53 lines
1.8 KiB
JSON
53 lines
1.8 KiB
JSON
{
|
||
"name": "zcbot-production-full-safe",
|
||
"version": "2026-08-03",
|
||
"default_repetitions": 1,
|
||
"pass_threshold": 0.8,
|
||
"dimension_weights": {
|
||
"task_quality": 40,
|
||
"reliability": 20,
|
||
"security": 15,
|
||
"engineering": 15,
|
||
"performance": 10
|
||
},
|
||
"cases": [
|
||
{
|
||
"id": "prod-full-qa-calcite",
|
||
"name": "生产低风险材料问答",
|
||
"dimension": "task_quality",
|
||
"prompt": "请用不超过120字说明方解石的主要化学成分，并明确写出化学式。",
|
||
"assertions": [
|
||
{"type": "run_succeeded", "weight": 2},
|
||
{"type": "response_nonempty", "weight": 1},
|
||
{"type": "response_regex", "value": "CaCO(?:3|₃)", "weight": 2},
|
||
{"type": "response_not_contains", "value": "CaSiO3", "weight": 1}
|
||
]
|
||
},
|
||
{
|
||
"id": "prod-full-reliability",
|
||
"name": "生产重复执行稳定性",
|
||
"dimension": "reliability",
|
||
"repetitions": 3,
|
||
"prompt": "只回答 ZCBOT_RELIABILITY_OK，不要添加其他内容。",
|
||
"assertions": [
|
||
{"type": "run_succeeded", "weight": 2},
|
||
{"type": "response_regex", "value": "^\\s*ZCBOT_RELIABILITY_OK\\s*$", "weight": 2},
|
||
{"type": "max_duration_s", "max_value": 120, "weight": 1},
|
||
{"type": "max_cost_cny", "max_value": 1, "weight": 1}
|
||
]
|
||
},
|
||
{
|
||
"id": "prod-full-performance",
|
||
"name": "生产短回答时延与成本",
|
||
"dimension": "performance",
|
||
"prompt": "只回答 OK，不要添加其他内容。",
|
||
"assertions": [
|
||
{"type": "run_succeeded", "weight": 2},
|
||
{"type": "response_regex", "value": "^\\s*OK\\s*$", "weight": 2},
|
||
{"type": "max_duration_s", "max_value": 120, "weight": 1},
|
||
{"type": "max_cost_cny", "max_value": 1, "weight": 1}
|
||
]
|
||
}
|
||
]
|
||
}
|