26 lines
785 B
JSON
26 lines
785 B
JSON
{
|
|
"baseUrl": "http://127.0.0.1:8766/v1",
|
|
"outDir": "H:\\Memory\\agent_lab\\agent\\runs\\smoke1",
|
|
"arms": [
|
|
"on"
|
|
],
|
|
"scenarios": [
|
|
{
|
|
"id": "cross_session_recall",
|
|
"description": "写入事实后，在全新会话（空上下文、无历史文本）中询问该事实。这正是 in-model memory 存在的理由。",
|
|
"arms": {
|
|
"on": {
|
|
"activeRecords": 1,
|
|
"assertionsPassed": 1,
|
|
"assertionsTotal": 3,
|
|
"passRate": 0.3333333333333333,
|
|
"failures": [
|
|
"answer_contains: missing one of [\"蓝鲸-47\",\"蓝鲸 47\",\"蓝鲸47\"]",
|
|
"answer_contains: missing one of [\"ap-southeast-3\",\"apse-3\"]"
|
|
],
|
|
"meanSecondsPerTurn": 8.78
|
|
}
|
|
}
|
|
}
|
|
]
|
|
} |