Files

T

john 212ff3ff80 Add User Model Service and Temporal Recall for MeMind V0.1.

Introduce UMS ingest/snapshot pipeline, Context Planner with multi-source recall, runtime context injection, canonical user mapping, and session snapshot loading on auth/me.

Co-authored-by: Cursor <cursoragent@cursor.com>

2026-09-03 23:25:18 +08:00

4.2 KiB

Raw Blame History

Temporal Recall API v1

字段	值
状态	Frozen（V0.1）
建议 Base URL	MeMind Portal 同域 `/api/v1/temporal-recall/*`
输入	`ContextPlan` 或简化 query
输出	`TimelineItem[]` + 分组元数据

1. 职责

按 Context Plan 并行检索多源，归一化、Dedupe、Rank，返回 Personal Timeline Recall Bundle。

回答： 「某个时间范围内发生了什么？」

2. `POST /v1/temporal-recall/query`

方式 A — 传入完整 Plan（推荐）

{
  "plan": { "...ContextPlan..." },
  "limit": 50
}

方式 B — 快捷 query（内部先调 Planner）

{
  "query": "我这周有什么重要的事？",
  "user_id": "a70ff537-8908-486e-9b6c-042e07cc25db",
  "now": "2026-09-03T22:00:00+08:00",
  "limit": 50
}

响应

{
  "query_type": "personal_temporal_recall",
  "temporal_mode": "AMBIGUOUS",
  "time_range": {
    "start": "2026-09-01T00:00:00+08:00",
    "end": "2026-09-08T00:00:00+08:00"
  },
  "groups": [
    {
      "label": "occurred_in_range",
      "items": [
        {
          "timeline_item_id": "...",
          "source": "meinput",
          "type": "mention",
          "event_time": null,
          "observed_time": "2026-09-02T14:30:00+08:00",
          "title": "MeInput 验证上屏",
          "content": "MeInput验证上屏",
          "importance": 0.71,
          "confidence": 0.95,
          "recall_score": 0.78,
          "source_ref": "meinput:segment:...",
          "status": "mentioned"
        }
      ]
    },
    {
      "label": "mentioned_or_planned",
      "items": []
    }
  ],
  "items": [],
  "stats": {
    "sources_queried": ["meinput", "chat"],
    "raw_count": 42,
    "deduped_count": 38,
    "returned_count": 25,
    "elapsed_ms": 320
  },
  "plan": { "...echo ContextPlan..." }
}

groups 在 temporal_mode=AMBIGUOUS 时区分「实际发生」与「提到/安排」；否则 items 为 flat ranked list。

3. `GET /v1/temporal-recall/info`

{
  "schema_version": 1,
  "supported_sources": ["meinput", "chat"],
  "planned_sources": ["calendar", "memory_v2", "email", "browser", "tasks"],
  "temporal_modes": ["OCCURRED_IN", "MENTIONED_IN", "PLANNED_IN", "CREATED_IN", "DUE_IN", "AMBIGUOUS"],
  "default_limit": 50,
  "max_limit": 200
}

4. Source Adapter 契约

每个 adapter 实现：

interface TemporalSourceAdapter {
  source: 'meinput' | 'chat' | 'calendar' | 'memory_v2';
  search(ctx: {
    userId: string;
    retrieval: ContextPlan['retrievals'][0];
    time: ContextPlan['time'];
    temporalMode: ContextPlan['temporal_mode'];
  }): Promise<TimelineItem[]>;
}

MeInput Adapter（V0.1）

调用 GET /v1/evidence/export（MeInput Cloud）
过滤 expression_segment，按 occurred_at 映射 observed_time
规则抽取 event_time（「明天下午三点」→ 解析为绝对时间）
source_ref = meinput:segment:{evidence_id}

Chat Adapter（V0.1）

查 h5_agent_runs + session messages（用户可见范围）
observed_time = message.created_at
commitment/todo 规则抽取

5. Rank 公式

recall_score =
  source_quality(source)
× temporal_match(item, plan.time, plan.temporal_mode)
× semantic_match(item, expanded_queries)
× importance(item)
× confidence(item)

阈值	展示
≥ 0.75	主答案
0.50 ~ 0.75	次要
< 0.50	丢弃

6. Dedupe

时间：|event_time_a - event_time_b| < 15min 或同日 + 同类
语义：title/content keyword overlap > 0.7 或 embedding cosine > 0.85（v0.2）
Merge → 保留最高 source_quality，填充 merged_from

7. 认证

调用方	认证
Agent Runtime	用户 sessionToken
内部 Worker	`TEMPORAL_RECALL_TOKEN`（可选）

8. V0.1 不做

Calendar / Email / Browser adapter
持久化 timeline 索引表
LLM 答案生成（只返回 structured timeline；Answer 层在 Agent）

9. 错误码

HTTP	code	说明
400	`invalid_plan`	Plan schema 校验失败
401	`unauthenticated`	未登录
503	`source_unavailable`	MeInput export 不可用
504	`recall_timeout`	并行检索超时（默认 5s）

4.2 KiB Raw Blame History Unescape Escape