Initial commit: Natural Memory Agent Lab：模型服务 + TypeScript agent + 记忆能力场景评测（冲突更新、跨会话回忆、遗忘撤回、多跳、未知拒答）

2026-09-19 12:09:13 +08:00
commit eb9bd87a4d
108 changed files with 6452 additions and 0 deletions
@@ -0,0 +1,31 @@
+{
+  "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。",
+  "memory_write_turns": [0],
+  "sessions": [
+    {
+      "id": "s1",
+      "turns": [
+        "记一下：我的项目代号是 蓝鲸-47，部署区域是 ap-southeast-3。",
+        "谢谢。"
+      ]
+    },
+    {
+      "id": "s2",
+      "turns": [
+        "我的项目代号是什么？只回答代号本身。"
+      ]
+    },
+    {
+      "id": "s3",
+      "turns": [
+        "部署区域呢？只回答区域本身。"
+      ]
+    }
+  ],
+  "assertions": [
+    { "type": "answer_contains", "session": "s2", "turn": 0, "any": ["蓝鲸-47", "蓝鲸 47", "蓝鲸47"] },
+    { "type": "answer_contains", "session": "s3", "turn": 0, "any": ["ap-southeast-3", "apse-3"] },
+    { "type": "active_record_contains", "any": ["蓝鲸-47"] }
+  ]
+}