gstack/test
Garry Tan 873fcccd74
feat(hooks): PreToolUse enforcement hook for AskUserQuestion preferences
Plan-tune cathedral T6 — the keystone that makes never-ask actually bind.
Today preferences are agent-convention (silently ignored). This hook
enforces them via Claude Code's hook protocol: when a never-ask preference
matches an AUQ that is two-way + has a marker + has a clear recommendation,
the hook returns permissionDecision: "deny" with permissionDecisionReason
naming the auto-decided option. The agent obeys the rejection feedback and
proceeds with the recommended option without re-firing AUQ.

Decision tree (per question):
  - marker absent → defer (D18: hash IDs are observed-only)
  - one-way door → defer (safety override — never auto-decide one-way)
  - always-ask preference → defer
  - no preference set → defer
  - ambiguous recommendation (two (recommended) labels OR no parseable rec)
    → defer (D2 refuse-on-ambiguous)
  - never-ask / ask-only-for-one-way + two-way + clean rec → deny+reason

Preference precedence per D8: project-local
(~/.gstack/projects/<slug>/question-preferences.json) wins, global
(~/.gstack/global-question-preferences.json) is fallback.

Why deny+reason instead of allow+updatedInput:
AskUserQuestion's updatedInput shape for "pre-resolve this question" isn't
structurally pinned in Claude Code docs (T4 spike open question). deny with
a reason that names the auto-decided option is the conservative + reliable
v1 — the model receives the rejection, reads the recommended option from
the reason, proceeds without re-prompting. Swap to allow+updatedInput once
the AUQ input shape is verified against real Claude Code.

Since deny prevents PostToolUse from firing, this hook logs the auto-decided
event itself via gstack-question-log (source=auto-decided) so /plan-tune's
Recent auto-decisions surface picks it up. Also writes a session marker
~/.gstack/sessions/<id>/.auto-decided-<tool_use_id> for coordination when
the AUQ-shape switch lands.

Multi-question AUQ: enforcement is all-or-nothing per call. If any question
in the batch isn't eligible (no marker, no preference, ambiguous rec, etc.),
the whole call defers so the user still gets to answer the rest normally.

Registry lookup: cheap regex extraction from scripts/question-registry.ts
(reading + bun-importing the TS file from a hook is too slow). Door type
defaults to two-way for unregistered.

Matcher covers both native AskUserQuestion and mcp__*__AskUserQuestion
(Conductor disables native — Codex outside-voice catch).

15 unit tests cover defer paths, enforcement, one-way safety override,
ambiguous-rec refuse, precedence (project wins, global fallback,
project-overrides-global), MCP matcher, auto-decided event logging,
session marker writing, crash safety.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-27 07:44:26 -07:00
..
fixtures Merge branch 'main' into garrytan/enable-plan-tune (catch up to v1.48.0.0) 2026-05-26 23:44:08 -07:00
helpers v1.48.0.0 feat: AskUserQuestion split rule + runtime AUTO_DECIDE carve-out (#1740) 2026-05-26 23:43:07 -07:00
agent-sdk-runner.test.ts v1.11.1.0 fix: plan-mode handshake + canUseTool test harness (#1182) 2026-04-24 00:04:53 -07:00
analytics.test.ts feat: safety hook skills + skill usage telemetry (v0.7.1) (#189) 2026-03-18 23:57:59 -05:00
artifacts-init-migration.test.ts v1.40.0.0 fix wave: gbrain sync hardening (8 community PRs + migration) (#1547) 2026-05-17 08:26:36 -07:00
audit-compliance.test.ts feat(v1.3.0.0): open agents learnings + cross-model benchmark skill (#1040) 2026-04-19 17:50:31 +08:00
benchmark-cli.test.ts v1.43.2.0 fix wave: post-Daegu paper-cut — 18 fixes, 28 bisect commits (#1642) 2026-05-21 21:21:07 -07:00
benchmark-runner.test.ts feat(v1.3.0.0): open agents learnings + cross-model benchmark skill (#1040) 2026-04-19 17:50:31 +08:00
brain-sync-windows-paths.test.ts v1.44.1.0 fix wave: post-windhoek paper-cut — 9 community PRs in one bundle (#1682) 2026-05-25 10:57:15 -07:00
brain-sync.test.ts v1.27.0.0 feat: /setup-gbrain Path 4 (remote MCP) + brain → artifacts rename (#1351) 2026-05-06 19:37:53 -07:00
build-gbrain-env.test.ts v1.43.2.0 fix wave: post-Daegu paper-cut — 18 fixes, 28 bisect commits (#1642) 2026-05-21 21:21:07 -07:00
build-script-shell-compat.test.ts v1.42.0.0 Daegu wave: 23 community-filed bugs + PTY classifier enforcement (24 bisect commits) (#1594) 2026-05-20 07:35:01 -07:00
builder-profile.test.ts feat: relationship closing — office-hours adapts to repeat users (v0.16.2.0) (#937) 2026-04-08 22:21:28 -10:00
catalog-mode-full.test.ts 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
catalog-trim.test.ts 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
codex-e2e-plan-format.test.ts fix(plan-reviews): restore RECOMMENDATION + Completeness split + Codex ELI10 (v1.6.3.0) (#1149) 2026-04-23 07:25:20 -07:00
codex-e2e.test.ts feat: worktree isolation for E2E tests + infrastructure elegance (v0.11.12.0) (#425) 2026-03-23 23:05:22 -07:00
codex-hardening.test.ts v1.34.2.0 fix wave: /codex review on CLI 0.130+, /investigate learnings, /sync-gbrain on Supabase (3 community-reported bugs) (#1478) 2026-05-14 11:11:52 -04:00
codex-resume-flag-semantics.test.ts v1.30.0.0 fix wave: 21 community PRs + Windows CI extension + codex flag-semantics smoke (#1391) 2026-05-09 08:06:47 -07:00
conductor-env-shim.test.ts v1.39.2.0 feat: GSTACK_* env-shim for Conductor + gbrain/gstack setup docs (#1534) 2026-05-16 12:32:33 -07:00
context-save-hardening.test.ts fix(checkpoint): rename /checkpoint → /context-save + /context-restore (v1.0.1.0) (#1064) 2026-04-19 08:38:19 +08:00
cso-preserved.test.ts 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
diff-scope.test.ts v1.44.1.0 fix wave: post-windhoek paper-cut — 9 community PRs in one bundle (#1682) 2026-05-25 10:57:15 -07:00
docs-config-keys.test.ts v1.43.2.0 fix wave: post-Daegu paper-cut — 18 fixes, 28 bisect commits (#1642) 2026-05-21 21:21:07 -07:00
e2e-harness-audit.test.ts v1.15.0.0 feat: slim preamble + real-PTY plan-mode E2E harness (#1215) 2026-04-26 13:55:13 -07:00
explain-level-config.test.ts v1.44.0.0 feat: long-lived sidebar — keepalive, restart, re-attach, scrollback replay (#1678) 2026-05-24 01:43:51 -07:00
extension-pty-inject-invariant.test.ts v1.42.0.0 Daegu wave: 23 community-filed bugs + PTY classifier enforcement (24 bisect commits) (#1594) 2026-05-20 07:35:01 -07:00
gbrain-detect-install.test.ts v1.12.0.0 feat: /setup-gbrain — coding-agent onboarding for gbrain (#1183) 2026-04-24 01:38:21 -07:00
gbrain-detect-shape.test.ts v1.37.0.0 feat: split-engine gbrain (remote MCP brain + local PGLite for code) (#1500) 2026-05-14 17:20:48 -07:00
gbrain-exec-invariant.test.ts v1.40.0.0 fix wave: gbrain sync hardening (8 community PRs + migration) (#1547) 2026-05-17 08:26:36 -07:00
gbrain-init-rollback.test.ts v1.37.0.0 feat: split-engine gbrain (remote MCP brain + local PGLite for code) (#1500) 2026-05-14 17:20:48 -07:00
gbrain-init-voyage-code-3.test.ts v1.43.1.0 feat: default PGLite to voyage-code-3 for code search + e2e tests (#1639) 2026-05-21 18:55:55 -07:00
gbrain-lib-validate-varname.test.ts v1.43.2.0 fix wave: post-Daegu paper-cut — 18 fixes, 28 bisect commits (#1642) 2026-05-21 21:21:07 -07:00
gbrain-lib-verify.test.ts v1.12.0.0 feat: /setup-gbrain — coding-agent onboarding for gbrain (#1183) 2026-04-24 01:38:21 -07:00
gbrain-local-status.test.ts v1.40.0.0 fix wave: gbrain sync hardening (8 community PRs + migration) (#1547) 2026-05-17 08:26:36 -07:00
gbrain-repo-policy.test.ts v1.12.0.0 feat: /setup-gbrain — coding-agent onboarding for gbrain (#1183) 2026-04-24 01:38:21 -07:00
gbrain-source-gitignore.test.ts v1.40.0.0 fix wave: gbrain sync hardening (8 community PRs + migration) (#1547) 2026-05-17 08:26:36 -07:00
gbrain-sources.test.ts v1.26.3.0 feat: /sync-gbrain skill + native code-surface orchestrator (#1314) 2026-05-04 09:29:48 -07:00
gbrain-supabase-provision.test.ts v1.43.2.0 fix wave: post-Daegu paper-cut — 18 fixes, 28 bisect commits (#1642) 2026-05-21 21:21:07 -07:00
gbrain-sync-skip.test.ts v1.37.0.0 feat: split-engine gbrain (remote MCP brain + local PGLite for code) (#1500) 2026-05-14 17:20:48 -07:00
gbrain-sync-voyage-code-3-integration.test.ts v1.43.1.0 feat: default PGLite to voyage-code-3 for code search + e2e tests (#1639) 2026-05-21 18:55:55 -07:00
gemini-e2e.test.ts feat: Confusion Protocol, Hermes + GBrain hosts, brain-first resolver (v0.18.0.0) (#1005) 2026-04-16 10:41:38 -07:00
gen-skill-docs-idempotency.test.ts 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
gen-skill-docs.test.ts v1.43.2.0 fix wave: post-Daegu paper-cut — 18 fixes, 28 bisect commits (#1642) 2026-05-21 21:21:07 -07:00
global-discover.test.ts v1.41.1.0 fix wave: 7 HIGH bugs from external audit + regression tests (PR #1169 follow-up) (#1592) 2026-05-20 06:56:41 -07:00
gstack-artifacts-init.test.ts v1.34.2.0 fix wave: /codex review on CLI 0.130+, /investigate learnings, /sync-gbrain on Supabase (3 community-reported bugs) (#1478) 2026-05-14 11:11:52 -04:00
gstack-artifacts-url.test.ts v1.43.2.0 fix wave: post-Daegu paper-cut — 18 fixes, 28 bisect commits (#1642) 2026-05-21 21:21:07 -07:00
gstack-brain-context-load.test.ts v1.42.0.0 Daegu wave: 23 community-filed bugs + PTY classifier enforcement (24 bisect commits) (#1594) 2026-05-20 07:35:01 -07:00
gstack-developer-profile.test.ts v1.44.1.0 fix wave: post-windhoek paper-cut — 9 community PRs in one bundle (#1682) 2026-05-25 10:57:15 -07:00
gstack-gbrain-detect-mcp-mode.test.ts v1.43.2.0 fix wave: post-Daegu paper-cut — 18 fixes, 28 bisect commits (#1642) 2026-05-21 21:21:07 -07:00
gstack-gbrain-mcp-verify.test.ts v1.27.0.0 feat: /setup-gbrain Path 4 (remote MCP) + brain → artifacts rename (#1351) 2026-05-06 19:37:53 -07:00
gstack-gbrain-source-wireup.test.ts v1.17.0.0: setup-gbrain wireup ships the gbrain federation surface (#1234) 2026-04-28 01:17:54 -07:00
gstack-gbrain-sync.test.ts v1.42.0.0 Daegu wave: 23 community-filed bugs + PTY classifier enforcement (24 bisect commits) (#1594) 2026-05-20 07:35:01 -07:00
gstack-learnings-search.test.ts v1.43.2.0 fix wave: post-Daegu paper-cut — 18 fixes, 28 bisect commits (#1642) 2026-05-21 21:21:07 -07:00
gstack-memory-helpers.test.ts v1.43.2.0 fix wave: post-Daegu paper-cut — 18 fixes, 28 bisect commits (#1642) 2026-05-21 21:21:07 -07:00
gstack-memory-ingest.test.ts v1.40.0.0 fix wave: gbrain sync hardening (8 community PRs + migration) (#1547) 2026-05-17 08:26:36 -07:00
gstack-next-version.test.ts v1.44.1.0 fix wave: post-windhoek paper-cut — 9 community PRs in one bundle (#1682) 2026-05-25 10:57:15 -07:00
gstack-paths.test.ts v1.42.0.0 Daegu wave: 23 community-filed bugs + PTY classifier enforcement (24 bisect commits) (#1594) 2026-05-20 07:35:01 -07:00
gstack-question-log.test.ts feat: gstack v1 — simpler prompts + real LOC receipts (v1.0.0.0) (#1039) 2026-04-18 15:05:42 +08:00
gstack-question-preference.test.ts v1.48.0.0 feat: AskUserQuestion split rule + runtime AUTO_DECIDE carve-out (#1740) 2026-05-26 23:43:07 -07:00
gstack-settings-hook-schema-aware.test.ts feat(settings-hook): schema-aware PreToolUse/PostToolUse registration 2026-05-27 07:40:51 -07:00
gstack-state-root-override.test.ts feat(bins): honor GSTACK_STATE_ROOT override for test isolation 2026-05-27 07:31:37 -07:00
gstack-upgrade-migration-v1_17_0_0.test.ts v1.17.0.0: setup-gbrain wireup ships the gbrain federation surface (#1234) 2026-04-28 01:17:54 -07:00
gstack-upgrade-migration-v1_37_0_0.test.ts v1.37.0.0 feat: split-engine gbrain (remote MCP brain + local PGLite for code) (#1500) 2026-05-14 17:20:48 -07:00
gstack-upgrade-migration-v1_40_0_0.test.ts v1.44.1.0 fix wave: post-windhoek paper-cut — 9 community PRs in one bundle (#1682) 2026-05-25 10:57:15 -07:00
helpers-unit.test.ts v1.15.0.0 feat: slim preamble + real-PTY plan-mode E2E harness (#1215) 2026-04-26 13:55:13 -07:00
hook-scripts.test.ts v1.31.1.0 fix wave: 3 community PRs (careful BSD sed, codex Step 0 rename, make-pdf setup ordering) (#1413) 2026-05-10 06:57:24 -07:00
host-config.test.ts community wave: 6 PRs + hardening (v0.18.1.0) (#1028) 2026-04-17 00:45:13 -07:00
investigate-freeze-path.test.ts v1.44.1.0 fix wave: post-windhoek paper-cut — 9 community PRs in one bundle (#1682) 2026-05-25 10:57:15 -07:00
jargon-list.test.ts feat: gstack v1 — simpler prompts + real LOC receipts (v1.0.0.0) (#1039) 2026-04-18 15:05:42 +08:00
land-and-deploy-postfail.test.ts v1.43.2.0 fix wave: post-Daegu paper-cut — 18 fixes, 28 bisect commits (#1642) 2026-05-21 21:21:07 -07:00
learnings-injection.test.ts v1.43.2.0 fix wave: post-Daegu paper-cut — 18 fixes, 28 bisect commits (#1642) 2026-05-21 21:21:07 -07:00
learnings.test.ts v1.34.2.0 fix wave: /codex review on CLI 0.130+, /investigate learnings, /sync-gbrain on Supabase (3 community-reported bugs) (#1478) 2026-05-14 11:11:52 -04:00
llm-judge-recommendation.test.ts v1.25.1.0 fix: office-hours Phase 4 STOP gate + AskUserQuestion recommendation judge (#1296) 2026-05-01 19:51:51 -07:00
llms-txt-shape.test.ts v1.28.0.0 feat: browse --headed/--proxy/--navigate + gstack/llms.txt + webdriver-only stealth (#1363) 2026-05-07 20:14:59 -07:00
memory-ingest-no-put_page.test.ts v1.42.0.0 Daegu wave: 23 community-filed bugs + PTY classifier enforcement (24 bisect commits) (#1594) 2026-05-20 07:35:01 -07:00
migration-checkpoint-ownership.test.ts fix(checkpoint): rename /checkpoint → /context-save + /context-restore (v1.0.1.0) (#1064) 2026-04-19 08:38:19 +08:00
migrations-v1.27.0.0.test.ts v1.27.0.0 feat: /setup-gbrain Path 4 (remote MCP) + brain → artifacts rename (#1351) 2026-05-06 19:37:53 -07:00
model-overlay-opus-4-7.test.ts v1.13.0.0 feat: add Claude outside-voice skill (#1212) 2026-04-25 11:52:48 -07:00
no-stale-gstack-brain-refs.test.ts v1.38.0.0 fix wave: Windows install hardening + Unicode sanitization at server egress (4 community PRs) (#1505) 2026-05-14 21:19:58 -07:00
openclaw-native-skills.test.ts community wave: 6 PRs + hardening (v0.18.1.0) (#1028) 2026-04-17 00:45:13 -07:00
parity-baseline-integrity.test.ts 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-suite.test.ts 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
plan-tune-gates.test.ts test(plan-tune): regression coverage for v1.49 consent + setup gates 2026-05-27 07:32:29 -07:00
plan-tune.test.ts feat: gstack v1 — simpler prompts + real LOC receipts (v1.0.0.0) (#1039) 2026-04-18 15:05:42 +08:00
post-rename-doc-regen.test.ts v1.27.0.0 feat: /setup-gbrain Path 4 (remote MCP) + brain → artifacts rename (#1351) 2026-05-06 19:37:53 -07:00
pr-title-rewrite.test.ts v1.23.0.0 feat: always prefix PR titles with v<VERSION> (#1284) 2026-05-01 07:06:37 -07:00
preamble-compose.test.ts v1.10.0.0: fix AskUserQuestion cadence + Pros/Cons format upgrade (#1178) 2026-04-23 18:25:34 -07:00
question-log-hook.test.ts feat(hooks): PostToolUse capture hook for AskUserQuestion 2026-05-27 07:42:46 -07:00
question-preference-hook.test.ts feat(hooks): PreToolUse enforcement hook for AskUserQuestion preferences 2026-05-27 07:44:26 -07:00
readme-throughput.test.ts feat: gstack v1 — simpler prompts + real LOC receipts (v1.0.0.0) (#1039) 2026-04-18 15:05:42 +08:00
regression-1539-review-self-verify.test.ts v1.43.2.0 fix wave: post-Daegu paper-cut — 18 fixes, 28 bisect commits (#1642) 2026-05-21 21:21:07 -07:00
regression-1611-gbrain-sync-resume.test.ts v1.43.2.0 fix wave: post-Daegu paper-cut — 18 fixes, 28 bisect commits (#1642) 2026-05-21 21:21:07 -07:00
regression-1624-retro-stale-base.test.ts v1.43.2.0 fix wave: post-Daegu paper-cut — 18 fixes, 28 bisect commits (#1642) 2026-05-21 21:21:07 -07:00
regression-pr1169-build-app-sed.test.ts v1.41.1.0 fix wave: 7 HIGH bugs from external audit + regression tests (PR #1169 follow-up) (#1592) 2026-05-20 06:56:41 -07:00
regression-pr1169-mktemp-fallbacks.test.ts v1.41.1.0 fix wave: 7 HIGH bugs from external audit + regression tests (PR #1169 follow-up) (#1592) 2026-05-20 06:56:41 -07:00
relink.test.ts v1.43.2.0 fix wave: post-Daegu paper-cut — 18 fixes, 28 bisect commits (#1642) 2026-05-21 21:21:07 -07:00
resolver-ask-user-format.test.ts v1.48.0.0 feat: AskUserQuestion split rule + runtime AUTO_DECIDE carve-out (#1740) 2026-05-26 23:43:07 -07:00
resolver-entry.test.ts 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
resolvers-gbrain-put-rewrite.test.ts v1.42.0.0 Daegu wave: 23 community-filed bugs + PTY classifier enforcement (24 bisect commits) (#1594) 2026-05-20 07:35:01 -07:00
review-log.test.ts fix: community PRs + security hardening + E2E stability (v0.12.7.0) (#552) 2026-03-26 23:21:27 -06:00
secret-sink-harness.test.ts v1.12.0.0 feat: /setup-gbrain — coding-agent onboarding for gbrain (#1183) 2026-04-24 01:38:21 -07:00
setup-codesign.test.ts v1.44.0.0 feat: long-lived sidebar — keepalive, restart, re-attach, scrollback replay (#1678) 2026-05-24 01:43:51 -07:00
setup-conductor-worktree.test.ts v1.38.0.0 fix wave: Windows install hardening + Unicode sanitization at server egress (4 community PRs) (#1505) 2026-05-14 21:19:58 -07:00
setup-gbrain-path4-structure.test.ts v1.27.0.0 feat: /setup-gbrain Path 4 (remote MCP) + brain → artifacts rename (#1351) 2026-05-06 19:37:53 -07:00
setup-windows-fallback.test.ts v1.38.0.0 fix wave: Windows install hardening + Unicode sanitization at server egress (4 community PRs) (#1505) 2026-05-14 21:19:58 -07:00
ship-plan-completion-invariants.test.ts v1.30.0.0 fix wave: 21 community PRs + Windows CI extension + codex flag-semantics smoke (#1391) 2026-05-09 08:06:47 -07:00
ship-version-sync.test.ts fix(ship): detect + repair VERSION/package.json drift in Step 12 (v1.1.1.0) (#1063) 2026-04-18 23:58:59 +08:00
skill-budget-regression.test.ts 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
skill-collision-sentinel.test.ts fix(checkpoint): rename /checkpoint → /context-save + /context-restore (v1.0.1.0) (#1064) 2026-04-19 08:38:19 +08:00
skill-coverage-floor.test.ts 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
skill-coverage-matrix.test.ts 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
skill-coverage-matrix.ts v1.47.0.0 feat: /spec — author backlog-ready spec in 5 phases + optional agent spawn (#1698) (#1733) 2026-05-26 21:36:53 -07:00
skill-cross-model-recommendation-emit.test.ts v1.25.1.0 fix: office-hours Phase 4 STOP gate + AskUserQuestion recommendation judge (#1296) 2026-05-01 19:51:51 -07:00
skill-e2e-ask-user-question-format-compliance.test.ts v1.32.0.0 fix wave: 7 community PRs + 5 gate-eval hardenings (#1431) 2026-05-11 12:16:26 -07:00
skill-e2e-auto-decide-preserved.test.ts v1.25.0.0 fix: AskUserQuestion resolves to host MCP variant when native is disallowed (#1287) 2026-05-01 08:45:36 -07:00
skill-e2e-autoplan-chain.test.ts v1.15.0.0 feat: slim preamble + real-PTY plan-mode E2E harness (#1215) 2026-04-26 13:55:13 -07:00
skill-e2e-autoplan-dual-voice.test.ts fix(checkpoint): rename /checkpoint → /context-save + /context-restore (v1.0.1.0) (#1064) 2026-04-19 08:38:19 +08:00
skill-e2e-benchmark-providers.test.ts v1.32.0.0 fix wave: 7 community PRs + 5 gate-eval hardenings (#1431) 2026-05-11 12:16:26 -07:00
skill-e2e-brain-privacy-gate.test.ts v1.27.0.0 feat: /setup-gbrain Path 4 (remote MCP) + brain → artifacts rename (#1351) 2026-05-06 19:37:53 -07:00
skill-e2e-bws.test.ts feat(v1.9.0.0): gbrain-sync — cross-machine gstack memory (#1151) 2026-04-23 17:54:54 -07:00
skill-e2e-context-skills.test.ts fix(checkpoint): rename /checkpoint → /context-save + /context-restore (v1.0.1.0) (#1064) 2026-04-19 08:38:19 +08:00
skill-e2e-cso.test.ts feat: /cso v2 — infrastructure-first security audit (v0.11.6.0) (#384) 2026-03-23 06:57:22 -07:00
skill-e2e-deploy.test.ts feat: /land-and-deploy first-run dry run + staging-first + trust ladder (v0.12.2.0) (#518) 2026-03-26 11:08:31 -07:00
skill-e2e-design.test.ts v1.32.0.0 fix wave: 7 community PRs + 5 gate-eval hardenings (#1431) 2026-05-11 12:16:26 -07:00
skill-e2e-ios-device.test.ts v1.43.0.0 feat: iOS device-farm (5 skills, Mac daemon, Tailscale) (#1574) 2026-05-21 16:09:26 -07:00
skill-e2e-ios-swift-build.test.ts v1.43.0.0 feat: iOS device-farm (5 skills, Mac daemon, Tailscale) (#1574) 2026-05-21 16:09:26 -07:00
skill-e2e-ios.test.ts v1.43.0.0 feat: iOS device-farm (5 skills, Mac daemon, Tailscale) (#1574) 2026-05-21 16:09:26 -07:00
skill-e2e-learnings.test.ts feat: recursive self-improvement — operational learning + full skill wiring (v0.13.8.0) (#647) 2026-03-31 23:08:22 -06:00
skill-e2e-memory-pipeline.test.ts v1.26.3.0 feat: /sync-gbrain skill + native code-surface orchestrator (#1314) 2026-05-04 09:29:48 -07:00
skill-e2e-office-hours-auto-mode.test.ts v1.25.0.0 fix: AskUserQuestion resolves to host MCP variant when native is disallowed (#1287) 2026-05-01 08:45:36 -07:00
skill-e2e-office-hours-phase4.test.ts v1.25.1.0 fix: office-hours Phase 4 STOP gate + AskUserQuestion recommendation judge (#1296) 2026-05-01 19:51:51 -07:00
skill-e2e-office-hours.test.ts 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
skill-e2e-opus-47.test.ts feat(v1.5.2.0): Opus 4.7 migration — model overlay, voice, routing (#1117) 2026-04-22 01:06:22 -07:00
skill-e2e-overlay-harness.test.ts feat(v1.10.1.0): overlay efficacy harness + Opus 4.7 fanout nudge removal (#1166) 2026-04-23 18:42:58 -07:00
skill-e2e-plan-ceo-finding-count.test.ts v1.21.1.0 test: tighten plan-ceo-review smoke (Step 0 must fire) (#1255) 2026-04-30 02:50:09 -07:00
skill-e2e-plan-ceo-finding-floor.test.ts v1.27.1.0 fix: anti-shortcut clause + gate-tier AskUserQuestion floor tests for all plan-* skills (#1354) 2026-05-06 20:27:20 -07:00
skill-e2e-plan-ceo-mode-routing.test.ts v1.21.1.0 test: tighten plan-ceo-review smoke (Step 0 must fire) (#1255) 2026-04-30 02:50:09 -07:00
skill-e2e-plan-ceo-plan-mode.test.ts v1.31.0.0 fix: delete AskUserQuestion fallback (root cause of forever war) + harness primitives (#1390) 2026-05-09 17:01:13 -07:00
skill-e2e-plan-ceo-split-overflow.test.ts v1.48.0.0 feat: AskUserQuestion split rule + runtime AUTO_DECIDE carve-out (#1740) 2026-05-26 23:43:07 -07:00
skill-e2e-plan-design-finding-count.test.ts v1.21.1.0 test: tighten plan-ceo-review smoke (Step 0 must fire) (#1255) 2026-04-30 02:50:09 -07:00
skill-e2e-plan-design-finding-floor.test.ts v1.27.1.0 fix: anti-shortcut clause + gate-tier AskUserQuestion floor tests for all plan-* skills (#1354) 2026-05-06 20:27:20 -07:00
skill-e2e-plan-design-plan-mode.test.ts v1.31.0.0 fix: delete AskUserQuestion fallback (root cause of forever war) + harness primitives (#1390) 2026-05-09 17:01:13 -07:00
skill-e2e-plan-design-with-ui.test.ts v1.32.0.0 fix wave: 7 community PRs + 5 gate-eval hardenings (#1431) 2026-05-11 12:16:26 -07:00
skill-e2e-plan-devex-finding-count.test.ts v1.21.1.0 test: tighten plan-ceo-review smoke (Step 0 must fire) (#1255) 2026-04-30 02:50:09 -07:00
skill-e2e-plan-devex-finding-floor.test.ts v1.27.1.0 fix: anti-shortcut clause + gate-tier AskUserQuestion floor tests for all plan-* skills (#1354) 2026-05-06 20:27:20 -07:00
skill-e2e-plan-devex-plan-mode.test.ts v1.26.2.0 fix: plan-eng-review STOP gates always fire AskUserQuestion + report-at-bottom contract enforcement (#1313) 2026-05-03 20:26:59 -07:00
skill-e2e-plan-eng-finding-count.test.ts v1.21.1.0 test: tighten plan-ceo-review smoke (Step 0 must fire) (#1255) 2026-04-30 02:50:09 -07:00
skill-e2e-plan-eng-finding-floor.test.ts v1.27.1.0 fix: anti-shortcut clause + gate-tier AskUserQuestion floor tests for all plan-* skills (#1354) 2026-05-06 20:27:20 -07:00
skill-e2e-plan-eng-multi-finding-batching.test.ts v1.31.0.0 fix: delete AskUserQuestion fallback (root cause of forever war) + harness primitives (#1390) 2026-05-09 17:01:13 -07:00
skill-e2e-plan-eng-plan-mode.test.ts v1.31.0.0 fix: delete AskUserQuestion fallback (root cause of forever war) + harness primitives (#1390) 2026-05-09 17:01:13 -07:00
skill-e2e-plan-format.test.ts v1.25.1.0 fix: office-hours Phase 4 STOP gate + AskUserQuestion recommendation judge (#1296) 2026-05-01 19:51:51 -07:00
skill-e2e-plan-mode-no-op.test.ts v1.15.0.0 feat: slim preamble + real-PTY plan-mode E2E harness (#1215) 2026-04-26 13:55:13 -07:00
skill-e2e-plan-prosons.test.ts v1.10.0.0: fix AskUserQuestion cadence + Pros/Cons format upgrade (#1178) 2026-04-23 18:25:34 -07:00
skill-e2e-plan-tune.test.ts feat: gstack v1 — simpler prompts + real LOC receipts (v1.0.0.0) (#1039) 2026-04-18 15:05:42 +08:00
skill-e2e-plan.test.ts v1.43.0.0 feat: iOS device-farm (5 skills, Mac daemon, Tailscale) (#1574) 2026-05-21 16:09:26 -07:00
skill-e2e-qa-bugs.test.ts v1.32.0.0 fix wave: 7 community PRs + 5 gate-eval hardenings (#1431) 2026-05-11 12:16:26 -07:00
skill-e2e-qa-workflow.test.ts feat: CI evals on Ubicloud — 12 parallel runners + Docker image (v0.11.10.0) (#360) 2026-03-23 10:17:33 -07:00
skill-e2e-review-army.test.ts feat: Review Army — parallel specialist reviewers for /review (v0.14.3.0) (#692) 2026-03-30 22:07:50 -06:00
skill-e2e-review.test.ts v1.32.0.0 fix wave: 7 community PRs + 5 gate-eval hardenings (#1431) 2026-05-11 12:16:26 -07:00
skill-e2e-session-intelligence.test.ts fix(checkpoint): rename /checkpoint → /context-save + /context-restore (v1.0.1.0) (#1064) 2026-04-19 08:38:19 +08:00
skill-e2e-setup-gbrain-bad-token.test.ts v1.27.0.0 feat: /setup-gbrain Path 4 (remote MCP) + brain → artifacts rename (#1351) 2026-05-06 19:37:53 -07:00
skill-e2e-setup-gbrain-path4-local-pglite.test.ts v1.37.0.0 feat: split-engine gbrain (remote MCP brain + local PGLite for code) (#1500) 2026-05-14 17:20:48 -07:00
skill-e2e-setup-gbrain-remote.test.ts v1.27.0.0 feat: /setup-gbrain Path 4 (remote MCP) + brain → artifacts rename (#1351) 2026-05-06 19:37:53 -07:00
skill-e2e-ship-idempotency.test.ts v1.15.0.0 feat: slim preamble + real-PTY plan-mode E2E harness (#1215) 2026-04-26 13:55:13 -07:00
skill-e2e-sidebar.test.ts feat: declarative multi-host platform + OpenCode, Slate, Cursor, OpenClaw (v0.15.5.0) (#793) 2026-04-04 15:32:20 -07:00
skill-e2e-skillify.test.ts v1.32.0.0 fix wave: 7 community PRs + 5 gate-eval hardenings (#1431) 2026-05-11 12:16:26 -07:00
skill-e2e-spec-execute.test.ts v1.47.0.0 feat: /spec — author backlog-ready spec in 5 phases + optional agent spawn (#1698) (#1733) 2026-05-26 21:36:53 -07:00
skill-e2e-workflow.test.ts v1.32.0.0 fix wave: 7 community PRs + 5 gate-eval hardenings (#1431) 2026-05-11 12:16:26 -07:00
skill-e2e.test.ts feat: recursive self-improvement — operational learning + full skill wiring (v0.13.8.0) (#647) 2026-03-31 23:08:22 -06:00
skill-llm-eval-spec.test.ts v1.47.0.0 feat: /spec — author backlog-ready spec in 5 phases + optional agent spawn (#1698) (#1733) 2026-05-26 21:36:53 -07:00
skill-llm-eval.test.ts feat: voice directive for all skills (v0.12.3.0) (#520) 2026-03-26 17:31:53 -06:00
skill-parser.test.ts feat: SKILL.md template system, 3-tier testing, DX tools (v0.3.3) (#41) 2026-03-13 21:08:12 -07:00
skill-routing-e2e.test.ts feat: Confusion Protocol, Hermes + GBrain hosts, brain-first resolver (v0.18.0.0) (#1005) 2026-04-16 10:41:38 -07:00
skill-size-budget.test.ts v1.48.0.0 feat: AskUserQuestion split rule + runtime AUTO_DECIDE carve-out (#1740) 2026-05-26 23:43:07 -07:00
skill-validation.test.ts 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
spec-template-invariants.test.ts v1.47.0.0 feat: /spec — author backlog-ready spec in 5 phases + optional agent spawn (#1698) (#1733) 2026-05-26 21:36:53 -07:00
spec-template-sync.test.ts v1.47.0.0 feat: /spec — author backlog-ready spec in 5 phases + optional agent spawn (#1698) (#1733) 2026-05-26 21:36:53 -07:00
static-no-legacy-writes.test.ts v1.44.1.0 fix wave: post-windhoek paper-cut — 9 community PRs in one bundle (#1682) 2026-05-25 10:57:15 -07:00
taste-engine.test.ts feat(v1.3.0.0): open agents learnings + cross-model benchmark skill (#1040) 2026-04-19 17:50:31 +08:00
team-mode.test.ts feat(v1.5.2.0): Opus 4.7 migration — model overlay, voice, routing (#1117) 2026-04-22 01:06:22 -07:00
telemetry.test.ts feat: community wave — 7 fixes, relink, sidebar Write, discoverability (v0.13.5.0) (#641) 2026-03-29 21:43:36 -06:00
terse-build.test.ts 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
test-free-shards.test.ts v1.24.0.0 feat: cross-platform hardening — curated Windows lane + Bun.which resolver + path-portability helper (#1252) 2026-05-01 07:21:28 -07:00
timeline.test.ts v1.44.1.0 fix wave: post-windhoek paper-cut — 9 community PRs in one bundle (#1682) 2026-05-25 10:57:15 -07:00
touchfiles.test.ts v1.48.0.0 feat: AskUserQuestion split rule + runtime AUTO_DECIDE carve-out (#1740) 2026-05-26 23:43:07 -07:00
uninstall.test.ts feat: community PRs — faster install, skill namespacing, uninstall, Codex fallback, Windows fix, Python patterns (v0.12.9.0) (#561) 2026-03-27 00:44:37 -06:00
upgrade-migration-v1.test.ts v1.44.0.0 feat: long-lived sidebar — keepalive, restart, re-attach, scrollback replay (#1678) 2026-05-24 01:43:51 -07:00
v0-dormancy.test.ts feat: gstack v1 — simpler prompts + real LOC receipts (v1.0.0.0) (#1039) 2026-04-18 15:05:42 +08:00
worktree.test.ts feat: content security — 4-layer prompt injection defense for pair-agent (#815) 2026-04-06 14:41:06 -07:00
writing-style-resolver.test.ts 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