mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-01 22:45:02 +01:00
Garry Tanandcapy-ai[bot]
4eff47c5cf
* feat(eval-plan): results --check refuses a results table without its no-gstack rows Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(model-panel): a <model>#no-gstack arm per model, identity-keyed cells, one campaign, results.md (GST-468) Each panel model also runs as <model>#no-gstack: the same fixture, ticket, tools, limits, route and reservation, with no skill folder and no routing line. The arm identity keys the ledger attempt, test name, row and summary; candidate folders are named after the fixture project and the seed commit has a neutral author. summarize reads one campaign (run id and PREREG.md sha256) and refuses a duplicate cell; suggestionLine reads the skill arms only, so the preregistered particle-1 line is unchanged. renderResults writes results.md, which passes gstack-eval-plan results --check against the new test/fixtures/model-panel/PREREG.md (supersedes GSTA-173 for later runs). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(arm-benchmark): no-gstack arm on a pinned model, 3 paired trials, both-order paired judge, spend ledger (GST-469) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(evals): no-gstack arm for the safety-rule and router evals (GST-470) GSTACK_SAFETY_ARM and GSTACK_ROUTER_ARM take a third value, none: the same fixture, tools and user request with no skill excerpt, rule text, step file or installed skill. Under none every behavioral check is recorded as an observation (none-arm-observations.jsonl) and never fails the case or writes contract-violations.jsonl; harness preconditions still assert. The four safety prompt builders (ship-evidence, codex-boundary, codex-consult, design-risk) and the router fixtures move into helpers; the rule, removed, current and before prompts stay byte-identical, proven against reference copies of main's code. pair-agent and ios-demo refuse none with the reason (NO_NONE_ARM). GSTACK_ROUTER_ARM now throws on an unknown value instead of silently running current. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: changelog fragment for the no-gstack arms in existing evals Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(arm-benchmark): arm-pair paired-judge calibration run (bar met 6/6, $7.22) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(paid-shards): keep loop-named panel and arm-benchmark cases selectable by --case The lanes moved each cell's testName into helpers, so the static detector no longer saw a computed registration and B4 failed for all eight cases. Same runtime test names; the paid runs are unaffected. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(tests): keep FREE_FIXTURES and the placeholder allowlist current for the no-gstack arms scripts/judge-calibration.ts is now an arm-benchmark paid touchfile, so it can no longer be a free consumer of test/fixtures/judge-calibration/** (CI free-suite 8). The eval-plan Step 5 fence names <prereg-path> and <results-path>; allowlist both as PATH placeholders (CI free-suite 19). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(eval-plan): cover a complete table after a partial one, --json output and the results usage error Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(eval-plan): keep the Step 7 coverage test as reviewed Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: name the changelog fragment after the branch slug Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: arm-benchmark project folder names and the arm-pair calibration corpus Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: keep the judge-calibration fixture README as reviewed Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(skills): describe eval-plan results --check Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --------- Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
119 lines
5.8 KiB
JSON
119 lines
5.8 KiB
JSON
{
|
|
"name": "gstack",
|
|
"version": "1.92.2",
|
|
"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 --no-compile-autoload-dotenv --no-compile-autoload-bunfig && bun build --compile browse/src/cli.ts --outfile browse/dist/browse --no-compile-autoload-dotenv --no-compile-autoload-bunfig && 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",
|
|
"audit:manifest": "bun run scripts/prompt-audit-manifest.ts",
|
|
"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": "bun run scripts/retired-command.ts test:evals",
|
|
"test:evals:all": "bun run scripts/retired-command.ts test:evals:all",
|
|
"test:e2e": "bun run scripts/retired-command.ts test:e2e",
|
|
"test:e2e:all": "bun run scripts/retired-command.ts test:e2e:all",
|
|
"test:gate": "bun run scripts/retired-command.ts test:gate",
|
|
"test:periodic": "bun run scripts/retired-command.ts test:periodic",
|
|
"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": "bun run scripts/retired-command.ts test:codex",
|
|
"test:codex:all": "bun run scripts/retired-command.ts test:codex:all",
|
|
"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": "bun run scripts/retired-command.ts eval:bg",
|
|
"eval:bg:all": "bun run scripts/retired-command.ts eval:bg:all",
|
|
"eval:bg:gate": "bun run scripts/eval-bg.ts gate",
|
|
"eval:bg:periodic": "bun run scripts/eval-bg.ts periodic",
|
|
"test:health": "bun run scripts/test-health-report.ts",
|
|
"test:exercised-map": "bun run scripts/exercised-map.ts",
|
|
"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/retired-command.ts eval:flake-rank",
|
|
"eval:pass-rates": "bun run scripts/eval-flake-rank.ts",
|
|
"eval:watch": "bun run scripts/retired-command.ts eval:watch",
|
|
"eval:select": "bun run scripts/eval-select.ts",
|
|
"analytics": "bun run scripts/analytics.ts",
|
|
"test:audit": "bun run scripts/retired-command.ts test:audit",
|
|
"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} EVALS_SCREEN_POLICY=${EVALS_SCREEN_POLICY:-narrow} 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": "bun run scripts/eval-bg.ts pr",
|
|
"eval:bg:release": "bun run scripts/eval-bg.ts release"
|
|
},
|
|
"dependencies": {
|
|
"@anthropic-ai/sdk": "^0.78.0",
|
|
"@huggingface/transformers": "^4.3.1",
|
|
"@ngrok/ngrok": "^1.7.0",
|
|
"cross-spawn": "^7.0.6",
|
|
"diff": "^9.0.0",
|
|
"html-to-docx": "1.8.0",
|
|
"html-to-vdom": "0.7.0",
|
|
"marked": "^18.1.1",
|
|
"playwright": "^1.62.1",
|
|
"sharp": "^0.35.4",
|
|
"socks": "^2.8.10",
|
|
"xterm": "^5.3.0",
|
|
"xterm-addon-fit": "^0.8.0"
|
|
},
|
|
"engines": {
|
|
"bun": ">=1.4.2"
|
|
},
|
|
"keywords": [
|
|
"browser",
|
|
"automation",
|
|
"playwright",
|
|
"headless",
|
|
"cli",
|
|
"claude",
|
|
"ai-agent",
|
|
"devtools"
|
|
],
|
|
"devDependencies": {
|
|
"@anthropic-ai/claude-agent-sdk": "0.2.141",
|
|
"@types/bun": "1.4.3",
|
|
"prettier": "3.9.10",
|
|
"typescript": "7.0.2"
|
|
},
|
|
"overrides": {
|
|
"@modelcontextprotocol/sdk": "1.32.0",
|
|
"adm-zip": "^0.6.1",
|
|
"fast-uri": "3.1.9",
|
|
"hono": "4.13.13",
|
|
"image-size": "2.0.4",
|
|
"ip-address": "10.7.4",
|
|
"proxy-addr": "2.0.8",
|
|
"sharp": "0.35.5"
|
|
},
|
|
"patchedDependencies": {
|
|
"playwright-core@1.62.1": "patches/playwright-core@1.62.1.patch"
|
|
}
|
|
}
|