garrytanandcapy-ai[bot] 30bcb700c1 feat(ship-measure): the measurement bar and the weekly off-ship sweep CLI ...

Decide each diagnostic measurement with one bar (scripts/lib/measure-bar.ts):
MEETS at 9/10; MEETS-qualified at 8/10 when every red is a mechanical
provider error, judge noise or a cited model miss; EXTEND at 7/10 (or an
unqualified 8/10) for one more batch on identical inputs, decided once on
the pooled 20; BELOW otherwise and for any timeout, hang, regression or
fixable cause. Behavior uses 12 trials (11/10/9; 22/20 of 24); judge counts
median-panel outputs. A batch with more than 30% provider-evidence failures
is void and redispatched once. Below-strict reds nobody classified return
needs-classify.

ship-measure gains classify (append-only records; provider refused without
evidence), decide and extend (refuses a changed identity, names the field,
never a third batch), exit codes 5 and 6, and a pooling identity (frozen
tree, runner, CLI, model, CI image, Bun, policy and harness versions).

ship-measure sweep ranks main's gate cases by their cost to the all-green
probability from eval:pass-rates history, measures the top K with the same
runner and bar under a weekly cap shared with the last 7 days of sweep
reports (ship_measure_sweep_cases, ship_measure_sweep_budget_usd), and
writes a report with the predicted all-green probability before and after.

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

2026-10-07 01:18:09 +00:00

..

arm-benchmark

v1.75.0.0 feat: ponytail import wave — simplification review lens, arm benchmark, reuse ladder, instruction-tier digest (#2722)

2026-08-29 10:10:35 -07:00

auq-matrix

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

autoplan

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

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

browse-judge

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

carve-existing-repository

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

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

ceo-existing-payment

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

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

ceo-stale-fill-decision

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

ci-gate

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

codex-review

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

codex-sandbox

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

context-bill/tree-a

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

cso-eval

v1.91.25.0 feat(cso): private two-architecture release scoring + self-checking runtime release gates (#3036)

2026-10-04 21:47:21 -07:00

cso-sarif

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

detector-corpora

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

docsync-replay

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-history

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

exit-propagation

v1.64.0.0 fix wave: full tracker audit — 90 fixes, 52 issues closed, ~50 community PRs absorbed (#2571)

2026-08-14 22:02:07 -07:00

golden

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

ios-qa/FixtureApp

v1.67.0.0 fix: the tracker wave — XProtect self-heal, complete installs, brain-sync integrity, 31 community PRs credited (#2604)

2026-08-16 19:34:41 -07:00

judge-calibration

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

mode-posture

feat: mode-posture energy fix for /plan-ceo-review and /office-hours (v1.1.2.0) (#1065)

2026-04-19 05:44:39 +08:00

module-size

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

office-hours-brain-writeback

v1.52.1.0 feat: brain-aware planning — 5 skills read structured gbrain context before asking (#1742)

2026-05-29 08:35:00 -07:00

paid-report-census

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

plans

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

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

pty-screen

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

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

redact-diagram

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

shard-cli-parity

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

shard-equivalence

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

shared-libs

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

ship-triage

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

skillify-narration

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

touchfile-moved-code

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

trial-cause

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

auq-pre-cut-plan-ceo-review-SKILL.md

v1.75.0.0 feat: ponytail import wave — simplification review lens, arm benchmark, reuse ladder, instruction-tier digest (#2722)

2026-08-29 10:10:35 -07:00

auto-decide-completed-mode-f359.json

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

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

auto-decide-current-declaration-6aef.json

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

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

auto-decide-explanatory-mode-043a.json

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

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

auto-decide-explanatory-mode-749df.json

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

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

auto-decide-handoff-before-log-37182865432.json

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

auto-decide-handoff-line-e354.json

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

auto-decide-mode-selector-749df.json

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

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

auto-decide-recommendation-361c.json

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

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

auto-decide-retry-ai.json

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

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

auto-decide-saved-ai.json

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

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

auto-decide-state-cab3.json

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

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

auto-decide-structured-77.json

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

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

auto-decide-target-361c.json

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

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

autoplan-amend-input-77.json

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

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

autoplan-dual-false-positive-6bd.json

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

autoplan-edit-digests-al.json

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

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

autoplan-home-phase-entry-fb10.json

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

autoplan-method-read-aa-events.json

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

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

autoplan-owned-state-edit.json

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

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

autoplan-phase-consumption-491.json

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

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

autoplan-phase-dash-ao.json

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

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

autoplan-phase-entry-alias-f359.json

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

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

autoplan-phase-entry-cf74.json

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

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

autoplan-phase-handoff-6714.json

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

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

autoplan-public-narration-ad.json

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

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

autoplan-publication-boundary-361c.json

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

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

autoplan-routing-manual-skills-ac.json

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

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

autoplan-settings-overwrite.json

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

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

autoplan-setup-packet-o-call.json

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

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

autoplan-setup-packet-o-screen.txt

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

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

autoplan-with-result-au.json

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

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

bash-directory-permission.json

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

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

batching-permission-at.json

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

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

ceo-approach-z-call.json

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

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

ceo-approach-z-screen.txt

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

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

ceo-barless-submit-ac.json

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

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

ceo-checkbox-l.screen.txt

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

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

ceo-completion-handoff-m-call.json

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

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

ceo-completion-handoff-o-call.json

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

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

ceo-completion-handoff-q-call.json

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

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

ceo-count-ad-v2.json

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

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

ceo-count-mode-preview-aa-screen.txt

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

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

ceo-count-s-distinct.json

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

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

ceo-expansion-auq-ac.json

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

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

ceo-expansion-complete-inventory-6f.json

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

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

ceo-expansion-disposition-77.json

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

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

ceo-expansion-pacing-77.json

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

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

ceo-expansion-pacing-fb10.json

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

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

ceo-expansion-pause-6714.json

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

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

ceo-expansion-plural-36903600510.json

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-expansion-posture-kind-dacc.json

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

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

ceo-fill-lifetime.json

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

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

ceo-handoff-n-calls.json

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

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

ceo-handoff-y-call.json

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

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

ceo-hold-commitment-ar.json

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

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

ceo-hold-note-briefs-36597762183.json

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-hold-posture-ag.json

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

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

ceo-hold-posture-l.json

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

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

ceo-hold-preservation-f359.json

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

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

ceo-hold-proof-fb10.json

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

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

ceo-mode-bundled-tab-local.json

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-clipped-mode-question-local.json

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-clipped-review-local.json

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-colon-at.json

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

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

ceo-mode-full-ad.json

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

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

ceo-mode-labels-l.json

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

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

ceo-mode-pending-submit.json

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

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

ceo-mode-posture-ad.json

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

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

ceo-mode-prerequisite-o-calls.json

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

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

ceo-mode-prerequisite-q-call.json

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

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

ceo-mode-preview-aa-screen.txt

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

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

ceo-mode-scrolled-review-36606688266.json

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-paired-option-values.json

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

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

ceo-prerequisite-ad-v2.json

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

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

ceo-prerequisite-n-call.json

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

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

ceo-preview-u-call.json

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

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

ceo-preview-u-screen.txt

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

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

ceo-questionless-w-native.json

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

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

ceo-report-permission-fb10.json

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

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

ceo-section-aa-report.md

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

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

ceo-section-loading-36597762183-report.md

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-section-loading-l-report.md

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

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

ceo-section-loading-q-report.md

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

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

ceo-section-r-rejected-report.md

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

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

ceo-section-s-trace-report.md

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

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

ceo-section-u-report.md

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

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

ceo-section-y-report.md

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

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

ceo-split-actor-6aef.json

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

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

ceo-split-collection-0bcd.json

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

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

ceo-split-collection-3638.json

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-e5-numbered-description-491.json

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

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

ceo-split-edit-permission-361c-public.json

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

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

ceo-split-padding-361c-public.json

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

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

ceo-split-wording-variants.json

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-native-journal-roots-2.1.284.json

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

codex-boundary-commands.json

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-review-sandbox-unavailable-37158847998.json

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

context-budget.json

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

coverage-audit-ae.json

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

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

coverage-audit-af.json

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

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

coverage-audit-aw.json

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

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

coverage-audit-ci-diagrams.json

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

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

coverage-audit-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

coverage-audit-parallel-column.json

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

coverage-audit-sed-context.json

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

coverage-audit-shell-legend-at.json

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

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

coverage-audit-summary.json

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

coverage-checkbox-tail-av.json

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

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

coverage-diagram-legend-as.json

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

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

coverage-shell-display-aq.json

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

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

cso-http-smoke.c

v1.87.0.0 feat: add verified CSO audits and replayable repair bundles (#2852)

2026-09-14 15:14:58 -07:00

design-board-questions.json

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

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

design-completion-envelope-90f.json

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

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

design-consultation-section-design-md.md

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

design-count-native-8525.json

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

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

design-count-native-issue-fields.json

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

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

design-crop-gutter-ap.json

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

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

design-detector-source-public.json

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

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

design-floor-focus-36597762183.json

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

design-handoff-n-calls.json

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

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

design-handoff-q-calls.json

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

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

design-html-section-complete.md

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

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

design-md-legacy.md

v1.84.0.0 feat: impeccable interop: detector pre-pass in four design skills, DOM-mode scans, open DESIGN.md format, one typed slop catalog (#2832)

2026-09-08 22:40:22 -07:00

design-outside-voices-question.json

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

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

design-plan-scope-ag.json

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

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

design-preview-v-screen.txt

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

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

design-scope-announcement-ao.json

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

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

design-scope-checkpoint-at.json

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

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

design-scope-declaration-ak.json

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

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

design-scope-selection-aj.json

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

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

design-tasks-bash-permission.json

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

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

design-ui-boxed-question.json

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

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

design-ui-focus-capture.json

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

devex-checkpoint-todos.json

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

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

devex-handoff-n-call.json

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

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

devex-handoff-o-call.json

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

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

devex-handoff-v-call.json

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

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

devex-handoff-z-call.json

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

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

devex-narrative-confirmation-36641820398.json

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

devex-narrative-confirmation-36794871032.json

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

devex-peer-comparison-classification.ts

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

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

devex-review-l-calls.json

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

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

disabled-dated-record-at.json

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

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

disabled-historical-line-aq.json

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

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

disabled-plan-attribution-36597762183.json

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

disabled-plan-attribution-ad-v2.json

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

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

disabled-plan-attribution-local-rerun.json

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

disabled-plan-self-report.json

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

disabled-prior-clock-36903600510.json

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

disabled-retained-record.json

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

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

docsync-followup-echo-37188668421.json

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

docsync-observer-commands.json

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

dx-manual-handoff-ao.json

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

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

dx-prerequisite-r-call.json

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

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

dx-selected-navigation-ap.json

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

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

eng-a689-retry-public.json

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

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

eng-annotated-cache-au.json

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

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

eng-architecture-cache-av-calls.json

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

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

eng-auq-validation-error.json

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

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

eng-batching-bullet-target-rerun.json

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

eng-batching-expanded-ledger-6714.json

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

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

eng-batching-native-8525.json

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

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

eng-batching-prefixed-ledger-f359.json

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

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

eng-batching-report-title-36798539821.json

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

eng-batching-saved-ledger-b176.json

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

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

eng-batching-saved-ledger-dacc.json

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

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

eng-batching-section-heading-37158847998.json

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

eng-batching-t-calls.json

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

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

eng-batching-unsourced-brief-36606688266.json

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

eng-binding-retry-z-calls.json

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

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

eng-binding-z-calls.json

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

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

eng-cache-brief-am.json

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

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

eng-cache-owner-an.json

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

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

eng-cache-writes-as.json

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

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

eng-completed-navigation-cab3.json

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

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

eng-count-ad-v2.json

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

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

eng-d1-clipped-elision-1579.json

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

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

eng-d2-planning-prelude-4d.json

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

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

eng-d2-truncated-border-0bcd.json

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

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

eng-declarative-as.json

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

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

eng-declared-retry-at.json

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

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

eng-devex-s-first-calls.json

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

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

eng-devex-s-retry-calls.json

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

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

eng-fb10-count-public.json

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

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

eng-file-permission-repaint.json

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

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

eng-first-category-af.json

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

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

eng-injected-export-aq.json

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

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

eng-library-hooks-aq.json

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

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

eng-native-review-identities-6714.json

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

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

eng-next-handoff-ah.json

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

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

eng-option-b-scope-al.json

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

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

eng-prerequisite-77.json

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

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

eng-published-navigation.json

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

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

eng-scope-y-calls.json

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

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

eng-seeded-completion-ai.json

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

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

eng-task-pause-navigation-f359.json

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

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

eng-test-plan-edit-cli.js

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

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

eng-test-plan-edit-dacc.json

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

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

eval-baselines.json

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

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

fake-impeccable.ts

v1.84.0.0 feat: impeccable interop: detector pre-pass in four design skills, DOM-mode scans, open DESIGN.md format, one typed slop catalog (#2832)

2026-09-08 22:40:22 -07:00

forcing-finding-seeds.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

free-shard-capture.ts

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

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

impeccable-antipatterns.json

v1.84.0.0 feat: impeccable interop: detector pre-pass in four design skills, DOM-mode scans, open DESIGN.md format, one typed slop catalog (#2832)

2026-09-08 22:40:22 -07:00

impeccable-captures.meta.json

v1.84.0.0 feat: impeccable interop: detector pre-pass in four design skills, DOM-mode scans, open DESIGN.md format, one typed slop catalog (#2832)

2026-09-08 22:40:22 -07:00

impeccable-detect-dom-sample.json

v1.84.0.0 feat: impeccable interop: detector pre-pass in four design skills, DOM-mode scans, open DESIGN.md format, one typed slop catalog (#2832)

2026-09-08 22:40:22 -07:00

impeccable-detect-help.txt

v1.84.0.0 feat: impeccable interop: detector pre-pass in four design skills, DOM-mode scans, open DESIGN.md format, one typed slop catalog (#2832)

2026-09-08 22:40:22 -07:00

impeccable-detect-sample.json

v1.84.0.0 feat: impeccable interop: detector pre-pass in four design skills, DOM-mode scans, open DESIGN.md format, one typed slop catalog (#2832)

2026-09-08 22:40:22 -07:00

judge-panel-replay-2026-10-05.json

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

module-size-ratchet.json

feat(ship-measure): the measurement bar and the weekly off-ship sweep CLI

2026-10-07 01:18:09 +00:00

native-auq-boxed-full-body-sep21.json

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

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

native-auq-clipped-elided-sep21.json

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

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

native-auq-devex-clipped-elided-sep21.json

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

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

native-auq-margin-elided-sep21.json

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

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

native-auq-packet-clipped-elided-sep21.json

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

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

native-auto-decide-ag.json

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

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

outside-async-task-m-events.json

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

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

outside-background-ai.json

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

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

outside-voice-failure-prose-allowlist.json

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

overlay-admission-child.ts

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

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

overlay-nudges.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

overlay-v4-replay-37198445662.json

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

parity-baseline-v1.44.1.json

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

parity-baseline-v1.64.1.0.json

v1.64.1.0 v1.64.1.0: the code-smell fix wave — every pipeline guard now provably fires (net −24,943 lines) (#2572)

2026-08-15 09:37:04 -07:00

parity-baseline-v1.81.0.0.json

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

pending-question-completion-ad.json

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

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

plan-count-crop-ak.json

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

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

plan-count-cropped-wrap-6714.json

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

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

plan-count-cross-cwd-ancestry-0bcd.json

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

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

plan-count-design-questionless-report.md

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

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

plan-count-edit-permission-t.json

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

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

plan-count-long-edit-0bcd.json

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

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

plan-count-owned-permission-v.json

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

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

plan-count-permission-ac.json

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

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

plan-count-permission-ad.json

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

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

plan-count-permission-ae.json

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

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

plan-count-permission-ah.json

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

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

plan-count-permission-target-ad-v2.json

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

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

plan-count-quoted-frame-ak.json

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

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

plan-create-combined-permission-70b.json

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

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

plan-create-cropped-title-batching.json

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-create-permission-361c.json

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

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

plan-create-prepublication-491.json

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

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

plan-decision-classification.ts

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

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

plan-edit-cropped-permission-1579.json

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

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

plan-eng-artifact-resume-37174266054.json

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-dx-custom-491.json

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

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

plan-floor-dx-editor-hint.json

v1.89.1.0 fix: remove continuous checkpoint commits (#2970)

2026-09-24 17:27:14 -04:00

plan-floor-edit-wrap-37176835584.json

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

plan-floor-permission-fb10.json

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

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

plan-floor-product-type-70b.json

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

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

plan-floor-quote-70b.json

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

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

plan-floor-routing-361c.json

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

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

plan-format-kind-notes.json

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-report-public.json

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

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

plan-scope-recovery-av.json

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

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

plan-scope-target-aw.json

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

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

plan-seed-cli.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

prosons-neutral-neg-captures.json

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-companion-cli.ts

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

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

pty-idle-turn-end.json

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

qa-eval-checkout-ground-truth.json

fix: 100% E2E pass — isolate test dirs, restart server, relax FP thresholds

2026-03-14 07:17:17 -05:00

qa-eval-ground-truth.json

fix: 100% E2E pass — isolate test dirs, restart server, relax FP thresholds

2026-03-14 07:17:17 -05:00

qa-eval-spa-ground-truth.json

fix: 100% E2E pass — isolate test dirs, restart server, relax FP thresholds

2026-03-14 07:17:17 -05:00

qa-functional-ci-36505065023.json

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

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

qa-functional-cli-learning-ci-36516246523.json

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

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

qa-only-browser-probe.ts

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

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

qa-only-charter-public.json

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

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

qa-only-observation-public.json

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

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

qa-webhook-r85-checkpoints.json

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

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

read-permission.json

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

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

remote-identity-vectors.json

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

review-army-lean-complete.js

v1.75.0.0 feat: ponytail import wave — simplification review lens, arm benchmark, reuse ladder, instruction-tier digest (#2722)

2026-08-29 10:10:35 -07:00

review-army-migration.sql

feat: Review Army — parallel specialist reviewers for /review (v0.14.3.0) (#692)

2026-03-30 22:07:50 -06:00

review-army-n-plus-one.rb

feat: Review Army — parallel specialist reviewers for /review (v0.14.3.0) (#692)

2026-03-30 22:07:50 -06:00

review-army-overbuild.js

v1.75.0.0 feat: ponytail import wave — simplification review lens, arm benchmark, reuse ladder, instruction-tier digest (#2722)

2026-08-29 10:10:35 -07:00

review-browse-error-ci-36516246523.json

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

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

review-count-markdown-6f.json

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

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

review-design-lite-reports-ci-36633323521.json

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

review-eval-design-slop.css

feat: design review lite in /review and /ship + gstack-diff-scope (v0.6.3) (#142)

2026-03-17 20:12:55 -05:00

review-eval-design-slop.dom.html

v1.84.0.0 feat: impeccable interop: detector pre-pass in four design skills, DOM-mode scans, open DESIGN.md format, one typed slop catalog (#2832)

2026-09-08 22:40:22 -07:00

review-eval-design-slop.html

feat: design review lite in /review and /ship + gstack-diff-scope (v0.6.3) (#142)

2026-03-17 20:12:55 -05:00

review-eval-enum-diff.rb

feat: contributor mode, session awareness, recommendation format (#90)

2026-03-16 01:45:50 -05:00

review-eval-enum.rb

feat: contributor mode, session awareness, recommendation format (#90)

2026-03-16 01:45:50 -05:00

review-eval-vuln.rb

feat: 3-tier eval suite with planted-bug outcome testing (EVALS=1)

2026-03-14 01:17:36 -05:00

review-n-plus-one-dispatch.json

v1.91.2.0 fix: consolidate gstack reliability wave (#2959)

2026-09-26 18:57:53 -04:00

sdk-columnar-af.json

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

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

sdk-compact-sequence-aj.json

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

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

sdk-order-b-ag.json

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

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

sdk-ordered-schedule-ar.md

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

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

sdk-ordering-ae.json

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

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

sdk-original-order-ai.json

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

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

sdk-reported-coordination-ar.md

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

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

sdk-schedule-continuation-ah.json

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

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

sdk-stale-table-ad-v3.json

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

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

shared-libs-index-flags-native-questions.json

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

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

shared-libs-index-flags-no-change-description.json

v1.89.1.0 fix: remove continuous checkpoint commits (#2970)

2026-09-24 17:27:14 -04:00

shared-libs-index-flags-r20-packets.json

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

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

shared-libs-index-flags-r44-packets.json

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

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

shared-libs-index-flags-r59-checker-public.json

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

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

shared-libs-index-flags-skip-description-public.json

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-index-flags-skip-question.json

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

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

shared-libs-lifecycle-r59-stage-scope-public.json

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

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

shared-libs-no-change-ci-public.json

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

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

shared-libs-paths-max-turns-public.json

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

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

shared-libs-plan-callers-fixes-behavior-local.json

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-callers-future-risk-37195203538.json

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-callers-no-hardening-36633323521.json

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-plan-callers-out-of-scope-37151477069.json

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-callers-parity-36776104571.json

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-plan-callers-passing-censuses.json

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-callers-slash-scope-37174266054.json

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-callers-verbless-scope-37186854666.json

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-readonly-substitution-ci16358.json

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

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

shared-libs-resolved-reads-public.json

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

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

shared-libs-revalidation-max-turns-public.json

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

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

shared-libs-review-start-public.json

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

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

ship-coverage-audit-af.json

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

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

test-value-seam-evidence.json

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-recovery-public.json

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

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

trial-record-v1-reader.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

webfetch-permission.json

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

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

workflow-required-steps.json

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