mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-21 04:10:47 +02:00
SinabinaandClaude Opus 4.8
313e8719f7
Backing the model benchmark with Braintrust's local eval runner and its autoevals scorer library instead of an in-house scoring engine. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
105 lines
5.6 KiB
JSON
105 lines
5.6 KiB
JSON
{
|
|
"name": "gstack",
|
|
"version": "1.60.1.0",
|
|
"description": "GStack 2 — six portable Agent Skills with an optional host-neutral runtime.",
|
|
"license": "MIT",
|
|
"type": "module",
|
|
"gstack": {
|
|
"packageRole": "runtime-control",
|
|
"runtimeVersion": "2.0.0",
|
|
"skillApi": "2.0"
|
|
},
|
|
"bin": {
|
|
"gstack": "./bin/gstack",
|
|
"gstack-runtime-bootstrap": "./runtime/runtime-bootstrap.mjs"
|
|
},
|
|
"files": [
|
|
"bin/gstack",
|
|
"runtime",
|
|
"README.md",
|
|
"LICENSE",
|
|
"VERSION"
|
|
],
|
|
"scripts": {
|
|
"build": "bash scripts/build.sh",
|
|
"build:runtime": "bash scripts/build.sh --runtime-only",
|
|
"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",
|
|
"ensure:gstack2-runtime": "bun run scripts/gstack2/ensure-runtime-payloads.ts",
|
|
"verify:gstack2-clean-generation": "bun run scripts/gstack2/verify-clean-generation.ts",
|
|
"gen:gstack2": "bun run ensure:gstack2-runtime && bun run scripts/gstack2/generate-skill-tree.ts",
|
|
"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-strict.ts",
|
|
"check:gstack2-generated": "bun run scripts/gstack2/check-generated.ts",
|
|
"test:gstack2": "bun run gen:gstack2 && bun run check:gstack2-generated && bun test --timeout 60000 test/gstack2-*.test.ts",
|
|
"test:gstack2:install": "bun run scripts/gstack2/test-install-matrix.ts --full",
|
|
"test:gstack2:parity": "bun run ensure:gstack2-runtime && bun run scripts/gstack2/run-parity.ts",
|
|
"test:free": "bun run scripts/test-free-shards.ts",
|
|
"test:windows": "bun run scripts/test-free-shards.ts --windows-only --shards 10000",
|
|
"test:evals": "EVALS=1 bun test --retry 2 --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:evals:all": "EVALS=1 EVALS_ALL=1 bun test --retry 2 --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:e2e": "EVALS=1 bun test --retry 2 --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:e2e:all": "EVALS=1 EVALS_ALL=1 bun test --retry 2 --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:gate": "EVALS=1 EVALS_TIER=gate bun test --retry 2 --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:periodic": "EVALS=1 EVALS_TIER=periodic EVALS_ALL=1 bun test --retry 2 --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:codex": "EVALS=1 bun test test/codex-e2e.test.ts",
|
|
"test:codex:all": "EVALS=1 EVALS_ALL=1 bun test test/codex-e2e.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 3600 -- bun run test:gate",
|
|
"eval:bg:periodic": "bin/gstack-detach --label evals-periodic --lock gstack-evals --timeout 5400 -- bun run test:periodic",
|
|
"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: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",
|
|
"check:release": "bun test test/release-hardening.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": {
|
|
"@anthropic-ai/sdk": "^0.78.0",
|
|
"@ngrok/ngrok": "^1.7.0",
|
|
"diff": "^9.0.0",
|
|
"html-to-docx": "1.8.0",
|
|
"marked": "^18.0.2",
|
|
"playwright": "npm:playwright-core@^1.58.2",
|
|
"sharp": "^0.34.5",
|
|
"socks": "^2.8.8",
|
|
"xterm": "5",
|
|
"xterm-addon-fit": "^0.8.0"
|
|
},
|
|
"engines": {
|
|
"bun": ">=1.0.0",
|
|
"node": ">=18.0.0"
|
|
},
|
|
"keywords": [
|
|
"browser",
|
|
"automation",
|
|
"playwright",
|
|
"headless",
|
|
"cli",
|
|
"claude",
|
|
"ai-agent",
|
|
"devtools"
|
|
],
|
|
"devDependencies": {
|
|
"@anthropic-ai/claude-agent-sdk": "0.2.117",
|
|
"@huggingface/transformers": "^4.1.0",
|
|
"autoevals": "^0.3.0",
|
|
"braintrust": "^3.24.0"
|
|
}
|
|
}
|