Garry Tanandcapy-ai[bot] e0531db793 v1.93.21.0 fix(ship): native FIXABLE collects at its own Severity outside gate and risk reviews (GST-987) (#3869) ...

* fix(review-ledger): a finding's Severity field sets its label, body severity words never raise it (GST-976)

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

* fix(review-ledger): Severity counts only in field position, locus-first and emoji-led labels lead, an inline field floors the next (GST-976 review)

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

* fix(review-ledger): linear lead-label prefix, all-caps leads before a space, fields after a parenthesis or without a colon at the line start (GST-976 review)

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

* fix(review-ledger): a lead's file:line has no runaway backtracking and may be a range; a mid-line Severity field must close its clause (GST-976 review)

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

* fix(review-ledger): a field at the line's start needs no closing clause; mid-line fields accept : / and → after the label (GST-976 fix-check)

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

* docs: changelog fragment and review-policy collect step for GST-976

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

* fix(review-ledger): a Severity field's label chain (High/Critical) takes its strongest label; mid-line fields keep the clause-closing set (GST-976 scoped check)

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

* test(review-ledger): never weaker than main invariant over pinned inputs, fixtures and generated field shapes; a multi-label Severity field counts as none, lowercase fields keep their label (GST-976)

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

* docs: GST-976 re-audit, multi-label and lowercase Severity fields

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

* fix: native FIXABLE raises only on gate and risk review classes (GST-987)

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

* fix: collect records fixable_raises:false so a later re-derive uses the same class (GST-987)

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

* fix: GST-987 review fixes: history/floor reasons and FIXABLE-only fields keep v2; manifest must name this ledger

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

* fix: GST-987 round-2 fixes: FIXABLE relaxes only beside Blocks: no; raw FIXABLE heading; unreadable manifest keeps v2

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

* fix: GST-987 fix-check: items under a FIXABLE heading need Blocks: no; Blocks: no-op is not Blocks: no; wrong-tree collect with an unreadable manifest

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

* docs: GST-987 docs audit: depth section notes the native FIXABLE exception

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

* fix: a paragraph under a numbered finding heading joins it, so its fields attach (gstack-evals #149, GST-987)

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

* fix: verify re-derives native labels with the collect's class (GST-987, after #3717)

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

* fix: #149 join stops at a labeled or located paragraph and after the fields (GST-987)

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

* test: GST-987 #149 sibling shapes as named never-weaker invariant fixtures

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

* chore: drop the released GST-976 changelog fragment carried by the stack

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>

2026-11-02 21:39:39 +00:00

..

arm-benchmark

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

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

autoplan-pairing

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

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-host

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-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

v1.91.136.0 fix(cso-eval): falsely-tested count leaves out instrumentation claims; incidental claims certified by a passing signed-bundle replay (#3270)

2026-10-18 17:06:36 +00:00

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

design-lint

v1.91.251.0 feat(design-lint): bundled free design lint (bin/gstack-design-lint + lib/design-lint/), hallmark sloplint port (#3459)

2026-10-26 17:35:04 +00:00

detector-corpora

v1.91.111.0 fix(evals): four PR-gate background reds were a detector, an interface, a helper and a workflow-block defect (#3231)

2026-10-17 00:56:33 +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

evidence

v1.91.238.0 fix(ship): gate-diff base in single-branch clones, gstack-post release versions and receipt ids, evidence tests_ran, restamp duplicate headings and stamp prompt (GSTA-102) (#3439)

2026-10-26 09:33:07 +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

factory-scorecard

test:health and factory scorecard: leave reused main pushes out of free-suite flake counts (#3725) (#3822)

2026-11-02 05:24:30 +00:00

gate-diff

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

golden

v1.93.6.0 feat: /plan-tune learns from ad-hoc question ids that carry a signal hint (#3442) (#3868)

2026-11-02 16:20:02 +00:00

ios-qa/FixtureApp

v1.91.38.0 fix(ios-qa): iPads work, a dropped route no longer relaunches the app, loud boot-token write (#3076)

2026-10-08 07:02:02 +00:00

judge-calibration

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

junit

v1.91.372.0 feat(flaky): gstack-flaky reruns a failed test command once and ledgers the flake (GSTA-158 P1) (#3612)

2026-10-31 15:33:39 +00:00

launch-env-echo

v1.91.243.0 fix(capy): source the launch environment from a 0600 file; no skill fence may print the environment (GSTA-104) (#3449)

2026-10-26 12:00:20 +00:00

merge-train-3345

v1.91.192.0 fix(ship-queue): merge-train hardening — repo key, CHANGELOG damage, 1 MiB fail-open, merged-in verify, --order (GSTA-67) (#3374)

2026-10-25 03:56:50 +00:00

merge-train-3453

v1.91.282.0 fix(ship-queue): one CHANGELOG rule before and after the merge, base keys stay in slot stamps, a stacked child carries past its released parent (#3518)

2026-10-27 21:21:50 +00:00

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

model-panel

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

model-policy-freshness

v1.91.190.0 fix(model-policy-freshness): accept OpenAI deprecated cells with a display name before the ids (#3155) (#3370)

2026-10-25 01:25:19 +00:00

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

multi-agent-wave

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

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

outside-review-severity

v1.91.91.0 fix(review-gates): fail closed on unparsed severities, survive auto-compaction copies, read-only plan-eng-review reports back (Wave 9 Lane B) (#3143)

2026-10-11 18:16:33 +00:00

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

pregate-timing

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

prose-lint

v1.91.273.0 feat(ship): PR bodies open with the problem and a Blast radius line, and gstack-prose-lint catches autopilot phrasing before /ship publishes a CHANGELOG entry or PR body (#3501)

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

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

review-depth

feat(ship): /ship and /autoplan size their review to the diff (GSTA-131) (#3527)

2026-10-28 05:45:54 +00:00

review-ledger

v1.93.21.0 fix(ship): native FIXABLE collects at its own Severity outside gate and risk reviews (GST-987) (#3869)

2026-11-02 21:39:39 +00:00

review-risk

v1.92.61.0 fix(ship): risk classes cover outbound clients, archives, child_process and metering (GST-850) (#3829)

2026-11-02 05:53:59 +00:00

review-wrong-tree

v1.92.65.0 fix(review): every reviewer brief opens with the REVIEWED_TREE step (GST-897) (#3830)

2026-11-02 08:12:24 +00:00

shard-cli-parity

v1.91.163.0 feat(evals): the gate reruns failed cases once and reports a flaky green (GSTA-49 F1) (#3315)

2026-10-20 04:47:11 +00:00

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-queue

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

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

skill-evals

v1.91.359.0 feat(verify): /verify skill and gstack-checks bin (GST-116 PR 1) (#3672)

2026-10-31 09:54:03 +00:00

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

state-matrix-6792

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

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-guard-pty-phase-boundary-stop-screen.txt

v1.91.134.0 feat(evals): readiness-gated paid dispatch (R1), verdict reuse (R2a/R2), receipt store that restores (#3262)

2026-10-18 06:03:18 +00:00

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-agent-payload-2.1.292.json

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

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

claude-usage-2.1.292.json

v1.91.316.0 ship: token cap with real meters and fresh-context delegation (GSTA-152 PR A) (#3593)

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

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

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

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

context-restore-fragment-match-captures.json

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

context-restore-transcript.jsonl

v1.91.272.0 feat(skills): absorb pstack's blast radius, transcript recall, vet-the-number and design-twice as lazy passes (#3500)

2026-10-27 09:59:09 +00:00

cookie-judge-train42-replies.json

v1.91.310.0 fix(flaky): the cookie workflow judge sends the response schema, released on GStack Minder's ruling (GSTA-139 S3) (#3581)

2026-10-29 06:03:55 +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-cd-chain.json

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

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-plan-eng-wc-bytes.json

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-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-separator-collision.json

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

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-audit-two-file-grep.json

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

coverage-audit-wc-anchor.json

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

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

credential-rejection-39696775546.json

v1.91.183.0 fix(evals): a rejected API key is INFRA, never 131 assertion reds and reruns (#3361)

2026-10-23 18:05:39 +00:00

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-floor-focus-cover-all.json

v1.91.281.0 fix(flaky): repair four paid gate detectors, the design-floor focus picker and the judged review/plan-review prose (GSTA-128) (#3516)

2026-10-27 19:40:06 +00:00

design-floor-focus-picker.ts

v1.91.281.0 fix(flaky): repair four paid gate detectors, the design-floor focus picker and the judged review/plan-review prose (GSTA-128) (#3516)

2026-10-27 19:40:06 +00:00

design-floor-focus-review-focus.json

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

design-floor-focus-template-0d.json

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

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-motion-finalized.html

v1.91.264.0 feat(design-motion): new /design-motion skill for showcase loops, adapted from Elaya's design-to-motion (GSTA-92 phase 2) (#3430)

2026-10-27 03:04:06 +00:00

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-39199692993.json

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

design-ui-focus-capture-39298269902-a1.json

v1.91.162.0 feat(evals): merge-train workflow side, inert behind the train policy block (GSTA-49 T1b) (#3279)

2026-10-20 02:13:39 +00:00

design-ui-focus-capture-39298269902-a2.json

v1.91.162.0 feat(evals): merge-train workflow side, inert behind the train policy block (GSTA-49 T1b) (#3279)

2026-10-20 02:13:39 +00:00

design-ui-focus-capture-39363705692.json

v1.91.167.0 fix(evals): plan-design focus and tpa pitch detectors accept the rewordings Opus 5.5 uses (GSTA-57) (#3320)

2026-10-20 18:05:16 +00:00

design-ui-focus-capture-39852003387.json

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

design-ui-focus-capture-40664336141.json

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

design-ui-focus-capture-41178131219.json

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

design-ui-focus-capture-41186376825.json

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

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

devex-tthw-sdk-call-opus.json

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

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-branch-listing-public.json

v1.91.281.0 fix(flaky): repair four paid gate detectors, the design-floor focus picker and the judged review/plan-review prose (GSTA-128) (#3516)

2026-10-27 19:40:06 +00:00

docsync-candidate-not-found-public.json

v1.91.145.0 fix(evals): qa-only opts in to the read-only grammar; stderr-to-null forms accepted (#3295)

2026-10-19 09:52:57 +00:00

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-help-not-found-public.json

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

docsync-invalid-first-attempt-public.json

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-observer-commands.json

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-phase-read-aborted-public.json

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-read-help-public.json

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-ship-receipt-not-found-public.json

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-spawned-missing-section-public.json

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-state-dir-artifacts-public.json

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

docsync-store-38969924945-bash.json

v1.91.111.0 fix(evals): four PR-gate background reds were a detector, an interface, a helper and a workflow-block defect (#3231)

2026-10-17 00:56:33 +00:00

docsync-two-attempts-public.json

v1.91.281.0 fix(flaky): repair four paid gate detectors, the design-floor focus picker and the judged review/plan-review prose (GSTA-128) (#3516)

2026-10-27 19:40:06 +00:00

dx-error-contract-case.ts

v1.91.114.0 feat(dx): score every error for an AI agent reader (agent-ready error contract + gstack-error-capture) (#3226)

2026-10-17 02:10:12 +00:00

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

exercised-map-replay.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

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

health-detect-legacy.sh

v1.92.68.0 feat(health): Step 1 detects tools with gstack-checks, no check lost (GST-116 PR 2) (#3691)

2026-11-02 09:26:46 +00:00

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

investigate-owned-final-texts-opus.json

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

investigate-owned-question-39195396438.json

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

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

model-policy-freshness.ts

v1.91.45.0 feat: configurable model tiers and advisory freshness (#3073)

2026-10-08 08:00:08 +00:00

module-size-ratchet.json

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

2026-11-02 14:49:46 +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

v1.91.150.0 test(evals): re-pin older paid models to the current generation; prosons and cookie-judge repairs (GSTA-49 TM3) (#3293)

2026-10-19 19:22:29 +00:00

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-ceo-floor-create-quote-wrap.json

v1.91.170.0 fix(autoplan): guard waits for an unflushed journal; plan floor harness reads cropped menus; office-hours reviewer recovers with Write (GSTA-57) (#3326)

2026-10-20 19:02:57 +00:00

plan-ceo-floor-edit-prepublication.json

v1.91.170.0 fix(autoplan): guard waits for an unflushed journal; plan floor harness reads cropped menus; office-hours reviewer recovers with Write (GSTA-57) (#3326)

2026-10-20 19:02:57 +00:00

plan-ceo-floor-toolonly-create.json

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-ceo-floor-unasked-decisions-872e154.json

v1.91.45.0 feat: configurable model tiers and advisory freshness (#3073)

2026-10-08 08:00:08 +00:00

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-design-floor-create-rule-crop.json

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-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

v1.92.32.0 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

qa-caller-child-handoff-2026-10-29.json

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

qa-caller-handoff-order-public.json

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-caller-merge-base-diff-40737741454.json

v1.91.302.0 fix: repair three flaky gate cases from the 2026-10-28 flaky pass (index flags, exploratory QA, cookie auth) (#3553)

2026-10-29 01:58:13 +00:00

qa-caller-read-probe-mtb1007a.json

v1.91.45.0 feat: configurable model tiers and advisory freshness (#3073)

2026-10-08 08:00:08 +00:00

qa-caller-review-plan-40707142223.json

v1.91.302.0 fix: repair three flaky gate cases from the 2026-10-28 flaky pass (index flags, exploratory QA, cookie auth) (#3553)

2026-10-29 01:58:13 +00:00

qa-caller-section-skip-ship-small-cli.json

v1.91.127.0 fix(evals): paid-gate reliability round 2: docsync candidate protocol, scope-block detection, qa fix-loop budgets, lettered consent (#3260)

2026-10-18 00:37:43 +00:00

qa-eval-checkout-ground-truth.json

…

qa-eval-ground-truth.json

…

qa-eval-spa-ground-truth.json

…

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-bookkeeping-joins-public.json

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-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-only-stop-cleanup-public.json

v1.91.145.0 fix(evals): qa-only opts in to the read-only grammar; stderr-to-null forms accepted (#3295)

2026-10-19 09:52:57 +00:00

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

…

review-eval-enum.rb

…

review-eval-vuln.rb

…

review-gate-integrity-opus-reports.json

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

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

sealed-guard-off-golden.json

v1.92.83.0 feat(sealed): skip commits the destination already holds or whose patch landed (GSTA-156 P1) (#3689)

2026-11-02 14:39:24 +00:00

session-update-heartbeat.sh

v1.91.106.0 fix: the 2026-10-15 issue wave (#3209)

2026-10-16 22:00:32 +00:00

shadow-fake-model.ts

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

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

shared-libs-claude-version-probe.json

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-index-flags-loop-read-39173752116.json

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-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-path-ignored-errored-read-40617200857.json

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

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

shared-libs-unsupported-git-opus-reports.json

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-unsupported-git-requests.json

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

ship-coverage-audit-af.json

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

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

ship-hook-consent-2026-10-30.json

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-hook-opus-replies.json

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

ship-local-hook-reply.json

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

ship-local-hook-train-replies.json

v1.91.281.0 fix(flaky): repair four paid gate detectors, the design-floor focus picker and the judged review/plan-review prose (GSTA-128) (#3516)

2026-10-27 19:40:06 +00:00

skill-bin-drift-allowlist.json

v1.91.287.0 feat(write-skill): write, change and diet skills; /learn at half its template size (#3524)

2026-10-28 02:58:29 +00:00

skill-md-size-allowlist.json

v1.92.57.0 fix(hermes): plain skill-start fence that Tirith can resolve, so Hermes can start gstack skills (GST-882) (#3825)

2026-11-02 05:02:04 +00:00

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-manual-wording.json

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

third-party-actions-opus-consent-renders.json

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

third-party-actions-pitch-captures.json

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

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

windows-bash-resolution.json

v1.91.106.0 fix: the 2026-10-15 issue wave (#3209)

2026-10-16 22:00:32 +00:00

workflow-required-steps.json

feat(ship): /ship and /autoplan size their review to the diff (GSTA-131) (#3527)

2026-10-28 05:45:54 +00:00