mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-02 11:45:20 +02:00
Garry Tan
c6c3294ee9
Three root causes fixed: - QA agent killed shared test server (kill port), breaking subsequent tests - Shared outcomeDir caused cross-contamination (b8 read b7's report) - max_false_positives=2 too strict for thorough QA agents finding derivative bugs Changes: - Restart test server in planted-bug beforeAll (resilient to agent kill) - Each planted-bug test gets isolated working directory (no cross-contamination) - max_false_positives 2→5 in all ground truth files - Accept error_max_turns for /qa quick (thorough QA is not failure) - "Write early, update later" prompt pattern ensures reports always exist - maxTurns 30→40, timeout 240s→300s for planted-bug evals Result: 10/10 E2E pass, 9/9 LLM judge pass. All three planted-bug evals score 5/5 detection with evidence quality 5. Total E2E cost: $1.69. 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": 2,
|
|
"max_false_positives": 5
|
|
}
|