mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-02 11:45:20 +02:00
Garry Tan
17c1c06cd9
* feat: diff-based test selection for E2E and LLM-judge evals Each test declares file dependencies in a TOUCHFILES map. The test runner checks git diff against the base branch and only runs tests whose dependencies were modified. Global touchfiles (session-runner, eval-store, gen-skill-docs) trigger all tests. New scripts: test:e2e:all, test:evals:all, eval:select Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: bump version and changelog (v0.6.1.0) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: plan-design-review-audit eval — bump turns to 30, add efficiency hints The test was flaky at 20 turns because the agent reads a 300-line SKILL.md, navigates, extracts design data, and writes a report. Added hints to skip preamble/batch commands/write early while still testing the real SKILL.md. Now completes in ~13 turns consistently. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
50 lines
1.8 KiB
JSON
50 lines
1.8 KiB
JSON
{
|
|
"name": "gstack",
|
|
"version": "0.3.3",
|
|
"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"
|
|
},
|
|
"scripts": {
|
|
"build": "bun run gen:skill-docs && bun build --compile browse/src/cli.ts --outfile browse/dist/browse && bun build --compile browse/src/find-browse.ts --outfile browse/dist/find-browse && git rev-parse HEAD > browse/dist/.version && rm -f .*.bun-build",
|
|
"gen:skill-docs": "bun run scripts/gen-skill-docs.ts",
|
|
"dev": "bun run browse/src/cli.ts",
|
|
"server": "bun run browse/src/server.ts",
|
|
"test": "bun test browse/test/ test/ --ignore test/skill-e2e.test.ts --ignore test/skill-llm-eval.test.ts",
|
|
"test:evals": "EVALS=1 bun test test/skill-llm-eval.test.ts test/skill-e2e.test.ts",
|
|
"test:evals:all": "EVALS=1 EVALS_ALL=1 bun test test/skill-llm-eval.test.ts test/skill-e2e.test.ts",
|
|
"test:e2e": "EVALS=1 bun test test/skill-e2e.test.ts",
|
|
"test:e2e:all": "EVALS=1 EVALS_ALL=1 bun test test/skill-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: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"
|
|
},
|
|
"dependencies": {
|
|
"playwright": "^1.58.2",
|
|
"diff": "^7.0.0"
|
|
},
|
|
"engines": {
|
|
"bun": ">=1.0.0"
|
|
},
|
|
"keywords": [
|
|
"browser",
|
|
"automation",
|
|
"playwright",
|
|
"headless",
|
|
"cli",
|
|
"claude",
|
|
"ai-agent",
|
|
"devtools"
|
|
],
|
|
"devDependencies": {
|
|
"@anthropic-ai/sdk": "^0.78.0"
|
|
}
|
|
}
|