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 +1,39 @@
+{
+  "baseUrl": "http://127.0.0.1:8766/v1",
+  "outDir": "H:\\Memory\\agent_lab\\agent\\runs\\v2",
+  "arms": [
+    "on",
+    "off"
+  ],
+  "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": 3.77
+        },
+        "off": {
+          "activeRecords": 0,
+          "assertionsPassed": 0,
+          "assertionsTotal": 3,
+          "passRate": 0,
+          "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\"]",
+            "active_record_contains: absent from active memory"
+          ],
+          "meanSecondsPerTurn": 3.65
+        }
+      }
+    }
+  ]
+}