mirror of
https://github.com/garrytan/gstack.git
synced 2026-10-31 22:14:25 +01:00
ac20ef1e13
* fix(make-pdf,design): real TOC page numbers and anchors; design models move to gpt-5.5 + gpt-image-2 (#2903, #2807) * ci: pin every action to a SHA, Scorecard, checksummed Bun, scoped Codex CLI in the CI image, macOS named-regressions job (#1948, #1706, #1997) * fix(cso,browse): Windows/macOS lease identity, retention skips bad runs, truthful 'not assessed' reports, env.kv false positive, Windows browse spawn fixes (#2894, #2912, #2048, #2637, #2805) * fix(outside-voice): one Codex model precedence for probe and dispatch, bounded timeouts with KILL escalation, probe cache identity, guarded mktemp, skills hidden in nested Codex (#2776, #2914, #2787, #2881, #2847) * feat(setup): install registry, ./setup --status, staged activation, per-scope migrations, host tiers and conformance kit, OpenCode/Hermes fixes, Copilot CLI (experimental), disabled_skills, slimmer CLAUDE.md (#1925, #2879, #2347, #2338, #2626, #2629, #2825, #2015, #393, #1206, #2096) Co-authored-by: Andrey Esipov <61357035+andrey-esipov@users.noreply.github.com> Co-authored-by: Matthew Williams <5863886+ridermw@users.noreply.github.com> Co-authored-by: Rocky Wu <92764750+lolisaigao1234@users.noreply.github.com> * fix(preamble): skills start in worktree-isolated Claude Code sessions — one literal skill-start line, context-recovery helper, no eval in skill blocks, $N token tripwire, honest plan-mode precedence (#2763, #2896, #2851) * fix(setup): per-install renders for renamed, vendored and custom-config installs, space-safe alias roots, per-host /cso launcher path (#1882, #2906) * test: free tests never write the real HOME (home-write tripwire), no orphaned browse daemons, symlinked-TMPDIR (macOS) fixes, gbrain-on-PATH isolation (#2895, #2816, #2829, #2841, #2982, #2911, #2909, #2908, #2910) * chore: integrate wave follow-ups — regenerate all hosts, README model docs, TODOS, touchfiles, duration seeds, Bun 1.3 telemetry test fix, replay fixtures pinned to their recorded bytes * v1.91.14.0: release metadata * test(browse): group-kill cleanup falls back to the leader when macOS returns EPERM for a live group * ci: Codex login steps run under bash (the CI container's default sh rejects pipefail) * fix: full-suite repairs — private state roots for 7 real-HOME writers, truthful home-guard attribution with --attribute-home, gstack-paths shim in ship-hook fixtures, Copilot in team-init probes, test-of-test detector, cookie review fixture pinned to the approved excerpt * fix(windows): LF for Dockerfiles, normalized home-guard exclusions, path.relative fixture containment, ship push test spawn timeouts * test(design-detect): widen the whole-scan budget test's timing margins so a loaded macOS runner can't time out the single-batch call * fix(evals): qa protocol names defined for the judge, async PTY judge so overlapping sessions keep their cleanup deadline, bws setup cases use the standard JUDGE_MS tier * test(pty): the non-blocking judge case is POSIX-only (its fake judge is a shebang script, like the PTY harness it covers) * test(evals): ship-coverage-audit names absolute skill paths, uses Read, and skips the Step 7 artifact nothing consumes (removes the mechanism behind 3 of 4 historical timeouts) * test: deflake terminal-agent concurrent startup (write the placeholder record before spawning, like the product) and qa-evidence resumed pipe (barrier on a full high-water mark instead of a sleep) * fix(design): daemon log stream handles open errors instead of crashing the daemon; shutdown test awaits the stubbed exit * test(evals): skillify checks the product's resolved state root (no GSTACK_HOME bypass), negative cases check every root; tpa shims live outside the agent's cwd and answer consistently * test(evals): coverage-audit detector splits parallel columns at │ rails and [+] groups; coverage prompts name absolute skill paths; TODOs from the gate eval census * fix(plan-eng-review): scope gate always sends the menu (no headless 'Scope pending' exit); PTY harness ends idle turn-ends and API-error panels promptly with a precise diagnostic * test(evals): one position-bound coverage-read rule credits read-only && chains (labels, context ranges, git displays in either order) and still rejects forged output * fix(ship): documentation section has one saved source inserted by cat (never retyped); spawned-marker evidence is the child output; refreshed codex/factory ship goldens * test(docsync): the byte-exact insert positive is POSIX-only (the bash-command observer refuses backslash paths by design) * test(evals): plan-design-with-ui focus-title rule accepts the comma-less 'dimensions or focus' wording (replayed on the captured CI run, negative controls kept) * fix(qa-callers): exploratory preflight says the scope/method Reads come after exploratory.md; design-review scan check credits an executed scan proven by one engine run over the changed files --------- Co-authored-by: Andrey Esipov <61357035+andrey-esipov@users.noreply.github.com> Co-authored-by: Matthew Williams <5863886+ridermw@users.noreply.github.com> Co-authored-by: Rocky Wu <92764750+lolisaigao1234@users.noreply.github.com>
109 lines
6.8 KiB
JSON
109 lines
6.8 KiB
JSON
{
|
|
"name": "gstack",
|
|
"version": "1.91.16",
|
|
"description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.",
|
|
"license": "MIT",
|
|
"type": "module",
|
|
"bin": {
|
|
"browse": "./browse/dist/browse",
|
|
"make-pdf": "./make-pdf/dist/pdf"
|
|
},
|
|
"scripts": {
|
|
"build": "bash scripts/build.sh",
|
|
"build:cso": "bash scripts/build-cso.sh",
|
|
"format:cso": "prettier --write 'lib/cso/*.ts'",
|
|
"format:cso:check": "prettier --check 'lib/cso/*.ts'",
|
|
"typecheck": "tsc -p tsconfig.json",
|
|
"typecheck:test": "bun run scripts/typecheck-test.ts",
|
|
"test:cso:docker": "bun test --max-concurrency 1 test/cso-docker-integration.test.ts test/cso-node-lifecycle-integration.test.ts test/cso-stack-cold-integration.test.ts",
|
|
"test:cso:macos": "bun test test/cso-macos-launcher.test.ts test/cso-registry-socket.test.ts",
|
|
"test:cso:windows": "bun test test/cso-windows-launcher.test.ts",
|
|
"vendor:xterm": "mkdir -p extension/lib && cp node_modules/xterm/lib/xterm.js extension/lib/xterm.js && cp node_modules/xterm/css/xterm.css extension/lib/xterm.css && cp node_modules/xterm-addon-fit/lib/xterm-addon-fit.js extension/lib/xterm-addon-fit.js",
|
|
"dev:make-pdf": "bun run make-pdf/src/cli.ts",
|
|
"dev:design": "bun run design/src/cli.ts",
|
|
"build:diagram-render": "cd lib/diagram-render && bun install && bun run scripts/build.ts",
|
|
"build:gates": "bun build --compile make-pdf/src/cli.ts --outfile make-pdf/dist/pdf && bun build --compile browse/src/cli.ts --outfile browse/dist/browse && bun run build:diagram-render",
|
|
"gen:skill-docs": "bun run scripts/gen-skill-docs.ts",
|
|
"gen:skill-docs:user": "bun run scripts/gen-skill-docs.ts --respect-detection",
|
|
"dev": "bun run browse/src/cli.ts",
|
|
"server": "bun run browse/src/server.ts",
|
|
"test": "bun run scripts/test-free-shards.ts",
|
|
"test:free": "bun run scripts/test-free-shards.ts",
|
|
"test:windows": "bun run scripts/test-free-shards.ts --windows-only",
|
|
"test:ubicloud": "bash scripts/ubicloud/test-free.sh",
|
|
"test:evals": "EVALS=1 bun test --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-llm-eval*.test.ts test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e*.test.ts test/llm-judge-recommendation.test.ts test/carve-section-loading*.test.ts",
|
|
"test:evals:all": "EVALS=1 EVALS_ALL=1 bun test --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-llm-eval*.test.ts test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e*.test.ts test/llm-judge-recommendation.test.ts test/carve-section-loading*.test.ts",
|
|
"test:e2e": "EVALS=1 bun test --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e*.test.ts test/carve-section-loading*.test.ts",
|
|
"test:e2e:all": "EVALS=1 EVALS_ALL=1 bun test --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e*.test.ts test/carve-section-loading*.test.ts",
|
|
"test:gate": "EVALS=1 EVALS_TIER=gate bun test --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-llm-eval*.test.ts test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e*.test.ts test/llm-judge-recommendation.test.ts test/carve-section-loading*.test.ts",
|
|
"test:periodic": "EVALS=1 EVALS_TIER=periodic EVALS_ALL=1 bun test --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-llm-eval*.test.ts test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e*.test.ts test/llm-judge-recommendation.test.ts test/carve-section-loading*.test.ts",
|
|
"test:gate:sharded": "bun run scripts/test-paid-shards.ts --tier gate",
|
|
"test:periodic:sharded": "EVALS_ALL=1 bun run scripts/test-paid-shards.ts --tier periodic",
|
|
"test:codex": "EVALS=1 bun test test/codex-e2e.test.ts test/codex-e2e-sol-scope.test.ts",
|
|
"test:codex:all": "EVALS=1 EVALS_ALL=1 bun test test/codex-e2e.test.ts test/codex-e2e-sol-scope.test.ts",
|
|
"skill:check": "bun run scripts/skill-check.ts",
|
|
"dev:skill": "bun run scripts/dev-skill.ts",
|
|
"start": "bun run browse/src/server.ts",
|
|
"eval:bg": "bin/gstack-detach --label evals --lock gstack-evals --timeout 5400 -- bun run test:evals",
|
|
"eval:bg:all": "bin/gstack-detach --label evals-all --lock gstack-evals --timeout 7200 -- bun run test:evals:all",
|
|
"eval:bg:gate": "bin/gstack-detach --label evals-gate --lock gstack-evals --timeout 49320 -- bun run test:gate:sharded",
|
|
"eval:bg:periodic": "bin/gstack-detach --label evals-periodic --lock gstack-evals --timeout 67380 -- bun run test:periodic:sharded",
|
|
"eval:list": "bun run scripts/eval-list.ts",
|
|
"eval:compare": "bun run scripts/eval-compare.ts",
|
|
"eval:summary": "bun run scripts/eval-summary.ts",
|
|
"eval:flake-rank": "bun run scripts/eval-flake-rank.ts",
|
|
"eval:pass-rates": "bun run scripts/eval-flake-rank.ts",
|
|
"eval:watch": "bun run scripts/eval-watch.ts",
|
|
"eval:select": "bun run scripts/eval-select.ts",
|
|
"analytics": "bun run scripts/analytics.ts",
|
|
"test:audit": "bun test test/audit-compliance.test.ts",
|
|
"slop": "npx slop-scan scan . 2>/dev/null || echo 'slop-scan not available (install with: npm i -g slop-scan)'",
|
|
"slop:diff": "bun run scripts/slop-diff.ts",
|
|
"test:quick": "bun run scripts/test-free-shards.ts --quick",
|
|
"test:pr": "EVALS_JOBS=${EVALS_JOBS:-2} bun run scripts/test-paid-shards.ts --tier gate --profile pr",
|
|
"test:release": "EVALS_ALL=1 EVALS_FRESH=1 EVALS_CACHE_PURPOSE=release bun run scripts/test-paid-shards.ts --tier gate --profile full && EVALS_ALL=1 EVALS_FRESH=1 EVALS_CACHE_PURPOSE=release bun run scripts/test-paid-shards.ts --tier periodic --profile full",
|
|
"eval:bg:pr": "bin/gstack-detach --label evals-pr --lock gstack-evals --timeout 92820 -- bun run test:pr",
|
|
"eval:bg:release": "bin/gstack-detach --label evals-release --lock gstack-evals --timeout 116700 -- bun run test:release"
|
|
},
|
|
"dependencies": {
|
|
"@huggingface/transformers": "^4.2.0",
|
|
"@ngrok/ngrok": "^1.7.0",
|
|
"cross-spawn": "^7.0.6",
|
|
"diff": "^9.0.0",
|
|
"html-to-docx": "1.8.0",
|
|
"marked": "^18.0.11",
|
|
"playwright": "^1.62.1",
|
|
"socks": "^2.8.9"
|
|
},
|
|
"engines": {
|
|
"bun": ">=1.0.0"
|
|
},
|
|
"keywords": [
|
|
"browser",
|
|
"automation",
|
|
"playwright",
|
|
"headless",
|
|
"cli",
|
|
"claude",
|
|
"ai-agent",
|
|
"devtools"
|
|
],
|
|
"devDependencies": {
|
|
"@anthropic-ai/claude-agent-sdk": "0.2.117",
|
|
"@anthropic-ai/sdk": "^0.78.0",
|
|
"@types/bun": "1.4.0",
|
|
"prettier": "3.9.9",
|
|
"typescript": "7.0.2",
|
|
"xterm": "^5.3.0",
|
|
"xterm-addon-fit": "^0.8.0"
|
|
},
|
|
"overrides": {
|
|
"adm-zip": "^0.6.1",
|
|
"ip-address": "10.3.1",
|
|
"sharp": "0.35.4"
|
|
},
|
|
"patchedDependencies": {
|
|
"playwright-core@1.62.1": "patches/playwright-core@1.62.1.patch"
|
|
}
|
|
}
|