skills/garrytan__gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-09-14 18:41:42 +08:00
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • 442a46f989 fix(test): reactivate 5 quarantined browse tests (2 security) Garry Tan 2026-08-29 04:50:55 +00:00
  • 9eaf15564c fix(test): the two expect(true) paid stubs become test.todo Garry Tan 2026-08-29 04:49:33 +00:00
  • e9643e131f fix(evals): judges honor the eval-model resolution chain + real 429 backoff Garry Tan 2026-08-29 04:47:18 +00:00
  • 63f8829578 fix(test): e2e-harness-audit derives its skill census from disk Garry Tan 2026-08-29 04:45:59 +00:00
  • 241935adce test: tripwire against module-scope GSTACK_HOME assignments Garry Tan 2026-08-29 04:44:45 +00:00
  • c252f00b4c fix(test): scope GSTACK_HOME to each file's execution window Garry Tan 2026-08-29 04:44:45 +00:00
  • 05a45ddb89 fix(ci): small-lane batch — timeouts, right-sizing, windows cache warm-start Garry Tan 2026-08-29 04:42:52 +00:00
  • 5cdc02f555 fix(ci): quality-gate drops the 74s full-history checkout Garry Tan 2026-08-29 04:42:16 +00:00
  • adaad18124 fix(ci): ci-image stops rebuilding the identical image every ship Garry Tan 2026-08-29 04:41:43 +00:00
  • c8722b243d test(ci): bind the three-way image-tag hashFiles() expressions Garry Tan 2026-08-29 04:41:04 +00:00
  • ace904d40a fix(ci): one bun version everywhere + drift tripwire Garry Tan 2026-08-29 04:40:41 +00:00
  • e2904be7a4 fix(ci): least-privilege permissions + fork-safe concurrency keys Garry Tan 2026-08-29 04:39:36 +00:00
  • 3c9f8abfc8 fix(config): converge on main's self-contained sha8_of — its tests extract the function standalone Garry Tan 2026-08-29 04:37:53 +00:00
  • 9fbd0700ff fix(ci): kill the three zero-test eval jobs (hollow green) Garry Tan 2026-08-29 04:37:37 +00:00
  • 29d94a505d fix(ci): free-tests lane actually runs the make-pdf e2e gates Garry Tan 2026-08-29 04:36:38 +00:00
  • 977f15bb8f Merge remote-tracking branch 'origin/main' into ponytail-inspiration-review Garry Tan 2026-08-29 04:33:02 +00:00
  • fe8fcab8c2 docs(testing): sandbox-doctor — one command makes a cloud sandbox run the suite green Garry Tan 2026-08-28 19:59:06 +00:00
  • 8de9f39c82 fix(next-version): only trust ls-remote when origin is actually configured Garry Tan 2026-08-28 19:59:06 +00:00
  • 8fd2783175 fix(config): portable sha256 — Linux ships sha256sum, not shasum Garry Tan 2026-08-28 19:59:06 +00:00
  • 97d33a90ad fix(browse): portable temp paths — TEMP_DIRS allowlist, tmpdir()-based test files Garry Tan 2026-08-28 19:59:06 +00:00
  • 626ebc1ba9 feat(test-runner): GSTACK_FREE_JOBS + opt-in flaky-retry pass for syscall-supervised sandboxes Garry Tan 2026-08-28 19:58:47 +00:00
  • b5a951e623 v1.72.0.0 feat: Aside recommended driver for third-party web actions (#2710) Garry Tan 2026-08-28 11:43:13 -07:00
  • cc2469f1fe fix(test): gate the symlink-refusal test to POSIX and drop the umask assumption #2710 aside-integration-options Garry Tan 2026-08-28 17:37:15 +00:00
  • 917a74e033 docs: close cross-model doc-review gaps for v1.72.0.0 Garry Tan 2026-08-28 17:26:57 +00:00
  • eb8742635c docs: apply cross-model doc review fixes for v1.72.0.0 Garry Tan 2026-08-28 05:09:00 +00:00
  • 99714e2a15 docs: update project documentation for v1.72.0.0 Garry Tan 2026-08-28 04:58:28 +00:00
  • d40f98660c chore: bump version and changelog (v1.72.0.0) Garry Tan 2026-08-28 04:47:59 +00:00
  • 05e3ed2fc3 docs: file the Aside follow-ups in TODOS Garry Tan 2026-08-28 04:47:59 +00:00
  • 0873fce89a test: consent-gate E2E suite + functional fs-capability probes Garry Tan 2026-08-28 04:47:50 +00:00
  • ade441afd0 chore: regenerate remaining browse-setup snippet consumers Garry Tan 2026-08-28 04:47:50 +00:00
  • 5856791c8c feat(contract): Aside is the recommended driver for third-party web actions Garry Tan 2026-08-28 04:47:24 +00:00
  • c5d849aaad fix: hash with sha256sum before shasum on Linux (config slugs + setup verify) Garry Tan 2026-08-28 04:47:09 +00:00
  • be509bfab4 fix(browse): never chmod shared, symlinked, or foreign-owned dirs to 0700 Garry Tan 2026-08-28 04:46:59 +00:00
  • cd53c0663c test: observability partial-file pin follows eval-store schema v2 Garry Tan 2026-08-28 02:43:17 +00:00
  • 76f38fcd0d test: absorb the ponytail-import wave into the guard fixtures — ceilings, schema pin, triad phrasing Garry Tan 2026-08-28 02:36:09 +00:00
  • 4c20eca33b feat(evals): with-skill vs without-skill arm benchmark — measures whether gstack's behavioral layer earns its tokens Garry Tan 2026-08-28 02:07:56 +00:00
  • 781f46d025 feat(preamble): AskUserQuestion repetition cut — gated, passed NOT-WORSE A/B Garry Tan 2026-08-28 02:00:50 +00:00
  • 3263fffea9 feat(hosts): instruction-only tier — a 2KB committed rules digest any agent host can read Garry Tan 2026-08-28 01:54:36 +00:00
  • cf0b39ddeb test: refresh golden ship baselines after preamble additions (reuse ladder + bounded closer) Garry Tan 2026-08-28 01:54:36 +00:00
  • 80ae2b59fa feat(retro,preamble): gstack-shortcut debt ledger — accepted shortcuts leave a joined trail Garry Tan 2026-08-28 01:50:31 +00:00
  • 86530fe320 docs(resolvers): terse-mode savings claim matches measurement — 2.6KB, not 3-5KB Garry Tan 2026-08-28 01:48:02 +00:00
  • 6d050d5430 feat(preamble): bounded-closer output rule for tier-2+ skills Garry Tan 2026-08-28 01:47:09 +00:00
  • fa655b6e97 feat(preamble): reuse ladder in Search Before Building — rungs 2-5 of ponytail's ladder, completeness kept Garry Tan 2026-08-28 01:46:39 +00:00
  • cbb4d35792 feat(review): simplification specialist — advisory over-engineering lens with ponytail's tag vocabulary Garry Tan 2026-08-28 01:45:53 +00:00
  • 848973007c feat(autoplan): eng review always runs last — the gate reviews the final amended plan Garry Tan 2026-08-28 01:41:29 +00:00
  • 394db326f2 v1.71.0.0 feat: token-load reduction — preamble runtime scripts, gated onboarding, 20 skill carves, CLAUDE.md trim (#2691) Garry Tan 2026-08-27 09:50:31 -07:00
  • a181601bde fix(test): stage design-consultation's sections/ into the E2E fixture #2691 prompt-token-load-reduction Garry Tan 2026-08-27 16:23:37 +00:00
  • 969fed9b4f test(e2e-design): widen the Aesthetic synonym set — vocabulary variance, not a regression Garry Tan 2026-08-27 16:15:09 +00:00
  • 41b6d1fdb5 docs: repoint the preamble-runtime version reference after the queue rebump (v1.71.0.0) Garry Tan 2026-08-27 15:53:04 +00:00
  • c7837f0732 Merge remote-tracking branch 'origin/main' into prompt-token-load-reduction Garry Tan 2026-08-27 15:50:05 +00:00
  • a3749bfa4b v1.70.1.0 fix: ship names the /document-release subagent at every decision point (tripwire + gate E2E) (#2700) Garry Tan 2026-08-27 08:46:41 -07:00
  • 8f18682880 fix(ci): run the ship-docsync gate E2E in the evals matrix + silent-skip tripwire #2700 ship-document-release-tests Garry Tan 2026-08-26 17:56:43 +00:00
  • 65b9cff299 fix: raise bun-polyfill subprocess budget to 60s for degraded Windows runners Garry Tan 2026-08-26 17:56:43 +00:00
  • bb56dfef96 docs: CHANGELOG accuracy fixes from the doc-release review Garry Tan 2026-08-26 16:27:23 +00:00
  • a5b1396599 chore: bump version and changelog (v1.70.1.0) Garry Tan 2026-08-26 16:09:12 +00:00
  • adb06cb30f fix: adversarial review fixes Garry Tan 2026-08-26 16:07:04 +00:00
  • 595f6e60bd fix: red-team review fixes Garry Tan 2026-08-26 15:53:08 +00:00
  • 14ee421fb1 fix: pre-landing review fixes Garry Tan 2026-08-26 15:32:55 +00:00
  • 62cdb0811c docs: fix stale document-release TODOS entry + three review-deferred items Garry Tan 2026-08-26 00:35:47 +00:00
  • 1d259d06d6 test: gate-tier E2E proving /ship dispatches the document-release subagent Garry Tan 2026-08-26 00:35:12 +00:00
  • 1f0ec2e0c0 test: pin the ship→document-release Step 18 wiring with a free tripwire Garry Tan 2026-08-26 00:09:28 +00:00
  • 2cb359cbc5 fix(ship): name the /document-release subagent at every Step 18 decision point Garry Tan 2026-08-26 00:08:46 +00:00
  • 98bb779a88 docs(changelog): correct numeric claims against measured counts Garry Tan 2026-08-25 21:14:53 +00:00
  • 3b7dac5fd8 docs: doc-review fixes — repair moved-file links, drop unbacked session-count claim Garry Tan 2026-08-25 21:12:38 +00:00
  • 4fc48508ac docs: update project documentation for v1.70.0.0 Garry Tan 2026-08-25 20:59:21 +00:00
  • 53c2f8988c chore: bump version and changelog (v1.70.0.0) Garry Tan 2026-08-25 20:50:15 +00:00
  • bd59358640 test(ci): demote the preamble A/B to periodic (OV7) and add it to the periodic matrix Garry Tan 2026-08-25 20:50:15 +00:00
  • 4f432f521c test: hermetic update-check, onboarding gate sequencing, seeding parity Garry Tan 2026-08-25 20:50:15 +00:00
  • 6161b8ae1e chore: regenerate renders for the question-log placeholder; goldens + baselines follow Garry Tan 2026-08-25 20:50:15 +00:00
  • 49321ce71f fix(resolvers): question-log session_id becomes a substitution placeholder + stale-comment sweep Garry Tan 2026-08-25 20:50:15 +00:00
  • 46d158c5ed fix(security): harden the skill-start trust boundary — review-army findings Garry Tan 2026-08-25 20:50:15 +00:00
  • cf53075104 test: raise carve-section-loading wall clock to 480s SDK / 540s bun Garry Tan 2026-08-25 19:31:38 +00:00
  • a37f2c48e3 fix(test): seed onboarding markers into the hermetic child GSTACK_HOME Garry Tan 2026-08-25 18:34:03 +00:00
  • 967c71d32c docs: trim CLAUDE.md 66.4→44.9KB — verbatim moves to docs/, pointers stay inline Garry Tan 2026-08-25 18:10:26 +00:00
  • 64f55cc0b1 test: register wave-4 carves (office-hours ext, design-html, design-shotgun) — 20 carved skills Garry Tan 2026-08-25 18:05:54 +00:00
  • 4fce22d708 feat(design): carve UX doctrine + Pretext patterns into read-on-demand sections Garry Tan 2026-08-25 18:05:54 +00:00
  • eae484c0f7 feat(office-hours): carve Phase 2A/2B into mode-exclusive sections (81→67KB skeleton) Garry Tan 2026-08-25 18:05:54 +00:00
  • 3bc3b5d5f9 fix(test): drop stale generate-lake-intro import (generator deleted in the emission-layer move) Garry Tan 2026-08-25 17:52:26 +00:00
  • 07b225a40c test: register wave-3 carves (qa, browse, retro) — guards, touchfiles, pins, baselines Garry Tan 2026-08-25 17:47:32 +00:00
  • e0250aa128 feat(retro): absorb inline git/awk metrics into bin/gstack-retro-metrics + carve report format Garry Tan 2026-08-25 17:47:32 +00:00
  • b007814be0 feat(browse): carve full command list + snapshot flags into sections/command-list.md (39→27KB skeleton) Garry Tan 2026-08-25 17:47:32 +00:00
  • f1d21b65ca feat(qa): carve QA patterns + health rubric into on-demand sections (68→48KB skeleton) Garry Tan 2026-08-25 17:47:32 +00:00
  • 706091cbf9 chore(guards): register wave-2 carves (15 carved skills); autoplan monolith retires; baselines follow Garry Tan 2026-08-25 17:03:12 +00:00
  • cdfe2d9074 feat(setup-gbrain): carve the branch-exclusive install paths into sections Garry Tan 2026-08-25 17:03:12 +00:00
  • 6bb1996004 feat(spec): carve the post-confirmation gate-and-file tail into one section Garry Tan 2026-08-25 17:03:12 +00:00
  • c593c93268 feat(autoplan): carve the four review phases + tasks aggregator into sections Garry Tan 2026-08-25 17:03:12 +00:00
  • 2877b63afe test(gen-skill-docs): review render pins read the carved union Garry Tan 2026-08-25 16:36:37 +00:00
  • 00737fcb1b chore(guards): register wave-1 carves; monolith invariants retire; baselines + ratchet follow Garry Tan 2026-08-25 16:36:16 +00:00
  • 4e54d6e0a2 feat(ios): demote the four ios skills to preamble-tier 2 (Phase 5) Garry Tan 2026-08-25 16:36:16 +00:00
  • b4fda5f484 feat(land-and-deploy): carve first-run validation, readiness gate, and merge/deploy into sections Garry Tan 2026-08-25 16:36:02 +00:00
  • 87589961a4 feat(codex): carve the three mutually exclusive modes into sections Garry Tan 2026-08-25 16:36:02 +00:00
  • 3a78bf7c1d feat(review): carve adversarial, plan-completion, and review-army into sections Garry Tan 2026-08-25 16:36:02 +00:00
  • c7488f7e38 chore(test): baseline + ratchet follow Phase 3 (OV9); OV8 evaluated — shrink floor stays Garry Tan 2026-08-25 16:09:08 +00:00
  • a3343beef0 chore(gen): regenerate all skills + goldens — AUQ slim Garry Tan 2026-08-25 16:09:08 +00:00
  • 353d64345b feat(gen): AUQ slim — tool resolution as a STATUS-line branch table, split rules to invariants + absolute pointer Garry Tan 2026-08-25 16:09:08 +00:00
  • 7f780ef530 chore(test): carve floors/ceilings recomputed; baseline + ratchet follow Phase 2 (OV9) Garry Tan 2026-08-25 16:03:53 +00:00
  • d2ac837773 test: onboarding tombstone + Phase 2 pin relocations Garry Tan 2026-08-25 16:03:53 +00:00
  • a57fef299c chore(gen): regenerate all skills + goldens — onboarding prose degated Garry Tan 2026-08-25 16:03:39 +00:00
  • f564d291f8 feat(gen): drop the 8 onboarding generators — renders keep one instruction-block rule Garry Tan 2026-08-25 16:03:39 +00:00
  • e55edf2cec feat(bin): instruction-emission layer — onboarding text appears only when its gate fires Garry Tan 2026-08-25 16:03:39 +00:00