garrytanandcapy-ai[bot] 4473f71da4 fix(eval-plan): pilot start keeps the R54 refusal; --tier-question rejects a flag ...

Review pass 1 (full depth) found the frontier refusal could be skipped by
starting a pilot on Haiku or Sonnet arms behind a dry run made on other arms,
or behind a dry-run.json written before the check existed. startPilot now
refuses a pilot whose every arm is Haiku or Sonnet unless its dry run recorded
a tier question. dry-run --tier-question no longer takes the next flag as its
answer. The testing doc now says the frontier re-cost is printed for
comparison with the brief cap, not enforced.

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

2026-11-01 23:50:50 +00:00

..

designs

v1.91.351.0 fix(skill-evals): close four Lane A check-command holes (GST-377) (#3664)

2026-10-31 05:17:59 +00:00

evals

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

images

feat: Completeness Principle — Boil the Lake (v0.6.1) (#140)

2026-03-17 16:34:08 -05:00

spikes

v1.61.0.0 fix wave: guards failing open / silent failures (9 fixes, 4 community PRs absorbed) (#2472)

2026-08-08 09:28:45 -07:00

ADDING_A_HOST.md

v1.92.22.0 feat: Gemini CLI host, and older installs drop the dev toolchain (#3778)

2026-11-01 09:35:42 +00:00

agent-ready-errors.md

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

askuserquestion-cjk.md

v1.56.0.0 Token-reduction Phase B + AUQ paranoid safety net (#1849)

2026-06-04 11:14:43 -07:00

askuserquestion-split.md

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

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

autoplan-guard-troubleshooting.md

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

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

BROWSER_INTERNALS.md

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

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

captain.md

v1.92.12.0 feat: wave PRs land 3 to 6 queued PRs as one train slot (gstack-ship-queue wave) (GST-574) (#3772)

2026-11-01 05:29:22 +00:00

capy-install.md

v1.92.18.0 fix(install): --project resolves to its git toplevel and refuses a repo slug (GST-743) (#3783)

2026-11-01 07:41:10 +00:00

CHANGELOG_STYLE.md

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

CONTRIBUTOR_REFERENCE.md

v1.92.11.0 feat: design mockups with Gemini when there's no OpenAI key (#990) (#3768)

2026-11-01 05:17:06 +00:00

cso-release-qualification.md

v1.91.378.0 fix(cso): pin scout-sbom-indexer source to 1.24.0, refuse floating source tags (GST-495) (#3699)

2026-10-31 18:12:53 +00:00

cso-scanners.md

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

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

design-lint.md

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

domain-skills.md

v1.91.246.0 docs(readme): cut the README to the first ten minutes; move everything else to docs/ pages verbatim (GSTA-99) (#3428)

2026-10-26 13:22:30 +00:00

eval-calls.md

v1.91.98.0 fix: plan obligations meet repo gates; priced paid gates; machine-proved restamps (field wave C, items 14-17) (#3166)

2026-10-13 15:38:41 +00:00

eval-models.md

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

explanation-diataxis-in-gstack.md

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

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

flaky.md

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

gbrain-quick-tour.md

v1.91.246.0 docs(readme): cut the README to the first ten minutes; move everything else to docs/ pages verbatim (GSTA-99) (#3428)

2026-10-26 13:22:30 +00:00

gbrain-sync-errors.md

v1.92.38.0 fix(brain-sync): set local edits aside around the retry merge and say why it failed (#3704) (#3728)

2026-11-01 20:15:10 +00:00

gbrain-sync.md

v1.92.38.0 fix(brain-sync): set local edits aside around the retry merge and say why it failed (#3704) (#3728)

2026-11-01 20:15:10 +00:00

gbrain-write-surfaces.md

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

hosts.md

v1.92.23.0 feat(harness): opt-in start hook for OpenClaw and Hermes, so agents run a skill's start command (GST-718) (#3786)

2026-11-01 09:52:31 +00:00

howto-bring-up-a-first-deploy.md

v1.91.151.0 fix: contributor ports — plan-eng-review structure id, context checkpoint gaps, first-deploy how-to (#3299)

2026-10-19 19:44:10 +00:00

howto-diagrams-and-formats.md

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

howto-document-a-shipped-feature.md

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

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

howto-ios-testing-with-gstack.md

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

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

install.md

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

loadouts.md

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

memorable-workflow-memory.md

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

model-policy.md

v1.91.350.0 feat(review): GSTA-167 variant G reviewer stack: blocking floor in both voices, one batched specialist, data-file classifier (#3660)

2026-10-31 05:06:03 +00:00

ON_THE_LOC_CONTROVERSY.md

feat: gstack v1 — simpler prompts + real LOC receipts (v1.0.0.0) (#1039)

2026-04-18 15:05:42 +08:00

OPENCLAW_PUBLISHING.md

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

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

OPENCLAW.md

v1.92.23.0 feat(harness): opt-in start hook for OpenClaw and Hermes, so agents run a skill's start command (GST-718) (#3786)

2026-11-01 09:52:31 +00:00

OVERLAY_BENCHMARK_CONTRACT.md

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

pregate.md

v1.92.44.0 fix(pregate): literals stops treating same-stem sibling files as the changed module (GST-820) (#3814)

2026-11-01 22:50:47 +00:00

privacy.md

v1.91.246.0 docs(readme): cut the README to the first ten minutes; move everything else to docs/ pages verbatim (GSTA-99) (#3428)

2026-10-26 13:22:30 +00:00

proactive.md

v1.92.6.0 feat: proactive core routes only the four core skills, and they carry their trigger phrases (#3770)

2026-11-01 01:25:15 +00:00

PROJECT_STRUCTURE.md

v1.92.22.0 feat: Gemini CLI host, and older installs drop the dev toolchain (#3778)

2026-11-01 09:35:42 +00:00

qa-without-a-webpage.md

v1.91.246.0 docs(readme): cut the README to the first ten minutes; move everything else to docs/ pages verbatim (GSTA-99) (#3428)

2026-10-26 13:22:30 +00:00

recommended-harness.md

v1.92.35.0 fix(pregate): a timeout-only policy keeps lane verdicts, warn lanes runs the tests, [] keeps removed-test suites (GST-775) (#3792)

2026-11-01 16:28:03 +00:00

reference-qa-deadlines.md

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

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

releases.md

v1.91.292.0 Stable channel: a regression exception beside the security one, and the stale weekly wording (#3533)

2026-10-28 09:59:40 +00:00

REMOTE_BROWSER_ACCESS.md

v1.91.155.0 fix(browse): a busy tab no longer blocks every command with "Daemon busy" (port of #3250) (#3301)

2026-10-19 21:30:33 +00:00

review-policy.md

v1.92.37.0 fix: review briefs check template slots before pasting reviewer text (GST-797) (#3797)

2026-11-01 17:35:19 +00:00

ship-budget.md

v1.92.40.0 ship-budget: a subagent's /ship cost says it is the root counter, an upper bound (GST-467) (#3696)

2026-11-01 20:45:39 +00:00

ship-policy.md

v1.92.42.0 fix(ship): notes-only review passes bind; carry handles large diffs; scoped carry route (GST-430, GST-448, GST-442, GST-444) (#3694)

2026-11-01 21:26:59 +00:00

skills.md

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

SLOP_SCAN.md

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

standalone-binaries.md

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

state-root.md

v1.92.14.0 feat: a .gstack-project file makes a nested repo or umbrella folder its own project (#2649, #1923) (#3777)

2026-11-01 05:57:18 +00:00

support-tiers.md

v1.92.43.0 docs: support tiers — full for macOS and Linux, minimal for Windows and Gemini (R50) (#3812)

2026-11-01 22:35:42 +00:00

TEST_PORTFOLIO.md

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

test-audit-2026-09.md

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

test-audit-2026-10.md

v1.91.105.0 fix(tests): the free suite stops needing its retry pass; test:health tells the truth (#3154) (#3212)

2026-10-16 13:29:38 -07:00

test-value-bar.md

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

TESTING_INTERNALS.md

fix(eval-plan): pilot start keeps the R54 refusal; --tier-question rejects a flag

2026-11-01 23:50:50 +00:00

triage.md

v1.91.235.0 docs(triage): parked issues stay open under the parked label; closing means fixed, duplicate or won't fix (GSTA-99) (#3427)

2026-10-26 07:37:42 +00:00

troubleshooting.md

v1.92.42.0 fix(ship): notes-only review passes bind; carry handles large diffs; scoped carry route (GST-430, GST-448, GST-442, GST-444) (#3694)

2026-11-01 21:26:59 +00:00

tutorial-document-generate.md

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

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

unattended.md

v1.92.42.0 fix(ship): notes-only review passes bind; carry handles large diffs; scoped carry route (GST-430, GST-448, GST-442, GST-444) (#3694)

2026-11-01 21:26:59 +00:00

uninstall.md

v1.92.23.0 feat(harness): opt-in start hook for OpenClaw and Hermes, so agents run a skill's start command (GST-718) (#3786)

2026-11-01 09:52:31 +00:00

voice-input.md

v1.92.6.0 feat: proactive core routes only the four core skills, and they carry their trigger phrases (#3770)

2026-11-01 01:25:15 +00:00

why-gstack.md

v1.91.246.0 docs(readme): cut the README to the first ten minutes; move everything else to docs/ pages verbatim (GSTA-99) (#3428)

2026-10-26 13:22:30 +00:00