garrytanandcapy-ai[bot] 049b4693a7 Count an outside review as clean only from its last VERDICT line ...

Every outside-review prompt now asks the reviewer to end with exactly
VERDICT: CLEAN or VERDICT: FINDINGS, and the parser reads a pass only from
that line. Prose no-findings sentences are no longer evidence for clean.
Codex's structured review and /codex review run through codex exec, since
codex review --base takes no prompt and could never give the line.

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

2026-11-07 20:18:01 +00:00

..

preamble

feat: retire /investigate after a no-gain eval (GST-1717) (#4110)

2026-11-07 06:52:04 +00:00

aside.ts

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

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

autoplan-driver.ts

fix(autoplan): export --public drops owner replies and redacts quoted owner words (GST-1243) (#3967)

2026-11-04 03:42:16 +00:00

browse.ts

v1.91.71.0 feat(install): gstack-doctor --check one-line verdict, gstack-capy-install, lazy Chromium (multi-agent wave PR A) (#3116)

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

composition.ts

feat: cut standalone /plan-eng-review; /autoplan keeps its eng phase (GST-1698) (#4108)

2026-11-07 04:17:35 +00:00

confidence.ts

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

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

constants.ts

fix(ship): make the five judge-flagged workflow spots match the code (GST-1346) (#4004)

2026-11-04 23:50:18 +00:00

contract-done-means.ts

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

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

coordinator-contract.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

defensive-review.ts

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

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

design-checklist.ts

v1.91.260.0 feat(design-review,plan-design-review): craft audit and Persuade plan checks; craft tells as checker-only catalog entries (GSTA-92 phase 2) (#3433)

2026-10-27 01:14:07 +00:00

design-craft.ts

v1.91.260.0 feat(design-review,plan-design-review): craft audit and Persuade plan checks; craft tells as checker-only catalog entries (GSTA-92 phase 2) (#3433)

2026-10-27 01:14:07 +00:00

design-doc-discovery.ts

v1.91.220.0 fix(office-hours,plan-reviews): write the plan-mode copy through to the design doc and warn when it is newer (#542) (#3408)

2026-10-25 22:31:08 +00:00

design.ts

Require the daemon secret and loopback Host/Origin on the design and iOS QA daemons (#4117)

2026-11-07 07:39:51 +00:00

dispatch-rules.ts

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

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

dx.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

fix-check.ts

v1.91.331.0 revert(review): restore pre-#3621 reviewer briefs (no-loss round 3) (#3638)

2026-10-30 10:40:19 +00:00

free-text-file.ts

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

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

gate-scan.ts

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

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

gbrain.ts

feat: retire /investigate after a no-gain eval (GST-1717) (#4110)

2026-11-07 06:52:04 +00:00

index.ts

v1.94.22.0 feat(skills): when-to-use descriptions, wider triggers and contract blocks for /investigate, /review, /qa, /verify (GST-1088 lane B) (#3909)

2026-11-03 15:21:29 +00:00

learnings.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

make-pdf.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

model-overlay.ts

v1.91.305.0 feat: render gstack per model with modules left out, measured before any model gets less (GSTA-140 PR 1a) (#3554)

2026-10-29 04:22:41 +00:00

outside-voice-steps.ts

Count an outside review as clean only from its last VERDICT line

2026-11-07 20:18:01 +00:00

outside-voice.ts

Count an outside review as clean only from its last VERDICT line

2026-11-07 20:18:01 +00:00

plan-gates.ts

feat: crew PRs carry their brief's Plan line; ship-queue ready and land check it (GST-1751) (#4118)

2026-11-07 09:53:38 +00:00

plan-reality.ts

v1.91.247.0 fix(plan-eng-review): define the three references its judged text left dangling (GSTA-91) (#3421)

2026-10-26 13:36:43 +00:00

plan-review.ts

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

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

preamble-hoist.ts

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

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

preamble.ts

v1.91.305.0 feat: render gstack per model with modules left out, measured before any model gets less (GSTA-140 PR 1a) (#3554)

2026-10-29 04:22:41 +00:00

qa.ts

v1.93.40.0 fix(ship): Step 9.2.1 QA reports go to a git-excluded run dir, not the product tree (GST-969) (#3898)

2026-11-03 03:14:57 +00:00

question-tuning.ts

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

redact-doc.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

review-army.ts

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

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

review-dashboard.ts

feat: cut standalone /plan-eng-review; /autoplan keeps its eng phase (GST-1698) (#4108)

2026-11-07 04:17:35 +00:00

review-scope.ts

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

runtime-root.ts

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

sections.ts

v1.91.305.0 feat: render gstack per model with modules left out, measured before any model gets less (GSTA-140 PR 1a) (#3554)

2026-10-29 04:22:41 +00:00

shared-libs.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

ship-driver.ts

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

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

sideways.ts

feat: retire /investigate after a no-gain eval (GST-1717) (#4110)

2026-11-07 06:52:04 +00:00

spec-review.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

tasks-section.ts

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

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

test-value.ts

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

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

testing.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

third-party-actions.ts

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

transcripts.ts

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

types.ts

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

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

utility.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

voice-triggers.ts

feat: cut standalone /plan-eng-review; /autoplan keeps its eng phase (GST-1698) (#4108)

2026-11-07 04:17:35 +00:00