garrytanandcapy-ai[bot] 1893a73fcb feat(review): variant G parts 1 and 3: blocking floor in both prose voices, specialists at medium (GSTA-167) ...

Part 1: the native adversarial and outside-voice prompts end with the blocking
floor ("would fail a test, break production, or lose data or secrets") and ask
each finding for Severity and Blocks: yes|no. Additive rule: a finding is
CRITICAL when its label rule says so or it says Blocks: yes; Blocks: no never
lowers one (proseVoiceSeverity, BLOCKING_FLOOR in lib/review-scope.ts).
Part 3: ROLE_EFFORT puts specialists at medium; Red Team, native adversarial
and fix-check stay full; light's batched specialist (carries the Red Team
prompt) stays full; --no-tiers sends specialists to host.

Repinned reviewer briefs with no-loss replay G1 (live Arm G1, not yet run):
ship/sections/review-army.md, ship/sections/adversarial.md,
review/sections/adversarial.md, lib/review-depth.ts. Merge only on G1's pass.
Review-skill parity ratio 1.3136 -> 1.3180 and the gstack-review size pins
+537 for the approved +0.3k tokens per voice.

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

2026-10-30 17:54:56 +00:00

..

code-intelligence

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

cso

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

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

design-lint

v1.91.274.0 feat(design-html,design-review): run gstack-design-lint; copy tier at its lines; waivers replace craft_exceptions (hallmark phase 2) (#3507)

2026-10-27 11:03:59 +00:00

diagram-render

v1.91.241.0 fix(deps): bump dompurify, MCP SDK, zod, body-parser, fast-uri, ip-address to OSV-fixed releases (#3462) (#3463)

2026-10-26 10:44:36 +00:00

gate-diff

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

pregate

v1.91.329.0 pregate: always run the whole-tree tests listed in .gstack/always-run.json (GST-167 PR 1, GST-98) (#3626)

2026-10-30 03:29:41 +00:00

agent-model.ts

v1.91.332.0 feat(capy): remember a user's model preference (agent_model); every Capy session reads factory.md (#3634)

2026-10-30 12:03:08 +00:00

approval-citations.ts

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

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

approval-classes.ts

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

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

approval-record.ts

v1.91.314.0 feat(autoplan): carry the owner's answer forward, gate ELI5 field, stacked approvals import (#3583)

2026-10-29 09:58:34 +00:00

aside-render.ts

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

autoplan-admission.ts

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

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

autoplan-budget.ts

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

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

autoplan-carry.ts

v1.91.314.0 feat(autoplan): carry the owner's answer forward, gate ELI5 field, stacked approvals import (#3583)

2026-10-29 09:58:34 +00:00

autoplan-checkpoint.ts

v1.91.115.0 feat: field list 2 wave A: autoplan round cap and public export, eval-plan diagnostics and model rules, --for review-voice (#3234)

2026-10-17 02:40:45 +00:00

autoplan-confirm.ts

v1.91.115.0 feat: field list 2 wave A: autoplan round cap and public export, eval-plan diagnostics and model rules, --for review-voice (#3234)

2026-10-17 02:40:45 +00:00

autoplan-export.ts

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

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

autoplan-gate-cost.ts

v1.91.269.0 feat(autoplan): gates print their cost, approvals mirror to the Captain's drive, Eng asks for a perf budget (GSTA-114 lane F, PR 3) (#3496)

2026-10-27 06:54:56 +00:00

autoplan-gate.ts

v1.91.314.0 feat(autoplan): carry the owner's answer forward, gate ELI5 field, stacked approvals import (#3583)

2026-10-29 09:58:34 +00:00

autoplan-migrate.ts

v1.91.97.0 fix: closable unattended /autoplan runs on Capy (field wave B, items 6-13) (#3165)

2026-10-13 15:17:39 +00:00

autoplan-phase-publication.ts

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

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

autoplan-plan-text.ts

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

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

autoplan-prompts.ts

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

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

autoplan-public.ts

v1.91.115.0 feat: field list 2 wave A: autoplan round cap and public export, eval-plan diagnostics and model rules, --for review-voice (#3234)

2026-10-17 02:40:45 +00:00

autoplan-reconcile.ts

v1.91.115.0 feat: field list 2 wave A: autoplan round cap and public export, eval-plan diagnostics and model rules, --for review-voice (#3234)

2026-10-17 02:40:45 +00:00

autoplan-revise.ts

v1.91.314.0 feat(autoplan): carry the owner's answer forward, gate ELI5 field, stacked approvals import (#3583)

2026-10-29 09:58:34 +00:00

autoplan-run.ts

v1.91.314.0 feat(autoplan): carry the owner's answer forward, gate ELI5 field, stacked approvals import (#3583)

2026-10-29 09:58:34 +00:00

autoplan-scope.ts

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

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

autoplan-state.ts

v1.91.314.0 feat(autoplan): carry the owner's answer forward, gate ELI5 field, stacked approvals import (#3583)

2026-10-29 09:58:34 +00:00

autoplan-timing.ts

v1.91.70.0 feat(unattended): artifact contract + validator, unattended session kind, findings-derived review log, gate list (multi-agent wave B-core) (#3115)

2026-10-10 23:26:08 +00:00

banned-terms.ts

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

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

bin-context.ts

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

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

bun-isolation.ts

v1.91.227.0 fix(windows): shell bins pass NUL as Bun's empty config when MSYS path conversion is off (#3415) (#3431)

2026-10-26 04:32:27 +00:00

captain-brief.ts

v1.91.314.0 feat(autoplan): carry the owner's answer forward, gate ELI5 field, stacked approvals import (#3583)

2026-10-29 09:58:34 +00:00

changelog-check.ts

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

ci-gate.ts

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

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

claude-bin.ts

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

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

claude-code-migration.ts

v1.91.332.0 feat(capy): remember a user's model preference (agent_model); every Capy session reads factory.md (#3634)

2026-10-30 12:03:08 +00:00

claude-code-windows-job.ts

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

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

claude-code.ts

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

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

claude-journal-records.ts

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

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

claude-owned-journal.ts

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

claude-public-transcript.ts

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

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

claude-usage.ts

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

conductor-env-shim.ts

v1.58.1.0 feat: hermetic local E2E + Conductor prose AskUserQuestion (#2004)

2026-06-14 11:40:57 -07:00

context-bill.ts

v1.91.242.0 fix(context-bill): bill installed skills whose SKILL.md is a symlink (GSTA-97) (#3423)

2026-10-26 10:57:52 +00:00

contributor-mode.ts

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

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

coordinator-contract.ts

v1.91.133.0 docs(coordinator-contract): Before done treats requires-remote as unfinished (#3261)

2026-10-18 02:51:19 +00:00

decision-trail.ts

v1.91.314.0 feat(autoplan): carry the owner's answer forward, gate ELI5 field, stacked approvals import (#3583)

2026-10-29 09:58:34 +00:00

design-catalog.ts

v1.91.274.0 feat(design-html,design-review): run gstack-design-lint; copy tier at its lines; waivers replace craft_exceptions (hallmark phase 2) (#3507)

2026-10-27 11:03:59 +00:00

design-detect-contract.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

design-md.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

doctor-components.ts

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

dom-dump-script.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

dom-dump.js

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

dx-error-capture.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-error-contract.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

egress-receipt.ts

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

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

error-handling.ts

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

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

eval-model.ts

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

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

eval-models.ts

v1.91.115.0 feat: field list 2 wave A: autoplan round cap and public export, eval-plan diagnostics and model rules, --for review-voice (#3234)

2026-10-17 02:40:45 +00:00

eval-plan.ts

v1.91.115.0 feat: field list 2 wave A: autoplan round cap and public export, eval-plan diagnostics and model rules, --for review-voice (#3234)

2026-10-17 02:40:45 +00:00

evidence-bundle.ts

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

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

factory-scorecard.ts

v1.91.333.0 fix(scorecard): --now bounds every windowed line; recommended-harness week is 83 PRs (GST-135) (#3635)

2026-10-30 12:16:21 +00:00

frontend-scope.ts

v1.91.160.0 fix(scope,review,ship): recognise Dart and Flutter in diff scope and test detection (#3284) (#3300)

2026-10-20 01:06:17 +00:00

fs-atomic.ts

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

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

fs-utils.ts

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

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

gate-cost-history.ts

v1.91.328.0 ship-queue: screen only when the selector restores every case; unscreened PRs fill train seats (GSTA-165 1a) (#3619)

2026-10-30 03:14:00 +00:00

gate-cost.ts

v1.91.138.0 feat(evals): red-head and READY-arrival replays for the gate-cost model (GSTA-49 T0) (#3274)

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

gate-list.ts

v1.91.314.0 feat(autoplan): carry the owner's answer forward, gate ELI5 field, stacked approvals import (#3583)

2026-10-29 09:58:34 +00:00

gate-outcomes.ts

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

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

gbrain-exec.ts

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

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

gbrain-guards.ts

fix(sync-gbrain): autopilot refusal names the matched pid and command and how to proceed (#3360 part 1) (#3377)

2026-10-25 06:51:16 +00:00

gbrain-local-status.ts

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

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

gbrain-repo-policy-client.ts

v1.91.194.0 feat(memorable): per-remote recall opt-in for read-only repos; recall veto fails closed (#3359) (#3381)

2026-10-25 05:06:30 +00:00

gbrain-sources.ts

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

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

gbrain-supabase-provision.ts

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

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

greptile-early.ts

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

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

gstack-decision-semantic.ts

v1.57.5.0 feat: cross-session decision memory + gbrain dream-stage call graph (#1910)

2026-06-08 06:20:58 -07:00

gstack-decision.ts

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

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

gstack-memory-helpers.ts

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

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

gstack-post.ts

v1.91.320.0 fix(pregate,gstack-post): PREGATE_NO_LANE names the base policy when a branch adds its own lane; pr-body refuses a body holding a title twice (#3579)

2026-10-29 16:22:12 +00:00

harness-qm.ts

v1.91.293.0 fix(harness): error lines print again; register qm stops at QM's pack cap instead of claiming QM works (GSTA-135) (#3532)

2026-10-28 10:16:23 +00:00

harness-register.ts

v1.91.317.0 feat(harness): trigger-first skill descriptions, hybrid OpenClaw layout, opt-in --context block (GSTA-135) (#3555)

2026-10-29 13:28:08 +00:00

headless-artifacts.ts

v1.91.314.0 feat(autoplan): carry the owner's answer forward, gate ELI5 field, stacked approvals import (#3583)

2026-10-29 09:58:34 +00:00

install-verdict.ts

v1.91.258.0 feat(capy-install): project floor, --for none, WARN for behind and Node-only pins, in-place review-voice upgrade, /cso env hygiene (GSTA-114 lane F, PR 1) (#3475)

2026-10-26 23:27:10 +00:00

is-conductor.ts

v1.58.1.0 feat: hermetic local E2E + Conductor prose AskUserQuestion (#2004)

2026-06-14 11:40:57 -07:00

issue-links.ts

v1.91.262.0 fix(release-cut,ship-queue): the weekly release accepts a train-gated commit; cross-repo refs, run ids, pr-body section merge, pregate by tree (#3483)

2026-10-27 01:45:08 +00:00

jsonl-store.ts

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

lane-ownership.ts

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

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

markdown-sections.ts

v1.91.172.0 feat(capy): approvals per thread, Captain plan briefs and before/after PR images (#3328)

2026-10-20 23:55:41 +00:00

memory-ingest-landing.ts

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

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

model-catalog.ts

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

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

model-policy-cli.ts

v1.91.332.0 feat(capy): remember a user's model preference (agent_model); every Capy session reads factory.md (#3634)

2026-10-30 12:03:08 +00:00

model-policy-freshness-github.ts

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

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

model-policy-freshness-parser-worker.ts

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

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

model-policy-freshness-publication.ts

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

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

model-policy-freshness-sources.ts

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

model-policy-freshness.ts

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

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

model-policy-notice.ts

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

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

model-policy.ts

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

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

motion-capture.ts

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

motion-encode.ts

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

office-hours-review.ts

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

outside-consent.ts

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

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

outside-review-result.ts

v1.91.198.0 fix(outside-review): a reviewer's own "not ready" verdict floors advisory-only findings (#3329, port of #3364) (#3376)

2026-10-25 06:38:53 +00:00

outside-voice-api.ts

v1.91.72.0 feat(autoplan): unattended runner gstack-autoplan next|submit, pluggable outside voice, review checklists, spec-loop cap (multi-agent wave B-runner) (#3117)

2026-10-11 00:32:15 +00:00

outside-voice-runner.ts

v1.91.72.0 feat(autoplan): unattended runner gstack-autoplan next|submit, pluggable outside voice, review checklists, spec-loop cap (multi-agent wave B-runner) (#3117)

2026-10-11 00:32:15 +00:00

owner-brief.ts

v1.91.269.0 feat(autoplan): gates print their cost, approvals mirror to the Captain's drive, Eng asks for a perf budget (GSTA-114 lane F, PR 3) (#3496)

2026-10-27 06:54:56 +00:00

path-spelling.ts

v1.91.89.0 fix(windows,setup): Git Bash hook false-positive recovery, incoming-checker auto-update, setup never deletes its own checkout (Wave 9 Lane A0) (#3140)

2026-10-11 16:48:11 +00:00

plan-reality.ts

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

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

pr-shots.ts

v1.91.172.0 feat(capy): approvals per thread, Captain plan briefs and before/after PR images (#3328)

2026-10-20 23:55:41 +00:00

pr-wait-github.ts

v1.91.278.0 fix(ship-queue): readiness takes dispatched Free Tests, stamp paths accept tentative key versions, ready and train build read the base overlap, pr-wait --exclude, restamp prints the corrected order (#3514)

2026-10-27 15:11:13 +00:00

pr-wait.ts

v1.91.278.0 fix(ship-queue): readiness takes dispatched Free Tests, stamp paths accept tentative key versions, ready and train build read the base overlap, pr-wait --exclude, restamp prints the corrected order (#3514)

2026-10-27 15:11:13 +00:00

pricing.ts

v1.91.100.0 fix: a gbrain LongMemEval call plan prices in full (gpt-4o, Voyage rerankers, dated Claude snapshots) (#3172)

2026-10-13 21:31:07 +00:00

prose-lint.ts

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

qa-deadline.ts

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

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

qa-evidence.ts

v1.91.178.0 fix(qa): materialize names the next write instead of qualifying the verdict by report root (flaky pass 2026-10-22) (#3341)

2026-10-22 19:57:52 +00:00

redact-audit-log.ts

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

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

redact-engine.ts

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

redact-patterns.ts

v1.91.313.0 fix(redact): pii.phone skips bare numeric constants; pii.email skips package@version filenames (#3578)

2026-10-29 08:53:23 +00:00

regen.ts

v1.91.306.0 ship-receipt: carry across regenerated outputs and onto a reviewed tree after a rebase (#3564)

2026-10-29 04:37:43 +00:00

remote-identity.ts

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

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

restamp.ts

v1.91.308.0 fix(restamp): keep a four-part package.json version in repos that declare it (#3557)

2026-10-29 05:35:56 +00:00

result-codes-budget.ts

feat(ship): GSTA-167 turn levers on the restored reviewers: ship preflight/release bins, own-jam meter, dispatch-pair metering, ship/DRIVER.md

2026-10-30 11:02:32 +00:00

result-codes-capy.ts

v1.91.314.0 feat(autoplan): carry the owner's answer forward, gate ELI5 field, stacked approvals import (#3583)

2026-10-29 09:58:34 +00:00

result-codes-release.ts

v1.91.307.0 ship: proportional review depth (light, standard, full) with depth-checked receipts (#3567)

2026-10-29 04:55:01 +00:00

result-codes.ts

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

review-collect.ts

feat(review): variant G part 4: data files no code names are docs in classifyDiff, untested state-matrix cells map below the floor per cell (GSTA-167 PR-a)

2026-10-30 17:13:11 +00:00

review-depth.ts

feat(review): variant G parts 1 and 3: blocking floor in both prose voices, specialists at medium (GSTA-167)

2026-10-30 17:54:56 +00:00

review-evidence.ts

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

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

review-scope.ts

feat(review): variant G parts 1 and 3: blocking floor in both prose voices, specialists at medium (GSTA-167)

2026-10-30 17:54:56 +00:00

runtime-pins.ts

v1.91.110.0 fix(capy): install the project's pinned Node; launch Bun through a bun-only directory (#3233)

2026-10-17 00:41:41 +00:00

sanitize-echo.ts

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

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

script-invocation.ts

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

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

sealed-guard.ts

fix(pregate): sealed labels the checked commit, not "pushed" (#3565) (#3566)

2026-10-29 13:56:33 +00:00

ship-bin-common.ts

feat(ship): GSTA-167 turn levers on the restored reviewers: ship preflight/release bins, own-jam meter, dispatch-pair metering, ship/DRIVER.md

2026-10-30 11:02:32 +00:00

ship-budget-calibration.json

feat(ship): GSTA-167 turn levers on the restored reviewers: ship preflight/release bins, own-jam meter, dispatch-pair metering, ship/DRIVER.md

2026-10-30 11:02:32 +00:00

ship-budget-cli.ts

feat(ship): variant E orchestration: one program per review pass and Step 14.5 audit, the review child starts at Step 9, a metered dispatch:docs role, and the driver's record headings (GSTA-167)

2026-10-30 15:28:39 +00:00

ship-budget.ts

feat(ship): variant E orchestration: one program per review pass and Step 14.5 audit, the review child starts at Step 9, a metered dispatch:docs role, and the driver's record headings (GSTA-167)

2026-10-30 15:28:39 +00:00

ship-handoff.ts

feat(ship): GSTA-167 turn levers on the restored reviewers: ship preflight/release bins, own-jam meter, dispatch-pair metering, ship/DRIVER.md

2026-10-30 11:02:32 +00:00

ship-policy.ts

v1.91.275.0 fix(ship-policy): DOCS_CAPS_KEY_VERSION is 1.91.270.0; key versions move through stamp_paths at the slot stamp (#3511)

2026-10-27 11:18:53 +00:00

ship-preflight.ts

feat(review): variant G part 4: data files no code names are docs in classifyDiff, untested state-matrix cells map below the floor per cell (GSTA-167 PR-a)

2026-10-30 17:13:11 +00:00

ship-queue-dispatch-ci.ts

v1.91.263.0 feat(ship-queue): screens read from the run, train watch/forget/prune --stale, verify --post-merge, ready --dispatch-ci, --stack-tests (#3484)

2026-10-27 02:48:59 +00:00

ship-queue-gate.ts

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

ship-queue-post-merge.ts

v1.91.263.0 feat(ship-queue): screens read from the run, train watch/forget/prune --stale, verify --post-merge, ready --dispatch-ci, --stack-tests (#3484)

2026-10-27 02:48:59 +00:00

ship-queue-screen.ts

v1.91.263.0 feat(ship-queue): screens read from the run, train watch/forget/prune --stale, verify --post-merge, ready --dispatch-ci, --stack-tests (#3484)

2026-10-27 02:48:59 +00:00

ship-queue-stack-tests.ts

v1.91.263.0 feat(ship-queue): screens read from the run, train watch/forget/prune --stale, verify --post-merge, ready --dispatch-ci, --stack-tests (#3484)

2026-10-27 02:48:59 +00:00

ship-queue-train-cli.ts

v1.91.263.0 feat(ship-queue): screens read from the run, train watch/forget/prune --stale, verify --post-merge, ready --dispatch-ci, --stack-tests (#3484)

2026-10-27 02:48:59 +00:00

ship-queue-train-forget.ts

v1.91.263.0 feat(ship-queue): screens read from the run, train watch/forget/prune --stale, verify --post-merge, ready --dispatch-ci, --stack-tests (#3484)

2026-10-27 02:48:59 +00:00

ship-queue-train-github.ts

v1.91.263.0 feat(ship-queue): screens read from the run, train watch/forget/prune --stale, verify --post-merge, ready --dispatch-ci, --stack-tests (#3484)

2026-10-27 02:48:59 +00:00

ship-queue-train-ready.ts

v1.91.328.0 ship-queue: screen only when the selector restores every case; unscreened PRs fill train seats (GSTA-165 1a) (#3619)

2026-10-30 03:14:00 +00:00

ship-queue-train-record.ts

v1.91.286.0 feat(ship-queue): the ship size cap composes across a merge train; verify refuses a stale all-merged train (#3519) (#3522)

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

ship-queue-train-verdict.ts

v1.91.255.0 fix(ship-queue): fill trains at 3 READY PRs or one hour, and price every case shard's trial (#3478)

2026-10-26 20:33:32 +00:00

ship-queue-train-verify.ts

v1.91.286.0 feat(ship-queue): the ship size cap composes across a merge train; verify refuses a stale all-merged train (#3519) (#3522)

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

ship-queue-train-watch.ts

v1.91.263.0 feat(ship-queue): screens read from the run, train watch/forget/prune --stale, verify --post-merge, ready --dispatch-ci, --stack-tests (#3484)

2026-10-27 02:48:59 +00:00

ship-queue-train.ts

v1.91.328.0 ship-queue: screen only when the selector restores every case; unscreened PRs fill train seats (GSTA-165 1a) (#3619)

2026-10-30 03:14:00 +00:00

ship-queue.ts

v1.91.307.0 ship: proportional review depth (light, standard, full) with depth-checked receipts (#3567)

2026-10-29 04:55:01 +00:00

ship-receipt-depth.ts

feat(review): variant G part 4: data files no code names are docs in classifyDiff, untested state-matrix cells map below the floor per cell (GSTA-167 PR-a)

2026-10-30 17:13:11 +00:00

ship-receipt-docs.ts

v1.91.270.0 feat(ship): version-less repos, docs-audit record and caps, the frozen-scope paid case, and the review-loop follow-ups (#3487)

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

ship-receipt-prose.ts

v1.91.278.0 fix(ship-queue): readiness takes dispatched Free Tests, stamp paths accept tentative key versions, ready and train build read the base overlap, pr-wait --exclude, restamp prints the corrected order (#3514)

2026-10-27 15:11:13 +00:00

ship-receipt.ts

v1.91.315.0 ship-receipt: carry a stacked child after its parent lands (#3572)

2026-10-29 10:12:18 +00:00

ship-release.ts

feat(ship): GSTA-167 turn levers on the restored reviewers: ship preflight/release bins, own-jam meter, dispatch-pair metering, ship/DRIVER.md

2026-10-30 11:02:32 +00:00

skill-bill.ts

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-triggers.ts

v1.91.317.0 feat(harness): trigger-first skill descriptions, hybrid OpenClaw layout, opt-in --context block (GSTA-135) (#3555)

2026-10-29 13:28:08 +00:00

source-root.ts

v1.91.97.0 fix: closable unattended /autoplan runs on Capy (field wave B, items 6-13) (#3165)

2026-10-13 15:17:39 +00:00

spec-review-cap.ts

v1.91.72.0 feat(autoplan): unattended runner gstack-autoplan next|submit, pluggable outside voice, review checklists, spec-loop cap (multi-agent wave B-runner) (#3117)

2026-10-11 00:32:15 +00:00

spend-ledger.ts

v1.91.115.0 feat: field list 2 wave A: autoplan round cap and public export, eval-plan diagnostics and model rules, --for review-voice (#3234)

2026-10-17 02:40:45 +00:00

staging-guard.ts

v1.56.1.0 fix(sync): staging-dir ownership guard + resume-correctness fixes (#1802) (#1856)

2026-06-07 06:51:10 -07:00

state-matrix.ts

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

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

state-root.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

tracker-guard.ts

v1.66.1.0 feat: content binding — evidence ledger, wtree staleness, tracker trust envelope, fail-closed hooks (#2603)

2026-08-16 09:53:31 -07:00

transcript-consent.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

tree-receipt.ts

v1.91.278.0 fix(ship-queue): readiness takes dispatched Free Tests, stamp paths accept tentative key versions, ready and train build read the base overlap, pr-wait --exclude, restamp prints the corrected order (#3514)

2026-10-27 15:11:13 +00:00

version-gate-train.ts

v1.91.237.0 fix(version-gate): a release output regenerated at the base VERSION is not a stamp (#3451)

2026-10-26 09:17:09 +00:00

version-source.ts

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

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

worktree.ts

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