Garry Tanandcapy-ai[bot] 781f928ccf test: remove the AI scorer that grades skill prose for clarity (freeze repair, GST-1371) (#4009) ...

* test: remove the skill-prose clarity LLM judges (GST-1371)

Removes the 21 eval cases where an LLM scored a skill's instruction text for
clarity, completeness and actionability, with their registrations, input
builders, response cache, calibration corpora, the cookie-workflow manual-review
approval and scripts/judge-controls.ts. The three remaining skill-llm-eval
judges keep their prompts, thresholds and samples; the file's supervision wall
shrinks to fit them. Outcome judges are untouched.

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

* test: pin the retired judge-control script and cookie manual-review record as deleted (GST-1371)

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

* test: register the manual-review fixture as free (GST-1371)

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

* test: keep the orphaned clarity-judge calibration corpora for a follow-up deletion (GST-1371)

Deleting the four corpus directories alone puts the diff over the /ship review
ceiling; they serve no configuration now and go in a follow-up.

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

* docs(todos): file the clarity-judge removal follow-ups (GST-1371)

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

* test: keep skill-bundle section paths POSIX so references dedupe on Windows (GST-1371)

windows-scoped-shard (run 41918796523) failed 'cross-skill references retain
complete bytes once': path.join gave the section entry a backslash path, so a
reference to the same section was not recognized as already bundled.

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

---------

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

2026-11-04 22:19:08 +00:00

..

providers

v1.91.352.0 feat(benchmark): particle-1 awareness, OpenRouter gateway provider, preregistered model panel (GSTA-173) (#3631)

2026-10-31 05:53:14 +00:00

pty

v1.93.10.0 wave(docs): #3590 #3591 #3819 #3618 #3824 #3828 (#3847)

2026-11-02 17:44:00 +00:00

agent-sdk-runner.ts

v1.93.10.0 wave(docs): #3590 #3591 #3819 #3618 #3824 #3828 (#3847)

2026-11-02 17:44:00 +00:00

anthropic-preflight.ts

v1.91.149.0 feat(evals): Codex host for gate cases, sol weekly and Fable/Astra monthly census arms (GSTA-49 TM2) (#3292)

2026-10-19 18:26:20 +00:00

arm-benchmark-harness.ts

v1.92.2.0 evals: no-gstack arms for the model panel, arm-benchmark, safety and routing evals (#3708)

2026-10-31 22:41:36 +00:00

arm-pair-judge.ts

v1.92.2.0 evals: no-gstack arms for the model panel, arm-benchmark, safety and routing evals (#3708)

2026-10-31 22:41:36 +00:00

aside-available.ts

v1.81.0.0 feat: Aside is the browser gstack drives first; every browsing skill, the PDF/diagram renderer, and web research; the bundled browser stays the automatic fallback (#2810)

2026-09-06 08:54:25 -07:00

auq-native-capture.ts

v1.93.10.0 wave(docs): #3590 #3591 #3819 #3618 #3824 #3828 (#3847)

2026-11-02 17:44:00 +00:00

auq-parallel-worker.ts

v1.90.2.0 perf: halve local free-suite time and preserve coverage (#2972)

2026-09-25 13:27:07 -04:00

auq-sdk-capture.ts

v1.91.276.0 feat(preamble): tier 2+ skills load the shared preamble once per session (GSTA-96) (#3434)

2026-10-27 13:28:18 +00:00

auq-substance-panel.ts

v1.91.30.0 fix: honest eval failure reports, Bun floor with safe auto-update, make-pdf and /review on Codex (#3033)

2026-10-06 18:07:50 +00:00

auto-decision-state.ts

v1.87.6.0 fix: make checks reliable and everyday validation faster (#2898)

2026-09-22 14:57:52 -04:00

autoplan-artifact-digest.ts

v1.91.8.0 test: smaller suite, derived paid selection, retired never-green evals (#2994)

2026-09-29 08:58:49 -07:00

autoplan-artifact-permission.ts

v1.91.8.0 test: smaller suite, derived paid selection, retired never-green evals (#2994)

2026-09-29 08:58:49 -07:00

autoplan-artifact-recorder.ts

v1.87.6.0 fix: make checks reliable and everyday validation faster (#2898)

2026-09-22 14:57:52 -04:00

autoplan-capy.ts

v1.93.36.0 autoplan: R65 defaults: no review for bug fixes, one lean reviewer with the draft code for features (#3897)

2026-11-03 02:08:50 +00:00

autoplan-ceo-only-evidence.ts

v1.92.50.0 wave(autoplan): #3781 #3743 #3751 #3762 (#3788)

2026-11-02 01:35:47 +00:00

autoplan-dual-voice-evidence.ts

v1.91.92.0 feat(outside-voice): enforce codex_reviews consent in the send binaries, codex_effort setting, privacy disclosures (Wave 9 Lane C) (#3144)

2026-10-11 19:09:12 +00:00

autoplan-guard-fixture.ts

v1.91.66.0 fix: /autoplan without permission prompts after background reviewers, 34 contributor PRs from the backlog triage (#3087)

2026-10-08 17:40:06 +00:00

autoplan-guard-pty.ts

v1.94.34.0 test(flaky): autoplan-guard-pty dispatch token relay; plan-design Voices menu accepts both bullet spellings (#3953)

2026-11-03 19:02:06 +00:00

autoplan-method-read-audit.ts

v1.87.6.0 fix: make checks reliable and everyday validation faster (#2898)

2026-09-22 14:57:52 -04:00

autoplan-phase-observer.ts

v1.87.6.0 fix: make checks reliable and everyday validation faster (#2898)

2026-09-22 14:57:52 -04:00

autoplan-preconfigured-fixture.ts

feat(hosts): /land-and-deploy and /modernize run only when typed on Claude Code and Cursor (C1) (#3808)

2026-11-04 03:33:48 +00:00

autoplan-run-fixture.ts

v1.92.50.0 wave(autoplan): #3781 #3743 #3751 #3762 (#3788)

2026-11-02 01:35:47 +00:00

bash-script.ts

v1.80.0.0 fix: setup survives a failed Chromium install, hooks share one state root, gstack never clobbers a skill it did not create (#2802)

2026-09-05 14:45:28 -07:00

benchmark-judge.ts

v1.84.1.0 fix: default Codex and Claude to frontier models (#2835)

2026-09-09 08:57:21 -07:00

benchmark-runner.ts

v1.91.352.0 feat(benchmark): particle-1 awareness, OpenRouter gateway provider, preregistered model panel (GSTA-173) (#3631)

2026-10-31 05:53:14 +00:00

bootstrap-retention.ts

v1.91.7.0 feat: add functional QA and pre-publication docs checks (#2983)

2026-09-29 06:07:35 -07:00

browser-available.ts

v1.91.18.0 feat: Opus 5.5 cleanup follow-ups — scoped transcript consent, opt-in Claude overlay, safety-rule evals, calibrated judges (#3023)

2026-10-03 18:49:34 -07:00

budget-override.test.ts

v1.91.24.0 test: audit wave — PR evals keep finished work, honest ceilings, EVAL_POLICY v2, faster free suite (#3031)

2026-10-05 01:29:54 +00:00

budget-override.ts

v1.46.0.0 feat: gstack v2 foundation — catalog tokens drop 56%, eval-first floor covers all 51 skills (#1712)

2026-05-26 16:50:03 -07:00

capture-context-budget.ts

v1.71.0.0 feat: token-load reduction — preamble runtime scripts, gated onboarding, 20 skill carves, CLAUDE.md trim (#2691)

2026-08-27 09:50:31 -07:00

capture-parity-baseline.test.ts

v1.46.0.0 feat: gstack v2 foundation — catalog tokens drop 56%, eval-first floor covers all 51 skills (#1712)

2026-05-26 16:50:03 -07:00

capture-parity-baseline.ts

v1.77.0.0 feat: test-infrastructure overhaul wave 1 — matrix deletion, flake telemetry, sync-spawn wedge class extinct (#2746)

2026-08-31 08:55:30 -07:00

capy-host.ts

v1.91.101.0 fix: close the field wave's residual gaps (#3173)

2026-10-14 17:36:39 +00:00

carve-guard-checks.ts

v1.57.0.0 feat: carve-guard system + carve cso/document-release/design-consultation (#1907)

2026-06-07 19:13:24 -07:00

carve-guards.ts

v1.94.35.0 fix(contracts): run gstack-skill-contract through the host-resolved bin path (GST-1088 lane B follow-up) (#3957)

2026-11-03 19:39:32 +00:00

carve-plan-fixture.ts

v1.87.6.0 fix: make checks reliable and everyday validation faster (#2898)

2026-09-22 14:57:52 -04:00

carve-section-case.ts

v1.91.24.0 test: audit wave — PR evals keep finished work, honest ceilings, EVAL_POLICY v2, faster free suite (#3031)

2026-10-05 01:29:54 +00:00

ceo-finding-fixture.ts

v1.91.19.0 fix: severe fix wave (truthful gates, no lost memory, every host finds gstack) (#3025)

2026-10-04 07:58:41 -07:00

ceo-hold-posture-review.ts

v1.91.12.0 v1.91.12.0: audit fix wave, ~11-minute paid eval lanes, eval reliability policy (#2999)

2026-10-01 13:55:16 -07:00

ceo-mode-option.ts

v1.91.19.0 fix: severe fix wave (truthful gates, no lost memory, every host finds gstack) (#3025)

2026-10-04 07:58:41 -07:00

ceo-section-loading-fixture.ts

v1.91.12.0 v1.91.12.0: audit fix wave, ~11-minute paid eval lanes, eval reliability policy (#2999)

2026-10-01 13:55:16 -07:00

ceo-split-question-policy.ts

v1.91.30.0 fix: honest eval failure reports, Bun floor with safe auto-update, make-pdf and /review on Codex (#3033)

2026-10-06 18:07:50 +00:00

ceo-stale-fill-decision.ts

v1.91.30.0 fix: honest eval failure reports, Bun floor with safe auto-update, make-pdf and /review on Codex (#3033)

2026-10-06 18:07:50 +00:00

claude-overlay-fixture.ts

v1.91.276.0 feat(preamble): tier 2+ skills load the shared preamble once per session (GSTA-96) (#3434)

2026-10-27 13:28:18 +00:00

claude-pty-runner.auq.unit.test.ts

v1.91.11.0 refactor: one state-root rule, browse route table, shared shard engine, PTY harness split, MECE review resolvers (#3002)

2026-10-01 11:57:48 -07:00

claude-pty-runner.boundaries.unit.test.ts

v1.91.185.0 fix(evals): plan-design focus rating in plain words, docsync own-call rule where --help is named, floor Create crop and 0D menu (GSTA-65) (#3358)

2026-10-23 18:35:59 +00:00

claude-pty-runner.classify.unit.test.ts

v1.91.11.0 refactor: one state-root rule, browse route table, shared shard engine, PTY harness split, MECE review resolvers (#3002)

2026-10-01 11:57:48 -07:00

claude-pty-runner.launch.unit.test.ts

v1.93.10.0 wave(docs): #3590 #3591 #3819 #3618 #3824 #3828 (#3847)

2026-11-02 17:44:00 +00:00

claude-pty-runner.plan-native.unit.test.ts

v1.91.11.0 refactor: one state-root rule, browse route table, shared shard engine, PTY harness split, MECE review resolvers (#3002)

2026-10-01 11:57:48 -07:00

claude-pty-runner.runners.unit.test.ts

v1.92.32.0 fix(flaky): Windows hook kill, publication-gates deadline, xvfb marker, devex floor idle API error (2026-10-29 flaky pass, GSTA-162) (#3607)

2026-11-01 15:47:35 +00:00

claude-pty-runner.scope-gate-floor.unit.test.ts

v1.87.6.0 fix: make checks reliable and everyday validation faster (#2898)

2026-09-22 14:57:52 -04:00

claude-pty-runner.screen.unit.test.ts

v1.92.32.0 fix(flaky): Windows hook kill, publication-gates deadline, xvfb marker, devex floor idle API error (2026-10-29 flaky pass, GSTA-162) (#3607)

2026-11-01 15:47:35 +00:00

claude-pty-runner.ts

v1.91.185.0 fix(evals): plan-design focus rating in plain words, docsync own-call rule where --help is named, floor Create crop and 0D menu (GSTA-65) (#3358)

2026-10-23 18:35:59 +00:00

codex-boundary-evidence.ts

v1.91.18.0 feat: Opus 5.5 cleanup follow-ups — scoped transcript consent, opt-in Claude overlay, safety-rule evals, calibrated judges (#3023)

2026-10-03 18:49:34 -07:00

codex-eval.ts

v1.91.149.0 feat(evals): Codex host for gate cases, sol weekly and Fable/Astra monthly census arms (GSTA-49 TM2) (#3292)

2026-10-19 18:26:20 +00:00

codex-host-runner.ts

v1.91.149.0 feat(evals): Codex host for gate cases, sol weekly and Fable/Astra monthly census arms (GSTA-49 TM2) (#3292)

2026-10-19 18:26:20 +00:00

codex-multiblock.ts

v1.91.30.0 fix: honest eval failure reports, Bun floor with safe auto-update, make-pdf and /review on Codex (#3033)

2026-10-06 18:07:50 +00:00

codex-probe-sourcing.ts

v1.91.34.0 fix: /autoplan on current Claude Code and long sessions, quieter pre-push and sync guards, gstack-post, gstack-doctor (#3069)

2026-10-07 23:29:05 +00:00

codex-session-runner.ts

v1.91.149.0 feat(evals): Codex host for gate cases, sol weekly and Fable/Astra monthly census arms (GSTA-49 TM2) (#3292)

2026-10-19 18:26:20 +00:00

context-restore-fragment.ts

v1.91.222.0 test: daily flaky-fix pass: qa-only late clock, fragment-match verdict, install-admission timeout, ff-update reap, judge parse diagnostics (GSTA-91) (#3413)

2026-10-25 23:39:42 +00:00

cookie-workflow-manual-review.ts

test: remove the AI scorer that grades skill prose for clarity (freeze repair, GST-1371) (#4009)

2026-11-04 22:19:08 +00:00

coverage-audit-evidence.ts

v1.93.2.0 GSTA-240 follow-up: native cookie cleanup waits for Edge to exit, plus three flaky-test repairs (#3805)

2026-11-02 15:08:48 +00:00

coverage-audit.ts

v1.91.16.0 fix: safe installs and upgrades, skills start everywhere, truthful completion (parallel wave) (#3014)

2026-10-03 07:54:09 -07:00

cso-eval-oracles.ts

v1.91.8.0 test: smaller suite, derived paid selection, retired never-green evals (#2994)

2026-09-29 08:58:49 -07:00

cso-ntfs-fixture.ts

v1.90.0.0 feat: make browser cookie imports explicit and safe (#2964)

2026-09-25 12:06:45 -04:00

cso-qualified-cli.ts

v1.91.29.0 fix(cso): native runtime qualification passes for Node, Bun, Python and Rails (#3044)

2026-10-06 10:32:19 -07:00

cso-runtime-catalog.ts

fix(cso): report a go.mod repository as Go (unsupported), not Python (#3263) (#3378)

2026-10-25 07:03:51 +00:00

disabled-plan-review-fixture.ts

v1.91.15.0 v1.91.15.0: Opus 5.5 prompt cleanup, behavior-level skill tests, transcript consent (#3017)

2026-10-03 01:19:03 -07:00

docsync-contract.ts

v1.93.2.0 GSTA-240 follow-up: native cookie cleanup waits for Edge to exit, plus three flaky-test repairs (#3805)

2026-11-02 15:08:48 +00:00

docsync-fault-actor.ts

v1.91.179.0 test(docsync): cut per-case spawn cost in the fault interface and split its outer run (flaky pass 2026-10-22) (#3342)

2026-10-22 20:10:23 +00:00

docsync-fault-callbacks.ts

v1.94.42.0 test: red-team retry, docsync replay and plan-seed fixture hold up on loaded runners (GSTA-262) (#3954)

2026-11-03 22:44:59 +00:00

docsync-fault-eval.ts

v1.91.169.0 fix(evals): docs-sync fixture accepts joined Git reads, literal loops and tr pipes; late-result says what its repair fixes (GSTA-57) (#3325)

2026-10-20 18:45:38 +00:00

docsync-fixture.ts

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)

2026-10-27 08:16:11 +00:00

docsync-interface.ts

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)

2026-10-28 19:09:45 +00:00

docsync-observer.ts

v1.92.31.0 fix(flaky): qa-callers child handoff and three ship-docsync detector gaps (2026-10-29 flaky pass, GSTA-162) (#3606)

2026-11-01 15:32:09 +00:00

docsync-repo.ts

v1.91.179.0 test(docsync): cut per-case spawn cost in the fault interface and split its outer run (flaky pass 2026-10-22) (#3342)

2026-10-22 20:10:23 +00:00

doctor-fixture.ts

v1.93.0.0 wave(browse): #3700 #3773 #3779 #3817 #3842 (#3858)

2026-11-02 14:49:46 +00:00

dx-selected-navigation.ts

v1.86.0.0 feat: route outside reviews by harness (#2850)

2026-09-14 14:32:45 -07:00

e2e-gate.ts

v1.91.24.0 test: audit wave — PR evals keep finished work, honest ceilings, EVAL_POLICY v2, faster free suite (#3031)

2026-10-05 01:29:54 +00:00

e2e-gate.unit.test.ts

v1.91.24.0 test: audit wave — PR evals keep finished work, honest ceilings, EVAL_POLICY v2, faster free suite (#3031)

2026-10-05 01:29:54 +00:00

e2e-helpers.ts

v1.93.10.0 wave(docs): #3590 #3591 #3819 #3618 #3824 #3828 (#3847)

2026-11-02 17:44:00 +00:00

e2e-hosts.ts

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)

2026-10-27 08:16:11 +00:00

emulate-bun-windows-eexist.ts

v1.69.0.0 fix: the silent-failure wave — 6 fixes, 5 community PRs absorbed, tracker closed with receipts (#2666)

2026-08-24 08:55:58 -07:00

eng-cache-writer-decision.ts

v1.91.201.0 fix(confidence): one severity scale, CRITICAL/INFORMATIONAL, for /ship's review army and /plan-eng-review (#3349) (#3402)

2026-10-25 07:15:55 +00:00

eng-seeded-coverage.ts

v1.91.30.0 fix: honest eval failure reports, Bun floor with safe auto-update, make-pdf and /review on Codex (#3033)

2026-10-06 18:07:50 +00:00

eval-budgets.ts

test: remove the AI scorer that grades skill prose for clarity (freeze repair, GST-1371) (#4009)

2026-11-04 22:19:08 +00:00

eval-store.test.ts

v1.91.30.0 fix: honest eval failure reports, Bun floor with safe auto-update, make-pdf and /review on Codex (#3033)

2026-10-06 18:07:50 +00:00

eval-store.ts

v1.93.10.0 wave(docs): #3590 #3591 #3819 #3618 #3824 #3828 (#3847)

2026-11-02 17:44:00 +00:00

exercised-commands.json

v1.91.130.0 feat(pr-selection): exercised-path consumer map in shadow mode, MAP_GAP and census refresh (#3259)

2026-10-18 01:37:29 +00:00

exercised-prototype.ts

v1.91.130.0 feat(pr-selection): exercised-path consumer map in shadow mode, MAP_GAP and census refresh (#3259)

2026-10-18 01:37:29 +00:00

failure-routing-fixture.ts

v1.92.2.0 evals: no-gstack arms for the model panel, arm-benchmark, safety and routing evals (#3708)

2026-10-31 22:41:36 +00:00

fake-bun-cli.ts

v1.86.0.0 feat: route outside reviews by harness (#2850)

2026-09-14 14:32:45 -07:00

fake-gbrain-brain.ts

v1.91.88.0 fix(memory): transcript ingest lands on managed gbrain 0.60, /retro global counts every session (Wave 9 Lane F) (#3136)

2026-10-11 16:33:10 +00:00

fake-gh-runs.ts

v1.94.17.0 ci-carry: guard carry, jobs-mapped lanes, aliases, per-file carry of runner-skipped files, path-skipped jobs (GST-1186, GST-1189, GST-1190) (#3929)

2026-11-03 14:14:50 +00:00

fake-impeccable.ts

v1.91.12.0 v1.91.12.0: audit fix wave, ~11-minute paid eval lanes, eval reliability policy (#2999)

2026-10-01 13:55:16 -07:00

fake-plan-seed.ts

v1.87.6.0 fix: make checks reliable and everyday validation faster (#2898)

2026-09-22 14:57:52 -04:00

free-fixtures-data.ts

test: remove the AI scorer that grades skill prose for clarity (freeze repair, GST-1371) (#4009)

2026-11-04 22:19:08 +00:00

free-owned-browser-settlement.ts

v1.91.349.0 fix(flaky): 2026-10-30 flaky pass — paid detector gaps, QA deadline receipt ack, Chromium WSAENOBUFS backport, free-test races (GSTA-178) (#3646)

2026-10-31 04:53:38 +00:00

fs-caps.ts

v1.72.0.0 feat: Aside recommended driver for third-party web actions (#2710)

2026-08-28 11:43:13 -07:00

gate-diff-repo.ts

feat: honest work and gate integrity — gate-edit detector, review/ship gate pass, zero-run green, claims-need-evidence kernel (#3114)

2026-10-10 22:33:01 +00:00

gate-disposition.ts

v1.91.144.0 feat(evals): Opus 5.5 is the paid gate's model under test; judge stays Fable (GSTA-49 TM1) (#3275)

2026-10-19 07:26:49 +00:00

generated-bash-lint.ts

v1.91.32.0 fix: Codex works from zsh, free text never enters shell commands, honest failures (#3057)

2026-10-06 23:42:19 +00:00

git-env.ts

test(redact): fixture git and hook installs share gitEnv(), so a global core.hooksPath is never rewritten (#3353) (#3384)

2026-10-25 12:14:02 +00:00

git-fixture-template.ts

v1.93.23.0 GSTA-253 flaky pass: plan-design focus header, shared-libs revalidation sources, .capy leak-scan skip, fixture state root (#3878)

2026-11-02 23:05:47 +00:00

health-eval-fixture.ts

v1.91.13.0 fix: severe bug wave (autoplan guard, land-and-deploy CI gate, project identity, gbrain, review gates) (#3013)

2026-10-02 11:11:00 -07:00

hermetic-env.test.ts

v1.91.19.0 fix: severe fix wave (truthful gates, no lost memory, every host finds gstack) (#3025)

2026-10-04 07:58:41 -07:00

hermetic-env.ts

v1.91.101.0 fix: close the field wave's residual gaps (#3173)

2026-10-14 17:36:39 +00:00

hermetic-skill-runtime.ts

v1.87.6.0 fix: make checks reliable and everyday validation faster (#2898)

2026-09-22 14:57:52 -04:00

host-renders-prune-fixture.ts

v1.92.30.0 test(free): split files over the 60 s seed ceiling and the Windows doctor file, then reseed (GSTA-151 A) (#3585)

2026-11-01 14:23:49 +00:00

install-fixture.ts

v1.91.231.0 fix(setup): install production dependencies only (~520 MB smaller install) (GSTA-97) (#3426)

2026-10-26 06:41:22 +00:00

ios-stub-state-server.ts

v1.91.18.0 feat: Opus 5.5 cleanup follow-ups — scoped transcript consent, opt-in Claude overlay, safety-rule evals, calibrated judges (#3023)

2026-10-03 18:49:34 -07:00

journal-padding.ts

v1.91.34.0 fix: /autoplan on current Claude Code and long sessions, quieter pre-push and sync guards, gstack-post, gstack-doctor (#3069)

2026-10-07 23:29:05 +00:00

llm-judge.ts

test: remove the AI scorer that grades skill prose for clarity (freeze repair, GST-1371) (#4009)

2026-11-04 22:19:08 +00:00

manual-judge-review-fixture.ts

test: remove the AI scorer that grades skill prose for clarity (freeze repair, GST-1371) (#4009)

2026-11-04 22:19:08 +00:00

model-panel-harness.ts

v1.92.2.0 evals: no-gstack arms for the model panel, arm-benchmark, safety and routing evals (#3708)

2026-10-31 22:41:36 +00:00

module-size.ts

v1.91.11.0 refactor: one state-root rule, browse route table, shared shard engine, PTY harness split, MECE review resolvers (#3002)

2026-10-01 11:57:48 -07:00

native-auto-decide.ts

v1.91.34.0 fix: /autoplan on current Claude Code and long sessions, quieter pre-push and sync guards, gstack-post, gstack-doctor (#3069)

2026-10-07 23:29:05 +00:00

none-arm.ts

v1.92.2.0 evals: no-gstack arms for the model panel, arm-benchmark, safety and routing evals (#3708)

2026-10-31 22:41:36 +00:00

observability.test.ts

v1.91.24.0 test: audit wave — PR evals keep finished work, honest ceilings, EVAL_POLICY v2, faster free suite (#3031)

2026-10-05 01:29:54 +00:00

office-hours-attempt.ts

v1.91.24.0 test: audit wave — PR evals keep finished work, honest ceilings, EVAL_POLICY v2, faster free suite (#3031)

2026-10-05 01:29:54 +00:00

office-hours-completion.ts

v1.91.156.0 fix(evals): office-hours marathon fixture loads the formatter's imports; validator checks the observed cap fixes (#3246) (#3309)

2026-10-19 21:55:24 +00:00

office-hours-formatter-fixture.ts

v1.91.156.0 fix(evals): office-hours marathon fixture loads the formatter's imports; validator checks the observed cap fixes (#3246) (#3309)

2026-10-19 21:55:24 +00:00

outside-voice-evidence.ts

v1.91.19.0 fix: severe fix wave (truthful gates, no lost memory, every host finds gstack) (#3025)

2026-10-04 07:58:41 -07:00

outside-voice-fixture.ts

v1.91.7.0 feat: add functional QA and pre-publication docs checks (#2983)

2026-09-29 06:07:35 -07:00

outside-voice-receipt.ts

v1.86.0.0 feat: route outside reviews by harness (#2850)

2026-09-14 14:32:45 -07:00

overlay-attempt.ts

v1.91.30.0 fix: honest eval failure reports, Bun floor with safe auto-update, make-pdf and /review on Codex (#3033)

2026-10-06 18:07:50 +00:00

overlay-case-policy.ts

v1.91.30.0 fix: honest eval failure reports, Bun floor with safe auto-update, make-pdf and /review on Codex (#3033)

2026-10-06 18:07:50 +00:00

overlay-case.ts

v1.91.30.0 fix: honest eval failure reports, Bun floor with safe auto-update, make-pdf and /review on Codex (#3033)

2026-10-06 18:07:50 +00:00

overlay-lifecycle.ts

v1.87.6.0 fix: make checks reliable and everyday validation faster (#2898)

2026-09-22 14:57:52 -04:00

overlay-measurement.ts

v1.87.6.0 fix: make checks reliable and everyday validation faster (#2898)

2026-09-22 14:57:52 -04:00

overlay-workspace.ts

v1.87.6.0 fix: make checks reliable and everyday validation faster (#2898)

2026-09-22 14:57:52 -04:00

owned-claude-transcript.ts

v1.87.6.0 fix: make checks reliable and everyday validation faster (#2898)

2026-09-22 14:57:52 -04:00

paid-test-set.ts

v1.91.24.0 test: audit wave — PR evals keep finished work, honest ceilings, EVAL_POLICY v2, faster free suite (#3031)

2026-10-05 01:29:54 +00:00

parity-harness.ts

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)

2026-10-28 00:27:22 +00:00

periodic-exclude-data.ts

v1.91.352.0 feat(benchmark): particle-1 awareness, OpenRouter gateway provider, preregistered model panel (GSTA-173) (#3631)

2026-10-31 05:53:14 +00:00

pin-merge-fixture.ts

v1.94.20.0 test(review): one file per review and harness pin, so independent repins merge cleanly (GST-1084) (#3903)

2026-11-03 15:04:56 +00:00

placeholder-allowlist.ts

v1.93.33.0 wave(review): #3705 #3744 #3745 #3764 #3765 #3795 (#3852)

2026-11-03 01:40:07 +00:00

plan-count-artifacts.ts

v1.89.0.0 feat: add shared-code extraction audit (#2925)

2026-09-24 01:53:58 -04:00

plan-count-file-permission.ts

v1.91.185.0 fix(evals): plan-design focus rating in plain words, docsync own-call rule where --help is named, floor Create crop and 0D menu (GSTA-65) (#3358)

2026-10-23 18:35:59 +00:00

plan-count-fixture.ts

v1.91.16.0 fix: safe installs and upgrades, skills start everywhere, truthful completion (parallel wave) (#3014)

2026-10-03 07:54:09 -07:00

plan-count-pending-exit.ts

v1.86.0.0 feat: route outside reviews by harness (#2850)

2026-09-14 14:32:45 -07:00

plan-count-pending-question.ts

v1.89.0.0 feat: add shared-code extraction audit (#2925)

2026-09-24 01:53:58 -04:00

plan-count-transcript.ts

v1.87.6.0 fix: make checks reliable and everyday validation faster (#2898)

2026-09-22 14:57:52 -04:00

plan-eng-artifact-fixture.ts

v1.91.19.0 fix: severe fix wave (truthful gates, no lost memory, every host finds gstack) (#3025)

2026-10-04 07:58:41 -07:00

plan-eng-resume.ts

v1.91.19.0 fix: severe fix wave (truthful gates, no lost memory, every host finds gstack) (#3025)

2026-10-04 07:58:41 -07:00

plan-floor-review.ts

v1.91.144.0 feat(evals): Opus 5.5 is the paid gate's model under test; judge stays Fable (GSTA-49 TM1) (#3275)

2026-10-19 07:26:49 +00:00

plan-floor-target.ts

v1.86.0.0 feat: route outside reviews by harness (#2850)

2026-09-14 14:32:45 -07:00

plan-format-kind-note.ts

v1.91.15.0 v1.91.15.0: Opus 5.5 prompt cleanup, behavior-level skill tests, transcript consent (#3017)

2026-10-03 01:19:03 -07:00

plan-mode-evidence.ts

v1.91.15.0 v1.91.15.0: Opus 5.5 prompt cleanup, behavior-level skill tests, transcript consent (#3017)

2026-10-03 01:19:03 -07:00

plan-review-board-feedback.ts

v1.94.34.0 test(flaky): autoplan-guard-pty dispatch token relay; plan-design Voices menu accepts both bullet spellings (#3953)

2026-11-03 19:02:06 +00:00

plan-review-cases.ts

v1.91.8.0 test: smaller suite, derived paid selection, retired never-green evals (#2994)

2026-09-29 08:58:49 -07:00

plan-review-decisions.ts

v1.91.12.0 v1.91.12.0: audit fix wave, ~11-minute paid eval lanes, eval reliability policy (#2999)

2026-10-01 13:55:16 -07:00

plan-scope-selection.ts

v1.86.0.0 feat: route outside reviews by harness (#2850)

2026-09-14 14:32:45 -07:00

plan-seed-submission.ts

v1.91.12.0 v1.91.12.0: audit fix wave, ~11-minute paid eval lanes, eval reliability policy (#2999)

2026-10-01 13:55:16 -07:00

plan-skill-question-events.ts

v1.87.6.0 fix: make checks reliable and everyday validation faster (#2898)

2026-09-22 14:57:52 -04:00

plan-skill-question-hook-scope.ts

v1.91.32.0 fix: Codex works from zsh, free text never enters shell commands, honest failures (#3057)

2026-10-06 23:42:19 +00:00

plan-skill-questions.ts

v1.87.6.0 fix: make checks reliable and everyday validation faster (#2898)

2026-09-22 14:57:52 -04:00

planning-wave-task.ts

v1.92.15.0 feat: plan reviews check facts and keep one task list; /office-hours hands its wireframe to design review (#340, #513, #973, #1048, #1791) (#3775)

2026-11-01 06:11:17 +00:00

pregate-fixture.ts

v1.93.23.0 GSTA-253 flaky pass: plan-design focus header, shared-libs revalidation sources, .capy leak-scan skip, fixture state root (#3878)

2026-11-02 23:05:47 +00:00

pricing.ts

v1.91.79.0 feat(eval-plan): /eval-plan tier 1, lane-check, evidence verify, coordinator contract, owner brief, contributor-PR mode, banned terms (multi-agent wave PR E) (#3123)

2026-10-11 03:10:06 +00:00

private-state-root.ts

v1.91.16.0 fix: safe installs and upgrades, skills start everywhere, truthful completion (parallel wave) (#3014)

2026-10-03 07:54:09 -07:00

prompt-structure.ts

v1.91.24.0 test: audit wave — PR evals keep finished work, honest ceilings, EVAL_POLICY v2, faster free suite (#3031)

2026-10-05 01:29:54 +00:00

prosons-posture.ts

v1.91.30.0 fix: honest eval failure reports, Bun floor with safe auto-update, make-pdf and /review on Codex (#3033)

2026-10-06 18:07:50 +00:00

pty-screen.ts

v1.91.11.0 refactor: one state-root rule, browse route table, shared shard engine, PTY harness split, MECE review resolvers (#3002)

2026-10-01 11:57:48 -07:00

pty-trust-dialog.ts

v1.86.0.0 feat: route outside reviews by harness (#2850)

2026-09-14 14:32:45 -07:00

qa-browser-deadline-evidence.ts

v1.91.168.0 fix(evals): QA deadline joins, QA-callers handoff order and plan-check probes (GSTA-57) (#3321)

2026-10-20 18:23:57 +00:00

qa-callers-fixture.ts

v1.93.33.0 wave(review): #3705 #3744 #3745 #3764 #3765 #3795 (#3852)

2026-11-03 01:40:07 +00:00

qa-checkpoint-evidence.ts

v1.91.18.0 feat: Opus 5.5 cleanup follow-ups — scoped transcript consent, opt-in Claude overlay, safety-rule evals, calibrated judges (#3023)

2026-10-03 18:49:34 -07:00

qa-evidence-producer.ts

v1.91.159.0 security: gstack's Bun entry points ignore the audited repo's .env and bunfig.toml (S1) (#3312)

2026-10-20 00:24:28 +00:00

qa-functional-eval.ts

v1.91.249.0 fix(evals): repair five paid-case flakes at their causes (GSTA-107 daily flaky pass) (#3472)

2026-10-26 16:55:25 +00:00

qa-functional-evidence.ts

v1.91.19.0 fix: severe fix wave (truthful gates, no lost memory, every host finds gstack) (#3025)

2026-10-04 07:58:41 -07:00

qa-functional-fixture.ts

v1.91.107.0 fix: the GBRA-40 field list (one Bun for install and check, rec gate approval, pregate never silent) (#3190)

2026-10-16 23:09:23 +00:00

qa-functional-observer.ts

v1.91.15.0 v1.91.15.0: Opus 5.5 prompt cleanup, behavior-level skill tests, transcript consent (#3017)

2026-10-03 01:19:03 -07:00

qa-only-cleanup.ts

v1.91.349.0 fix(flaky): 2026-10-30 flaky pass — paid detector gaps, QA deadline receipt ack, Chromium WSAENOBUFS backport, free-test races (GSTA-178) (#3646)

2026-10-31 04:53:38 +00:00

qa-probe-names.ts

v1.91.18.0 feat: Opus 5.5 cleanup follow-ups — scoped transcript consent, opt-in Claude overlay, safety-rule evals, calibrated judges (#3023)

2026-10-03 18:49:34 -07:00

read-only-commands.ts

v1.91.174.0 fix(evals): local-hook detector credits "set it up by hand"; read-only grammar steers globbed options to the quoted form (#3332)

2026-10-21 18:11:21 +00:00

resolve-repo-path.test.ts

v1.91.8.0 test: smaller suite, derived paid selection, retired never-green evals (#2994)

2026-09-29 08:58:49 -07:00

resolve-repo-path.ts

v1.91.8.0 test: smaller suite, derived paid selection, retired never-green evals (#2994)

2026-09-29 08:58:49 -07:00

restamp-fixture.ts

v1.93.23.0 GSTA-253 flaky pass: plan-design focus header, shared-libs revalidation sources, .capy leak-scan skip, fixture state root (#3878)

2026-11-02 23:05:47 +00:00

run-bin.test.ts

v1.74.0.0 test/CI overhaul: green means green, suites restructured for speed (#2721)

2026-08-29 09:06:54 -07:00

run-bin.ts

v1.74.0.0 test/CI overhaul: green means green, suites restructured for speed (#2721)

2026-08-29 09:06:54 -07:00

safety-codex-boundary-task.ts

v1.92.2.0 evals: no-gstack arms for the model panel, arm-benchmark, safety and routing evals (#3708)

2026-10-31 22:41:36 +00:00

safety-codex-consult-task.ts

v1.92.2.0 evals: no-gstack arms for the model panel, arm-benchmark, safety and routing evals (#3708)

2026-10-31 22:41:36 +00:00

safety-design-risk-task.ts

v1.92.2.0 evals: no-gstack arms for the model panel, arm-benchmark, safety and routing evals (#3708)

2026-10-31 22:41:36 +00:00

safety-rules.ts

v1.92.2.0 evals: no-gstack arms for the model panel, arm-benchmark, safety and routing evals (#3708)

2026-10-31 22:41:36 +00:00

safety-ship-evidence-task.ts

v1.92.2.0 evals: no-gstack arms for the model panel, arm-benchmark, safety and routing evals (#3708)

2026-10-31 22:41:36 +00:00

schema-canary.ts

v1.91.34.0 fix: /autoplan on current Claude Code and long sessions, quieter pre-push and sync guards, gstack-post, gstack-doctor (#3069)

2026-10-07 23:29:05 +00:00

scratch-repo.ts

v1.91.8.0 test: smaller suite, derived paid selection, retired never-green evals (#2994)

2026-09-29 08:58:49 -07:00

sdk-system-prompt.ts

v1.93.10.0 wave(docs): #3590 #3591 #3819 #3618 #3824 #3828 (#3847)

2026-11-02 17:44:00 +00:00

secret-sink-harness.ts

v1.12.0.0 feat: /setup-gbrain — coding-agent onboarding for gbrain (#1183)

2026-04-24 01:38:21 -07:00

session-drain-policy.ts

v1.91.7.0 feat: add functional QA and pre-publication docs checks (#2983)

2026-09-29 06:07:35 -07:00

session-ledger.ts

v1.93.10.0 wave(docs): #3590 #3591 #3819 #3618 #3824 #3828 (#3847)

2026-11-02 17:44:00 +00:00

session-runner.test.ts

v1.88.1.0 fix: harden credential boundaries and owned state (#2942)

2026-09-23 08:54:53 -04:00

session-runner.ts

v1.93.10.0 wave(docs): #3590 #3591 #3819 #3618 #3824 #3828 (#3847)

2026-11-02 17:44:00 +00:00

setup-codex-scope-cyclic.ts

v1.92.30.0 test(free): split files over the 60 s seed ceiling and the Windows doctor file, then reseed (GSTA-151 A) (#3585)

2026-11-01 14:23:49 +00:00

setup-gbrain-fixture-command.ts

v1.87.6.0 fix: make checks reliable and everyday validation faster (#2898)

2026-09-22 14:57:52 -04:00

setup-gbrain-fixture.ts

v1.87.6.0 fix: make checks reliable and everyday validation faster (#2898)

2026-09-22 14:57:52 -04:00

setup-gbrain-sandbox.ts

v1.91.12.0 v1.91.12.0: audit fix wave, ~11-minute paid eval lanes, eval reliability policy (#2999)

2026-10-01 13:55:16 -07:00

shared-libs-checker-evidence.ts

v1.93.23.0 GSTA-253 flaky pass: plan-design focus header, shared-libs revalidation sources, .capy leak-scan skip, fixture state root (#3878)

2026-11-02 23:05:47 +00:00

shared-libs-eval-fixture.ts

v1.91.144.0 feat(evals): Opus 5.5 is the paid gate's model under test; judge stays Fable (GSTA-49 TM1) (#3275)

2026-10-19 07:26:49 +00:00

shared-libs-path-fixture.ts

v1.91.7.0 feat: add functional QA and pre-publication docs checks (#2983)

2026-09-29 06:07:35 -07:00

shared-libs-plan-actor.ts

v1.91.19.0 fix: severe fix wave (truthful gates, no lost memory, every host finds gstack) (#3025)

2026-10-04 07:58:41 -07:00

shared-libs-plan-excerpt.ts

v1.89.0.0 feat: add shared-code extraction audit (#2925)

2026-09-24 01:53:58 -04:00

shared-libs-review-start-evidence.ts

v1.91.301.0 fix(flaky): four paid rule cases stop failing correct runs (2026-10-28 pass) (#3547)

2026-10-29 00:16:09 +00:00

ship-bin-fixture.ts

v1.91.355.0 ship: poll readers in-program, 32 KB returns, gated fix program, unattended push defers the guard offer, calls meter (GSTA-167 calls PR 1) (#3662)

2026-10-31 07:22:56 +00:00

ship-budget-harness.ts

v1.92.33.0 fix(flaky): 2026-10-31 flaky pass — paid detector gaps, Windows cold first launches, fixture races, ubicloud pack index copy (GSTA-199) (#3697)

2026-11-01 16:01:55 +00:00

ship-frozen-scope-actor.ts

v1.92.75.0 fix(ship): the receipt counts every blocker the readers found (GST-951) (#3845)

2026-11-02 12:06:35 +00:00

ship-hook-actor.ts

v1.91.349.0 fix(flaky): 2026-10-30 flaky pass — paid detector gaps, QA deadline receipt ack, Chromium WSAENOBUFS backport, free-test races (GSTA-178) (#3646)

2026-10-31 04:53:38 +00:00

ship-measure-seeded-fixture.ts

v1.91.32.0 fix: Codex works from zsh, free text never enters shell commands, honest failures (#3057)

2026-10-06 23:42:19 +00:00

ship-queue-fixture.ts

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)

2026-10-29 00:01:37 +00:00

ship-queue-train-cases.ts

v1.92.54.0 ship-queue: train land takes the shared land lock; verify proves the stamp; restamp stages its writes (#3599, #3531) (#3737)

2026-11-02 03:23:35 +00:00

ship-queue-train-fixture.ts

v1.92.54.0 ship-queue: train land takes the shared land lock; verify proves the stamp; restamp stages its writes (#3599, #3531) (#3737)

2026-11-02 03:23:35 +00:00

ship-skip-actor.ts

v1.91.7.0 feat: add functional QA and pre-publication docs checks (#2983)

2026-09-29 06:07:35 -07:00

ship-triage-labels.ts

v1.91.15.0 v1.91.15.0: Opus 5.5 prompt cleanup, behavior-level skill tests, transcript consent (#3017)

2026-10-03 01:19:03 -07:00

shipped-skill-routing.ts

v1.91.15.0 v1.91.15.0: Opus 5.5 prompt cleanup, behavior-level skill tests, transcript consent (#3017)

2026-10-03 01:19:03 -07:00

size-ledger.ts

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)

2026-10-28 00:27:22 +00:00

skill-body-narration.ts

v1.91.15.0 v1.91.15.0: Opus 5.5 prompt cleanup, behavior-level skill tests, transcript consent (#3017)

2026-10-03 01:19:03 -07:00

skill-census.ts

v1.63.0.0 feat: GStack 2 fork port wave — egress receipts, context-bill, sharded gate, /health fix (#2541)

2026-08-14 09:28:56 -07:00

skill-contract-fixture.ts

v1.94.36.0 fix(skill-contracts): agent_dispatch rejects markers; the waive hint names the installed bin (GST-1242) (#3964)

2026-11-03 19:49:58 +00:00

skill-fixture.ts

v1.93.33.0 wave(review): #3705 #3744 #3745 #3764 #3765 #3795 (#3852)

2026-11-03 01:40:07 +00:00

skill-parser.ts

v1.87.6.0 fix: make checks reliable and everyday validation faster (#2898)

2026-09-22 14:57:52 -04:00

skill-startup.ts

v1.91.277.0 feat(preamble): office-hours stops copying the shared AskUserQuestion subsections (GSTA-96) (#3453)

2026-10-27 13:47:00 +00:00

sol-skill-fixture.ts

v1.87.6.0 fix: make checks reliable and everyday validation faster (#2898)

2026-09-22 14:57:52 -04:00

state-matrix-fixture.ts

v1.91.116.0 feat: field list 2 wave B: gstack-ship-queue, approval classes, state-machine review, pregate timing check, update-check main moves (#3235)

2026-10-17 03:32:16 +00:00

stored-zip.ts

v1.91.24.0 test: audit wave — PR evals keep finished work, honest ceilings, EVAL_POLICY v2, faster free suite (#3031)

2026-10-05 01:29:54 +00:00

sync-command-capture.test.ts

v1.87.6.0 fix: make checks reliable and everyday validation faster (#2898)

2026-09-22 14:57:52 -04:00

sync-command-capture.ts

v1.87.6.0 fix: make checks reliable and everyday validation faster (#2898)

2026-09-22 14:57:52 -04:00

sync-gbrain-readiness-fixture.ts

v1.91.12.0 v1.91.12.0: audit fix wave, ~11-minute paid eval lanes, eval reliability policy (#2999)

2026-10-01 13:55:16 -07:00

sync-gbrain-readiness-verdict.ts

v1.91.12.0 v1.91.12.0: audit fix wave, ~11-minute paid eval lanes, eval reliability policy (#2999)

2026-10-01 13:55:16 -07:00

test-selection.ts

v1.91.360.0 fix: a PR's changelog.d fragment no longer forces the full paid gate (GST-400) (#3674)

2026-10-31 10:08:55 +00:00

test-value-fixture.ts

v1.91.15.0 v1.91.15.0: Opus 5.5 prompt cleanup, behavior-level skill tests, transcript consent (#3017)

2026-10-03 01:19:03 -07:00

third-party-actions.ts

v1.92.33.0 fix(flaky): 2026-10-31 flaky pass — paid detector gaps, Windows cold first launches, fixture races, ubicloud pack index copy (GSTA-199) (#3697)

2026-11-01 16:01:55 +00:00

tool-map.ts

v1.81.0.0 feat: Aside is the browser gstack drives first; every browsing skill, the PDF/diagram renderer, and web research; the bundled browser stays the automatic fallback (#2810)

2026-09-06 08:54:25 -07:00

touchfile-closure.ts

v1.91.8.0 test: smaller suite, derived paid selection, retired never-green evals (#2994)

2026-09-29 08:58:49 -07:00

touchfiles-data.ts

test: remove the AI scorer that grades skill prose for clarity (freeze repair, GST-1371) (#4009)

2026-11-04 22:19:08 +00:00

touchfiles.ts

v1.66.0.0 feat: test/evals/CI speedup — 90s truthful free suite, diff-billed evals, required Linux lane (#2593)

2026-08-15 22:20:30 -07:00

ubi-runner-fake-vm.ts

v1.92.41.0 fix(ubicloud): pack and usage on macOS, reap and up on an empty project (#3680, #3679, #3678) (#3746)

2026-11-01 21:11:44 +00:00

unreachable-gbrain.ts

v1.91.16.0 fix: safe installs and upgrades, skills start everywhere, truthful completion (parallel wave) (#3014)

2026-10-03 07:54:09 -07:00

warm-first-exec.ts

v1.92.33.0 fix(flaky): 2026-10-31 flaky pass — paid detector gaps, Windows cold first launches, fixture races, ubicloud pack index copy (GSTA-199) (#3697)

2026-11-01 16:01:55 +00:00

workflow-boundaries-fixture.ts

v1.91.144.0 feat(evals): Opus 5.5 is the paid gate's model under test; judge stays Fable (GSTA-49 TM1) (#3275)

2026-10-19 07:26:49 +00:00

workflow-excerpt.ts

v1.91.15.0 v1.91.15.0: Opus 5.5 prompt cleanup, behavior-level skill tests, transcript consent (#3017)

2026-10-03 01:19:03 -07:00

workflow-judge-input.ts

test: remove the AI scorer that grades skill prose for clarity (freeze repair, GST-1371) (#4009)

2026-11-04 22:19:08 +00:00