader reached by path.join(__dirname, 'lib', 'value.js') was waived, and a Go helper test renamed into another directory got the test-rename exemption. namedBy now greps the basename repo-wide (non-Markdown); the Go and Ruby test refusal runs before the rename exemption. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(pregate): align removed-path prose with the waiver rules Ship docs audit (gsta137-docs-1): name the snapshot, baseline and .gstack/ trees the waiver excludes, add usercustomize.py to the loaded-by-name list, and give the unreadable-deleted-test explain line. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: bump version and changelog (v1.91.292.0) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: a removed test runs the tests of files that still name it (pregate lanes) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pregate waives only removed tests; other removals owe what an edit owes (D3 narrowed by the controller) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: a removed test is named by any whole-word mention of its name without the extension (pregate lanes) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: a removed test is named by any mention of its name without the extension (pregate lanes) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: unstamp (VERSION back to 1.91.291.0, CHANGELOG entry under [Unreleased]); the slot call stamps Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: CHANGELOG [Unreleased] entry passes the prose-lint gate Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * v1.91.295.0 fix(pregate): deleting or renaming a test no longer fails lanes 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]
|
4b8c03bea9 |
v1.91.294.0 fix(doctor): cut Git Bash process starts so the doctor tests fit Windows CI (GSTA-138) (#3540)
* perf(doctor): cut Git Bash process starts in doctor, hook-check and launch probe (GSTA-138) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes The doctor's in-process config read reselected the state root after the doctor set GSTACK_STATE_ROOT, so --check and --json printed 'selected by GSTACK_STATE_ROOT' whatever selected the root. cfg now keeps _gstack_sr_var. Adds the regression test, a CRLF/blank/200-byte launch-probe detail test, and corrects the clamp comment. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: check the doctor cores row's test_backend by behavior, not the reader's spelling test/owner-brief-contributor-banned.test.ts pinned the literal 'gstack-config" get test_backend' in bin/gstack-doctor-check.sh, which the in-process cfg read removed (CI: quick-bun-default, free-suite 14). It now runs gstack-doctor --check --require cores against a state root holding test_backend: ubicloud and expects test_backend=ubicloud, with an empty state root as the negative control (test_backend=local). The under-8-cores wording pin stays. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: CHANGELOG [Unreleased] entry for the doctor's Windows process cuts Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: stamp v1.91.294.0 for #3540 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]
|
9e3308f65a |
v1.91.293.0 fix(harness): error lines print again; register qm stops at QM's pack cap instead of claiming QM works (GSTA-135) (#3532)
* fix(harness): print error lines again; register qm stops before QM's pack cap instead of claiming QM works Bun gives every thrown Error an own numeric 'line' property, which shadowed HarnessError.prototype.line(), so every refused gstack-harness command crashed with 'e.line is not a function'. The printer is now report(). QM imports a skill pack by cloning the whole repository and refuses past 32 MiB / 5,000 files (Harness Evals preflight, HARN-5); gstack's repository is 73 MiB in 4,280 files. register qm now measures first and stops with HARNESS_QM_PACK_TOO_LARGE before any request; QM's own cap refusal maps to the same code. docs/hosts.md lists QM as not available yet. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * s Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(harness): read QM's recorded import error for the cap; refuse to size a non-git checkout; skip symlinks like QM Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: drop a stray a/SKILL.md committed by a scratch experiment Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: no doc implies QM registration works (document-release audit) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(install): stable's 72-hour rule also excepts a regression fix (#3533) 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]
|
219f7488bb |
v1.91.292.0 Stable channel: a regression exception beside the security one, and the stale weekly wording (#3533)
* feat(release): regression cuts pass the 72-hour floor like security cuts; weekly wording follows the twice-weekly cadence Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: a regression anchor needs a published release; an unmoved exception tag reruns only with its recorded reason; a version may end the sentence Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * RESTAMP: 1.91.291.0 -> 1.91.292.0 (stamped; queue_mode=stamp-at-merge base=origin/main@6f27f0c269cb policy=base origin/main@6f27f0c269cb:.gstack/ship-policy.json) STAMP_VERSION: 1.91.292.0 stage version: done (wrote 1.91.292.0) stage release_tool: done (bun scripts/gen-agents-digest.ts) stage changelog: done (Unreleased -> 1.91.292.0) stage stamp_paths: skipped (no tentative mention newer than the fork version 1.91.291.0 and none of base 1.91.291.0 on a line this branch added) stage mirror: skipped (no mirror in policy) stage apply: done (4 file(s)) FILES: CHANGELOG.md VERSION agents-digest/gstack-AGENTS.md package.json MERGE_CONDITION: sha=40a8df86de0bda12cedea7dbdc744b90f4b1d5eb GSTACK_RESULT: skill=restamp status=complete run=/workspace/gstack/.gstack/tmp/restamp-journal.json 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]
|
6f27f0c269 |
v1.91.291.0 release: stamp #3527 (/ship and /autoplan size their review to the diff) (#3530)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> |
||
|
Garry Tanandcapy-ai[bot]
|
148d28ea81 |
feat(ship): /ship and /autoplan size their review to the diff (GSTA-131) (#3527)
* wip(GSTA-131): review depth, fix-check transitions, dispatch counters, carry pregate, autoplan round policy Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * wip(GSTA-131): reviewers stay at full effort; audits light Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(ship): Step 9 dispatches what gstack-review-plan plans; fix-check after below-floor fixes; cap two full passes plus one fix-check Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: review-dispatch-compare has a free lane; review-depth fixtures registered free; resumed max_rounds case off the old default Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(GSTA-131): ship review pass-1 repairs: fix-check binds under its own skill, Step 11.5 accepts a fix-check or a planned adversarial skip, delta carry with a pregate, carry --pregate pinned to the checkout, quiet-after-cap revise regates, skill-dir markdown and rule docs classed code, gate signals from tests class up, plan fails closed on git errors, per-class compare ratios Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(GSTA-131): ship review pass-2 repairs: Step 11 follows the last full-pass plan, Important Rules restored, ship goldens regenerated, true per-class medians, review-policy transitions and once-per-invocation voices, docs/** assets stay docs-class, CLI and fix-check binding tests Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(changelog): GSTA-131 review depth, fix-check, delta /ship and autoplan rounds Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: ship-policy cap and counters, review-policy /review cycle cap, unattended passes (docs audit) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(review): 400-word findings cap fits the /review size pins (five host pins lowered by 2); CHANGELOG max_rounds wording Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(changelog): gate integrity names the size-ledger entry and the lowered /review pins Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: the round-budget case asserts the default through ROUNDS output only (pregate literals heuristic) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: curate ship-receipt-carry-pregate out of the Windows lane like its --pregate siblings Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(changelog): end the Windows curation sentence instead of a mid-sentence colon Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(ship): one decision each for the review-loop exits, the planned adversarial skip and Step 16's TODOS rerun (screen judge repair) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(ship): fix-check repairs: pin the renamed Step 11 heading, keep the below-floor exit at the cap, name the plan run a repeat reuses, print the native skip on outside-only plans 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]
|
44f19d0106 |
v1.91.290.0 feat(harness): gstack registers its skills in whatever agent harness it is installed into (GSTA-135) (#3526)
* wip: gstack-harness registrar (GSTA-135) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * wip: harness registration in setup, uninstall, tests Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * wip: harness hosts experimental, troubleshooting codes, kit Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: agent harness registration (GSTA-135) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: harness hosts run in place from the checkout in --status Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: bun-free ledger reader Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: CHANGELOG for harness registration (Unreleased) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(harness): keep edits beside themselves, never follow symlinks, cut only gstack's own context block Review blockers on #3526: uninstall deleted the edit backups under the state root; unregister followed a symlinked folder below the destination; a lone or edited context marker made the cut eat user lines; a re-register adding --context left an unrecorded block. Also: ledger written before the files, --refresh-registered no longer re-runs harness hosts through setup (gstack-harness refresh keeps their mode), bash goes through runBashSync, and setup tests follow openclaw/hermes becoming installs. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(harness): a ledger with no destination row touches nothing (no hang) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: harness registration in README, install and hosts (document-release 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> |
||
|
Garry Tanandcapy-ai[bot]
|
a14c28aca7 |
v1.91.289.0 feat: skill diet pilots for plan-design-review, office-hours and design-review (GSTA-134) (#3525)
* feat(plan-design-review): skill diet (GSTA-134 pilot 1) SKILL.md 66,063 -> 56,209 B (claude host); review-sections.md 52,243 -> 50,183 B. Cut model-known prose (cognitive patterns, verbose designer prose, duplicated formatting rules); UX principles kept as a five-line Krug summary after the blind judge showed wayfinding loss without it. Section layout unchanged: autoplan's methodology snapshot requires review-sections.md as the only indexed section. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(office-hours): skill diet (GSTA-134 pilot 2) Moves the Phase 3.5 Codex second opinion and the Phase 4.25 visual design (designer mockups / HTML sketch) out of the eager SKILL.md into on-demand sections behind STOP pointers; the CODEX_SECOND_OPINION, DESIGN_MOCKUP and DESIGN_SKETCH resolvers are untouched. Claude-host SKILL.md 73,248 -> 43,885 bytes. skill-diet before/after (Opus, 9 tasks x 3): success 26/27 -> 27/27, median tokens per successful run 170,197 -> 124,941; blind judge after 10, before 5 of 15. YC pitch, flattery and promo text unchanged (sections byte-identical to main). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(design-review): skill diet (GSTA-134 pilot 3) Moves the outside voices and the test-framework bootstrap into on-demand sections (the bootstrap now loads at Phase 8e.5, its only consumer: a JS-behavior fix that needs a regression test with no known test command), replaces the UX principles block with a Krug summary, and tightens the DESIGN_METHODOLOGY prose (design-review is its only consumer). Shared resolvers TEST_BOOTSTRAP and DESIGN_OUTSIDE_VOICES are untouched. Claude-host SKILL.md 115,947 -> 84,869 bytes. skill-diet before/after (Opus, 12 tasks x 3): success 32/36 -> 34/36, median tokens per successful run 326,662 -> 257,819; blind judge after 9, before 5, tie 1. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: re-pin size, context and carve guards for the GSTA-134 skill diets Every pin moves down except office-hours' parity maxSizeRatio (1.1796 -> 1.1921, GStack Minder's call as merge-queue owner): its union grew 1,662 B because the second-opinion question now sits in the skeleton while the untouched CODEX_SECOND_OPINION resolver keeps its own copy. design-review leaves the size allowlist on every host. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: drop the stale <affected-url> placeholder after the design-review Phase 8d diet Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: design-review checklist headers count the items they list after the diet Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: design-review report path and UX_PRINCIPLES consumers after the skill diets Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: CHANGELOG [Unreleased] for the GSTA-134 skill diets 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]
|
cd4fc4be73 |
v1.91.288.0 feat(release): stable moves at most every 72 hours, with a verified security exception and Monday/Thursday cuts (#3523)
* wip: stable 72-hour floor, security exception, twice-weekly cadence Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * wip: changelog, coverage cases for tag-before-stable and multi-tag Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: floor fails closed on undatable moves, recorded security evidence on finish, npm-only advisory match Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: prose fixes for the floor and security sections Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: FLOOR_UNKNOWN wording names the security exception; sanitizer and outcome rows match the code Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: the floor dates stable from its v<VERSION> tag, so a stray extra tag cannot stall cuts silently 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]
|
7204a39a27 |
v1.91.287.0 feat(write-skill): write, change and diet skills; /learn at half its template size (#3524)
* test(skill-evals): /learn before/after tasks, written before any cut (GSTA-133) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(learnings): --help, unknown-flag errors and --stats on the learnings bins; cross-project search no longer drops every project when the state root path contains the slug Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * refactor(learn): diet /learn onto the levels: tool flags replace the inline stats program, one mode table, prune rules kept Skill-Diet: learn Skill-Size: 5797→2586 bytes (SKILL.md.tmpl) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(write-skill): /write-skill skill, gstack-skill-bill, static skill-to-bin drift ratchet, shared skill eval contract Skill-Size: 0→3245 bytes (write-skill/SKILL.md.tmpl) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(learn): guard the state-root lookup in Prune; re-measure the learn ceiling Skill-Size: 2586→2707 bytes (learn/SKILL.md.tmpl) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (drift scanner, learnings flags, skill-bill baselines, eval fixtures) - skill-bin-drift: a redirect no longer ends a command, so `bin/x 2>/dev/null --bogus` is checked - gstack-learnings-search: a missing value or a non-positive --limit exits 2 like an unknown flag - gstack-skill-bill: the gstack root skill is a checkout skill; Skill-Diet trailers match the exact name; the baseline counts the committed bytes untrimmed - skill-evals task files get a free contract test and are registered in FREE_FIXTURES, with the drift allowlist - learn eval: the no-code-change safety task no longer asks the model to fix code (its check penalised obeying the user) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(learn,write-skill): full bin paths in the mode table; prune asks per entry unless the request names the action Skill-Diet: learn Skill-Size: 2707→2955 bytes (learn/SKILL.md.tmpl) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(changelog): /write-skill, gstack-skill-bill, drift ratchet, eval contract, /learn diet Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: drift ratchet in CONTRIBUTING's static tests; /learn prune example asks per entry Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(skill-bill): report a checkout skill's eval task file and check it against the contract The skill-evals task-file test now exercises lib/skill-bill.ts's checkEvalTasks, with a negative control, instead of a test-only validator (test-of-test ratchet). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(skill-bill): EVAL TASKS path uses forward slashes on every platform; a non-object task entry is a problem, not a crash Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(learn): BASH_COMPAT guard on in-window heredocs; count skill-e2e-write-skill in the paid census 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]
|
398618259d |
v1.91.286.0 feat(ship-queue): the ship size cap composes across a merge train; verify refuses a stale all-merged train (#3519) (#3522)
* feat(ship-queue): the ship size cap composes across a merge train; verify refuses a stale all-merged train (#3519 b, c) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (runnable clear-time NEXT, stale exit only on a fetched main, open-slot freeze control, LF size-ledger fixture) - verify's clear-time NEXT names gh pr view <n> --json state,headRefOid per unreadable slot instead of a pasteable #n@sha that views the current branch's PR - QUEUE_TRAIN_STALE needs a fetched main (never under --no-fetch) and reports a freeze restored from the notes ref instead of saying the queue is not frozen - freezeQueue docstring matches the unreadable field - new test: a train with a slot still OPEN freezes even when another train verified main's sha - test/size-ledger.test.ts fixture repo sets core.autocrlf false (Windows Free Tests shard 4 counted CRLF bytes) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: CHANGELOG [Unreleased] entry for the ship size ledger and QUEUE_TRAIN_STALE Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: run scripts/size-ledger.ts (check on this tree, refusals write nothing) The remote pregate refused |
||
|
Garry Tanandcapy-ai[bot]
|
737e5a239e |
v1.91.285.0 docs(captain): plan before build — a sized /autoplan is a building lane's first act, the owner's word gates the build (#3521)
* docs(captain): plan before build — a sized /autoplan is a building lane's first act, the owner's word gates the build (GSTA-130) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(capy skill): Plan, approve, ship — the Capy-wide short form (autoplan sized to the work, ELI5 with rec and do it, APPROVED before the build, /ship at the final head, no merge without the owner's word) (GSTA-130) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(changelog): restore the full history; the Unreleased block had been written over a truncated read (GSTA-130) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(capy skill): tighten Plan, approve, ship to one-line bullets so the Capy skill stays under its 4120-token eager ceiling (GSTA-130) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes — import --by takes the owner alone, the controller checks the row against its relay, brief.md spells the full answer command and carries the run dir, first act after the install check (GSTA-130) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(captain): name the lane brief in the template lists; fix two template command lines docs/skills.md and docs/PROJECT_STRUCTURE.md enumerate captain/templates/ and omitted brief.md (document-release audit gsta130-docs-1). brief.md's restore line now names the checkpoint dir that resume --from takes, and plan-ask.md's answer line carries --rec-hash like brief.md (ship review pass 2). 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]
|
10b77de4f2 |
v1.91.284.0 feat(absorb-tstack): /modernize skill, per-skill Codex default prompts, gstack-post --attribute, the unattended grant and a CONTRIBUTING porting section (#3497)
* feat(absorb-tstack): /modernize skill, per-skill Codex default prompts, gstack-post --attribute, the unattended grant and a CONTRIBUTING porting section Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(modernize): read the PR text through gstack-issue-guard; re-measure the context ceiling Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes - gstack-post: with --attribute, report scan findings at the body file's own line numbers and a finding inside the callout as PART: attribute (the coordinates were shifted by the three callout lines) - /modernize: route commit messages through gstack-issue-guard with the rest of the PR text, read isCrossRepository and maintainerCanModify, fetch a fork head from pull/N/head, refuse a PR whose head is the base branch, and list moved files NUL-safely - docs/unattended.md: say that /ship never rebases or force-pushes and an unattended /modernize stops at its verdict - CHANGELOG: seven skills carry a codex_default_prompt, not six Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: /modernize fetches a fork head with a forced refspec and stops when the PR moved A rerun after the author force-pushed left refs/modernize/pr-N stale (the non-forced refspec is rejected with exit 0 through the pipe), and the lease pinned to the current remote head would then have let the rebased stale head overwrite the author's newer commits. The fetch is forced, Steps 2 and 4 stop when the head is not the one observed in Step 1, and the head-is-base guard applies only to same-repository PRs (a fork's main into main is a valid head). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: /modernize stops on merge commits in the PR range and pushes a fork head to the fork A plain git rebase drops merge commits and git range-diff compares only the non-merge patches, so a change authored in a PR's merge commit disappeared while the proof printed = for every patch and Step 5 force-pushed the loss. Step 4 now counts merges in $MERGE_BASE..$OLD_HEAD and stops when there are any, switches with -C so a rerun after a refused lease does not fail on the existing branch, and asks for a cross-repository diff to be read as untrusted input before the repository's test command runs it. Step 5 pushes a fork head to the fork's URL with the same pinned lease instead of to origin, where the lease could never match. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: cover the Codex default-prompt render, the openai.yaml ownership proof and the unattended grant Adds the /ship coverage audit's tests: test/host-renders-openai-yaml-proof.test.ts drives bin/gstack-host-renders.sh's weakened proof against a rendered yaml, a hand-written one and a generic-prompt one; test/unattended-grant.test.ts pins the docs/unattended.md grant section and the handoff pointer; test/gen-skill-docs.test.ts adds modernize to the skills whose codex_default_prompt must reach openai.yaml. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: name the static lists a new skill still needs and the Codex metadata file From the ship documentation audit: CONTRIBUTING's new-skill checklist said no static list needs a row, which this PR disproved (lib/doctor-components.ts SKILL_REQUIREMENTS and the catalog rows); the host comparison table and docs/ADDING_A_HOST.md gain the agents/openai.yaml default_prompt source; a blank line before the new docs/unattended.md grant heading. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes CHANGELOG [Unreleased] gate-integrity record: the catalog and context-budget figures re-measured on top of main (1,314 -> 1,359; modernize 9466; alwaysOnTotal 7458 -> 7880), as the merge commit's ratchets state. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: name the optional codex_default_prompt key in the new-skill checklist Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(parity): re-pin the ship union cap at 1.7405 after the main merge GSTA-36 grant 2026-10-27. On the tree merged with |
||
|
Garry Tanandcapy-ai[bot]
|
215c76e334 |
v1.91.283.0 fix(benchmark): reconcile the collection, comparison, budget and trend phases with the vet-the-number section (GSTA-128) (#3520)
* fix(benchmark): reconcile the collection, comparison, budget and trend phases with the vet-the-number section
The perf-collection judge (run 40558235014, both attempts, six samples) named
the same contradictions: Phase 3 offered an optional 3-run median while the
mandatory vet section demands 5 alternating runs per side and a stored
baseline cannot be interleaved; the budget example read '4/6 passing' against
a rule that counts WARNING as below budget; the trend table showed Grade and
Bundle columns no stored file defined; Phase 9 named two files with no
contents. Phase 3 now runs 5 per page with median and range and names
--quick as the one-run ballpark; the baseline schema carries runs and
range_ms; Phase 5 says how the seven questions apply against a stored
baseline (compare the delta with both spreads, name the limiter from Phase 6,
inconclusive when either side is one run); the grade example counts 3 PASS,
1 WARNING, 2 FAIL; Phase 8 reads the benchmark and baseline JSON files by
timestamp; Phase 9 defines the JSON as the Phase 4 object plus grade, verdict
and per-metric status. Nearby prose tightened so the skeleton stays under its
31,300-byte cap (31,290). Judge after the repair: clarity, completeness and
actionability 4/4/4 on all three samples, twice.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* changelog: /benchmark phases reconciled with the vet-the-number section (GSTA-128)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: /benchmark runs five times per page in docs/skills.md
Step 14.5 of /ship on #3520: the /benchmark section said 'Multiple runs averaged' and
'3 runs each'; it now matches Phase 3 (five runs per page, median with range, --quick a
single-run ballpark). GSTA-128.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* RESTAMP: 1.91.282.0 -> 1.91.283.0 (stamped; queue_mode=stamp-at-merge base=origin/main@9ccb5233f309 policy=base origin/main@9ccb5233f309:.gstack/ship-policy.json)
ship, next in queue at 1.91.283.0
STAMP_VERSION: 1.91.283.0
claims: ignored (stamp-at-merge)
stage version: done (wrote 1.91.283.0)
stage release_tool: done (bun scripts/gen-agents-digest.ts)
stage changelog: done (Unreleased -> 1.91.283.0)
stage stamp_paths: skipped (no tentative mention newer than the fork version 1.91.281.0 and none of base 1.91.282.0 on a line this branch added)
stage mirror: skipped (no mirror in policy)
stage apply: done (4 file(s))
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 695e20bd5..15162a5d0 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,6 +1,6 @@
# Changelog
-## [Unreleased]
+## [1.91.283.0] - 2026-10-27
**/benchmark's collection, comparison, budget and trend phases now agree with its vet-the-number section.** The 2026-10-27 flaky pass (GSTA-128) read the `benchmark/SKILL.md perf collection` judge's six samples from run 40558235014: every sample named the same contradictions, so the prose was repaired and no threshold moved.
diff --git a/VERSION b/VERSION
index 269b6e89c..0b68a0506 100644
--- a/VERSION
+++ b/VERSION
@@ -1 +1 @@
-1.91.282.0
+1.91.283.0
diff --git a/agents-digest/gstack-AGENTS.md b/agents-digest/gstack-AGENTS.md
index 583844b7e..894898db8 100644
--- a/agents-digest/gstack-AGENTS.md
+++ b/agents-digest/gstack-AGENTS.md
@@ -1,4 +1,4 @@
-# gstack digest v1.91.282.0 — regenerate/re-copy after upgrading gstack
+# gstack digest v1.91.283.0 — regenerate/re-copy after upgrading gstack
Behavioral rules from gstack (https://github.com/garrytan/gstack), compressed
for agent hosts without a full skill install. The full skills add workflows,
diff --git a/node_modules b/node_modules
new file mode 120000
index 000000000..858ae29ce
--- /dev/null
+++ b/node_modules
@@ -0,0 +1 @@
+/workspace/gstack/node_modules
\ No newline at end of file
diff --git a/package.json b/package.json
index 66ec462ee..da0b87294 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
{
"name": "gstack",
- "version": "1.91.282",
+ "version": "1.91.283",
"description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.",
"license": "MIT",
"type": "module",
FILES: CHANGELOG.md VERSION agents-digest/gstack-AGENTS.md package.json
MERGE_CONDITION: sha=aa8c07b76935d91ec548fb5a32fd429392f88460
next: NEW_VERSION=1.91.283.0; commit and push only the stamp diff above (FILES), with no edit of your own: the train's verify accepts the CHANGELOG only as the base's plus this PR's entry re-headed; merge with the expected head
|
||
|
Garry Tanandcapy-ai[bot]
|
9ccb5233f3 |
v1.91.282.0 fix(ship-queue): one CHANGELOG rule before and after the merge, base keys stay in slot stamps, a stacked child carries past its released parent (#3518)
* Ship-queue train tooling: one CHANGELOG rule, base keys stay, stacked-child carry (GSTA-129) Four train-24 (GSTA-96) defects in one change. verify --train applies the same CHANGELOG rule before and after the merge: main's CHANGELOG plus the PR's own lines (its authored diff plus what mergeChangelogs writes for it). A head the pre-merge verify accepted no longer freezes the queue after its squash merge, and a freeze record lists a slot GitHub reports MERGED as merged. restamp's stamp_paths stage leaves a *_KEY_VERSION line the base introduced after the fork point alone, base merge committed or staged, and says so. mergeChangelogs with a base carries a stacked child's edits to its released parent entry as "Correction to the <version> entry below" bullets under the child's own Gate integrity section instead of returning null; the slot one-liner prints each carried correction. #3453's two 1.91.276.0 corrections are restored that way here. The digest-freshness defect is already closed by #3451 (regeneratedAtBase); docs/ship-policy.md now says how an unstamped generator change ships. Docs: ship-policy § Run a merge train, captain.md § Merge trains and the slot-call template carry the stamp-files and stacked-child rules. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Review fixes: carried union from slot 2, GitHub-merged slot-1 freeze, no-own-entry refusal, fail-closed base diff (GSTA-129) Pre-landing review pass 1 (six specialists and the Red Team, all INFORMATIONAL): - mergeStep unions the carried child from slot 2 on, so a stacked child behind another slot never repeats its released parent's text under a second [Unreleased] (Red Team, lib/ship-queue-train.ts). - stopped() freezes the queue when any slot is MERGED on GitHub, so a slot-1 squash that fails the post-merge check no longer answers "nothing merged" (Red Team, lib/ship-queue-train-verify.ts). - ownEntryAboveMain refuses a CHANGELOG equal to main's: no entry of the PR's own (state-machines, lib/changelog-check.ts). - branchAddedLines refuses when the base diff cannot run instead of reading it as "nothing added" (Red Team, lib/restamp.ts). - slot-call.md and docs/captain.md name the stamp files as the ones the slot call names, STAMP_FILES plus a *_KEY_VERSION file the PR introduced, matching docs/ship-policy.md (maintainability). Also: the coverage tests Step 7 added (post-merge parent check, carry shapes), and two dependency-map rows (test/helpers/free-fixtures-data.ts for the merge-train-3453 fixtures, scripts/test-pr-profile.ts for captain/templates/**) so the paid-gate selector and the FREE_FIXTURES inventory accept the new files. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Review pass 2: an unreadable GitHub state at a failed slot refuses, never "nothing merged" (GSTA-129) stopped() read prState's 'unreadable' as "not merged": with nothing in t.merged, a slot-1 squash already on main while gh pr view failed answered "nothing of the train merged, so the queue is not frozen". It now refuses with QUEUE_PROOF_MISSING ("whether #<n> merged on GitHub could not be read, so whether the queue must freeze is unknown") and asks for the verify to be rerun; no freeze, no backstop. Raised independently by five pass-2 reviewers. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Docs audit: troubleshooting codes and ship-policy sections match the shipped train rules (GSTA-129) The /document-release audit (edit mode) corrected two docs the PR had not reached: docs/troubleshooting.md's QUEUE_TRAIN_TREE_MISMATCH, QUEUE_PROOF_MISSING, QUEUE_TRAIN_FROZEN and POLICY_SOURCE_UNAVAILABLE entries, and docs/ship-policy.md's train build conflict rule (the carried stacked child is the exception), the verify freeze paragraph (slot-1 GitHub-MERGED freeze, unreadable-state refusal) and the restamp stamp_paths stage (base-added lines stay; an unrunnable base diff refuses). Five mid-sentence colons in the PR's own paragraphs are rewritten for the prose lint, and the CHANGELOG Docs bullet names docs/troubleshooting.md. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * HARNESS_VERSION: scripts/test-pr-profile.ts row recorded non-behavioral at version 6 (GSTA-129) The remote free tier's only red was the HARNESS_VERSION guard: scripts/test-pr-profile.ts is a pinned shared-harness file and gained the captain/templates/** FREE_ONLY_PR_FILES row. Recorded with bump-harness-version.ts --non-behavioral: no paid case reads the crew templates, so no selection, input or verdict changes and no pass-rate series resets. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: type the saved fixture PR row for the test-code ratchet (GSTA-129) CI's typecheck:test ratchet refused one new TS2698 (spread of a loosely typed fixture row) in the slot-1 freeze test; the row is read as any, as the neighbouring state writes already do. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ship-queue verify: build the freeze record from the one GitHub read that decided to freeze freezeQueue took a second prState read per unverified slot and filed anything but an exact MERGED under unmerged, so a slot that read MERGED at stopped() and was unreadable a moment later was recorded as unmerged (the record half of train 24's #3453 misfile). stopped() now reads each unverified slot once and passes those states in; a MERGED slot stays merged, and a slot unreadable beside a merged one is kept out of unmerged and named in the reason. The fixture's gh shim gains a per-PR vanish count so a test can change GitHub's answer between two reads. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ship-queue verify: say what happens to a slot unreadable beside a merged one The freeze reason, docs and CHANGELOG said the slot was kept out of unmerged 'until read', but nothing reads it again: the NEXT after the repair is built from unmerged alone. Say so (the operator seats it in a train by hand once gh answers) and pin the record shape with a test. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * v1.91.282.0 stamp 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]
|
392f50d47b |
v1.91.281.0 fix(flaky): repair four paid gate detectors, the design-floor focus picker and the judged review/plan-review prose (GSTA-128) (#3516)
* fix(flaky): repair the five paid gate detectors and the judged review/plan-review prose (GSTA-128)
Daily flaky pass over the 2026-10-27 Open ledger entries, paid cases first.
- ship-docsync-store (40458489644, 40477638211): docsync-observer admitted only
`git branch --show-current`; both captured parents' fourth call was a read ending
in `git branch -a`. Operand-free branch listings are now part of the read grammar.
- ship-docsync-completion (40465691803): the parent ran two /document-release
dispatches and wrote the accepted second section into the report while the case
compared the first. The contract now follows the last foreground dispatch.
- ship-local-hook-preservation (40467320097): the red reply delegated the guard to
the repo owner ("have someone wire the guard in by hand"); toUser now reads a
determiner-led phrasal object and owner/maintainer/someone + themselves.
- plan-design-finding-floor (x2): the pending menu asked to cover all 7 dimensions
without the word "focus"; the picker now reads that question shape.
- Judge cases: plan-review headers no longer offer a "(or unverified)" branch the
four-mode preflight can never print; /review's Scope Check is emitted in Step 3
after the full diff read; the small-diff rule and the specialists record agree on
State Machines; Step 5.8.2 names which post-fix rerun rule governs. Nearby prose
tightened so review, ship and plan-eng-review stay at their parity caps; shrunk
size pins lowered per the guard's own instruction.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(plan-review): expect the renamed routing row ('Any other mode') in the Eng provider case
The GSTA-128 prose repair renamed the plan-review routing row from 'other preflight mode, including harness mismatch' to 'Any other mode (not_installed, under_current_harness)'; test/plan-review-cases.test.ts:657 still asserted the old text and failed quick-bun-default on #3516 (run 40524518937).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(eval-select): register the three new free fixtures in FREE_FIXTURES
eval: select reported docsync-branch-listing-public.json, docsync-two-attempts-public.json and design-floor-focus-cover-all.json as unknown dependencies (needs touchfile entry) and fell back to the full gate on that alone. Each is read only by a free test, so they belong in FREE_FIXTURES beside their siblings.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(review): pre-landing review fixes for the paid flaky-case repairs
Pass 1 of /ship's review loop on #3516 (core, four specialists, native and
outside adversarial, Red Team). Fixed in the diff:
- test/skill-e2e-ship-docsync.test.ts: the two-attempt retained-edit filter
dropped a path from changedPaths even when the accepted contract's
files_updated claimed it, so an honest re-audit that re-edits the same
document read as 'unreported edits'. acceptedChangedPaths() in
test/helpers/docsync-contract.ts keeps a retained path the accepted
contract claims; the free replay proves the old filter red on that shape.
- test/helpers/ship-hook-actor.ts: the owner+reflexive manual-integration arm
credited a denial ('so the owner does not have to do it themselves') or a
first-person claim. ownersOwnHand() requires a hook noun, rejects a
negation before the reflexive and a first-person subject; probes added.
- scripts/resolvers/plan-gates.ts + review/sections/manifest.json: the
no-plan path still said 'Emit Step 1.5's Scope Check once' and the STOP
trigger 'finishing Step 1.5's Scope Check', the circular prerequisite gate
40454750574 flagged, on the path most reviews take. Both now point at
Step 3 ('Step 3 emits the Scope Check once without plan fields';
'Before leaving Step 1.5').
- review/SKILL.md.tmpl: Step 3 item 5 emits the Scope Check on the first
pass only (a fix-range repeat pass reads a partial diff by construction);
two prose tightenings keep the review skeleton under its pins, which are
lowered by 3 on the eight pinned hosts.
- test/helpers/docsync-interface.ts: the declared branch-listing class now
enumerates the exact flag set DOCS_BRANCH_LIST_FLAGS accepts.
Coverage audit (Step 7) tests: plan-review and doc-review run headers admit
only the CODEX_MODE values their preflight prints
(test/outside-voice-preflight.test.ts); the final Scope Check is emitted
once in Step 3 and every owner names that point, no-plan path and STOP
trigger included (test/review-workflow-clarity.test.ts).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(ship-hook-actor): read the owner's denial in the owner's own clause
Review pass 2 on #3516 (State Machines, with the same site flagged by every
other reviewer): the pass-1 negation guard in ownersOwnHand() scanned the
whole sentence prefix before the reflexive, so an honest request after a
negated subordinate clause ("Since the installer did not run, the repo owner
needs to add the guard to the existing hooks themselves") was refused, a
recall regression against
|
||
|
Garry Tanandcapy-ai[bot]
|
703b0049eb |
v1.91.280.0 fix(flaky): ubi-runner quota wait counts down; pregate TERM teardown and design-lint linearity measure what they mean (GSTA-128) (#3517)
* fix(flaky): ubi-runner quota wait counts its budget down; pregate TERM teardown and design-lint linearity checks measure what they mean (GSTA-128) Daily flaky pass, free-tier timing entries from the 2026-10-27 ledger. - test/ubicloud-runner.test.ts quota case (Free Tests 40474956830, 40480063084, 40488875742): quota_preflight pinned a wall-clock deadline before its first usage call, so a slow fake-CLI spawn on a loaded runner shaved the printed budget to "waiting up to 2s more". The budget now counts seconds spent waiting for room; usage reads between sleeps no longer eat it. Loaded local loop: 8/12 and 6/12 green before, 12/12 after. - test/ubicloud-pregate-remote.test.ts TERM teardown (40487321907 shard 13): the stub's `>>` creates the .down file before echo writes the line, and the test polled the inode, then read "". Both teardown waits now wait for the written line. - test/design-lint-fifth-cycle.test.ts tracked-caps linearity (40494745147 shard 15): the 8000-label run was timed once by wall clock on a shared runner (515 ms against the 500 ms floor). It now measures the lint's own CPU time, fastest of three runs, against the same unchanged bound. - The hung-setup watchdog assertion now carries the runner's stderr, so its next red names the cause (one unexplained exit 2 in 46 local runs). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(ubi-runner): prove the quota wait countdown; CHANGELOG entry for the free-tier timing repairs (GSTA-128) The existing WAIT=3 quota case passes under both the old wall-clock deadline and the new countdown because its fake usage read is instant. The new case slows the usage read to 1.2 s and asserts the printed 2 s budget (origin/main prints 1 s), then stubs sleep for a 70 s wait to see the 30 s steps and the release when the peer VM disappears. /ship Step 13 adds the [Unreleased] CHANGELOG entry; the train re-heads it at the slot. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(ubi-runner): assert the quota wait budget on its log line, not on elapsed wall time (GSTA-128) 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]
|
b3e94a3f8d |
v1.91.279.0 eval:select exemptions and ETHOS.md registration (#3499), below-floor review rulings (#3504, #3485), Windows curation, GSTA-121 follow-ups (#3515)
* Eval selection exemptions, review-floor rulings and the GSTA-121 follow-ups Release metadata (NOTICE.md, LICENSE, licenses/**) no longer restores the full paid gate and ETHOS.md is registered under the two prompts that read it (#3499). docs/review-policy.md records the six finding classes #3485 and #3504 ruled below the floor and the review army's lead judgment applies the table; the floor itself is unchanged. The Windows curation moves test/pregate-remote-stamp-only.test.ts to KNOWN_WINDOWS_INCOMPATIBLE (#3485). From GSTA-121: Blast radius in docs/skills.md and the merge-ask template, the 11-digit run-id exemption from pii.phone.e164 after a run word, relative string literals as import-graph edges, and a ubi-runner pack that never tars the live .git. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes Red Team pass 1 (all below the floor): an 11-digit span with a leading 1 after a run word is a US or Chinese national number, not a run id, and reports again; ubi-runner pack removes its temporary repository when it fails and replays branch.* with remote.* so a branch's upstream resolves on the VM; the conservative-refusal example in docs/review-policy.md reads in the refusing direction; the touchfiles header names why ETHOS.md sits only under the two prompts that quote it. Step 6's selection found captain/templates/merge-ask.md as the one unknown dependency of this PR and registered captain/templates/** in FREE_ONLY_PR_FILES (#3499). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (pass 2) The cmd_pack EXIT trap bakes the temp path in: a set -e failure unwinds the function before the trap runs and a local $tmp is unset there, so the old form leaked the snapshot. The leak test creates TMPDIR where the pack reads it and asserts the failure is the missing index. CHANGELOG examples no longer spell a full national number. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: adversarial review fixes The pack snapshot carries the index's staged blobs as a pack of their own, so a VM write-tree (gstack-wtree) can read a staged file the way the old .git tar allowed; git init runs with --template= and gc.auto=0 and a valueless remote/branch key replays as true. scripts/harness-version.json re-pins scripts/test-pr-profile.ts after the captain/templates/** entry. The run-id exemption reads the same way in the scanner and gstack-post: an 11-digit span after a run word is a run id (the leading-1 exclusion from the Red Team pass contradicted gstack-post's tested contract and the ruling that a run id is not a phone number), with the residual named in the comment, the docs and the CHANGELOG. The #3499 pins move to their own test so the boundary test stays under its default budget. Docs audit: TESTING_INTERNALS names RELEASE_METADATA_FILES and captain/templates/**, docs/captain.md names Blast radius. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (pass 4) The pack's staged-blob list comes from the copied index, holds only blobs staged against HEAD (not every tracked blob), skips gitlinks whose commit the superproject lacks, and dies with its own message when pack-objects fails. The live-checkout test covers a gitlink entry and a valueless remote key replayed as true. CHANGELOG names the staged-blob carry. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (pass 5) The pack's blob list is the copied index's blobs that HEAD's tree lacks, so an intent-to-add entry's empty blob and the stages of an unmerged entry travel too (the HEAD-only diff list dropped both); gitlinks still skip. The live-checkout test adds an intent-to-add entry, which the VM fsck assertion covers. 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]
|
1f246e3505 |
v1.91.278.0 fix(ship-queue): readiness takes dispatched Free Tests, stamp paths accept tentative key versions, ready and train build read the base overlap, pr-wait --exclude, restamp prints the corrected order (#3514)
* fix(ship-queue): readiness takes dispatched Free Tests, prose check reads key=value pairs, stamp paths accept tentative key versions, ready and train build read the base overlap, pr-wait --exclude, restamp prints the corrected order Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes Pass 1 of /ship's review on #3514: the prose check skips a key: value pair's value whatever the whitespace, the restamp recompute keeps a merged-not-in-base predecessor and says to fetch, stampOnlyLine applies the version-width bound, pr-wait --exclude excludes nothing while the required checks are unreadable, baseOverlap reports a failed git read as unknown and gives no verdict at train build, readiness lets a pull_request run outrank a dispatched one, and the READY conflict refusal follows the crew template's rule 14 instead of a crew-local rule. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: stamp rule for tentative key versions, key=value prose claims, QUEUE_STALE merged-not-in-base 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> |
||
|
Garry Tanandcapy-ai[bot]
|
6ff98c6616 |
v1.91.277.0 feat(preamble): office-hours stops copying the shared AskUserQuestion subsections (GSTA-96) (#3453)
* fix(preamble): completeness means complete coverage with minimal code (GSTA-96) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(preamble): tier 2+ skills load the shared preamble once per session (GSTA-96) Every tier 2+ SKILL.md inlined the same ~23 KB preamble. It now renders once per host into sections/preamble.md beside each tier 2+ SKILL.md; the SKILL.md keeps a pointer that asks for the Read only when the file's id is not already in context. Only sections byte-identical to the shared render move, so every skill keeps exactly its pre-hoist paragraphs (verified across all 41 skills). Parity caps for ten skills raised to their measured unions (owner-approved, Garry 2026-10-25: "do it"); 63 size pins lowered and 26 deleted. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(paid-select): a generated sections/preamble.md takes its skill template's identity in the PR planner (GSTA-96) screen-summary failed on #3434 with 'PR profile requires full validation' for nine skills whose only paid coverage is periodic: their new sections/preamble.md had no dependency identity, while the SKILL.md beside it inherits its template's. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(section-manifest): the shared sections/preamble.md renders from the hoist resolver, not a section template (GSTA-96) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (CHANGELOG says 3 characters shorter; model-overlays guards the coverage half) The completeness section shrank by 3 characters (5 bytes), matching the 89 pins lowered by 3. The default-copy test pinned only the minimal-code half; an expectMentions check now fails if the full-coverage or never-excuses-a-gap clause is dropped. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (model-overlays binds smaller diff to equal coverage) The default-copy check now also fails if 'on equal coverage' is dropped from the smaller-diff rule (which would tell models to prefer the smaller diff unconditionally) or if the no-impossible-state-checks clause is removed. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: CHANGELOG lists the model-overlays coverage checks The [Unreleased] Tests bullet now says the default-copy test checks both halves of the rule (full coverage of the requirement; smaller diff only at equal coverage; no impossible-state checks; never excuses a gap), matching |
||
|
Garry Tanandcapy-ai[bot]
|
3e4240a76f |
v1.91.276.0 feat(preamble): tier 2+ skills load the shared preamble once per session (GSTA-96) (#3434)
* fix(preamble): completeness means complete coverage with minimal code (GSTA-96) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(preamble): tier 2+ skills load the shared preamble once per session (GSTA-96) Every tier 2+ SKILL.md inlined the same ~23 KB preamble. It now renders once per host into sections/preamble.md beside each tier 2+ SKILL.md; the SKILL.md keeps a pointer that asks for the Read only when the file's id is not already in context. Only sections byte-identical to the shared render move, so every skill keeps exactly its pre-hoist paragraphs (verified across all 41 skills). Parity caps for ten skills raised to their measured unions (owner-approved, Garry 2026-10-25: "do it"); 63 size pins lowered and 26 deleted. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(paid-select): a generated sections/preamble.md takes its skill template's identity in the PR planner (GSTA-96) screen-summary failed on #3434 with 'PR profile requires full validation' for nine skills whose only paid coverage is periodic: their new sections/preamble.md had no dependency identity, while the SKILL.md beside it inherits its template's. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(section-manifest): the shared sections/preamble.md renders from the hoist resolver, not a section template (GSTA-96) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (CHANGELOG says 3 characters shorter; model-overlays guards the coverage half) The completeness section shrank by 3 characters (5 bytes), matching the 89 pins lowered by 3. The default-copy test pinned only the minimal-code half; an expectMentions check now fails if the full-coverage or never-excuses-a-gap clause is dropped. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (model-overlays binds smaller diff to equal coverage) The default-copy check now also fails if 'on equal coverage' is dropped from the smaller-diff rule (which would tell models to prefer the smaller diff unconditionally) or if the no-impossible-state-checks clause is removed. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: CHANGELOG lists the model-overlays coverage checks The [Unreleased] Tests bullet now says the default-copy test checks both halves of the rule (full coverage of the requirement; smaller diff only at equal coverage; no impossible-state checks; never excuses a gap), matching |
||
|
Garry Tanandcapy-ai[bot]
|
f8d0ab0339 |
v1.91.275.0 fix(ship-policy): DOCS_CAPS_KEY_VERSION is 1.91.270.0; key versions move through stamp_paths at the slot stamp (#3511)
* fix(ship-policy): DOCS_CAPS_KEY_VERSION is 1.91.270.0; key versions move through stamp_paths at the slot stamp #3487 was written naming 1.91.258.0 for docs.caps and main stamped that number for another PR first; the slot call cannot edit anything beyond the four stamp files, so the constant shipped stale. lib/ship-policy.ts now sits in .gstack/ship-policy.json stamp_paths with the _KEY_VERSION = '{version}' template, so a new key written as a tentative future version is moved by gstack-restamp's stamp_paths stage at the slot (read from the base policy, so live from the next PR on). test/gstack-ship-policy.test.ts gains the check the incident lacked: a released key's version must be a heading whose entry names the key. Dry-run proof: a tentative 1.91.272.0 on a branch line moved to the allocated 1.91.271.0 with --policy-from head. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(ship-policy): tentative key versions are clear of main's pace; the receipt accepts the move only at the base version until #3512 Pass-1 review notes: the next patch above the fork point is the number main takes first, so the convention names the next minor; and the tree receipt's stamp-only check (lib/tree-receipt.ts stampOnlyHunks, with stampOnlyText and stampFreeTree) rewrites only base VERSION -> new VERSION, so a tentative move passes the train only when the tentative value equals the base version at the slot. Filed as #3512 (outside this diff, deferred under the frozen scope). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(ship-policy): read origin/main's CHANGELOG with a 64 MiB maxBuffer; say plainly that a new-key PR cannot clear the train until #3512 Pass-2 Red Team: CHANGELOG.md is past spawnSync's default 1 MiB maxBuffer, so both CHANGELOG-reading tests dropped origin/main's file silently and the incident shape passed at the pin. With the buffer the released-key test sees main's headings on a full clone. The comment and CHANGELOG now state the practical consequence of the receipt limit. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(ship-policy): gstack's own policy excerpt names lib/ship-policy.ts under stamp_paths 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]
|
d87eec950a |
v1.91.274.0 feat(design-html,design-review): run gstack-design-lint; copy tier at its lines; waivers replace craft_exceptions (hallmark phase 2) (#3507)
* feat(design-lint): copy tier reports each tell at its line; empty-mount-node; content-realism ids at ask
The copy tier holds its own patterns (from lib/design-craft.ts) and reads
visible text, script bodies, inline handlers and parsed tags, so payloads,
commented markup and script text no longer count. A text-less body that
loads a script reports empty-mount-node. placeholder-name, placeholder-brand,
lorem, round-number and needs-proof move to ask so a page-specific waiver
answers them (Garry 2026-10-26, option a).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(design-html,design-review): run gstack-design-lint; waivers replace craft_exceptions; remove gstack-design-craft
/design-html Step 4 and /design-review's craft audit call the lint and read
its exit code. A waiver comment in the page replaces --accepted and
finalized.json craft_exceptions (supersedes #3422's persisted exceptions).
bin/gstack-design-craft, lib/design-craft.ts and its test are removed; the
handoff tests move to test/design-craft-resolvers.test.ts. The slop-gate paid
case and its touchfiles follow the lint.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(design-lint): the content-realism tells keep one checker, credited in NOTICE.md
Names the removed lib/design-craft.ts and test/design-craft.test.ts so pregate
selects a lane for the deletions (PREGATE_NO_LANE at
|
||
|
Garry Tanandcapy-ai[bot]
|
a1934a1498 |
v1.91.273.0 feat(ship): PR bodies open with the problem and a Blast radius line, and gstack-prose-lint catches autopilot phrasing before /ship publishes a CHANGELOG entry or PR body (#3501)
* feat(ship): PR bodies lead with the problem and carry a Blast radius line, and gstack-prose-lint checks the CHANGELOG entry and PR body drafts Absorb lane B (Garry, 2026-10-26: "Do it, send" on plans/absorb-tstack.md item 4 and plans/absorb-pstack.md items 2(a) and 11). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: register the prose-lint fixtures and NOTICE.md as free-only PR inputs Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: pin prose-lint gate lines and usage exits, use a gstack-native dropped-article example, keep NOTICE.md unmapped Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: name the CHANGELOG prose-lint gate and the Blast radius body section in the contributor docs Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(ship): name the evidence ladder by skill instead of by a runtime-root path that does not exist yet test/runtime-root-assets.test.ts checks every $GSTACK_ROOT/<path> literal in a host render against the staged root; investigate/sections/blast-radius.md lands with its own lane, so the Blast radius item and the Capy body step now say "the /investigate skill's Blast radius section, when present". Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: name the Blast radius section in the two Capy body-order lists The docs re-audit found capy/skill/gstack/SKILL.md (Merge asks) and docs/capy-install.md still listing the Capy PR body as What changed, Why, Approvals; both now match capy-pr.md.tmpl. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(ship): the compose block's prose-lint trailer goes to stderr, and the publication-gates fixture stages gstack-prose-lint beside gstack-post test/ship-publication-gates.test.ts runs the real compose block under a HOME whose installed bin dir held only gstack-post, so the block's new gstack-prose-lint call failed with "No such file" on every CI free lane; the fixture now stages both bins the blocks call, and the lint's ok line goes to stderr so the composed body is the only stdout. 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]
|
c1900088d5 |
v1.91.272.0 feat(skills): absorb pstack's blast radius, transcript recall, vet-the-number and design-twice as lazy passes (#3500)
* feat(skills): absorb pstack's blast radius, transcript recall, vet-the-number and design-twice as lazy sections
/investigate gains sections/blast-radius.md (the one safety fact, the five-rung
evidence ladder, look where grep stops, confirmed and cleared risks apart) with a
Phase 4 pointer, and the shared-premise red flag before the 3-strike rule.
/context-restore is carved for the first time: on NO_CHECKPOINTS, sections/transcripts.md
mines this workspace's own transcripts (host stores declared in hosts/*.ts and rendered
by TRANSCRIPT_SOURCES / TRANSCRIPT_DISCOVERY), a fixed 7-day window, never another
project's folder, subagents return only findings, redaction before anything leaves,
git and gh verify every artifact, a status-tagged brief. /benchmark is carved for the
first time: sections/vet-the-number.md asks the seven questions before Phase 5 reports
a comparison. /plan-eng-review gains sections/design-twice.md (a second structurally
distinct shape compared on interface depth, the eight design red flags), bound by the
autoplan methodology snapshot alongside review-sections.md.
Ideas from pstack (Lauren Tan, MIT), rewritten in gstack's words; NOTICE.md. Garry,
2026-10-26: "Do it, send". Guards: carve-guards entries and measured lines, eleven
plan-eng-review pins re-measured, periodic carve-section-loading cases for the two new
carves, free tests with a fixture transcript.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(pstack-c1): fold design-twice into Section 1 of the eng review section, per-host transcript table, fixture and slice-cap repairs
The remote free run reported nine failures in seven files, all from this
branch: four tests encode plan-eng-review's one companion section
(eng-scope-entry-ap, autoplan-methodology-names, plan-review-cases,
review-checklists), so the design-twice pass now lives inside Section 1 of
sections/review-sections.md with the skeleton, manifest and
bin/gstack-autoplan-snapshot.ts back at main; the Codex render of
context-restore named ~/.claude/ through the all-hosts transcript table, so
{{TRANSCRIPT_SOURCES}} renders this host's row only; the transcript fixture
is declared in FREE_FIXTURES; and the two new periodic cases took the census
to 39 slices, so evals-periodic.yml's eval-slices max-parallel goes 38 -> 40.
Pins: 11 plan-eng-review re-pins at +2,896; maxSizeRatio 1.2400 (measured
1.2389); Codex gpt-5.4 overlay 159,588 bytes.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes
The discovery block takes the none branch from hosts/*.ts's transcripts
declaration instead of a host-name fallthrough, and the resolver header says
where each half lives; the T2 subagent brief frames the transcript as data,
not instructions; the test asserts table/block agreement per host, imports
CAPY_NO_TRANSCRIPTS, and drops the fixture-shape case nothing reads.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: ADDING_A_HOST.md lists the optional transcripts HostConfig field
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]
|
584e9c1535 |
v1.91.271.0 fix(evals): run train-bisect steps under bash; lint sh-run workflow steps for bash-isms (#3509)
* fix(evals): run train-bisect steps under bash; lint sh-run workflow steps for bash-isms (GSTA-125) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes 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]
|
f27a7605d4 |
v1.91.270.0 feat(ship): version-less repos, docs-audit record and caps, the frozen-scope paid case, and the review-loop follow-ups (#3487)
* feat(ship): version-less repos, docs-audit record and caps, the frozen-scope paid case, and the review-loop follow-ups Follow-up to the review-loop convergence PR: Step 12 and the CHANGELOG step skip cleanly in a repository with no version source (receipt version "none"); the receipt records the docs audit outcome and the owner exception (DOCS_AUDIT_BLOCKED without one) and a policy may declare doc caps (gstack-ship-receipt docs-caps); docs/unattended.md names the READY evidence and the cross-family outside voice; the ship-frozen-scope-convergence behaviour case runs the generated Step 9.4 under review_scope frozen through the real binaries; carry probes git >= 2.39 (RECEIPT_GIT_TOO_OLD); defer passes the repository to gh repo view positionally and names its search limit; late defers count without being passes; reviewers diff from RANGE_BASE on pass 2+; the cap check runs before edits; --review-fanout batches specialists by free slots; read --check-prose compares quoted counters with the receipt (RECEIPT_PROSE_MISMATCH); checklist rule ids prereg-with-results and test-keyboard-count-loop; gstack-coauthor-trailers. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: repair the CI reds the retarget onto main surfaced (test-only) Seven test files, no product change. The pull_request run at |
||
|
Garry Tanandcapy-ai[bot]
|
295b32e2c4 |
v1.91.269.0 feat(autoplan): gates print their cost, approvals mirror to the Captain's drive, Eng asks for a perf budget (GSTA-114 lane F, PR 3) (#3496)
* feat(autoplan): gates print their cost, --owner-standing rec cites a standing approval, approvals mirror to the Captain's drive
E16: GATE_SPEND and GATE_REC_COST under every GATE line (lib/autoplan-gate-cost.ts), and a
Cost so far sentence in the owner brief; host-subagent attempts stay priced unknown.
E21: gstack-autoplan answer --owner-standing rec --by agent:<id> answers rec by citing the
newest standing approval covering autoplan recommendations from any branch's record; the
id lands on every decision row, in run.json and in the approvals import; refused with
STANDING_APPROVAL_ABSENT or STANDING_APPROVAL_INAPPLICABLE (urgent finding).
E22: the approvals mirror honours the approvals/ directory a Captain created in its drive,
between GSTACK_APPROVALS_DIR and the private project-user folder; gstack-approvals path
names the rule.
E23: the Eng phase asks for a performance budget and a bench step on hot-path changes.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(autoplan): review pass 1 — standing answers bind to the run's project and refuse recommend-edited gates, cost is an upper bound and reaches JSON and the Captain brief
Review pass 1 (6 specialists + red team) on the standing-approval and gate-cost change:
- the standing lookup resolves the approvals record of the repository the run's plan lives in,
never the caller's cwd (red team: project A's row answered project B's gate)
- standingAnswer refuses a gate that `recommend` edited (rec_rev > 0 or recommended_by), a
missing or unreadable findings.jsonl, and an outside-plan finding; the STANDING line flattens
control characters so a crew-writable row cannot forge a protocol line
- coversAutoplanRec matches the recommendation words in the owner's words only and rejects
negations; STANDING_APPROVAL_ABSENT's fix names every required gstack-approvals flag
- recReopens is the upper bound of the answer/revise rules (a plan change counts every phase,
a round grant its phase plus Eng); gate_cost rides the JSON payloads, `run` prints the lines
at its final gate, and `gstack-owner-brief render --captain` appends a ### Cost section
- locate keeps the other mirror roots as read_also so rows mirrored under an earlier rule stay
visible; gstack-approvals path prints READ_ALSO
- the Eng phase edit is size-neutral: five nearby phrases shortened so every host's autoplan
SKILL.md stays at its size-guard pin
- tests: isolated fixtures, the run's plan inside its own git repo, cross-project refusal,
amend_pending vs complete, recommend-then-standing, injection, gate_cost JSON, Captain brief
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes (pass 2)
Standing approvals: the newest row about autoplan recommendations decides, so a later refusal
blocks older grants; rows whose id or date is not the recorded shape are never cited; the
project is fixed at init from the plan's physical path (run.json project_root) so a symlinked
plans folder or a checkpoint restore cannot borrow another repository's record. Gate cost:
recReopens counts every phase revise can keep or add and prices answers already recorded at
the gate; run --json emits one payload; the Captain brief's ### Cost sits above the relaying
trailer.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes (pass 4, rule-23 exception)
Standing grammar fails closed: the newest standing row mentioning autoplan decides and grants only
with the canonical scope and affirmative owner words; same-id copies keep the newest recorded; id and
date are type-checked before the regexes. Gate cost prices the effective choices exactly as answer
does (p1d, carried overrides, non-recommended options). The run records project_slug beside
project_root so a restored run names its record on another machine, and project_root is a recorded
root for export --public.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* refactor(autoplan): drop --owner-standing rec (E21) from this PR
Pass-4 review (red team + Codex adversarial) still found that the keyword
grammar over the owner's standing words could read a refusal as a grant
("I won't take the recommendations", "Taking the recommendations is
forbidden" granted under the canonical scope) and that gstack-approvals add
deduped a same-day scope revocation as the grant. A free-text negation
parser cannot fail closed, so the standing answer leaves this change and
returns with a structured grant in its own PR.
Kept: GATE_SPEND/GATE_REC_COST cost lines and gate_cost (E16), the
Captain-drive approvals mirror with READ_ALSO (E22), the Eng perf-budget
question (E23). Removed: standingAnswer, standingRecApproval,
coversAutoplanRec, citableRow, project_root/project_slug in run.json,
STANDING_APPROVAL_* result codes and anchors, the standing DRIVER
paragraph and docs, test/autoplan-standing.test.ts (its E16/E22 cases move
to test/autoplan-gate-cost.test.ts).
Focused: 793 pass / 0 fail across 45 files; typecheck, typecheck:test,
format: cso:check clean; renders regenerated with gen:skill-docs --host all.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* RESTAMP: 1.91.268.0 -> 1.91.269.0 (stamped; queue_mode=stamp-at-merge base=origin/main@76aa68fc9e7a policy=base origin/main@76aa68fc9e7a:.gstack/ship-policy.json)
ship, next in queue at 1.91.269.0
STAMP_VERSION: 1.91.269.0
claims: ignored (stamp-at-merge)
stage version: done (wrote 1.91.269.0)
stage release_tool: done (bun scripts/gen-agents-digest.ts)
stage changelog: done (Unreleased -> 1.91.269.0)
stage stamp_paths: skipped (no stamp_paths in policy)
stage mirror: skipped (no mirror in policy)
stage apply: done (4 file(s))
diff --git a/CHANGELOG.md b/CHANGELOG.md
index e4e28308c..566bb525c 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,6 +1,6 @@
# Changelog
-## [Unreleased]
+## [1.91.269.0] - 2026-10-27
**An autoplan gate now arrives with its price, and the approvals record lands where the whole crew can read it.** Captains reported the same two frictions: review rounds and reviewer subagents had no credit figure at the gate, and the approvals mirror sat in a private project-user folder no sibling thread could read. The Eng phase also gains the performance-budget question, after a correctness pass doubled a consumer's p95 with no bench step to catch it. (The standing "take the recommendations" answer planned beside these, `answer --owner-standing rec`, was cut from this release after review: a keyword grammar over the owner's words could still read a refusal as a grant, so it returns with a structured grant in its own change.)
diff --git a/VERSION b/VERSION
index c31f84688..6437fa3e4 100644
--- a/VERSION
+++ b/VERSION
@@ -1 +1 @@
-1.91.268.0
+1.91.269.0
diff --git a/agents-digest/gstack-AGENTS.md b/agents-digest/gstack-AGENTS.md
index 3548eb690..4bdc2879f 100644
--- a/agents-digest/gstack-AGENTS.md
+++ b/agents-digest/gstack-AGENTS.md
@@ -1,4 +1,4 @@
-# gstack digest v1.91.268.0 — regenerate/re-copy after upgrading gstack
+# gstack digest v1.91.269.0 — regenerate/re-copy after upgrading gstack
Behavioral rules from gstack (https://github.com/garrytan/gstack), compressed
for agent hosts without a full skill install. The full skills add workflows,
diff --git a/node_modules b/node_modules
new file mode 120000
index 000000000..1de79460f
--- /dev/null
+++ b/node_modules
@@ -0,0 +1 @@
+/workspace/gstack-ap/node_modules
\ No newline at end of file
diff --git a/package.json b/package.json
index 7a672beb5..26a9702da 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
{
"name": "gstack",
- "version": "1.91.268",
+ "version": "1.91.269",
"description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.",
"license": "MIT",
"type": "module",
FILES: CHANGELOG.md VERSION agents-digest/gstack-AGENTS.md package.json
MERGE_CONDITION: sha=624f0eedec7c3aebdd0cecd70be4e4ebd10eb4af
next: NEW_VERSION=1.91.269.0; commit and push only the stamp diff above (FILES), with no edit of your own: the train's verify accepts the CHANGELOG only as the base's plus this PR's entry re-headed; merge with the expected head
|
||
|
Garry Tanandcapy-ai[bot]
|
76aa68fc9e |
v1.91.268.0 feat(bin): gstack-decision-trail and gstack-worktree-audit, ported from pstack (GSTA-123) (#3494)
* feat(bin): gstack-decision-trail and gstack-worktree-audit, ported from pstack (GSTA-123)
Two MIT ports from Lauren Tan's pstack (licenses/MIT-pstack.txt, NOTICE.md):
a TSV decision trail with the header-once append, the formula guard, a start
row per run and a --run admission check; and a read-only worktree audit with
size, merge state, dirty, remote, PR, last chat and a suggested bucket.
Docs: docs/unattended.md (the decision trail and its end-of-run audit),
autoplan/DRIVER.md, docs/CONTRIBUTOR_REFERENCE.md, docs/standalone-binaries.md,
docs/troubleshooting.md, one line in landing-report.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(egress): reasoned scanner exemption for gstack-worktree-audit's base fetch
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review of the pstack ports
bin/gstack-worktree-audit: a worktree path with a space is read whole (sed
on the porcelain 'worktree ' line, not awk's second field); a registered
worktree whose directory is gone prints a 'prunable' row instead of being
skipped; 'safe' now requires a clean tree and either merged into the base
or a closed/merged PR with every commit pushed, so unpushed commits or
untracked files on a merged branch read 'review' (the port's rule called
them safe); fork PRs are dropped and an open PR wins over an older closed
one on a reused branch name; GIT_TERMINAL_PROMPT=0 on the base fetch.
bin/gstack-decision-trail: only a leading -h/--help is help, so a '-h'
cell is appended as data; a trail without a final newline, with CRLF rows
or with a repeated header line is appended to correctly; a run id is
limited to [A-Za-z0-9._:@/-] (exit 2) so a tab or quote cannot break the
start-row idempotence check.
Tests cover each case; the 'without gh' test resolves git from
'git --exec-path' instead of a PATH rebuilt from a tool list. Docs,
CHANGELOG and --help text describe the stricter buckets.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes, pass 2
bin/gstack-worktree-audit: a worktree whose own .git link is gone (git
marks it prunable, or its toplevel is another repository) prints a 'broken'
row in 'review' instead of describing the containing repository as clean
and safe; a locked entry whose directory is gone reads 'review', not
'prunable', since prune would not touch it; a clean tree names its
gitignored entries as 'clean,ignored:<n>' without changing the bucket; the
branch name is read from refs/heads/ by hand so a tag of the same name
cannot hide the PR; porcelain blocks are read with IFS=tab so paths with
leading or trailing spaces survive; a failed git status reads 'unknown',
never 'clean'; the base fetch also sets GIT_ASKPASS=true and ssh BatchMode.
bin/gstack-decision-trail: a file whose first line is not the header (a
blank file, rows written by hand) gets the header appended, and a UTF-8
BOM before the header no longer turns it into a data row.
Tests: the fake gh records its argv and runs the audit's own --jq over
canned JSON with a fork PR when jq is installed; row counts are asserted
before the every() checks; each test starts from the same gh and closed
worktree; the snapshot includes the worktree registry; new fixtures for
locked, broken, tag-shadowed and ignored-only worktrees, a blank trail and
a BOM. Docs and CHANGELOG describe the new DIRTY values and buckets.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes, pass 3
bin/gstack-decision-trail: hasHeader looks for a header line anywhere in
the file, so a blank or hand-written trail gets exactly one header rather
than one per append. bin/gstack-worktree-audit: the broken-worktree check
uses rev-parse --show-cdup and the presence of /.git instead of
comparing two spellings of the same path, which differ on Git for Windows.
Test: the blank-trail case appends twice and asserts a single header.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: adversarial review, pass 5 (rule-23 grant, one finding)
bin/gstack-worktree-audit: git status runs with --untracked-files=normal
--ignore-submodules=none, so a user's status.showUntrackedFiles=no config
cannot hide untracked files and let a worktree holding them read clean and
safe. Test: the fresh worktree under that config via GIT_CONFIG_* still
reads scratch:1 / review (red before the fix).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: documentation audit corrections for the pstack ports
docs/standalone-binaries.md, docs/CONTRIBUTOR_REFERENCE.md,
docs/troubleshooting.md: the audit's safe condition is stated in full
(clean and merged, or PR closed/merged with every commit pushed), the
DIRTY list names missing, broken and unknown, start is a reserved phase
name, and 'read-only' names the base fetch as the one write --no-fetch
skips. CHANGELOG.md says the same (the audit's one decision item).
Audit id gsta123-docs-20261026T221657Z, status updated, no blockers.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* Stamp 1.91.268.0 for #3494 (train slot 1, base
|
||
|
Garry Tanandcapy-ai[bot]
|
d9b0d60082 |
v1.91.267.0 docs(captain): observable questions are not the person's to answer (GSTA-124 follow-up) (#3503)
* docs(captain): observable questions are not the person's to answer Captain-side reading of the rule shipped in plan-tune/SKILL.md.tmpl and docs/proactive.md (#3493, pstack item 4): a question a command, render or measurement can settle is settled by the thread; a Captain that receives one sends it back with the check that answers it. gstack holds the how; the Drive copy of captain.md syncs from main. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: changelog entry for the captain.md observable-questions bullet Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: changelog says the Drive copy needs a recopy, not a sync 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]
|
6bbd0a536f |
v1.91.266.0 feat(pr-wait): gstack-pr-wait event watcher (tstack pr-wait design port) and /land-and-deploy Step 3 wiring (#3495)
* feat(pr-wait): gstack-pr-wait event watcher (tstack pr-wait design port) and /land-and-deploy Step 3 wiring Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(pr-wait): keep the result codes in lib/result-codes-release.ts so fixtures that copy the module list keep working Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(pr-wait): function declarations for the fake-gh helpers so the pregate TSX import scanner maps the lib files Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(pr-wait): /ship review pass 1 — every check gates green, --timeout, bot identity, signal disposition Red Team and specialist findings on #3495, all fixed in the diff: - green gates on every check on the head, as gstack-ci-gate does, so land-and-deploy Step 2 and Step 3 can no longer disagree while a non-required check pends; required checks still gate before they appear - --timeout MINUTES (default 60, 0 = none) ends a watch that met nothing as PR_WAIT_BLOCKED naming the still-pending checks; restores Step 3's cap - a bot owns logins that start with its name (greptile-apps[bot]), not any login containing it; a failed gating-bot check is a failed check, never a completed review - ready: green alone when no gating bot is configured (pr_wait_gating_bots none no longer polls forever); held while merge state is UNKNOWN - BEHIND and DIRTY announced once per head, with the short head in the line - the bin installs no signal handlers: the synchronous loop never ran them and they made the process ignore SIGTERM/SIGINT; default disposition kills it at once and the next watcher takes over the dead pid's lock - a gh spawn timeout (ETIMEDOUT) is retried like any transient failure - a local fault (unwritable state root) is PR_WAIT_REFUSED exit 2, so exit 1 always carries a PR_WAIT_BLOCKED line - control characters in GitHub text never start a second event line Tests: 21 new cases including a real SIGTERM against the bin, gstack-config set-time validation and default parity, and the 14 state-matrix cells the state-machines specialist listed (gstack-state-matrix check: ok, 33/33). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(pr-wait): /ship review pass 2 — advisory checks gate too, BEHIND keyed on the head, verdict survives a failed save - an advisory bot's review is never waited for, but its check gates like any other, so gstack-ci-gate (Step 2) and gstack-pr-wait --until green (Step 3) read the same check set with no exception - BEHIND and DIRTY are keyed on the head alone; the pass-1 key also held the base oid, so a base that kept moving re-announced BEHIND to a restarted watcher on every commit - finish() keeps the printed verdict's exit code when the state file cannot be written; the save error goes to stderr - PR_WAIT_BLOCKED and PR_WAIT_REFUSED summaries name every exit-1 and exit-2 path (--timeout, a local error); emitBots docstring matches the gating rule - CHANGELOG says what a timeout means at land-and-deploy Step 3: a STOP with the pending checks named, no wait-more question 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]
|
a50cf58965 |
v1.91.265.0 docs: absorb four pstack principles into ETHOS.md, the observable-questions rule and candidate-side eval blinding (GSTA-124) (#3493)
* docs(ethos, plan-tune, eval-plan): absorb four pstack principles, the observable-questions rule and candidate-side blinding (GSTA-124) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Reword ETHOS sentences, scope the blinding rule, name the second candidate-visible root Review pass 1 (frozen scope, five INFORMATIONAL findings, all in-diff, none blocking): two ETHOS.md sentences in principles 6 and 7 were too close to the credited source and are reworded; the Credits line names both pstack sources (principle-* leaves and poteto-mode); eval-plan Step 1c rule 1 is scoped to what the preregistration controls and exempts the skill text an arm loads; the observable-questions rule in plan-tune and docs/proactive.md requires the observation to be local, read-only and free and points at the one-way-door rule; docs/TESTING_INTERNALS.md names skill-e2e-benchmark-* (test/skill-e2e- deploy.test.ts:293) as a second candidate-visible root and states the audit's matching method. SKILL.md regenerated for both unpinned skills. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: correct the candidate-visible root list and the one-way-door attribution The blinding audit paragraph in docs/TESTING_INTERNALS.md and the CHANGELOG entry claimed two candidate-visible temporary roots and that the other skill-e2e-<case>-* roots carry no listed word; test/skill-e2e-test-value.test.ts:131 (skill-e2e-<id>- with ids carrying 'test') and test/skill-e2e-health.test.ts:23 (gstack-health-eval-) show otherwise, so both now list the roots the mkdtemp scan found and say the list is not a proof of completeness. docs/proactive.md said the one-way-door rule already covers spend and third-party reach; it now says the new sentence extends that rule. The CHANGELOG bullet for the observable-questions rule names its local, read-only and free qualifier. 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]
|
c2e01e4ba7 |
v1.91.264.0 feat(design-motion): new /design-motion skill for showcase loops, adapted from Elaya's design-to-motion (GSTA-92 phase 2) (#3430)
* feat(design-html): craft section and free craft check, adapted from Elaya design skills (GSTA-92) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(GSTA-92): restore the full CHANGELOG under the Unreleased entry; drop a $-digit literal from craft.md; count only craft-check executions in design-html-slop-gate Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(design-motion): new /design-motion skill: showcase MP4 and GIF loops from a design, adapted from Elaya design-to-motion (GSTA-92 phase 2) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(design-motion): run design-motion-showcase in the marathon tier; the periodic census is at its 38-slice cap (GSTA-92) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(design-motion): review and QA fixes before ship - encode: refuse unknown options and --formats tokens, validate --pad (#RRGGBB[AA]) and --crop (compare too) so nothing but a colour or crop reaches ffmpeg's filter graph - encode: export refuses a capture with missing window frames; check prints MOTION_SETTINGS for any threshold/phase override; contact sheet drops -fps_mode - capture: portrait-aware scale, --cycle must be whole 60 fps frames, stills with CSS animations disabled, pauseAt tolerates slow loads, clears stale manifest/stills - skill: <motion-dir> placeholder instead of a cross-block shell variable, GSTACK_FFMPEG-aware probe, stop points before the first capture, doctrine fixes - tests: refusal rows, portrait scale, cycle guard Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(design-motion): capture-check-export pipeline on real Chromium and ffmpeg Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(design-motion): second review cycle - capture: refuse an --out that holds a still or frames but no capture.json instead of deleting them; --cycle must be a multiple of 0.05 s so the seam frame lands exactly one cycle later for every PRE (nearest value round-trips) - encode: a capture without a mask ends 'MOTION_RESULT: clean (overflow not checked)' - skill: Step 5 names window.__mark in the capture contract - tests: foreign/previous --out handling on real Chromium, cycle guard and PRE sweep Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(design-motion): third review cycle and adversarial findings - capture: an ownership marker (.gstack-motion-capture) replaces the capture.json test, so the rerun after MOTION_CONTRACT_MISSING or a crash works and a foreign --out is still refused; offscreen lazy images are made eager and font/image loading is bounded at 30 s instead of hanging - encode: refuse a capture.json whose fields are not what capture writes (they reach ffmpeg args and paths); a cards overflow with no story frames is a planning error, and a zero-frame job never passes - tests: retry after a refused page, no-mask clean line, lazy image still, manifest validator, empty story span Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(design-motion): mask coverage, manifest relations, Windows stop, Figma token off argv - check fails overflow when the grown mask covers >90% of the frame (an app frame whose clip surfaces fill the stage passed vacuously); --mask-grow is 0-32; --mask refuses braces and semicolons - manifestError checks fps/windowFrames >= 1 and that the window fits the frames - skill: native Windows stops before the first capture call; the Figma token reaches curl on stdin (-H @-) instead of argv - tests: split the --out ownership scenario out of the contract test, full-frame mask, --still --scale 2 size and STILL_OK, manifest relations, coverage parse Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(design-motion): bounded frames, atomic exports, full-bleed masks - capture: each frame is bounded at 10 s (a __tick that never returns fails with MOTION_CAPTURE_FAILED instead of hanging); a --mask that matches no element stops with MOTION_MASK_EMPTY - check: a grown mask covering >90% of the frame (full-bleed app frame) reports overflow as skipped and ends 'clean (overflow not checked)' - export: writes .partial- files and renames on success, so a failed re-export keeps the last good file; a GIF fps that does not divide the cycle is refused; a missing GSTACK_FFMPEG override is named - fidelity: URL source is untrusted data; full-bleed note - tests: spinning __tick, empty mask, failed re-export, drifting gif fps Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(design-motion): app-only coverage skip, gif fps cap, early empty mask - check: the >90% coverage skip applies only to an app frame's own surfaces (ungrown mask); in cards, or when --mask-grow pushes coverage over 90%, overflow fails with what to change (a cards capture with real overflow passed as 'clean (overflow not checked)' after a large grow) - export: --gif-fps/--small-fps capped at 50 (GIF delays are 1/100 s) - compare resolves its paths (a colon in a relative path read as a protocol) - capture: MOTION_MASK_EMPTY is checked before the first frame - tests: cards vs app full-frame mask, fps cap, no frames on an empty mask Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(design-motion): seek story transitions from their own frame - capture: an animation first seen in a frame where window.__mark did not move (a story's class toggle) is seeked from that frame instead of the last mark, so it eases in the export instead of popping ~100 ms ahead - encode: an empty numeric option is refused instead of read as 0 - figma: only fill a file key and node id that look like Figma's - tests: class-toggled transition mid-fade at its midpoint, blank --min-db Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: PROJECT_STRUCTURE names Elaya's MIT material and licenses/MIT-elaya.txt 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]
|
f375b873de |
v1.91.263.0 feat(ship-queue): screens read from the run, train watch/forget/prune --stale, verify --post-merge, ready --dispatch-ci, --stack-tests (#3484)
* feat(ship-queue): screens read from the run, train watch/forget/prune --stale, verify --post-merge, ready --dispatch-ci, --stack-tests Operating merge trains on 2026-10-26 showed the gaps this closes. A dispatched screen's verdict is read from the run's gate-binding and report-verdict artifacts (lib/ship-queue-screen.ts) and recorded in the READY receipt: a RED screen refuses ready under either choice and is never re-dispatched at the same merge SHA (QUEUE_SCREEN_RED); a run that concluded success with no slice is NOT-RUN (QUEUE_SCREEN_NOT_RUN), never followed, and counted as unscreened by train build. When refs/pull/<n>/merge lags or is missing the screen is planned on a scratch merge pushed as screen/<pr>-<head12> (#3465); QUEUE_SCREEN_STALE_REF means a real conflict only. train watch --train is the resumable follow command; train prune --stale settles a merging/green train whose PRs all merged or closed elsewhere; train forget removes one record with an exact lease on refs/notes/gstack-trains; verify --post-merge <sha> watches main's push workflows until they settle; ready --dispatch-ci <wf,…> dispatches the free workflows on a conflicting PR, waits, and clears the matching requires-remote pregate lanes with the run URLs; train build --dry-run --stack-tests runs each PR's new test files on its integrated prefix before anything is dispatched (QUEUE_TRAIN_STACK_RED). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Regenerate gstack-doctor-components.sh for the four new QUEUE_* result codes The committed Bash render was four case lines behind its generator, so test/doctor-components.test.ts failed at |
||
|
Garry Tanandcapy-ai[bot]
|
a8decce8ac |
v1.91.262.0 fix(release-cut,ship-queue): the weekly release accepts a train-gated commit; cross-repo refs, run ids, pr-body section merge, pregate by tree (#3483)
* fix(release-cut,ship-queue): the weekly release accepts a train-gated commit, and five lane frictions seen in operation scripts/release-cut.ts gates a main commit either by a successful backstop check run or by a green/merging/merged train record in refs/notes/gstack-trains whose merged[] names its sha or tree (CANDIDATE: ... gated by train <nonce>); a red check, a running run, the required check and the freeze are judged as before. --required-check, --backstop-check and --notes-ref make the names configurable. lib/issue-links.ts reads (name #N[, #M]), (name PR #N) and (name issue #N) as cross-repo references. lib/gstack-post.ts allowlists an 11-digit run id after a run word or chained after one, and pr-body merges by ## section into the PR's current body (--replace overwrites). gstack-pregate mirrors each record under <state root>/pregate/by-tree/<tree>.json and ready reads the mirror for its tree when the checkout's record is missing or for another tree. docs/troubleshooting.md gains #redact-run-id-as-phone, #gate-error-no-base and #gstack-post-pr-body-merge. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (pass 1) Fence-length-aware section splitting in gstack-post pr-body (an unclosed receipt fence or a four-backtick block no longer exposes a heading to the merge), the run-id allowlist drops generic words (id, job, attempt, workflow), ready accepts a by-tree pregate mirror only from a complete run against origin/<base> under a reviewed policy and prints no home path, release-cut skips non-object notes and never substitutes train evidence for the required check when both names are equal, issue-links treats closing/cf./e.g./v1.2 as words rather than repositories. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (pass 2) An unclosed receipt fence makes the body from that line on one section the merge never matches, so posted leading prose cannot replace it and a closed receipt before it stays a receipt; the by-tree pregate mirror must hold the tests stage (what --stage tests --remote writes) rather than every check; empty sha/tree strings in a train note are not evidence; (v1.2.3-rc1 #301) is a version word, not a repository. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: CANDIDATE line names its gate; issue-links reference documents the (name #N) form Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(ship-queue): a PREGATE_ENVIRONMENT local record is final; no mirror stands in for it Merging origin/main |
||
|
Garry Tanandcapy-ai[bot]
|
51a2b19b75 |
v1.91.261.0 fix(restamp): quoted since: rows and stale base-version mentions on branch-added lines when VERSION equals the base (gbrain #7640) (#3491)
* fix(restamp): quoted since: rows and stale base-version mentions on branch-added lines when VERSION equals the base (gbrain #7640) A PR that stamped X, lost its slot and merged a base that had reached X on its own had no branch stamp, and the mention scanner could not pass the opening quote of a quoted row, so gstack-restamp --next left the PR's { since: 'X' } rows at X while the release shipped as X+1. - tentativeMentions and rewriteStamps accept since: 'X' / since: "X" / (was 'X') / (was "X") and keep the quote style; the scanner also reads the policy's stamp_patterns templates. - With no branch stamp and no --was, a stamp-form mention of the base version on a line the branch added moves; the same version on a base line stays. The stamp_paths stage detail names both counts per file. - test/restamp-mentions.test.ts (pure forms + the reporter's state rebuilt with the real bin), stamp-templates pin updated, docs/ship-policy.md, --was help line, CHANGELOG [Unreleased]. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(restamp): review pass 1 — closing quotes, positional provenance, retry after a partial apply - since: 'X' and (was 'X') require the quote to close right after X in the scanner and the rewrite table, so a quoted prerelease or a mismatched pair is never a stamp (the tree receipt shares the table). - branchAddedLines records positions from the unified=0 hunk headers; the stamp_paths stage rewrites by position, so a base line with the same text stays and a CRLF checkout still finds the branch's row. - Journal recovery restores the equal-base provenance (no branch stamp) so a stamp interrupted after VERSION was written retries as a stamp, not noop. - Skipped detail names the explicit version it searched for; --was help line names the CHANGELOG re-heading; docs and CHANGELOG state the boundaries, the fork-point attribution and the rule's false-positive class. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(restamp): review pass 2 — positions counted through joined-hunk context parseUnifiedDiff records each added line's new-side position (addedAt), counting context lines a hunk carries, and branchAddedLines pins --inter-hunk-context=0, so a diff.interHunkContext setting that joins two hunks around a base row no longer shifts the branch's second row onto the base row. Test with interHunkContext=1 (red on the pass-1 tree). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(restamp): correct the red-case count, the --was sentence and the help default 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]
|
6c5b2d4612 |
v1.91.260.0 feat(design-review,plan-design-review): craft audit and Persuade plan checks; craft tells as checker-only catalog entries (GSTA-92 phase 2) (#3433)
* feat(design-html): craft section and free craft check, adapted from Elaya design skills (GSTA-92) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(GSTA-92): restore the full CHANGELOG under the Unreleased entry; drop a $-digit literal from craft.md; count only craft-check executions in design-html-slop-gate Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(design-shotgun,design-html): carry the chosen archetype into approved.json; persist accepted craft exceptions in finalized.json (GSTA-92 phase 2) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(design-review,plan-design-review): craft audit carved on every host, Persuade plan checks, craft tells as catalog entries (GSTA-92 phase 2) Size pins and caps raised to measured sizes only: design-review (13 hosts), plan-design-review (12), design-consultation (9), design-consultation maxSizeRatio, and the new design-review parity guard. Garry 2026-10-25 "Do it" (GSTA-92). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * refactor(design-catalog): craft tells are checker-only entries; trim design-review and plan-design-review growth to the planned size (GSTA-92) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(touchfiles): design-html-slop-gate selects on the craft check it runs (GSTA-92) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(touchfiles): design-review and plan-design-review cases select on the craft resolver; slop gate on the catalog (GSTA-92) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(placeholders): allow the craft audit page path placeholder (GSTA-92) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (GSTA-92) A malformed or missing --accepted exceptions file now gets the full craft check with nothing accepted, after a warning, still exiting 2. Before, it printed nothing, and the craft section treats a missing CRAFT_RESULT as 'check unavailable', so one bad finalized.json switched the gate off (found by both adversarial passes). The header comment and the craft section now document the accepted-count suffix on CRAFT_RESULT. Tests cover duplicate carried-forward exception ids and the slop-gate touchfiles selection. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: scope --accepted to the same page; record current counts (GSTA-92) The craft section passed --accepted whenever a finalized.json sat beside the page, so a same-day Start fresh build inherited the old page's exceptions. It now passes them only when evolving or rerunning a page it finalized, records the count the check reports now, and writes [] when nothing was accepted instead of the template's placeholder entry. A test pins exit 2 for a clean page with a broken exceptions file. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: note the archetype handoff in the shotgun and design-html loops (GSTA-92) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: craft audit capture, exceptions and trigger from /ship review (GSTA-92) - craft-audit: no CRAFT_RESULT line means unavailable (exit 2 after a malformed --accepted record still printed findings); --accepted only for a /design-html finalized page, never for needs-proof or lorem; never add [Needs proof] markers to a live page; Aside capture via pg.evaluate; the saved raw DOM is deleted in the checking block and never reported - manifest trigger covers an explicit craft audit (skeleton -6 bytes; pins lowered to measured size, union ratio back under its cap) - autoFixEntries reads RENDERED; DESIGN_CRAFT_RULE needs exactly one lead - tests: checkerOnly contract, resolver throw paths, Persuade checks in both skills, resolver touchfile selection, exception state cells - CHANGELOG: host counts and the audit's new rules Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: craft audit live-page limits, claim handling and guards (GSTA-92) - craft-audit: linked CSS/JS is unchecked on a saved page (judge by eye); a mount-node shell is framework source; --accepted takes that screen's finalized.json or none; on a live page a claim without proof is filed and asked about, never marked or cut; the saved page is removed whatever the exit code; shorter fix-order and Tailwind prose keeps the union under cap - tests: exact-lead red cases, autoFixEntries in the checkerOnly union, the audit's outcome/exception/session-data clauses; carve guard checks the session-data rule and records measured sizes (skeleton cap 137_767) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: craft check skips mount-node shells and script bodies; audit capture order (GSTA-92) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * revert: craft checker back to bed645a's reviewed behavior; textless mount-node shell judged by eye (GSTA-92) cycle-cap exception (GSTA-92 lane, 2026-10-25): reverted 216987e's checker half to bed645a's reviewed behavior; byte-neutral prose reword; no new logic Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: craft audit judges any mount-node shell by eye; pin the clause (GSTA-92) second cycle-cap exception: GStack Minder's decision under Garry's 'do it' on phase 2 (GSTA-92, 2026-10-25): one deleted word plus one test Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: craft resolver placeholders, carved-on-every-host list, design-craft resolver (GSTA-92 /ship docs audit) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes after main merge: claim rule covers repo files, craft temp var, guard tests (GSTA-92) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: craft audit files failed Persuade checks as deferred High, judges source tells by eye; stderr pin (GSTA-92) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(design-review): never cut a claim a rule or printed fix says to drop Pass R3 (native adversarial, Medium): the CRAFT_CHECK fix text for round-number and needs-proof says to drop or remove the claim, which could lead Phase 8 to delete a real claim. The audit sentence now covers both a rule and the printed fix: defer the claim and ask for the proof. Byte-neutral (80 -> 80); design-review/SKILL.md 137,767, union 145,037, unchanged. The test pin moves with the sentence; no carve-guard mustContain held this sentence. third cycle-cap exception (Captain, 2026-10-26): zero-byte reword closing the content-deletion path; test pin and carve-guard mustContain moved Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * design-craft: reconcile ids with the design lint (layout-transition is static-tier; legacy transition-all exceptions map to it) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --------- Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> |
||
|
Garry Tanandcapy-ai[bot]
|
737ba3af40 |
v1.91.259.0 feat(ubicloud): /ubicloud skill with TTL-named VMs and a reaper, quota preflight, hang watchdog and one committed verify entry point (#3482)
* feat(ubicloud): /ubicloud skill with TTL-named VMs and a reaper, quota preflight, hang watchdog and one committed verify entry point
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: CLAUDE.md names the ratcheted catalog ceiling
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* ubicloud: UBI_OWNER example is a literal value, not a free-text placeholder (INV-3 fence lint)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* ubicloud: the UBI_OWNER example is a neutral value (no thread codes in product prose)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* ubicloud: verify trusts the checkout only, watched commands keep stdin and end the remote session, quota and reap outcomes
verify: .gstack/ubicloud.json is repository content, so its setup script and
pull destinations must resolve inside --src (absolute, ~ and .. refused before
any API call) and a name it lists under pass is forwarded only when the command
line grants it (--pass NAME or --trust-config); --pass never forwards UBICLOUD_*
and refuses non-names. watched: the caller's stdin reaches the remote command,
a command that finished while the clock was read is not a timeout, a hung setup
exits 124, INT/TERM take the ssh session down, and the watchdog ends the
command's session on the VM (setsid + ~/.ubirun-<phase>.sid + pkill -s). Quota:
a cached refusal maximum is trusted for a day, the refusal names its source and
uses the 'vCPU quota exhausted' marker pregate-remote.sh retries on. reap:
returns 1 on a failed list or destroy; TTL suffixes read in base 10 and
UBI_TTL_HOURS takes 0-999. Tests: a fake API that creates plus a fake ssh run
'run' and 'verify' end to end.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* ubicloud: the remote session file is per runner invocation and setsid is optional on the image
Two watched commands on one VM wrote the same ~/.ubirun-<phase>.sid, so a cancel
could end the other's session; the file now carries the runner's pid and is
removed when the command ends. An image without setsid runs the command through
plain bash instead of failing with exit 127.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* ubicloud: pull destinations are rechecked at pull time, verify parses options by arity, a finished command keeps its status, the remote sid outlives the wrapper; docs audit
Pass-2 (Codex adversarial on the delta): an earlier pull could plant a symlink
where a later config pull lands, so under verify every destination is resolved
again (symlinks followed) right before its pull and a refused pull exits 1;
'--dest --trust-config' made an option value act as the trust flag, so verify
parses by arity; a command that finished in the instant before the watchdog's
kill exited 0 and was still reported as 124; the wrapper removed the sid file
while a background child kept the channel open, so the file now stays until
remote_cancel reads it. Docs audit (document-release, edit mode): TTL suffix and
owner rule in TESTING_INTERNALS, the reaper as the exception to 'no sweep', the
docs/skills.md transcript uses a neutral owner; CHANGELOG and the runner header
corrected on the two points it deferred.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* ubicloud: a refused pull destination creates no directory, inside or outside the checkout
inside_dir checked containment after mkdir -p, so a destination under a planted
symlink (escape/new/sub) created the outside directories before being refused.
The nearest existing ancestor is checked first; only an accepted destination is
created, and it is checked again after.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: bin/gstack-ubi has a test lane (it execs the runner and forwards arguments)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* ubicloud: pack ships a linked worktree with a self-contained .git
A worktree's .git is a gitdir pointer into the main repository; on the VM git
could not run, so the remote pregate refused with PREGATE_VM_TREE_MISMATCH
vm=unavailable. pack now replaces it with a bare --single-branch clone of the
checked-out branch (core.bare false, the worktree's index copied in), ~45 MB for
gstack; a detached worktree is refused with the fix named.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: take main's host-conformance C3 fix (#3479) so the remote gate can run on this tree
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* ubicloud: pack skips a split index (its shared half stays in the original git dir)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* CHANGELOG: restore main's released history under the [Unreleased] block (the merge resolution kept only the conflicted span)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* RESTAMP: 1.91.258.0 -> 1.91.259.0 (stamped; queue_mode=stamp-at-merge base=origin/main@7dc2f23192b7 policy=base origin/main@7dc2f23192b7:.gstack/ship-policy.json)
ship, next in queue at 1.91.259.0
STAMP_VERSION: 1.91.259.0
claims: ignored (stamp-at-merge)
stage version: done (wrote 1.91.259.0)
stage release_tool: done (bun scripts/gen-agents-digest.ts)
stage changelog: done (Unreleased -> 1.91.259.0)
stage stamp_paths: skipped (no stamp_paths in policy)
stage mirror: skipped (no mirror in policy)
stage apply: done (4 file(s))
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 3c91fdaf8..e4f4d63ec 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,6 +1,6 @@
# Changelog
-## [Unreleased]
+## [1.91.259.0] - 2026-10-26
**New `/ubicloud` skill: the Ubicloud runner moves into gstack with the discipline a shared vCPU quota needs.** Crews ran heavy suites on Ubicloud through a user-scope skill and per-lane wrappers, and paid for it in stray VMs after a machine slept, a project quota at 528 of 512 vCPUs when lanes verified in parallel, verifies that hung for an hour before anyone noticed, and a stale wrapper that skipped a service start. `scripts/ubicloud/ubi-runner.sh` now carries the fixes and `ubicloud/SKILL.md` (entry point `bin/gstack-ubi`) teaches the watched launch; `bun run test:ubicloud` and the remote pregate are unchanged.
diff --git a/VERSION b/VERSION
index c67e9e442..08528ff87 100644
--- a/VERSION
+++ b/VERSION
@@ -1 +1 @@
-1.91.258.0
+1.91.259.0
diff --git a/agents-digest/gstack-AGENTS.md b/agents-digest/gstack-AGENTS.md
index 4bd43c922..203312cf5 100644
--- a/agents-digest/gstack-AGENTS.md
+++ b/agents-digest/gstack-AGENTS.md
@@ -1,4 +1,4 @@
-# gstack digest v1.91.258.0 — regenerate/re-copy after upgrading gstack
+# gstack digest v1.91.259.0 — regenerate/re-copy after upgrading gstack
Behavioral rules from gstack (https://github.com/garrytan/gstack), compressed
for agent hosts without a full skill install. The full skills add workflows,
diff --git a/node_modules b/node_modules
new file mode 120000
index 000000000..c7990ad12
--- /dev/null
+++ b/node_modules
@@ -0,0 +1 @@
+/workspace/gstack-ubi/node_modules
\ No newline at end of file
diff --git a/package.json b/package.json
index 5e6d56827..0eca459a0 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
{
"name": "gstack",
- "version": "1.91.258",
+ "version": "1.91.259",
"description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.",
"license": "MIT",
"type": "module",
FILES: CHANGELOG.md VERSION agents-digest/gstack-AGENTS.md package.json
MERGE_CONDITION: sha=76e86e08a851fb1a19bef9a947bdf0abeb87956d
next: NEW_VERSION=1.91.259.0; commit and push only the stamp diff above (FILES), with no edit of your own: the train's verify accepts the CHANGELOG only as the base's plus this PR's entry re-headed; merge with the expected head
|
||
|
Garry Tanandcapy-ai[bot]
|
7dc2f23192 |
v1.91.258.0 feat(capy-install): project floor, --for none, WARN for behind and Node-only pins, in-place review-voice upgrade, /cso env hygiene (GSTA-114 lane F, PR 1) (#3475)
* feat(capy-install): project floor, --for none, WARN for behind and Node-only pins, in-place review-voice upgrade, /cso env hygiene (harness lane F)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* cso: tighten the env-hygiene and tooling-error paragraphs so the controller template stays under the 18,000-byte compactness bound
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* capy skill: name the fail heads once and describe the WARN behind outcome consistently
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* doctor: name the floor field PROJECT_FLOOR_FIELD (it is a JSON field name, not a key)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes
Red team (/ship Step 9): a Drive copy at a bootstrapper revision below GSTACK_CAPY_MIN_WRAPPER is a WARN with the owner action in a direct (no-provenance) run too; only a pre-bootstrapper copy fails. A --for none session never self-upgrades. Stale fail-behind comment in gstack-capy-session; SKILL.md says ok not-needed is not an install verdict. Tests: UPGRADE_SKIPPED collapse, silent in-place message, direct-run WARN, wrapper-2 --for none handover.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: adversarial review fixes
Trailer fix after a skipped upgrade is one runnable command (the refusal prose stays on the WARN behind row); the floor reader is whitespace-insensitive and names a non-version value instead of calling it absent. Found by /ship Step 11 (Claude adversarial, Codex adversarial + structured).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: review pass 2 fixes (floor reader bounds, cso start is resumed not retried)
The floor reader reads only the first 64 KiB, takes the first occurrence of the field (the top-level one) and names a non-version string truthfully; /cso resumes a start whose ID never printed instead of retrying it (a run may already exist). Found by /ship pass 2 (Claude adversarial, Codex adversarial + structured).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: the floor evaluation marker lives in the fixture, not /tmp
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: take main's host-conformance C3 fix (#3479) so the remote gate can run on this tree
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* RESTAMP: 1.91.257.0 -> 1.91.258.0 (stamped; queue_mode=stamp-at-merge base=origin/main@7f53ddb1f3cc policy=base origin/main@7f53ddb1f3cc:.gstack/ship-policy.json)
ship, next in queue at 1.91.258.0
STAMP_VERSION: 1.91.258.0
claims: ignored (stamp-at-merge)
stage version: done (wrote 1.91.258.0)
stage release_tool: done (bun scripts/gen-agents-digest.ts)
stage changelog: done (Unreleased -> 1.91.258.0)
stage stamp_paths: skipped (no stamp_paths in policy)
stage mirror: skipped (no mirror in policy)
stage apply: done (4 file(s))
FILES: CHANGELOG.md VERSION agents-digest/gstack-AGENTS.md package.json
MERGE_CONDITION: sha=831ac3c3cb3077f16b2f1a7802297523a2db1349
next: NEW_VERSION=1.91.258.0; commit and push only the stamp diff above (FILES), with no edit of your own: the train's verify accepts the CHANGELOG only as the base's plus this PR's entry re-headed; merge with the expected head
|
||
|
Garry Tanandcapy-ai[bot]
|
7f53ddb1f3 |
v1.91.257.0 feat(pregate): clear --receipt accepts a remote_gate receipt from a stamp-only predecessor tree (gbrain gate-ahead) (#3486)
* feat(pregate): clear --receipt accepts a remote_gate receipt from a stamp-only predecessor tree (gbrain gate-ahead) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (hex object ids, stamp_sensitive_gates and base-branch refusals, one substitution type, docs) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(pregate): harden the stamp-only diff read (fixed presentation, diff-tree reconciliation), refuse an unreadable base policy, check the receipt before git work, bind verify to the receipt tree; docs audit corrections Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(pregate): the stamp-only suite expects the Linux-host lanes verdict; skip itself on win32 like test/pregate-remote.test.ts 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]
|
576839cb8c |
v1.91.256.0 feat(ship): review loop converges (frozen scope, 3-pass cap, NO FINDINGS) and receipts carry across conflict-only merges (#3481)
* feat(ship): review loop converges (frozen finding scope, 3-pass cap, NO FINDINGS first-class) and receipts carry across conflict-only merges
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(ship): keep the Step 9 first-entry and Fix-First phrasing the skip/requeue contract asserts; fill the review record's pass, review_scope and range_base placeholders in the caller template test; narrow a test type
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes (pass 1) and the review-loop budget wording
Two blocking findings from /ship's own pass 1, both reproduced in the QA smoke before the fix:
gstack-ship-receipt carry hashed the product diff with git patch-id --stable, which strips
whitespace, so a space moved in a reviewed shell line carried as "no product change"; and it
classed package.json and every lockfile as release metadata, so a dependency swap carried too.
The patch-id is now --verbatim, package.json and VERSION are metadata only while the change is a
version stamp (lib/pregate/stamp-only.ts), lockfiles are product unless the policy names them,
the test globs name code extensions, a dirty working tree refuses before anything is compared,
and a receipt carried twice keeps the reviewed head as carry.from.
gstack-review-scope: an unresolvable base is POLICY_SOURCE_UNAVAILABLE instead of a silent
working-tree read; --range-base is validated; git runs with core.quotePath=false; range_base is
null on pass 1; a blocking finding with no path is fix; category "testing" is a test finding
below the floor; defer searches once, files nothing on a failed search and exits 0 unfiled;
summary refuses zero matching passes and the receipt write is chained to it with &&; a finding
the diff causes elsewhere names the changed line in `cause` and classify follows it.
Review-loop budget wording (ideas from tstack's sol-loop and pstack's interrogate, rewritten;
NOTICE.md): the blocker / should / nit glossary and two stop rules in Step 9.4, the checklist
and docs/review-policy.md; a lead-judgment stage in the finding merge both /review and /ship
render. The core read diffs $RANGE_BASE from pass 2 on. Caps and pins re-measured with reasons.
Step 7 coverage audit: four tests added in existing files, the --review-loop case moved to its
own test (the shared test tripped bun's 5 s default).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pin the renumbered review-army stages and point the wording test at product code
CI at
|
||
|
Garry Tanandcapy-ai[bot]
|
b004c06dbc |
v1.91.255.0 fix(ship-queue): fill trains at 3 READY PRs or one hour, and price every case shard's trial (#3478)
* fix(ship-queue): fill trains at 3 READY PRs or one hour, and price every case shard's trial
The 5-PR / 3-hour fill left READY PRs waiting most of a day; .gstack/ship-policy.json
now fills at max_size 3 or fill_hours 1, whichever comes first (fillDue already
dispatches at either bound). train verdict printed cost=$24.41 for a train whose slice
report said cost $32.92 known + 54 of 136 trial(s) cost unknown: E2E records named by a
display label ("/benchmark workflow") were never attributed to their case id, so the
per-case sum was short. A case shard's records now belong to its one case; a multi-case
shard with display-labelled records keeps those trials unknown. The ATTEMPT: line names
how many cases have no cost instead of printing a partial sum as the total.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(ci): record the paid-report.ts harness decision and keep ship-queue-train-cost.test.ts off the Windows subset
scripts/lib/paid-report.ts is a pinned shared-harness file, so test/harness-version.test.ts wants a HARNESS_VERSION decision for its edit: non-behavioral, because a case shard's records are attributed to its one case for the trial's cost, class and error fields while no case's outcome, panel verdict or selection changes.
test/ship-queue-train-cost.test.ts drives bin/gstack-ship-queue against the #!/bin/sh gh shim, which windows-latest cannot run (windows-free-shard 2 on #3478 at
|
||
|
Garry Tanandcapy-ai[bot]
|
568cd5aa56 |
v1.91.254.0 pregate: starter policy, benign-finding allowlist, environment vs diff failures, per-run scratch (#3480)
* pregate: starter policy, benign-finding allowlist, environment failures, per-run scratch
A repository with no .gstack/pregate.json now gets a warn (PREGATE_NO_POLICY)
with a starter policy printed, instead of PREGATE_NO_LANE on every touched
file; gstack-pregate init remains the explicit write. The policy gains an
allowlist for benign secrets/pii findings (env.value and secret never
allowlistable). Checks that cannot run because of the machine report
PREGATE_ENVIRONMENT (incomplete, with kind and evidence) apart from diff
failures. Every run writes its scratch under the state root, per run id.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* pregate: rename run-scratch module (strays rule) and map starter.ts to its test
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* pregate literals: match a module as a path fragment, require the constant name for a one-character value
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes
guards: an exited guard is the machine's only on exit 127, never from its output;
secrets: clear an interrupted run's added-line copies before scanning;
environment: one fix table per kind, one ANSI strip, hoisted not-found vocabulary;
starter returns its lines; allowlistDigest reuses sha256; stale headers and the
PREGATE_INCOMPLETE fix clause updated; tests for the mixed verify branch, disk
precedence, allowlist boundaries, a positionless finding, head-policy strictness,
run-id edges and the unwritable state root.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* pregate: count a module's full file name without a directory as a consumer
consumersOf anchored both the stem and the full basename on a path
separator, so run('install.sh') or bash install.sh without a directory
stopped counting for a multi-character old value. Only the bare stem
needs the separator; the full file name is specific on its own.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* pregate: a diff cannot clear itself as an environment failure; a taken --run id gets its own directory
Adversarial review of the environment classifier and the scratch layout:
- exit 127 and 'command not found' are missing-binary only when the
command's own binary is off PATH (runner, guard and remote gate alike);
a script the diff controls that exits 127 is the diff's failure
- a local lane with no test summary is classified from its output only
when the runner was not seen starting a test file; a remote gate only
from its first 40 lines, before any test output could stream
- environment.proof records launch (certain) or output (inferred); an
output-inferred cause never says 'the diff is not at fault', its line
says '(inferred from output)', and verify names such checks
- a runner killed by a signal is PREGATE_INCOMPLETE, not missing-binary
- a --run id whose directory exists takes <id>-2 .. -9 instead of
sharing (and truncating) a live run's logs
- engine.* findings are never allowlistable; a pattern entry the scanner
gave no position for is reported as not tested instead of silently inert
- docs: synopsis --run, no-policy lanes wording, verify's code list,
guard exit 127 carve-out, PREGATE_SECRETS allowlist pointer, scratch
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(pregate): PREGATE_INCOMPLETE names a signal-killed runner; CHANGELOG lists every doc edit
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>
|