Commit Graph

  • 11de390be1 v1.58.5.0 feat: first-run activation scaffold + gstack router front door (#2078) main Garry Tan 2026-06-25 09:42:45 -07:00
  • 606741e2eb fix(ci): also register pty-smoke skills project-scoped (cwd/.claude/skills) garrytan/retention-cohorts Garry Tan 2026-06-24 15:32:53 -07:00
  • 0c006f12ad fix(ci): guard rm expansion in pty-smoke registry (shellcheck SC2115) Garry Tan 2026-06-24 15:21:26 -07:00
  • 3ed655bcb5 fix(ci): copy SKILL.md as real files in pty-smoke registry (cross-mount symlink) Garry Tan 2026-06-24 15:21:10 -07:00
  • 525254455a chore: revert pty-smoke harness experiments (race-retry + CI debug step) Garry Tan 2026-06-24 08:16:04 -07:00
  • 9e85de551e debug(ci): temporarily instrument pty-smoke skill discovery Garry Tan 2026-06-24 08:07:14 -07:00
  • 7472d99031 fix(test): tolerate skill-discovery race in PTY plan-mode smoke Garry Tan 2026-06-24 07:59:22 -07:00
  • 48254d7830 fix(test): repoint bws skillmd-* setup-block assertions to browse/SKILL.md Garry Tan 2026-06-24 07:44:49 -07:00
  • 22882c913b Merge remote-tracking branch 'origin/main' into garrytan/retention-cohorts Garry Tan 2026-06-24 07:17:35 -07:00
  • ad60143f29 chore: bump version and changelog (v1.58.5.0) Garry Tan 2026-06-21 07:16:58 -07:00
  • 18d3e9fc0f chore: regenerate SKILL.md + llms.txt for first-run activation Garry Tan 2026-06-21 07:16:53 -07:00
  • 866159861d test: cover first-run detection + repoint browse-content assertions to /browse Garry Tan 2026-06-21 07:16:24 -07:00
  • 938fa4a035 feat: first-run activation — project-aware scaffold, router front door, onboarding nudges Garry Tan 2026-06-21 07:16:18 -07:00
  • 9fd03fae9e v1.58.4.0 fix: high-priority community bug wave + PTY plan-mode smoke gate (#2077) Garry Tan 2026-06-21 07:15:19 -07:00
  • 1b34cbf25b chore: bump version and changelog (v1.58.4.0) garrytan/triage-high-priority-prs Garry Tan 2026-06-21 07:00:13 -07:00
  • 7a2f5e54a2 Merge remote-tracking branch 'origin/main' into garrytan/triage-high-priority-prs Garry Tan 2026-06-21 06:52:06 -07:00
  • 12244c4e47 ci(evals): install gstack skill registry for the PTY smoke suite Garry Tan 2026-06-18 11:22:48 -07:00
  • a861c00cfa v1.58.3.0 feat: gbrowser anti-detection Layer C stealth (#2047) Garry Tan 2026-06-18 10:45:05 -07:00
  • d04e06acd3 docs: sync browser stealth docs to Layer C (v1.58.3.0) gbrowser-anti-detection Garry Tan 2026-06-18 10:34:58 -07:00
  • 7b8e932eaa chore: bump version and changelog (v1.58.3.0) Garry Tan 2026-06-18 10:29:54 -07:00
  • 1067b12e96 fix(browse): recreateContext() re-applies stealth (closes 4th un-stealth path) Garry Tan 2026-06-18 01:39:23 -07:00
  • d63f2adb6f test(browse): cover readHostProfile clamp, toString depth-3, chrome.* calls Garry Tan 2026-06-18 01:26:48 -07:00
  • 4f10857b64 refactor(browse): drop dead HostProfile.platform, export test internals Garry Tan 2026-06-18 01:26:48 -07:00
  • 21b37cca9f fix(browse): handoff() + launchHeaded() spread the shared STEALTH_LAUNCH_ARGS Garry Tan 2026-06-18 01:26:48 -07:00
  • 832bb48d93 ci(evals): gate the deterministic PTY plan-mode smokes in CI Garry Tan 2026-06-18 01:17:16 -07:00
  • b9919f25b4 test(tiers): reclassify stochastic plan-eng/plan-design ask-first smokes as periodic Garry Tan 2026-06-18 01:00:49 -07:00
  • 496ce80293 feat(plan-review): ask-first scope gate for plan-eng + plan-design review Garry Tan 2026-06-18 00:59:03 -07:00
  • e4c372ed98 test(browse): runtime + extended-mode coverage for the stealth blend Garry Tan 2026-06-18 00:58:57 -07:00
  • be67fcce0f test(pty): detect stripAnsi-collapsed prose AUQs + judge spinner-precedence Garry Tan 2026-06-18 00:58:50 -07:00
  • 588379fda3 docs(browse): correct stale stealth comments Garry Tan 2026-06-18 00:58:50 -07:00
  • 248ca588fa fix(browse): make --gstack-suppress-prepare-stack-trace opt-in, not default-on Garry Tan 2026-06-18 00:58:45 -07:00
  • c389084a64 fix(browse): apply stealth on every launch path + share automation-artifact cleanup Garry Tan 2026-06-18 00:58:34 -07:00
  • 2e102232e4 Merge remote-tracking branch 'origin/main' into garrytan/trunk-land-skill garrytan/trunk-land-skill Garry Tan 2026-06-17 08:36:46 -07:00
  • 66e1f44a86 Merge origin/main into gbrowser-anti-detection Garry Tan 2026-06-17 07:54:24 -07:00
  • f436aab0db test(pty): detect markdown bold-bullet prose AUQs (fixes office-hours smoke) Garry Tan 2026-06-16 22:42:12 -07:00
  • 6216c3e326 test(pty): pin spawned claude to EVALS model chain (default claude-sonnet-4-6) Garry Tan 2026-06-14 11:49:23 -07:00
  • c7ae63201a v1.58.1.0 feat: hermetic local E2E + Conductor prose AskUserQuestion (#2004) Garry Tan 2026-06-14 11:40:57 -07:00
  • 80c02eb185 docs: regenerate diagram SKILL.md with Conductor prose preamble garrytan/conductor-skip-askuserquestion Garry Tan 2026-06-14 09:32:29 -07:00
  • 264da8a811 chore: sync package.json to 1.58.1.0 Garry Tan 2026-06-14 09:32:29 -07:00
  • d5b869afd5 docs: document hermetic-by-default E2E + eval:bg detached runs in CONTRIBUTING Garry Tan 2026-06-14 09:28:39 -07:00
  • a4197b962c harden: hermetic temp-dir GC grace window + half-seed cleanup Garry Tan 2026-06-14 09:21:44 -07:00
  • 350cce05d6 Merge remote-tracking branch 'origin/main' into garrytan/conductor-skip-askuserquestion Garry Tan 2026-06-14 09:12:58 -07:00
  • c15f78924e fix: workflow judge re-appends body-carved sections after the marker slice Garry Tan 2026-06-13 10:48:35 -07:00
  • 14fc0866d9 v1.58.0.0 feat: diagram + multi-format document engine (mermaid, excalidraw, single-file HTML, DOCX) (#1990) Garry Tan 2026-06-12 15:38:53 -07:00
  • 6d2274e0dc fix: ios-qa daemon scenarios use unique pidfiles under --concurrent Garry Tan 2026-06-12 15:27:19 -07:00
  • 6b715c7fb6 fix: operational-learning fixture copies lib/jsonl-store.ts with the bin Garry Tan 2026-06-12 15:27:19 -07:00
  • 778042be5c docs: hermetic local E2E is the default; retire stale SDK env warning Garry Tan 2026-06-12 11:44:45 -07:00
  • fce00b207f test: refresh codex/factory ship goldens with detached-eval block Garry Tan 2026-06-12 11:44:45 -07:00
  • b2318467e5 docs: apply Codex doc-review findings for v1.58.0.0 garrytan/excalidraw-diagram-skills Garry Tan 2026-06-12 11:24:38 -07:00
  • 65549a4f2a test: static tripwire pins hermetic wiring in all five runners Garry Tan 2026-06-12 11:23:06 -07:00
  • 704619870c feat: agent-sdk-runner spawns hermetic children via complete Options.env Garry Tan 2026-06-12 11:21:31 -07:00
  • b89ce2677c feat: codex/gemini runners spawn hermetic children Garry Tan 2026-06-12 11:18:22 -07:00
  • 9799593abb feat: PTY runner spawns hermetic claude sessions Garry Tan 2026-06-12 11:17:19 -07:00
  • c3e65b1634 feat: session-runner spawns hermetic children + isolation canaries Garry Tan 2026-06-12 11:13:50 -07:00
  • 8c7e04517c docs: sync make-pdf image-policy docs with final shipped behavior (v1.58.0.0) Garry Tan 2026-06-12 11:11:14 -07:00
  • 51e9351ed7 fix(ios-qa): isolate E2E tests under --concurrent (3 real races) Garry Tan 2026-06-12 11:10:15 -07:00
  • 2d56961636 feat: hermetic child-env builder for E2E runners Garry Tan 2026-06-12 11:07:05 -07:00
  • 9e63c2dfc9 refactor: extract pure promotedEnv() from conductor-env-shim Garry Tan 2026-06-12 11:04:10 -07:00
  • 4831d25e3e chore: bump version and changelog (v1.58.0.0) Garry Tan 2026-06-12 11:00:35 -07:00
  • 26a7cab26d fix(make-pdf): adversarial-review wave — offline posture enforced, symlink-aware confinement, bounded reads Garry Tan 2026-06-12 10:01:48 -07:00
  • 1bd984f86d fix: pre-existing test failure in skill-e2e-bws operational-learning Garry Tan 2026-06-12 09:49:51 -07:00
  • 1d130e2446 feat(make-pdf): out-of-tree image reads warn; --strict makes them fatal (D8.1) Garry Tan 2026-06-12 09:38:52 -07:00
  • 91ba37530d test(make-pdf)+feat(diagram): review-wave test pins + skill transport hardening Garry Tan 2026-06-12 07:57:42 -07:00
  • f2a03d43cb ci: make-pdf gate covers the diagram-render bundle; bundle pinned to LF Garry Tan 2026-06-12 07:57:42 -07:00
  • 9db479a38d fix(make-pdf): pre-landing review wave — fence fidelity, injection hardening, Windows paths, transport rework Garry Tan 2026-06-12 07:57:42 -07:00
  • 0b7b5ee0f7 test(make-pdf): fill ship-audit coverage gaps — downscale, reset contract, excalidraw fence, WebP Garry Tan 2026-06-12 07:10:10 -07:00
  • 8759442089 docs: diagram + multi-format documentation across README, make-pdf skill, and how-to guide Garry Tan 2026-06-12 06:57:42 -07:00
  • 3cbb5c3bbd test: fix operational-learning E2E fixture — copy lib/jsonl-store.ts Garry Tan 2026-06-12 06:54:17 -07:00
  • 832a148e55 docs: P1 TODO — eval harness live progress + incremental persistence Garry Tan 2026-06-12 06:44:19 -07:00
  • 4c11fe4e61 test(make-pdf): pin zero-truncation invariant, typography floor, centering math Garry Tan 2026-06-12 06:32:55 -07:00
  • 9397e7f847 feat(make-pdf): typography scale-up, zero image truncation, landscape vertical centering Garry Tan 2026-06-12 06:32:55 -07:00
  • 4e560d4aba chore: bump version and changelog (v1.57.11.0) Garry Tan 2026-06-12 06:27:34 -07:00
  • 201e46b230 fix: adversarial review fixes (Claude + Codex cross-model passes) Garry Tan 2026-06-11 23:46:35 -07:00
  • a38089aac6 docs: wire detached-eval guidance into /ship + correct CLAUDE.md flags Garry Tan 2026-06-12 06:24:39 -07:00
  • 6eea549121 feat: eval:bg* use run-scoped logs + machine lock + watchdog Garry Tan 2026-06-12 06:23:29 -07:00
  • a4fb10e519 feat: harden gstack-detach against all four eval-infra killers Garry Tan 2026-06-12 06:23:14 -07:00
  • 2a68d366b2 test(diagram): register /diagram in the skill coverage matrix Garry Tan 2026-06-12 00:43:59 -07:00
  • 29b948bd90 test(diagram): paid E2E pair — gate triplet contract + periodic authoring judge Garry Tan 2026-06-12 00:32:37 -07:00
  • 462c06224a feat(diagram): /diagram skill — English in, editable diagram triplet out Garry Tan 2026-06-12 00:32:37 -07:00
  • 582fa0c60f test(make-pdf): format gate — html no-network-refs + docx zip content checks Garry Tan 2026-06-12 00:12:04 -07:00
  • aec7e2b72b feat(make-pdf): --to html|docx output formats Garry Tan 2026-06-12 00:12:04 -07:00
  • a2c1eae16e test(make-pdf): width-policy unit suite + landscape e2e gate with negative fixtures Garry Tan 2026-06-12 00:06:46 -07:00
  • 89c35352cc feat(make-pdf): width directives + conservative auto-landscape via CSS named pages Garry Tan 2026-06-12 00:06:45 -07:00
  • e7c0c1bf51 test(make-pdf): diagram pre-pass unit suite + e2e render gates Garry Tan 2026-06-11 23:59:40 -07:00
  • 67e87fe421 feat(make-pdf): diagram pre-pass — mermaid/excalidraw fences render as vector SVG; local images inline as data URIs Garry Tan 2026-06-11 23:59:40 -07:00
  • 69bf3b07a1 feat(diagram-render): __downscaleRaster for print-resolution image normalization Garry Tan 2026-06-11 23:59:40 -07:00
  • 8c8e3b9e52 fix: pre-landing review fixes Garry Tan 2026-06-11 23:31:26 -07:00
  • a311cb1ec5 feat(diagram-render): offline mermaid+excalidraw render bundle for browse Garry Tan 2026-06-11 23:26:28 -07:00
  • c07e1ffcfb docs(todos): P3 content-hash diagram render cache for make-pdf Garry Tan 2026-06-11 23:26:28 -07:00
  • 88ca684929 test: coverage-audit additions for the fix wave Garry Tan 2026-06-11 23:08:54 -07:00
  • b608b060b9 docs: CLAUDE.md — agents must run long evals via gstack-detach Garry Tan 2026-06-11 23:07:11 -07:00
  • f8a0dc0888 feat: eval:bg* scripts — detached eval runs for agents Garry Tan 2026-06-11 23:06:33 -07:00
  • d1fc21cbca feat: gstack-detach — run agent eval/bench jobs in their own session Garry Tan 2026-06-11 23:05:59 -07:00
  • 028cb52ca8 feat(redact): six new credential patterns — GitLab, HuggingFace, npm, DigitalOcean, Bearer, GCP SA (#1946) Garry Tan 2026-06-11 20:58:58 -07:00
  • 6bc00abb0f fix(redact): prepush guard fails closed on git failure; /ship owns hook install (#1946) Garry Tan 2026-06-11 20:40:46 -07:00
  • 0f165cbed0 test: strip ambient Conductor env in memory-cache-injection hook harness Garry Tan 2026-06-11 20:38:18 -07:00
  • fcdcde95a2 v1.58.0.0 feat: Conductor renders AskUserQuestion decisions as prose Garry Tan 2026-06-11 20:20:19 -07:00
  • c8f078b482 fix(telemetry): redact error_message spans before they leave the machine (#1947) Garry Tan 2026-06-11 20:38:06 -07:00
  • b3085f137e fix(security): community-pulse + both dashboards never report fake zeros (#1947) Garry Tan 2026-06-11 20:35:17 -07:00
  • 82c5140fda fix(question-log): dedupe INJECTION_PATTERNS via lib/jsonl-store (#1934) Garry Tan 2026-06-11 20:30:45 -07:00