mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-02 03:35:09 +02:00
Garry Tan
76803d789a
Adds comprehensive eval infrastructure: - Tier 1 (free): 13 new static tests — cross-skill path consistency, QA structure validation, greptile format, planted-bug fixture validation - Tier 2 (Agent SDK E2E): /qa quick, /review with pre-built git repo, 3 planted-bug outcome evals (static, SPA, checkout — each with 5 bugs) - Tier 3 (LLM judge): QA workflow quality, health rubric clarity, cross-skill consistency, baseline score pinning New fixtures: 3 HTML pages with 15 total planted bugs, ground truth JSON, review-eval-vuln.rb, eval-baselines.json. Shared llm-judge.ts helper (DRY). Unified EVALS=1 flag replaces SKILL_E2E + ANTHROPIC_API_KEY checks. `bun run test:evals` runs everything that costs money (~$4/run). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
44 lines
1.5 KiB
JSON
44 lines
1.5 KiB
JSON
{
|
|
"fixture": "qa-eval.html",
|
|
"bugs": [
|
|
{
|
|
"id": "broken-link",
|
|
"category": "functional",
|
|
"severity": "medium",
|
|
"description": "Navigation link 'Resources' points to /nonexistent-404-page which returns 404",
|
|
"detection_hint": "link|404|broken|dead|nonexistent|Resources"
|
|
},
|
|
{
|
|
"id": "disabled-submit",
|
|
"category": "functional",
|
|
"severity": "high",
|
|
"description": "Contact form submit button has 'disabled' attribute permanently — form can never be submitted",
|
|
"detection_hint": "disabled|submit|button|form|cannot submit|contact"
|
|
},
|
|
{
|
|
"id": "content-overflow",
|
|
"category": "visual",
|
|
"severity": "medium",
|
|
"description": "Statistics text is clipped by overflow:hidden container — content wider than 400px container",
|
|
"detection_hint": "overflow|clipped|truncated|hidden|text cut|statistics"
|
|
},
|
|
{
|
|
"id": "missing-alt",
|
|
"category": "accessibility",
|
|
"severity": "medium",
|
|
"description": "Logo image (<img src='/logo.png'>) has no alt attribute",
|
|
"detection_hint": "alt|accessibility|image|a11y|missing alt|logo"
|
|
},
|
|
{
|
|
"id": "console-error",
|
|
"category": "console",
|
|
"severity": "high",
|
|
"description": "TypeError on page load: Cannot read properties of undefined (reading 'map')",
|
|
"detection_hint": "console|error|TypeError|undefined|map"
|
|
}
|
|
],
|
|
"total_bugs": 5,
|
|
"minimum_detection": 3,
|
|
"max_false_positives": 2
|
|
}
|