mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-11 15:39:04 +02:00
Garry TanandOpenAI Codex
71f6048e8a
* fix: default cross-model workflows to frontier models * chore: bump version and changelog (v1.82.1.0) Co-Authored-By: OpenAI Codex <noreply@openai.com> * fix: repair frontier eval budgets and workflow instructions Preserve frontier models and quality thresholds while fixing truncated judge output, ordered section expansion, consent checks, QA scoring, and ship audit gates. Add regression coverage and refresh generated docs. Co-Authored-By: OpenAI Codex <noreply@openai.com> * fix: resolve workflow gaps exposed by frontier evals Clarify plan-review ordering and fallback modes, preserve deploy readiness gates, honor configured merge methods, correct benchmark and canary contracts, and restore vendored installs on setup failure. Cover recovery with real-shell regressions. Co-Authored-By: OpenAI Codex <noreply@openai.com> * fix: use agent capture budgets for deploy evals Multi-turn deploy and benchmark sessions were incorrectly limited to the single-call judge timeout. Use the existing capture tier and leave outer-test cleanup headroom, with a free policy regression test. Keep all behavioral assertions and frontier models unchanged. Co-Authored-By: OpenAI Codex <noreply@openai.com> * fix: clarify retro workflow and evaluate compare instructions Include compare mode in the frontier judge excerpt, define metric sources and snapshot ordering, and preserve the existing prompt-size budget. Co-authored-by: OpenAI Codex <noreply@openai.com> * fix: make documentation release review and publication consistent Review before commit, clarify changelog safeguards and unavailable reviewer modes, and preserve raw PR bodies across separate shell calls. Keep title sync in one shell and add regression coverage. Co-authored-by: OpenAI Codex <noreply@openai.com> --------- Co-authored-by: OpenAI Codex <noreply@openai.com>
93 lines
5.7 KiB
JSON
93 lines
5.7 KiB
JSON
{
|
|
"name": "gstack",
|
|
"version": "1.84.1",
|
|
"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",
|
|
"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:evals": "EVALS=1 bun test --retry 1 --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/gemini-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 --retry 1 --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/gemini-e2e.test.ts test/llm-judge-recommendation.test.ts test/carve-section-loading.test.ts",
|
|
"test:e2e": "EVALS=1 bun test --retry 1 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e*.test.ts test/gemini-e2e.test.ts test/carve-section-loading.test.ts",
|
|
"test:e2e:all": "EVALS=1 EVALS_ALL=1 bun test --retry 1 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e*.test.ts test/gemini-e2e.test.ts test/carve-section-loading.test.ts",
|
|
"test:gate": "EVALS=1 EVALS_TIER=gate bun test --retry 1 --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/gemini-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 --retry 1 --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/gemini-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",
|
|
"test:gemini": "EVALS=1 bun test test/gemini-e2e.test.ts",
|
|
"test:gemini:all": "EVALS=1 EVALS_ALL=1 bun test test/gemini-e2e.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 25200 -- bun run test:gate:sharded",
|
|
"eval:bg:periodic": "bin/gstack-detach --label evals-periodic --lock gstack-evals --timeout 37800 -- 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: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"
|
|
},
|
|
"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",
|
|
"xterm": "^5.3.0",
|
|
"xterm-addon-fit": "^0.8.0"
|
|
},
|
|
"overrides": {
|
|
"adm-zip": "^0.6.0",
|
|
"ip-address": "10.3.1",
|
|
"sharp": "0.35.0"
|
|
},
|
|
"patchedDependencies": {
|
|
"playwright-core@1.62.1": "patches/playwright-core@1.62.1.patch"
|
|
}
|
|
}
|