perf(management): message补无渠道前缀索引——修驾驶舱channel=all超时34s→1.3s

该回未回决赛圈点查(owner+talker定位末条消息)在channel=None时无渠道
前缀条件,现有索引全以channel打头用不上,服务器100万行实测dashboard
34~37s撞前端15s超时(ECONNABORTED);补(owner,talker,timestamp)索引
后实测1.3~1.8s。服务器已先行手工建索引止血,本迁移幂等兜底对齐。
模型+迁移双声明防autogenerate反DROP

docs/DEPLOY.md

@@ -228,6 +228,32 @@ alembic 链自当前线上版本起新增 3 支迁移:`a7d3e9f1c2b4` msg_daily_s
   幂等自动补种,无需手插;后续加新词默认只扫增量,要扫历史消息需重跑
   `--full`。
 
+### 管理后台批次A附加步骤(一次性,2026-09-09)
+
+迁移链新增 `b7c8d9e0f1a2`(经营管理域六表:first_reply_fact /
+employee_metric_daily / employee_call_daily / employee_score_config /
+employee_score_snapshot / management_followup)。**服务器 backend 容器
+不会自动跑 alembic**,须手动:
+
+```bash
+sudo docker compose -f docker-compose.server.yml exec backend alembic upgrade head
+```
+
+部署带该迁移后在**夜间低峰**跑两条一次性回填(幂等;本地实测耗时:
+fact 72s / 宽表+通话 71s,均分钟级):
+
+```bash
+sudo docker compose -f docker-compose.server.yml exec backend python -m app.sync.cli first-reply-facts
+sudo docker compose -f docker-compose.server.yml exec backend python -m app.sync.cli employee-metrics
+```
+
+- `first-reply-facts`:跨日精确首响事实表(本地实测 11,020 会话 → 6.8 万行)。
+- `employee-metrics`:员工指标宽表 + 通话日小表(本地实测 12,371 宽表行 +
+  1,163 通话行);**必须在 first-reply-facts 之后跑**——fact 表是后续评分/
+  下钻的数据源,须先填充(宽表自身从 message 表经同一算法重算串类列,
+  不读 fact 表,先跑宽表不会出 0,但 fact 缺失会阻塞后续能力)。
+- 两命令均为按日 delete+insert 幂等重建,复跑结果一致,中断重跑无副作用。
+
 ## 8. 本地收尾(部署验证通过后)
 
 ```bash

docs/superpowers/plans/2026-09-08-management-batch-a-verification.md

@@ -0,0 +1,411 @@
+# 批次A Task 0 核实记录：五项核实 + 回测名单
+
+- **日期**：2026-09-09
+- **方式**：`docker exec -i yunke-mysql-1 mysql -uyunke -pyunke yunke -e "<SQL>"`（容器名以 `docker ps` 实测为准，确认为 `yunke-mysql-1`）
+- **用途**：本记录的全部结论直接约束批次A（数据底座）后续任务的实现细节；偏差处显式标注「影响 Task N」。任务编号引用 [2026-09-08-management-console-batch-a-data-foundation.md](./2026-09-08-management-console-batch-a-data-foundation.md)。
+- **数据快照范围**：`stat_daily_staff` / `msg_daily_stats` 覆盖 20251024 ~ 20260907；`phone_call.start_call_time` 覆盖 2025-10-18 ~ 2026-09-05。
+
+---
+
+## ① 员工主数据（staff 表）
+
+| 指标 | 实测 |
+|---|---|
+| staff 总数 | **41**（与计划假设 ≈41 一致） |
+| `is_on_job=1` | 41（全部在职） |
+| `wechat_account` DISTINCT user_id | 41 |
+| `whatsapp_account` DISTINCT user_id | 20 |
+| 微信幽灵账号（user_id 不在 staff） | **0** |
+| WA 幽灵账号（补充核实） | **0** |
+| `stat_daily_staff` DISTINCT user_id | 40（其 user_id 全部在 staff 内；员工 `FD685A5620184156BE75A8D73FB72F64` 无任何消息统计行） |
+
+**结论**：账号表 → staff 无幽灵映射，`known_user_ids` 过滤（v2 §1.3 #11）零损耗，不会意外丢行。两个渠道的 account_map 产出 user_id 均能落到 staff。**无偏差，Task 5/6 按计划实现即可。**
+
+---
+
+## ② phone_call 列与单位
+
+表结构关键列：`call_id`(PK)、`channel`、`start_call_time`(bigint)、`call_duration`(int)、`call_status`(int)、`incoming_call`(int)、`user_id`、`call_number`、`fetched_at`、`updated_at`。
+
+### channel 分布
+
+| channel | 行数 |
+|---|---|
+| `voice_call` | 2,504 |
+| `wa_voice_call` | 686 |
+| 合计 | **3,190**（与已知 3,190 条一致） |
+
+### call_duration 单位：**秒**（确认）
+
+| 指标 | 实测 |
+|---|---|
+| 总和 | 263,651 秒 = **73.24 小时**（对照已知约 73 小时，吻合） |
+| 均值 | 82.65 秒（对照预期均值 ≈82 秒，吻合） |
+
+### call_status × duration 交叉
+
+| call_status | 行数 | duration=0 | duration>0 | 语义判定 |
+|---|---|---|---|---|
+| 1 | 1,508 | 31 | 1,477 | **接通**（含 31 条 0 秒即挂） |
+| 2 | 1,682 | 1,682 | 0 | **未接通**（未接/拒接/取消，与方向无关） |
+
+### incoming_call 分布
+
+| incoming_call | 行数 | 语义 |
+|---|---|---|
+| 1 | 1,764 | 呼入 |
+| 0 | 1,426 | 呼出 |
+
+### start_call_time：**毫秒 epoch**（确认）
+
+13 位整数；`FROM_UNIXTIME(x/1000)` 解出 max = 2026-09-05 16:00:55（合理近期），按秒解释则超范围。min = 2025-10-18。与 `message.timestamp` 毫秒同口径。
+
+### call_number 形态（按 channel 完全可分）
+
+- `voice_call` → 微信 ID：`wxid_*` 或自定义微信号（`csf7169708`、`yuanye751380`、`Maple_1988` 等）
+- `wa_voice_call` → WA JID：`2348182388888@s.whatsapp.net` 等
+
+### 与计划默认假设的偏差（重要）
+
+1. **计划假设 #4「PhoneCall.channel 是通话类型（phone_call/voice_call）非消息渠道」不完全成立**：实测无 `phone_call`（蜂窝）值，且 `wa_voice_call` **能**从 channel 列判别 WA。计划 Task 5 注释「voice_call 行无法从列判别微信/WA」不成立。**影响 Task 5**：`_followup_exists` 可按渠道收窄——`voice_call` 只查该员工 wechat 账号的 1:1 消息、`wa_voice_call` 只查 whatsapp 账号（当前双渠道任一匹配的写法也不会错——wxid 不会撞 WA JID，仅多一次无效查询；收窄属优化非必需）。
+2. `call_duration` 单位=秒、`start_call_time`=毫秒 epoch：**与计划默认一致，Task 5 无需换算**（`day_bounds_ms` 直接用）。
+3. 接通判定：计划默认 `duration>0`。实测 `call_status=1 AND duration>0` = 1,477 行，`duration>0` 口径与之差 31 行（31 条接通但 0 秒，占 1.0%）。**影响 Task 5**：`answered=dur>0` 口径可用；若追求语义精确可改 `call_status=1`（含 0 秒接通），差异 ≤1%，实现时任选其一并在表注释写明。
+
+---
+
+## ③ customer 归属字段填充率
+
+| 指标 | 实测 |
+|---|---|
+| 总行数 | 16,339 |
+| `user_id` 填充 | 16,339（**100%**） |
+| `owner_account_id` 填充 | 16,339（**100%**） |
+| `delete_flag=1` | 53 |
+
+分渠道：wechat 7,040（owner 填充 7,040）/ whatsapp 9,299（owner 填充 9,299）。
+
+### 两条归属路径一致性（全表校验，非抽样）
+
+`customer.user_id` vs `owner_account_id → wechat_account.wx_id / whatsapp_account.uid → user_id`：
+
+| 渠道 | 校验行数 | 一致 |
+|---|---|---|
+| whatsapp | 9,299 | 9,299 |
+| wechat | 7,040 | 7,040 |
+
+**结论**：两条路径 100% 等价、零冲突。生命周期归属覆盖面完整。**影响 Task 6**：默认 `owner_account_id → account_map → user_id` 路径确认可用；`customer.user_id` 列可直接当冗余等价路径使用（如需省一次 join，实测安全）。
+
+补充观察（**影响 Task 3/6 的 peer 对齐**）：**微信侧主体是无后缀裸 ID，后缀形态是少数**。`customer.friend_id` 实测形态分布（全表）：
+
+| 渠道 | 形态 | 行数 | 占比 |
+|---|---|---|---|
+| wechat | **无后缀裸 ID**（`a_515855826`、`a053136a` 等） | 6,779 | **96.3%** |
+| wechat | `@openim` 后缀 | 261 | 3.7% |
+| whatsapp | `@s.whatsapp.net` | 9,266 | 99.6% |
+| whatsapp | `@lid` 后缀 | 33 | 0.4% |
+
+`message.talker_id` 侧同查（行数口径）：wechat 裸 ID 844,287 / `@openim` 16,873 / `@chatroom` 17,003（群）；whatsapp `@s.whatsapp.net` 72,357 / `@lid` 4,284 / `@g.us` 9,439（群）。即：微信 peer 主键以裸 ID 为准、`@openim` 为少数共存；WA 侧基本全带后缀。Task 3 实现 peer 匹配时按实测形态对齐（两边原值相等才命中），不做猜测性截断/补后缀。
+
+---
+
+## ④ 群占比（msg_daily_stats，量化混合口径偏差）
+
+| channel | peer_kind | 行数 | 消息量(send+recv) | 会话线程(cust_threads) |
+|---|---|---|---|---|
+| wechat | friend | 38,343 | 269,074 | 82,879 |
+| wechat | room | 16,234 | 609,089 | 26,220 |
+| whatsapp | friend | 11,673 | 77,994 | 14,178 |
+| whatsapp | room | 866 | 8,086 | 1,402 |
+| **合计** | | **67,116** | **964,243** | **124,679** |
+
+占比汇总：
+
+| 维度 | room 占比 | 说明 |
+|---|---|---|
+| 微信消息量 | **69.4%**（609,089/878,163） | 微信消息近七成来自群 |
+| WA 消息量 | 9.4%（8,086/86,080） | WA 几乎纯 1:1 |
+| 总消息量 | **64.0%**（617,175/964,243） | |
+| 总会话线程 | **22.2%**（27,622/124,679） | |
+
+**结论**：若现有看板首响/回复率不分 `peer_kind`，消息量维度被群污染 64%、线程维度 22%——污染主要来自微信侧（微信消息 69% 是群消息）。批次A `first_reply_fact` / `employee_metric_daily` 强制 `peer_kind='friend'` 过滤是必要的，不能沿用混合口径。
+
+---
+
+## ⑤ call_followup join 键（call_number ↔ message.talker_id，1:1 消息）
+
+| channel | 分母（call_number 非空） | 命中（talker_id 匹配且非群消息） | 命中率 |
+|---|---|---|---|
+| `voice_call` | 2,504 | 2,378 | **95.0%** |
+| `wa_voice_call`（补充核实） | 686 | 681 | **99.3%** |
+
+**结论**：双渠道命中率均远超 50% 阈值，`call_followup_count` 一期**高置信**，无需降级标记、无需在口径中注记低置信。**影响 Task 5**：24h 跟进判定按计划实现。未命中成因已精确解释（复核补充）：`voice_call` 的 126 条未命中**恰好等于** `call_number` 带 `@chatroom` 后缀的 126 条群通话（实测这 126 条对 1:1 消息全部 0 命中——join 限定 `room_id` 为空，群通话本就不该匹配）；剔除群通话后 1:1 可匹配通话命中率为 **2,378/2,378 = 100%**。`wa_voice_call` 侧后缀分布为 `@s.whatsapp.net` 676 / `@g.us`（群）9 / `@lid` 1，未命中 5 条**全部为** `@g.us` 群通话（逐条列出验证）。
+
+---
+
+## 回测员工名单
+
+选取依据：消息量/WA 量/活跃群排名 + 低样本端（见文末各候选分渠道数据）。覆盖：微信为主、WA 为主、群运营为主、高负载、低样本（前三类与高负载有合并）。
+
+| # | user_id | 名字 | 覆盖类型 | 关键数据（20251024~20260907） |
+|---|---|---|---|---|
+| 1 | `369D257EEC9A4357935FDE19DDD99CAA` | 王云青 | **高负载 + 群运营为主 + 微信为主**（合并） | 消息量 #1（162,740：微信 162,371 / WA 369）；活跃群 #1（4,036）；通话 431+9 |
+| 2 | `9C0B195A2C234C829FF507E011B4B460` | 田瑞志 | **WA 为主** | WA 消息 9,986 / 总 11,597 = 86%；WA 通话 28 |
+| 3 | `F99F6557C2904A7E8F4C5A3BD8A597A1` | 张士蓓 | **双通道混合**（WA 量 #1，群 #2） | 微信 91,936 + WA 12,529；活跃群 2,273；通话最多（471 微信 + 97 WA） |
+| 4 | `DC48798A5EA24DBB8B31A89CB858E08B` | 15639270965 | **纯微信无 WA 行**（验证 WA 缺失路径） | 微信 78,680，`stat_daily_staff` 无 whatsapp 行；通话 3 |
+| 5 | `946C08639BF84DFEBBF5EC2A607AE1FA` | 18539430257 | **低样本**（验证空数据路径） | 消息 8 条，无群、无通话、无 WA |
+
+> 名单中的 #1/#3 建议作为 Task 8「本地全量回填实测」的 2 名回测员工（数据最厚、双通道+通话+群全齐）。
+
+---
+
+## 偏差汇总（对后续任务的约束清单）
+
+| # | 偏差/确认 | 影响 |
+|---|---|---|
+| 1 | `phone_call.channel` 实测仅 `voice_call`（微信）/`wa_voice_call`（WA）两值，**无蜂窝 `phone_call` 值**；channel 可判别渠道，计划「无法从列判别微信/WA」结论修正 | Task 5（followup 可按渠道收窄，属优化非必需） |
+| 2 | `call_duration` 单位=**秒**（263,651s=73.24h≈已知 73h）；`start_call_time`=**毫秒 epoch** | Task 5（默认口径正确，无需换算） |
+| 3 | 接通判定 `dur>0` vs `call_status=1` 差 31 行（1.0%），前者少计 31 条 0 秒接通 | Task 5（任选其一，注释写明） |
+| 4 | `customer.owner_account_id` 填充 **100%**，与 `user_id` 列全表 100% 等价 | Task 6（默认 owner 路径确认；可直接用 user_id 列省 join） |
+| 5 | 微信侧 peer ID **主体为无后缀裸 ID**（customer.friend_id 6,779/7,040=96.3%；message.talker_id 行数口径 844,287 裸 vs 16,873 `@openim`），后缀形态（`@openim` 等）为少数；WA 侧基本全带后缀（`@s.whatsapp.net`/`@lid`） | Task 3/6（peer 对齐按实测形态原值匹配，勿截断/勿补后缀） |
+| 6 | 群消息占总消息量 64%（微信侧 69%） | Task 3/6（friend 过滤必须，佐证 spec 口径） |
+| 7 | call_number↔talker_id 命中率 voice_call 95.0% / wa_voice_call 99.3% | Task 5（call_followup_count 高置信，不降级） |
+| 8 | staff 41 行无幽灵账号；`stat_daily_staff` 仅 40 名员工有行 | Task 5/6（known_user_ids 过滤零损耗） |
+
+---
+
+# 批次A回填实测与对账（Task 8，2026-09-09）
+
+- **环境**：本地 Docker MySQL（`yunke-mysql-1`），数据快照同上（stat/msg 覆盖 20251024~20260907）。
+- **方式**：Task 7 真机全量回填后本任务只读对账抽查（未重跑回填）；对账前全库同源校验复验一次，确认库状态即 Task 7 收尾状态。
+
+## 1. 回填实测汇总（Task 7 真机数字，Task 8 复验）
+
+| 项目 | 实测 |
+|---|---|
+| `first-reply-facts` | 11,020 会话 → **68,476** fact 行，**72s**（冷） |
+| `employee-metrics` | **12,371** 宽表行（day×channel×user）+ **1,163** 通话行（**314** 天并集），**71s** 冷 / 36s 热 |
+| 幂等复跑 | 两命令复跑结果一致（delete+insert 语义，无重复无漂移） |
+| 全库同源 | `SUM(employee_metric_daily.threads_answered)` = **68,476** ≡ fact 行数（Task 8 复验通过） |
+| 孤儿检查 | 宽表/通话表 user_id 不在 staff = **0**；fact 账号不在对应渠道账号表 = **0**（Task 8 复验通过） |
+| 通话日并集修复 | `employee_call_daily` 覆盖 **314** 天（修复前 306）：8 个消息空窗日找回 27 通话 / 13 接通 |
+
+## 2. 对账抽查（2 员工 × 3 日期 × 三组）
+
+员工取自本文回测名单：**王云青** `369D257EEC9A4357935FDE19DDD99CAA`（#1，高负载+群运营，混合口径差异最大场景；1 微信 + 2 WA 账号）、**田瑞志** `9C0B195A2C234C829FF507E011B4B460`（#2，WA 为主；1 微信 + 2 WA 账号）。日期 20260815 / 20260801 / 20260601（近/中/远）。跨渠道员工按 channel 分别对账（①②组逐渠道逐日须一致）。
+
+判定标准：**①组（消息计数列 ↔ msg_daily_stats friend 聚合）与 ②组（串类列 ↔ fact 行数）必须逐日一致；③组（宽表串类 cust_threads ↔ 日切 stat_daily_staff.cust_threads）允许差异，差值=跨夜串归属效应。**
+
+### 王云青
+
+| 渠道 | 日期 | ① mds sent/recv | ① 宽表 sent/recv | ① 判定 | ② fact 行 | ② 宽表 answered | ② 判定 | ③ 宽表 threads | ③ 日切 threads | ③ 差值 |
+|---|---|---|---|---|---|---|---|---|---|---|
+| wechat | 20260601 | 186 / 177 | 186 / 177 | ✅ | 76 | 76 | ✅ | 76 | 121 | 45 |
+| wechat | 20260801 | 0 / 38 | 0 / 38 | ✅ | 0 | 0 | ✅ | 0 | 16 | 16 |
+| wechat | 20260815 | 0 / 23 | 0 / 23 | ✅ | 0 | 0 | ✅ | 0 | 17 | 17 |
+| whatsapp | 20260601 | （无行） | 0 / 0 | ✅ | （无行） | 0 | ✅ | 0 | （无行） | — |
+| whatsapp | 20260801 | 0 / 1 | 0 / 1 | ✅ | 1 | 1 | ✅ | 1 | 1 | 0 |
+| whatsapp | 20260815 | 0 / 4 | 0 / 4 | ✅ | 1 | 1 | ✅ | 1 | 2 | 1 |
+
+### 田瑞志
+
+| 渠道 | 日期 | ① mds sent/recv | ① 宽表 sent/recv | ① 判定 | ② fact 行 | ② 宽表 answered | ② 判定 | ③ 宽表 threads | ③ 日切 threads | ③ 差值 |
+|---|---|---|---|---|---|---|---|---|---|---|
+| wechat | 三日期均 | （无行） | 0 / 0 | ✅ | （无行） | 0 | ✅ | 0 | （无行） | — |
+| whatsapp | 20260601 | 1 / 1 | 1 / 1 | ✅ | 1 | 1 | ✅ | 1 | 1 | 0 |
+| whatsapp | 20260801 | （无行） | 0 / 0 | ✅ | （无行） | 0 | ✅ | 0 | 2 | 2 |
+| whatsapp | 20260815 | （无行） | 0 / 0 | ✅ | （无行） | 0 | ✅ | 0 | （无行） | — |
+
+注：「无行」= 源表该 (渠道, 日) 无该员工数据，宽表记 0/0——一致。20260601 无 WA 数据未换日期：田瑞志 whatsapp 该日恰好有 1 条收发（对账有效），王云青 whatsapp 全期仅 369 条消息、无行属真实分布。
+
+**结论：①②组 12/12 逐日全部一致（含渠道拆分）；③组宽表全部 ≤ 日切值。**
+
+## 3. 跨夜串差值观察（③组差异解释）
+
+- **归属语义**：宽表串按「串末条客户消息所在上海自然日」归属（`first_reply_facts.compute_conversation`）；日切表按「当日有客户消息的 peer 数」计。串末条必在归属日当天 ⇒ 结构上保证 ③组逐日 宽表 ≤ 日切，差值=归属到其他日终了的跨夜/多日串。
+- **差值形态**：王云青 wechat 三日差 45/16/17——该员工深夜消息多（20260801/15 发送 0、仅收 38/23 条，客户消息跨零点后串归属顺延）；whatsapp 差 0/1。田瑞志 whatsapp 20260801 差 2（2 个 peer 当日来消息但串末条在次日）。
+- **串未丢失验证**：王云青 wechat 全期 宽表 12,055 threads（11,930 answered，314 天）vs 日切 20,981（14,647 answered，312 天）——串模型把多日串折叠为 1（比值 57.4%），且抽查 20260814~31 逐日，日切 17 线程的 20260815 对应串终落在真实结束日（0819=8、0821=10、0828=9），无凭空丢失。
+- 另：宽表 `cust_threads ≥ threads_answered`（如王云青 wechat 20260602 = 54/52）——未闭合尾串计入分母不产 fact 样本，与算法注释一致。
+
+## 4. 批次A验收清单（Task 8 收尾核对）
+
+| # | 项 | 状态 | 依据 |
+|---|---|---|---|
+| 1 | 6 张表本地存在，migration 幂等 + downgrade 干净 | ✅ | Task 2（迁移 `b7c8d9e0f1a2`，alembic head 实测一致；表实测在库：first_reply_fact / employee_metric_daily / employee_call_daily / employee_score_config / employee_score_snapshot / management_followup） |
+| 2 | first-reply-facts 全量回填成功且复跑幂等 | ✅ | Task 7（本文 §1） |
+| 3 | employee-metrics 全量回填成功且复跑幂等 | ✅ | Task 7（本文 §1） |
+| 4 | 跨夜串判别测试通过 | ✅ | Task 3（test_first_reply_facts.py 恰 12 例，Task 8 复跑全绿；含跨夜/多日串/同毫秒并列） |
+| 5 | friend-only 口径判别测试通过 | ✅ | Task 6（test_all_friend_pairs_only_friend + 宽表 friend 过滤判别例） |
+| 6 | 同源判别测试通过 + 全库 SUM 验证 | ✅ | Task 3/6；全库 68,476 ≡ 68,476（本文 §1 复验） |
+| 7 | 幽灵员工过滤测试通过 | ✅ | Task 5/6；孤儿=0（本文 §1 复验） |
+| 8 | 对账抽查 ①②一致、③差异可解释 | ✅ | 本文 §2/§3 |
+| 9 | 全量测试套件绿 | ✅ | **653 passed in 62s**（Task 8 本机实跑，2026-09-09） |
+| 10 | 核实文档完整 | ✅ | 本文补齐 |
+| 11 | 写钩子零改动 | ✅ | 批次A全部 17 个 commits（27f91e5→0fce21a）逐一核查，无一触碰 storage/summary.py、storage/repos.py（repos.py 最近一次改动 d428953 属 customer_account_link 工作线，先于批次A） |
+
+---
+
+# 批次B冒烟（Task B5，2026-09-09）
+
+经营管理后台六端点真机冒烟 + 性能初测。回测员工王云青 `369D257EEC9A4357935FDE19DDD99CAA`（#1 高负载+群运营），窗口 30 天 `20260810~20260908`。
+
+## 0. 环境与启动方式
+
+- **基线**：`pytest tests/ -q` → **721 passed in 60.9s**（批次B收尾后全绿）。
+- **后端启动**：docker 无 `yunke-backend/frontend-1` 容器；冒烟前 8000 端口空闲（连接拒绝，无常驻进程）。本任务自起：`yunke-server/.venv/Scripts/python.exe -m uvicorn app.api.main:app --port 8000`（无 `--reload`），`GET /api/health` → `{"status":"ok"}`；`openapi.json` 含 management 路由（grep 命中）确认新代码已加载。
+- **鉴权模式**：`.env` 中 `API_TOKEN=`（空值）→ 鉴权中间件 no-op，**免鉴权直接 curl**（无 Authorization 头）。
+- **进程处置**：uvicorn 留跑供用户查看，Git Bash PID **2423**（`kill 2423` 关闭；或任务管理器结束对应 python.exe）。
+
+## 1. 六端点结果（HTTP 码 × 耗时 × 大小）
+
+首次访问含冷启动（连接池/查询编译/InnoDB 冷缓存），dashboard 另测暖态三次：
+
+| 端点 | HTTP | 首次耗时 | 暖态耗时 | 大小 | 判定 |
+|---|---|---|---|---|---|
+| `/api/management/dashboard` | 200 | 12.03s | **2.92 / 2.39 / 2.18s** | 22,309B | ⚠️ 超 1.5s 目标（慢段定位见 §2） |
+| `/api/management/employees?page_size=50` | 200 | 0.34s | 0.30 / 0.31s | 58,865B | ✅ ≤1.5s |
+| `/api/management/employees/{王云青}` | 200 | 0.40s | — | 4,739B | ✅ |
+| `…/metrics?section=service` | 200 | 0.40s | — | 4,655B | ✅ |
+| `…/drilldown?metric_code=first_reply_p90` | 200 | 0.016s | — | 5,268B | ✅ |
+| `/api/management/metric-definitions` | 200 | 0.005s | — | 4,081B | ✅ |
+
+## 2. dashboard 慢段定位（分段实测，不做优化——决策归批次F）
+
+用 app 同一 session 复放 dashboard 组装流水线逐段计时（合计 2.685s ≈ 暖态端点耗时）：
+
+| 段 | 耗时 |
+|---|---|
+| load_score_config | 0.044s |
+| assemble_employees（评分+异常，2 窗聚合） | 0.262s |
+| wide_daily_rows / call_daily_rows | 0.007s / 0.002s |
+| service_daily_trend | 0.032s |
+| data_as_of | 0.009s |
+| **action_counts（unreplied+churn+sensitive）** | **2.328s** |
+
+action_counts 内部：`unreplied(hours=2)` **2.38s**；`churn(real,30d)` 0.12s；sensitive count 0.005s。unreplied 再拆：候选窗口函数查询（row_number over 67,116 行 friend 分区 → 3,123 候选）仅 **0.10~0.16s**；>500 候选走「仅本页决赛圈」分支无 N+1，但**单条尾部消息点查耗时 1.7~1.9s**。EXPLAIN 实证：`channel=None`（全平台）时无法使用 channel 打头的全部索引（`ix_message_channel_owner_talker_time(channel,owner,talker,timestamp)` 等），优化器退化到 `ix_message_room`（`room_id IS NULL/''`）→ **扫 378,202 行 + filesort**（message 表 96.4 万行）。
+
+优化方向（供批次F选择）：① 查询改写按渠道 UNION/`channel IN (…)` 绑定前缀走现有索引；② 补 `(owner_account_id, talker_id, timestamp)` 无 channel 前缀索引；③ dashboard 对 action_counts 做短 TTL 缓存。除 unreplied 外全链路 <0.5s，达标无压力。
+
+## 3. 合理性抽查
+
+- **employees 列表**：`total=41`/rows=41（=本文① staff 总数 ✓）。**王云青行与宽表 SQL 聚合逐字段全等**：msg_sent=111 / msg_recv=1003 / cust_threads=89 / threads_answered=57 / fr_sum_ms=698,140,844、days_with_data=29。数量级说明：「千级」预期对应全期全口径（全期 162,740 条消息/12,055 串，群聊为主）；本窗 friend 口径 recv=1003 千级 ✓，sent=111 为真实分布——同窗全口径 recv≈2.0 万（stat_daily_staff 实测） vs friend 1,003，差额几乎全是群消息；cust_threads=89 是串模型多日串折叠（本文 §3 已验证折叠比 57.4%）+本窗 friend 活动偏低。
+- **dashboard kpis**：active_employees=**40**（~40 ✓，=本文① stat 有数员工数）、active_customers=2,195、msg_total=42,422、cust_threads=9,330、answered=8,460、call 263/接通 113；lifecycle new/cooling/dormant/reactivated=231/1,432/3,353/145。**anomalies=28（critical 3 / warning 25）**，首条 `reply_p90_worsened` critical：P90 324.98min vs 基线期 18.06min（+1700%，样本 62、涉及 51 客户）。dimension_summary：risk/action 全 41 pending（批次C接线，符合预期），service scored 27/insufficient 4/pending 10、均分 56.0。趋势 30 点，末日 20260908 全零——数据止于 20260907（本文快照范围），边界正确。
+- **detail（王云青）**：`score.trial=true` ✓、grade=**E**（total=39，scored 非 insufficient）、dimensions：risk/action **pending** ✓（批次C）、service 47.8 / customer 0.0 / workload 100；含 accounts/prev/baseline/anomalies。
+- **metrics section=service**：数值与宽表窗聚合一致 + trend 30 点 ✓。
+- **drilldown first_reply_p90**：total=**57**=该员工账号窗内 fact 行数（=threads_answered ✓）。首行 fr_ms=**498,242,238ms≈5.8 天**——超「分钟~小时」预期，但与源表全等（fact MAX 同值）；窗内全库更极端值达 1,617,406,247ms≈18.7 天（thread_end 08-14 → reply 09-02，沉睡客户复活串），属真实数据形态非计算缺陷。该员工 p50=97,153ms（1.6min）/p90=1,651,758ms（27.5min）分钟级 ✓。极值是否 winsorize/封顶归批次F口径决策。
+- **metric-definitions**：19 项定义（msg_sent…call_followup_rate）+ score_config + caliber_notes，`config_source="db"`（评分配置 v1.0 种子生效 ✓）。
+
+**结论：六端点全 200、数据与库逐字段可对；唯一性能缺口=dashboard 的 unreplied 行动计数（channel 无前缀索引可用），暖态 2.2~2.9s，其余端点全部达标。**
+
+## 4. 批次B遗留观察项归档（终评补录，2026-09-09）
+
+| # | 项 | 归档 |
+|---|---|---|
+| 1 | call_band 样本基数：band 类指标样本量取 active_friends（规格字面），WA 通话量上来后"通话多客户少"员工会被误标 insufficient——当前数据零影响（实测 calls≥1 且 af<10 仅 5 人且 calls≤5，怎么选都不足）；归批次F回测前一行修正（sample_basis 字段或按源指标取样本） |
+| 2 | 配置源名唯一性：两个 code 指向同一源指标会使 employees comparisons 键静默覆盖——已在 validate_config 加源名唯一校验+测试（批次B终评闭环），默认配置六个源名互异不受影响 |
+| 3 | dashboard 性能（2.2~2.9s，unreplied channel=None 无前缀索引）与 fr_ms 天级极值 winsorize：见上文 §2/§3，决策归批次F |
+
+---
+
+# 批次D走查与验收（Task D4，2026-09-10）
+
+批次D收尾：员工总览（b72e957）+ 员工详情（5776175）+ 驾驶舱环比/异常跳员工闭环（422a726，前置接口/时间预设 ddeda3f）。Playwright 真机七步全链路走查 + v1 §19.1 员工子集与批次D验收清单逐项核对。环境：后端 uvicorn 8000（免鉴权）+ 前端 vite dev 5173，视口 **1366px**。
+
+## 0. 四门禁（全绿）
+
+| 门禁 | 结果 |
+|---|---|
+| 后端 `pytest tests/ -q` | **723 passed** in 65.29s |
+| 前端 `npm run build` | ✓ built in 1.03s（exit 0） |
+| 前端 `npm run test`（vitest） | Test Files 2 passed / **Tests 23 passed** |
+
+## 1. 七步动线走查记录（数字为真机实测，关键值已对 API 复核）
+
+**① 驾驶舱默认近30天（20260812~20260910）**：三 KPI 卡环比箭头 ✓（客户端自 prev_kpis 按 (cur-prev)/prev 计算，API 复核数值吻合）——全渠道：活跃客户 **1,992人 ↓12.6%**（prev 2,278）/ 活跃员工 **40人 →0.0%**（40/40）/ 消息量 **37,742条 ↓21.0%**（prev 47,749）；切微信：**979人 ↓25.3% / 40人 ↑2.6% / 27,949条 ↓29.6%**。方向与量级合理（等长紧邻前窗）。
+
+**② 异常卡员工名 → 员工详情**：点微信异常榜员工名链接（落点须为 a.el-link；整行点击触发行下钻抽屉，属预期交互）→ 落地 `/management/employees/18B5EE6B1AD94B15A5CD1CDABCECAB96?channel=wechat&start=…&end=…`（驾驶舱当前筛选 query 随行 ✓）。
+
+**③ 员工详情（朱晨曦，综合 21/E）**：五维条 **3 实 + 2 待数据**——合规风险/行动执行 pending 灰条占位，服务质量 0 分/客户经营 0 分/有效负载 100 分（API dimensions 逐项一致；行序随接口返回序，见遗留①）。四对比表（当前/上期/基线/中位）✓（cust_threads 62/114/107+中位）。服务质量页签双折线渲染（canvas 1074×300）→「查看超时明细」→ 首响P90 抽屉 **Total 11** → 点行进聊天：**17 条消息**，时间线与所点明细行吻合（客户 08-31 11:59:12 → 回复 17:24:11 ≈ 5小时24分）。
+
+**④ 客户经营页签**：返回列表再进 → section=customer →「沉睡客户名单」抽屉 **Total 89** ✓。
+
+**⑤ 员工总览对比**：勾选 2 人 → 对比抽屉并列两列指标 ✓（2-5 人为按钮启用门槛），关闭复原。
+
+**⑥ 排序+翻页+CSV（微信渠道）**：综合分降序（服务端 sort）——第 1 页 **55→21**（林峰 55 领头），第 2 页 **11 / 1 / 其余「--」**（18 人 insufficient_sample **空值排尾** ✓）。导出 CSV：**3 行口径前言**（口径/窗口+渠道/试算版本）**+ 表头 + 41 行数据**，toast「已导出 41 条」。
+
+**⑦ 控制台与持久化**：走查全程 console **0 errors**；修复遗留告警后（见 §3）全新加载 **0 warnings**。刷新保持 ✓——列表 view=service 刷新还原（Total 41）、详情返回后 section=service 还原。
+
+**附**：9 档时间预设逐一真机核验：今日 0910~0910 / 昨日 0909 / 近7 0904~0910 / 近30 0812~0910 / 本周 0907~0910（周一周首 ✓）/ 上周 0831~0906 / 本月 0901~0910 / 上月 0801~0831 / 自定义 0901~0907。1366px 驾驶舱与员工总览双页截图目检：KPI 3×2 网阵、双趋势图、表格列均无塌陷/无横向溢出。
+
+## 2. 验收清单核对
+
+**v1 §19.1 员工子集（6 项）**
+
+| # | 项 | 状态 | 依据 |
+|---|---|---|---|
+| 1 | 能查看所有员工多维状态 | ✅ | total=41（API=列表=CSV 行数三方一致）；四视图（管理概览/工作负载/服务质量/客户经营）切换正常 |
+| 2 | 任一分数可展开为指标/公式/样本/事实 | ✅ | 表头「?」→ 指标口径抽屉（19 项定义+公式+样本）；行/详情下钻按钮 → 事实明细 → 聊天原文（§1 ③） |
+| 3 | 四对比 | ✅ | 详情四对比表逐列可见（§1 ③：62/114/107/中位） |
+| 4 | 样本不足不评分 | ✅ | 18 人 insufficient_sample 综合分显「--」（§1 ⑥），CSV 同口径 |
+| 5 | 异常两次点击进事实 | ✅ | 异常卡员工名（第1击）→ 详情下钻按钮（第2击）→ 事实明细/聊天 |
+| 6 | 默认排序非总分/消息量榜 | ✅ | 默认 sort_by=anomaly_severity（异常严重度优先） |
+
+**批次D验收清单（5 项）**
+
+| # | 项 | 状态 | 依据 |
+|---|---|---|---|
+| 1 | 员工总览：41 人四视图/服务端排序分页/keyword/对比 2-5 人/CSV 含口径注释 | ✅ | §1 ⑤⑥；CSV 前言 3 行 |
+| 2 | 员工详情：五维条 3+2 占位/五页签懒加载/四对比/评分明细可展开/下钻进抽屉/账号跳聊天 | ✅ | §1 ③④；页签懒加载+loaded 缓存+section URL 还原 |
+| 3 | 驾驶舱：三 KPI 环比箭头/异常卡可跳员工详情 | ✅ | §1 ①②（闭环打通） |
+| 4 | 时间预设全套 9 档 | ✅ | §1 附 |
+| 5 | URL 全参数保持；四门禁绿；后端仅 dashboard 一处小改且测试补齐 | ✅ | §1 ⑦ + §0；后端改动=dashboard prev_kpis（D3，随测试提交） |
+
+## 3. 走查发现并修复（随本任务提交）
+
+| 问题 | 修复 |
+|---|---|
+| `AnomalyList.vue` 员工链接 `:underline="false"` 触发 Element Plus 废弃 API 告警——驾驶舱每次加载刷 **31 条** `[el-link] underline boolean deprecated`（异常榜每行一条） | 改 `underline="never"`（string API）；修复后全新加载 0 errors 0 warnings |
+
+## 4. 遗留观察项（不阻塞）
+
+| # | 项 | 归档 |
+|---|---|---|
+| 1 | 五维条行序随接口返回序 | 合规风险/行动执行（待数据）排在三实维之前——非固定语义序；批次E 接线 risk/action 后自然消解，如需固定序前端按 dim 顺序数组排即可 |
+| 2 | 走查任务字面 Step6 措辞偏差 | 「切视图服务质量→点综合分列排序」按字面不可执行（综合分列仅管理概览视图有）；实际动线=管理概览排序→切服务质量视图导出，已按实际动线完成走查 |
+| 3 | 空值显示 `-` 与 `--` 混用 | format.ts 的 formatMsDuration/formatRatio 按各自注释约定 null 显 `-`，员工总览本地数值/比率格式化显 `--`——同表跨列观感不一；纯观感项，批次E 顺手统一即可 |
+
+---
+
+# 批次F-调度接入验证（Task F3，2026-09-10）
+
+F1（`_analytics_tick` 段2 管理域滚动，0dc5993）/ F2（夜间链管理步，2ac63e3）已提交后，本地真机直调 tick 验证 + 本地 scheduler 镜像重建。方法：临时脚本（已删）按 tests/test_scheduler_analytics_tick.py 的构造方式 `SyncScheduler(engine=create_async_engine(get_settings().db_url), session_maker=...)`，不 start、只 `await scheduler._analytics_tick()`，对六个上游函数挂计时包装（与测试 monkeypatch 同一延迟 import 打点位），连跑两次。
+
+## 1. tick 两段实测（本地真机库，连跑两次）
+
+| 段 | 内容 | 第1次（冷） | 第2次（暖） |
+|---|---|---|---|
+| 总计 | `_analytics_tick` 全程 | **2.78s** | **0.74s** |
+| 段1 | recompute_days（staff 滚动3天） | 0.86s | 0.15s |
+| 段1 | scanner.run_incremental（敏感词增量） | 0.14s | 0.02s |
+| 段2 | pairs_active_in_days（fact 活跃对发现） | 0.04s | 0.02s |
+| 段2 | recompute_pairs（fact 重算） | 0.00s | 0.00s |
+| 段2 | recompute_metric_days（宽表滚动3天） | 1.51s | 0.52s |
+| 段2 | recompute_call_days（通话滚动3天） | 0.22s | 0.02s |
+
+（段值不含各自 session.commit；日志输出：`staff_days=0 scanned=10 hits=0` + `mgmt fact_pairs=0 wide_rows=168 call_rows=0`，两次一致。）
+
+- **远低于 <60s 预算**。本地镜像已停同步 7 天，滚动窗（0908~0910）内无消息/通话活动——`staff_days=0`、`fact_pairs=0`、`call_rows=0` 属停同步后的数据真空而非缺陷；`wide_rows=168`= 3 天 × 56 行/天（39 员工，wechat 38 + whatsapp 18 行/天，双渠道员工两行），宽表对零活跃员工照常出零值行。段2 主成本=宽表重算，随员工数×天数扩展而非会话数，服务器侧活跃会话数百的形态下同量级。
+- **幂等 ✓**：三表行数跑前 fact=68,476 / wide=12,371 / calls=1,163 → 第1次后 68,476 / **12,539** / 1,163 → 第2次后 68,476 / 12,539 / 1,163。wide 的 +168 为首跑补齐：0908~0910 三天行在表内原本不存在（本地夜间链停摆 7 天没写过），第1次 DELETE+INSERT 补齐后第2次行数纹丝不动——滚动窗语义下幂等成立。
+
+## 2. 本地 scheduler 容器重建（范围仅本地；服务器镜像 2026-09-09 已重建不碰）
+
+- `docker compose up -d --build scheduler`：镜像 `yunke-scheduler:latest`（`ded96dfc9625`，2026-09-10 构建）重建成功，容器 recreate + 起来。
+- 冒烟：`docker exec yunke-scheduler-1 python -c "import app.sync.scheduler"` → ok；容器日志确认 **4 个 job 全注册**——3×`_safe_page_run`（full/messages/full-history）+ **`SyncScheduler._analytics_tick`（F1 新 job 已进夜间/4h 链）**，"Scheduler started" 正常。
+- **调度状态**：验证完即 `docker stop`——重建前容器本就 Exited 7 天（本地不跑调度，避免与服务器调度器双跑同刷云客触发风控），维持 stopped 现状；容器已绑新镜像，用户随时 `docker compose start scheduler` 即以新代码上线。mysql/redis 未动。
+
+## 3. 已知边界（归档）
+
+| # | 项 | 说明 |
+|---|---|---|
+| 1 | phone_call 未进页面同步链 | 通话小表（employee_call_daily）暂从既有静态源重生成——本地 call_rows=0 即此边界的体现；审计 P0-5 由并行会话领地，不在此处理 |
+| 2 | 补同步历史日期 | tick 只滚动当日+前2天；更早日期的修正由夜间全量（full_sync 汇总/管理步）覆盖语义兜底 |
+| 3 | 本地数据真空 | 本地镜像停摆 7 天，0908~0910 无消息/通话——fact/敏感词扫描的真实活跃量级须在服务器侧（夜间链已跑）观察 |

docs/superpowers/plans/2026-09-08-yunke-management-console-implementation-v2.md

@@ -0,0 +1,318 @@
+# 云客经营管理后台实施计划 v2（贴合代码修订版）
+
+- **日期**：2026-09-08
+- **版本**：v2.0
+- **状态**：待评审后进入开发
+- **与 v1 的关系**：替代 `2026-09-08-yunke-management-console-implementation.md`（plans/ 与 specs/ 两份副本内容相同）的**技术设计部分**；产品范围、页面内容细则、验收标准沿用 v1，本文不重复，冲突处以本文为准
+- **上游方案**：[云客数据智能管理平台完整实施计划](./2026-09-08-yunke-data-intelligence-management-plan.md)
+- **修订方式**：对 v1 逐项做「现有代码 ↔ 文档要求」查漏补缺，钉在真实代码事实上重新设计底座
+
+---
+
+## 0. 已确认的决策记录
+
+| 决策项 | 结论 |
+|---|---|
+| 一期范围 | 按 v1 原计划全量：管理驾驶舱 + 员工总览 + 员工详情 + 考核快照（Task 0-13） |
+| 业务口径 | 全按 v1 §21 默认值：自然时间 SLA、2h+24h 双 SLA、30 天沉睡、综合分标「试算」、CSV 导出、仅管理层可见、个人基线=过去 4 周 |
+| 底座方案 | 方案 B：新增首响事实表 + 收敛版员工宽表（v1 架构骨架不变） |
+| 关键修正 | 见 §1 修订总览——fact 表独立计算（跨日精确算法）、宽表 1:1 口径全量自算、生命周期沿用距今天数口径 |
+
+---
+
+## 1. 相对 v1 的修订总览
+
+### 1.1 P1 级（正确性/口径，必须修正）
+
+| # | 问题 | 证据 | 修正 |
+|---|---|---|---|
+| 1 | **跨夜串丢失**：现有日切算法下「客户 23:00 发→员工次日 9:00 回」的首响样本整条丢失（Day1 串未闭合只计 threads；Day2 重起算时无客户消息不成串，员工回复落空段）。P90/24h 回复率系统性低估，而评分重度依赖这两项 | `app/storage/summary.py` `_thread_stats` 日切近似，docstring 自述「跨夜串归属日偏差」实为样本丢失 | fact 表**不挂写钩子**，由 4h 滚动+夜间全量任务用**跨日精确串算法**（按会话全历史计算）独立生成；写钩子零改动，`_thread_stats` 不改 |
+| 2 | **stat_daily_staff 是 friend+room 混合口径**：`sent/recv/threads/answered/fr` 五列聚合无 kind 过滤，群消息污染首响/回复率。v1 说「从 stat_daily_staff 拷贝」不可行 | `app/storage/staff_summary.py` `recompute_days` 聚合循环 | 宽表消息计数列从 msg_daily_stats 按 `peer_kind='friend'` 自算（account_map 归并模式复用）；串类三列由 fact 模块同源输出（见 #5）；管理页与现有看板排行的数字差异属口径不同，各自标注 |
+| 3 | **「降温」定义冲突**：上游整合计划（`2026-09-08-yunke-data-intelligence-management-plan.md` §8.1/§15）降温=频次低于个人基线；现有 churn/客户资产分层=距今天数区间。两套「降温」会并存打架 | `app/analytics/metrics.py` churn 三分法 | 一期生命周期 4 列统一用**现有距今天数口径**；频次基线降温后置二期；差异写入 metric-definitions |
+| 4 | **对账口径必须预写死**：fact（跨日精确）与 msg_daily_stats 三列（日切近似）即使 friend 口径也不相等，差集=跨夜闭合串 | 同 #1 | Task 2 验收断言：fact 样本集 ⊇ 日切被回串，差集=跨夜串；禁止相等断言 |
+| 5 | **回复率分子分母必须同源**：v2 初稿宽表串类列（cust_threads 等）取自 msg_daily_stats 日切聚合，而回复率分子取自 fact（跨日）——多日未回串使日切分母膨胀，回复率被系统性低估 | 本轮复查发现（#2 修正的连带遗漏） | 宽表串类三列改由 fact 计算模块**同源输出**（按串末条归属日的 threads/answered/fr_sum）；msg_sent/recv 与 active_friends/rooms 与串算法无关，仍取 msg_daily_stats |
+
+### 1.2 P2 级（性能/实现修正）
+
+| # | 问题 | 修正 |
+|---|---|---|
+| 6 | 周期分位数若 Python 拉全窗口 fact 行（月窗最坏 ~8 万行 ≈10MB 传输）不可取 | 改 SQL 窗口函数 `PERCENT_RANK() OVER (PARTITION BY user_id ORDER BY fr_ms)`（MySQL 8.4 / SQLite 3.25+ 双方言支持），传输降为员工数×2 行 |
+| 7 | fact 4h 增量成本 | 滚动 3 天=近 3 天活跃会话**全历史重算**（最大 friend 会话 5.2 万条 ≈1-2s × 几十活跃会话，4h 一次可接受）；一期取简单正确，预留「尾部增量」优化（历史已闭合串不变） |
+| 8 | full_sync_all.sh 步数变化 | 12→**14** 步：第 13 步 fact 全量重建、第 14 步宽表全量重建（宽表必须在 fact 之后） |
+| 9 | **通话列渠道错位**：v2 初稿把通话四列放进 (day, channel, user) 宽表，但 `phone_call.channel` 是**通话类型**（phone_call/voice_call）非消息渠道（models.py docstring 自证「calls are not tied to a messaging channel」）——channel=all 聚合时通话四列双计 | `app/db/models.py` PhoneCall 定义（批次A计划定案） | 通话拆出独立小表 `employee_call_daily`（day, user_id 主键，无渠道维），宽表删去通话四列 |
+
+### 1.3 P3 级（补充明确/简化）
+
+| # | 项 | 结论 |
+|---|---|---|
+| 10 | 员工主数据来源未核实 | 列入 Task 0 核实（默认 = `staff` 表，user_id 主键 + is_on_job，models.py 已有） |
+| 11 | 幽灵员工 | account_map 映射不上的 owner（离职/异常账号），宽表生成时直接**过滤**，不进管理域员工列表（评分场景不适用 analytics 的「读侧标注」策略） |
+| 12 | 功能开关降级 | 现状单 admin 账号无角色可分，v1 Task 13 的「功能开关」是过度设计；改为**上线顺序控制**（本地先行→服务器后上），RBAC 二/三期（与 v1 §15 一致） |
+| 13 | fr_ms 边界 | 按 ts 排序保证非负；超长样本（>30 天）保留在 fact，评分按异常裁剪原则处理（上游整合计划 §6.5「极端值不直接放大分数」）：>30 天样本参与分布展示，但不作为 0 分依据，单独列入超时明细 |
+| 14 | 五维分布图 | 一期只画 3 个可用维度（客户经营/服务质量/有效负载）+ 2 个「待数据」占位（行动执行/风险合规），不暗示完整五维 |
+
+---
+
+## 2. 查漏补缺：复用映射总表
+
+| v1 能力项 | 现有可复用 | 本次动作 |
+|---|---|---|
+| 员工日指标底座 | `stat_daily_staff`（8 列，混合口径）、`msg_daily_stats`（首响三列，日切近似） | 两表**均不动**；新增 `first_reply_fact` + `employee_metric_daily`（§3） |
+| 时间窗/环比口径 | `app/analytics/metrics.py` `scope_day_keys`/`_prev_scope_days`（5 种窗+同期对齐） | management 层直接 import，不复制时区逻辑 |
+| 生命周期分层 | `metrics.py` 客户资产分层 / churn 三分法（距今天数口径） | 提炼共享函数，日聚合任务与 analytics 共用；analytics 调用点保持不变（包装层） |
+| 首响均值/回复率算法 | `staff_ranking` 的 fr_avg/reply_rate | 周期值改为宽表 SUM + fact 表精确分位 |
+| 异常检测雏形 | `anomaly`（昨日 vs 前 7 日均值偏离>50%） | `management/anomalies.py` 扩展为规则集：回复恶化（fact P90）、待回复增长（B2）、活动骤降/过载（宽表） |
+| 驾驶舱页面 | `DashboardView.vue` 的图表模式、`useChart`、筛选栏、骨架屏/空态分语 | 新建 ManagementDashboardView，复用全部 composables/utils；旧页并存过渡后重定向 |
+| 流失/该回未回/敏感词 | 三个现有页面 | 不动，作为下钻目标 + 驾驶舱行动入口聚合 |
+| 数据截至/新鲜度 | `app/analytics/health.py` 的 data_as_of 逻辑 | 管理页「数据截至/完整性」角标直接复用 |
+| 调度 | `analytics_tick`（4h：staff 汇总+敏感扫描） | 追加第三步：fact 滚动重算 + 宽表滚动重算 |
+| 回填/自愈 | `full_sync_all.sh` 第 11/12 步 | 追加第 13/14 步（fact/宽表全量重建）+ 两条回填 CLI |
+| 员工事实下钻 | `/staff-chat`、`/chat`、`/groups`、`/calls` | 不动，管理页只做链接跳转 |
+| CSV 导出 | `csvExport.ts`（全量翻页+中文 BOM） | 直接复用 |
+
+---
+
+## 3. 数据库设计：6 张新表
+
+### 3.1 `first_reply_fact` 首响事实表（本设计新增）
+
+**用途**：任意时间窗精确 P50/P90、2h/24h 回复率分子、指标解释抽屉的构成明细下钻证据。
+
+**算法（跨日精确串口径，区别于 msg_daily_stats 的日切近似）**：
+
+- 串 = 同一会话内客户连续消息（is_send=False）不被员工消息（is_send=True）打断的段；is_send=None 跳过；
+- 每个被回串一个样本：`fr_ms = 员工首条回复 ts − 串末条客户消息 ts`；
+- 样本归属 = 串末条消息所在**上海自然日**（跨夜串不再丢失）；
+- 只写 `peer_kind='friend'`（1:1）行——群串语义不成立且占串数大头，不写；
+- 模块同时输出**每日串聚合**（threads/answered/fr_sum，同按串末条归属日）供宽表消费——回复率分子分母同源（§1.1 #5）；
+- 按会话全历史计算，幂等模式=按会话 delete+insert。
+
+**表结构**：
+
+```text
+唯一键: (channel, owner_account_id, peer_id, thread_end_ts, reply_ts)
+列:     day            int      串末条所在上海日 yyyymmdd（冗余物化，索引用）
+        thread_end_ts  BigInteger  串末条客户消息 ts(ms)
+        reply_ts       BigInteger  员工首条回复 ts(ms)
+        fr_ms          BigInteger
+索引:   (day, channel) 趋势/窗口查询；唯一键自身覆盖会话下钻
+```
+
+**生成链路（不挂写钩子）**：
+
+- 4h tick：对近 3 天有消息的会话（从 msg_daily_stats 近 3 天行取 pairs）做全历史重算；
+- 夜间全量：full_sync_all.sh 第 13 步，遍历全部 friend 会话（复用 `recompute_all` 的 pairs 遍历模式）；
+- 回填 CLI：`python -m app.sync.cli first-reply-facts`，分批可重跑可记水位；
+- 量级：日均几百行、全年几十万行，远小于 message 表。
+
+### 3.2 `employee_metric_daily` 员工指标宽表（v1 表的收敛版）
+
+**口径总则**：消息串类列 = 1:1（friend-only）口径，从 msg_daily_stats 自算；与现有看板（friend+room 混合）的数字差异属口径不同。
+
+```text
+PK: (day, channel, user_id, metric_version)
+
+消息计数列（msg_daily_stats 自算，friend 过滤 + account_map 归并；与串算法无关）:
+  msg_sent, msg_recv
+串类列（fact 计算模块同源输出，跨日精确、按串末条归属日——与回复率分子同口径）:
+  cust_threads, threads_answered, fr_sum_ms
+负载列（msg_daily_stats，friend/room 分行天然区分）:
+  active_friends（1:1 distinct 客户）, active_rooms（distinct 群）
+首响日值（趋势图用，从 fact 算）:
+  first_reply_p50_ms, first_reply_p90_ms
+生命周期 4 列（距今天数口径，当日持有客户状态分布，按 customer 当前归属）:
+  new_customer_count, cooling_customer_count,
+  dormant_customer_count, reactivated_customer_count
+元数据:
+  data_complete, computed_at
+```
+
+**通话小表 `employee_call_daily`**（§1.2 #9 拆出，无渠道维）：
+
+```text
+PK: (day, user_id)
+列: call_count, call_seconds, answered_call_count, call_followup_count, computed_at
+数据源: phone_call 按 user_id+start_call_time 日聚合；接通=call_duration>0；
+        followup=通话后 24h 内该员工任一账号对该客户有消息（Task 0 核实 join 键）
+```
+
+**相对 v1 的删减与更名**：
+
+- 6 列可派生不落：`reply_2h/24h_count`、`unreplied_2h/24h_count`（fact 表 fr_ms≤阈值计数 + cust_threads 派生）、`first_reply_count/first_reply_sum_ms`（≡ threads_answered/fr_sum_ms）；
+- `effective_sessions` 不单列：v1 §6.3 工作负载视图的「有效会话」≡ cust_threads（1:1 有客户消息串的天级会话数），页面字段名从 cust_threads 映射；
+- `activated_customer_count` 一期不做：「有效激活」定义是 v1 §21 #4 未决口径（几轮互动/几天窗口），随二期频次基线生命周期一起定义；
+- `customer_threads` 更名为 `cust_threads`（与 msg_daily_stats/stat_daily_staff 现有列名对齐）。
+
+**metric_version 语义**：只影响派生列（生命周期/通话跟进的算法口径）；消息计数与串类事实列与版本无关。默认值 `v1`，算法演进时新版本并行落表不覆盖旧数据。
+
+**时效说明**：消息计数列的源数据（msg_daily_stats）随写钩子近实时更新，串类列的源数据（fact）随 4h/夜间重算更新——两类列的上游时效不同，但宽表行统一随 4h/夜间重算落库；computed_at 取宽表生成时间，data_complete 标注 fact 是否已覆盖当日。
+
+**评分用周期值的计算来源**（不在宽表存储）：周期 P50/P90、2h/24h 回复率一律从 fact 表精确计算（SQL 窗口函数），宽表日值仅供趋势展示。
+
+### 3.3 `employee_score_config` / `employee_score_snapshot` / `management_followup`
+
+按 v1 §11.1 原样实施，无修改：
+
+- config：version 唯一、status、effective_from/to、config_json（维度/指标/权重/方向/阈值/样本门槛），激活前权重总和与阈值校验；
+- snapshot：snapshot_batch_id、period_type/period、score_config_version、metric_version、total_score、grade、score_status（scored/insufficient_sample/incomplete_data）、dimension_scores_json、metric_details_json、data_as_of、frozen_at/frozen_by、supersedes_id；同批次员工唯一；冻结后业务层禁改；
+- followup：source_type/code/period/value、reason、action_type、owner_manager_id、status（open/in_progress/resolved/cancelled）、due_at、result、employee_feedback；索引 `(employee_user_id, status, due_at)`、`(owner_manager_id, status)`。
+
+### 3.4 迁移要求
+
+- 一个 Alembic migration 建 5 张表；migration 只建表和索引，**不扫描消息**；
+- 数据回填走独立 CLI 分批执行（可暂停/重跑/记水位），先在本地 Docker 快照验证耗时与一致性；
+- downgrade 只删本次新增对象；SQLite（测试）/MySQL（生产）双方言；
+- 升级前确认当前 head（服务器注意：backend 容器**不自动跑 alembic**，须手动 `exec backend alembic upgrade head`）。
+
+---
+
+## 4. 计算链路与调度
+
+```text
+message 入库（写钩子，全路径覆盖——现状，零改动）
+  → msg_daily_stats                        [summary.py]
+      → stat_daily_staff                    [staff_summary.py，现状]
+
+message（按会话全历史，跨日精确算法）        [新 storage/first_reply_facts.py]
+  → first_reply_fact
+      │
+      └─→ employee_metric_daily             [新 storage/employee_metrics.py：
+             msg 计数(msg_daily_stats,friend) + 串类/分位(fact 同源)
+             + customer 生命周期]
+phone_call → employee_call_daily              [通话小表，无渠道维，§1.2 #9]
+              → 期聚合/四对比（上期/个人基线4周/团队中位数）
+                  → 试算评分 + 异常规则      [management/]
+                      → 周/月快照（不可变）  [management/snapshots]
+```
+
+- **4h**：`analytics_tick` 追加第三步：fact 滚动重算（近 3 天活跃会话）→ 宽表重算（当日+滚动 3 天）；失败只记日志不中断（沿用现有异常隔离模式）；
+- **夜间**：full_sync_all.sh 第 13 步 fact 全量重建、第 14 步宽表全量重建（顺序：必须在 msg_daily_stats/stat_daily_staff 之后）；
+- **生命周期历史快照**：补同步触及历史日期时不能只重算那几天（那天的「距上次互动天数」依赖更早历史），统一由夜间全量按会话日序列重放覆盖；4h tick 只算当日；
+- **通话后跟进**（call_followup_count）：3,190 条通话量级小，逐通话窄查 24h 内员工对该客户的消息（join 键以 Task 0 核实结果为准），聚合任务内完成；
+- **性能原则**：管理页面禁止实时扫描 96 万条原始消息；趋势和员工表读宽表+fact；原始消息只用于小范围下钻。
+
+---
+
+## 5. 口径决议表（管理域 vs 现有看板）
+
+| 指标 | 管理域口径 | 现有看板口径 | 差异原因 |
+|---|---|---|---|
+| 消息量/串/首响均值 | 1:1（friend-only） | friend+room 混合 | 服务质量语义要求 1:1 |
+| 首响分位 | 跨日精确串（fact） | 日切近似（跨夜丢失） | P90 正确性 |
+| 降温客户 | 距今天数区间（同 churn 页） | 同 | 一期统一，频次基线降温二期 |
+| 活跃员工 | 宽表口径（幽灵员工已过滤，§1.3 #10） | `_active_staff` 含映射不上的账号并读侧标注 | 评分场景不接受幽灵员工 |
+| 交互天数/日桶 | Asia/Shanghai 自然日 | 同 | 一致 |
+
+三方差异（管理页 vs 数据看板 vs 云客原版）在 metric-definitions 端点与页面口径说明中如实标注，不做静默差异。
+
+---
+
+## 6. API 设计（`/api/management/*`）
+
+沿用 v1 §12.3 的 11 个端点与通用响应约定（比例 0~1、时长带单位后缀、空值≠0、稳定 error_code、data_as_of+metric_version+sample_status 必返），实现落点：
+
+| 端点 | 关键实现落点 |
+|---|---|
+| `GET /dashboard` | 一次返回 KPI/双趋势/生命周期/维度分布/异常/行动聚合；data_as_of 复用 health.py |
+| `GET /employees` | 服务端分页排序；默认按异常严重度排（不做总分榜）；每员工带四对比值+sample_status |
+| `GET /employees/{user_id}` | 首屏只回头部+维度分+趋势摘要+异常+辅导摘要 |
+| `GET /employees/{user_id}/metrics?section=` | service/customer/workload/calls_groups 四页签懒加载；行动/风险页签一期不建 |
+| `GET /employees/{user_id}/drilldown?metric_code=` | **白名单**：`first_reply_p90`→fact 逐串明细（含跳聊天定位）、`unreplied`→复用 B2、`cooling_customers`→客户列表带筛选、`call_followup`→通话列表。禁止前端传 SQL 字段/表达式 |
+| `GET /metric-definitions` | 指标元数据（口径/单位/方向/样本门槛/公式/版本），含 §5 差异标注 |
+| `GET/POST /reviews` | 草稿幂等生成（同 period+config 已有 draft 返回既有批次）；`data_complete=false` 拒绝冻结 |
+| `POST /reviews/{batch_id}/freeze` | 仅 draft→frozen；MVP 不做 published（RBAC 前置） |
+| `GET/POST/PATCH /followups` | 状态机白名单流转 |
+
+**周期分位数**：SQL 窗口函数 `PERCENT_RANK() OVER (PARTITION BY user_id ORDER BY fr_ms)` 取最接近 0.5/0.9 分位的行，双方言一致。
+
+**一期评分**：综合分 = 可用维度（客户经营 30 + 服务质量 25 + 有效负载 15 = 70%）按 `100/70` 归一化 + **「试算」角标**；行动执行/风险维度显示「待数据」，不补 0 不补满分（v1 §10.1 默认）。
+
+---
+
+## 7. 前端设计
+
+- **路由**：`/management/dashboard`、`/management/employees`、`/management/employees/:userId`（activeMenu 高亮父级）、`/management/reviews`；MainLayout 新增「经营管理」分组（二期菜单不渲染、不放空页面）；`/analytics/dashboard` 过渡期并存、稳定后重定向；
+- **目录**：`views/management/` 四页 + `components/management/`（ManagementFilterBar/ManagementKpiCard/ComparisonValue/DataAsOfBadge/ScoreBar/ScoreBreakdown/EmployeeMetricsTable/MetricDefinitionDrawer/MetricDrilldownDrawer/AnomalyList/FollowupDrawer）+ `composables/useManagementFilters.ts`（URL query 为真源）+ `api/management.ts`；
+- **复用清单**：useChart（维度分布用分组条形图，BarChart 已注册，**不引雷达图**）、axios client 的 token/401 处理、`utils/format.ts`、`csvExport.ts`、seq 守卫防旧响应覆盖、DashboardView 的骨架屏/空态分语模式；
+- **展示规范**：样本不足显示 `--` 与「样本不足」（非 0 分）；「越低越好」指标反转趋势色；1366px 主表可用；导出与当前筛选排序一致。
+
+---
+
+## 8. 任务拆分（v1 Task 0-13 修正版）
+
+| 任务 | 内容 | 相对 v1 的变化 | 估时 |
+|---|---|---|---|
+| Task 0 | 口径冻结：回测员工名单（3-5 名覆盖微信为主/WA 为主/群为主/高负载/低样本）+ 默认口径记录成文档（配置落库在 Task 3 种子 CLI，本任务不改代码）+ **五项核实**（phone_call 表结构与客户标识 join 键、call_followup 多账号语义——员工任一账号跟进即算、customer 归属字段与换人规则、员工主数据来源、群占比抽样量化混合口径偏差） | 默认值已确认，工作量缩减 | 0.5 天 |
+| Task 1 | 5 张表模型 + migration + 模型冒烟测试 | 6→5 张表；核实项前置完成 | 1-1.5 天 |
+| Task 2 | fact 独立计算模块（跨日精确算法，同源输出每日串聚合供宽表）+ 宽表生成（消息计数 friend 自算+串类取 fact+生命周期+通话）+ 生命周期共享函数提炼（analytics 调用点不动）+ 两条回填 CLI | **删除「_thread_stats 兼容扩展」**（不再需要）；验收含对账判据（§1.1 #4/#5）+ 写钩子零改动确认 | 2.5-3.5 天 |
+| Task 3 | scoring.py：归一化/四对比/样本保护 + 配置校验 + **默认配置 v1.0 种子落库**（受控 CLI，Task 11 快照的前置依赖） | 含 100/70 归一试算逻辑 | 2 天 |
+| Task 4 | anomalies.py 规则集 | 数据源：fact（P90 恶化）、B2（待回复增长）、宽表（骤降/过载） | 1 天 |
+| Task 5 | 管理 API（dashboard/employees/detail/metrics/drilldown/metric-definitions） | 窗口函数分位 + 性能目标 | 2-3 天 |
+| Task 6 | 前端公共组件与路由（api/management.ts、useManagementFilters、components、router、MainLayout） | 按文档 | 1.5-2 天 |
+| Task 7 | ManagementDashboardView（KPI/双趋势/生命周期/异常榜/下钻） | 复用图表模式，估时较 v1 略降 | 2-2.5 天 |
+| Task 8 | EmployeeAnalyticsView（一期 4 视图+分页排序+指标抽屉+员工对比） | 行动/风险视图不建 | 2-3 天 |
+| Task 9 | EmployeeAnalyticsDetailView（概览/服务质量/客户经营/工作负载/通话与群五页签） | 按文档 | 3-4 天 |
+| Task 10 | followups 闭环（查询/创建/更新/状态流转测试） | 按文档 | 1.5-2 天 |
+| Task 11 | 考核快照（草稿/详情/冻结/重算替代/列表/CSV） | 按文档 | 2-3 天 |
+| Task 12 | 调度接入：analytics_tick 第三步 + full_sync 第 13/14 步 + 失败隔离 + 手动重跑入口 | 步数 12→14；**服务器 scheduler 镜像重建遗留**（9d3cc8e 部署时未重建）一并处理 | 1-1.5 天 |
+| Task 13 | 回测校准 + 上线顺序控制（本地→服务器）+ 试运行记录 | 功能开关→部署顺序控制 | 2-3 天 |
+
+**批次划分**（每批独立验收，不夹带无关重构）：
+
+| 批次 | 任务 | 可见结果 |
+|---|---|---|
+| A | Task 1-2 | 表+fact+宽表可在测试与脚本中查询，回填可重跑 |
+| B | Task 3-5 | OpenAPI 可验证全部只读管理接口 |
+| C | Task 6-7 | 新导航+驾驶舱可用，异常两次点击到事实 |
+| D | Task 8-9 | 员工总览+详情可比较可下钻 |
+| E | Task 10-11 | 辅导闭环+冻结周期结果 |
+| F | Task 12-13 | 持续运行+内部试运行 |
+
+**总工期**：单链 18-24 个工作日；前后端并行 12-16 天。口径确认（已完成）、数据回测和试运行不可省略。
+
+---
+
+## 9. 测试与验收（v1 §16 基础上新增判别项）
+
+**后端单元/API 测试**（新增文件按 v1 §16.1 清单）：
+
+- **跨夜串判别**（P1#1 防线）：seed 客户 23:00 消息+员工次日 9:00 回复，断言 fact 产生 fr_ms≈10h 的行——正是日切口径丢失的场景；
+- **口径判别**（P1#2 防线）：seed 同员工 friend+room 两类会话，断言宽表 1:1 列不含 room 串；
+- **分位数精确性**：构造已知 fr_ms 集合，断言周期 P50/P90 精确值；窗口函数 SQLite/MySQL 双方言一致；
+- **fact 超集断言**（P1#4）：fact ⊇ 日切被回串，差集=跨夜串，不做相等断言；
+- **分子分母同源**（P1#5）：任意窗口 reply_rate ≤ 1；宽表 threads_answered ≡ fact 行数（同窗口）；存在多日未回串时宽表 cust_threads < 日切口径值（分母不再膨胀）；
+- **fact 回填幂等**：重跑不重不漏；
+- **快照不可变**：冻结后 PATCH 拒绝（后端强制）；
+- 评分边界：正/反向指标、阈值边界、权重合计、样本不足不评分、空值≠0、缺失维度不默认 0/100；
+- 下钻白名单：非法 metric_code 拒绝；
+- 幽灵员工过滤：映射不上的 owner 不进宽表。
+
+**数据核验**（3-5 名回测员工，覆盖微信为主/WA 为主/群为主/高负载/低样本）：抽查 3 日期消息与活跃客户、20 个首响串（对照 fact 明细）、10 个待回复客户、5 条通话后跟进、生命周期变化、评分展开明细；对账点增加宽表消息计数列（msg_sent/msg_recv）↔ msg_daily_stats friend 聚合——**串类列禁止相等断言**（口径差异见 §1.1 #4/#5）。
+
+**性能验收**（v1 §16.5 全部目标基础上追加）：员工列表服务质量视图 30 天窗（含 fact 窗口函数分位）p95 ≤ 1.5s。
+
+**前端**：`npm run build` + Vitest（格式化/趋势方向/样本状态/筛选 query/旧响应不覆盖）。
+
+---
+
+## 10. 部署注记（写入 DEPLOY.md）
+
+1. 服务器 backend 容器**不自动跑 alembic**——升级带迁移必须手动 `sudo docker exec <backend> alembic upgrade head`；
+2. 两条回填 CLI（`first-reply-facts` / `employee-metrics`）部署后执行一次，DEPLOY.md §7 注记（含耗时参考与避抓取窗口建议）；
+3. scheduler 镜像重建（含 9d3cc8e 遗留）：`cd /opt/yunke && sudo docker compose -f docker-compose.server.yml --env-file .env up -d --build scheduler`——重建前 fr 三列/第 11-14 步不自愈；
+4. fact 表索引创建量级小（几十万行），无需特殊避峰；
+5. 上线顺序：本地 Docker 全量回填对账 → 本地试用 → 服务器升级+回填 → 管理者只读试用。
+
+---
+
+## 11. 沿用 v1 不变的部分（索引）
+
+以下内容直接按 v1 执行，本文不重复：
+
+- 页面内容细则：v1 §5-§9（驾驶舱布局/KPI 卡清单、员工总览六视图、员工详情页签、快照页、二三期概要）；
+- 评分标准化公式与等级：v1 §10.2/§10.4；
+- 后端模块目录与分层职责：v1 §12.1/§12.2（其中 storage 两模块以本文 §3/§4 为准）；
+- API 通用响应约定全文：v1 §12.4；
+- 前端可视化规范全文：v1 §13.4；
+- 验收标准：v1 §19；
+- 灰度顺序/影子考核/回滚：v1 §20（其中「功能开关」按本文 §1.3 #11 替换为上线顺序控制）。

docs/superpowers/plans/2026-09-09-management-console-batch-b-api-plan.md

@@ -0,0 +1,546 @@
+# 云客经营管理后台·批次B（评分/异常/管理API）实施计划
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** 在批次A数据底座之上交付只读管理 API——期聚合查询、五维试算评分、确定性异常规则、指标元数据、6 个 `/api/management/*` 端点，OpenAPI 可验证；前端（批次C）紧随其后。
+
+**Architecture:** 新建 `app/management/` 业务层（metric_definitions / employee_metrics 期聚合 / scoring / anomalies），`app/api/routers/management.py` 只做参数校验与编排（照 analytics 惯例：SessionDep + Annotated 参数 + dict 返回）。**本期只做 6 个只读端点**（dashboard / employees / employee detail / metrics sections / drilldown 白名单 / metric-definitions）；reviews 与 followups 写端点属批次E。依据：[v2 计划](./2026-09-08-yunke-management-console-implementation-v2.md) §1（决策记录）/§6（API 设计）/§8（Task 3-5）；批次A已交付全部数据表与回填。
+
+**Tech Stack:** 同批次A（FastAPI + SQLAlchemy async；测试内存 SQLite；生产 MySQL 8.4）。
+
+---
+
+## 执行者必读：批次A交付物与既定口径
+
+1. **数据表就绪**（迁移 b7c8d9e0f1a2，本地已回填）：`first_reply_fact`（68,476 行，PK 含 reply_msg_id）、`employee_metric_daily`（12,371 行，metric_version='v1'，串类列与 fact 同源）、`employee_call_daily`（1,163 行）、`employee_score_config`（空，本批次 B0 种子）。
+2. **复用模块**：`app/storage/first_reply_facts.py`（fact 表直接查询）、`app/analytics/lifecycle.py`（阈值常量）、`app/analytics/metrics.py` 的 `action_counts`（dashboard 行动入口聚合）、`app/analytics/health.py` 的 `data_as_of`。
+3. **周期口径**：start/end 为 yyyymmdd 上海自然日（与 analytics custom scope 同校验：缺一 422、日历非法 422、start>end 422、跨度 ≤366 天）；上期=等长紧邻前窗；个人基线=紧邻当前窗之前的 28 天窗。
+4. **评分默认（全部标「试算」，config 里可调）**：维度权重 客户经营30/服务25/行动执行20(pending_data)/有效负载15/合规风险10(pending_data)；可用维度归一化 ×100/70；样本门槛 min=30 串/soft=10 串（周期内）；等级 A≥90/B≥80/C≥70/D≥60/E。
+5. **鉴权**：app 级 `require_auth` 全局生效，management 路由无需额外处理；`GET` only。
+6. **测试命令**：`cd yunke-server && .venv/Scripts/python.exe -m pytest tests/test_management_api.py -v`；提交中文 conventional；master 直提（项目惯例）；仓库有并行会话活动——`git status` 后只 add 自己的文件。
+7. **前端不做**（批次C另出计划）；`schemas_management.py` 留批次E写端点用（analytics 惯例 dict 返回，本期一致）；错误响应沿用 analytics 的 `HTTPException(422/404, message)` 风格（v1 §12.4 的稳定 error_code 为有意偏差，前端按 HTTP 状态码分支）。
+
+## 文件地图
+
+| 文件 | 职责 | 动作 |
+|---|---|---|
+| `yunke-server/app/management/__init__.py` | 包标记（空） | 新建 |
+| `yunke-server/app/management/metric_definitions.py` | 指标元数据注册表 + 默认评分配置 DEFAULT_SCORE_CONFIG | 新建 |
+| `yunke-server/app/management/employee_metrics.py` | 期聚合查询（宽表 SUM/fact 窗口函数分位/期末生命周期/通话/distinct 活跃/四对比） | 新建 |
+| `yunke-server/app/management/scoring.py` | 标准化/维度分/归一化试算/样本保护/等级 | 新建 |
+| `yunke-server/app/management/anomalies.py` | 4 条确定性规则 → v1 §5.4 异常卡片 | 新建 |
+| `yunke-server/app/sync/cli.py` | `score-config` 种子子命令 | 修改 |
+| `yunke-server/app/api/routers/management.py` | 6 只读端点 | 新建 |
+| `yunke-server/app/api/main.py` | include_router | 修改 |
+| `yunke-server/tests/test_management_scoring.py` 等 4 个测试文件 | 判别测试 | 新建 |
+| `docs/superpowers/plans/2026-09-08-management-batch-a-verification.md` | 批次B冒烟数据追加 | 修改（B5） |
+
+---
+
+### Task B0: 指标元数据 + 默认评分配置 + 种子 CLI
+
+**Files:**
+- Create: `yunke-server/app/management/__init__.py`（空文件）
+- Create: `yunke-server/app/management/metric_definitions.py`
+- Modify: `yunke-server/app/sync/cli.py`（`score-config` 子命令）
+- Test: `yunke-server/tests/test_management_scoring.py`（本任务先写配置/种子部分）
+
+- [ ] **Step 1: 写测试（先失败）**
+
+`tests/test_management_scoring.py`：
+
+```python
+"""管理域评分配置/引擎判别测试(批次B)。"""
+import json
+
+import sqlalchemy as sa
+
+from app.db.models import EmployeeScoreConfig
+from app.management.metric_definitions import (
+    DEFAULT_SCORE_CONFIG,
+    METRIC_DEFINITIONS,
+    validate_config,
+)
+
+
+def test_config_weights_sum_and_structure():
+    dims = DEFAULT_SCORE_CONFIG["dimensions"]
+    assert sum(d["weight"] for d in dims.values()) == 100
+    # 一期 pending_data 的维度不参与试算
+    available = [d for d in dims.values() if d.get("status") != "pending_data"]
+    assert sum(d["weight"] for d in available) == 70  # 30+25+15
+    assert dims["action"]["status"] == "pending_data"
+    assert dims["risk"]["status"] == "pending_data"
+
+
+def test_config_normalization_declared():
+    assert DEFAULT_SCORE_CONFIG["normalization"] == "available_only_rescale"
+
+
+def test_validate_config_rejects_bad_weight_sum():
+    bad = json.loads(json.dumps(DEFAULT_SCORE_CONFIG))  # deep copy
+    bad["dimensions"]["service"]["weight"] = 26  # 总和 101
+    problems = validate_config(bad)
+    assert any("权重" in p for p in problems)
+
+
+def test_metric_definitions_cover_scored_metrics():
+    # 每个参与评分的 metric_code 都有元数据(名称/单位/方向)
+    for dim in DEFAULT_SCORE_CONFIG["dimensions"].values():
+        for code in dim.get("metrics", {}):
+            md = METRIC_DEFINITIONS[code]
+            assert md["name"] and md["unit"] and md["direction"] in (1, -1)
+
+
+async def test_seed_and_idempotent(make_session):
+    from app.sync.cli import _seed_score_config  # 纯会话函数(见 Step 3)
+    s = make_session
+    v1 = await _seed_score_config(s)
+    await s.commit()
+    assert v1 == "v1.0"
+    rows = (await s.execute(sa.select(EmployeeScoreConfig))).scalars().all()
+    assert len(rows) == 1 and rows[0].status == "active"
+    # 幂等:已存在同版本返回 None 不新建
+    assert await _seed_score_config(s) is None
+    await s.commit()
+    assert len((await s.execute(sa.select(EmployeeScoreConfig))).scalars().all()) == 1
+```
+
+- [ ] **Step 2: 跑测试确认失败**（ModuleNotFoundError: app.management）
+
+- [ ] **Step 3: 实现 metric_definitions.py**
+
+```python
+"""管理域指标元数据与默认评分配置(批次B,v2 §6/§10)。
+
+METRIC_DEFINITIONS 是 /api/management/metric-definitions 的单一数据源:
+名称/单位/方向/口径说明(含与现有看板的三方口径差异标注)。
+DEFAULT_SCORE_CONFIG 为 v1.0 试算起点——所有阈值标「试算」,调整走
+新配置版本(employee_score_config),不静默改数。
+"""
+from __future__ import annotations
+
+# direction: +1 越大越好 / -1 越小越好;caliber 注明与看板差异
+METRIC_DEFINITIONS: dict[str, dict] = {
+    "msg_sent": {"name": "发出消息(1:1)", "unit": "条", "direction": 1,
+                 "caliber": "仅私聊;现有看板为私聊+群聊混合"},
+    "msg_recv": {"name": "收到消息(1:1)", "unit": "条", "direction": 1,
+                 "caliber": "仅私聊"},
+    "cust_threads": {"name": "客户消息串", "unit": "串", "direction": 1,
+                     "caliber": "跨日精确,按串末条归属日;看板为日切口径(多日串重复计)"},
+    "threads_answered": {"name": "被回串数", "unit": "串", "direction": 1,
+                         "caliber": "≡first_reply_fact行数(同源)"},
+    "fr_avg_ms": {"name": "平均首响", "unit": "ms", "direction": -1,
+                  "caliber": "fr_sum_ms/threads_answered"},
+    "fr_p50_ms": {"name": "首响中位数", "unit": "ms", "direction": -1,
+                  "caliber": "周期内 fact 精确分位(窗口函数)"},
+    "fr_p90_ms": {"name": "首响P90", "unit": "ms", "direction": -1,
+                  "caliber": "周期内 fact 精确分位;日切口径会丢跨夜长尾"},
+    "reply_2h_rate": {"name": "2h回复率", "unit": "0-1", "direction": 1,
+                      "formula": "count(fr_ms<=2h)/cust_threads",
+                      "caliber": "分子分母同源(fact/宽表同一算法)"},
+    "reply_24h_rate": {"name": "24h回复率", "unit": "0-1", "direction": 1,
+                       "formula": "count(fr_ms<=24h)/cust_threads"},
+    "active_friends": {"name": "活跃客户(周期)", "unit": "人", "direction": 1,
+                       "caliber": "期内distinct客户(msg_daily_stats直查),非宽表日值求和"},
+    "active_rooms": {"name": "活跃群(日均)", "unit": "个", "direction": 1},
+    "new_customer_count": {"name": "新客(期末)", "unit": "人", "direction": 1,
+                           "caliber": "期末单日持有状态,非期内求和"},
+    "cooling_customer_count": {"name": "降温客户(期末)", "unit": "人", "direction": -1,
+                               "caliber": "距今天数口径(7-29天);频次基线口径二期"},
+    "dormant_customer_count": {"name": "沉睡客户(期末)", "unit": "人", "direction": -1,
+                               "caliber": "≥30天且历史≥5条"},
+    "reactivated_customer_count": {"name": "回流客户(期内)", "unit": "人", "direction": 1,
+                                   "caliber": "当日回流且前次间隔>30天,期内求和"},
+    "call_count": {"name": "通话数", "unit": "通", "direction": 1,
+                   "caliber": "语音通话(微信+WA),无消息渠道维度"},
+    "answered_rate": {"name": "接通率", "unit": "0-1", "direction": 1,
+                      "formula": "answered_call/call_count", "caliber": "接通=duration>0"},
+    "call_followup_rate": {"name": "通话后跟进率", "unit": "0-1", "direction": 1,
+                           "formula": "call_followup_count/answered_call",
+                           "caliber": "接通后24h内任一账号有1:1消息(含客户发来)"},
+    "active_share": {"name": "活跃客户占比", "unit": "0-1", "direction": 1,
+                     "formula": "期末active_friends/(期末active+cooling+dormant)",
+                     "caliber": "试算口径:期末单日存量"},
+}
+
+# 阈值全部为试算起点(v2 §0 决议:全默认+试算标记);type 三种:
+#   target      : floor..target 线性 0..100(方向已含在 target>floor)
+#   reverse     : ≤target_ms 100 分,≥floor_ms 0 分,中间线性降
+#   band        : 区间内 80..100,低于下限不评分(None),超上限不再加分
+DEFAULT_SCORE_CONFIG: dict = {
+    "version": "v1.0",
+    "name": "一期试算(3维可用)",
+    "normalization": "available_only_rescale",  # 可用维度 100/Σweight 再 ×100
+    "trial": True,
+    "sample_guards": {"min_threads": 30, "soft_threads": 10, "min_days": 5},
+    "grade_bounds": {"A": 90, "B": 80, "C": 70, "D": 60},  # 低于 D 线为 E
+    "dimensions": {
+        "customer": {"weight": 30, "name": "客户经营", "metrics": {
+            "active_share": {"type": "target", "floor": 0.20, "target": 0.60},
+        }},
+        "service": {"weight": 25, "name": "服务质量", "metrics": {
+            "reply_2h_rate": {"type": "target", "floor": 0.40, "target": 0.85},
+            "reply_24h_rate": {"type": "target", "floor": 0.75, "target": 0.97},
+            "fr_p90_ms": {"type": "reverse", "target_ms": 1_800_000,
+                          "floor_ms": 14_400_000},  # 30min..4h
+        }},
+        "action": {"weight": 20, "name": "行动执行",
+                   "status": "pending_data"},  # 批次E 接 followups/任务
+        "workload": {"weight": 15, "name": "有效负载", "metrics": {
+            "active_friends_band": {"type": "band", "metric": "active_friends",
+                                    "low": 5, "high": 80,
+                                    "basis": "period_distinct"},
+            "call_band": {"type": "band", "metric": "call_count",
+                          "low": 1, "high": 200, "basis": "period_total",
+                          "note": "通话低不扣分仅提示;band 得分下限 80"},
+        }},
+        "risk": {"weight": 10, "name": "合规风险",
+                 "status": "pending_data"},  # 批次E/三期接风险事件
+    },
+}
+
+
+def validate_config(config: dict) -> list[str]:
+    """配置校验:权重总和/结构/引用的 metric_code 有元数据。返回问题清单。"""
+    problems: list[str] = []
+    dims = config.get("dimensions", {})
+    total = sum(d.get("weight", 0) for d in dims.values())
+    if total != 100:
+        problems.append(f"维度权重总和须=100,当前 {total}")
+    for key, dim in dims.items():
+        if dim.get("status") == "pending_data":
+            continue
+        for code, spec in dim.get("metrics", {}).items():
+            src = spec.get("metric", code)
+            if src not in METRIC_DEFINITIONS:
+                problems.append(f"{key}.{code} 引用未定义指标 {src}")
+    return problems
+```
+
+- [ ] **Step 4: cli.py 加 `score-config` 子命令**
+
+parser（sensitive-scan 与 first-reply-facts 之间任意位置）：
+
+```python
+    p_score = sub.add_parser(
+        "score-config",
+        help="Seed the default score config (idempotent).",
+        description=(
+            "Insert DEFAULT_SCORE_CONFIG (v1.0, trial) into "
+            "employee_score_config as active. Skips if the version "
+            "already exists. Batch B."
+        ),
+    )
+```
+
+命令函数与分发（照 _cmd_daily_stats 惯例）：
+
+```python
+async def _seed_score_config(session) -> str | None:
+    """种子默认评分配置;已存在同版本返回 None(幂等)。纯会话函数可测。"""
+    from app.db.models import EmployeeScoreConfig
+    from app.management.metric_definitions import (
+        DEFAULT_SCORE_CONFIG,
+        validate_config,
+    )
+
+    problems = validate_config(DEFAULT_SCORE_CONFIG)
+    if problems:
+        raise ValueError(f"score config invalid: {problems}")
+    exists = (
+        await session.execute(
+            sa.select(EmployeeScoreConfig.id).where(
+                EmployeeScoreConfig.version == DEFAULT_SCORE_CONFIG["version"]
+            )
+        )
+    ).scalar_one_or_none()
+    if exists is not None:
+        return None
+    session.add(
+        EmployeeScoreConfig(
+            version=DEFAULT_SCORE_CONFIG["version"],
+            name=DEFAULT_SCORE_CONFIG["name"],
+            status="active",
+            config_json=DEFAULT_SCORE_CONFIG,
+            created_by="seed-cli",
+        )
+    )
+    await session.flush()
+    return DEFAULT_SCORE_CONFIG["version"]
+
+
+async def _cmd_score_config(args: argparse.Namespace) -> int:
+    settings = get_settings()
+    engine, session_maker = await _init_db(settings.db_url)
+    try:
+        async with session_maker() as session:
+            version = await _seed_score_config(session)
+            await session.commit()
+        print(f"[score-config] {'seeded ' + version if version else 'already present, skipped'}")
+        return 0
+    finally:
+        await engine.dispose()
+```
+
+（cli.py 头部补 `import sqlalchemy as sa` 若无。）
+
+- [ ] **Step 5: 测试通过 + 提交**
+
+```bash
+cd yunke-server && .venv/Scripts/python.exe -m pytest tests/test_management_scoring.py -v   # 5 passed
+cd yunke-server && .venv/Scripts/python.exe -m app.sync.cli score-config   # 真机种子一次
+git add yunke-server/app/management/ yunke-server/app/sync/cli.py yunke-server/tests/test_management_scoring.py
+git commit -m "feat(management): 指标元数据+试算评分配置v1.0+种子CLI——权重校验/幂等落库"
+```
+
+---
+
+### Task B1: 期聚合查询服务
+
+**Files:**
+- Create: `yunke-server/app/management/employee_metrics.py`
+- Test: `yunke-server/tests/test_management_period_metrics.py`
+
+核心函数（完整实现）：
+
+```python
+"""管理域期聚合查询(批次B)——评分/异常/employees API 的单一数据源。
+
+窗口:days=[start_day..end_day] 闭区间 yyyymmdd;上期=等长紧邻前窗;
+个人基线=紧邻当前窗之前的 28 天。所有查询走 (day, ...) 索引,不扫消息表
+(除 distinct 活跃客户走 msg_daily_stats friend 行)。
+"""
+from __future__ import annotations
+
+import datetime as dt
+from collections import namedtuple
+from zoneinfo import ZoneInfo
+
+import sqlalchemy as sa
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.db.models import (
+    EmployeeCallDaily,
+    EmployeeMetricDaily,
+    FirstReplyFact,
+    MsgDailyStats,
+    Staff,
+)
+from app.storage.staff_summary import account_map
+from app.storage.summary import day_bounds_ms
+
+_SH = ZoneInfo("Asia/Shanghai")
+
+PeriodMetrics = namedtuple("PeriodMetrics", [
+    "user_id", "days_with_data", "msg_sent", "msg_recv", "cust_threads",
+    "threads_answered", "fr_sum_ms", "fr_p50_ms", "fr_p90_ms",
+    "reply_2h_count", "reply_24h_count",
+    "active_friends",          # 期内 distinct(直查,非日值求和)
+    "active_rooms_avg",        # 日均
+    "new_customer", "cooling_customer", "dormant_customer",  # 期末单日存量
+    "reactivated_customer",    # 期内求和
+    "call_count", "call_seconds", "answered_call", "call_followup",
+])
+
+
+def _day_range(start: int, end: int) -> list[int]:
+    """闭区间日键列表(纯 Python,上海自然日语义由调用方保证)。"""
+    def _d(k): return dt.date(k // 10000, k // 100 % 100, k % 100)
+    def _k(d): return d.year * 10000 + d.month * 100 + d.day
+    out, cur = [], _d(start)
+    while cur <= _d(end):
+        out.append(_k(cur))
+        cur += dt.timedelta(days=1)
+    return out
+
+
+def prev_window(start: int, end: int) -> tuple[int, int]:
+    """等长紧邻前窗。"""
+    n = len(_day_range(start, end))
+    def _d(k): return dt.date(k // 10000, k // 100 % 100, k % 100)
+    def _k(d): return d.year * 10000 + d.month * 100 + d.day
+    pe = _d(start) - dt.timedelta(days=1)
+    ps = pe - dt.timedelta(days=n - 1)
+    return _k(ps), _k(pe)
+
+
+def baseline_window(start: int) -> tuple[int, int]:
+    """个人基线:紧邻当前窗之前的 28 天。"""
+    def _d(k): return dt.date(k // 10000, k // 100 % 100, k % 100)
+    def _k(d): return d.year * 10000 + d.month * 100 + d.day
+    be = _d(start) - dt.timedelta(days=1)
+    bs = be - dt.timedelta(days=27)
+    return _k(bs), _k(be)
+```
+
+`period_metrics(session, start, end, channel, user_ids=None) -> dict[str, PeriodMetrics]` 实现要点（写全代码进计划）：
+
+1. **宽表 SUM**（`WHERE day BETWEEN s AND e AND channel=? AND metric_version='v1' AND user_id IN (...)` GROUP BY user_id）：msg_sent/msg_recv/cust_threads/threads_answered/fr_sum_ms/active_rooms（SUM→avg=SUM/天数）、reactivated（SUM）、`days_with_data=COUNT(*)`；**期末存量**：另查 `day=(SELECT MAX(day)≤e 同 user/channel)` 的 new/cooling/dormant 行（ correlated 或两段查询——用 `sa.select(...).where(day<=end).order_by(day.desc())` per user 取首行，员工 41 人循环可接受；或一次查询取 (user, MAX(day)) 再 join）。
+2. **fact 分位与回复计数**（单条 SQL，窗口函数，双方言）：
+```python
+sub = (
+    sa.select(
+        FirstReplyFact.owner_account_id.label("owner"),
+        FirstReplyFact.fr_ms.label("fr"),
+        sa.func.row_number().over(
+            partition_by=FirstReplyFact.owner_account_id,   # 列表达式,非别名——MySQL 窗口规范不认 SELECT 别名
+            order_by=FirstReplyFact.fr_ms,
+        ).label("rn"),
+        sa.func.count().over(
+            partition_by=FirstReplyFact.owner_account_id
+        ).label("n"),
+    ).where(FirstReplyFact.day.between(start, end),
+            FirstReplyFact.channel == channel)
+    .subquery()
+)
+# 每 owner:rn=ceil(0.5*n) 行的 fr 即 p50;rn=ceil(0.9*n) 即 p90;
+# 回复计数:SUM(fr<=2h)/SUM(fr<=24h) 另用条件聚合直查(不用窗口)。
+```
+   owner→user 经 account_map(channel)。p50/p90 取最接近秩（`rn == (n+1)//2` 与 `rn == max(1, (9*n+9)//10)`——**用「最接近秩」公式并在测试里锁死**：ceil(q·n) 最近邻，与批次A `_percentile` 口径一致）。
+3. **reply 计数**：`SELECT owner, SUM(fr_ms<=7200000), SUM(fr_ms<=86400000) FROM first_reply_fact WHERE day BETWEEN ... GROUP BY owner`（MySQL 布尔求和；SQLite 同义 `SUM(CASE WHEN ...)`——用 case 写法双方言安全）。
+4. **distinct 活跃客户**：msg_daily_stats friend 行 in window → peer 集合按 account_map 归并到 user → len。
+5. **通话**：employee_call_daily SUM（无渠道维；channel 参数只影响消息侧——**通话四列在 channel 查询里也返回全渠道值，响应里标注**）。
+6. `team_median`：对每指标取全体 user 的中位数（scoring 层用）。
+7. **channel=all**：router 层把 "all" 翻译成 None 传入（照 analytics 惯例，哨兵字符串不进 SQL）；channel=None 时两条渠道的 account_map 合并、宽表/fact 查询去渠道过滤、分位与活跃跨渠道合并到同一 user。
+
+**测试**（seed 宽表/fact/通话行 + Staff/account，构造已知分位数集合断言 p50/p90 精确值、期末存量取 ≤e 最近行、distinct 活跃跨日去重、prev/baseline 窗口日期算术含月末）——完整测试代码进计划（约 6 个用例）。
+
+- [ ] Steps: 测试先失败 → 实现 → 通过 → 全量回归 → 提交
+  `feat(management): 期聚合查询——fact窗口函数精确分位/期末生命周期存量/distinct活跃/前窗基线窗口`
+
+---
+
+### Task B2: 评分引擎 scoring.py
+
+**Files:**
+- Create: `yunke-server/app/management/scoring.py`
+- Test: 追加 `tests/test_management_scoring.py`
+
+核心（完整代码进计划）：
+
+```python
+def normalize(spec: dict, value: float | None) -> float | None:
+    """单指标 0..100;样本不足/数据缺 → None(不评分,不默认 0/100)。"""
+    t = spec["type"]
+    if value is None:
+        return None
+    if t == "target":
+        if value <= spec["floor"]:
+            return 0.0
+        if value >= spec["target"]:
+            return 100.0
+        return (value - spec["floor"]) / (spec["target"] - spec["floor"]) * 100
+    if t == "reverse":
+        if value <= spec["target_ms"]:
+            return 100.0
+        if value >= spec["floor_ms"]:
+            return 0.0
+        return (spec["floor_ms"] - value) / (spec["floor_ms"] - spec["target_ms"]) * 100
+    if t == "band":
+        if value < spec["low"]:
+            return None  # 负载不足→不评分(样本保护语义)
+        return 100.0 if value <= spec["high"] else 80.0  # 超上限 80 不再加
+    raise ValueError(t)
+
+
+def score_employee(config, current: PeriodMetrics, baseline: PeriodMetrics | None,
+                   team: dict[str, float]) -> dict:
+    """返回 {total_score, grade, score_status, trial, dimensions{...},
+    metrics{code: {value, prev, baseline, median, sample_size,
+    sample_status, score, formula_note}}}。"""
+```
+
+规则（写死进测试）：
+- 周期值派生：`reply_2h_rate = reply_2h_count/cust_threads`（threads=0 → None）；`fr_p90_ms` 直取；`active_share` **分子=期末该渠道最近一行(≤end)的 active_friends，分母=同一行的 active_friends+cooling_customer+dormant_customer**（分母 0 → None；宽表无生命周期 active 存量列，active 以 active_friends 列充当）；band 用 active_friends 周期 distinct（B2 决议:抗单日噪声,与 B1 口径一致）与 call_count 总量。
+- 样本保护：`cust_threads < min_threads(30)` → 该 service/customer 指标 sample_status="insufficient"，不评分；soft(10)~min 之间 "low_confidence"（评分但标注）。
+- 维度分 = 各指标得分的均值（等权）；任一指标 None 时该指标剔除并按剩余归一；**全部 None → 维度 pending**。
+- 总分 = Σ(可用维度 weight×dim_score)/Σ(可用维度 weight)×100；可用=pending_data 以外且维度分非 None；全 None → score_status="insufficient_sample"（total None）。
+- grade 按 grade_bounds；insufficient → grade None + status。
+- `trial=True` 恒返（一期 3 维）。
+
+**测试**（≥8 用例，完整代码进计划）：target 边界（floor/target/中点 50）、reverse 两端与中间、band 三段、threads=0 → None 非 0、insufficient_sample 整员工、pending 维度不参与（100/70 归一后 A 线仍可达）、试算标记、全部指标有明细含四对比位。
+
+- [ ] Steps: TDD → 提交 `feat(management): 评分引擎——三类标准化/维度归一/样本保护/等级/完整明细`
+
+---
+
+### Task B3: 异常规则 anomalies.py
+
+**Files:**
+- Create: `yunke-server/app/management/anomalies.py`
+- Test: `yunke-server/tests/test_management_anomalies.py`
+
+4 条确定性规则（输入=period_metrics 当前+基线+团队中位数；输出=v1 §5.4 卡片列表，完整代码进计划）：
+
+| rule_code | 触发 | severity | drilldown |
+|---|---|---|---|
+| reply_p90_worsened | p90 > 基线p90×1.5 且样本≥soft；×2.5 升 critical | warning/critical | metric_code=first_reply_p90 |
+| reply_rate_dropped | reply_2h_rate < 基线×0.7 且当前≥soft 样本 | warning | metric_code=unreplied |
+| activity_drop | 日均 msg_total < 基线日均×0.5 且基线≥min_days | warning | 员工详情 |
+| workload_overload | active_friends 周期 distinct > band 上限 80 | warning | 员工详情 |
+
+卡片字段照 v1 §5.4 JSON（rule_code/severity/employee_user_id/title/current_value/baseline_value/unit/sample_size/**affected_count**/reason[纯数据事实]/drilldown/suggested_action——文案固定模板，不用 LLM）。`affected_count` 按规则定义：reply_p90_worsened 与 reply_rate_dropped=期内未回串数（cust_threads−threads_answered）；activity_drop=当前期活跃客户数；workload_overload=active_friends 日均。
+
+**测试**（≥6 用例）：每规则触发/不触发边界、基线 None 不触发、severity 升级阈值、卡片结构字段齐全。
+
+- [ ] Steps: TDD → 提交 `feat(management): 确定性异常规则×4——P90恶化/回复率骤降/活动骤降/过载`
+
+---
+
+### Task B4: 管理 API 6 端点
+
+**Files:**
+- Create: `yunke-server/app/api/routers/management.py`
+- Modify: `yunke-server/app/api/main.py`（import + include_router(management.router)）
+- Test: `yunke-server/tests/test_management_api.py`
+
+路由骨架（完整代码进计划，照 analytics 惯例）：
+
+```python
+router = APIRouter(prefix="/api/management", tags=["management"])
+SessionDep = Annotated[AsyncSession, Depends(get_session)]
+AllChannelParam = Annotated[Literal["all", "wechat", "whatsapp"], Query()]
+YmdParam = Annotated[int, Query(ge=20000101, le=29991231)]
+```
+
+| 端点 | 行为要点 |
+|---|---|
+| `GET /dashboard` | 参数 channel/start/end/compare(previous\|personal_baseline\|team_median,默认 previous)。组装：kpis（活跃客户/活跃员工/待回复[复用 analytics unreplied total]/通话量/生命周期期末分布）+ communication_trend（宽表按日 SUM msg+distinct friends 近 trend 天）+ service_trend（fr 日值 p50/p90 宽表列按日 + reply_2h_rate 派生）+ lifecycle（期末存量分布）+ dimension_summary（全员 3 维分布计数）+ anomalies（B3 全员）+ action_summary（复用 analytics action_counts）+ data_as_of（复用 health）。单次响应聚合，内部并发可用 asyncio.gather |
+| `GET /employees` | 参数 channel/start/end/view/keyword/status/sort_by/sort_order/page/page_size(≤100 默认 20)。行=staff 身份(name/is_on_job) + PeriodMetrics + 四对比 + score_employee 结果摘要(total/grade/sample_status/trial) + anomaly_count + anomaly_weight。默认排序=**anomaly_severity**（权重和 critical=2/warning=1 desc，同分再比 count desc——对应 v2 §6「按异常严重度排序」，非单纯计数）；keyword 匹配 staff.name/user_id |
+| `GET /employees/{user_id}` | 404 校验（staff 无此 user_id）；头部身份+账号清单(wechat/whatsapp account 表)+宽表总览+评分明细+异常+基线摘要 |
+| `GET /employees/{user_id}/metrics?section=` | section ∈ overview\|service\|customer\|workload\|calls（一期 5 个，v2 §6）；每 section 返回该域 PeriodMetrics 明细+四对比+trend（宽表按日序列） |
+| `GET /employees/{user_id}/drilldown?metric_code=&start=&end=&channel=&page=&page_size=` | **白名单**：`first_reply_p90|first_reply_p50`→fact 逐串明细（含 thread_end/reply ts/fr_ms+跳聊天参数 owner/talker）；`unreplied`→调 analytics unreplied(user 过滤)；`cooling_customers|dormant_customers`→customer 表 owner 归属+lifecycle 判定列清单；`call_followup`→phone_call 行清单。白名单外 422 |
+| `GET /metric-definitions` | METRIC_DEFINITIONS + DEFAULT_SCORE_CONFIG 摘要（权重/试算标记/样本门槛）+ 三方口径差异说明 |
+
+**API 测试**（完整代码进计划，make_client fixture，≥12 用例）：参数默认值/422（custom 缺参、跨度>366、metric_code 白名单外、page_size>100）/404（员工不存在）/响应结构关键字段（data_as_of、metric_version、sample_status、trial 标记）/employees 分页排序/dashboard 各段齐全/渠道过滤生效。
+
+- [ ] Steps: TDD → main.py 注册 → OpenAPI 冒烟（`/docs` 可见 6 端点）→ 全量回归 → 提交
+  `feat(management): 只读管理API六端点——dashboard/employees/detail/sections/drilldown白名单/指标定义`
+
+---
+
+### Task B5: 真机冒烟 + 性能初测 + 记录
+
+- [ ] 本地起后端（先 `docker stop yunke-backend-1 yunke-frontend-1` 若在跑；`cd yunke-server && .venv/Scripts/python.exe -m uvicorn app.api.main:app --port 8000` 后台）；
+- [ ] curl 六端点（带 token，从 .env API_TOKEN；无 token 模式则直接）真机各一次，记录响应体积与耗时（目标：dashboard p95≤1.5s、employees≤1.5s——v2 §9 性能线）；
+- [ ] 抽查：某回测员工（王云青 369D257E…）30 天窗 employees 行——P90/回复率/维度分人工合理性检查（对照核实文档对账数字）；
+- [ ] 结果（耗时表+抽查截图级数字）追加到批次A核实文档「批次B冒烟」小节；
+- [ ] 提交 `docs(management): 批次B真机冒烟——六端点耗时/回测员工抽查/记录`
+
+---
+
+## 批次B验收清单
+
+- [ ] `score-config` 种子幂等，配置过校验，v1.0 active；
+- [ ] 期聚合：p50/p90 精确分位（窗口函数）与期末存量口径有判别测试；
+- [ ] 评分：三类标准化边界/样本保护/100-70 归一/试算标记全锁测试；
+- [ ] 异常：4 规则触发边界 + 卡片结构完整；
+- [ ] 6 端点：OpenAPI 可见、参数校验 422/404 齐全、白名单生效、dict 返回含 data_as_of/metric_version/sample_status；
+- [ ] 全量测试绿（653 + 新增 ~30）；
+- [ ] 真机冒烟耗时达标并记录；
+- [ ] 未动批次A任何存储层代码（宽表/fact 生成零改动）。
+
+## 批次C-F
+
+批次C：前端（api/management.ts + useManagementFilters + components/management/* + ManagementDashboardView + 路由/导航「经营管理」分组）——批次B合入后出计划，消费真实 API 形态。D：员工总览/详情页。E：followups+快照（写端点+schemas）。F：调度接入（analytics_tick 第三步/full_sync 13-14 步/scheduler 镜像重建）+回测试运行。

docs/superpowers/plans/2026-09-09-management-console-batch-c-frontend-plan.md

@@ -0,0 +1,305 @@
+# 云客经营管理后台·批次C（前端导航+管理驾驶舱）实施计划
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** 交付经营管理后台的第一个可视化页面——管理驾驶舱（`/management/dashboard`）+「经营管理」导航分组；管理者 5 分钟看整体、异常两次点击进事实。
+
+**Architecture:** 前端纯增量：`api/management.ts`（六端点 typed client，契约=批次B终评冻结面）+ `composables/useManagementFilters.ts`（URL query 为真源）+ `components/management/` 六个组件 + `ManagementDashboardView.vue`。复用 useChart/api client/format utils/seq 守卫惯例；不引新 UI 框架、不引雷达图（维度分布用条形图）。依据 [v2 计划](./2026-09-08-yunke-management-console-implementation-v2.md) §4/§5/§7/§13 与批次B契约清单；员工总览/详情页是批次D。
+
+**Tech Stack:** Vue3 + TS + Element Plus + ECharts（useChart 按需已有 Line/Bar）+ vitest（若仓库已配）。
+
+---
+
+## 执行者必读
+
+1. **后端就绪**（本地 8000 已跑或按 DEPLOY 起）：六端点见 `/tmp` 之外的真实路径 `/api/management/*`；**契约以批次B终评清单为准**（None≠0；`scope.channel` 回显原值；drilldown 白名单六值；异常卡片 12 字段；`config_source=db`）。
+2. **前端惯例**：路由扁平 + `meta.title` + 登录守卫（public 才放行）；API 走 `getJson/requestJson`（client.ts 已带 Bearer+baseURL=/api）；图表用 `useChart`（容器稳定，不 v-if）；请求序号 seq 守卫防旧响应覆盖（DashboardView 现有模式照抄）；格式化放 `utils/format.ts` 不重复实现；el-select 空串 value 显示英文占位用 `'all'` 哨兵。
+3. **不做**：员工总览/详情页、辅导、快照（D/E 批次）；`/analytics/dashboard` 不重定向（并存过渡）；二期菜单不渲染不放空页。
+4. **验收基准**：v2 §5——5 分钟判总体；异常两次点击到事实；全部卡片显示数据截至与对比窗口；`npm run build` 过。
+5. 仓库有并行会话活动——`git status` 后只 add 自己文件；提交中文 conventional；master 直提。
+
+## 文件地图
+
+| 文件 | 职责 | 动作 |
+|---|---|---|
+| `yunkes/src/api/management.ts` | 六端点 typed client | 新建 |
+| `yunkes/src/composables/useManagementFilters.ts` | URL query ↔ 筛选（channel/start/end/compare + 预设窗） | 新建 |
+| `yunkes/src/components/management/DataAsOfBadge.vue` | 数据截至/版本/试算角标 | 新建 |
+| `yunkes/src/components/management/ManagementKpiCard.vue` | KPI 卡（主值+辅助+点击跳转） | 新建 |
+| `yunkes/src/components/management/ManagementFilterBar.vue` | 筛选栏（渠道/时间预设/自定义/口径入口按钮） | 新建 |
+| `yunkes/src/components/management/AnomalyList.vue` | 异常榜（severity 标签+数字+下钻事件） | 新建 |
+| `yunkes/src/components/management/MetricDrilldownDrawer.vue` | 下钻抽屉（drilldown 端点行清单+聊天跳转） | 新建 |
+| `yunkes/src/components/management/MetricDefsDrawer.vue` | 指标口径抽屉（metric-definitions 渲染） | 新建 |
+| `yunkes/src/views/management/ManagementDashboardView.vue` | 驾驶舱页 | 新建 |
+| `yunkes/src/router/index.ts` | /management/dashboard 路由 | 修改 |
+| `yunkes/src/layouts/MainLayout.vue` | 「经营管理」分组 | 修改 |
+
+---
+
+### Task C0: 后端契约补全——drilldown 行补 channel 字段
+
+**Files:** Modify `yunke-server/app/management/api_assembly.py` + `yunke-server/tests/test_management_api.py`
+
+批次B已提交但未部署，前端冻结前补齐（评审发现：fr_fact_rows/lifecycle_customers 的行无 channel 键，前端 channel=all 时 WA 行会跳错聊天路由）：
+1. `fr_fact_rows` 每行加 `channel`（SELECT 已有该列，透传即可）；
+2. `lifecycle_customers` 每行加 `channel`（c.channel 透传）；
+3. 测试断言补两行（drilldown p90 与 cooling/dormant 的响应行含 channel）。
+- [ ] `cd yunke-server && .venv/Scripts/python.exe -m pytest tests/test_management_api.py -q`（23 passed）+ 全量 -q
+- [ ] commit `fix(management): drilldown行补channel字段——前端聊天路由判渠道用(契约冻结前补齐)`
+
+### Task C1: api/management.ts（typed client）
+
+**Files:** Create `yunkes/src/api/management.ts`
+
+完整代码（契约=批次B as-built；先对照后端 router 响应键核对再落笔）：
+
+```typescript
+// 经营管理板块 API(批次C)。契约以批次B终评冻结面为准:
+// None≠0(无样本分位/率=null);scope.channel 回显原值;drilldown 白名单六值。
+import { getJson } from './client'
+import type { Channel } from './types'
+
+export type MgmtChannel = 'all' | Channel
+export type CompareMode = 'previous' | 'personal_baseline' | 'team_median'
+export type DrilldownCode =
+  | 'first_reply_p90' | 'first_reply_p50' | 'unreplied'
+  | 'cooling_customers' | 'dormant_customers' | 'call_followup'
+
+export interface MgmtScope { channel: MgmtChannel; start: number; end: number; compare?: CompareMode; view?: string; user_id?: string; metric_code?: string }
+export interface Kpis {
+  active_customers: number; active_employees: number
+  msg_total: number; cust_threads: number; threads_answered: number
+  call_count: number; call_seconds: number; answered_call: number
+  lifecycle: { new: number; cooling: number; dormant: number; reactivated: number }
+}
+export interface CommTrendPoint { day: number; msg_total: number; active_customers: number; call_cnt: number }
+export interface SvcTrendPoint { day: number; fr_p50_ms: number | null; fr_p90_ms: number | null; reply_2h_rate: number | null }
+export interface DimSummary { [dim: string]: { name: string; weight: number; scored_count: number; pending_count: number; insufficient_count: number; avg_score: number | null } }
+export interface AnomalyCard {
+  rule_code: string; severity: 'critical' | 'warning'; employee_user_id: string
+  title: string; current_value: number; baseline_value: number | null; unit: string
+  sample_size: number; affected_count: number; reason: string
+  drilldown: { type: string; query: { metric_code?: string; user_id?: string } }
+  suggested_action: string
+}
+export interface DashboardResp {
+  scope: MgmtScope; data_as_of: number | null; metric_version: string; config_source: 'db' | 'default'
+  kpis: Kpis
+  communication_trend: CommTrendPoint[]
+  service_trend: SvcTrendPoint[]
+  lifecycle: Kpis['lifecycle']
+  dimension_summary: DimSummary
+  anomalies: AnomalyCard[]
+  action_summary: { unreplied_2h: number; churn_real_30d: number; sensitive_pending: number }
+}
+export interface EmployeeRow {
+  user_id: string; name: string | null; is_on_job: boolean | null
+  metrics: Record<string, number | null>
+  comparisons: Record<string, { current: number | null; prev: number | null; baseline: number | null; median: number | null }>
+  score: { total_score: number | null; grade: string | null; score_status: string; trial: boolean; dimensions: Record<string, { score: number | null; status: string }> }
+  anomaly_count: number; anomaly_weight: number
+}
+export interface EmployeesResp { total: number; page: number; page_size: number; rows: EmployeeRow[]; scope: MgmtScope; data_as_of: number | null; metric_version: string; config_source: 'db' | 'default' }
+export interface FactDrillRow { day: number; channel: string; owner_account_id: string; peer_id: string; thread_end_ts: number; reply_ts: number; fr_ms: number }
+export interface LifecycleDrillRow { friend_id: string; channel: string; nickname: string | null; last_day: number; state: string }
+export interface CallDrillRow { call_id: string; channel: string; call_number: string | null; start_call_time: number; call_duration: number }
+export interface DrilldownResp { total: number; items: Record<string, unknown>[]; note?: string; truncated?: boolean; summary?: Record<string, number> }
+export interface MetricDefsResp {
+  definitions: Record<string, { name: string; unit: string; direction: number; caliber?: string; formula?: string }>
+  score_config: { version: string; name: string; trial: boolean; normalization: string; sample_guards: Record<string, number>; grade_bounds: Record<string, number>; dimensions: Record<string, { name: string; weight: number; status?: string }> }
+  caliber_notes: string
+  config_source: 'db' | 'default'
+}
+
+export const getDashboard = (channel: MgmtChannel, start: number, end: number, compare: CompareMode = 'previous') =>
+  getJson<DashboardResp>('/management/dashboard', { channel, start, end, compare })
+export const getEmployees = (params: Record<string, unknown>) =>
+  getJson<EmployeesResp>('/management/employees', params)
+export const getEmployeeDrilldown = (userId: string, metricCode: DrilldownCode, start: number, end: number, channel: MgmtChannel, page = 1, pageSize = 20) =>
+  getJson<DrilldownResp>(`/management/employees/${userId}/drilldown`, { metric_code: metricCode, start, end, channel, page, page_size: pageSize })
+export const getMetricDefs = () => getJson<MetricDefsResp>('/management/metric-definitions')
+```
+
+（员工详情/sections 两个端点的 client 函数批次D 再加——本期页面不消费，YAGNI；本期 client 为四函数。）
+
+- [ ] 步骤：写文件 → `cd yunkes && npx vue-tsc --noEmit`（或 build）类型过 → 后端（8000，dev 5173 的 /api 代理已指向它）冒烟一次 getDashboard 类型与真实响应吻合（console 对比关键字段）→ commit `feat(management): 前端API client——管理端点typed契约(批次B冻结面)`
+
+### Task C2: useManagementFilters composable
+
+**Files:** Create `yunkes/src/composables/useManagementFilters.ts`（+ vitest 若仓库已配测试脚本，先 `grep '"test"' yunkes/package.json` 确认）
+
+完整代码：
+
+```typescript
+// 管理页统一筛选(URL query 为真源——刷新/分享保持)。批次C:驾驶舱用;
+// 批次D 员工页复用(view 等额外参数由页面自行挂 query)。
+import { computed, watch } from 'vue'
+import { useRoute, useRouter } from 'vue-router'
+
+export type Preset = 'last7' | 'last30' | 'thisMonth' | 'lastMonth' | 'custom'
+export const CHANNELS = [
+  { value: 'all', label: '全部渠道' },
+  { value: 'wechat', label: '微信' },
+  { value: 'whatsapp', label: 'WhatsApp' },
+] as const
+
+function ymd(d: Date): number { return d.getFullYear() * 10000 + (d.getMonth() + 1) * 100 + d.getDate() }
+function addDays(d: Date, n: number): Date { const x = new Date(d); x.setDate(x.getDate() + n); return x }
+
+/** 预设 → [start,end] yyyymmdd(上海自然日由本地时区近似——与后端一致的公历日)。 */
+export function presetRange(p: Preset, today = new Date()): { start: number; end: number } {
+  const t0 = new Date(today.getFullYear(), today.getMonth(), today.getDate())
+  switch (p) {
+    case 'last7': return { start: ymd(addDays(t0, -6)), end: ymd(t0) }
+    case 'last30': return { start: ymd(addDays(t0, -29)), end: ymd(t0) }
+    case 'thisMonth': return { start: ymd(new Date(t0.getFullYear(), t0.getMonth(), 1)), end: ymd(t0) }
+    case 'lastMonth': {
+      const first = new Date(t0.getFullYear(), t0.getMonth() - 1, 1)
+      const last = new Date(t0.getFullYear(), t0.getMonth(), 0)
+      return { start: ymd(first), end: ymd(last) }
+    }
+  }
+  // custom 由调用方直传
+  return { start: ymd(t0), end: ymd(t0) }
+}
+
+export function useManagementFilters() {
+  const route = useRoute()
+  const router = useRouter()
+
+  const channel = computed<'all' | 'wechat' | 'whatsapp'>(() => {
+    const v = route.query.channel
+    return v === 'wechat' || v === 'whatsapp' ? v : 'all'
+  })
+  const start = computed(() => {
+    const v = Number(route.query.start)
+    return Number.isFinite(v) && v >= 20000101 ? v : presetRange('last30').start
+  })
+  const end = computed(() => {
+    const v = Number(route.query.end)
+    return Number.isFinite(v) && v >= 20000101 ? v : presetRange('last30').end
+  })
+  const compare = computed(() => {
+    const v = route.query.compare
+    return v === 'personal_baseline' || v === 'team_median' ? v : 'previous'
+  })
+
+  function apply(patch: Record<string, string | number | undefined>) {
+    const q: Record<string, string> = {}
+    for (const [k, v] of Object.entries({ ...route.query, ...patch })) {
+      if (v !== undefined && v !== null && v !== '') q[k] = String(v)
+    }
+    router.replace({ query: q })
+  }
+
+  // 预设切换:清掉 start/end 让默认值生效,custom 则带具体日期
+  function applyPreset(p: Preset, custom?: { start: number; end: number }) {
+    if (p === 'custom' && custom) apply({ start: custom.start, end: custom.end })
+    else apply({ start: undefined, end: undefined })
+  }
+
+  return { channel, start, end, compare, apply, applyPreset, presetRange }
+}
+```
+
+- [ ] vitest（若已配）：presetRange 五预设的日期算术（含月末/跨月）+ query 缺省回退 last30 + apply 写回 query。未配则手测并在报告注明。
+- [ ] commit `feat(management): useManagementFilters——URL query 真源/预设窗/渠道哨兵`
+
+### Task C3: 六个基础组件
+
+**Files:** Create `components/management/` 下六件。规格（完整 SFC 代码进实施，要点钉死）：
+
+1. **DataAsOfBadge**：props `{ dataAsOf: number | null; metricVersion?: string; trial?: boolean; configSource?: string }`；渲染 el-tag 组：数据截至（`data_as_of` ms→`YYYY-MM-DD HH:mm`，null 显示「无数据」灰 tag）+ 指标版本 + 试算（warning 色，trial=true 才显示）。格式化用 utils/format.ts 现有函数，无则组件内小 helper。
+2. **ManagementKpiCard**：props `{ label: string; value: number | null; unit?: string; hint?: string; to?: string }`；主值大字（null 显示 `--`），hint 小字，有 to 则整卡 clickable `router.push`。不做趋势箭头（对比值批次D 表格里呈现）。
+3. **ManagementFilterBar**：props modelValue 透传 filters composable 的值 + `@apply`；内容：el-radio-group 渠道（CHANNELS）+ el-select 预设（四预设+自定义）+ 自定义时 el-date-picker type=daterange（value-format YYYYMMDD 字符串转 number）+「指标口径」文字按钮（emit open-defs）+ 插槽放 DataAsOfBadge。改即 apply（防抖 300ms 不需要——change 事件天然低频）。
+4. **AnomalyList**：props `{ anomalies: AnomalyCard[] }`；el-table 或列表卡片：severity（critical=红 danger tag「严重」/warning=橙 warning tag「关注」）、title、current vs baseline（unit 感知格式化：ms→时长/0-1→%/其他千分位）、sample_size、affected_count、suggested_action（灰小字）；行 click → emit `drill(card)`。空态「暂无异常」。
+5. **MetricDrilldownDrawer**：props `{ userId: string; card: AnomalyCard | null; start: number; end: number; channel: MgmtChannel }`（v-model:visible）；打开时按 card.drilldown.query.metric_code 调 getEmployeeDrilldown：
+   - `first_reply_p90/p50` → 表格：客户(peer_id)/串末条时间/回复时间/首响时长（fr_ms 降序已由后端）；行点击跳聊天：`/staff-chat/{owner_account_id}/single/{peer_id}`（channel=whatsapp 时 `/chat/whatsapp/{owner}/{peer}`）。
+   - `unreplied` → 表格 peer/等待时长/预览；note/truncated 提示。
+   - `cooling/dormant_customers` → 表格 客户/最后互动日/状态；行点击跳该客户聊天（同上映射）。
+   - `call_followup` → 表格 通话（时间/号码/时长）+ summary 卡。
+   分页 el-pagination（后端分页）；员工姓名/标题显示 card.employee_user_id 对应名字由父传（dashboard anomalies 无 name——显示 user_id 短版即可，批次D 带名字）。
+6. **MetricDefsDrawer**：v-model:visible；打开调 getMetricDefs；el-collapse 按 维度/单指标 两组渲染：每指标 name+unit+direction（越大越好/越小越好）+formula+caliber；顶部 score_config 摘要（版本/试算标记/样本门槛/各维度权重与 pending 状态）+ caliber_notes 段落。
+
+- [ ] 步骤：六组件逐个写 + vue-tsc 过 → 冒烟渲染（C5 页面里真用）→ commit `feat(management): 驾驶舱六组件——KPI卡/筛选栏/异常榜/下钻抽屉/口径抽屉/数据截至角标`
+
+### Task C4: 路由 + 导航
+
+- router/index.ts 在 analytics 四页之后加：
+
+```typescript
+  {
+    // 经营管理板块(批次C):驾驶舱;员工分析/考核快照批次D/E再加
+    path: '/management/dashboard',
+    name: 'management-dashboard',
+    component: () => import('@/views/management/ManagementDashboardView.vue'),
+    meta: { title: '管理驾驶舱' },
+  },
+```
+
+- MainLayout「数据分析」el-sub-menu 之前加「经营管理」分组（单项：管理驾驶舱 → goPlain('/management/dashboard')）——分组在最上（管理优先级高于查看）。
+- 验证：登录态点菜单进页面、刷新保持、activeMenu 高亮正确。
+
+- [ ] commit `feat(management): 经营管理导航分组+驾驶舱路由`
+
+### Task C5: ManagementDashboardView
+
+**Files:** Create `yunkes/src/views/management/ManagementDashboardView.vue`
+
+结构（完整 SFC 进实施，要点钉死）：
+
+```text
+<ManagementFilterBar>（含 DataAsOfBadge + 口径按钮）
+六个 KPI 卡（el-row/gutter，1366px 两行三卡）:
+  活跃客户(kpis.active_customers,hint=串/被回)→无跳转(批次D员工页)
+  活跃员工(kpis.active_employees,hint=期内有数据天数>0 口径)
+  消息量(msg_total,hint=1:1口径·与数据看板口径不同)
+  待回复(action_summary.unreplied_2h,红点>0)→/analytics/unreplied
+  即将流失(action_summary.churn_real_30d)→/analytics/churn
+  风险待处理(action_summary.sensitive_pending)→/analytics/sensitive
+双图表(el-row 两列,useChart×2):
+  客户沟通趋势:Line msg_total + Bar call_cnt 双 y 轴(x=day)
+  服务质量趋势:双 y 轴——左轴 ms(Line fr_p50_ms/fr_p90_ms,tooltip 时长格式化)、
+  右轴 0-1(Line reply_2h_rate,%)——不注明双轴则率线贴底
+  ——图内空数据/None 点处理:reply_2h_rate null 断点(connectNulls=false)
+双条形图(el-row 两列):
+  生命周期分布:Bar new/cooling/dormant/reactivated 四类
+  员工维度分布:Bar dimension_summary 三维 avg_score(0-100)+pending 数 tooltip
+异常榜(AnomalyList @drill → MetricDrilldownDrawer)
+seq 守卫:filters 变化 → seq++ → 请求 → 回来校验 seq 才渲染(照 DashboardView 模式)
+loading:el-skeleton 首屏;错误:el-alert + 重试按钮(保留上次数据)
+```
+
+要点：
+- `watch([channel, start, end, compare], load)`；`onMounted(load)`；
+- day 轴 `20260810`→`08-10` 短格式；
+- **共享格式化**：把 DashboardView 里的 `fmtFr`(ms→时长)/`fmtPct`(0-1→%) 提升为 `utils/format.ts` 的 `formatMsDuration`/`formatRatio`（AnomalyList/抽屉/图表 tooltip 三处消费，不复制第三份）；
+- 异常榜点卡片 → drawer（metric_code 白名单外 type=employee 的卡片——activity_drop/overload 无 drilldown 端点，drawer 显示「员工分析批次D上线」占位说明——**两类 drilldown.type=employee 的卡片点击行为：显示 el-empty 占位**）；
+- 试算角标常显（config_source 透传）。
+
+- [ ] 步骤：写页面 → `npm run build` 过 → 本地前后端真机走查（起 8000 后端 + `npm run dev` 5173，Playwright 或手动）：六卡有数、双图渲染、异常卡点开抽屉、抽屉行跳聊天、口径抽屉渲染、刷新 URL 保持、1366px 布局不塌 → commit `feat(management): 管理驾驶舱页——KPI/双趋势/生命周期/维度分布/异常两次点击到事实`
+
+### Task C6: 收尾验收
+
+- [ ] `cd yunkes && npm run build`（0 error）；
+- [ ] `npm run test --silent`（若配了 vitest）或记录未配；
+- [ ] 验收清单核对（v2 §5.3/§19.1 驾驶舱子集）：5 分钟判总体 ✓/异常两次点击进事实 ✓/口径入口 ✓/数据截至+对比窗口显示 ✓/渠道筛选 ✓/URL 保持 ✓/试算标记 ✓/空态与错误态 ✓；
+- [ ] 全量后端测试仍绿（前端不动后端，确认无意外）；
+- [ ] commit（若剩零散修正）。
+
+---
+
+## 批次C验收清单
+
+- [ ] 「经营管理」分组出现且仅含管理驾驶舱；
+- [ ] 六 KPI 卡数字与后端响应一致（抽查待回复/风险与 analytics 页对得上）；
+- [ ] 双趋势图渲染 30 点、None 断点正确；
+- [ ] 异常卡 critical 红标在前；点击 metric 类卡片→抽屉→行→聊天定位（两次点击到事实）；
+- [ ] employee 类异常卡占位不报错；
+- [ ] 口径抽屉含试算标记与三方口径差异说明；
+- [ ] URL query 刷新/分享保持筛选；
+- [ ] `npm run build` 过；后端 722 测试不受影响。
+
+## 批次D-F
+
+D：员工总览+详情页（消费 employees/detail/sections 端点+指标解释抽屉）；E：辅导闭环+考核快照（写端点）；F：调度接入+dashboard 性能修复（unreplied 索引）+部署上线。

docs/superpowers/plans/2026-09-10-management-console-batch-d-employees-plan.md

@@ -0,0 +1,172 @@
+# 云客经营管理后台·批次D（员工总览+员工详情）实施计划
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** 补上管理闭环最大断点——员工总览（41 人多维一张表）与员工详情（五维/页签/四对比/事实下钻），打通「异常→员工全景→事实」链路；附带驾驶舱 KPI 环比与时间预设补全（体验级小项）。
+
+**Architecture:** 纯前端为主（消费批次B已就绪的 employees/detail/metrics sections/drilldown 端点）+ 两处小后端增强（dashboard kpis 加 prev 块；无新端点）。新页 `EmployeeAnalyticsView`/`EmployeeAnalyticsDetailView` + 对比抽屉；复用 C3 六组件（FilterBar/DataAsOfBadge/AnomalyList/MetricDrilldownDrawer/MetricDefsDrawer）与 useManagementFilters。依据 [v2 计划](./2026-09-08-yunke-management-console-implementation-v2.md) §6/§7/§13 + 批次B契约清单。
+
+**Tech Stack:** 同批次C（Vue3+TS+Element Plus+useChart+vitest）；后端 FastAPI 小改。
+
+---
+
+## 执行者必读
+
+1. **消费的端点 as-built 形态**（写 client 前已核对 management.py:321-443）：
+   - `GET /employees`（行结构见批次C client 的 EmployeeRow——已含 metrics/comparisons/score 摘要/anomaly_count/weight）；
+   - `GET /employees/{id}`：`{user_id,name,is_on_job,accounts[{channel,account_id,nick_name,user_name}],metrics(22字段dict 含 user_id 键),score{total_score,grade,score_status,trial,dimensions{name,weight,score,status,metrics{code:{value,score,sample_size,sample_status,formula_note}}},metrics_detail{code:{value,prev,baseline,median,sample_size,sample_status,score,unit,name}}},anomalies[],prev(dict|null),baseline(dict|null),scope,data_as_of,metric_version,config_source}`；
+   - `GET /employees/{id}/metrics?section=`：`{section,metrics(该域字段dict),trend[{day,cols...}](无数据日计数0/分位None),comparisons(源指标名键),scope,data_as_of,metric_version}`；
+   - drilldown/metric-definitions 已有 client。
+2. **前端惯例**同批次C必读（seq 守卫/useChart/URL query/csvExport.ts 全量翻页+中文 BOM/命名路由跳转）。
+3. **不做**：辅导/快照（E）；员工对比不新开 API（勾选 2-5 行客户端拼数据）；「指标解释抽屉」= 复用 MetricDefsDrawer（点击列头 ? 图标打开）——不做每指标单独解释面板（v1 §6.5 的完整版二期）。
+4. 仓库并行会话照旧；中文 conventional 提交；master 直提。
+
+## 文件地图
+
+| 文件 | 动作 |
+|---|---|
+| `yunkes/src/api/management.ts` | 补 getEmployeeDetail/getEmployeeMetrics + types（D0） |
+| `yunkes/src/composables/useManagementFilters.ts` | 预设补 今日/昨日/本周/上周（D0） |
+| `yunkes/src/views/management/EmployeeAnalyticsView.vue` | 新建（D1） |
+| `yunkes/src/components/management/EmployeeCompareDrawer.vue` | 新建（D1，对比抽屉） |
+| `yunkes/src/views/management/EmployeeAnalyticsDetailView.vue` | 新建（D2） |
+| `yunkes/src/router/index.ts` + `MainLayout.vue` | 两路由+两菜单（D1/D2 各自） |
+| `yunke-server/app/api/routers/management.py` + `api_assembly.py` | dashboard kpis 加 prev 块（D3） |
+| `yunkes/src/components/management/ManagementKpiCard.vue` + `AnomalyList.vue` + 驾驶舱页 | delta 显示 + 员工跳详情（D3） |
+
+---
+
+### Task D0: client 补全 + 预设扩展
+
+- [ ] `api/management.ts` 追加：
+
+```typescript
+export interface EmployeeAccount { channel: string; account_id: string; nick_name: string | null; user_name: string | null }
+export interface ScoreMetricDetail { value: number | null; prev: number | null; baseline: number | null; median: number | null; sample_size: number; sample_status: string; score: number | null; unit: string; name: string }
+// formula_note 在 dimensions[dim].metrics[code] 上（scoring.py 维度级明细），不在 metrics_detail
+export interface EmployeeDetailResp {
+  user_id: string; name: string | null; is_on_job: boolean | null
+  accounts: EmployeeAccount[]
+  metrics: Record<string, number | string | null>
+  score: {
+    total_score: number | null; grade: string | null; score_status: string; trial: boolean
+    dimensions: Record<string, { name: string; weight: number; score: number | null; status: string; metrics?: Record<string, { value: number | null; score: number | null; sample_size: number; sample_status: string; formula_note?: string }> }>
+    metrics_detail: Record<string, ScoreMetricDetail>
+  }
+  anomalies: AnomalyCard[]
+  prev: Record<string, number | string | null> | null
+  baseline: Record<string, number | string | null> | null
+  scope: MgmtScope; data_as_of: number | null; metric_version: string; config_source: 'db' | 'default'
+}
+export interface SectionResp {
+  section: string; metrics: Record<string, number | null>
+  trend: Record<string, number | null>[]
+  comparisons: Record<string, { current: number | null; prev: number | null; baseline: number | null; median: number | null }>
+  scope: MgmtScope; data_as_of: number | null; metric_version: string
+}
+export type MetricsSection = 'overview' | 'service' | 'customer' | 'workload' | 'calls'
+export const getEmployeeDetail = (userId: string, channel: MgmtChannel, start: number, end: number) =>
+  getJson<EmployeeDetailResp>(`/management/employees/${userId}`, { channel, start, end })
+export const getEmployeeMetrics = (userId: string, section: MetricsSection, channel: MgmtChannel, start: number, end: number) =>
+  getJson<SectionResp>(`/management/employees/${userId}/metrics`, { section, channel, start, end })
+```
+
+（写入前 curl 真机抽查 detail 响应键核对——同批次C C1 惯例，以真实响应为准修。）
+
+- [ ] `useManagementFilters.ts` 预设补：`Preset` 加 `'today' | 'yesterday' | 'thisWeek' | 'lastWeek'`；`presetRange` 四分支（today=当天单日窗；yesterday=昨日单日；thisWeek=本周一..今天；lastWeek=上周一..周日，**周一为一周起点**）；vitest 补 5 例（today/yesterday/thisWeek 周中+周一/lastWeek 跨月）。FilterBar 的预设选项组同步加（el-select options），分组显示：常用（今日/昨日/近7/近30）/日历（本周/上周/本月/上月）/自定义。
+- [ ] vue-tsc + `npm run test`（23+ 过）+ commit `feat(management): client补员工详情/分段接口+时间预设补今日昨日本周上周`
+
+### Task D1: 员工总览页
+
+**Files:** Create `EmployeeAnalyticsView.vue` + `EmployeeCompareDrawer.vue`；改 router（`/management/employees`）+ MainLayout（管理驾驶舱下加「员工分析」菜单项）。
+
+**页面结构**：
+
+```text
+ManagementFilterBar（复用；compare 选择器在此页透出——el-select 对比方式：上期/个人基线/团队中位数→apply({compare})）
+工具行：keyword el-input(placeholder 姓名/ID搜索) | status el-select(全部/在职/离线) | 视图 el-radio-group×4
+  （management=概览/workload=负载/service=服务/customer=客户经营——切换列组）| 指标口径按钮 | 导出 CSV | DataAsOfBadge
+主表 el-table（服务端排序 sort-change→query；行选择框多选 2-5 人→「对比」按钮开抽屉）：
+  固定列：姓名(链接进详情)+ID 小字、在职 tag
+  management 视图列：综合分(total_score+grade tag+trial*)、异常(anomaly_count 红数字+weight)、活跃客户、消息量、串/被回、维度三列(customer/service/workload score 各 0-100 或「--」)
+  workload 视图列：活跃客户、活跃群(日均)、消息收/发、通话量/秒、串
+  service 视图列：首响P50/P90(formatMsDuration)、2h回复率、24h回复率(formatRatio)、被回/串
+  customer 视图列：新客/降温/沉睡/回流(期末+期内注)、活跃占比
+  列头 ? 图标→打开 MetricDefsDrawer（复用）
+  空数据/样本不足单元格显示「--」灰字（sample_status=insufficient 时 total 亦然）
+分页 el-pagination（服务端 page/page_size 20；total）
+```
+
+**行为**：query 真源（view/keyword/status/sort_by/sort_order/page 全进 URL）；seq 守卫；**服务端排序仅四列**（后端 sort_by 白名单：anomaly_severity[默认]/total_score/active_friends/cust_threads——其余列头不显示排序箭头，tooltip「该列不支持服务端排序」）；`sort_by=total_score` 时 null 排最后由后端保证；compare 参数仅客户端显示态（employees 端点无此参数，行恒带全部四对比值）；**CSV**：扩展 `utils/csvExport.ts` 支持可选前置注释行（`exportListToCsv(..., preamble?: string[])`——含口径说明如「1:1口径·窗口 20260810-20260908·试算」）+ fetchPage 适配器（/employees 返回 `{rows,total}`，适配为 csvExport 期望的 `{items,total}`），导出当前视图列全量翻页。
+
+**EmployeeCompareDrawer**：props `{ rows: EmployeeRow[] }`（勾选行已有数据，不另发请求）；内容：五维分对比条（3 可用维度每人一行，横向 bar 0-100）+ 关键指标表（活跃客户/P90/2h率/异常数 每人一列）+ 顶部说明「同口径同时窗对比，不产生优劣结论」；>5 人禁开。
+
+**路由/菜单**：
+
+```typescript
+  { path: '/management/employees', name: 'management-employees',
+    component: () => import('@/views/management/EmployeeAnalyticsView.vue'),
+    meta: { title: '员工分析' } },
+```
+
+- [ ] vue-tsc/test/build + 真机初查（表格渲染 41 人/切视图列变/排序翻页/keyword/CSV 打开内容对）+ commit `feat(management): 员工总览页——四视图/服务端排序分页/对比抽屉/CSV导出`
+
+### Task D2: 员工详情页
+
+**Files:** Create `EmployeeAnalyticsDetailView.vue`；router 加 `/management/employees/:userId`（props:true；**activeMenu 需高亮父菜单「员工分析」**——MainLayout 的 el-menu :default-active 绑定的是路径，嵌套路由时用 route.meta 或 watch 设 index——看 MainLayout 现有 active 处理方式，最简方案：菜单 index 用路径匹配 + 详情页 route path 前缀匹配高亮，若现结构不支持则 meta.activeMenu='/management/employees' 并在 el-menu :default-active 计算）。
+
+**页面结构**：
+
+```text
+头部卡：姓名(+在职 tag)+ID | 账号清单(渠道 tag+account_id+昵称,点击跳 staff-chat/通讯录按渠道)
+  | 本期试算分大数字+grade tag+score_status(insufficient 时灰注「样本不足·不参与考核」)+trial*
+  | DataAsOfBadge | 返回列表链接
+五维条（v1 §7.2 概览的核心）:横向五条 bar——3 可用维度实分数值,action/risk 灰「待数据」占位
+  (ScoreBreakdown 简版:直接在页内画,不新建组件,el-progress/自定义 div)
+el-tabs 五页签(懒加载:激活才调 getEmployeeMetrics):
+  概览: 六数卡取自**detail.metrics**(msg/活跃/串/通话——section 端点字段有限,期值以 detail 为准)
+    + 四对比小表(comparisons 直渲染,源指标名行)
+  服务质量: 数卡 P50/P90 + 2h/24h回复率(**客户端从 metrics.reply_2h_count/cust_threads 派生,
+    与 derive_metrics 同式**——section 趋势无每日率序列) + 趋势图=**首响 P50/P90 双线(ms 轴)
+    ±串数(次轴可选)**——不做率右轴(员工级无每日率数据,率的团队级序列在驾驶舱)
+  客户经营: 期末四态数卡(取自 detail.metrics) + 降温/沉睡下钻按钮(→DrilldownDrawer lifecycle 分支)
+  工作负载: 数卡取 detail.metrics(收发/活跃客户/群/通话量) + 趋势图用 section=workload 的
+    active_friends/active_rooms 双线(trend 列为日值 active_rooms)
+  通话: 通话四数(detail.metrics) + call_followup 下钻按钮
+  **页签下钻按钮与 MetricDrilldownDrawer 的衔接**:抽屉是 card 驱动——按钮合成最小伪卡片
+    `{title:'首响P90明细', drilldown:{type:'metric',query:{metric_code:'first_reply_p90',user_id}}}` 传入
+异常区:AnomalyList(复用,@drill→MetricDrilldownDrawer 复用)
+评分明细折叠面板(el-collapse「评分怎么算出来的」): metrics_detail 表(code/名称/当前/上期/基线/中位/样本/得分)
+  + prev/baseline 原始 PeriodMetrics 两个 JSON 折叠(调试用,灰字注明)
+```
+
+**行为**：query 真源（channel/start/end/compare/section 进 URL，页签切换 replace）；seq 守卫每页签独立（切页签取消旧渲染）；404 员工→el-result 错误页+返回链接；「创建辅导记录」按钮**占位禁用**（tooltip「批次E上线」）。
+
+- [ ] vue-tsc/test/build + 真机初查（王云青详情：五维条/五页签懒加载/异常/评分明细展开/账号跳聊天）+ commit `feat(management): 员工详情页——五维条/五页签懒加载/四对比/评分明细/事实下钻复用`
+
+### Task D3: 驾驶舱 KPI 环比 + 异常跳员工
+
+**后端**（`management.py` dashboard + `api_assembly.py`）：①dashboard 端点 kpis 加 `prev_kpis` 块（active_customers/active_employees/msg_total/cust_threads——dashboard 走 assemble_employees(with_prev=False)，需加一次 prev 窗 period_metrics 全员调用，B5 实测三窗合计 ~0.3s，加一窗 +0.1s 量级）+ `msg_delta`（(cur-prev)/prev，prev=0→null）。lifecycle/通话不加环比（期末/全渠道口径环比意义弱，注明）。②**异常卡补 `employee_name`**（assemble_employees 手里已有全员 name——组装 anomalies 时带上，一行）；同步 AnomalyCard type。测试补：dashboard 响应含 prev_kpis 且数字=prev 窗聚合 + anomalies[0].employee_name 非空。
+**前端**：KpiCard 加 `delta?: number | null` prop（↑绿↓红，方向语义由调用方定——涨=好传正绿；不传不显示）；驾驶舱三卡接 delta（活跃客户/活跃员工/消息量）；AnomalyList 的 title 下加员工行（`employee_name` 链接→`/management/employees/{user_id}`）+ 新增 `showEmployee?: boolean` prop（默认 true；D2 员工详情页复用时传 false 免自链接）。
+- [ ] 后端 pytest（test_management_api.py 补 prev_kpis 断言）+ 前端走查三卡箭头/异常跳员工 + commit `feat(management): 驾驶舱KPI环比(prev_kpis+delta箭头)+异常卡跳员工详情`
+
+### Task D4: 真机走查 + 验收
+
+- [ ] 全链路走查（Playwright）：驾驶舱→异常卡→**员工详情**（新链路！）→页签→下钻→聊天；员工总览→对比抽屉→CSV；1366px；刷新保持；
+- [ ] 验收对照（v1 §19.1 员工子集）：能查看所有员工多维状态 ✓/任一分数展开为指标公式样本事实 ✓（评分明细面板）/四对比 ✓/样本不足不评分显示 ✓/异常两次点击进事实 ✓/默认排序非总分榜 ✓；
+- [ ] 四门禁（vue-tsc/vitest/build/后端 pytest）；
+- [ ] commit 收尾零散 + 走查记录追加核实文档「批次D走查」小节。
+
+---
+
+## 批次D验收清单
+
+- [ ] 员工总览：41 人四视图/服务端排序分页/keyword/对比 2-5 人/CSV 含口径注释；
+- [ ] 员工详情：五维条 3+2 占位/五页签懒加载/四对比/评分明细可展开/三处下钻按钮进抽屉/账号跳聊天；
+- [ ] 驾驶舱：三 KPI 有环比箭头/异常卡可跳员工详情（闭环打通）；
+- [ ] 时间预设全套（今日/昨日/近7/近30/本周/上周/本月/上月/自定义）；
+- [ ] URL 全参数保持；四门禁绿；后端仅 dashboard 一处小改且测试补齐。
+
+## 批次E-F
+
+E：followups 辅导闭环（写端点+schemas_management+详情页按钮激活）+ 考核快照（生成/冻结/列表/导出）。F：调度接入（analytics_tick 第三步+full_sync 13/14 步+scheduler 镜像重建还 9d3cc8e 旧账）+ dashboard 性能修复（unreplied 索引三选一）+ 服务器部署+回测试运行。

docs/superpowers/plans/2026-09-10-management-console-batch-f-scheduling-plan.md

@@ -0,0 +1,142 @@
+# 云客经营管理后台·批次F-调度子批（管理指标接入定时链）实施计划
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task.
+
+**Goal:** 管理域三张派生表（first_reply_fact / employee_metric_daily / employee_call_daily）进入生产定时链——4h 滚动 + 夜间全量自愈，数据每天活起来（同步审计 2026-09-10 结论 #5 的管理域部分）。
+
+**Architecture:** 两处接线：`scheduler.py _analytics_tick` 加**独立事务**的管理滚动段（近 3 天，失败不回滚既有 staff/敏感词段）；`yunke-server/scripts/full_sync_all.sh` 在 11/12 步后加 13/14 步（fact 全量 → 宽表+通话全量）+ 终局快照补三表行数。CLI 已有（first-reply-facts / employee-metrics），无新端点。**边界：不碰审计文档 P0 的脚本加固/实体补抓（并行会话领地）**。
+
+**Tech Stack:** 同批次A（APScheduler + SQLAlchemy async + bash）。
+
+---
+
+## 执行者必读
+
+1. **上游函数签名（as-built）**：`first_reply_facts.pairs_active_in_days(session, days) / recompute_pairs(session, pairs)`；`storage/employee_metrics.recompute_metric_days(session, days) / recompute_call_days(session, days)`；`staff_summary.rolling_days(today, 3)`（返回当日+前2天列表）。全部幂等 delete+insert。
+2. **隔离语义（v2 Task 12：指标失败不中断主流程）**：tick 内管理段用**独立 session+commit**——失败只回滚管理段自身，staff/敏感词段已提交不受影响（当前实现是单 try 单事务，改造为两段）。
+3. **锁竞争既有结论**（tick docstring 已记录）：与夜间 full_sync 重叠时 DELETE+INSERT 可能锁等待，非致命，幂等下轮自愈——管理段沿用同一语义，docstring 注明。
+4. 脚本在 `yunke-server/scripts/full_sync_all.sh`（注意路径已从根 scripts/ 迁移）；测试先例 `tests/test_scheduler_analytics_tick.py`。
+5. 并行会话活动照旧；中文 conventional 提交。
+
+## 任务
+
+### Task F1: _analytics_tick 管理段 + 测试
+
+**Files:** Modify `yunke-server/app/sync/scheduler.py` + `tests/test_scheduler_analytics_tick.py`
+
+改造 `_analytics_tick`（:703）为两段：
+
+```python
+    async def _analytics_tick(self) -> None:
+        """4h 分析链(staff 滚动3天 + 敏感词增量 + 管理域滚动)——异常只记日志不断链。
+
+        两段独立事务:段1 staff+敏感词;段2 管理域(fact 近3天活跃会话 + 宽表/
+        通话 滚动3天,批次F 2026-09-10)。段2 失败只回滚自身,不牵连段1 已
+        提交结果(v2 Task12:指标失败不中断主分析链)。纯 DB 无浏览器,不抢
+        ``_page_lock``;与夜间 full_sync 13/14 步重叠时的锁竞争语义同段1
+        (非致命,幂等下轮自愈)。
+        """
+        # ── 段1:staff 滚动 + 敏感词增量(既有,原样保留) ──
+        try:
+            async with self._session_maker() as session:
+                from app.analytics.sensitive import scanner
+                from app.storage.staff_summary import recompute_days, rolling_days
+                from app.storage.summary import day_key
+
+                today = day_key(int(time.time() * 1000))
+                n = await recompute_days(session, rolling_days(today, 3))
+                scan = await scanner.run_incremental(session)
+                await session.commit()
+            logger.info(
+                "[analytics-tick] staff_days=%s scanned=%s hits=%s",
+                n, scan.get("scanned"), scan.get("hits"),
+            )
+        except Exception:  # noqa: BLE001 — scheduler MUST NOT crash
+            logger.exception("analytics tick failed")
+
+        # ── 段2:管理域滚动(fact 活跃会话 + 宽表/通话,当日+滚动3天) ──
+        try:
+            async with self._session_maker() as session:
+                from app.storage.employee_metrics import (
+                    recompute_call_days,
+                    recompute_metric_days,
+                )
+                from app.storage.first_reply_facts import (
+                    pairs_active_in_days,
+                    recompute_pairs,
+                )
+                from app.storage.staff_summary import rolling_days
+                from app.storage.summary import day_key
+
+                rd = rolling_days(day_key(int(time.time() * 1000)), 3)
+                pairs = await pairs_active_in_days(session, rd)
+                f = await recompute_pairs(session, pairs)
+                w = await recompute_metric_days(session, rd)
+                c = await recompute_call_days(session, rd)
+                await session.commit()
+            logger.info(
+                "[analytics-tick] mgmt fact_pairs=%s wide_rows=%s call_rows=%s",
+                f, w, c,
+            )
+        except Exception:  # noqa: BLE001
+            logger.exception("management metrics tick failed")
+```
+
+（导入合并/去重按文件现状微调；today 变量两段各自取或共享只读。注：`recompute_metric_days` 内部会再查一次 `pairs_active_in_days`（与本段显式调用重复但廉价）——非冗余待修，fact 段需要显式拿 pairs 计数记日志。）
+
+**测试追加**（照既有文件 mock 模式）：
+1. tick 调用顺序：staff recompute_days → 敏感 scan → pairs_active_in_days(rolling3) → recompute_pairs → recompute_metric_days → recompute_call_days；
+2. **段2 失败隔离**：recompute_metric_days 抛异常 → staff recompute_days 与敏感 scan 仍被调用且各自 commit 成功、tick 不抛、异常被记（caplog）；
+3. rolling 窗口传参 = rolling_days(today,3)。
+
+- [ ] `pytest tests/test_scheduler_analytics_tick.py -v` + 全量 -q → commit `feat(management): 4h分析链接入管理域滚动段——独立事务隔离/fact活跃会话+宽表+通话滚动3天`
+
+### Task F2: full_sync_all.sh 13/14 步 + 快照行数
+
+**Files:** Modify `yunke-server/scripts/full_sync_all.sh`
+
+第 12 步之后（COMPLETE 横幅之前）加：
+
+```bash
+# 13:首响事实表全量重建(管理域,跨日精确串;批次A)——会话发现读
+#    msg_daily_stats(fact 行直算读 message),故须在 11 步后;与 11/12
+#    同为夜间自愈链(绕过钩子的写入由全量重算纠正)
+echo "$(date) --- 13/14 First-reply-facts rebuild ---"
+$PY -m app.sync.cli first-reply-facts
+# 14:管理宽表+通话小表全量重建(驾驶舱/员工页读路径;串类列与 fact 同
+#    算法各自直算,放 fact 后保持派生链顺序语义)
+echo "$(date) --- 14/14 Employee-metrics rebuild ---"
+$PY -m app.sync.cli employee-metrics
+```
+
+终局快照 TABLES 追加三行（放 daily stats rows 后）：
+
+```python
+    ("first reply facts", "SELECT COUNT(*) FROM first_reply_fact"),
+    ("employee metric rows", "SELECT COUNT(*) FROM employee_metric_daily"),
+    ("employee call rows", "SELECT COUNT(*) FROM employee_call_daily"),
+```
+
+- [ ] `bash -n yunke-server/scripts/full_sync_all.sh` 语法过 + commit `feat(management): 夜间全量脚本13/14步——fact与宽表全量自愈+终局快照三表行数`
+
+### Task F3: 本地 scheduler 容器重建 + 真机验证 + 归档
+
+1. **真机验证滚动段**（直接跑 tick 逻辑，不等 4h）：临时脚本或 `python -c` 用 scheduler 的 session_maker 调 `_analytics_tick()`（或手动等价：按 rolling 3 天调三个 recompute + commit）——记录耗时（预期 fact 活跃会话数十秒级内）+ 三表当日行数变化（recompute 后 updated 行 freshness）；
+2. **幂等复跑**：连跑两次行数一致；
+3. **本地 scheduler 容器重建**（新代码进夜间链）：`docker ps` 确认 scheduler 容器名 → `docker compose -f docker-compose.yml up -d --build scheduler`——**范围仅本地**（服务器 scheduler 镜像 2026-09-09 已重建过，服务器侧等部署时随 DEPLOY.md 流程走，本任务不碰）；重建前后 `docker exec <scheduler> python -c "import app.sync.scheduler"` 冒烟；（已知后果不阻塞：phone_call 尚未进 4h/每日页面同步链[审计P0-5,并行会话领地]——通话小表滚动重算在补齐前只是从静态源幂等重生成）；
+4. 归档：耗时/行数/容器重建记录 → 核实文档「批次F-调度」小节 + commit。
+
+- [ ] commit `docs(management): 批次F调度接入验证——滚动段耗时/幂等/容器重建(清9d3cc8e旧账)`
+
+## 验收清单
+
+- [ ] tick 两段隔离测试过（段2 异常不牵连段1）；
+- [ ] 夜间脚本 13/14 步 + 快照三表行数；
+- [ ] 滚动段真机耗时记录（预期 <60s）+ 幂等；
+- [ ] 本地 scheduler 容器已重建（新代码），夜间 02:00 链将含管理域；
+- [ ] 全量测试绿；
+- [ ] 未触碰审计 P0 领地（脚本加固/实体补抓——并行会话负责）。
+
+## 后续（不在本子批）
+
+E：辅导+快照；F 余项：dashboard 性能修复（unreplied 索引）、winsorize 决策、服务器部署（届时服务器 scheduler 镜像重建走 DEPLOY.md）。

yunke-server/app/analytics/lifecycle.py

@@ -0,0 +1,71 @@
+"""客户生命周期判定(管理域,批次A)——距今天数口径(v2 §1.1 #3 决议)。
+
+阈值取已确认默认(v1 §21,用户拍板):新客 7 天、沉睡 30 天;历史互动
+门槛 MIN_HISTORY_MSGS=5 对齐 analytics churn real 的 min_msgs=5。
+analytics 现有页(churn/客户资产)**暂不切换**到此模块——两套数字的
+差异在 metric-definitions 标注(v2 §5);后续统一时再接,避免动既有
+测试。
+
+本模块为纯叶子节点,禁止 import app.storage(防止 storage→analytics
+消费时成环)。
+"""
+
+from __future__ import annotations
+
+import datetime as dt
+
+NEW_DAYS = 7
+DORMANT_DAYS = 30
+MIN_HISTORY_MSGS = 5
+
+STATES = ("new", "active", "cooling", "dormant", "reactivated")
+
+
+def _to_date(day: int) -> dt.date:
+    return dt.date(day // 10000, (day // 100) % 100, day % 100)
+
+
+def day_add(day: int, delta_days: int) -> int:
+    """yyyymmdd 键加减天数。"""
+    d = _to_date(day) + dt.timedelta(days=delta_days)
+    return d.year * 10000 + d.month * 100 + d.day
+
+
+def days_between(day_a: int, day_b: int) -> int:
+    """b − a 的天数(输入 yyyymmdd 键)。"""
+    return (_to_date(day_b) - _to_date(day_a)).days
+
+
+def classify(
+    first_day: int | None,
+    last_day: int | None,
+    prev_day: int | None,
+    as_of: int,
+    hist_msgs: int,
+) -> str | None:
+    """as_of 日的客户状态;输入均为互动日键(yyyymmdd,上海自然日)。
+
+    - first_day: 该客户全历史首次互动日;last_day: ≤as_of 的最近互动日;
+      prev_day: last_day 之前的一次互动日(无则 None);hist_msgs: 历史总消息数。
+    - 返回 None = 未激活(first/last 缺)或历史不足的长期静默(不计入任何列)。
+
+    判定优先级:new → reactivated → active → cooling → dormant。
+    """
+    if first_day is None or last_day is None:
+        return None
+    if first_day >= day_add(as_of, -(NEW_DAYS - 1)):
+        return "new"
+    if (
+        last_day == as_of
+        and prev_day is not None
+        and days_between(prev_day, last_day) > DORMANT_DAYS
+    ):
+        return "reactivated"
+    gap = days_between(last_day, as_of)
+    if gap < NEW_DAYS:
+        return "active"
+    if gap < DORMANT_DAYS:
+        return "cooling"
+    if hist_msgs >= MIN_HISTORY_MSGS:
+        return "dormant"
+    return None

yunke-server/app/api/main.py

@@ -49,6 +49,7 @@ from app.api.routers import (
     export,
     groups,
     login,
+    management,
     media,
     messages,
     moments,
@@ -101,6 +102,7 @@ app.include_router(sessions.router)
 app.include_router(export.router)
 app.include_router(voice_clips.router)
 app.include_router(analytics.router)
+app.include_router(management.router)
 
 
 @app.get("/api/health")

yunke-server/app/api/routers/customer.py

@@ -7,6 +7,12 @@ Read-only query over the mirrored ``customer`` table. Supports filtering by
 nickname / remark / friend_id / phone, ``%``/``_`` escaped as literals — the
 通讯录 search box). Results are ordered by ``last_chat_time desc`` (nulls
 last) then ``friend_id`` so the most-recently-active contacts surface first.
+
+**owner_account_id 维度走 ``customer_account_link``**(2026-09-08):customer
+档案 PK=friend_id 全局单行、归属 last-wins,共享客户在其他员工名下会漏
+(实测 36 vs 12);link 表每个「渠道×账号×客户」一行,员工维度列表/计数与
+云客 per-employee 口径一致。带 department/user/add_time/last_chat 等其余
+过滤时回退档案路径(组合场景罕见,保持旧行为)。
 """
 
 from __future__ import annotations
@@ -19,7 +25,7 @@ from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.api.deps import get_session
 from app.api.schemas import CustomerOut, Page
-from app.db.models import Customer, Staff, WechatAccount
+from app.db.models import Customer, CustomerAccountLink, Staff, WechatAccount
 
 router = APIRouter(prefix="/api", tags=["customers"])
 
@@ -61,6 +67,74 @@ async def customers_declared_total(session: SessionDep) -> dict:
     }
 
 
+async def _list_owner_links(
+    session: AsyncSession,
+    *,
+    page: int,
+    page_size: int,
+    channel: str | None,
+    owner_account_id: str,
+    friend_id: str | None,
+    q: str | None,
+) -> Page[CustomerOut]:
+    """员工维度客户列表:读 ``customer_account_link``(渠道×账号×客户一行)。
+
+    排序/搜索语义与档案路径一致(last_chat_time desc、四列模糊);link 自带
+    per-relation 快照(备注/收发计数按员工各一份,与云客 per-employee 列表
+    相同)。CustomerOut 的档案专属列(raw_json/version/send_today 等)为 None。
+    """
+    conditions = [CustomerAccountLink.owner_account_id == owner_account_id]
+    if channel is not None:
+        conditions.append(CustomerAccountLink.channel == channel)
+    if friend_id is not None:
+        conditions.append(CustomerAccountLink.friend_id == friend_id)
+    if q:
+        # LIKE 通配符转义(同档案路径):昵称/备注/微信号/手机号四列任一命中
+        escaped = q.replace("\\", "\\\\").replace("%", "\\%").replace("_", "\\_")
+        like = f"%{escaped}%"
+        conditions.append(
+            sa.or_(
+                CustomerAccountLink.friend_nickname.like(like, escape="\\"),
+                CustomerAccountLink.friend_remark.like(like, escape="\\"),
+                CustomerAccountLink.friend_id.like(like, escape="\\"),
+                CustomerAccountLink.phone.like(like, escape="\\"),
+            )
+        )
+
+    total = (
+        await session.execute(
+            sa.select(sa.func.count())
+            .select_from(CustomerAccountLink)
+            .where(*conditions)
+        )
+    ).scalar_one()
+    # LEFT JOIN 档案带 raw_json(2026-09-09):WA 客户列表大量列只存在于
+    # raw_json(userName/salePhone/createTime 等员工侧字段),link 快照没存;
+    # raw_json 按 friend_id 全局一份,挂谁名下内容相同。注:共享客户的员工
+    # 侧字段是「最后写入员工」的记录,可能非本员工(客户自身字段不受影响)。
+    rows = (
+        await session.execute(
+            sa.select(CustomerAccountLink, Customer.raw_json, Customer.version)
+            .outerjoin(Customer, Customer.friend_id == CustomerAccountLink.friend_id)
+            .where(*conditions)
+            .order_by(
+                sa.nullslast(CustomerAccountLink.last_chat_time.desc()),
+                CustomerAccountLink.friend_id.asc(),
+            )
+            .limit(page_size)
+            .offset((page - 1) * page_size)
+        )
+    ).all()
+    items = []
+    for link, raw_json, version in rows:
+        out = CustomerOut.model_validate(link)
+        out.raw_json = raw_json
+        if version is not None:
+            out.version = version
+        items.append(out)
+    return Page(items=items, total=total, page=page, page_size=page_size)
+
+
 @router.get("/customers")
 async def list_customers(
     session: SessionDep,
@@ -76,6 +150,34 @@ async def list_customers(
     q: Annotated[str | None, Query()] = None,
 ) -> Page[CustomerOut]:
     """List customers with optional filters and pagination."""
+    # 员工维度优先走 link 表(共享好友每账号一行,见模块 docstring);该账号
+    # link 还无数据时回退档案路径(过渡安全:回填前页面不至于空;也兼容
+    # 只写档案的理论路径)。与其余仅档案路径支持的过滤组合时同样回退。
+    if (
+        owner_account_id is not None
+        and department_id is None
+        and user_id is None
+        and add_time_since is None
+        and last_chat_since is None
+    ):
+        link_exists = (
+            await session.execute(
+                sa.select(sa.func.count())
+                .select_from(CustomerAccountLink)
+                .where(CustomerAccountLink.owner_account_id == owner_account_id)
+            )
+        ).scalar_one()
+        if link_exists:
+            return await _list_owner_links(
+                session,
+                page=page,
+                page_size=page_size,
+                channel=channel,
+                owner_account_id=owner_account_id,
+                friend_id=friend_id,
+                q=q,
+            )
+
     conditions = []
     if channel is not None:
         conditions.append(Customer.channel == channel)

yunke-server/app/api/routers/export.py

@@ -1,21 +1,25 @@
 """GET /api/export/chat-html — 导出一段 1:1 / 群聊天为独立 HTML 文件。
+GET /api/export/chat-html-zip — 勾选的多个 1:1 会话打成一个 zip(每会话一个 HTML)。
 
 对齐云客微信客户列表「导出HTML聊天记录」：按 (channel, owner, talker_id|room_id)
 拉消息（可选 start/end 时间范围），渲染自包含 HTML 聊天页（is_send 决定左右气泡），
-作为 attachment 返回下载。
+作为 attachment 返回下载。zip 版对齐员工客户页的批量「导出聊天记录」(2026-09-08)。
 """
 from __future__ import annotations
 
+import io
+import re
+import zipfile
 from datetime import datetime, timezone
 from html import escape
 from typing import Annotated
 
 import sqlalchemy as sa
-from fastapi import APIRouter, Depends, Query, Response
+from fastapi import APIRouter, Depends, HTTPException, Query, Response
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.api.deps import get_session
-from app.db.models import Message
+from app.db.models import Customer, CustomerAccountLink, Message
 
 router = APIRouter(prefix="/api/export", tags=["export"])
 
@@ -170,3 +174,110 @@ async def export_chat_html(
         media_type="text/html; charset=utf-8",
         headers={"Content-Disposition": f'attachment; filename="{filename}"'},
     )
+
+
+# 员工客户页批量「导出聊天记录」:一次勾选的会话数上限(防误点全选把服务端打爆;
+# 50 个会话 × 每会话 EXPORT_MAX_ROWS 已是内存上界内的最坏情况)。
+ZIP_MAX_CONVS = 50
+
+
+def _safe_zip_name(name: str, fallback: str) -> str:
+    """会话显示名 → zip 内文件名:去路径/Windows 非法字符,限长,空回退。"""
+    cleaned = re.sub(r'[<>:"/\\|?*\x00-\x1f]', "_", name).strip("._ ")
+    return cleaned[:40] or fallback
+
+
+@router.get("/chat-html-zip")
+async def export_chat_html_zip(
+    session: SessionDep,
+    channel: Annotated[str, Query()],
+    owner_account_id: Annotated[str, Query()],
+    talker_ids: Annotated[str, Query()] = "",
+    start: Annotated[int | None, Query(ge=0)] = None,
+    end: Annotated[int | None, Query(ge=0)] = None,
+) -> Response:
+    """勾选客户的 1:1 聊天批量导出为一个 zip(每会话一个 HTML,复用单导出渲染器)。
+
+    ``talker_ids`` 逗号分隔的 friend_id 列表;文件名取客户备注/昵称(缺省回退
+    friend_id),加序号前缀保唯一;单会话行数沿用 EXPORT_MAX_ROWS 截断告警。
+    """
+    ids = [t.strip() for t in talker_ids.split(",") if t.strip()]
+    if not ids:
+        raise HTTPException(status_code=422, detail="talker_ids 不能为空")
+    if len(ids) > ZIP_MAX_CONVS:
+        raise HTTPException(
+            status_code=422, detail=f"一次最多导出 {ZIP_MAX_CONVS} 个会话"
+        )
+
+    # 文件名显示名:批量取一次(备注 > 昵称 > friend_id)。优先
+    # customer_account_link per-owner 快照——共享客户的档案行可能挂在别的
+    # 员工名下,按 owner 查档案会查空、zip 文件名回退成 wxid(2026-09-09,
+    # 同 sessions._meta 修复);link 没覆盖的回退档案。
+    link_rows = (await session.execute(
+        sa.select(
+            CustomerAccountLink.friend_id,
+            CustomerAccountLink.friend_nickname,
+            CustomerAccountLink.friend_remark,
+        ).where(
+            CustomerAccountLink.channel == channel,
+            CustomerAccountLink.owner_account_id == owner_account_id,
+            CustomerAccountLink.friend_id.in_(ids),
+        )
+    )).all()
+    names = {
+        r.friend_id: (r.friend_remark or r.friend_nickname or r.friend_id)
+        for r in link_rows
+    }
+    missing = [t for t in ids if t not in names]
+    if missing:
+        cust_rows = (await session.execute(
+            sa.select(
+                Customer.friend_id,
+                Customer.friend_nickname,
+                Customer.friend_remark,
+            ).where(
+                Customer.channel == channel,
+                Customer.owner_account_id == owner_account_id,
+                Customer.friend_id.in_(missing),
+            )
+        )).all()
+        for r in cust_rows:
+            names[r.friend_id] = (r.friend_remark or r.friend_nickname or r.friend_id)
+
+    buf = io.BytesIO()
+    with zipfile.ZipFile(buf, "w", zipfile.ZIP_DEFLATED) as zf:
+        for i, tid in enumerate(ids, 1):
+            q = sa.select(Message).where(
+                Message.channel == channel,
+                Message.owner_account_id == owner_account_id,
+                Message.talker_id == tid,
+                # DM:限定 room_id 为空,避免误捞群消息(同单导出)
+                (Message.room_id == None) | (Message.room_id == ""),  # noqa: E711
+            )
+            if start is not None:
+                q = q.where(Message.timestamp >= start)
+            if end is not None:
+                q = q.where(Message.timestamp <= end)
+            q = q.order_by(
+                sa.nullslast(Message.timestamp.asc()), Message.msg_id.asc()
+            ).limit(EXPORT_MAX_ROWS)
+            rows = list((await session.execute(q)).scalars().all())
+            capped = len(rows) >= EXPORT_MAX_ROWS
+            warning = (
+                f'<div class="export-warning">⚠️ 结果超过 {EXPORT_MAX_ROWS} 条，'
+                f"仅导出前 {EXPORT_MAX_ROWS} 条。请缩小日期范围。</div>"
+                if capped
+                else ""
+            )
+            html = _render_chat_html(rows, channel, owner_account_id, tid, warning=warning)
+            safe = _safe_zip_name(names.get(tid) or tid, f"conv{i}")
+            zf.writestr(f"{i:02d}_{safe}.html", html)
+    return Response(
+        content=buf.getvalue(),
+        media_type="application/zip",
+        headers={
+            "Content-Disposition": (
+                f'attachment; filename="chat-records-{channel}-{owner_account_id}.zip"'
+            )
+        },
+    )

yunke-server/app/api/routers/groups.py

@@ -5,6 +5,10 @@
   ``owner_user_id`` column) and ``q`` (substring match on ``room_name``,
   ``%``/``_`` escaped as literals — the 通讯录群 tab search box), ordered by
   ``last_chat_time desc`` (nulls last) so recently-active groups surface first.
+  微信群统计扩展(2026-09-09,云客「微信群统计」同款):``msg_start``/``msg_end``
+  统计时段(窗内输出沟通消息数/新增/退出成员数聚合)、``last_start``/
+  ``last_end`` 最新消息时间段、``group_remark`` 群备注子串;行补员工微信/
+  员工信息列(wechat_account/staff 关联)。
 * ``GET /api/groups/{room_id}/members`` -> ``list[GroupMemberOut]`` — the
   members of a single group (small set, no pagination needed).
 """
@@ -19,7 +23,15 @@ from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.api.deps import get_session
 from app.api.schemas import GroupMemberOut, GroupOut, Page
-from app.db.models import ChatGroup, GroupMember
+from app.db.models import (
+    ChatGroup,
+    ChatGroupMemberStats,
+    GroupMember,
+    MsgDailyStats,
+    Staff,
+    WechatAccount,
+)
+from app.storage.summary import day_key
 
 router = APIRouter(prefix="/api", tags=["groups"])
 
@@ -38,6 +50,11 @@ async def list_groups(
     user_id: Annotated[str | None, Query()] = None,
     room_id: Annotated[str | None, Query()] = None,
     q: Annotated[str | None, Query()] = None,
+    group_remark: Annotated[str | None, Query()] = None,
+    last_start: Annotated[int | None, Query(ge=0)] = None,
+    last_end: Annotated[int | None, Query(ge=0)] = None,
+    msg_start: Annotated[int | None, Query(ge=0)] = None,
+    msg_end: Annotated[int | None, Query(ge=0)] = None,
 ) -> Page[GroupOut]:
     """List chat groups with optional ``channel`` / ``owner_account_id`` /
     ``user_id`` / ``room_id`` / ``q`` filters.
@@ -47,6 +64,13 @@ async def list_groups(
     filter on ``GET /api/customers``. ``room_id`` is an exact-match lookup
     (composite PK: the same room may return one row per owner; chat page
     group-name resolution). ``q`` is a substring match on ``room_name``.
+
+    微信群统计参数(2026-09-09):``last_start``/``last_end`` 过滤
+    ``last_chat_time`` 范围(最新消息时间段);``msg_start``/``msg_end``
+    统计时段——窗内聚合三列(``window_msg_count`` 沟通消息数=
+    msg_daily_stats 按天求和、``window_added``/``window_lost`` 成员进出=
+    chat_group_member_stats 按天求和,上线日起有数据);``group_remark``
+    群备注子串。员工微信/员工信息列经 wechat_account/staff 关联补齐。
     """
     conditions = []
     if channel is not None:
@@ -57,10 +81,17 @@ async def list_groups(
         # LIKE 通配符转义: %/_ 按字面匹配(镜像 customers/messages 的 q 处理)
         escaped = q.replace("\\", "\\\\").replace("%", "\\%").replace("_", "\\_")
         conditions.append(ChatGroup.room_name.like(f"%{escaped}%", escape="\\"))
+    if group_remark:
+        escaped_r = group_remark.replace("\\", "\\\\").replace("%", "\\%").replace("_", "\\_")
+        conditions.append(ChatGroup.group_remark.like(f"%{escaped_r}%", escape="\\"))
     if room_id is not None:
         conditions.append(ChatGroup.room_id == room_id)
     if user_id is not None:
         conditions.append(ChatGroup.owner_user_id == user_id)
+    if last_start is not None:
+        conditions.append(ChatGroup.last_chat_time >= last_start)
+    if last_end is not None:
+        conditions.append(ChatGroup.last_chat_time <= last_end)
 
     total_stmt = sa.select(sa.func.count()).select_from(ChatGroup)
     if conditions:
@@ -70,6 +101,29 @@ async def list_groups(
     list_stmt = sa.select(ChatGroup)
     if conditions:
         list_stmt = list_stmt.where(*conditions)
+    if (channel or "wechat") == "wechat":
+        # 云客「微信群统计」同款排序(2026-09-10 真机终判):owner_account_id
+        # (=微信号/wxid 混存,如 Nancyjade < csf7169708 < wxid_01gv…——大写
+        # 在小写前=区分大小写)**二进制字节序升序**分组,组内 room_id 字符串
+        # 升序。字节序按方言:MySQL 用 CAST(col AS BINARY)(collate("BINARY")
+        # 会被 SQLAlchemy 反引号成标识符);SQLite 用 COLLATE BINARY(其 CAST
+        # AS BINARY 语义不符)。WA 保持最近活跃优先。
+        dialect = session.bind.dialect.name if session.bind is not None else ""
+        if dialect == "mysql":
+            owner_order = sa.literal_column(
+                "CAST(chat_group.owner_account_id AS BINARY)"
+            ).asc()
+        else:
+            owner_order = ChatGroup.owner_account_id.collate("BINARY").asc()
+        list_stmt = (
+            list_stmt.order_by(
+                owner_order,
+                ChatGroup.room_id.asc(),
+            )
+            .limit(page_size)
+            .offset((page - 1) * page_size)
+        )
+    else:
         list_stmt = (
             list_stmt.order_by(
                 sa.nullslast(ChatGroup.last_chat_time.desc()),
@@ -79,7 +133,84 @@ async def list_groups(
             .offset((page - 1) * page_size)
         )
     rows = (await session.execute(list_stmt)).scalars().all()
-    items = [GroupOut.model_validate(row) for row in rows]
+
+    # ---- 员工微信/员工信息列(wechat_account/staff 关联,本页行集) ----
+    acc_map: dict[str, tuple[str | None, str | None, str | None]] = {}
+    owners = {r.owner_account_id for r in rows if r.owner_account_id}
+    if owners:
+        for wx, nick, alias, raw in (await session.execute(
+            sa.select(
+                WechatAccount.wx_id, WechatAccount.nick_name,
+                WechatAccount.alias, WechatAccount.raw_json,
+            ).where(WechatAccount.wx_id.in_(owners))
+        )).all():
+            avatar = None
+            if isinstance(raw, dict):
+                h = raw.get("headImageUrl")
+                avatar = h if isinstance(h, str) else None
+            acc_map[wx] = (nick, alias, avatar)
+    staff_map: dict[str, tuple[str | None, str | None]] = {}
+    uids = {r.owner_user_id for r in rows if r.owner_user_id}
+    if uids:
+        for uid, name, phone in (await session.execute(
+            sa.select(Staff.user_id, Staff.name, Staff.phone)
+            .where(Staff.user_id.in_(uids))
+        )).all():
+            staff_map[uid] = (name, phone)
+
+    # ---- 统计时段窗内聚合(msg_daily_stats 沟通消息数 + member_stats 进出) ----
+    msg_cnt: dict[tuple[str, str], int] = {}
+    added_map: dict[tuple[str, str], int] = {}
+    lost_map: dict[tuple[str, str], int] = {}
+    if msg_start is not None and msg_end is not None and rows:
+        d0, d1 = day_key(msg_start), day_key(msg_end)
+        pairs = [(r.owner_account_id, r.room_id) for r in rows]
+        owners_in = {p[0] for p in pairs}
+        rooms_in = {p[1] for p in pairs}
+        for owner, room, cnt in (await session.execute(
+            sa.select(
+                MsgDailyStats.owner_account_id, MsgDailyStats.peer_id,
+                sa.func.coalesce(sa.func.sum(
+                    MsgDailyStats.send_cnt + MsgDailyStats.recv_cnt), 0),
+            ).where(
+                MsgDailyStats.channel == (channel or "wechat"),
+                MsgDailyStats.peer_kind == "room",
+                MsgDailyStats.owner_account_id.in_(owners_in),
+                MsgDailyStats.peer_id.in_(rooms_in),
+                MsgDailyStats.day >= d0, MsgDailyStats.day <= d1,
+            ).group_by(MsgDailyStats.owner_account_id, MsgDailyStats.peer_id)
+        )).all():
+            msg_cnt[(owner, room)] = int(cnt)
+        for owner, room, a, l in (await session.execute(
+            sa.select(
+                ChatGroupMemberStats.owner_account_id, ChatGroupMemberStats.room_id,
+                sa.func.coalesce(sa.func.sum(ChatGroupMemberStats.added), 0),
+                sa.func.coalesce(sa.func.sum(ChatGroupMemberStats.lost), 0),
+            ).where(
+                ChatGroupMemberStats.channel == (channel or "wechat"),
+                ChatGroupMemberStats.owner_account_id.in_(owners_in),
+                ChatGroupMemberStats.room_id.in_(rooms_in),
+                ChatGroupMemberStats.day >= d0, ChatGroupMemberStats.day <= d1,
+            ).group_by(ChatGroupMemberStats.owner_account_id, ChatGroupMemberStats.room_id)
+        )).all():
+            added_map[(owner, room)] = int(a)
+            lost_map[(owner, room)] = int(l)
+
+    items = []
+    for r in rows:
+        out = GroupOut.model_validate(r)
+        acc = acc_map.get(r.owner_account_id or "")
+        if acc:
+            out.staff_nickname, out.staff_wx_alias, out.staff_avatar = acc
+        st = staff_map.get(r.owner_user_id or "")
+        if st:
+            out.staff_name, out.staff_phone = st
+        if msg_start is not None and msg_end is not None:
+            key = (r.owner_account_id or "", r.room_id)
+            out.window_msg_count = msg_cnt.get(key, 0)
+            out.window_added = added_map.get(key, 0)
+            out.window_lost = lost_map.get(key, 0)
+        items.append(out)
     return Page(items=items, total=total, page=page, page_size=page_size)
 
 

yunke-server/app/api/routers/management.py

@@ -0,0 +1,571 @@
+"""GET /api/management/* —— 经营管理后台只读端组(批次B Task B4)。
+
+六个端点:dashboard(总览)/ employees(列表,一期四视图共用行集)/
+employees/{user_id}(详情)/ employees/{user_id}/metrics(分段指标+趋势)/
+employees/{user_id}/drilldown(白名单下钻)/ metric-definitions(口径字典)。
+
+惯例同 analytics.py:channel=all 在 router 层翻译为 None 传服务层;
+start/end yyyymmdd 缺一/日历非法/start>end/跨度>366 天皆 422(_window);
+重查询与行构造在 app.management.api_assembly,本文件只做薄编排。
+所有查询共用单 AsyncSession——**顺序 await,不并发**(见 assembly 模块)。
+"""
+from __future__ import annotations
+
+import datetime as dt
+from typing import Annotated, Any, Literal
+
+import sqlalchemy as sa
+from fastapi import APIRouter, Depends, HTTPException, Query
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.analytics import health as health_svc
+from app.analytics import metrics as metrics_svc
+from app.api.deps import get_session
+from app.db.models import Staff, WechatAccount, WhatsappAccount
+from app.management import api_assembly as asm
+from app.management.anomalies import detect_anomalies
+from app.management.employee_metrics import (
+    baseline_window,
+    day_range,
+    period_metrics,
+    prev_window,
+)
+from app.management.metric_definitions import METRIC_DEFINITIONS
+from app.storage.employee_metrics import METRIC_VERSION
+from app.storage.staff_summary import account_map
+
+router = APIRouter(prefix="/api/management", tags=["management"])
+
+SessionDep = Annotated[AsyncSession, Depends(get_session)]
+AllChannelParam = Annotated[Literal["all", "wechat", "whatsapp"], Query()]
+YmdParam = Annotated[int, Query(ge=20000101, le=29991231)]
+CompareParam = Annotated[
+    Literal["previous", "personal_baseline", "team_median"], Query()
+]
+ViewParam = Annotated[
+    Literal["management", "workload", "service", "customer"], Query()
+]
+StatusParam = Annotated[Literal["all", "on_job", "offline"], Query()]
+SortByParam = Annotated[
+    Literal["anomaly_severity", "total_score", "active_friends", "cust_threads"],
+    Query(),
+]
+SortOrderParam = Annotated[Literal["asc", "desc"], Query()]
+SectionParam = Annotated[
+    Literal["overview", "service", "customer", "workload", "calls"], Query()
+]
+
+# drilldown 白名单(外 422 "unknown metric_code")
+_DRILLDOWN_CODES = frozenset({
+    "first_reply_p50", "first_reply_p90", "unreplied",
+    "cooling_customers", "dormant_customers", "call_followup",
+})
+
+# unreplied 适配:上游无私有 owner 过滤,取全量决赛圈结果再按 owner 过滤。
+# 500 = analytics.metrics._FINALIZE_ALL_MAX 同值(候选 ≤500 时单次调用即
+# 拿到全部已过滤 items;超过则上游本就按候选分页,响应标 truncated)。
+_UNREPLIED_FETCH = 500
+
+# 三方口径差异说明(硬编码,与 METRIC_DEFINITIONS.caliber 互补的总述)
+CALIBER_NOTES = (
+    "管理域指标为 1:1 私聊口径且跨日精确(消息串按会话全历史计算、"
+    "归属串末条所在自然日);现有看板为私聊+群聊混合、日切口径"
+    "(跨夜串重复计/丢失,回复率分子分母同源近似)。"
+    "通话指标(通话数/时长/接通/跟进)无消息渠道维度——"
+    "voice_call 与 wa_voice_call 合并计数,不随 channel 参数过滤。"
+)
+
+# 各 section 的期指标字段(自 PeriodMetrics 挑)与宽表/通话表趋势列
+_SECTION_FIELDS: dict[str, tuple[str, ...]] = {
+    "overview": ("days_with_data", "msg_sent", "msg_recv", "active_friends",
+                 "active_rooms_avg"),
+    "service": ("cust_threads", "threads_answered", "fr_sum_ms",
+                "fr_p50_ms", "fr_p90_ms", "reply_2h_count", "reply_24h_count"),
+    "customer": ("new_customer", "cooling_customer", "dormant_customer",
+                 "reactivated_customer", "end_active_friends"),
+    "workload": ("active_friends", "active_rooms_avg", "cust_threads"),
+    "calls": ("call_count", "call_seconds", "answered_call", "call_followup"),
+}
+_SECTION_TREND_COLS: dict[str, tuple[str, ...]] = {
+    "overview": ("msg_sent", "msg_recv", "active_friends"),
+    "service": ("cust_threads", "threads_answered", "fr_sum_ms",
+                "first_reply_p50_ms", "first_reply_p90_ms"),
+    "customer": ("new_customer_count", "cooling_customer_count",
+                 "dormant_customer_count", "reactivated_customer_count"),
+    "workload": ("active_friends", "active_rooms"),
+    "calls": ("call_count", "call_seconds", "answered_call_count",
+              "call_followup_count"),
+}
+
+
+def _window(start: int | None, end: int | None) -> tuple[int, int]:
+    """管理端点公共窗口校验(照 analytics custom scope 惯例)。"""
+    if start is None or end is None:
+        raise HTTPException(422, "start and end are required")
+    try:
+        sd = dt.date(start // 10000, (start // 100) % 100, start % 100)
+        ed = dt.date(end // 10000, (end // 100) % 100, end % 100)
+    except ValueError as exc:  # 如 20260230——Query 只拦范围不拦日历
+        raise HTTPException(422, "invalid start/end calendar date") from exc
+    if sd > ed:
+        raise HTTPException(422, "start must be <= end")
+    if (ed - sd).days > 365:  # 含端点共 366 天
+        raise HTTPException(422, "span must be <= 366 days")
+    return start, end
+
+
+def _translate(channel: str) -> str | None:
+    return None if channel == "all" else channel
+
+
+async def _get_staff(session: AsyncSession, user_id: str) -> Staff:
+    staff = (await session.execute(
+        sa.select(Staff).where(Staff.user_id == user_id)
+    )).scalar_one_or_none()
+    if staff is None:
+        raise HTTPException(404, f"employee {user_id} not found")
+    return staff
+
+
+@router.get("/dashboard")
+async def management_dashboard(
+    session: SessionDep,
+    channel: AllChannelParam = "all",
+    start: YmdParam | None = None,
+    end: YmdParam | None = None,
+    compare: CompareParam = "previous",
+) -> dict[str, Any]:
+    """经营管理总览:KPI + 双趋势 + 生命周期 + 维度分布 + 异常汇总 +
+    行动入口计数,单往返。compare 仅回显(对比数值在 employees 行内)。"""
+    start, end = _window(start, end)
+    ch = _translate(channel)
+    config, config_source = await asm.load_score_config(session)
+    assembled = await asm.assemble_employees(
+        session, config, start, end, ch, with_prev=False
+    )
+    pms = [a["cur"] for a in assembled.values()]
+
+    # ---- 趋势两查:宽表全员逐日 + 通话小表逐日 + fact 逐日 ----
+    wide = await asm.wide_daily_rows(session, start, end, ch)
+    wide_by_day = {d["day"]: d for d in wide}
+    threads_by_day = {d["day"]: d["cust_threads"] for d in wide}
+    calls = await asm.call_daily_rows(session, start, end)
+    call_by_day = {d["day"]: d["call_count"] for d in calls}
+    comm_trend = []
+    for day in day_range(start, end):
+        d = wide_by_day.get(day)
+        comm_trend.append({
+            "day": day,
+            "msg_total": (d["msg_sent"] + d["msg_recv"]) if d else 0,
+            # 团队合计口径:当日各员工宽表 active_friends 求和
+            "active_customers": d["active_friends"] if d else 0,
+            "call_cnt": call_by_day.get(day, 0),
+        })
+    service_trend = await asm.service_daily_trend(
+        session, start, end, ch, threads_by_day
+    )
+
+    lifecycle = {
+        "new": sum(p.new_customer for p in pms),
+        "cooling": sum(p.cooling_customer for p in pms),
+        "dormant": sum(p.dormant_customer for p in pms),
+        "reactivated": sum(p.reactivated_customer for p in pms),
+    }
+    kpis = {
+        # 全员 active_friends 求和:跨员工可能重复计客户(共享客户)
+        "active_customers": sum(p.active_friends for p in pms),
+        "active_employees": sum(1 for p in pms if p.days_with_data > 0),
+        "msg_total": sum(p.msg_sent + p.msg_recv for p in pms),
+        "cust_threads": sum(p.cust_threads for p in pms),
+        "threads_answered": sum(p.threads_answered for p in pms),
+        "call_count": sum(p.call_count for p in pms),
+        "call_seconds": sum(p.call_seconds for p in pms),
+        "answered_call": sum(p.answered_call for p in pms),
+        "lifecycle": lifecycle,
+    }
+
+    # ---- 前窗环比基线(批次D):prev 窗全员一次 period_metrics,聚合式与
+    # kpis 完全同式(活跃客户=Σactive_friends、活跃员工=天数>0 计数、
+    # msg_total=Σ(sent+recv)、cust_threads=Σ)。lifecycle(期末存量)与
+    # 通话(全渠道口径,表无渠道维)不加环比——期末/混合口径的环比意义弱。
+    ps, pe = prev_window(start, end)
+    prev_pms = list((await period_metrics(session, ps, pe, ch)).values())
+    prev_kpis = {
+        # 全员求和口径同 kpis(跨员工共享客户可能重复计)
+        "active_customers": sum(p.active_friends for p in prev_pms),
+        "active_employees": sum(1 for p in prev_pms if p.days_with_data > 0),
+        "msg_total": sum(p.msg_sent + p.msg_recv for p in prev_pms),
+        "cust_threads": sum(p.cust_threads for p in prev_pms),
+    }
+    # 前窗无消息(prev=0)不算环比——None 而非 0/负∞
+    prev_msg = prev_kpis["msg_total"]
+    msg_delta = (
+        round((kpis["msg_total"] - prev_msg) / prev_msg, 3)
+        if prev_msg > 0 else None
+    )
+
+    # ---- 维度分布(全员 score_employee 的维度状态计数) ----
+    dim_summary: dict[str, dict] = {}
+    for a in assembled.values():
+        for key, dim in a["score"]["dimensions"].items():
+            e = dim_summary.setdefault(key, {
+                "name": dim.get("name"), "weight": dim.get("weight", 0),
+                "scored_count": 0, "insufficient_count": 0,
+                "pending_count": 0, "_scores": [],
+            })
+            if dim["status"] == "scored":
+                e["scored_count"] += 1
+                e["_scores"].append(dim["score"])
+            elif dim["status"] == "insufficient":
+                e["insufficient_count"] += 1
+            else:  # pending / pending_data
+                e["pending_count"] += 1
+    for e in dim_summary.values():
+        scores = e.pop("_scores")
+        e["avg_score"] = (
+            sum(scores) / len(scores) if scores else None
+        )
+
+    # ---- 异常汇总:critical 先、warning 后,同 severity 按 affected desc ----
+    # dashboard 卡片 enrich employee_name(staff 名,assemble 已在手)供前端
+    # 跳员工详情;员工详情端点的 anomalies 不带(自指无意义)
+    anomalies = [
+        {**a, "employee_name": data["name"]}
+        for data in assembled.values()
+        for a in data["anomalies"]
+    ]
+    sev_rank = {"critical": 0, "warning": 1}
+    anomalies.sort(key=lambda a: (
+        sev_rank.get(a["severity"], 9),
+        -a.get("affected_count", 0),
+        a["employee_user_id"],
+    ))
+
+    return {
+        "scope": {"channel": channel, "start": start, "end": end,
+                  "compare": compare},
+        "data_as_of": await health_svc.data_as_of(session),
+        "metric_version": METRIC_VERSION,
+        "config_source": config_source,
+        "kpis": kpis,
+        "prev_kpis": prev_kpis,
+        "msg_delta": msg_delta,
+        "communication_trend": comm_trend,
+        "service_trend": service_trend,
+        "lifecycle": lifecycle,
+        "dimension_summary": dim_summary,
+        "anomalies": anomalies,
+        "action_summary": await metrics_svc.action_counts(session, channel=ch),
+        "caliber_notes": {
+            "active_customers": "kpis.active_customers 为全员周期 distinct "
+            "求和,跨员工共享客户可能重复计",
+            "trend_active_customers": "communication_trend.active_customers "
+            "为宽表日值团队合计(日口径求和)",
+            "reply_2h_rate": "分子=fact 当日 ≤2h 计数,分母=宽表当日串数",
+        },
+    }
+
+
+@router.get("/employees")
+async def management_employees(
+    session: SessionDep,
+    channel: AllChannelParam = "all",
+    start: YmdParam | None = None,
+    end: YmdParam | None = None,
+    view: ViewParam = "management",
+    keyword: str | None = None,
+    status: StatusParam = "all",
+    sort_by: SortByParam = "anomaly_severity",
+    sort_order: SortOrderParam = "desc",
+    page: int = Query(1, ge=1),
+    page_size: int = Query(20, ge=1, le=100),
+) -> dict[str, Any]:
+    """员工列表(一期 management/workload/service/customer 四视图共用
+    行集,view 仅回显)。默认 anomaly_severity 排序:含 critical 者 →
+    权重和 → 卡片数;total_score 排序 None 恒排最后。"""
+    start, end = _window(start, end)
+    ch = _translate(channel)
+    config, config_source = await asm.load_score_config(session)
+    assembled = await asm.assemble_employees(
+        session, config, start, end, ch, with_prev=True
+    )
+    items = list(assembled.items())
+
+    if ch is not None:
+        # 渠道过滤=账号归属(该渠道无账号的员工不进列表;有账号无数据仍
+        # 展示零值行)
+        owners_uids = set((await account_map(session, ch)).values())
+        items = [(u, d) for u, d in items if u in owners_uids]
+    if keyword:
+        kw = keyword.strip().lower()
+        items = [
+            (u, d) for u, d in items
+            if kw in (d["name"] or "").lower() or kw in u.lower()
+        ]
+    if status == "on_job":
+        items = [(u, d) for u, d in items if d["is_on_job"] is True]
+    elif status == "offline":
+        items = [(u, d) for u, d in items if d["is_on_job"] is not True]
+
+    items.sort(key=lambda kv: kv[0])  # 决胜底座:user_id asc(稳定排序)
+    if sort_by == "anomaly_severity":
+        items.sort(key=lambda kv: (
+            any(a["severity"] == "critical" for a in kv[1]["anomalies"]),
+            kv[1]["anomaly_weight"], kv[1]["anomaly_count"],
+        ), reverse=(sort_order == "desc"))
+    elif sort_by == "total_score":
+        # None(样本不足等)恒排最后,与升降序无关
+        if sort_order == "desc":
+            items.sort(key=lambda kv: (
+                kv[1]["score"]["total_score"] is None,
+                -(kv[1]["score"]["total_score"] or 0),
+            ))
+        else:
+            items.sort(key=lambda kv: (
+                kv[1]["score"]["total_score"] is None,
+                kv[1]["score"]["total_score"] or 0,
+            ))
+    else:  # active_friends / cust_threads(PeriodMetrics 数值列)
+        if sort_order == "desc":
+            items.sort(key=lambda kv: -getattr(kv[1]["cur"], sort_by))
+        else:
+            items.sort(key=lambda kv: getattr(kv[1]["cur"], sort_by))
+
+    total = len(items)
+    page_rows = items[(page - 1) * page_size: page * page_size]
+    return {
+        "total": total,
+        "page": page,
+        "page_size": page_size,
+        "rows": [asm.build_employee_row(u, d, config) for u, d in page_rows],
+        "scope": {"channel": channel, "start": start, "end": end,
+                  "view": view},
+        "data_as_of": await health_svc.data_as_of(session),
+        "metric_version": METRIC_VERSION,
+        "config_source": config_source,
+    }
+
+
+@router.get("/employees/{user_id}")
+async def management_employee_detail(
+    session: SessionDep,
+    user_id: str,
+    channel: AllChannelParam = "all",
+    start: YmdParam | None = None,
+    end: YmdParam | None = None,
+) -> dict[str, Any]:
+    """员工详情:身份+账号清单+期指标全字段+评分完整明细(含逐指标
+    metrics_detail)+异常卡片+prev/baseline 原始 PeriodMetrics。"""
+    start, end = _window(start, end)
+    ch = _translate(channel)
+    staff = await _get_staff(session, user_id)
+    config, config_source = await asm.load_score_config(session)
+
+    cur_map = await period_metrics(session, start, end, ch, user_ids={user_id})
+    bs, be = baseline_window(start)
+    base_map = await period_metrics(session, bs, be, ch, user_ids={user_id})
+    ps, pe = prev_window(start, end)
+    prev_map = await period_metrics(session, ps, pe, ch, user_ids={user_id})
+    cur, base, prev = (cur_map.get(user_id), base_map.get(user_id),
+                       prev_map.get(user_id))
+    if cur is None:  # 防御:_get_staff 已保证在 staff,period_metrics 必含
+        raise HTTPException(404, f"employee {user_id} not found")
+    team = asm.team_derived_medians(
+        await period_metrics(session, start, end, ch)
+    )
+    score = asm.score_with_guards(config, cur, baseline=base, team=team,
+                                  prev=prev)
+    anomalies = detect_anomalies(
+        user_id, cur, base, n_days=len(day_range(start, end)), config=config
+    )
+
+    accounts: list[dict] = []
+    for wa in (await session.execute(
+        sa.select(WechatAccount).where(WechatAccount.user_id == user_id)
+    )).scalars():
+        accounts.append({
+            "channel": "wechat", "account_id": wa.wx_id,
+            "nick_name": wa.nick_name, "user_name": wa.user_name,
+        })
+    for wa in (await session.execute(
+        sa.select(WhatsappAccount).where(WhatsappAccount.user_id == user_id)
+    )).scalars():
+        accounts.append({
+            "channel": "whatsapp", "account_id": wa.uid,
+            "nick_name": wa.nick_name, "user_name": wa.user_name,
+        })
+
+    return {
+        "user_id": user_id,
+        "name": staff.name,
+        "is_on_job": staff.is_on_job,
+        "accounts": accounts,
+        "metrics": cur._asdict(),
+        "score": score,
+        "anomalies": anomalies,
+        "prev": prev._asdict() if prev is not None else None,
+        "baseline": base._asdict() if base is not None else None,
+        "scope": {"channel": channel, "start": start, "end": end},
+        "data_as_of": await health_svc.data_as_of(session),
+        "metric_version": METRIC_VERSION,
+        "config_source": config_source,
+    }
+
+
+@router.get("/employees/{user_id}/metrics")
+async def management_employee_metrics(
+    session: SessionDep,
+    user_id: str,
+    section: SectionParam = "overview",
+    channel: AllChannelParam = "all",
+    start: YmdParam | None = None,
+    end: YmdParam | None = None,
+) -> dict[str, Any]:
+    """员工分段指标:该域期指标 + 窗口逐日趋势 + 四对比
+    (current/prev/baseline/median,派生率走 scoring.derive_metrics 口径)。"""
+    start, end = _window(start, end)
+    ch = _translate(channel)
+    await _get_staff(session, user_id)
+    cur_map = await period_metrics(session, start, end, ch, user_ids={user_id})
+    bs, be = baseline_window(start)
+    base_map = await period_metrics(session, bs, be, ch, user_ids={user_id})
+    ps, pe = prev_window(start, end)
+    prev_map = await period_metrics(session, ps, pe, ch, user_ids={user_id})
+    cur, base, prev = (cur_map.get(user_id), base_map.get(user_id),
+                       prev_map.get(user_id))
+    if cur is None:
+        raise HTTPException(404, f"employee {user_id} not found")
+    team = asm.team_derived_medians(
+        await period_metrics(session, start, end, ch)
+    )
+
+    if section == "calls":
+        src_rows = await asm.call_daily_rows(session, start, end,
+                                             user_id=user_id)
+    else:
+        src_rows = await asm.wide_daily_rows(session, start, end, ch,
+                                             user_id=user_id)
+    by_day = {r["day"]: r for r in src_rows}
+    cols = _SECTION_TREND_COLS[section]
+    trend = []
+    for day in day_range(start, end):
+        row = by_day.get(day)
+        point: dict[str, Any] = {"day": day}
+        for col in cols:
+            if row is not None:
+                point[col] = row.get(col)
+            else:  # 无数据日:计数列补 0,分位列补 None
+                point[col] = None if col.startswith("first_reply") else 0
+        trend.append(point)
+
+    return {
+        "section": section,
+        "metrics": {f: getattr(cur, f) for f in _SECTION_FIELDS[section]},
+        "trend": trend,
+        "comparisons": asm.derived_comparisons(cur, prev, base, team),
+        "scope": {"channel": channel, "start": start, "end": end,
+                  "user_id": user_id},
+        "data_as_of": await health_svc.data_as_of(session),
+        "metric_version": METRIC_VERSION,
+    }
+
+
+@router.get("/employees/{user_id}/drilldown")
+async def management_employee_drilldown(
+    session: SessionDep,
+    user_id: str,
+    metric_code: str,
+    channel: AllChannelParam = "all",
+    start: YmdParam | None = None,
+    end: YmdParam | None = None,
+    page: int = Query(1, ge=1),
+    page_size: int = Query(20, ge=1, le=100),
+) -> dict[str, Any]:
+    """指标下钻(白名单六项,外 422):首响分位逐串证据 / 未回串 /
+    降温·沉睡客户名单 / 通话跟进列表。所有分支按员工 owner 账号过滤。"""
+    if metric_code not in _DRILLDOWN_CODES:
+        raise HTTPException(422, f"unknown metric_code: {metric_code}")
+    start, end = _window(start, end)
+    ch = _translate(channel)
+    await _get_staff(session, user_id)
+    scope = {"user_id": user_id, "metric_code": metric_code,
+             "channel": channel, "start": start, "end": end}
+    owners = await asm.user_owner_accounts(session, user_id, ch)
+
+    def _paged(items: list[dict]) -> dict[str, Any]:
+        ix = (page - 1) * page_size
+        return {"items": items[ix: ix + page_size], "total": len(items),
+                "page": page, "page_size": page_size, "scope": scope}
+
+    if metric_code in ("first_reply_p50", "first_reply_p90"):
+        if not owners:
+            return _paged([])
+        total, items = await asm.fr_fact_rows(
+            session, owners, ch, start, end, page=page, page_size=page_size
+        )
+        return {"items": items, "total": total, "page": page,
+                "page_size": page_size, "scope": scope}
+
+    if metric_code == "unreplied":
+        if not owners:  # 无账号→必空,免进上游决赛圈点查
+            return _paged([])
+        # 上游无私有 owner 过滤:一次拉全量决赛圈结果(候选 ≤500 时完整),
+        # 按 owner 账号过滤后内存分页;候选超限标 truncated(过滤可能不全)
+        res = await metrics_svc.unreplied(
+            session, channel=ch, hours=24, page=1, page_size=_UNREPLIED_FETCH
+        )
+        owner_set = set(owners)
+        owned = [i for i in res["items"]
+                 if i["owner_account_id"] in owner_set]
+        out = _paged(owned)
+        out["note"] = ("按该员工 owner 账号自全量未回清单过滤"
+                       "(hours=24,与看板清单同源同判定)")
+        if res["total"] > len(res["items"]):
+            out["truncated"] = True
+        return out
+
+    if metric_code in ("cooling_customers", "dormant_customers"):
+        want = ("cooling" if metric_code == "cooling_customers"
+                else "dormant")
+        if not owners:
+            return _paged([])
+        matches = await asm.lifecycle_customers(session, owners, end, want)
+        return _paged(matches)
+
+    # call_followup:窗口通话列表(start desc)+ 期聚合摘要
+    # (逐通话跟进标记复用批次A _followup_exists 太重,留批次C按需再加)
+    total, items = await asm.user_calls_page(
+        session, user_id, start, end, page=page, page_size=page_size
+    )
+    summary_rows = await asm.call_daily_rows(session, start, end,
+                                             user_id=user_id)
+    summary = {col: sum(r[col] for r in summary_rows)
+               for col in ("call_count", "call_seconds",
+                           "answered_call_count", "call_followup_count")}
+    return {"items": items, "total": int(total), "page": page,
+            "page_size": page_size, "summary": summary, "scope": scope,
+            "note": "逐通话跟进标记留批次C;此处为窗口通话列表+期聚合"
+                    "(followup 为接通后24h内有跟进的通话数)"}
+
+
+@router.get("/metric-definitions")
+async def management_metric_definitions(
+    session: SessionDep,
+) -> dict[str, Any]:
+    """指标口径字典 + 当前评分配置(含 pending 维度)+ 三方口径差异说明。
+    config_source: "db"=激活配置 / "default"=未种子回退默认。"""
+    config, source = await asm.load_score_config(session)
+    return {
+        "definitions": METRIC_DEFINITIONS,
+        "score_config": {
+            "version": config.get("version"),
+            "name": config.get("name"),
+            "trial": config.get("trial"),
+            "normalization": config.get("normalization"),
+            "sample_guards": config.get("sample_guards"),
+            "grade_bounds": config.get("grade_bounds"),
+            "dimensions": config.get("dimensions"),
+        },
+        "config_source": source,
+        "caliber_notes": CALIBER_NOTES,
+    }

yunke-server/app/api/routers/sessions.py

@@ -22,7 +22,13 @@ from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.api.deps import get_session
 from app.api.schemas import SessionListOut, SessionOut
-from app.db.models import ChatGroup, Customer, Message, MsgDailyStats
+from app.db.models import (
+    ChatGroup,
+    Customer,
+    CustomerAccountLink,
+    Message,
+    MsgDailyStats,
+)
 from app.storage.summary import day_key, has_rows as _summary_has_rows
 
 router = APIRouter(prefix="/api", tags=["sessions"])
@@ -117,19 +123,42 @@ async def _summary_rows(
 
 
 async def _meta(session: AsyncSession, owner: str, channel: str, friend_ids: list[str], room_ids: list[str]):
-    """查 customer/chat_group 表合并昵称/头像;好友行额外带 delete_flag(is_del 过滤用)。
+    """查 customer_account_link(主)/customer(兜底)/chat_group 合并昵称/头像。
+
+    好友名优先读 ``customer_account_link`` 的 per-owner 快照——共享客户的
+    档案行(customer 全局单行,last-wins)可能挂在别的员工名下,按 owner 查
+    档案会查空,会话列表就回退显示 wxid(2026-09-09 用户报「有昵称却显示
+    微信号」);link 表每账号一行,回填后都有昵称。link 没覆盖的(空表过渡/
+    老数据)回退档案路径。
 
     friends 值为 ``(name, avatar, delete_flag)``;群无删除标记,groups 值仍为
     ``(name, avatar)``。
     """
     friends: dict[str, tuple[str, str | None, int | None]] = {}
     if friend_ids:
+        for fid, remark, nick, real, avatar, delete_flag in (await session.execute(
+            sa.select(
+                CustomerAccountLink.friend_id, CustomerAccountLink.friend_remark,
+                CustomerAccountLink.friend_nickname, CustomerAccountLink.real_name,
+                CustomerAccountLink.head_image_url, CustomerAccountLink.delete_flag,
+            )
+            .where(
+                CustomerAccountLink.channel == channel,
+                CustomerAccountLink.owner_account_id == owner,
+                CustomerAccountLink.friend_id.in_(friend_ids),
+            )
+        )).all():
+            friends[fid] = (remark or nick or real or fid, avatar, delete_flag)
+        # link 未覆盖的好友回退档案(按 owner 过滤;共享好友在此仍可能查空,
+        # 上层以 wxid 兜底显示)
+        missing = [fid for fid in friend_ids if fid not in friends]
+        if missing:
             for fid, remark, nick, real, avatar, delete_flag in (await session.execute(
                 sa.select(
                     Customer.friend_id, Customer.friend_remark, Customer.friend_nickname,
                     Customer.real_name, Customer.head_image_url, Customer.delete_flag,
                 )
-            .where(Customer.channel == channel, Customer.owner_account_id == owner, Customer.friend_id.in_(friend_ids))
+                .where(Customer.channel == channel, Customer.owner_account_id == owner, Customer.friend_id.in_(missing))
             )).all():
                 friends[fid] = (remark or nick or real or fid, avatar, delete_flag)
     groups: dict[str, tuple[str, str | None]] = {}

yunke-server/app/api/routers/staff_chat_stats.py

@@ -20,7 +20,7 @@ from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.api.deps import get_session
 from app.api.schemas import StaffChatCustomerOut, StaffChatStatsOut, StaffChatStatsSummary
-from app.db.models import Customer, Message, MsgDailyStats
+from app.db.models import Customer, CustomerAccountLink, Message, MsgDailyStats
 from app.storage.summary import day_key, has_rows as _summary_has_rows
 
 router = APIRouter(prefix="/api", tags=["staff-chat-stats"])
@@ -144,8 +144,30 @@ async def _aggregate_summary(
 
 
 async def _customer_names(session: AsyncSession, owner: str, talker_ids: list[str]) -> dict[str, tuple[str, str, str]]:
+    """客户名/头像解析:优先 customer_account_link per-owner 快照,档案兜底。
+
+    共享客户的档案行(customer 全局单行,last-wins)可能挂在别的员工名下,
+    按 owner 查档案会查空、明细列表回退显示 wxid(2026-09-09,同 sessions
+    ._meta 修复)。
+    """
     if not talker_ids:
         return {}
+    info: dict[str, tuple[str, str, str]] = {}
+    link_stmt = sa.select(
+        CustomerAccountLink.friend_id,
+        CustomerAccountLink.friend_remark,
+        CustomerAccountLink.friend_nickname,
+        CustomerAccountLink.real_name,
+        CustomerAccountLink.head_image_url,
+    ).where(
+        CustomerAccountLink.channel == "wechat",
+        CustomerAccountLink.owner_account_id == owner,
+        CustomerAccountLink.friend_id.in_(talker_ids),
+    )
+    for fid, remark, nick, real, head in (await session.execute(link_stmt)).all():
+        info[fid] = (remark or nick or real or fid, real or "", head or "")
+    missing = [t for t in talker_ids if t not in info]
+    if missing:
         stmt = sa.select(
             Customer.friend_id,
             Customer.friend_remark,
@@ -155,9 +177,8 @@ async def _customer_names(session: AsyncSession, owner: str, talker_ids: list[st
         ).where(
             Customer.channel == "wechat",
             Customer.owner_account_id == owner,
-        Customer.friend_id.in_(talker_ids),
+            Customer.friend_id.in_(missing),
         )
-    info: dict[str, tuple[str, str, str]] = {}
         for fid, remark, nick, real, head in (await session.execute(stmt)).all():
             info[fid] = (remark or nick or real or fid, real or "", head or "")
     return info

yunke-server/app/api/routers/staff_stats.py

@@ -40,7 +40,14 @@ from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.api.deps import get_session
 from app.api.schemas import StaffStatsCountsOut, StaffStatsDetailOut
-from app.db.models import ChatGroup, Customer, Message, PhoneCall, WechatAccount
+from app.db.models import (
+    ChatGroup,
+    Customer,
+    CustomerAccountLink,
+    Message,
+    PhoneCall,
+    WechatAccount,
+)
 
 router = APIRouter(prefix="/api", tags=["staff-stats"])
 
@@ -96,50 +103,57 @@ async def _new_customers(
 ) -> tuple[int, list[dict[str, Any]]]:
     """新客户:add_time 窗内;add_time IS NULL 用首条消息时间兜底。
 
+    读 ``customer_account_link``(2026-09-09):customer 档案全局单行、
+    归属 last-wins,共享客户在其他员工名下会漏计;link 每账号一行,与
+    云客按员工统计的口径一致(数字会比档案口径大)。
+
     无 ``detail`` 分支——计数模式有意复用明细物化(窗内新增客户通常
     几十行,``len()`` 即可;COUNT 需 direct+fallback 双查询,不值)。
     """
-    base = [Customer.channel == "wechat", Customer.owner_account_id == wxid]
+    base = [
+        CustomerAccountLink.channel == "wechat",
+        CustomerAccountLink.owner_account_id == wxid,
+    ]
     # 兜底口径:每个 add_time 为空的客户,取其与该员工首条消息 min(timestamp)
     # (LEFT JOIN 走 ix_message_channel_owner_talker_time,HAVING 在 SQL 侧过滤窗)。
     fallback = (
         sa.select(
-            Customer.friend_id,
+            CustomerAccountLink.friend_id,
-            Customer.friend_nickname,
+            CustomerAccountLink.friend_nickname,
-            Customer.friend_remark,
+            CustomerAccountLink.friend_remark,
-            Customer.head_image_url,
+            CustomerAccountLink.head_image_url,
             sa.func.min(Message.timestamp).label("first_ts"),
         )
         .outerjoin(
             Message,
             sa.and_(
                 Message.channel == "wechat",
-                Message.owner_account_id == Customer.owner_account_id,
+                Message.owner_account_id == CustomerAccountLink.owner_account_id,
-                Message.talker_id == Customer.friend_id,
+                Message.talker_id == CustomerAccountLink.friend_id,
                 Message.timestamp.is_not(None),
             ),
         )
-        .where(*base, Customer.add_time.is_(None))
+        .where(*base, CustomerAccountLink.add_time.is_(None))
-        # GROUP BY 显式列出全部裸选列:friend_id 是 Customer 唯一 PK,其余列
+        # GROUP BY 显式列出全部裸选列:friend_id 是 link 复合 PK 的尾列,
-        # 函数依赖于它→分组结果不变;MySQL 8 FD 推断可容忍裸列,但显式列表
+        # (owner,friend) 已由 WHERE 钉死,其余列函数依赖于它→分组结果不变;
-        # 在 ONLY_FULL_GROUP_BY 下部署安全(SQLite 同样兼容)。
+        # MySQL ONLY_FULL_GROUP_BY 部署安全(SQLite 同样兼容)。
         .group_by(
-            Customer.friend_id,
+            CustomerAccountLink.friend_id,
-            Customer.friend_nickname,
+            CustomerAccountLink.friend_nickname,
-            Customer.friend_remark,
+            CustomerAccountLink.friend_remark,
-            Customer.head_image_url,
+            CustomerAccountLink.head_image_url,
         )
         .having(sa.func.min(Message.timestamp) >= start)
         .having(sa.func.min(Message.timestamp) <= end)
     )
     # 直接口径:add_time 本身在窗内。
     direct = sa.select(
-        Customer.friend_id,
+        CustomerAccountLink.friend_id,
-        Customer.friend_nickname,
+        CustomerAccountLink.friend_nickname,
-        Customer.friend_remark,
+        CustomerAccountLink.friend_remark,
-        Customer.head_image_url,
+        CustomerAccountLink.head_image_url,
-        Customer.add_time,
+        CustomerAccountLink.add_time,
-    ).where(*base, Customer.add_time >= start, Customer.add_time <= end)
+    ).where(*base, CustomerAccountLink.add_time >= start, CustomerAccountLink.add_time <= end)
 
     rows: list[dict[str, Any]] = [
         {
@@ -237,19 +251,43 @@ async def _red_transfer(
     talker_ids = [m.talker_id for m in msgs if m.talker_id]
     nick_map: dict[str, str] = {}
     if talker_ids:
+        # 昵称优先 link per-owner 快照(共享好友档案行可能挂别的员工名下,
+        # 2026-09-09 同 sessions._meta),档案兜底
         nick_map = {
             fid: nick
             for fid, nick in (
                 await session.execute(
-                    sa.select(Customer.friend_id, Customer.friend_nickname).where(
+                    sa.select(
-                        Customer.channel == "wechat",
+                        CustomerAccountLink.friend_id,
-                        Customer.owner_account_id == wxid,
+                        CustomerAccountLink.friend_nickname,
-                        Customer.friend_id.in_(talker_ids),
+                    ).where(
+                        CustomerAccountLink.channel == "wechat",
+                        CustomerAccountLink.owner_account_id == wxid,
+                        CustomerAccountLink.friend_id.in_(talker_ids),
                     )
                 )
             ).all()
             if nick
         }
+        missing = [t for t in talker_ids if t not in nick_map]
+        if missing:
+            nick_map.update(
+                {
+                    fid: nick
+                    for fid, nick in (
+                        await session.execute(
+                            sa.select(
+                                Customer.friend_id, Customer.friend_nickname
+                            ).where(
+                                Customer.channel == "wechat",
+                                Customer.owner_account_id == wxid,
+                                Customer.friend_id.in_(missing),
+                            )
+                        )
+                    ).all()
+                    if nick
+                }
+            )
     rows: list[dict[str, Any]] = []
     for m in msgs:
         raw_name = (m.raw_json or {}).get("name") if m.raw_json else None
@@ -273,15 +311,20 @@ async def _flag_customers(
     flag_cond: sa.ColumnElement,
     *,
     detail: bool,
+    model: type,
 ) -> tuple[int, list[dict[str, Any]]]:
     """del_customers / blocked_customers 共用:现存量口径,忽略时间窗。
 
+    ``model`` 由调用方决定(两者列名同形):del 走 ``CustomerAccountLink``
+    (delete_flag per-relation,共享好友不漏),blocked 走 ``Customer``
+    档案(is_block 未镜像进 link,2026-09-09)。
+
     无时间字段→明细行 time 用 updated_at 毫秒(仅展示;update 触发即变)。
     """
-    conds = [Customer.channel == "wechat", Customer.owner_account_id == wxid, flag_cond]
+    conds = [model.channel == "wechat", model.owner_account_id == wxid, flag_cond]
     count = (
         await session.execute(
-            sa.select(sa.func.count()).select_from(Customer).where(*conds)
+            sa.select(sa.func.count()).select_from(model).where(*conds)
         )
     ).scalar_one()
     if not detail:
@@ -289,13 +332,13 @@ async def _flag_customers(
     rows = (
         await session.execute(
             sa.select(
-                Customer.friend_id,
+                model.friend_id,
-                Customer.friend_nickname,
+                model.friend_nickname,
-                Customer.friend_remark,
+                model.friend_remark,
-                Customer.updated_at,
+                model.updated_at,
             )
             .where(*conds)
-            .order_by(Customer.updated_at.desc(), Customer.friend_id.asc())
+            .order_by(model.updated_at.desc(), model.friend_id.asc())
         )
     ).all()
     return count, [
@@ -311,18 +354,26 @@ async def _flag_customers(
 async def _del_customers(
     session: AsyncSession, wxid: str, start: int, end: int, detail: bool
 ) -> tuple[int, list[dict[str, Any]]]:
-    """删除客户:delete_flag=1 现存量(start/end 按口径忽略)。"""
+    """删除客户:delete_flag=1 现存量(start/end 按口径忽略)。
+
+    读 link(per-relation delete_flag,共享好友不漏计,2026-09-09)。
+    """
     return await _flag_customers(
-        session, wxid, Customer.delete_flag == 1, detail=detail
+        session, wxid, CustomerAccountLink.delete_flag == 1,
+        detail=detail, model=CustomerAccountLink,
     )
 
 
 async def _blocked_customers(
     session: AsyncSession, wxid: str, start: int, end: int, detail: bool
 ) -> tuple[int, list[dict[str, Any]]]:
-    """流失(拉黑)客户:is_block=1 现存量(start/end 按口径忽略)。"""
+    """流失(拉黑)客户:is_block=1 现存量(start/end 按口径忽略)。
+
+    保持档案口径:is_block 未镜像进 link 表,切了会漏;已知偏差=共享好友
+    在其他员工名下的拉黑不计入(待 link 补列后切换)。
+    """
     return await _flag_customers(
-        session, wxid, Customer.is_block.is_(True), detail=detail
+        session, wxid, Customer.is_block.is_(True), detail=detail, model=Customer
     )
 
 

yunke-server/app/api/schemas.py

@@ -39,6 +39,13 @@ class CustomerOut(BaseModel):
     last_chat_time: int | None = None
     add_time: int | None = None
     message_count: int | None = None
+    # 累计发送/接收条数(同步自云客 friend 记录的 sendNum/receiveNum;员工
+    # 客户页「发送条数/接收条数」列用,2026-09-08)
+    send_num: int | None = None
+    receive_num: int | None = None
+    # 云客数据来源代码(customer_account_link 路径直读;档案路径为 None,
+    # 前端回退 raw_json.fromType)
+    from_type: int | None = None
     version: str | None = None
     # Verbatim upstream friend record (~60 camelCase fields). Surfaced so the
     # all-fields drawer can render every column the 云客 source page shows
@@ -192,6 +199,17 @@ class GroupOut(BaseModel):
     owner_avatar: str | None = None
     friend_count: int | None = None
     create_time: int | None = None  # 建群时间 ms epoch
+    # 微信群统计页(2026-09-09,云客 getChatroomList 同款)
+    group_remark: str | None = None  # 群备注
+    staff_nickname: str | None = None  # 员工微信·昵称(wechat_account.nick_name)
+    staff_wx_alias: str | None = None  # 员工微信·微信号(wechat_account.alias)
+    staff_avatar: str | None = None  # 员工微信·头像
+    staff_name: str | None = None  # 员工信息·姓名(staff.name)
+    staff_phone: str | None = None  # 员工信息·手机(staff.phone)
+    # 统计时段窗内聚合(仅请求带 msg_start/msg_end 时非 None):
+    window_msg_count: int | None = None  # 沟通消息数(窗内,msg_daily_stats)
+    window_added: int | None = None  # 新增成员数(窗内,按天表求和)
+    window_lost: int | None = None  # 退出成员数(窗内)
     raw_json: dict[str, Any] | None = None
 
 

yunke-server/app/db/models.py

@@ -262,6 +262,46 @@ class Customer(Base):
     )
 
 
+class CustomerAccountLink(Base):
+    """账号↔客户 多对多关联(customer_account_link,2026-09-08)。
+
+    ``customer`` 表 PK=``friend_id`` 全局一客户一行,归属=最后抓取员工
+    (last-wins)——共享客户(同一人加多个员工)在其他员工名下「消失」:
+    实测 Lily 云客好友 36 vs 镜像页面 12,24 个全在别的员工名下。云客
+    的口径是**每个账号各算一个**(per-employee 列表连备注/收发计数都按
+    关系各存一份);本表每个「渠道×账号×客户」一行,由
+    :func:`app.storage.repos.upsert_customer` 随档案同事务维护,员工维度
+    的列表/计数(`/api/customers?owner_account_id=`)读这里。
+
+    快照列为员工客户页所需(昵称/备注/头像 per-relation);全字段档案
+    (raw_json/60 列)仍在 ``customer`` 表按 friend_id 关联。
+    """
+
+    __tablename__ = "customer_account_link"
+
+    channel: Mapped[str] = mapped_column(String(16), primary_key=True)
+    owner_account_id: Mapped[str] = mapped_column(String(128), primary_key=True)
+    friend_id: Mapped[str] = mapped_column(String(128), primary_key=True)
+    # per-relation 展示快照(云客好友记录按员工各一份;备注是员工自己的)
+    friend_nickname: Mapped[str | None] = mapped_column(String(255), nullable=True)
+    friend_remark: Mapped[str | None] = mapped_column(String(255), nullable=True)
+    head_image_url: Mapped[str | None] = mapped_column(String(1024), nullable=True)
+    real_name: Mapped[str | None] = mapped_column(String(64), nullable=True)
+    phone: Mapped[str | None] = mapped_column(String(64), nullable=True)
+    last_chat_time: Mapped[int | None] = mapped_column(BigInteger, nullable=True)
+    add_time: Mapped[int | None] = mapped_column(BigInteger, nullable=True)
+    send_num: Mapped[int | None] = mapped_column(Integer, nullable=True)
+    receive_num: Mapped[int | None] = mapped_column(Integer, nullable=True)
+    message_count: Mapped[int | None] = mapped_column(Integer, nullable=True)
+    # 云客 fromType 代码(数据来源列;int,前端 fromTypeLabel 映射)
+    from_type: Mapped[int | None] = mapped_column(Integer, nullable=True)
+    # 同 customer.delete_flag 口径(int 0/1)
+    delete_flag: Mapped[int | None] = mapped_column(Integer, nullable=True)
+
+    fetched_at: Mapped[dt.datetime] = _fetched_at()
+    updated_at: Mapped[dt.datetime] = _updated_at()
+
+
 class ChatGroup(Base):
     """聊天群 — source: ``POST /wechatweb/chatroom/getChatroomList``.
 
@@ -304,6 +344,9 @@ class ChatGroup(Base):
     owner_avatar: Mapped[str | None] = mapped_column(String(1024), nullable=True)
     friend_count: Mapped[int | None] = mapped_column(Integer, nullable=True)  # 群成员中员工好友数
     create_time: Mapped[int | None] = mapped_column(BigInteger, nullable=True)  # 建群时间 ms epoch
+    # 群备注(微信群统计页「群备注」列;getChatroomList.remark /
+    # friend_list/es 的 friendWxRemark,2026-09-09)
+    group_remark: Mapped[str | None] = mapped_column(String(255), nullable=True)
 
     version: Mapped[str | None] = mapped_column(String(64), nullable=True)
     raw_json: Mapped[dict[str, Any] | None] = mapped_column(JSON, nullable=True)
@@ -322,6 +365,34 @@ class ChatGroup(Base):
     )
 
 
+class ChatGroupMemberStats(Base):
+    """群成员进出按天统计(chat_group_member_stats,2026-09-09)。
+
+    云客「微信群统计」的新增/退出成员数是 ``getChatroomList`` 按
+    ``startTime~endTime`` 任意窗实时算的;本地无成员进出事件流,改为每夜
+    抓一次「当日窗」的 addMembers/lossMembers 落一行,页面任意日窗=按天
+    求和。**上线日起积累**(历史日期无数据;chat_group.add_members/
+    loss_members 旧列保留作最近一次抓取窗的快照)。
+    """
+
+    __tablename__ = "chat_group_member_stats"
+
+    channel: Mapped[str] = mapped_column(String(16), primary_key=True)
+    owner_account_id: Mapped[str] = mapped_column(String(128), primary_key=True)
+    room_id: Mapped[str] = mapped_column(String(128), primary_key=True)
+    # yyyymmdd(上海自然日,同 msg_daily_stats 口径)
+    day: Mapped[int] = mapped_column(Integer, primary_key=True)
+    added: Mapped[int] = mapped_column(
+        Integer, nullable=False, default=0, server_default=sa.text("0")
+    )
+    lost: Mapped[int] = mapped_column(
+        Integer, nullable=False, default=0, server_default=sa.text("0")
+    )
+
+    fetched_at: Mapped[dt.datetime] = _fetched_at()
+    updated_at: Mapped[dt.datetime] = _updated_at()
+
+
 class GroupMember(Base):
     """群成员 — composite PK (channel, room_id, member_id).
 
@@ -466,6 +537,18 @@ class Message(Base):
             "ix_message_fetched_at",
             "fetched_at",
         ),
+        # 该回未回决赛圈点查(owner+talker 定位末条消息)在 channel=None
+        # (全平台计数——管理驾驶舱 action_counts 复用)时无渠道前缀条件,
+        # 上面全部以 channel 打头的索引用不上,逐候选退化扫表+filesort:
+        # 2026-09-10 服务器实测 dashboard 34~37s 撞前端 15s 超时
+        # (ECONNABORTED);补无渠道前缀索引后 1.3~1.8s(100 万行在线建
+        # 索引 49s)。「模型+迁移双声明」防 alembic autogenerate 反 DROP。
+        Index(
+            "ix_message_owner_talker_time",
+            "owner_account_id",
+            "talker_id",
+            "timestamp",
+        ),
     )
 
 
@@ -959,11 +1042,249 @@ class SensitiveScanState(Base):
     updated_at: Mapped[dt.datetime] = _updated_at()
 
 
+# ==========================================================================
+# 经营管理后台(2026-09-08 v2 spec,批次A)——fact/宽表/通话小表 + 三张业务表
+# ==========================================================================
+
+
+class FirstReplyFact(Base):
+    """首响事实表(管理域)——一行 = 一个被回的 1:1 客户消息串(v2 §3.1)。
+
+    跨日精确串口径:按会话**全历史**计算,fr_ms = 员工首条回复 ts − 串末条
+    客户消息 ts,day = 串末条所在上海自然日。区别于 msg_daily_stats 首响
+    三列的日切近似(跨夜串整条丢失,v2 §1.1 #1)。只写 1:1(friend)会话
+    ——群串语义不成立。由回填 CLI / 4h 滚动 / 夜间全量重算,**不挂写钩子**
+    (写钩子零改动)。用途:精确 P50/P90、2h/24h 回复率分子、下钻证据。
+    """
+
+    __tablename__ = "first_reply_fact"
+
+    channel: Mapped[str] = mapped_column(String(16), primary_key=True)
+    owner_account_id: Mapped[str] = mapped_column(String(128), primary_key=True)
+    peer_id: Mapped[str] = mapped_column(String(128), primary_key=True)
+    thread_end_ts: Mapped[int] = mapped_column(BigInteger, primary_key=True)
+    reply_ts: Mapped[int] = mapped_column(BigInteger, primary_key=True)
+    # 回复消息 msg_id:同毫秒 F,T,F,T 交换的 (thread_end_ts, reply_ts) 并列
+    # 去重(一条回复恰好闭合一个串);兼作下钻证据定位回复消息
+    reply_msg_id: Mapped[str] = mapped_column(String(64), primary_key=True)
+    # 串末条所在上海自然日 yyyymmdd(冗余物化,窗口/趋势索引)
+    day: Mapped[int] = mapped_column(Integer, nullable=False)
+    fr_ms: Mapped[int] = mapped_column(BigInteger, nullable=False)
+
+    __table_args__ = (Index("ix_fr_fact_day_channel", "day", "channel"),)
+
+
+class EmployeeMetricDaily(Base):
+    """员工×日管理指标宽表(v2 §3.2)——1:1 口径,管理域专用。
+
+    列来源(v2 §1.1 #2/#5):消息计数/负载列自 msg_daily_stats
+    (peer_kind='friend' 过滤 + account_map 归并);串类三列与首响日值由
+    first_reply_facts.compute_conversation 同源输出(串末条归属日)——
+    回复率分子分母同口径。metric_version 只影响派生列(生命周期),
+    默认 'v1'。account_map 映射不上或不在 staff 的 owner(幽灵员工)
+    过滤不落表(v2 §1.3 #11)。通话在 employee_call_daily(无渠道维)。
+    """
+
+    __tablename__ = "employee_metric_daily"
+
+    day: Mapped[int] = mapped_column(Integer, primary_key=True)
+    channel: Mapped[str] = mapped_column(String(16), primary_key=True)
+    user_id: Mapped[str] = mapped_column(String(64), primary_key=True)
+    metric_version: Mapped[str] = mapped_column(
+        String(16), primary_key=True, default="v1", server_default="v1"
+    )
+    # 消息计数列(1:1 口径)
+    msg_sent: Mapped[int] = mapped_column(
+        Integer, nullable=False, default=0, server_default=sa.text("0")
+    )
+    msg_recv: Mapped[int] = mapped_column(
+        Integer, nullable=False, default=0, server_default=sa.text("0")
+    )
+    # 负载列(active_rooms 为群负载,唯一计入宽表的群维度)
+    active_friends: Mapped[int] = mapped_column(
+        Integer, nullable=False, default=0, server_default=sa.text("0")
+    )
+    active_rooms: Mapped[int] = mapped_column(
+        Integer, nullable=False, default=0, server_default=sa.text("0")
+    )
+    # 串类列(与 first_reply_fact 同源,按串末条归属日)
+    cust_threads: Mapped[int] = mapped_column(
+        Integer, nullable=False, default=0, server_default=sa.text("0")
+    )
+    threads_answered: Mapped[int] = mapped_column(
+        Integer, nullable=False, default=0, server_default=sa.text("0")
+    )
+    fr_sum_ms: Mapped[int] = mapped_column(
+        BigInteger, nullable=False, default=0, server_default=sa.text("0")
+    )
+    # 首响日值(趋势图用;评分用周期值从 fact 表窗口函数精确计算)
+    first_reply_p50_ms: Mapped[int | None] = mapped_column(BigInteger, nullable=True)
+    first_reply_p90_ms: Mapped[int | None] = mapped_column(BigInteger, nullable=True)
+    # 生命周期 4 列(距今天数口径,当日持有客户状态分布,当前归属)
+    new_customer_count: Mapped[int] = mapped_column(
+        Integer, nullable=False, default=0, server_default=sa.text("0")
+    )
+    cooling_customer_count: Mapped[int] = mapped_column(
+        Integer, nullable=False, default=0, server_default=sa.text("0")
+    )
+    dormant_customer_count: Mapped[int] = mapped_column(
+        Integer, nullable=False, default=0, server_default=sa.text("0")
+    )
+    reactivated_customer_count: Mapped[int] = mapped_column(
+        Integer, nullable=False, default=0, server_default=sa.text("0")
+    )
+    # 预留完整性标记:宽表生成当前恒写 True(串类列与 fact 同一算法直算,
+    # 不读 fact 表)——真实语义(如校验 fact 覆盖/同步完整)由批次B定义
+    data_complete: Mapped[bool] = mapped_column(
+        Boolean, nullable=False, default=False, server_default=sa.text("0")
+    )
+    computed_at: Mapped[dt.datetime] = mapped_column(
+        sa.DateTime, nullable=False, server_default=sa.func.now()
+    )
+
+
+class EmployeeCallDaily(Base):
+    """员工×日通话小表(v2 §1.2 #9)——通话无消息渠道维度,独立于宽表。
+
+    phone_call.channel 是通话类型(实测值 voice_call/wa_voice_call,
+    无蜂窝 phone_call 行)非消息渠道,塞进 (day,channel,user) 宽表会在
+    channel=all 聚合时双计。接通 =
+    call_duration > 0;followup = 通话后 24h 内该员工任一账号对该客户
+    有消息(Task 0 已核实:1:1 通话可匹配率 100%,@chatroom 群通话除外)。
+    """
+
+    __tablename__ = "employee_call_daily"
+
+    day: Mapped[int] = mapped_column(Integer, primary_key=True)
+    user_id: Mapped[str] = mapped_column(String(64), primary_key=True)
+    call_count: Mapped[int] = mapped_column(
+        Integer, nullable=False, default=0, server_default=sa.text("0")
+    )
+    call_seconds: Mapped[int] = mapped_column(
+        BigInteger, nullable=False, default=0, server_default=sa.text("0")
+    )
+    answered_call_count: Mapped[int] = mapped_column(
+        Integer, nullable=False, default=0, server_default=sa.text("0")
+    )
+    call_followup_count: Mapped[int] = mapped_column(
+        Integer, nullable=False, default=0, server_default=sa.text("0")
+    )
+    computed_at: Mapped[dt.datetime] = mapped_column(
+        sa.DateTime, nullable=False, server_default=sa.func.now()
+    )
+
+
+class EmployeeScoreConfig(Base):
+    """评分配置版本(v1 §10.4/v2 §3.3)——config_json 存维度/指标/权重/
+    方向/阈值/样本门槛;激活前须过权重总和与阈值校验(批次B scoring 实现)。
+    MVP 无可视化编辑器,受控 CLI 种子维护。
+    JSON 列(config_json 等)修改须整列重赋值,原地修改不会提交。"""
+
+    __tablename__ = "employee_score_config"
+
+    id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
+    version: Mapped[str] = mapped_column(String(32), unique=True, nullable=False)
+    name: Mapped[str] = mapped_column(String(128), nullable=False)
+    # draft | active | retired
+    status: Mapped[str] = mapped_column(
+        String(16), nullable=False, default="draft", server_default="draft"
+    )
+    effective_from: Mapped[int | None] = mapped_column(Integer, nullable=True)
+    effective_to: Mapped[int | None] = mapped_column(Integer, nullable=True)
+    config_json: Mapped[dict[str, Any]] = mapped_column(JSON, nullable=False)
+    created_by: Mapped[str | None] = mapped_column(String(64), nullable=True)
+    approved_by: Mapped[str | None] = mapped_column(String(64), nullable=True)
+    created_at: Mapped[dt.datetime] = mapped_column(
+        sa.DateTime, nullable=False, server_default=sa.func.now()
+    )
+    activated_at: Mapped[dt.datetime | None] = mapped_column(sa.DateTime, nullable=True)
+
+
+class EmployeeScoreSnapshot(Base):
+    """周/月考核快照(v1 §8/v2 §3.3)——不可变:冻结后业务层禁改评分字段;
+    重算走 supersedes_id 替代链。同批次×员工唯一。"""
+
+    __tablename__ = "employee_score_snapshot"
+
+    id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
+    snapshot_batch_id: Mapped[str] = mapped_column(String(64), nullable=False)
+    # week | month | custom
+    period_type: Mapped[str] = mapped_column(String(8), nullable=False)
+    period_start: Mapped[int] = mapped_column(Integer, nullable=False)
+    period_end: Mapped[int] = mapped_column(Integer, nullable=False)
+    user_id: Mapped[str] = mapped_column(String(64), nullable=False)
+    score_config_version: Mapped[str] = mapped_column(String(32), nullable=False)
+    metric_version: Mapped[str] = mapped_column(String(16), nullable=False)
+    total_score: Mapped[int | None] = mapped_column(Integer, nullable=True)
+    grade: Mapped[str | None] = mapped_column(String(2), nullable=True)
+    # scored | insufficient_sample | incomplete_data
+    score_status: Mapped[str] = mapped_column(
+        String(24), nullable=False, default="scored", server_default="scored"
+    )
+    dimension_scores_json: Mapped[dict[str, Any] | None] = mapped_column(JSON, nullable=True)
+    metric_details_json: Mapped[dict[str, Any] | None] = mapped_column(JSON, nullable=True)
+    data_as_of: Mapped[int] = mapped_column(Integer, nullable=False)
+    generated_at: Mapped[dt.datetime] = mapped_column(
+        sa.DateTime, nullable=False, server_default=sa.func.now()
+    )
+    frozen_at: Mapped[dt.datetime | None] = mapped_column(sa.DateTime, nullable=True)
+    frozen_by: Mapped[str | None] = mapped_column(String(64), nullable=True)
+    supersedes_id: Mapped[int | None] = mapped_column(Integer, nullable=True)
+
+    __table_args__ = (
+        sa.UniqueConstraint("snapshot_batch_id", "user_id",
+                            name="uq_score_snapshot_batch_user"),
+        Index("ix_score_snapshot_period", "period_type", "period_start"),
+    )
+
+
+class ManagementFollowup(Base):
+    """管理辅导闭环(v1 §7.3/v2 §3.3)——来源指标→问题→管理动作→结果。"""
+
+    __tablename__ = "management_followup"
+
+    id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
+    employee_user_id: Mapped[str] = mapped_column(String(64), nullable=False)
+    # metric | anomaly | review | manual
+    source_type: Mapped[str] = mapped_column(String(16), nullable=False)
+    source_code: Mapped[str | None] = mapped_column(String(64), nullable=True)
+    source_period_start: Mapped[int | None] = mapped_column(Integer, nullable=True)
+    source_period_end: Mapped[int | None] = mapped_column(Integer, nullable=True)
+    source_value_json: Mapped[dict[str, Any] | None] = mapped_column(JSON, nullable=True)
+    reason: Mapped[str | None] = mapped_column(sa.Text, nullable=True)
+    action_type: Mapped[str | None] = mapped_column(String(32), nullable=True)
+    owner_manager_id: Mapped[str | None] = mapped_column(String(64), nullable=True)
+    # open | in_progress | resolved | cancelled
+    status: Mapped[str] = mapped_column(
+        String(16), nullable=False, default="open", server_default="open"
+    )
+    due_at: Mapped[dt.datetime | None] = mapped_column(sa.DateTime, nullable=True)
+    result: Mapped[str | None] = mapped_column(sa.Text, nullable=True)
+    employee_feedback: Mapped[str | None] = mapped_column(sa.Text, nullable=True)
+    created_by: Mapped[str | None] = mapped_column(String(64), nullable=True)
+    created_at: Mapped[dt.datetime] = mapped_column(
+        sa.DateTime, nullable=False, server_default=sa.func.now()
+    )
+    updated_at: Mapped[dt.datetime] = _updated_at()
+    closed_at: Mapped[dt.datetime | None] = mapped_column(sa.DateTime, nullable=True)
+
+    __table_args__ = (
+        Index("ix_followup_emp_status_due", "employee_user_id", "status", "due_at"),
+        Index("ix_followup_owner_status", "owner_manager_id", "status"),
+    )
+
+
 __all__ = [
     "ChatGroup",
     "Customer",
     "Department",
+    "EmployeeCallDaily",
+    "EmployeeMetricDaily",
+    "EmployeeScoreConfig",
+    "EmployeeScoreSnapshot",
+    "FirstReplyFact",
     "GroupMember",
+    "ManagementFollowup",
     "Media",
     "Message",
     "MomentsPost",

yunke-server/app/management/anomalies.py

@@ -0,0 +1,234 @@
+"""管理域确定性异常规则(批次B Task B3,v1 §5.4 异常卡片)。
+
+4 条规则,输入=当前+个人基线 PeriodMetrics,输出异常卡片 dict 列表。
+全部确定性——不使用 LLM 推断,reason/title/suggested_action 均为固定
+中文模板填数,reason 只描述数据事实(百分比/样本数/未回串数)。
+
+规则表(触发比较均为严格 > / <):
+- reply_p90_worsened : cur.fr_p90_ms > base×1.5 且 cur.cust_threads≥
+                       soft_threads;>×2.5 升 critical
+- reply_rate_dropped : derive(reply_2h_rate) cur < base 同式×0.7 且
+                       cur.cust_threads≥soft_threads(率由 scoring.
+                       derive_metrics 派生,与评分同一口径)
+- activity_drop      : cur 日均 (msg_sent+msg_recv)/n_days < base 日均
+                       (…/28)×0.5 且 base.days_with_data≥min_days
+                       (基线太稀疏不可比;基线窗口恒 28 天=baseline_window
+                       语义,当前窗口天数由 n_days 传入)
+- workload_overload  : cur.active_friends(周期 distinct) > workload 维
+                       active_friends_band.high(与评分 band 同源阈值)
+
+无基线不判:baseline=None 直接返回 [](新员工无个人对比位即不出卡,
+含与基线无关的 overload——新入职负载爬坡期误报多,不判);某侧值
+None/不可算(无串样本的率、无 fact 的分位、0ms 退化基线)→ 对应规则
+不触发。
+
+纯函数(无 session/IO):B4 dashboard/employees 对全员逐个调用。
+阈值不硬编码:soft_threads/min_days 取 config.sample_guards,过载上限取
+config.dimensions.workload.metrics.active_friends_band.high;乘数
+(1.5/2.5/0.7/0.5)是规则语义本身,定义为模块常量而非可调参数。
+"""
+from __future__ import annotations
+
+from app.management.employee_metrics import PeriodMetrics
+from app.management.scoring import derive_metrics
+
+# 规则乘数(语义常量,非可调参数——调整即换规则版本)
+P90_WARN_MULTIPLIER = 1.5
+P90_CRITICAL_MULTIPLIER = 2.5
+RATE_DROP_MULTIPLIER = 0.7
+ACTIVITY_DROP_MULTIPLIER = 0.5
+BASELINE_WINDOW_DAYS = 28  # 个人基线窗口恒 28 天(employee_metrics.baseline_window)
+
+# ---- 固定文案模板(.format 填数,reason 只含数据事实) ----
+TITLE_P90 = "回复 P90 较个人基线上升 {pct}%"
+TITLE_RATE = "2h 回复率较个人基线下降 {pct}%"
+TITLE_ACTIVITY = "日均消息量较个人基线下降 {pct}%"
+TITLE_OVERLOAD = "活跃客户 {current} 人超过负载上限 {limit} 人"
+
+REASON_P90 = (
+    "近 {n_days} 天首响 P90 为 {cur}(基线前 28 天为 {base}),上升 {pct}%;"
+    "期内 {threads} 串客户消息中 {unreplied} 串未回"
+)
+REASON_RATE = (
+    "近 {n_days} 天 2h 回复率为 {cur:.0%}({cur_cnt}/{cur_thr} 串),"
+    "基线(前 28 天)为 {base:.0%}({base_cnt}/{base_thr} 串);"
+    "期内 {unreplied} 串未回"
+)
+REASON_ACTIVITY = (
+    "近 {n_days} 天日均消息 {cur:.1f} 条/天,基线(前 28 天)日均 {base:.1f} 条/天,"
+    "下降 {pct}%;当前活跃客户 {friends} 人"
+)
+REASON_OVERLOAD = (
+    "近 {n_days} 天活跃客户 {current} 人(周期 distinct 口径),"
+    "超过配置上限 {limit} 人"
+)
+
+ACTION_P90 = "查看超时未回客户明细,与员工确认近期负载与接待安排"
+ACTION_RATE = "查看未回串明细,排查回复流程与时段覆盖问题"
+ACTION_ACTIVITY = "与员工确认在岗状态与客户维护情况,并核对账号数据接入是否正常"
+ACTION_OVERLOAD = "评估客户分配与负载均衡,考虑分流部分客户或安排协助"
+
+
+def _fmt_ms(ms: float) -> str:
+    # 与 scoring._fmt_ms 同式(模块私有不跨文件引用)
+    minutes = ms / 60_000
+    if minutes >= 60 and minutes % 60 == 0:
+        return f"{minutes // 60:g}h"
+    return f"{minutes:g}min"
+
+
+def _pct_up(cur: float, base: float) -> int:
+    """较基线上升百分比(四舍五入取整;触发后调用,base>0 已保证)。"""
+    return int(round((cur - base) / base * 100))
+
+
+def _pct_down(cur: float, base: float) -> int:
+    """较基线下降百分比(触发后调用,base>0 已由触发条件保证)。"""
+    return int(round((base - cur) / base * 100))
+
+
+def detect_anomalies(
+    user_id: str,
+    current: PeriodMetrics,
+    baseline: PeriodMetrics | None,
+    *,
+    n_days: int,
+    config: dict,
+) -> list[dict]:
+    """单员工确定性异常检测(纯函数,卡片结构见 v1 §5.4/模块 docstring)。
+
+    输出按规则表序:p90 恶化 → 回复率骤降 → 活动骤降 → 过载
+    (排序/聚合由 B4 调用方按 severity/affected_count 处理)。
+    """
+    if baseline is None:
+        return []  # 无基线不判(新员工)
+    guards = config.get("sample_guards", {})
+    soft = guards.get("soft_threads", 10)
+    min_days = guards.get("min_days", 5)
+    band_high = (
+        config.get("dimensions", {})
+        .get("workload", {})
+        .get("metrics", {})
+        .get("active_friends_band", {})
+        .get("high")
+    )
+    cards: list[dict] = []
+    unreplied = current.cust_threads - current.threads_answered
+    threads_ok = current.cust_threads >= soft
+
+    # ---- 1. reply_p90_worsened:P90 较个人基线恶化 ×1.5/×2.5 ----
+    if (
+        threads_ok
+        and current.fr_p90_ms is not None
+        and baseline.fr_p90_ms is not None
+        and baseline.fr_p90_ms > 0  # 0ms 基线为退化数据,不可比
+    ):
+        base_p90 = baseline.fr_p90_ms
+        if current.fr_p90_ms > base_p90 * P90_CRITICAL_MULTIPLIER:
+            severity = "critical"
+        elif current.fr_p90_ms > base_p90 * P90_WARN_MULTIPLIER:
+            severity = "warning"
+        else:
+            severity = None
+        if severity is not None:
+            pct = _pct_up(current.fr_p90_ms, base_p90)
+            cards.append({
+                "rule_code": "reply_p90_worsened",
+                "severity": severity,
+                "employee_user_id": user_id,
+                "title": TITLE_P90.format(pct=pct),
+                "current_value": current.fr_p90_ms,
+                "baseline_value": base_p90,
+                "unit": "ms",
+                "sample_size": current.cust_threads,
+                "affected_count": unreplied,
+                "reason": REASON_P90.format(
+                    n_days=n_days, cur=_fmt_ms(current.fr_p90_ms),
+                    base=_fmt_ms(base_p90), pct=pct,
+                    threads=current.cust_threads, unreplied=unreplied,
+                ),
+                "drilldown": {"type": "metric", "query": {
+                    "metric_code": "first_reply_p90", "user_id": user_id}},
+                "suggested_action": ACTION_P90,
+            })
+
+    # ---- 2. reply_rate_dropped:2h 回复率较基线降 30%+ ----
+    if threads_ok:
+        cur_rate = derive_metrics(current)["reply_2h_rate"]
+        base_rate = derive_metrics(baseline)["reply_2h_rate"]
+        if (
+            cur_rate is not None and base_rate is not None
+            and cur_rate < base_rate * RATE_DROP_MULTIPLIER
+        ):
+            cards.append({
+                "rule_code": "reply_rate_dropped",
+                "severity": "warning",
+                "employee_user_id": user_id,
+                "title": TITLE_RATE.format(
+                    pct=_pct_down(cur_rate, base_rate)),
+                "current_value": cur_rate,
+                "baseline_value": base_rate,
+                "unit": "0-1",
+                "sample_size": current.cust_threads,
+                "affected_count": unreplied,
+                "reason": REASON_RATE.format(
+                    n_days=n_days, cur=cur_rate, cur_cnt=current.reply_2h_count,
+                    cur_thr=current.cust_threads, base=base_rate,
+                    base_cnt=baseline.reply_2h_count,
+                    base_thr=baseline.cust_threads, unreplied=unreplied,
+                ),
+                "drilldown": {"type": "metric", "query": {
+                    "metric_code": "unreplied", "user_id": user_id}},
+                "suggested_action": ACTION_RATE,
+            })
+
+    # ---- 3. activity_drop:日均消息量较基线腰斩 ----
+    if n_days > 0 and baseline.days_with_data >= min_days:
+        cur_daily = (current.msg_sent + current.msg_recv) / n_days
+        base_daily = (
+            baseline.msg_sent + baseline.msg_recv
+        ) / BASELINE_WINDOW_DAYS
+        if cur_daily < base_daily * ACTIVITY_DROP_MULTIPLIER:
+            cards.append({
+                "rule_code": "activity_drop",
+                "severity": "warning",
+                "employee_user_id": user_id,
+                "title": TITLE_ACTIVITY.format(
+                    pct=_pct_down(cur_daily, base_daily)),
+                "current_value": cur_daily,
+                "baseline_value": base_daily,
+                "unit": "条",
+                "sample_size": current.active_friends,
+                "affected_count": current.active_friends,
+                "reason": REASON_ACTIVITY.format(
+                    n_days=n_days, cur=cur_daily, base=base_daily,
+                    pct=_pct_down(cur_daily, base_daily),
+                    friends=current.active_friends,
+                ),
+                "drilldown": {"type": "employee",
+                              "query": {"user_id": user_id}},
+                "suggested_action": ACTION_ACTIVITY,
+            })
+
+    # ---- 4. workload_overload:活跃客户超 band 上限 ----
+    if band_high is not None and current.active_friends > band_high:
+        cards.append({
+            "rule_code": "workload_overload",
+            "severity": "warning",
+            "employee_user_id": user_id,
+            "title": TITLE_OVERLOAD.format(
+                current=current.active_friends, limit=band_high),
+            "current_value": current.active_friends,
+            "baseline_value": None,  # 与个人基线无关,阈值在 band 配置
+            "unit": "人",
+            "sample_size": current.active_friends,
+            "affected_count": current.active_friends,
+            "reason": REASON_OVERLOAD.format(
+                n_days=n_days, current=current.active_friends,
+                limit=band_high,
+            ),
+            "drilldown": {"type": "employee", "query": {"user_id": user_id}},
+            "suggested_action": ACTION_OVERLOAD,
+        })
+
+    return cards

yunke-server/app/management/api_assembly.py

@@ -0,0 +1,533 @@
+"""管理 API 组装层(批次B Task B4)——router 六端点共用的重查询与行构造。
+
+拆出 router 的原因:employees/dashboard 的组装(多窗聚合 + 评分 + 异常 +
+对比派生)上百行,放 router 会淹没端点定义;本模块只做数据组装,参数
+校验/HTTP 语义留在 router。
+
+查询纪律(与 analytics.metrics 同):**禁止 asyncio.gather**——单
+AsyncSession 不能并发执行查询,全部顺序 await。重端点不做 N+1:
+period_metrics 每窗一次调用全员;员工循环(评分/异常)是纯函数。
+"""
+from __future__ import annotations
+
+import copy
+import statistics
+from bisect import bisect_right
+
+import sqlalchemy as sa
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.analytics.lifecycle import classify
+from app.db.models import (
+    Customer,
+    EmployeeCallDaily,
+    EmployeeMetricDaily,
+    EmployeeScoreConfig,
+    FirstReplyFact,
+    MsgDailyStats,
+    PhoneCall,
+    Staff,
+)
+from app.management.anomalies import detect_anomalies
+from app.management.employee_metrics import (
+    PeriodMetrics,
+    baseline_window,
+    day_range,
+    percentile,
+    period_metrics,
+    prev_window,
+    team_medians,
+)
+from app.management.metric_definitions import DEFAULT_SCORE_CONFIG
+from app.management.scoring import derive_metrics, score_employee
+from app.storage.employee_metrics import METRIC_VERSION
+from app.storage.staff_summary import account_map
+from app.storage.summary import day_bounds_ms
+
+# 异常权重(anomaly_severity 排序/汇总):critical=2 / warning=1
+SEVERITY_WEIGHT = {"critical": 2, "warning": 1}
+
+# 派生指标中需对「员工派生值」另取中位的键(scoring.team 键=派生指标名;
+# 其余如 fr_p90_ms/active_friends/call_count 直接用 team_medians 输出)
+_DERIVED_MEDIAN_KEYS = ("reply_2h_rate", "reply_24h_rate", "active_share")
+
+
+async def load_score_config(session: AsyncSession) -> tuple[dict, str]:
+    """激活评分配置(DB)→ (config_json, "db");无 active 行 →
+    (DEFAULT_SCORE_CONFIG 深拷贝, "default")——未跑种子的环境也能出分。"""
+    row = (await session.execute(
+        sa.select(EmployeeScoreConfig)
+        .where(EmployeeScoreConfig.status == "active")
+        .order_by(EmployeeScoreConfig.id.desc())
+        .limit(1)
+    )).scalar_one_or_none()
+    if row is not None:
+        return row.config_json, "db"
+    return copy.deepcopy(DEFAULT_SCORE_CONFIG), "default"
+
+
+def team_derived_medians(metrics: dict[str, PeriodMetrics]) -> dict[str, float | None]:
+    """评分用团队中位:PeriodMetrics 字段中位 + 派生率/占比的员工级中位
+    (scoring 要求 team 键=派生指标名,见其模块 docstring)。"""
+    team = dict(team_medians(metrics))
+    for key in _DERIVED_MEDIAN_KEYS:
+        vals = [
+            v for v in (derive_metrics(pm).get(key) for pm in metrics.values())
+            if v is not None
+        ]
+        team[key] = statistics.median(vals) if vals else None
+    return team
+
+
+def score_with_guards(
+    config: dict,
+    cur: PeriodMetrics,
+    baseline: PeriodMetrics | None = None,
+    team: dict[str, float] | None = None,
+    prev: PeriodMetrics | None = None,
+) -> dict:
+    """score_employee + min_days 接线(B2 评审遗留):当前窗天数 <
+    config.sample_guards.min_days → score_status 覆盖 insufficient_sample,
+    total/明细保留展示(按天稀疏的数据不参与考核但可查看)。"""
+    score = score_employee(config, cur, baseline=baseline, team=team, prev=prev)
+    min_days = config.get("sample_guards", {}).get("min_days", 5)
+    if cur.days_with_data < min_days:
+        score["score_status"] = "insufficient_sample"
+    return score
+
+
+async def assemble_employees(
+    session: AsyncSession,
+    config: dict,
+    start_day: int,
+    end_day: int,
+    channel: str | None,
+    *,
+    with_prev: bool = True,
+) -> dict[str, dict]:
+    """全员组装:staff → 当前/基线(/前)窗 period_metrics → 逐员工
+    score_with_guards + detect_anomalies(纯函数循环)。
+
+    dashboard 传 with_prev=False(只需评分+异常,省一次前窗聚合);
+    employees/detail 需要 prev/团队中位时传 True。返回
+    {uid: {name, is_on_job, cur, prev, baseline, score, anomalies,
+           anomaly_count, anomaly_weight}}——过滤/排序/分页由调用方做。
+    """
+    staff_rows = (await session.execute(
+        sa.select(Staff.user_id, Staff.name, Staff.is_on_job)
+    )).all()
+    staff = {uid: (name, onjob) for uid, name, onjob in staff_rows if uid}
+    if not staff:
+        return {}
+
+    n_days = len(day_range(start_day, end_day))
+    cur = await period_metrics(session, start_day, end_day, channel)
+    bs, be = baseline_window(start_day)
+    base = await period_metrics(session, bs, be, channel)
+    prev: dict[str, PeriodMetrics] | None = None
+    team: dict[str, float | None] | None = None
+    if with_prev:
+        ps, pe = prev_window(start_day, end_day)
+        prev = await period_metrics(session, ps, pe, channel)
+        team = team_derived_medians(cur)
+
+    out: dict[str, dict] = {}
+    for uid, (name, onjob) in staff.items():
+        c = cur.get(uid)
+        if c is None:  # 防御:period_metrics 恒含全员,此处不该走到
+            continue
+        b = base.get(uid)
+        p = prev.get(uid) if prev is not None else None
+        score = score_with_guards(config, c, baseline=b, team=team, prev=p)
+        anomalies = detect_anomalies(uid, c, b, n_days=n_days, config=config)
+        out[uid] = {
+            "name": name,
+            "is_on_job": onjob,
+            "cur": c,
+            "prev": p,
+            "baseline": b,
+            "score": score,
+            "anomalies": anomalies,
+            "anomaly_count": len(anomalies),
+            "anomaly_weight": sum(
+                SEVERITY_WEIGHT.get(a["severity"], 0) for a in anomalies
+            ),
+        }
+    return out
+
+
+def _code_to_source(config: dict) -> dict[str, str]:
+    """配置指标 code → 源指标名(spec.metric,无则 code 本身)。
+
+    comparisons 键域统一为源指标名(与 derive_metrics / sections 端点一致,
+    冻结批次C契约):active_friends_band→active_friends、call_band→call_count,
+    其余 code 本身即源名。"""
+    out: dict[str, str] = {}
+    for dim in config.get("dimensions", {}).values():
+        for code, spec in dim.get("metrics", {}).items():
+            out[code] = spec.get("metric", code)
+    return out
+
+
+def build_employee_row(uid: str, data: dict, config: dict) -> dict:
+    """employees 列表行:metrics 全字段 + comparisons 四值(自评分
+    metrics_detail 透传,键映射为源指标名)+ score 摘要 + 异常计数/权重。"""
+    score = data["score"]
+    code_src = _code_to_source(config)
+    return {
+        "user_id": uid,
+        "name": data["name"],
+        "is_on_job": data["is_on_job"],
+        "metrics": data["cur"]._asdict(),
+        "comparisons": {
+            code_src.get(code, code): {
+                "current": d["value"],
+                "prev": d["prev"],
+                "baseline": d["baseline"],
+                "median": d["median"],
+            }
+            for code, d in score["metrics_detail"].items()
+        },
+        "score": {
+            "total_score": score["total_score"],
+            "grade": score["grade"],
+            "score_status": score["score_status"],
+            "trial": score["trial"],
+            "dimensions": {
+                key: {"score": dim["score"], "status": dim["status"]}
+                for key, dim in score["dimensions"].items()
+            },
+        },
+        "anomaly_count": data["anomaly_count"],
+        "anomaly_weight": data["anomaly_weight"],
+    }
+
+
+def derived_comparisons(
+    cur: PeriodMetrics,
+    prev: PeriodMetrics | None,
+    baseline: PeriodMetrics | None,
+    team: dict[str, float | None] | None,
+) -> dict[str, dict]:
+    """四对比(current/prev/baseline/median),派生口径=scoring.derive_metrics
+    ——评分、异常、展示三方同一派生式。"""
+    cv = derive_metrics(cur)
+    pv = derive_metrics(prev) if prev is not None else {}
+    bv = derive_metrics(baseline) if baseline is not None else {}
+    return {
+        key: {
+            "current": cv.get(key),
+            "prev": pv.get(key),
+            "baseline": bv.get(key),
+            "median": team.get(key) if team else None,
+        }
+        for key in cv
+    }
+
+
+async def wide_daily_rows(
+    session: AsyncSession,
+    start_day: int,
+    end_day: int,
+    channel: str | None,
+    user_id: str | None = None,
+) -> list[dict]:
+    """宽表逐日聚合(加性列跨渠道求和;user_id=None 为全员合计)。
+
+    first_reply_p50/p90_ms 是 (day,channel,user) 行内单值不可求和:
+    单员工视图(channel=None 双渠道同日)取当日 cust_threads 较大渠道的
+    值(当日主力渠道,并列取 wechat);全员视图不取用这两列(分位由
+    service_daily_trend 从 fact 精确算)。
+    """
+    conds = [
+        EmployeeMetricDaily.day.between(start_day, end_day),
+        EmployeeMetricDaily.metric_version == METRIC_VERSION,
+    ]
+    if channel is not None:
+        conds.append(EmployeeMetricDaily.channel == channel)
+    if user_id is not None:
+        conds.append(EmployeeMetricDaily.user_id == user_id)
+    rows = (await session.execute(
+        sa.select(
+            EmployeeMetricDaily.day.label("day"),
+            EmployeeMetricDaily.channel.label("ch"),
+            sa.func.sum(EmployeeMetricDaily.msg_sent).label("sent"),
+            sa.func.sum(EmployeeMetricDaily.msg_recv).label("recv"),
+            sa.func.sum(EmployeeMetricDaily.active_friends).label("af"),
+            sa.func.sum(EmployeeMetricDaily.active_rooms).label("ar"),
+            sa.func.sum(EmployeeMetricDaily.cust_threads).label("thr"),
+            sa.func.sum(EmployeeMetricDaily.threads_answered).label("ans"),
+            sa.func.sum(EmployeeMetricDaily.fr_sum_ms).label("frs"),
+            sa.func.sum(EmployeeMetricDaily.new_customer_count).label("nw"),
+            sa.func.sum(EmployeeMetricDaily.cooling_customer_count).label("cool"),
+            sa.func.sum(EmployeeMetricDaily.dormant_customer_count).label("dorm"),
+            sa.func.sum(EmployeeMetricDaily.reactivated_customer_count).label("react"),
+            sa.func.max(EmployeeMetricDaily.first_reply_p50_ms).label("p50"),
+            sa.func.max(EmployeeMetricDaily.first_reply_p90_ms).label("p90"),
+        ).where(*conds).group_by(EmployeeMetricDaily.day, EmployeeMetricDaily.channel)
+    )).all()
+
+    per_day: dict[int, dict] = {}
+
+    def _blank(day: int) -> dict:
+        return {
+            "day": day, "msg_sent": 0, "msg_recv": 0, "active_friends": 0,
+            "active_rooms": 0, "cust_threads": 0, "threads_answered": 0,
+            "fr_sum_ms": 0, "new_customer_count": 0,
+            "cooling_customer_count": 0, "dormant_customer_count": 0,
+            "reactivated_customer_count": 0,
+            "first_reply_p50_ms": None, "first_reply_p90_ms": None,
+            "_pick": (-1, -1),  # 主力渠道追踪 (cust_threads, wechat 加分)
+        }
+
+    for (day, ch, sent, recv, af, ar, thr, ans, frs, nw, cool, dorm,
+         react, p50, p90) in rows:
+        d = per_day.setdefault(day, _blank(day))
+        d["msg_sent"] += int(sent or 0)
+        d["msg_recv"] += int(recv or 0)
+        d["active_friends"] += int(af or 0)
+        d["active_rooms"] += int(ar or 0)
+        d["cust_threads"] += int(thr or 0)
+        d["threads_answered"] += int(ans or 0)
+        d["fr_sum_ms"] += int(frs or 0)
+        d["new_customer_count"] += int(nw or 0)
+        d["cooling_customer_count"] += int(cool or 0)
+        d["dormant_customer_count"] += int(dorm or 0)
+        d["reactivated_customer_count"] += int(react or 0)
+        if user_id is not None:
+            pick = (int(thr or 0), 1 if ch == "wechat" else 0)
+            if pick > d["_pick"]:
+                d["_pick"] = pick
+                d["first_reply_p50_ms"] = p50
+                d["first_reply_p90_ms"] = p90
+
+    out = []
+    for day in sorted(per_day):
+        d = per_day[day]
+        d.pop("_pick", None)
+        out.append(d)
+    return out
+
+
+async def call_daily_rows(
+    session: AsyncSession,
+    start_day: int,
+    end_day: int,
+    user_id: str | None = None,
+) -> list[dict]:
+    """通话小表逐日聚合(恒全渠道——表无渠道维);user_id=None 为全员。"""
+    conds = [EmployeeCallDaily.day.between(start_day, end_day)]
+    if user_id is not None:
+        conds.append(EmployeeCallDaily.user_id == user_id)
+    rows = (await session.execute(
+        sa.select(
+            EmployeeCallDaily.day,
+            sa.func.sum(EmployeeCallDaily.call_count),
+            sa.func.sum(EmployeeCallDaily.call_seconds),
+            sa.func.sum(EmployeeCallDaily.answered_call_count),
+            sa.func.sum(EmployeeCallDaily.call_followup_count),
+        ).where(*conds).group_by(EmployeeCallDaily.day)
+    )).all()
+    return [
+        {
+            "day": day, "call_count": int(cc or 0),
+            "call_seconds": int(cs or 0),
+            "answered_call_count": int(ca or 0),
+            "call_followup_count": int(cf or 0),
+        }
+        for day, cc, cs, ca, cf in rows
+    ]
+
+
+async def service_daily_trend(
+    session: AsyncSession,
+    start_day: int,
+    end_day: int,
+    channel: str | None,
+    threads_by_day: dict[int, int],
+) -> list[dict]:
+    """服务趋势(dashboard 全团队):fact 逐日 (day, fr_ms) 行拉回 Python
+    最近邻秩分位(跨员工合并样本——团队级分位);reply_2h_rate = fact
+    当日 ≤2h 计数 / 宽表当日 cust_threads 合计(分母 0 → None)。
+
+    输出全窗口逐日(无数据日 p50/p90 为 None),threads_by_day 来自
+    wide_daily_rows 的全员 cust_threads 列。
+    """
+    conds = [FirstReplyFact.day.between(start_day, end_day)]
+    if channel is not None:
+        conds.append(FirstReplyFact.channel == channel)
+    rows = (await session.execute(
+        sa.select(FirstReplyFact.day, FirstReplyFact.fr_ms).where(*conds)
+    )).all()
+    by_day: dict[int, list[int]] = {}
+    for day, fr in rows:
+        by_day.setdefault(day, []).append(int(fr))
+    out = []
+    for day in day_range(start_day, end_day):
+        frs = by_day.get(day, [])
+        cnt_2h = sum(1 for f in frs if f <= 7_200_000)
+        denom = threads_by_day.get(day, 0)
+        out.append({
+            "day": day,
+            "fr_p50_ms": percentile(frs, 1, 2),
+            "fr_p90_ms": percentile(frs, 9, 10),
+            "reply_2h_rate": (cnt_2h / denom) if denom else None,
+        })
+    return out
+
+
+async def user_owner_accounts(
+    session: AsyncSession, user_id: str, channel: str | None
+) -> list[str]:
+    """员工在所选渠道下的 owner 账号(channel=None → 两渠道合并)。"""
+    chs = ("wechat", "whatsapp") if channel is None else (channel,)
+    out: list[str] = []
+    for ch in chs:
+        amap = await account_map(session, ch)
+        out.extend(owner for owner, uid in amap.items() if uid == user_id)
+    return out
+
+
+async def lifecycle_customers(
+    session: AsyncSession,
+    owner_accounts: list[str],
+    as_of_day: int,
+    want_state: str,
+) -> list[dict]:
+    """drilldown cooling/dormant:该员工账号归属客户(delete_flag 过滤)+
+    msg_daily_stats friend 行全历史 → lifecycle.classify(as_of=窗口末日),
+    返回状态匹配行 {friend_id, channel, nickname, last_day, state},按 last_day asc
+    (最陈旧在前)、friend_id asc 排序。
+
+    历史按 (channel, peer) 键控、跨 owner 合并——与批次A _lifecycle_daily
+    的 peer 键控口径一致(归属由 Customer.owner_account_id 决定,互动史
+    不随归属走:共享/换归属客户的全部历史都算,否则 KPI 计了而名单丢人)。
+    hist 为 ≤as_of 的历史消息数(时点语义,as_of 之后的消息不虚增沉睡门槛)。"""
+    custs = (await session.execute(
+        sa.select(Customer).where(
+            sa.or_(Customer.delete_flag.is_(None), Customer.delete_flag == 0),
+            Customer.owner_account_id.in_(owner_accounts),
+        )
+    )).scalars().all()
+    if not custs:
+        return []
+    ids = [c.friend_id for c in custs]
+    rows = (await session.execute(
+        sa.select(
+            MsgDailyStats.channel,
+            MsgDailyStats.peer_id,
+            MsgDailyStats.day,
+            MsgDailyStats.send_cnt,
+            MsgDailyStats.recv_cnt,
+        ).where(
+            MsgDailyStats.peer_kind == "friend",
+            MsgDailyStats.peer_id.in_(ids),
+        )
+    )).all()
+    hist: dict[tuple[str, str], dict[int, int]] = {}
+    for ch, peer, day, snd, rcv in rows:
+        dm = hist.setdefault((ch, peer), {})
+        dm[day] = dm.get(day, 0) + int(snd or 0) + int(rcv or 0)
+
+    matches: list[dict] = []
+    for c in custs:
+        dm = hist.get((c.channel, c.friend_id))
+        if not dm:
+            continue
+        days_list = sorted(dm)
+        idx = bisect_right(days_list, as_of_day) - 1
+        if idx < 0:
+            continue  # 窗口末日之前从未互动
+        last = days_list[idx]
+        prev_d = days_list[idx - 1] if idx > 0 else None
+        hist_msgs = sum(dm[d] for d in days_list[: idx + 1])
+        state = classify(days_list[0], last, prev_d, as_of_day, hist_msgs)
+        if state == want_state:
+            matches.append({
+                "friend_id": c.friend_id,
+                "channel": c.channel,
+                "nickname": c.friend_nickname or c.friend_remark or c.friend_id,
+                "last_day": last,
+                "state": state,
+            })
+    matches.sort(key=lambda m: (m["last_day"], m["friend_id"]))
+    return matches
+
+
+async def fr_fact_rows(
+    session: AsyncSession,
+    owner_accounts: list[str],
+    channel: str | None,
+    start_day: int,
+    end_day: int,
+    *,
+    page: int,
+    page_size: int,
+) -> tuple[int, list[dict]]:
+    """drilldown 首响分位:该员工账号窗内 fact 逐串证据行,fr_ms desc
+    (同值按日/串末时刻 desc 决胜)分页。chat_hint 给出会话定位参数
+    (owner+talker 直达聊天记录)。返回 (total, items)。"""
+    conds = [
+        FirstReplyFact.day.between(start_day, end_day),
+        FirstReplyFact.owner_account_id.in_(owner_accounts),
+    ]
+    if channel is not None:
+        conds.append(FirstReplyFact.channel == channel)
+    total = (await session.execute(
+        sa.select(sa.func.count()).select_from(FirstReplyFact).where(*conds)
+    )).scalar_one()
+    rows = (await session.execute(
+        sa.select(FirstReplyFact).where(*conds)
+        .order_by(FirstReplyFact.fr_ms.desc(), FirstReplyFact.day.desc(),
+                  FirstReplyFact.thread_end_ts.desc())
+        .offset((page - 1) * page_size).limit(page_size)
+    )).scalars().all()
+    items = [{
+        "day": f.day,
+        "channel": f.channel,
+        "owner_account_id": f.owner_account_id,
+        "peer_id": f.peer_id,
+        "thread_end_ts": f.thread_end_ts,
+        "reply_ts": f.reply_ts,
+        "fr_ms": f.fr_ms,
+        "chat_hint": {"owner_account_id": f.owner_account_id,
+                      "talker_id": f.peer_id},
+    } for f in rows]
+    return int(total), items
+
+
+async def user_calls_page(
+    session: AsyncSession,
+    user_id: str,
+    start_day: int,
+    end_day: int,
+    *,
+    page: int,
+    page_size: int,
+) -> tuple[int, list[dict]]:
+    """drilldown 通话跟进:该员工窗内通话行(start_call_time desc,
+    call_id desc 决胜)分页。返回 (total, items)。"""
+    lo, _ = day_bounds_ms(start_day)
+    _, hi = day_bounds_ms(end_day)  # 末日次日 00:00(左闭右开上界)
+    conds = [
+        PhoneCall.user_id == user_id,
+        PhoneCall.start_call_time.is_not(None),
+        PhoneCall.start_call_time >= lo,
+        PhoneCall.start_call_time < hi,
+    ]
+    total = (await session.execute(
+        sa.select(sa.func.count()).select_from(PhoneCall).where(*conds)
+    )).scalar_one()
+    rows = (await session.execute(
+        sa.select(PhoneCall).where(*conds)
+        .order_by(PhoneCall.start_call_time.desc(), PhoneCall.call_id.desc())
+        .offset((page - 1) * page_size).limit(page_size)
+    )).scalars().all()
+    items = [{
+        "call_id": c.call_id,
+        "channel": c.channel,
+        "call_number": c.call_number,
+        "start_call_time": c.start_call_time,
+        "call_duration": c.call_duration,
+    } for c in rows]
+    return int(total), items

yunke-server/app/management/employee_metrics.py

@@ -0,0 +1,342 @@
+"""管理域期聚合查询(批次B)——评分/异常/employees API 的单一数据源。
+
+窗口:days=[start_day..end_day] 闭区间 yyyymmdd;上期=等长紧邻前窗;
+个人基线=紧邻当前窗之前的 28 天。所有查询走 (day, ...) 索引,不扫消息表
+(除 distinct 活跃客户走 msg_daily_stats friend 行)。
+
+口径要点:
+- 分位/回复计数:first_reply_fact 窗内行拉回 Python 按员工合并排序取
+  最近邻秩 ceil(q·n)(整除算术 (n+1)//2 / (9n+9)//10——SQLite 无原生
+  ceil,MySQL `/` 返回浮点,Python 侧取秩零方言风险)。合并按员工而非
+  owner:一员工多账号(wx1+wx2→u1,channel=None 时人人如此)的样本必须
+  跨账号归并,逐 owner 取分位再映射会互相覆盖。fact 全库全期 ≤6.8万行,
+  Python 侧聚合可行。
+- 期末存量(new/cooling/dormant/end_active_friends):状态快照取
+  「每 (user, channel) 最新 ≤end 行」——channel=None 时两渠道各取各的
+  最新行再相加(直接取全渠道最大 day 的那一行会丢另一渠道的存量)。
+  end_active_friends 与 new/cooling/dormant 同源同行(该渠道最新行的
+  active_friends 列),供评分 active_share 用——区别于 active_friends
+  字段的周期 distinct 口径。
+- active_rooms_avg = SUM(active_rooms)/全窗天数(含无数据日摊薄),
+  非有数据天数——「日均负载」语义。
+- days_with_data = COUNT(DISTINCT day):单渠道时与 COUNT(*) 等价
+  (PK 含 day+channel,每日至多一行),channel=None 双渠道同日也只计 1 天。
+- 通话四列恒全渠道(employee_call_daily 无渠道维),channel 参数不过滤。
+"""
+from __future__ import annotations
+
+import datetime as dt
+import statistics
+from collections import namedtuple
+from collections.abc import Iterable
+
+import sqlalchemy as sa
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.db.models import (
+    EmployeeCallDaily,
+    EmployeeMetricDaily,
+    FirstReplyFact,
+    MsgDailyStats,
+    Staff,
+)
+from app.storage.employee_metrics import METRIC_VERSION
+from app.storage.staff_summary import account_map
+
+PeriodMetrics = namedtuple("PeriodMetrics", [
+    "user_id", "days_with_data", "msg_sent", "msg_recv", "cust_threads",
+    "threads_answered", "fr_sum_ms", "fr_p50_ms", "fr_p90_ms",
+    "reply_2h_count", "reply_24h_count",
+    "active_friends",          # 期内 distinct(直查,非日值求和)
+    "active_rooms_avg",        # 日均(全窗天数摊薄)
+    "new_customer", "cooling_customer", "dormant_customer",  # 期末单日存量
+    "end_active_friends",      # 期末行 active_friends 跨渠道 SUM(active_share 分子)
+    "reactivated_customer",    # 期内求和
+    "call_count", "call_seconds", "answered_call", "call_followup",
+])
+
+
+def _to_date(k: int) -> dt.date:
+    return dt.date(k // 10000, k // 100 % 100, k % 100)
+
+
+def _to_key(d: dt.date) -> int:
+    return d.year * 10000 + d.month * 100 + d.day
+
+
+def day_range(start: int, end: int) -> list[int]:
+    """闭区间日键列表。"""
+    out, cur = [], _to_date(start)
+    while cur <= _to_date(end):
+        out.append(_to_key(cur))
+        cur += dt.timedelta(days=1)
+    return out
+
+
+def prev_window(start: int, end: int) -> tuple[int, int]:
+    """等长紧邻前窗。"""
+    n = len(day_range(start, end))
+    pe = _to_date(start) - dt.timedelta(days=1)
+    ps = pe - dt.timedelta(days=n - 1)
+    return _to_key(ps), _to_key(pe)
+
+
+def baseline_window(start: int) -> tuple[int, int]:
+    """个人基线:紧邻当前窗之前的 28 天。"""
+    be = _to_date(start) - dt.timedelta(days=1)
+    bs = be - dt.timedelta(days=27)
+    return _to_key(bs), _to_key(be)
+
+
+def percentile(vals: list[int], q_num: int, q_den: int) -> int | None:
+    """最近邻秩分位 ceil(q·n) 的样本值,q=q_num/q_den(1/2、9/10)。
+
+    公有供同包 api_assembly(B4 服务趋势)复用;整数算术
+    rank=(q_num*n + q_den - 1)//q_den 对正整数 n 恒落在 [1,n]
+    (与 math.ceil(q·n) 等价,与批次A storage 层 _percentile 同口径——
+    后者为不同层单独保留);空列表→None(与 0 严格区分)。
+    """
+    if not vals:
+        return None
+    s = sorted(vals)
+    n = len(s)
+    rank = max(1, min(n, (q_num * n + q_den - 1) // q_den))
+    return s[rank - 1]
+
+
+# 累加器初值:全员(staff)都出结果行,无数据员工为零值而非缺行——
+# employees API 全员列表语义。
+_ZERO: dict[str, object] = {
+    "days_with_data": 0, "msg_sent": 0, "msg_recv": 0, "cust_threads": 0,
+    "threads_answered": 0, "fr_sum_ms": 0,
+    "fr_p50_ms": None, "fr_p90_ms": None,
+    "reply_2h_count": 0, "reply_24h_count": 0,
+    "active_friends": 0, "active_rooms_sum": 0,
+    "new_customer": 0, "cooling_customer": 0, "dormant_customer": 0,
+    "end_active_friends": 0,
+    "reactivated_customer": 0,
+    "call_count": 0, "call_seconds": 0, "answered_call": 0, "call_followup": 0,
+}
+
+
+async def period_metrics(
+    session: AsyncSession,
+    start_day: int,
+    end_day: int,
+    channel: str | None,
+    user_ids: Iterable[str] | None = None,
+) -> dict[str, PeriodMetrics]:
+    """窗口 [start_day, end_day] × channel(None=全渠道)的员工期指标。
+
+    user_ids 传入时与 staff 表求交(幽灵过滤);返回含全部目标员工的
+    PeriodMetrics(无数据员工为零值行)。channel=None 时两渠道
+    account_map 合并(wx_id 与 WA uid 命名空间不撞,无冲突)。
+    """
+    staff_ids = {
+        u for u in (await session.execute(sa.select(Staff.user_id))).scalars() if u
+    }
+    target = staff_ids if user_ids is None else staff_ids & set(user_ids)
+    if not target:
+        return {}
+
+    if channel is None:
+        amap: dict[str, str] = {}
+        for ch in ("wechat", "whatsapp"):
+            amap.update(await account_map(session, ch))
+    else:
+        amap = await account_map(session, channel)
+
+    n_days = len(day_range(start_day, end_day))
+    acc: dict[str, dict] = {uid: dict(_ZERO) for uid in target}
+
+    # ---- 宽表 SUM:消息计数/串类/日均负载/复活 ----
+    wide_conds = [
+        EmployeeMetricDaily.day.between(start_day, end_day),
+        EmployeeMetricDaily.metric_version == METRIC_VERSION,
+        EmployeeMetricDaily.user_id.in_(target),
+    ]
+    if channel is not None:
+        wide_conds.append(EmployeeMetricDaily.channel == channel)
+    wide = (await session.execute(
+        sa.select(
+            EmployeeMetricDaily.user_id.label("uid"),
+            sa.func.count(sa.distinct(EmployeeMetricDaily.day)).label("nd"),
+            sa.func.sum(EmployeeMetricDaily.msg_sent).label("sent"),
+            sa.func.sum(EmployeeMetricDaily.msg_recv).label("recv"),
+            sa.func.sum(EmployeeMetricDaily.cust_threads).label("thr"),
+            sa.func.sum(EmployeeMetricDaily.threads_answered).label("ans"),
+            sa.func.sum(EmployeeMetricDaily.fr_sum_ms).label("frs"),
+            sa.func.sum(EmployeeMetricDaily.active_rooms).label("rooms"),
+            sa.func.sum(
+                EmployeeMetricDaily.reactivated_customer_count
+            ).label("react"),
+        ).where(*wide_conds).group_by(EmployeeMetricDaily.user_id)
+    )).all()
+    for uid, nd, sent, recv, thr, ans, frs, rooms, react in wide:
+        a = acc[uid]
+        a["days_with_data"] = int(nd or 0)
+        a["msg_sent"] = int(sent or 0)
+        a["msg_recv"] = int(recv or 0)
+        a["cust_threads"] = int(thr or 0)
+        a["threads_answered"] = int(ans or 0)
+        a["fr_sum_ms"] = int(frs or 0)
+        a["active_rooms_sum"] = int(rooms or 0)
+        a["reactivated_customer"] = int(react or 0)
+
+    # ---- 期末存量:每 (user, channel) 最新 ≤end 行,跨渠道相加 ----
+    stock_conds = [
+        EmployeeMetricDaily.day <= end_day,
+        EmployeeMetricDaily.metric_version == METRIC_VERSION,
+        EmployeeMetricDaily.user_id.in_(target),
+    ]
+    if channel is not None:
+        stock_conds.append(EmployeeMetricDaily.channel == channel)
+    latest = (await session.execute(
+        sa.select(
+            EmployeeMetricDaily.user_id.label("uid"),
+            EmployeeMetricDaily.channel.label("ch"),
+            sa.func.max(EmployeeMetricDaily.day).label("d"),
+        ).where(*stock_conds).group_by(
+            EmployeeMetricDaily.user_id, EmployeeMetricDaily.channel
+        )
+    )).all()
+    if latest:
+        # (user, channel, day) 含 metric_version 唯一(主键)——OR 点查
+        # 精确取回各渠道最新行,再按 user 跨渠道 SUM
+        stocks = (await session.execute(
+            sa.select(
+                EmployeeMetricDaily.user_id.label("uid"),
+                sa.func.sum(EmployeeMetricDaily.new_customer_count).label("nw"),
+                sa.func.sum(
+                    EmployeeMetricDaily.cooling_customer_count
+                ).label("cool"),
+                sa.func.sum(
+                    EmployeeMetricDaily.dormant_customer_count
+                ).label("dorm"),
+                sa.func.sum(EmployeeMetricDaily.active_friends).label("af"),
+            ).where(sa.or_(*(
+                sa.and_(
+                    EmployeeMetricDaily.user_id == uid,
+                    EmployeeMetricDaily.channel == ch,
+                    EmployeeMetricDaily.day == d,
+                    EmployeeMetricDaily.metric_version == METRIC_VERSION,
+                )
+                for uid, ch, d in latest
+            ))).group_by(EmployeeMetricDaily.user_id)
+        )).all()
+        for uid, nw, cool, dorm, af in stocks:
+            a = acc[uid]
+            a["new_customer"] = int(nw or 0)
+            a["cooling_customer"] = int(cool or 0)
+            a["dormant_customer"] = int(dorm or 0)
+            a["end_active_friends"] = int(af or 0)
+
+    # ---- fact 分位 + 2h/24h 回复计数(同一过滤,Python 侧一次聚合) ----
+    fr_conds = [FirstReplyFact.day.between(start_day, end_day)]
+    if channel is not None:
+        fr_conds.append(FirstReplyFact.channel == channel)
+    fr_rows = (await session.execute(
+        sa.select(
+            FirstReplyFact.owner_account_id.label("owner"),
+            FirstReplyFact.fr_ms.label("fr"),
+        ).where(*fr_conds)
+    )).all()
+    fr_by_user: dict[str, list[int]] = {}
+    for owner, fr in fr_rows:
+        uid = amap.get(owner or "")
+        if uid is not None and uid in target:
+            fr_by_user.setdefault(uid, []).append(int(fr))
+    for uid, frs in fr_by_user.items():
+        acc[uid]["fr_p50_ms"] = percentile(frs, 1, 2)
+        acc[uid]["fr_p90_ms"] = percentile(frs, 9, 10)
+        # 2h/24h 计数与分位同源同窗——回复率分子分母口径一致
+        acc[uid]["reply_2h_count"] = sum(1 for fr in frs if fr <= 7_200_000)
+        acc[uid]["reply_24h_count"] = sum(1 for fr in frs if fr <= 86_400_000)
+
+    # ---- distinct 活跃客户:账号归并到员工后按 peer 去重 ----
+    af_conds = [
+        MsgDailyStats.day.between(start_day, end_day),
+        MsgDailyStats.peer_kind == "friend",
+    ]
+    if channel is not None:
+        af_conds.append(MsgDailyStats.channel == channel)
+    pairs = (await session.execute(
+        sa.select(MsgDailyStats.owner_account_id, MsgDailyStats.peer_id)
+        .distinct().where(*af_conds)
+    )).all()
+    active: dict[str, set[str]] = {}
+    for owner, peer in pairs:
+        uid = amap.get(owner or "")
+        if uid is None or uid not in target:
+            continue
+        # (uid, peer) 粒度:同一员工多账号(wx1+wx2)的共享客户只计 1
+        # ——与宽表日值口径一致(storage 侧账号归并后 add(peer))
+        active.setdefault(uid, set()).add(peer or "")
+    for uid, pset in active.items():
+        acc[uid]["active_friends"] = len(pset)
+
+    # ---- 通话:恒全渠道(表无渠道维,channel 参数不过滤) ----
+    calls = (await session.execute(
+        sa.select(
+            EmployeeCallDaily.user_id.label("uid"),
+            sa.func.sum(EmployeeCallDaily.call_count).label("cc"),
+            sa.func.sum(EmployeeCallDaily.call_seconds).label("cs"),
+            sa.func.sum(EmployeeCallDaily.answered_call_count).label("ca"),
+            sa.func.sum(EmployeeCallDaily.call_followup_count).label("cf"),
+        ).where(
+            EmployeeCallDaily.day.between(start_day, end_day),
+            EmployeeCallDaily.user_id.in_(target),
+        ).group_by(EmployeeCallDaily.user_id)
+    )).all()
+    for uid, cc, cs, ca, cf in calls:
+        a = acc[uid]
+        a["call_count"] = int(cc or 0)
+        a["call_seconds"] = int(cs or 0)
+        a["answered_call"] = int(ca or 0)
+        a["call_followup"] = int(cf or 0)
+
+    return {
+        uid: PeriodMetrics(
+            user_id=uid,
+            days_with_data=a["days_with_data"],
+            msg_sent=a["msg_sent"],
+            msg_recv=a["msg_recv"],
+            cust_threads=a["cust_threads"],
+            threads_answered=a["threads_answered"],
+            fr_sum_ms=a["fr_sum_ms"],
+            fr_p50_ms=a["fr_p50_ms"],
+            fr_p90_ms=a["fr_p90_ms"],
+            reply_2h_count=a["reply_2h_count"],
+            reply_24h_count=a["reply_24h_count"],
+            active_friends=a["active_friends"],
+            active_rooms_avg=(a["active_rooms_sum"] / n_days) if n_days else 0.0,
+            new_customer=a["new_customer"],
+            cooling_customer=a["cooling_customer"],
+            dormant_customer=a["dormant_customer"],
+            end_active_friends=a["end_active_friends"],
+            reactivated_customer=a["reactivated_customer"],
+            call_count=a["call_count"],
+            call_seconds=a["call_seconds"],
+            answered_call=a["answered_call"],
+            call_followup=a["call_followup"],
+        )
+        for uid, a in acc.items()
+    }
+
+
+def team_medians(metrics: dict[str, PeriodMetrics]) -> dict[str, float | None]:
+    """每数值字段的全员中位数(纯函数,评分归一用)。
+
+    None(无样本的分位等)剔除后取中位——statistics.median:奇数取中位
+    样本、偶数取中间两数均值;全员 None → None(调用方按无基线处理)。
+    """
+    out: dict[str, float | None] = {}
+    for field in PeriodMetrics._fields:
+        if field == "user_id":
+            continue
+        vals = [
+            v for v in (getattr(m, field) for m in metrics.values())
+            if v is not None
+        ]
+        out[field] = statistics.median(vals) if vals else None
+    return out

yunke-server/app/management/metric_definitions.py

@@ -0,0 +1,205 @@
+"""管理域指标元数据与默认评分配置(批次B,v2 §6/§10)。
+
+METRIC_DEFINITIONS 是 /api/management/metric-definitions 的单一数据源:
+名称/单位/方向/口径说明(含与现有看板的三方口径差异标注)。
+DEFAULT_SCORE_CONFIG 为 v1.0 试算起点——所有阈值标「试算」,调整走
+新配置版本(employee_score_config),不静默改数。
+"""
+from __future__ import annotations
+
+import copy
+
+import sqlalchemy as sa
+
+# direction: +1 越大越好 / -1 越小越好;caliber 注明与看板差异
+METRIC_DEFINITIONS: dict[str, dict] = {
+    "msg_sent": {"name": "发出消息(1:1)", "unit": "条", "direction": 1,
+                 "caliber": "仅私聊;现有看板为私聊+群聊混合"},
+    "msg_recv": {"name": "收到消息(1:1)", "unit": "条", "direction": 1,
+                 "caliber": "仅私聊"},
+    "cust_threads": {"name": "客户消息串", "unit": "串", "direction": 1,
+                     "caliber": "跨日精确,按串末条归属日;看板为日切口径(多日串重复计)"},
+    "threads_answered": {"name": "被回串数", "unit": "串", "direction": 1,
+                         "caliber": "≡first_reply_fact行数(同源)"},
+    "fr_avg_ms": {"name": "平均首响", "unit": "ms", "direction": -1,
+                  "caliber": "fr_sum_ms/threads_answered"},
+    "fr_p50_ms": {"name": "首响中位数", "unit": "ms", "direction": -1,
+                  "caliber": "周期内 fact 精确分位(窗口函数)"},
+    "fr_p90_ms": {"name": "首响P90", "unit": "ms", "direction": -1,
+                  "caliber": "周期内 fact 精确分位;日切口径会丢跨夜长尾"},
+    "reply_2h_rate": {"name": "2h回复率", "unit": "0-1", "direction": 1,
+                      "formula": "count(fr_ms<=2h)/cust_threads",
+                      "caliber": "分子分母同源(fact/宽表同一算法)"},
+    "reply_24h_rate": {"name": "24h回复率", "unit": "0-1", "direction": 1,
+                       "formula": "count(fr_ms<=24h)/cust_threads"},
+    "active_friends": {"name": "活跃客户(周期)", "unit": "人", "direction": 1,
+                       "caliber": "期内distinct客户(msg_daily_stats直查),非宽表日值求和"},
+    "active_rooms": {"name": "活跃群(日均)", "unit": "个", "direction": 1},
+    "new_customer_count": {"name": "新客(期末)", "unit": "人", "direction": 1,
+                           "caliber": "期末单日持有状态,非期内求和"},
+    "cooling_customer_count": {"name": "降温客户(期末)", "unit": "人", "direction": -1,
+                               "caliber": "距今天数口径(7-29天);频次基线口径二期"},
+    "dormant_customer_count": {"name": "沉睡客户(期末)", "unit": "人", "direction": -1,
+                               "caliber": "≥30天且历史≥5条"},
+    "reactivated_customer_count": {"name": "回流客户(期内)", "unit": "人", "direction": 1,
+                                   "caliber": "当日回流且前次间隔>30天,期内求和"},
+    "call_count": {"name": "通话数", "unit": "通", "direction": 1,
+                   "caliber": "语音通话(微信+WA),无消息渠道维度"},
+    "answered_rate": {"name": "接通率", "unit": "0-1", "direction": 1,
+                      "formula": "answered_call/call_count", "caliber": "接通=duration>0"},
+    "call_followup_rate": {"name": "通话后跟进率", "unit": "0-1", "direction": 1,
+                           "formula": "call_followup_count/answered_call",
+                           "caliber": "接通后24h内任一账号有1:1消息(含客户发来)"},
+    "active_share": {"name": "活跃客户占比", "unit": "0-1", "direction": 1,
+                     "formula": "期末active_friends/(期末active+cooling+dormant)",
+                     "caliber": "试算口径:期末单日存量;宽表无生命周期active存量列,active以active_friends列充当"},
+}
+
+# 阈值全部为试算起点(v2 §0 决议:全默认+试算标记);type 三种:
+#   target      : floor..target 线性 0..100(方向已含在 target>floor)
+#   reverse     : ≤target_ms 100 分,≥floor_ms 0 分,中间线性降
+#   band        : 区间内 100,超上限 80(不再加分),低于下限 None(负载
+#                 不足→不评分)——得分取值范围 80..100
+DEFAULT_SCORE_CONFIG: dict = {
+    "version": "v1.0",
+    "name": "一期试算(3维可用)",
+    "normalization": "available_only_rescale",  # 可用维度 100/Σweight 再 ×100
+    "trial": True,
+    "sample_guards": {"min_threads": 30, "soft_threads": 10, "min_days": 5},
+    "grade_bounds": {"A": 90, "B": 80, "C": 70, "D": 60},  # 低于 D 线为 E
+    "dimensions": {
+        "customer": {"weight": 30, "name": "客户经营", "metrics": {
+            "active_share": {"type": "target", "floor": 0.20, "target": 0.60},
+        }},
+        "service": {"weight": 25, "name": "服务质量", "metrics": {
+            "reply_2h_rate": {"type": "target", "floor": 0.40, "target": 0.85},
+            "reply_24h_rate": {"type": "target", "floor": 0.75, "target": 0.97},
+            "fr_p90_ms": {"type": "reverse", "target_ms": 1_800_000,
+                          "floor_ms": 14_400_000},  # 30min..4h
+        }},
+        "action": {"weight": 20, "name": "行动执行",
+                   "status": "pending_data"},  # 批次E 接 followups/任务
+        "workload": {"weight": 15, "name": "有效负载", "metrics": {
+            # basis=period_distinct:用周期 distinct active_friends(B1 口径),
+            # 比单日期末值更抗单日噪声(2026-09-09 B2 决议)
+            "active_friends_band": {"type": "band", "metric": "active_friends",
+                                    "low": 5, "high": 80,
+                                    "basis": "period_distinct"},
+            "call_band": {"type": "band", "metric": "call_count",
+                          "low": 1, "high": 200, "basis": "period_total",
+                          "note": "通话低不扣分仅提示;band 得分下限 80"},
+        }},
+        "risk": {"weight": 10, "name": "合规风险",
+                 "status": "pending_data"},  # 批次E/三期接风险事件
+    },
+}
+
+
+def validate_config(config: dict) -> list[str]:
+    """配置校验:权重总和/结构/引用的 metric_code 有元数据/阈值形状/
+    grade_bounds 形状/指标 code 跨维度唯一。
+
+    阈值形状(随评分引擎落地的 B0 评审预埋要求):
+    - type 须为 target/reverse/band 三者之一
+    - target : floor < target
+    - reverse: target_ms < floor_ms(100 分线在 0 分线之前)
+    - band   : low < high
+    B4 预埋(配置将自 DB 加载,写入侧不再重跑种子校验):
+    - grade_bounds 须含 A/B/C/D 且严格降序
+    - 指标 code 跨维度不得重复:metrics_detail 为扁平 dict,
+      同名 code 会相互覆盖(后写胜出)
+    - 源指标名跨维度不得重复:employees 行 comparisons 按源名建键
+      (api_assembly._code_to_source),两个 code 指向同一源名会静默覆盖
+    """
+    problems: list[str] = []
+    dims = config.get("dimensions", {})
+    total = sum(d.get("weight", 0) for d in dims.values())
+    if total != 100:
+        problems.append(f"维度权重总和须=100,当前 {total}")
+    gb = config.get("grade_bounds")
+    if not isinstance(gb, dict) or not all(
+        isinstance(gb.get(k), int) for k in ("A", "B", "C", "D")
+    ):
+        problems.append("grade_bounds 须含 A/B/C/D 且严格降序")
+    elif not (gb["A"] > gb["B"] > gb["C"] > gb["D"]):
+        problems.append(
+            f"grade_bounds 须严格降序 A>B>C>D"
+            f"(当前 A={gb['A']} B={gb['B']} C={gb['C']} D={gb['D']})"
+        )
+    seen_codes: dict[str, str] = {}
+    seen_sources: dict[str, str] = {}
+    for key, dim in dims.items():
+        if dim.get("status") == "pending_data":
+            continue
+        for code, spec in dim.get("metrics", {}).items():
+            if code in seen_codes:
+                problems.append(f"指标 code 重复定义于多维度: {code}")
+            seen_codes[code] = key
+            src = spec.get("metric", code)
+            if src in seen_sources:
+                problems.append(
+                    f"{key}.{code} 与 {seen_sources[src]} 指向同一源指标 {src}"
+                    f"(comparisons 键域将相互覆盖)"
+                )
+            else:
+                seen_sources[src] = f"{key}.{code}"
+            if src not in METRIC_DEFINITIONS:
+                problems.append(f"{key}.{code} 引用未定义指标 {src}")
+            mtype = spec.get("type")
+            if mtype not in ("target", "reverse", "band"):
+                problems.append(
+                    f"{key}.{code} 类型非法:{mtype!r}(须 target/reverse/band)"
+                )
+            elif mtype == "target" and not spec.get("floor", 0) < spec.get("target", 0):
+                problems.append(
+                    f"{key}.{code} target 型须 floor<target"
+                    f"(当前 floor={spec.get('floor')} target={spec.get('target')})"
+                )
+            elif mtype == "reverse" and not (
+                spec.get("target_ms", 0) < spec.get("floor_ms", 0)
+            ):
+                problems.append(
+                    f"{key}.{code} reverse 型须 target_ms<floor_ms"
+                    f"(当前 target_ms={spec.get('target_ms')}"
+                    f" floor_ms={spec.get('floor_ms')})"
+                )
+            elif mtype == "band" and not spec.get("low", 0) < spec.get("high", 0):
+                problems.append(
+                    f"{key}.{code} band 型须 low<high"
+                    f"(当前 low={spec.get('low')} high={spec.get('high')})"
+                )
+    return problems
+
+
+async def _seed_score_config(session) -> str | None:
+    """种子默认评分配置;已存在同版本返回 None(幂等)。纯会话函数可测。
+
+    同 ensure_starter_words 先例:域包提供纯会话种子函数,CLI 只做接线。
+    config_json 用 deepcopy 冻结快照——JSON 列须整列重赋值,深拷贝防止
+    长驻 API 进程未来的原地修改波及模块常量。
+    """
+    from app.db.models import EmployeeScoreConfig
+
+    problems = validate_config(DEFAULT_SCORE_CONFIG)
+    if problems:
+        raise ValueError(f"score config invalid: {problems}")
+    exists = (
+        await session.execute(
+            sa.select(EmployeeScoreConfig.id).where(
+                EmployeeScoreConfig.version == DEFAULT_SCORE_CONFIG["version"]
+            )
+        )
+    ).scalar_one_or_none()
+    if exists is not None:
+        return None
+    session.add(
+        EmployeeScoreConfig(
+            version=DEFAULT_SCORE_CONFIG["version"],
+            name=DEFAULT_SCORE_CONFIG["name"],
+            status="active",
+            config_json=copy.deepcopy(DEFAULT_SCORE_CONFIG),
+            created_by="seed-cli",
+        )
+    )
+    await session.flush()
+    return DEFAULT_SCORE_CONFIG["version"]

yunke-server/app/management/scoring.py

@@ -0,0 +1,230 @@
+"""管理域评分引擎(批次B)——试算版(v2 §0 决议:全默认+试算标记)。
+
+三类标准化(v1 §10.2):
+- target  : floor..target 线性 0..100(≤floor 得 0,≥target 得 100)
+- reverse : ≤target_ms 100 分,≥floor_ms 0 分,中间线性降
+- band    : 区间内 100,超上限 80(不再加),低于下限 None(负载不足→不评分)
+样本保护(v1 §10.3):指标样本量=串类 cust_threads/band 类 active_friends;
+<soft_threads(10) insufficient 不评分;soft(10)~min_threads(30) 低置信照评。
+维度分=指标均分(等权,None 剔除按剩余归一);总分=可用维度加权重归一
+(满分 Σweight×100/Σweight,一期可用 70 → 100/70 放大回百分制)——
+action/risk pending_data 不参与,不默认 0/100。
+
+band 基数=周期 distinct active_friends(basis=period_distinct,B2 决议:
+比单日期末值更抗噪声且与 B1 口径一致)。
+
+team 中位数键=派生指标名(spec 的 metric 字段,无则 code 本身):
+fr_p90_ms/active_friends/call_count 可直接用 team_medians 输出,
+reply_*_rate/active_share 需调用方对派生值取中位后传入。
+"""
+from __future__ import annotations
+
+import math
+
+from app.management.employee_metrics import PeriodMetrics
+from app.management.metric_definitions import METRIC_DEFINITIONS
+
+_GRADE_ORDER = ("A", "B", "C", "D")  # 低于 D 线为 E
+
+
+def normalize(spec: dict, value: float | None) -> float | None:
+    """三类标准化(v1 §10.2):value None→None;band 低于下限→None。
+
+    - target  : (v-floor)/(target-floor) 线性 0..100,两端截断
+    - reverse : (floor_ms-v)/(floor_ms-target_ms) 线性降 100..0,两端截断
+    - band    : [low,high] 内 100,>high 80(不再加),<low None(不评分)
+    """
+    if value is None:
+        return None
+    mtype = spec["type"]
+    if mtype == "target":
+        floor, target = spec["floor"], spec["target"]
+        if value <= floor:
+            return 0.0
+        if value >= target:
+            return 100.0
+        return (value - floor) / (target - floor) * 100.0
+    if mtype == "reverse":
+        target_ms, floor_ms = spec["target_ms"], spec["floor_ms"]
+        if value <= target_ms:
+            return 100.0
+        if value >= floor_ms:
+            return 0.0
+        return (floor_ms - value) / (floor_ms - target_ms) * 100.0
+    if mtype == "band":
+        low, high = spec["low"], spec["high"]
+        if value < low:
+            return None
+        if value > high:
+            return 80.0
+        return 100.0
+    raise ValueError(f"未知指标类型 {mtype!r}(须 target/reverse/band)")
+
+
+def derive_metrics(pm: PeriodMetrics) -> dict[str, float | None]:
+    """从 PeriodMetrics 派生可评分指标值(键=指标名,None=无值≠0)。
+
+    公有供 anomalies(B3)/dashboard(B4) 复用——评分与异常对比同一派生口径。
+    """
+    out: dict[str, float | None] = {
+        "fr_p90_ms": pm.fr_p90_ms,
+        "active_friends": pm.active_friends,   # band 用,周期 distinct
+        "call_count": pm.call_count,           # band 用,period_total
+    }
+    if pm.cust_threads:
+        out["reply_2h_rate"] = pm.reply_2h_count / pm.cust_threads
+        out["reply_24h_rate"] = pm.reply_24h_count / pm.cust_threads
+    else:
+        # 无串样本→无率(严格区分 0%),分子分母同源
+        out["reply_2h_rate"] = None
+        out["reply_24h_rate"] = None
+    denom = pm.end_active_friends + pm.cooling_customer + pm.dormant_customer
+    out["active_share"] = (
+        pm.end_active_friends / denom if denom > 0 else None
+    )
+    return out
+
+
+def _fmt_ms(ms: float) -> str:
+    minutes = ms / 60_000
+    if minutes >= 60 and minutes % 60 == 0:
+        return f"{minutes // 60:g}h"
+    return f"{minutes:g}min"
+
+
+def _formula_note(spec: dict) -> str:
+    """指标计分公式的中文说明(B4 透出,阈值全部来自 config)。"""
+    mtype = spec["type"]
+    if mtype == "target":
+        return (
+            f"floor {spec['floor']}..target {spec['target']} 线性 0..100 分"
+            "(≤floor 0,≥target 100)"
+        )
+    if mtype == "reverse":
+        return (
+            f"≤{_fmt_ms(spec['target_ms'])} 100 分,"
+            f"≥{_fmt_ms(spec['floor_ms'])} 0 分,中间线性降"
+        )
+    return (
+        f"{spec['low']}..{spec['high']} 区间内 100 分,超上限 80 分,"
+        f"低于 {spec['low']} 不评分(负载不足);basis={spec.get('basis', '-')}"
+    )
+
+
+def score_employee(
+    config: dict,
+    current: PeriodMetrics,
+    baseline: PeriodMetrics | None = None,
+    team: dict[str, float] | None = None,
+    prev: PeriodMetrics | None = None,
+) -> dict:
+    """单员工试算评分(纯函数,B4 端点直接透出)。
+
+    prev/baseline/team 为四对比位槽位:prev/baseline 按同口径派生后对比,
+    team 为指标级中位数(键=派生指标名,可 None)。返回结构见模块 docstring
+    ——metrics_detail 键=配置里的 metric_code(band 型如 active_friends_band)。
+    """
+    cur_vals = derive_metrics(current)
+    prev_vals = derive_metrics(prev) if prev is not None else None
+    base_vals = derive_metrics(baseline) if baseline is not None else None
+    guards = config.get("sample_guards", {})
+    soft = guards.get("soft_threads", 10)
+    minimum = guards.get("min_threads", 30)
+
+    dimensions: dict[str, dict] = {}
+    metrics_detail: dict[str, dict] = {}
+
+    for dim_key, dim in config.get("dimensions", {}).items():
+        entry: dict = {
+            "name": dim.get("name", dim_key),
+            "weight": dim.get("weight", 0),
+            "score": None,
+            "status": "pending",
+        }
+        if dim.get("status") == "pending_data" or not dim.get("metrics"):
+            # 一期 action/risk:数据未接入——不参与归一,不带 metrics
+            dimensions[dim_key] = entry
+            continue
+
+        dim_scores: list[float] = []
+        any_insufficient = False  # 有值但样本不足→维度 insufficient
+        dim_metrics: dict[str, dict] = {}
+        for code, spec in dim["metrics"].items():
+            src = spec.get("metric", code)
+            value = cur_vals.get(src)
+            # 样本量:串类=cust_threads,band 类=active_friends
+            sample_size = (
+                current.active_friends
+                if spec.get("type") == "band" else current.cust_threads
+            )
+            if sample_size >= minimum:
+                sample_status = "ok"
+            elif sample_size >= soft:
+                sample_status = "low_confidence"
+            else:
+                sample_status = "insufficient"
+            score: float | None = None
+            if value is not None:
+                if sample_status == "insufficient":
+                    any_insufficient = True  # 有可评值但不评分
+                else:
+                    score = normalize(spec, value)
+            if score is not None:
+                dim_scores.append(score)
+            dim_metrics[code] = {
+                "value": value,
+                "score": score,
+                "sample_size": sample_size,
+                "sample_status": sample_status,
+                "formula_note": _formula_note(spec),
+            }
+            metrics_detail[code] = {
+                "value": value,
+                "prev": prev_vals.get(src) if prev_vals else None,
+                "baseline": base_vals.get(src) if base_vals else None,
+                "median": team.get(src) if team else None,
+                "sample_size": sample_size,
+                "sample_status": sample_status,
+                "score": score,
+                "unit": METRIC_DEFINITIONS.get(src, {}).get("unit", ""),
+                "name": METRIC_DEFINITIONS.get(src, {}).get("name", code),
+            }
+
+        if dim_scores:
+            entry["score"] = sum(dim_scores) / len(dim_scores)
+            entry["status"] = "scored"
+        elif any_insufficient:
+            entry["status"] = "insufficient"
+        else:
+            entry["status"] = "pending"  # 全部无值(期末无存量/无串样本等)
+        entry["metrics"] = dim_metrics
+        dimensions[dim_key] = entry
+
+    # 可用维度加权重归一:Σ(w×s)/Σw(满分=Σw×100/Σw=100),四舍五入取整
+    available = [
+        (d["weight"], d["score"]) for d in dimensions.values()
+        if d["score"] is not None
+    ]
+    total: int | None = None
+    if available:
+        wsum = sum(w for w, _ in available)
+        total = int(math.floor(
+            sum(w * s for w, s in available) / wsum + 0.5
+        ))
+    grade: str | None = None
+    if total is not None:
+        grade = "E"
+        bounds = config.get("grade_bounds", {})
+        for g in _GRADE_ORDER:  # A..D 阈值递减,首中即停
+            if total >= bounds[g]:
+                grade = g
+                break
+
+    return {
+        "total_score": total,
+        "grade": grade,
+        "score_status": "scored" if total is not None else "insufficient_sample",
+        "trial": bool(config.get("trial")),
+        "dimensions": dimensions,
+        "metrics_detail": metrics_detail,
+    }

yunke-server/app/scraper/wechat.py

@@ -901,7 +901,7 @@ def _normalize_chat_group(record: dict[str, Any]) -> dict[str, Any]:
       ``'YYYY-MM-DD HH:mm:ss'`` 字符串,另兼容 ms-int/数字串,统一归一为
       ms-epoch int,复用 ``_parse_add_time`` 的双形态解析)
     """
-    return {
+    rec = {
         "room_id": record.get("friendWxId"),
         "channel": "wechat",
         "room_name": record.get("friendWxNickname"),
@@ -929,6 +929,12 @@ def _normalize_chat_group(record: dict[str, Any]) -> dict[str, Any]:
         "version": record.get("version"),
         "raw_json": record,
     }
+    # 群备注(2026-09-09 微信群统计):friend_list/es 是唯一备注源
+    # (getChatroomList 行无备注键);**有值才写**——空值不放键,upsert 不
+    # 更新该列,不会被无备注的抓取轮次清空
+    if record.get("friendWxRemark"):
+        rec["group_remark"] = record["friendWxRemark"]
+    return rec
 
 
 async def scrape_wechat_groups(

yunke-server/app/storage/employee_metrics.py

@@ -0,0 +1,356 @@
+"""employee_call_daily / employee_metric_daily 维护层(管理域,批次A)。
+
+数据流(v2 §4):
+  msg_daily_stats(friend) + first_reply_facts 同源扫描 + customer 生命周期
+    → employee_metric_daily (day, channel, user, metric_version)   [Task 6]
+  phone_call(按 user_id+start_call_time 日聚合)
+    → employee_call_daily (day, user)——通话无渠道维(v2 §1.2 #9)     [本任务]
+
+幽灵员工过滤(v2 §1.3 #11):owner 映射不上或不在 staff 表的不落表。
+重算语义:按 day delete+insert,幂等;夜间全量 + (批次F)4h 滚动。
+"""
+from __future__ import annotations
+
+import logging
+import math
+from bisect import bisect_right
+from collections.abc import Iterable
+from itertools import accumulate
+
+import sqlalchemy as sa
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.analytics.lifecycle import classify
+from app.db.models import (
+    Customer,
+    EmployeeCallDaily,
+    EmployeeMetricDaily,
+    Message,
+    MsgDailyStats,
+    PhoneCall,
+    Staff,
+)
+from app.storage.first_reply_facts import (
+    compute_conversation,
+    load_conversation,
+    pairs_active_in_days,
+)
+from app.storage.staff_summary import account_map
+from app.storage.summary import day_bounds_ms
+
+logger = logging.getLogger(__name__)
+
+# 通话类型 → 消息渠道(Task0 核实:channel 列可判别,voice_call=微信/
+# wa_voice_call=WA;followup 消息查询按此收窄)
+_CALL_CHANNEL_TO_MSG: dict[str, str] = {"voice_call": "wechat", "wa_voice_call": "whatsapp"}
+
+
+async def known_user_ids(session: AsyncSession) -> set[str]:
+    """员工主数据 user_id 集合(staff 表;Task0 已核实 41 行全在职)。"""
+    rows = (await session.execute(sa.select(Staff.user_id))).scalars().all()
+    return {u for u in rows if u}
+
+
+async def _followup_exists(
+    session: AsyncSession,
+    msg_channel: str,
+    owner_accounts: list[str],
+    peer: str,
+    call_ts_ms: int,
+    window_ms: int = 86_400_000,
+) -> bool:
+    """通话后 24h 内员工任一账号对该客户有 1:1 消息。
+
+    含客户发来的消息——口径=窗口内存在任一方向 1:1 消息。
+    按通话类型收窄消息渠道(Task0:voice_call→wechat/wa_voice_call→whatsapp,
+    1:1 通话可匹配率 100%,@chatroom 群通话天然不匹配 1:1 消息)。"""
+    if not owner_accounts or not peer:
+        return False
+    n = (
+        await session.execute(
+            sa.select(sa.func.count()).select_from(Message).where(
+                Message.channel == msg_channel,
+                Message.owner_account_id.in_(owner_accounts),
+                Message.talker_id == peer,
+                sa.or_(Message.room_id.is_(None), Message.room_id == ""),
+                Message.timestamp.is_not(None),
+                Message.timestamp > call_ts_ms,
+                Message.timestamp <= call_ts_ms + window_ms,
+            )
+        )
+    ).scalar_one()
+    return bool(n)
+
+
+async def recompute_call_days(session: AsyncSession, days: Iterable[int]) -> int:
+    """重算给定日的通话小表:按 day delete+insert,幂等。返回写入行数。
+
+    口径:接通 = call_duration > 0(Task0:与 call_status=1 差 31 条/1.0%,
+    取 dur>0 与现有 roadmap 口径一致);call_seconds 单位=秒(Task0 已核实);
+    followup 只对已接通通话判定(未接通的回拨语义留二期)。
+    """
+    # 员工→该渠道账号(followup 判定用,按消息渠道分组)
+    acct = {ch: await account_map(session, ch) for ch in ("wechat", "whatsapp")}
+    rev: dict[str, dict[str, list[str]]] = {}  # uid → msg_channel → owners
+    for msg_ch, amap in acct.items():
+        for owner, uid in amap.items():
+            rev.setdefault(uid, {}).setdefault(msg_ch, []).append(owner)
+
+    written = 0
+    staff_ids = await known_user_ids(session)  # 幽灵过滤(v2 §1.3 #11)
+    for day in sorted(set(days)):
+        lo, hi = day_bounds_ms(day)
+        calls = (
+            await session.execute(
+                sa.select(
+                    PhoneCall.user_id,
+                    PhoneCall.channel,
+                    PhoneCall.call_number,
+                    PhoneCall.start_call_time,
+                    PhoneCall.call_duration,
+                ).where(
+                    PhoneCall.start_call_time.is_not(None),
+                    PhoneCall.start_call_time >= lo,
+                    PhoneCall.start_call_time < hi,
+                )
+            )
+        ).all()
+        await session.execute(
+            sa.delete(EmployeeCallDaily).where(EmployeeCallDaily.day == day)
+        )
+        # (uid, call_type, number, ts, dur)——msg_channel 按通话类型映射;
+        # 未知通话类型(如蜂窝 phone_call)无消息渠道可查,followup 判
+        # False 但仍计数
+        agg: dict[str, dict] = {}
+        for uid, call_ch, number, ts, dur in calls:
+            if not uid or uid not in staff_ids:
+                continue
+            a = agg.setdefault(uid, {"cnt": 0, "sec": 0, "answered": 0, "followup": 0})
+            a["cnt"] += 1
+            a["sec"] += int(dur or 0)
+            if (dur or 0) > 0:
+                a["answered"] += 1
+                msg_ch = _CALL_CHANNEL_TO_MSG.get(call_ch or "")
+                if msg_ch and number:
+                    owners = rev.get(uid, {}).get(msg_ch, [])
+                    if await _followup_exists(session, msg_ch, owners, str(number), int(ts)):
+                        a["followup"] += 1
+        for uid, a in sorted(agg.items()):
+            session.add(
+                EmployeeCallDaily(
+                    day=day,
+                    user_id=uid,
+                    call_count=a["cnt"],
+                    call_seconds=a["sec"],
+                    answered_call_count=a["answered"],
+                    call_followup_count=a["followup"],
+                )
+            )
+            written += 1
+    return written
+
+
+METRIC_VERSION = "v1"
+
+
+def _percentile(vals: list[int], q: float) -> int | None:
+    """最近邻秩分位 ceil(q·n);空列表→None(与 0 严格区分)。"""
+    if not vals:
+        return None
+    s = sorted(vals)
+    idx = min(len(s) - 1, max(0, math.ceil(q * len(s)) - 1))
+    return s[idx]
+
+
+async def _lifecycle_daily(
+    session: AsyncSession,
+    days: list[int],
+    channel: str,
+    amap: dict[str, str],
+    valid_users: set[str],
+) -> dict[int, dict[str, dict[str, int]]]:
+    """逐日 {day: {user: {state: count}}}——customer 当前归属 + 互动日 sweep。
+
+    数据源:msg_daily_stats friend 行全历史(互动日/条数)。hist 为 ≤as_of
+    的历史消息数(时点语义:与 last 同一 bisect 位取按日累积数组 cum[idx],
+    as_of 之后的消息不虚增历史日的沉睡门槛)。16k 客户 × 窗口天数
+    bisect+classify,夜间全量实测见批次A核实文档;4h tick 只算当日+3 天。
+    """
+    rows = (
+        await session.execute(
+            sa.select(
+                MsgDailyStats.peer_id, MsgDailyStats.day,
+                MsgDailyStats.send_cnt, MsgDailyStats.recv_cnt,
+            ).where(
+                MsgDailyStats.channel == channel,
+                MsgDailyStats.peer_kind == "friend",
+            )
+        )
+    ).all()
+    # peer → {day: 消息条数};days_list 与累积数组 cum 对齐:
+    # cum[i] = 该客户 ≤days_list[i] 的历史消息数(hist 时点语义)
+    day_msgs: dict[str, dict[int, int]] = {}
+    for peer, day, snd, rcv in rows:
+        dm = day_msgs.setdefault(peer, {})
+        dm[day] = dm.get(day, 0) + int(snd or 0) + int(rcv or 0)
+    interaction = {p: sorted(dm) for p, dm in day_msgs.items()}
+
+    custs = (
+        await session.execute(
+            sa.select(Customer.owner_account_id, Customer.friend_id).where(
+                Customer.channel == channel,
+                sa.or_(Customer.delete_flag.is_(None), Customer.delete_flag == 0),
+                Customer.owner_account_id.is_not(None),
+            )
+        )
+    ).all()
+    peer_to_user: dict[str, str] = {}
+    for owner, peer in custs:
+        uid = amap.get(owner or "")
+        if uid and uid in valid_users and peer:
+            peer_to_user[str(peer)] = uid
+
+    out: dict[int, dict[str, dict[str, int]]] = {d: {} for d in days}
+    for peer, days_list in interaction.items():
+        uid = peer_to_user.get(peer)
+        if uid is None:
+            continue
+        first = days_list[0]
+        cum = list(accumulate(day_msgs[peer][d] for d in days_list))
+        for d in days:
+            idx = bisect_right(days_list, d) - 1
+            if idx < 0:
+                continue
+            last = days_list[idx]
+            prev = days_list[idx - 1] if idx > 0 else None
+            hist_asof = cum[idx]
+            state = classify(first, last, prev, d, hist_asof)
+            if state:
+                out[d].setdefault(uid, {}).setdefault(state, 0)
+                out[d][uid][state] += 1
+    return out
+
+
+async def recompute_metric_days(
+    session: AsyncSession,
+    days: Iterable[int],
+    channels: tuple[str, ...] = ("wechat", "whatsapp"),
+) -> int:
+    """重算给定日的宽表:按 (day, channel) delete+insert,幂等。返回写入行数。
+
+    串类列与首响日值:扫窗口内活跃 friend 会话的**全历史**(每会话一次),
+    与 first_reply_fact 同一 compute_conversation——分子分母同源(v2 §1.1 #5)。
+    """
+    days = sorted(set(days))
+    valid_users = await known_user_ids(session)
+    pairs = await pairs_active_in_days(session, days)
+    pairs_by_channel: dict[str, list] = {}
+    for p in pairs:
+        pairs_by_channel.setdefault(p[0], []).append((p[1], p[2]))
+
+    written = 0
+    for channel in channels:
+        amap = await account_map(session, channel)
+        # ---- 串类+分位:逐会话全历史一次,聚合到 (day, user) ----
+        thread_cols: dict[tuple[int, str], dict] = {}
+        frs: dict[tuple[int, str], list[int]] = {}
+        day_set = set(days)
+        for owner, peer in pairs_by_channel.get(channel, []):
+            uid = amap.get(owner)
+            if uid is None or uid not in valid_users:
+                continue
+            rows = await load_conversation(session, channel, owner, peer)
+            facts, agg = compute_conversation(rows)
+            for d, a in agg.items():
+                if d not in day_set:
+                    continue
+                key = (d, uid)
+                t = thread_cols.setdefault(
+                    key, {"threads": 0, "answered": 0, "fr": 0}
+                )
+                t["threads"] += a.threads
+                t["answered"] += a.answered
+                t["fr"] += a.fr_sum_ms
+                frs.setdefault(key, []).extend(
+                    f.fr_ms for f in facts if f.day == d
+                )
+
+        # ---- 生命周期 ----
+        life = await _lifecycle_daily(session, days, channel, amap, valid_users)
+
+        # ---- 消息计数+负载:msg_daily_stats(算法无关列) ----
+        for day in days:
+            mds = (
+                await session.execute(
+                    sa.select(
+                        MsgDailyStats.owner_account_id,
+                        MsgDailyStats.peer_kind,
+                        MsgDailyStats.peer_id,
+                        MsgDailyStats.send_cnt,
+                        MsgDailyStats.recv_cnt,
+                    ).where(
+                        MsgDailyStats.day == day, MsgDailyStats.channel == channel
+                    )
+                )
+            ).all()
+            await session.execute(
+                sa.delete(EmployeeMetricDaily).where(
+                    EmployeeMetricDaily.day == day,
+                    EmployeeMetricDaily.channel == channel,
+                    EmployeeMetricDaily.metric_version == METRIC_VERSION,
+                )
+            )
+            agg: dict[str, dict] = {}
+            for owner, kind, peer, snd, rcv in mds:
+                uid = amap.get(owner)
+                if uid is None or uid not in valid_users:
+                    continue  # 幽灵过滤
+                a = agg.setdefault(
+                    uid,
+                    {"sent": 0, "recv": 0, "friends": set(), "rooms": set()},
+                )
+                # 消息计数列 = 1:1 口径(v2 §1.1 #2):room 只进 active_rooms
+                if kind == "friend":
+                    a["sent"] += int(snd or 0)
+                    a["recv"] += int(rcv or 0)
+                    a["friends"].add(peer)
+                elif kind == "room":
+                    a["rooms"].add(peer)
+            day_life = life.get(day, {})
+            # 行并集:消息源 ∪ 生命周期源——纯生命周期日(员工当日无消息
+            # 但持有降温/沉睡客户)也要出宽表行,否则客户经营维度漏天
+            all_uids = sorted(set(agg) | set(day_life))
+            for uid in all_uids:
+                a = agg.get(
+                    uid, {"sent": 0, "recv": 0, "friends": set(), "rooms": set()}
+                )
+                key = (day, uid)
+                t = thread_cols.get(key, {"threads": 0, "answered": 0, "fr": 0})
+                lv = day_life.get(uid, {})
+                session.add(
+                    EmployeeMetricDaily(
+                        day=day,
+                        channel=channel,
+                        user_id=uid,
+                        metric_version=METRIC_VERSION,
+                        msg_sent=a["sent"],
+                        msg_recv=a["recv"],
+                        active_friends=len(a["friends"]),
+                        active_rooms=len(a["rooms"]),
+                        cust_threads=t["threads"],
+                        threads_answered=t["answered"],
+                        fr_sum_ms=t["fr"],
+                        first_reply_p50_ms=_percentile(frs.get(key, []), 0.5),
+                        first_reply_p90_ms=_percentile(frs.get(key, []), 0.9),
+                        new_customer_count=lv.get("new", 0),
+                        cooling_customer_count=lv.get("cooling", 0),
+                        dormant_customer_count=lv.get("dormant", 0),
+                        reactivated_customer_count=lv.get("reactivated", 0),
+                        data_complete=True,
+                    )
+                )
+                written += 1
+            # 防御性 flush:防 autoflush=False 类配置下逐日 add 的 ORM 对象
+            # 攒到事务尾(夜间全量约 52k 行;与 Task3 周期性 flush 同教训)
+            await session.flush()
+    return written

yunke-server/app/storage/first_reply_facts.py

@@ -0,0 +1,195 @@
+"""first_reply_fact 维护层(管理域,批次A)——跨日精确串算法。
+
+区别于 app.storage.summary._thread_stats 的日切近似(v2 §1.1 #1):
+按会话**全历史**计算,跨夜串(客户 23:00 → 员工次日 9:00 回)不再丢失。
+**不挂写钩子**(v2 §3.1):由回填 CLI / 4h 滚动 / 夜间全量重算,写钩子
+零改动。只处理 1:1(friend)会话——群串语义不成立。
+
+compute_conversation 同时输出每日串聚合(threads/answered/fr_sum_ms,
+按串末条归属日)——employee_metric_daily 的串类列与 fact 行**同源**
+(回复率分子分母一致,v2 §1.1 #5)。
+
+时序确定性:同毫秒并列(ts 相同的 F/T 消息)按 msg_id 定序(wechat
+msgSvrId 服务端单调,近似真实到达序)——SQL 等键返回顺序未定义,不做
+定序会导致串归属随查询抖动;fact PK 含 reply_msg_id,同毫秒 F,T,F,T
+交换的两个样本不撞主键。
+"""
+from __future__ import annotations
+
+import logging
+from collections import namedtuple
+from collections.abc import Iterable
+
+import sqlalchemy as sa
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.db.models import FirstReplyFact, Message, MsgDailyStats
+from app.storage.summary import day_key
+
+logger = logging.getLogger(__name__)
+
+# 一个被回串的首响样本;day = 串末条客户消息所在上海自然日,
+# reply_msg_id = 闭合该串的员工回复消息 msg_id(PK 并列去重 + 下钻证据)
+FactSample = namedtuple("FactSample", "thread_end_ts reply_ts fr_ms day reply_msg_id")
+# 某会话某日的串聚合(分子分母同源)
+DayAgg = namedtuple("DayAgg", "threads answered fr_sum_ms")
+
+
+class _DayAcc:
+    __slots__ = ("answered", "fr_sum_ms", "threads")
+
+    def __init__(self) -> None:
+        self.threads = 0
+        self.answered = 0
+        self.fr_sum_ms = 0
+
+
+def compute_conversation(rows: list) -> tuple[list[FactSample], dict[int, DayAgg]]:
+    """跨日精确串算法。rows = [(ts, is_send, msg_id)] 该会话全历史,
+    **须按 (ts, msg_id) 升序**(load_conversation 负责排序;同毫秒并列以
+    msg_id 定序,见模块 docstring)。
+
+    - 串 = 客户连续消息(is_send=False)不被员工消息(is_send=True)打断的
+      段;is_send=None 跳过(不打断也不起串)——与 _thread_stats 判定一致。
+    - 每个被回串一个样本:fr_ms = 员工首条回复 ts − 串**末条**客户消息 ts,
+      归属 day = 串末条所在上海自然日(跨夜串不再丢失);reply_msg_id =
+      该回复消息 msg_id——一条回复恰好闭合一个串,同毫秒 F,T,F,T 交换的
+      (thread_end_ts, reply_ts) 并列靠它去重,兼作下钻证据。
+    - 会话末尾仍未闭合的串:计入当日 threads(回复率分母),不产生样本。
+    """
+    facts: list[FactSample] = []
+    acc: dict[int, _DayAcc] = {}
+    in_thread = False
+    end_ts: int | None = None
+    for ts, is_send, msg_id in rows:
+        if is_send is False:
+            in_thread = True
+            end_ts = int(ts)
+        elif is_send is True:
+            if in_thread and end_ts is not None:
+                fr = int(ts) - end_ts
+                d = day_key(end_ts)
+                facts.append(FactSample(end_ts, int(ts), fr, d, msg_id))
+                a = acc.setdefault(d, _DayAcc())
+                a.threads += 1
+                a.answered += 1
+                a.fr_sum_ms += fr
+            in_thread = False
+            end_ts = None
+        # is_send=None:跳过
+    if in_thread and end_ts is not None:  # 会话末尾未闭合串
+        a = acc.setdefault(day_key(end_ts), _DayAcc())
+        a.threads += 1
+    return facts, {d: DayAgg(a.threads, a.answered, a.fr_sum_ms)
+                   for d, a in acc.items()}
+
+
+async def load_conversation(
+    session: AsyncSession, channel: str, owner: str, peer: str
+) -> list:
+    """拉取该 1:1 会话全历史 (timestamp, is_send, msg_id),Python 侧按
+    (ts, msg_id) 排序——串算法需严格时序且同毫秒并列须定序(SQL 等键顺序
+    未定义,不排序会随查询抖动;与 summary.recompute_days 同惯例,避免
+    依赖 SQL 排序)。friend 过滤口径与 summary._peer_filter 的 friend 分支
+    同源:talker_id 原值精确匹配 + room_id 为空(peer_id 与 talker_id 同源
+    同形态,不做截断/归一化)。
+
+    公有命名:employee_metrics 宽表生成复用同一加载口径(同源原则)。"""
+    rows = (
+        await session.execute(
+            sa.select(
+                Message.timestamp, Message.is_send, Message.msg_id
+            ).where(
+                Message.channel == channel,
+                Message.owner_account_id == owner,
+                Message.talker_id == peer,
+                sa.or_(Message.room_id.is_(None), Message.room_id == ""),
+                Message.timestamp.is_not(None),
+            )
+        )
+    ).all()
+    return sorted(rows, key=lambda r: (r[0], r[2]))
+
+
+async def recompute_pairs(
+    session: AsyncSession, pairs: list[tuple[str, str, str]]
+) -> int:
+    """重算给定 friend 会话的 fact 行:按会话 delete+insert,幂等。
+
+    pairs = [(channel, owner_account_id, peer_id)]。返回会话数。每 500 个
+    会话 flush 一次约束 session 内存(与 summary.recompute_all 同惯例——
+    全量回填百万级 fact 行不能攒到最后),同时打进度日志(回填分钟级,
+    可观测)。commit 由调用方负责。
+    """
+    n = 0
+    for channel, owner, peer in sorted(pairs):
+        rows = await load_conversation(session, channel, owner, peer)
+        facts, _agg = compute_conversation(rows)
+        await session.execute(
+            sa.delete(FirstReplyFact).where(
+                FirstReplyFact.channel == channel,
+                FirstReplyFact.owner_account_id == owner,
+                FirstReplyFact.peer_id == peer,
+            )
+        )
+        for f in facts:
+            session.add(
+                FirstReplyFact(
+                    channel=channel,
+                    owner_account_id=owner,
+                    peer_id=peer,
+                    thread_end_ts=f.thread_end_ts,
+                    reply_ts=f.reply_ts,
+                    reply_msg_id=f.reply_msg_id,
+                    day=f.day,
+                    fr_ms=f.fr_ms,
+                )
+            )
+        n += 1
+        if n % 500 == 0:
+            await session.flush()
+            logger.info("first_reply_facts: 已重算 %d 个会话", n)
+    return n
+
+
+async def all_friend_pairs(session: AsyncSession) -> list[tuple[str, str, str]]:
+    """全部 1:1 会话(friend 行 distinct)——全量回填用。
+
+    依赖 msg_daily_stats 已回填(先 stats 后 facts):friend 会话清单取自
+    stats 表而非 message 全表 distinct——写路径钩子保证 stats 常新,代价
+    远低于扫 message。
+    """
+    rows = (
+        await session.execute(
+            sa.select(
+                MsgDailyStats.channel,
+                MsgDailyStats.owner_account_id,
+                MsgDailyStats.peer_id,
+            ).where(MsgDailyStats.peer_kind == "friend")
+        )
+    ).all()
+    return sorted({(r[0], r[1], r[2]) for r in rows})
+
+
+async def pairs_active_in_days(
+    session: AsyncSession, days: Iterable[int]
+) -> list[tuple[str, str, str]]:
+    """窗口内有消息的 friend 会话(4h 滚动重算用;批次F 接调度)。"""
+    rows = (
+        await session.execute(
+            sa.select(
+                MsgDailyStats.channel,
+                MsgDailyStats.owner_account_id,
+                MsgDailyStats.peer_id,
+            ).where(
+                MsgDailyStats.peer_kind == "friend",
+                MsgDailyStats.day.in_(list(days)),
+            )
+        )
+    ).all()
+    return sorted({(r[0], r[1], r[2]) for r in rows})
+
+
+async def recompute_all(session: AsyncSession) -> int:
+    """全量重建(回填/夜间自愈,幂等)。"""
+    return await recompute_pairs(session, await all_friend_pairs(session))

yunke-server/app/storage/repos.py

@@ -62,7 +62,9 @@ from sqlalchemy.orm import DeclarativeBase
 
 from app.db.models import (
     ChatGroup,
+    ChatGroupMemberStats,
     Customer,
+    CustomerAccountLink,
     Department,
     GroupMember,
     Media,
@@ -81,8 +83,10 @@ _logger = logging.getLogger(__name__)
 
 __all__ = [
     "upsert_chat_group",
+    "upsert_chat_group_member_stats",
     "upsert_customer",
     "upsert_customers",
+    "prune_customer_links",
     "upsert_department",
     "upsert_media",
     "upsert_messages",
@@ -380,9 +384,34 @@ async def upsert_customer(session: AsyncSession, rec: dict[str, Any]) -> None:
     """Idempotently upsert one :class:`Customer` (PK = ``friend_id``).
 
     Same ``friend_id`` twice -> one row, with non-PK fields refreshed from the
-    later record.
+    later record. 同时维护 ``customer_account_link``(渠道×账号×客户一行,
+    2026-09-08):customer 档案全局单行 last-wins,共享客户的其他员工关系
+    靠 link 表保留;员工维度列表/计数读 link(对齐云客 per-employee 口径)。
     """
     await _upsert_one(session, Customer, rec)
+    owner = rec.get("owner_account_id")
+    if owner:
+        raw = rec.get("raw_json") or {}
+        link_rec = {
+            "channel": rec.get("channel"),
+            "owner_account_id": owner,
+            "friend_id": rec.get("friend_id"),
+            "friend_nickname": rec.get("friend_nickname"),
+            "friend_remark": rec.get("friend_remark"),
+            "head_image_url": rec.get("head_image_url"),
+            "real_name": rec.get("real_name"),
+            "phone": rec.get("phone"),
+            "last_chat_time": rec.get("last_chat_time"),
+            "add_time": rec.get("add_time"),
+            "send_num": rec.get("send_num"),
+            "receive_num": rec.get("receive_num"),
+            "message_count": rec.get("message_count"),
+            "delete_flag": rec.get("delete_flag"),
+        }
+        # fromType 只在 raw_json(云客数据来源代码,员工客户页列)
+        if isinstance(raw, dict) and raw.get("fromType") is not None:
+            link_rec["from_type"] = raw.get("fromType")
+        await _upsert_one(session, CustomerAccountLink, link_rec)
 
 
 async def upsert_customers(session: AsyncSession, recs: list[dict[str, Any]]) -> int:
@@ -392,10 +421,33 @@ async def upsert_customers(session: AsyncSession, recs: list[dict[str, Any]]) ->
     single row (the last write wins) at the DB layer.
     """
     for rec in recs:
-        await _upsert_one(session, Customer, rec)
+        await upsert_customer(session, rec)
     return len(recs)
 
 
+async def prune_customer_links(
+    session: AsyncSession,
+    *,
+    channel: str,
+    owner_account_id: str,
+    keep_friend_ids: list[str],
+) -> int:
+    """删除该账号名下**不在最新名单**里的 customer_account_link 行。
+
+    云客 isDel=0 只返回当前好友;抓取器逐员工整批 upsert 后调用本函数对账
+    (离开名单=已不是好友,或好友转移)。**调用方必须保证名单完整**(翻满
+    声明 total)再调——拿到半份名单就 prune 会误删。返回删除行数。
+    """
+    conditions = [
+        CustomerAccountLink.channel == channel,
+        CustomerAccountLink.owner_account_id == owner_account_id,
+    ]
+    if keep_friend_ids:
+        conditions.append(CustomerAccountLink.friend_id.not_in(keep_friend_ids))
+    result = await session.execute(sa.delete(CustomerAccountLink).where(*conditions))
+    return int(result.rowcount or 0)
+
+
 async def upsert_messages(session: AsyncSession, recs: list[dict[str, Any]]) -> int:
     """Batch idempotent upsert for :class:`Message` (PK = ``msg_id``).
 
@@ -581,6 +633,18 @@ async def upsert_chat_group(session: AsyncSession, rec: dict[str, Any]) -> None:
         await _upsert_one(session, GroupMember, member_rec)
 
 
+async def upsert_chat_group_member_stats(
+    session: AsyncSession, rec: dict[str, Any]
+) -> None:
+    """Idempotently upsert one :class:`ChatGroupMemberStats` day row.
+
+    PK = (channel, owner_account_id, room_id, day)。每夜「当日窗」抓取的
+    addMembers/lossMembers 落一行;同日重跑刷新(幂等)。页面任意日窗的
+    新增/退出 = 按天求和(2026-09-09 微信群统计对齐)。
+    """
+    await _upsert_one(session, ChatGroupMemberStats, rec)
+
+
 # ---------------------------------------------------------------------------
 # PhoneCall (voice_call) upsert (M2, Task 2.4)
 # ---------------------------------------------------------------------------
@@ -739,8 +803,13 @@ async def upsert_media(
 
     dialect = await _dialect_name(session)
     pk_cols = _pk_col_names(Media)
+    # 只更新实际插入的列(2026-09-10 生产修复):此前取全部表列,server_default
+    # 列(fetched_at/updated_at)不在 values 里 → MySQL 编译出
+    # ``new.fetched_at`` 悬空引用 → 每夜 call_recordings 步骤 1054 静默
+    # 失败,录音本地化停更多日。
     update_cols = [
-        c.name for c in Media.__table__.columns if c.name not in pk_cols
+        c.name for c in Media.__table__.columns
+        if c.name not in pk_cols and c.name in values
     ]
     media_cols = Media.__table__.c
 
@@ -748,7 +817,8 @@ async def upsert_media(
         """Map each updated column to its conflict-set expression.
 
         Volatile download artifacts use ``COALESCE(incoming, existing)``; every
-        other column is refreshed directly from the incoming row.
+        other column is refreshed directly from the incoming row. ``updated_at``
+        刷新为 now()(冲突重下时反映最新一次落盘)。
         """
         set_: dict[str, Any] = {}
         for name in update_cols:
@@ -756,6 +826,7 @@ async def upsert_media(
                 set_[name] = sa.func.coalesce(other_cols[name], media_cols[name])
             else:
                 set_[name] = other_cols[name]
+        set_["updated_at"] = sa.func.now()
         return set_
 
     if dialect == "sqlite":

yunke-server/app/sync/cli.py

@@ -15,6 +15,9 @@ Three invocations (plus analytics backfills, see below)::
     python -m app.sync.cli daily-stats
     python -m app.sync.cli staff-daily-stats
     python -m app.sync.cli sensitive-scan --full
+    python -m app.sync.cli first-reply-facts
+    python -m app.sync.cli employee-metrics
+    python -m app.sync.cli score-config
 
 Auth + DB
 ---------
@@ -49,6 +52,8 @@ import signal
 import sys
 from typing import Any
 
+import sqlalchemy as sa
+
 from app.config import get_settings
 from app.db import models  # noqa: F401  (register tables on Base.metadata)
 from app.db.base import Base
@@ -136,6 +141,43 @@ def _build_parser() -> argparse.ArgumentParser:
         help="Full backfill scan (first deploy / new-word history).",
     )
 
+    # ``first-reply-facts`` ----------------------------------------------
+    p_fr = sub.add_parser(
+        "first-reply-facts",
+        help="Rebuild first_reply_fact (cross-day exact threads).",
+        description=(
+            "Full rebuild of the first-reply fact table from the message "
+            "table (cross-day exact thread algorithm — overnight samples "
+            "not lost, unlike msg_daily_stats day-cut). Deploy backfill + "
+            "nightly self-heal step. Idempotent."
+        ),
+    )
+
+    # ``employee-metrics`` ------------------------------------------------
+    p_emp = sub.add_parser(
+        "employee-metrics",
+        help="Rebuild employee_metric_daily + employee_call_daily.",
+        description=(
+            "Full rebuild of the management wide table (per-day x channel "
+            "x staff, 1:1 caliber) and the call daily table. Must run "
+            "AFTER first-reply-facts (the fact table feeds Batch-B "
+            "scoring and drilldown; both recompute threads from messages "
+            "via one shared algorithm). Deploy backfill + nightly "
+            "self-heal. Idempotent."
+        ),
+    )
+
+    # ``score-config`` ----------------------------------------------------
+    p_score = sub.add_parser(
+        "score-config",
+        help="Seed the default score config (idempotent).",
+        description=(
+            "Insert DEFAULT_SCORE_CONFIG (v1.0, trial) into "
+            "employee_score_config as active. Skips if the version "
+            "already exists. Batch B."
+        ),
+    )
+
     # ``scheduler`` -----------------------------------------------------------
     p_sched = sub.add_parser(
         "scheduler",
@@ -374,6 +416,77 @@ async def _cmd_sensitive_scan(args: argparse.Namespace) -> int:
         await engine.dispose()
 
 
+async def _cmd_first_reply_facts(args: argparse.Namespace) -> int:
+    """全量重建 first_reply_fact(跨日精确串;部署回填/夜间自愈,幂等)。"""
+    settings = get_settings()
+    engine, session_maker = await _init_db(settings.db_url)
+    try:
+        from app.storage.first_reply_facts import recompute_all
+
+        async with session_maker() as session:
+            pairs = await recompute_all(session)
+            await session.commit()
+        print(f"[first-reply-facts] rebuilt {pairs} conversations")
+        return 0
+    finally:
+        await engine.dispose()
+
+
+async def _cmd_employee_metrics(args: argparse.Namespace) -> int:
+    """全量重建 employee_metric_daily + employee_call_daily(幂等)。"""
+    settings = get_settings()
+    engine, session_maker = await _init_db(settings.db_url)
+    try:
+        from app.db.models import MsgDailyStats, PhoneCall
+        from app.storage.employee_metrics import (
+            recompute_call_days,
+            recompute_metric_days,
+        )
+        from app.storage.summary import day_key
+
+        async with session_maker() as session:
+            msg_days = (
+                await session.execute(sa.select(MsgDailyStats.day).distinct())
+            ).scalars().all()
+            # 宽表全走消息派生源,只算消息日。
+            rows = await recompute_metric_days(session, list(msg_days))
+            # 通话日 = 消息日 ∪ 通话日:消息空窗日(节假日/同步缺口)的通话
+            # 也要进小表。start_call_time→上海日必须在 Python 侧走 day_key
+            # ——MySQL 会话时区是 UTC,SQL 日期函数会切错日。
+            call_ts = (
+                await session.execute(
+                    sa.select(PhoneCall.start_call_time)
+                    .where(PhoneCall.start_call_time.is_not(None))
+                    .distinct()
+                )
+            ).scalars().all()
+            call_days = sorted(set(msg_days) | {day_key(ts) for ts in call_ts})
+            calls = await recompute_call_days(session, call_days)
+            await session.commit()
+        print(
+            f"[employee-metrics] rebuilt {rows} wide rows, {calls} call rows "
+            f"({len(call_days)} days)"
+        )
+        return 0
+    finally:
+        await engine.dispose()
+
+
+async def _cmd_score_config(args: argparse.Namespace) -> int:
+    settings = get_settings()
+    engine, session_maker = await _init_db(settings.db_url)
+    try:
+        from app.management.metric_definitions import _seed_score_config
+
+        async with session_maker() as session:
+            version = await _seed_score_config(session)
+            await session.commit()
+        print(f"[score-config] {'seeded ' + version if version else 'already present, skipped'}")
+        return 0
+    finally:
+        await engine.dispose()
+
+
 def main(argv: list[str] | None = None) -> int:
     """CLI entry point. Returns a process exit code."""
     # Configure logging so the scheduler's JSON line + the orchestrator's
@@ -398,6 +511,12 @@ def main(argv: list[str] | None = None) -> int:
             return asyncio.run(_cmd_staff_daily_stats(args))
         if args.command == "sensitive-scan":
             return asyncio.run(_cmd_sensitive_scan(args))
+        if args.command == "first-reply-facts":
+            return asyncio.run(_cmd_first_reply_facts(args))
+        if args.command == "employee-metrics":
+            return asyncio.run(_cmd_employee_metrics(args))
+        if args.command == "score-config":
+            return asyncio.run(_cmd_score_config(args))
     except KeyboardInterrupt:
         # So `python -m app.sync.cli scheduler` exits cleanly on Ctrl-C.
         return 0

yunke-server/app/sync/scheduler.py

@@ -602,41 +602,65 @@ class SyncScheduler:
                 if not bash:
                     logger.error("page sync 'full': bash not found on PATH")
                     return
-                commands: list[list[str]] = [[bash, "scripts/full_sync_all.sh"]]
+                commands = [([bash, "scripts/full_sync_all.sh"], 22 * 3600)]  # 22h 上限:防极端情况拖进次日相位(全量常态 10-20h)
             elif kind == "messages":
-                # 先刷客户列表(最近沟通时间是云客列表的实时排序键,friends 快照
+                # 2026-09-10 调度根治(用户报「员工列表时间差 2 天」):
-                # 滞后会让本地排序与云客第一页完全不同,2026-08-20),再抓全部四类
+                # ① 序列头部刷员工账号表(accounts ~1min)——员工列表「数据
-                # 消息增量(2026-08-21 全接入:水位增量后单对话 1 页,可承受);
+                #    更新时间/最新消息时间」从此最多滞后 4h(此前只在每日
-                # 末尾追加员工朋友圈浅扫(2026-08-25,max-pages 3 即每员工最多
+                #    full 刷,长任务挤掉 full 就停更);
-                # 3 页,新帖通常落第一页;全量翻页由每日 full 走 full_sync_all.sh)
+                # ② 消息实体只扫**近 24h 活跃**对话(--active-window-hours;
+                #    从未扫过的不受限)——全对话遍历(WA 9,357 个×~3.5s≈9h)
+                #    曾把序列拖到 15h+,超过 4h 间隔→与 02:00 full 背靠背
+                #    互相挤死;陈旧对话无新消息,每日 full 兜底;
+                # ③ 每命令超时保险丝(超时 kill 下轮补,增量幂等)。
+                # friends 仍先刷(最近沟通时间是排序键+活跃窗口的判定源)。
+                msg_entities = [
+                    ("accounts", None, 900),
+                    ("wa-accounts", None, 900),
+                    ("friends", None, 2400),
+                    ("wa-friends", None, 2400),
+                    ("messages", 24, 4800),
+                    ("wa-messages", 24, 4800),
+                    # chatroom-stats 全窗(~1min):刷 chat_group.last_chat_time——
+                    # 群消息活跃窗的判定源。不加则窗口用的是昨晚 full 的快照,
+                    # 「昨天安静、今天突然活跃」的群会被窗口漏到明晚(2026-09-10)
+                    ("chatroom-stats", None, 1800),
+                    ("group-messages", 24, 4800),
+                    ("wa-group-messages", 24, 2400),
+                    ("moments", None, 2400),
+                ]
                 commands = [
-                    [sys.executable, "scripts/scrape_via_page.py", "--entity", "friends"],
+                    (
-                    [sys.executable, "scripts/scrape_via_page.py", "--entity", "wa-friends"],
-                ] + [
                         [
                             sys.executable,
                             "scripts/scrape_via_page.py",
                             "--entity",
-                        e,
+                            entity,
+                        ]
+                        + (
+                            [
                                 "--max-conversations",
                                 "99999",
+                                "--active-window-hours",
+                                str(window),
                             ]
-                    for e in ("messages", "wa-messages", "group-messages", "wa-group-messages")
+                            if window
-                ] + [
+                            else (
-                    [
+                                ["--max-pages", "3"]
-                        sys.executable,
+                                if entity == "moments"
-                        "scripts/scrape_via_page.py",
+                                else []
-                        "--entity",
+                            )
-                        "moments",
+                        ),
-                        "--max-pages",
+                        timeout,
-                        "3",
+                    )
-                    ]
+                    for entity, window, timeout in msg_entities
                 ]
             elif kind == "full-history":
                 # 每周全量对齐(周日 05:00):强制全量翻历史,对齐增量模式抓不到的
                 # 撤回/编辑消息 + 彻底消除 lastChatTime 滞后窗口(2026-08-21)
                 entities = ["messages", "group-messages", "wa-messages", "wa-group-messages"]
                 commands = [
+                    (
                         [
                             sys.executable,
                             "scripts/scrape_via_page.py",
@@ -645,7 +669,10 @@ class SyncScheduler:
                             "--max-conversations",
                             "99999",
                             "--full-history",
-                    ]
+                        ],
+                        6 * 3600,  # 单实体 6h 上限(2026-09-10:防周日的全历史
+                        # 对齐拖进周一,把 02:00 full 又挤掉——同类事故根治)
+                    )
                     for e in entities
                 ]
             else:
@@ -653,8 +680,8 @@ class SyncScheduler:
                 return
 
             rc = 0
-            for args in commands:
+            for args, timeout in commands:
-                rc = await self._page_subprocess(args) or rc
+                rc = await self._page_subprocess(args, timeout=timeout) or rc
                 if rc != 0:
                     logger.warning("page sync %s: command failed rc=%s, skipping rest", kind, rc)
                     break
@@ -674,25 +701,27 @@ class SyncScheduler:
             print(line, flush=True)
 
     async def _analytics_tick(self) -> None:
-        """4h 分析链(stat_daily_staff 滚动3天 + 敏感词增量)——异常只记日志不断链。
+        """4h 分析链(staff 滚动3天 + 敏感词增量 + 管理域滚动)——异常只记日志不断链。
 
-        纯 DB 无浏览器子进程,不抢 ``_page_lock``(DB 写毫秒级;
+        两段独立事务:段1 staff+敏感词(既有);段2 管理域(fact 近3天活跃会话
-        ``max_instances=1`` 防自身重叠即可)。与夜间 full_sync 的
+        + 宽表/通话 滚动3天,批次F 2026-09-10)。段2 失败只回滚自身,不牵连
-        staff-daily-stats 步骤重叠时,两侧 DELETE+INSERT 在重叠 PK 范围上
+        段1 已提交结果(v2 Task12:指标失败不中断主分析链)。纯 DB 无浏览器
-        可能死锁/锁等待——非致命:tick 吞异常下轮重试,夜间脚本无 set -e
+        子进程,不抢 ``_page_lock``;``max_instances=1`` 防自身重叠即可。与
-        次日自愈(UNIQUE/PK 幂等只保证串行提交下不重复,不消锁竞争)。
+        夜间 full_sync 的汇总/管理步重叠时,两侧 DELETE+INSERT 在重叠 PK
+        范围可能锁等待——非致命:tick 吞异常下轮重试,夜间脚本幂等自愈。
 
         时区:``day_key`` 内部钉死 Asia/Shanghai,喂 UTC epoch
-        (``time.time()*1000``)即无歧义——用 epoch 而非 naive datetime
+        (``time.time()*1000``)即无歧义。
-        只为读法直接,数学上两者经本地时区往返等价。
         """
+        from app.storage.summary import day_key
+
+        today = day_key(int(time.time() * 1000))
+        # ── 段1:staff 滚动 + 敏感词增量(既有,语义原样) ──
         try:
             async with self._session_maker() as session:
                 from app.analytics.sensitive import scanner
                 from app.storage.staff_summary import recompute_days, rolling_days
-                from app.storage.summary import day_key
 
-                today = day_key(int(time.time() * 1000))
                 n = await recompute_days(session, rolling_days(today, 3))
                 scan = await scanner.run_incremental(session)
                 await session.commit()
@@ -703,8 +732,39 @@ class SyncScheduler:
         except Exception:  # noqa: BLE001 — scheduler MUST NOT crash
             logger.exception("analytics tick failed")
 
-    async def _page_subprocess(self, args: list[str]) -> int:
+        # ── 段2:管理域滚动(fact 活跃会话 + 宽表/通话,当日+滚动3天) ──
-        """启动页面子进程并等待结束;继承环境 + 补 DB_URL/PYTHONIOENCODING。"""
+        try:
+            async with self._session_maker() as session:
+                from app.storage.employee_metrics import (
+                    recompute_call_days,
+                    recompute_metric_days,
+                )
+                from app.storage.first_reply_facts import (
+                    pairs_active_in_days,
+                    recompute_pairs,
+                )
+                from app.storage.staff_summary import rolling_days
+
+                rd = rolling_days(today, 3)
+                pairs = await pairs_active_in_days(session, rd)
+                f = await recompute_pairs(session, pairs)
+                w = await recompute_metric_days(session, rd)
+                c = await recompute_call_days(session, rd)
+                await session.commit()
+            logger.info(
+                "[analytics-tick] mgmt fact_pairs=%s wide_rows=%s call_rows=%s",
+                f, w, c,
+            )
+        except Exception:  # noqa: BLE001
+            logger.exception("management metrics tick failed")
+
+    async def _page_subprocess(self, args: list[str], *, timeout: float | None = None) -> int:
+        """启动页面子进程并等待结束;继承环境 + 补 DB_URL/PYTHONIOENCODING。
+
+        ``timeout``(秒,2026-09-10 调度根治保险丝):超时 kill 子进程返回
+        非零——上游 break 跳过本序列剩余命令,增量幂等下轮自动补,防止
+        单命令拖死整个调度相位(4h 序列曾因此 15h+ 与 full 互相挤死)。
+        """
         env = {**os.environ, "PYTHONIOENCODING": "utf-8"}
         settings = get_settings()
         if settings.db_url and "DB_URL" not in env:
@@ -714,7 +774,18 @@ class SyncScheduler:
             cwd=str(REPO_ROOT),
             env=env,
         )
+        if timeout is None:
             return await proc.wait()
+        try:
+            return await asyncio.wait_for(proc.wait(), timeout)
+        except asyncio.TimeoutError:
+            logger.error(
+                "page sync subprocess timeout after %.0fs (killed): %s",
+                timeout, " ".join(args[-6:]),
+            )
+            proc.kill()
+            await proc.wait()
+            return 124  # 超时语义(同 shell timeout 惯例)
 
     async def _safe_run(
         self, entity: str, *, log: bool = True

yunke-server/migrations/versions/b7c8d9e0f1a2_management_phase1_tables.py

@@ -0,0 +1,164 @@
+"""经营管理后台批次A:6 张新表(fact/宽表/通话小表/评分配置/快照/辅导)
+
+Revision ID: b7c8d9e0f1a2
+Revises: f7a8b9c0d1e2
+Create Date: 2026-09-08
+
+spec: docs/superpowers/plans/2026-09-08-yunke-management-console-implementation-v2.md §3。
+幂等:sa.inspect 先查,存在即跳过;SQLite/MySQL 通用。回填走 CLI
+(first-reply-facts / employee-metrics),migration 不扫数据。
+"""
+from collections.abc import Sequence
+
+import sqlalchemy as sa
+from alembic import op
+
+revision: str = "b7c8d9e0f1a2"
+down_revision: str | Sequence[str] | None = "f7a8b9c0d1e2"
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+_TABLES = [
+    ("first_reply_fact", lambda: op.create_table(
+        "first_reply_fact",
+        sa.Column("channel", sa.String(length=16), primary_key=True),
+        sa.Column("owner_account_id", sa.String(length=128), primary_key=True),
+        sa.Column("peer_id", sa.String(length=128), primary_key=True),
+        sa.Column("thread_end_ts", sa.BigInteger(), primary_key=True),
+        sa.Column("reply_ts", sa.BigInteger(), primary_key=True),
+        # 同毫秒 F,T,F,T 交换的 (thread_end_ts, reply_ts) 并列去重(一条回复
+        # 恰好闭合一个串,reply_msg_id 唯一定位);兼作下钻证据定位回复消息
+        sa.Column("reply_msg_id", sa.String(length=64), primary_key=True),
+        sa.Column("day", sa.Integer(), nullable=False),
+        sa.Column("fr_ms", sa.BigInteger(), nullable=False),
+    )),
+    ("employee_metric_daily", lambda: op.create_table(
+        "employee_metric_daily",
+        sa.Column("day", sa.Integer(), primary_key=True),
+        sa.Column("channel", sa.String(length=16), primary_key=True),
+        sa.Column("user_id", sa.String(length=64), primary_key=True),
+        sa.Column("metric_version", sa.String(length=16), primary_key=True,
+                  server_default="v1"),
+        sa.Column("msg_sent", sa.Integer(), nullable=False, server_default=sa.text("0")),
+        sa.Column("msg_recv", sa.Integer(), nullable=False, server_default=sa.text("0")),
+        sa.Column("active_friends", sa.Integer(), nullable=False, server_default=sa.text("0")),
+        sa.Column("active_rooms", sa.Integer(), nullable=False, server_default=sa.text("0")),
+        sa.Column("cust_threads", sa.Integer(), nullable=False, server_default=sa.text("0")),
+        sa.Column("threads_answered", sa.Integer(), nullable=False, server_default=sa.text("0")),
+        sa.Column("fr_sum_ms", sa.BigInteger(), nullable=False, server_default=sa.text("0")),
+        sa.Column("first_reply_p50_ms", sa.BigInteger(), nullable=True),
+        sa.Column("first_reply_p90_ms", sa.BigInteger(), nullable=True),
+        sa.Column("new_customer_count", sa.Integer(), nullable=False, server_default=sa.text("0")),
+        sa.Column("cooling_customer_count", sa.Integer(), nullable=False, server_default=sa.text("0")),
+        sa.Column("dormant_customer_count", sa.Integer(), nullable=False, server_default=sa.text("0")),
+        sa.Column("reactivated_customer_count", sa.Integer(), nullable=False, server_default=sa.text("0")),
+        sa.Column("data_complete", sa.Boolean(), nullable=False, server_default=sa.text("0")),
+        sa.Column("computed_at", sa.DateTime(), nullable=False, server_default=sa.func.now()),
+    )),
+    ("employee_call_daily", lambda: op.create_table(
+        "employee_call_daily",
+        sa.Column("day", sa.Integer(), primary_key=True),
+        sa.Column("user_id", sa.String(length=64), primary_key=True),
+        sa.Column("call_count", sa.Integer(), nullable=False, server_default=sa.text("0")),
+        sa.Column("call_seconds", sa.BigInteger(), nullable=False, server_default=sa.text("0")),
+        sa.Column("answered_call_count", sa.Integer(), nullable=False, server_default=sa.text("0")),
+        sa.Column("call_followup_count", sa.Integer(), nullable=False, server_default=sa.text("0")),
+        sa.Column("computed_at", sa.DateTime(), nullable=False, server_default=sa.func.now()),
+    )),
+    ("employee_score_config", lambda: op.create_table(
+        "employee_score_config",
+        sa.Column("id", sa.Integer(), primary_key=True, autoincrement=True),
+        sa.Column("version", sa.String(length=32), nullable=False, unique=True),
+        sa.Column("name", sa.String(length=128), nullable=False),
+        sa.Column("status", sa.String(length=16), nullable=False, server_default="draft"),
+        sa.Column("effective_from", sa.Integer(), nullable=True),
+        sa.Column("effective_to", sa.Integer(), nullable=True),
+        sa.Column("config_json", sa.JSON(), nullable=False),
+        sa.Column("created_by", sa.String(length=64), nullable=True),
+        sa.Column("approved_by", sa.String(length=64), nullable=True),
+        sa.Column("created_at", sa.DateTime(), nullable=False, server_default=sa.func.now()),
+        sa.Column("activated_at", sa.DateTime(), nullable=True),
+    )),
+    ("employee_score_snapshot", lambda: op.create_table(
+        "employee_score_snapshot",
+        sa.Column("id", sa.Integer(), primary_key=True, autoincrement=True),
+        sa.Column("snapshot_batch_id", sa.String(length=64), nullable=False),
+        sa.Column("period_type", sa.String(length=8), nullable=False),
+        sa.Column("period_start", sa.Integer(), nullable=False),
+        sa.Column("period_end", sa.Integer(), nullable=False),
+        sa.Column("user_id", sa.String(length=64), nullable=False),
+        sa.Column("score_config_version", sa.String(length=32), nullable=False),
+        sa.Column("metric_version", sa.String(length=16), nullable=False),
+        sa.Column("total_score", sa.Integer(), nullable=True),
+        sa.Column("grade", sa.String(length=2), nullable=True),
+        sa.Column("score_status", sa.String(length=24), nullable=False, server_default="scored"),
+        sa.Column("dimension_scores_json", sa.JSON(), nullable=True),
+        sa.Column("metric_details_json", sa.JSON(), nullable=True),
+        sa.Column("data_as_of", sa.Integer(), nullable=False),
+        sa.Column("generated_at", sa.DateTime(), nullable=False, server_default=sa.func.now()),
+        sa.Column("frozen_at", sa.DateTime(), nullable=True),
+        sa.Column("frozen_by", sa.String(length=64), nullable=True),
+        sa.Column("supersedes_id", sa.Integer(), nullable=True),
+        sa.UniqueConstraint("snapshot_batch_id", "user_id",
+                            name="uq_score_snapshot_batch_user"),
+    )),
+    ("management_followup", lambda: op.create_table(
+        "management_followup",
+        sa.Column("id", sa.Integer(), primary_key=True, autoincrement=True),
+        sa.Column("employee_user_id", sa.String(length=64), nullable=False),
+        sa.Column("source_type", sa.String(length=16), nullable=False),
+        sa.Column("source_code", sa.String(length=64), nullable=True),
+        sa.Column("source_period_start", sa.Integer(), nullable=True),
+        sa.Column("source_period_end", sa.Integer(), nullable=True),
+        sa.Column("source_value_json", sa.JSON(), nullable=True),
+        sa.Column("reason", sa.Text(), nullable=True),
+        sa.Column("action_type", sa.String(length=32), nullable=True),
+        sa.Column("owner_manager_id", sa.String(length=64), nullable=True),
+        sa.Column("status", sa.String(length=16), nullable=False, server_default="open"),
+        sa.Column("due_at", sa.DateTime(), nullable=True),
+        sa.Column("result", sa.Text(), nullable=True),
+        sa.Column("employee_feedback", sa.Text(), nullable=True),
+        sa.Column("created_by", sa.String(length=64), nullable=True),
+        sa.Column("created_at", sa.DateTime(), nullable=False, server_default=sa.func.now()),
+        sa.Column("updated_at", sa.DateTime(), nullable=False, server_default=sa.func.now()),
+        sa.Column("closed_at", sa.DateTime(), nullable=True),
+    )),
+]
+
+_INDEXES = [
+    ("first_reply_fact", "ix_fr_fact_day_channel", ["day", "channel"]),
+    ("employee_score_snapshot", "ix_score_snapshot_period", ["period_type", "period_start"]),
+    ("management_followup", "ix_followup_emp_status_due",
+     ["employee_user_id", "status", "due_at"]),
+    ("management_followup", "ix_followup_owner_status", ["owner_manager_id", "status"]),
+]
+
+
+def _has_index(bind, table: str, index: str) -> bool:
+    insp = sa.inspect(bind)
+    if not insp.has_table(table):
+        return False
+    return index in {ix["name"] for ix in insp.get_indexes(table)}
+
+
+def upgrade() -> None:
+    bind = op.get_bind()
+    insp = sa.inspect(bind)
+    for name, create in _TABLES:
+        if not insp.has_table(name):
+            create()
+    # 索引守卫独立于建表(MySQL DDL 逐句自动提交;建表成功但索引失败的
+    # 中断重跑要能补上索引)
+    for table, index, cols in _INDEXES:
+        if not _has_index(bind, table, index):
+            op.create_index(index, table, cols)
+
+
+def downgrade() -> None:
+    bind = op.get_bind()
+    insp = sa.inspect(bind)
+    for table in ("management_followup", "employee_score_snapshot",
+                  "employee_score_config", "employee_call_daily",
+                  "employee_metric_daily", "first_reply_fact"):
+        if insp.has_table(table):
+            op.drop_table(table)

yunke-server/migrations/versions/c9d0e1f2a3b4_group_remark_and_member_stats.py

@@ -0,0 +1,80 @@
+"""chat_group 补 group_remark 列 + chat_group_member_stats 按天进出表
+
+Revision ID: c9d0e1f2a3b4
+Revises: b7c8d9e0f1a2
+Create Date: 2026-09-09
+
+内容
+----
+微信群列表对齐云客「微信群统计」页(2026-09-09 真机探明,数据源切
+``getChatroomList``):
+
+* ``chat_group.group_remark`` —— 群备注列(getChatroomList.remark /
+  friend_list/es 的 friendWxRemark,此前只存 raw_json);
+* ``chat_group_member_stats`` —— 群成员进出**按天**统计表。云客的新增/
+  退出成员数是按任意时间窗实时算的,本地无成员进出事件流,改为每夜抓
+  一次「当日窗」的 addMembers/lossMembers 落行,页面任意日窗=按天求和;
+  上线日起积累,历史日期无数据。
+
+幂等:列/表存在即跳过。SQLite/MySQL 通用。
+"""
+from collections.abc import Sequence
+
+import sqlalchemy as sa
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = 'c9d0e1f2a3b4'
+down_revision: str | Sequence[str] | None = 'b7c8d9e0f1a2'
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+_TABLE = 'chat_group_member_stats'
+_COL = 'group_remark'
+
+
+def _has_table(table: str) -> bool:
+    insp = sa.inspect(op.get_bind())
+    return table in insp.get_table_names()
+
+
+def _has_column(table: str, column: str) -> bool:
+    insp = sa.inspect(op.get_bind())
+    return column in {c["name"] for c in insp.get_columns(table)}
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    if not _has_column("chat_group", _COL):
+        op.add_column("chat_group", sa.Column(_COL, sa.String(255), nullable=True))
+    # 回填:群备注从存量 raw_json.friendWxRemark 提取(friend_list/es 来源;
+    # getChatroomList 行无备注键)。幂等:只补 NULL 行。MySQL 方言
+    # (JSON_UNQUOTE),SQLite(测试库,不走生产迁移)跳过。
+    if op.get_bind().dialect.name == "mysql":
+        op.execute(
+            "UPDATE chat_group SET group_remark = JSON_UNQUOTE(JSON_EXTRACT(raw_json, '$.friendWxRemark')) "
+            "WHERE group_remark IS NULL "
+            "AND JSON_UNQUOTE(JSON_EXTRACT(raw_json, '$.friendWxRemark')) IS NOT NULL "
+            "AND JSON_UNQUOTE(JSON_EXTRACT(raw_json, '$.friendWxRemark')) != ''"
+        )
+    if _has_table(_TABLE):
+        return  # 已建过,幂等跳过
+    op.create_table(
+        _TABLE,
+        sa.Column('channel', sa.String(16), primary_key=True),
+        sa.Column('owner_account_id', sa.String(128), primary_key=True),
+        sa.Column('room_id', sa.String(128), primary_key=True),
+        sa.Column('day', sa.Integer(), primary_key=True),
+        sa.Column('added', sa.Integer(), nullable=False, server_default='0'),
+        sa.Column('lost', sa.Integer(), nullable=False, server_default='0'),
+        sa.Column('fetched_at', sa.DateTime(), nullable=True),
+        sa.Column('updated_at', sa.DateTime(), nullable=True),
+    )
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    if _has_table(_TABLE):
+        op.drop_table(_TABLE)
+    if _has_column("chat_group", _COL):
+        op.drop_column("chat_group", _COL)

yunke-server/migrations/versions/d8e9f0a1b2c3_message_owner_talker_time_index.py

@@ -0,0 +1,41 @@
+"""message 补无渠道前缀索引 (owner_account_id, talker_id, timestamp)
+
+Revision ID: d8e9f0a1b2c3
+Revises: c9d0e1f2a3b4
+Create Date: 2026-09-10
+
+背景:该回未回决赛圈点查在 channel=None(管理驾驶舱 action_counts)时
+无渠道前缀条件,现有索引全部以 channel 打头用不上——服务器 100 万行
+实测 dashboard 34~37s 撞前端 15s 超时;索引落地后 1.3~1.8s。
+幂等:sa.inspect 先查,存在即跳过(服务器已先行手工建同名索引,本迁移
+兜底对齐 schema 版本)。「模型+迁移双声明」防 autogenerate 反 DROP。
+"""
+from collections.abc import Sequence
+
+import sqlalchemy as sa
+from alembic import op
+
+revision: str = "d8e9f0a1b2c3"
+down_revision: str | Sequence[str] | None = "c9d0e1f2a3b4"
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+_IDX = "ix_message_owner_talker_time"
+
+
+def _has_index(bind) -> bool:
+    insp = sa.inspect(bind)
+    if not insp.has_table("message"):
+        return False
+    return _IDX in {ix["name"] for ix in insp.get_indexes("message")}
+
+
+def upgrade() -> None:
+    if not _has_index(op.get_bind()):
+        op.create_index(_IDX, "message",
+                         ["owner_account_id", "talker_id", "timestamp"])
+
+
+def downgrade() -> None:
+    if _has_index(op.get_bind()):
+        op.drop_index(_IDX, table_name="message")

yunke-server/migrations/versions/f7a8b9c0d1e2_customer_account_link_table.py

@@ -0,0 +1,78 @@
+"""customer_account_link 账号↔客户多对多关联表
+
+Revision ID: f7a8b9c0d1e2
+Revises: e6f7a8b9c0d1
+Create Date: 2026-09-08
+
+内容
+----
+customer 表 PK=friend_id 全局一客户一行、归属=最后抓取员工(last-wins)。
+共享客户(同一人加多个员工)在镜像里只挂在最后抓的员工名下——实测 Lily
+云客好友 36,镜像员工客户页只有 12,其余 24 个全在另外 9 个员工名下
+(2026-09-08 用户报「好友数与点进去的数量不一致」真机探明)。
+
+云客口径是**每个账号各算一个**(per-employee 列表连备注/收发计数都按
+关系各一份)。本表每个「渠道×账号×客户」一行:
+
+- 写:repos.upsert_customer 随档案同事务维护(所有好友抓取路径一处挂全);
+- 读:/api/customers?owner_account_id= 改读本表(员工维度列表/计数),
+  与云客 contacts_num 完全对齐;
+- 对账:scrape_friends 逐员工整批 upsert 后删除该员工名下不在最新名单
+  里的 link(云客 isDel=0 返回当前好友,删链=已不是好友)。
+
+**上线后需重跑 friends + wa-friends 各一次回填 link**(server:
+`docker compose exec backend python scripts/scrape_via_page.py --entity friends`)
+——存量关系无法从单行档案反推。
+
+幂等:sa.inspect 先查表存在则跳过。SQLite/MySQL 通用。
+"""
+from collections.abc import Sequence
+
+import sqlalchemy as sa
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = 'f7a8b9c0d1e2'
+down_revision: str | Sequence[str] | None = 'e6f7a8b9c0d1'
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+_TABLE = 'customer_account_link'
+
+
+def _has_table(table: str) -> bool:
+    insp = sa.inspect(op.get_bind())
+    return table in insp.get_table_names()
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    if _has_table(_TABLE):
+        return  # 已建过(或先手工建过),幂等跳过
+    op.create_table(
+        _TABLE,
+        sa.Column('channel', sa.String(16), primary_key=True),
+        sa.Column('owner_account_id', sa.String(128), primary_key=True),
+        sa.Column('friend_id', sa.String(128), primary_key=True),
+        sa.Column('friend_nickname', sa.String(255), nullable=True),
+        sa.Column('friend_remark', sa.String(255), nullable=True),
+        sa.Column('head_image_url', sa.String(1024), nullable=True),
+        sa.Column('real_name', sa.String(64), nullable=True),
+        sa.Column('phone', sa.String(64), nullable=True),
+        sa.Column('last_chat_time', sa.BigInteger(), nullable=True),
+        sa.Column('add_time', sa.BigInteger(), nullable=True),
+        sa.Column('send_num', sa.Integer(), nullable=True),
+        sa.Column('receive_num', sa.Integer(), nullable=True),
+        sa.Column('message_count', sa.Integer(), nullable=True),
+        sa.Column('from_type', sa.Integer(), nullable=True),
+        sa.Column('delete_flag', sa.Integer(), nullable=True),
+        sa.Column('fetched_at', sa.DateTime(), nullable=True),
+        sa.Column('updated_at', sa.DateTime(), nullable=True),
+    )
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    if not _has_table(_TABLE):
+        return
+    op.drop_table(_TABLE)

yunke-server/scripts/backfill_group_members.py

@@ -1,12 +1,15 @@
 #!/usr/bin/env python
-"""从群消息派生 group_member（发言者=成员）。
+"""从群消息派生 group_member（发言者=成员）+ customer 兜底补全昵称/头像。
 
 云客 API 不单独给群成员列表（chatroom payload 的 memberIds 我们抓不到，
-2026-08-20 确认），但群消息的 talker 就是发言成员的 wxid、sender_name 是其
+2026-08-20 确认），但群消息的 talker 就是发言成员的 wxid、sender_name/
-群昵称——368k 群消息足够派生出高质量成员表（覆盖所有发过言的成员）。
+sender_head_url 是其群昵称/头像——群消息足够派生出高质量成员表（覆盖
+所有发过言的成员）。昵称/头像取该成员在群里**最新一条**消息的值。
 
-昵称取该成员在群里最新一条消息的 sender_name（SQLite 的 max()+裸列行为，
+未发言的成员（被拉进群从没说话）从 customer 表兜底：member_id=friend_id
-取 max(timestamp) 同行的值）。幂等可重跑；建议在 group-messages 之后执行。
+命中本司好友时补好友昵称/头像（2026-09-10 群详情成员墙）。
+
+幂等可重跑；建议在 group-messages 之后执行（full_sync_all.sh 8b 已挂）。
 
 用法:
     cd yunke-server && DB_URL="sqlite+aiosqlite:///./smoke.db" \
@@ -26,13 +29,14 @@ from app.storage.repos import _upsert_one
 logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s")
 log = logging.getLogger("backfill_group_members")
 
-# row_number() 窗口取 timestamp 最新一行的 sender_name：MySQL 8 的
+# row_number() 窗口取 timestamp 最新一行的 sender_name/sender_head_url：
-# only_full_group_by 拒绝 SQLite 式「max()+裸列」(1055)，窗口写法两库通用
+# MySQL 8 的 only_full_group_by 拒绝 SQLite 式「max()+裸列」(1055)，窗口
-# 且语义严格（最新一条的昵称），不依赖方言碰巧行为
+# 写法两库通用且语义严格（最新一条的昵称/头像），不依赖方言碰巧行为
 SQL = sa_text("""
-SELECT room_id, talker_id, sender_name, last_ts, msg_count
+SELECT room_id, talker_id, sender_name, sender_head_url, last_ts, msg_count
 FROM (
-  SELECT room_id, talker_id, sender_name, timestamp AS last_ts,
+  SELECT room_id, talker_id, sender_name, sender_head_url,
+         timestamp AS last_ts,
          count(*) OVER (PARTITION BY room_id, talker_id) AS msg_count,
          row_number() OVER (
            PARTITION BY room_id, talker_id ORDER BY timestamp DESC
@@ -44,6 +48,17 @@ FROM (
 WHERE rn = 1
 """)
 
+# 未发言成员兜底:member_id 命中 customer(本司好友)时补 NULL 的昵称/头像。
+# customer 全局一人一行(PK=friend_id),join 不放大行数;COALESCE 只补不清。
+CUSTOMER_FALLBACK = sa_text("""
+UPDATE group_member gm
+JOIN customer c ON c.friend_id = gm.member_id AND c.channel = gm.channel
+SET gm.nickname = COALESCE(gm.nickname, c.friend_nickname),
+    gm.avatar = COALESCE(gm.avatar, c.head_image_url)
+WHERE gm.channel = 'wechat'
+  AND (gm.nickname IS NULL OR gm.avatar IS NULL)
+""")
+
 
 async def main() -> None:
     async with async_engine.connect() as conn:
@@ -51,12 +66,13 @@ async def main() -> None:
     log.info(f"派生出 {len(rows)} 个 (群, 成员) 对")
 
     async with async_session_maker() as session:
-        for room_id, talker_id, sender_name, last_ts, msg_count in rows:
+        for room_id, talker_id, sender_name, head_url, last_ts, msg_count in rows:
             await _upsert_one(session, GroupMember, {
                 "channel": "wechat",
                 "room_id": room_id,
                 "member_id": talker_id,
                 "nickname": sender_name,
+                "avatar": head_url,
                 # raw_json 附加派生统计，抽屉可见
                 "raw_json": {
                     "derived_from": "group_messages",
@@ -65,7 +81,13 @@ async def main() -> None:
                 },
             })
         await session.commit()
-    log.info(f"DONE: group_member upserted={len(rows)}")
+
+    # 兜底补未发言成员(独立事务,幂等)
+    async with async_engine.begin() as conn:
+        res = await conn.execute(CUSTOMER_FALLBACK)
+        log.info(f"customer 兜底补全 {res.rowcount} 行昵称/头像")
+
+    log.info("DONE: group_member upsert 完成")
 
 
 if __name__ == "__main__":

yunke-server/scripts/full_sync_all.sh

@@ -26,6 +26,12 @@ echo "$(date) --- 5/10 WeChat groups ---"
 $PY scripts/scrape_via_page.py --entity groups --max-employees 100
 echo "$(date) --- 5b/10 WA groups ---"
 $PY scripts/scrape_via_page.py --entity wa-groups
+# 5c: 微信群统计(getChatroomList,云客「微信群统计」同款)——全窗刷档案列
+#     (真成员数/群备注/员工信息)+ 昨日窗落成员进出日行(页面窗内新增/退出)
+echo "$(date) --- 5c/10 WeChat chatroom stats ---"
+$PY scripts/scrape_via_page.py --entity chatroom-stats
+YDAY=$(date -d "yesterday" +%F)
+$PY scripts/scrape_via_page.py --entity chatroom-stats --day "$YDAY"
 echo "$(date) --- 6/10 Voice calls (WeChat + WA) ---"
 $PY scripts/scrape_via_page.py --entity voice-calls
 # 语音重扫会把 record_media_hash 覆盖回 None —— 必须紧跟录音重链接
@@ -53,6 +59,15 @@ $PY -m app.sync.cli daily-stats
 # A1 员工指标读路径依赖此表,2026-09-04)
 echo "$(date) --- 12/12 Staff-daily-stats rebuild ---"
 $PY -m app.sync.cli staff-daily-stats
+# 13:首响事实表全量重建(管理域,跨日精确串;批次A)——会话发现读
+#     msg_daily_stats(fact 行直算读 message),故须在 11 步后;与 11/12
+#     同为夜间自愈链(绕过钩子的写入由全量重算纠正)
+echo "$(date) --- 13/14 First-reply-facts rebuild ---"
+$PY -m app.sync.cli first-reply-facts
+# 14:管理宽表+通话小表全量重建(驾驶舱/员工页读路径;串类列与 fact 同
+#     算法各自直算,放 fact 后保持派生链顺序语义)
+echo "$(date) --- 14/14 Employee-metrics rebuild ---"
+$PY -m app.sync.cli employee-metrics
 
 echo "=============================================="
 echo "$(date) === FULL RE-SYNC COMPLETE ==="
@@ -78,6 +93,9 @@ TABLES = [
     ("wechat messages", "SELECT COUNT(*) FROM message WHERE channel='wechat'"),
     ("whatsapp messages", "SELECT COUNT(*) FROM message WHERE channel='whatsapp'"),
     ("daily stats rows", "SELECT COUNT(*) FROM msg_daily_stats"),
+    ("first reply facts", "SELECT COUNT(*) FROM first_reply_fact"),
+    ("employee metric rows", "SELECT COUNT(*) FROM employee_metric_daily"),
+    ("employee call rows", "SELECT COUNT(*) FROM employee_call_daily"),
     ("voice calls", "SELECT COUNT(*) FROM phone_call WHERE channel IN ('voice_call','wa_voice_call')"),
     ("voice clips", "SELECT COUNT(*) FROM voice_clip"),
     ("moments posts", "SELECT COUNT(*) FROM moments_post"),

yunke-server/scripts/scrape_via_page.py

@@ -267,10 +267,10 @@ async def scrape_friends(cookie_str: str, max_employees: int = 100):
     小漂移可忽略,且与云客后台「按员工看客户列表」口径一致。员工清单来自
     本地 wechat_account(user_id 列)。
     """
-    from app.db.base import async_engine
+    from app.db.base import async_engine, async_session_maker
     from sqlalchemy import text as sa_text
     from app.scraper.wechat import _normalize
-    from app.storage.repos import upsert_customer
+    from app.storage.repos import prune_customer_links, upsert_customer
 
     dept = await _root_dept_id()
     async with async_engine.connect() as conn:
@@ -334,9 +334,21 @@ async def scrape_friends(cookie_str: str, max_employees: int = 100):
             if records:
                 await _upsert_all(upsert_customer, records)
                 total_upserted += len(records)
+            # 对账(2026-09-08):云客 isDel=0 返回当前好友;名单取满(>=声明
+            # total)才可信,删掉该账号名下已不在名单里的 link(转移/删好友)。
+            # 半份名单宁可不对账,防误删。
+            pruned = 0
+            if declared is not None and len(rows) >= declared:
+                keep_ids = [r.get("friendWxId") for r in rows if r.get("friendWxId")]
+                async with async_session_maker() as session:
+                    pruned = await prune_customer_links(
+                        session, channel="wechat", owner_account_id=wx_id,
+                        keep_friend_ids=keep_ids,
+                    )
+                    await session.commit()
             logger.info(
                 f"  [{i+1}/{len(employees)}] {wx_id[:16]}..: declared={declared} "
-                f"rows={len(rows)} (total fetched {total_fetched})"
+                f"rows={len(rows)} pruned={pruned} (total fetched {total_fetched})"
             )
             await asyncio.sleep(2 + (i % 3))
 
@@ -502,7 +514,50 @@ async def paginate_chats(fetch_page, end_ms: int, max_pages: int = 200, sleep=No
         await sleep(1)
 
 
-async def _discover_conversations(channel: str, voice_channel: str) -> list[tuple[str, str]]:
+# ---------------------------------------------------------------------------
+# 空对话/空群「已扫」记忆(2026-09-10 同步审计):从未有消息的对话(纯语音/
+# 未聊过客户,WA 实测 2,468 个)水位恒 0,每轮都被当 unscanned 全量翻史
+# (~2.6s/个)——时长黑洞本体。拉到 0 条有效消息即记 sync_state 扫描标记;
+# 发现层排除「已扫空且不活跃」的——客户一旦开始发消息(last_chat_time 进
+# 活跃窗)自动回到访问集;周日 full_history 强制全访问兜底(云客补历史)。
+# ---------------------------------------------------------------------------
+
+
+async def _mark_scan_empty(kind: str, scope: str) -> None:
+    """记录「该对话/群已扫且无消息」。UPDATE 0 行则 INSERT(sync_state 无唯一键)。"""
+    import time as _t
+
+    from app.db.base import async_engine
+    from sqlalchemy import text as sa_text
+
+    now_ms = int(_t.time() * 1000)
+    async with async_engine.begin() as conn:
+        res = await conn.execute(sa_text(
+            "UPDATE sync_state SET last_timestamp = :ts "
+            "WHERE entity_type = :et AND scope_id = :sid"
+        ), {"et": kind, "sid": scope, "ts": now_ms})
+        if not res.rowcount:
+            await conn.execute(sa_text(
+                "INSERT INTO sync_state (entity_type, channel, scope_id, last_timestamp) "
+                "VALUES (:et, NULL, :sid, :ts)"
+            ), {"et": kind, "sid": scope, "ts": now_ms})
+
+
+async def _load_scan_empty(kind: str) -> set[str]:
+    from app.db.base import async_engine
+    from sqlalchemy import text as sa_text
+
+    async with async_engine.connect() as conn:
+        rows = (await conn.execute(sa_text(
+            "SELECT scope_id FROM sync_state WHERE entity_type = :et"
+        ), {"et": kind})).fetchall()
+    return {r[0] for r in rows if r[0]}
+
+
+async def _discover_conversations(
+    channel: str, voice_channel: str, active_since_ms: int | None = None,
+    *, exclude_scanned_empty: bool = True,
+) -> list[tuple[str, str]]:
     """Conversation-pair discovery for the message scrapers (wechat + WA).
 
     Sources (union, dedup):
@@ -515,6 +570,11 @@ async def _discover_conversations(channel: str, voice_channel: str) -> list[tupl
 
     Order: pairs with no messages yet FIRST (new coverage survives an
     interruption), then the rest by customer last_chat_time DESC.
+
+    ``active_since_ms``(2026-09-10 调度根治):4h 增量模式传「now-24h」——
+    **已扫过**的对话仅保留 last_chat_time 在窗内的(活跃的),陈旧对话本轮
+    跳过(没有新消息,每日全量兜底);**从未扫过**的(fresh)无论新旧全保
+    (新覆盖优先原则不变)。None=不过滤(全量模式)。
     """
     import json as _json
 
@@ -524,14 +584,14 @@ async def _discover_conversations(channel: str, voice_channel: str) -> list[tupl
     async with async_engine.connect() as conn:
         cust = (
             await conn.execute(sa_text(
-                "SELECT owner_account_id, friend_id FROM customer "
+                "SELECT owner_account_id, friend_id, last_chat_time FROM customer "
                 "WHERE channel=:ch AND owner_account_id IS NOT NULL AND friend_id IS NOT NULL "
                 "ORDER BY last_chat_time DESC"
             ), {"ch": channel})
         ).fetchall()
         voice = (
             await conn.execute(sa_text(
-                "SELECT raw_json FROM phone_call WHERE channel=:vc"
+                "SELECT raw_json, start_call_time FROM phone_call WHERE channel=:vc"
             ), {"vc": voice_channel})
         ).fetchall()
         with_msgs = (
@@ -542,20 +602,45 @@ async def _discover_conversations(channel: str, voice_channel: str) -> list[tupl
         ).fetchall()
 
     have = {(r[0], r[1]) for r in with_msgs}
+    scanned_empty = (
+        await _load_scan_empty(f"{channel}_conv_empty") if exclude_scanned_empty else set()
+    )
     seen: set[tuple[str, str]] = set()
     fresh: list[tuple[str, str]] = []
     known: list[tuple[str, str]] = []
 
-    def _add(key: tuple[str, str]) -> None:
+    def _active(last_ts: int | None) -> bool:
+        """窗口判定:未开窗口恒真;有窗时 last_ts 缺失(从未聊过)也保(fresh)。"""
+        if active_since_ms is None:
+            return True
+        return last_ts is None or last_ts >= active_since_ms
+
+    def _add(key: tuple[str, str], last_ts: int | None) -> None:
         if key in seen:
             return
         seen.add(key)
-        (fresh if key not in have else known).append(key)
+        if key not in have:
+            # 从未扫过:新覆盖优先,不受窗口限制。但「已扫空且不活跃」的除外
+            # (2026-09-10:WA 2,468 个无消息对话每轮全翻史的黑洞)——一旦
+            # 活跃(last_chat_time 进窗)自动回到访问集;full_history 强制全访。
+            scope = f"{key[0]}:{key[1]}"
+            if (
+                exclude_scanned_empty
+                and scope in scanned_empty
+                and active_since_ms is not None
+                and not _active(last_ts)
+            ):
+                return
+            fresh.append(key)
+        elif _active(last_ts):
+            known.append(key)
+        # else: 已扫过且陈旧 → 本轮跳过
 
-    for owner, friend in cust:
+    for owner, friend, last_ts in cust:
-        _add((owner, friend))
+        _add((owner, friend), last_ts)
     voice_only = 0
-    for (rj,) in voice:
+    cust_keys = {(r[0], r[1]) for r in cust}
+    for rj, call_ts in voice:
         try:
             d = _json.loads(rj)
         except (TypeError, ValueError):
@@ -564,13 +649,15 @@ async def _discover_conversations(channel: str, voice_channel: str) -> list[tupl
         if not owner or not talker or str(talker).endswith("@chatroom"):
             continue
         before = len(seen)
-        _add((str(owner), str(talker)))
+        _add((str(owner), str(talker)), call_ts)
-        if len(seen) > before and (str(owner), str(talker)) not in cust:
+        if len(seen) > before and (str(owner), str(talker)) not in cust_keys:
             voice_only += 1
 
+    skipped = len(cust) + voice_only - len(fresh) - len(known)
     logger.info(
         f"discovery[{channel}]: {len(cust)} customer pairs + {voice_only} voice-only pairs, "
-        f"{len(fresh)} unscanned (first) / {len(known)} already have messages"
+        f"{len(fresh)} unscanned (first) / {len(known)} active in window"
+        + (f" / {skipped} stale skipped" if active_since_ms is not None else f" / {len(known)} already have messages")
     )
     return fresh + known
 
@@ -623,7 +710,7 @@ def _page_min_ts(data: dict) -> int:
     return min(ts_list) if ts_list else 0
 
 
-async def scrape_messages(cookie_str: str, max_conversations: int = 100, full_history: bool = False):
+async def scrape_messages(cookie_str: str, max_conversations: int = 100, full_history: bool = False, active_window_hours: int | None = None):
     """Scrape wechat messages via browser fetch POST /wechatweb/msg/chats.
 
     **增量同步(默认)**:每对话水位 = 本地 max(timestamp);请求带
@@ -636,7 +723,15 @@ async def scrape_messages(cookie_str: str, max_conversations: int = 100, full_hi
     from app.db.base import async_session_maker
     from app.storage.repos import upsert_messages
 
-    conversations = await _discover_conversations("wechat", "voice_call")
+    conversations = await _discover_conversations(
+        "wechat", "voice_call",
+        active_since_ms=(
+            int((__import__("time").time() - active_window_hours * 3600) * 1000)
+            if active_window_hours else None
+        ),
+        # full_history(周日对齐)强制全访问:云客可能补出历史消息
+        exclude_scanned_empty=not full_history,
+    )
     watermarks = await _conversation_watermarks("wechat")
     cust_activity = await _customer_activity("wechat")
 
@@ -725,6 +820,9 @@ async def scrape_messages(cookie_str: str, max_conversations: int = 100, full_hi
                             ts = int(str(ts_raw)) if ts_raw else None
                         except (ValueError, TypeError):
                             ts = None
+                        # 增量模式过滤边界旧消息(云客 start inclusive,2026-09-10)
+                        if watermark and ts is not None and ts <= watermark:
+                            continue
                         records.append({
                             "msg_id": str(row.get("msgId") or row.get("msgSvrId") or row.get("id") or f"{owner_id}:{friend_id}:{i}:{len(records)}"),
                             "channel": "wechat",
@@ -774,6 +872,8 @@ async def scrape_messages(cookie_str: str, max_conversations: int = 100, full_hi
                 continue
 
             total_fetched += len(records)
+            if not records:
+                await _mark_scan_empty("wechat_conv_empty", f"{owner_id}:{friend_id}")
             total_pages += pages
 
             if records:
@@ -841,7 +941,7 @@ def _normalize_group_message(row: dict, owner_id: str, room_id: str) -> dict | N
     }
 
 
-async def scrape_group_messages(cookie_str: str, max_groups: int = 500, full_history: bool = False):
+async def scrape_group_messages(cookie_str: str, max_groups: int = 500, full_history: bool = False, active_window_hours: int | None = None):
     """Scrape WeChat GROUP chat messages via browser fetch POST /wechatweb/msg/chats.
 
     Same endpoint as 1:1 chats — pass the room id as ``friendId`` (confirmed
@@ -856,12 +956,17 @@ async def scrape_group_messages(cookie_str: str, max_groups: int = 500, full_his
     from app.storage.repos import upsert_messages
     from sqlalchemy import text as sa_text
 
+    active_since_ms = (
+        int((__import__("time").time() - active_window_hours * 3600) * 1000)
+        if active_window_hours else None
+    )
     async with async_engine.connect() as conn:
         result = await conn.execute(sa_text(
             "SELECT owner_account_id, room_id FROM chat_group "
             "WHERE channel='wechat' AND owner_account_id IS NOT NULL "
+            "AND (:t IS NULL OR last_chat_time IS NULL OR last_chat_time >= :t) "
             "ORDER BY last_chat_time DESC"
-        ))
+        ), {"t": active_since_ms})
         groups = [(row[0], row[1]) for row in result.fetchall()]
 
     room_wms = await _room_watermarks()
@@ -922,6 +1027,9 @@ async def scrape_group_messages(cookie_str: str, max_groups: int = 500, full_his
                                     continue
                                 rec = _normalize_group_message(row, owner_id, room_id)
                                 if rec is not None:
+                                    # 增量模式过滤边界旧消息(同 1:1,2026-09-10)
+                                    if watermark and (rec.get("timestamp") or 0) <= watermark:
+                                        continue
                                     records.append(rec)
 
                     except Exception as e:
@@ -1463,10 +1571,10 @@ async def scrape_wa_friends(cookie_str: str, max_pages: int = 2000):
     全局查询有 ~1 万行硬上限(实测云客声明 11931 vs 全局翻页只到 10000,
     2026-08-20);逐员工 ``uid`` 过滤(员工 WA 号)范围小无上限,页码字段是
     ``page``,total-aware 翻页(短页继续,满声明数或连续空页停)。"""
-    from app.db.base import async_engine
+    from app.db.base import async_engine, async_session_maker
     from sqlalchemy import text as sa_text
     from app.scraper.whatsapp import _normalize_whatsapp_friend
-    from app.storage.repos import upsert_customer
+    from app.storage.repos import prune_customer_links, upsert_customer
 
     dept = await _root_dept_id()
     async with async_engine.connect() as conn:
@@ -1520,8 +1628,20 @@ async def scrape_wa_friends(cookie_str: str, max_pages: int = 2000):
             if records:
                 await _upsert_all(upsert_customer, records)
                 total_upserted += len(records)
+            # 对账(2026-09-08,同微信 friends):名单取满才删该账号名下
+            # 不在当前列表里的 link。
+            pruned = 0
+            if declared is not None and len(rows) >= declared:
+                keep_ids = [r.get("friendUid") for r in rows if r.get("friendUid")]
+                async with async_session_maker() as session:
+                    pruned = await prune_customer_links(
+                        session, channel="whatsapp", owner_account_id=wa_uid,
+                        keep_friend_ids=keep_ids,
+                    )
+                    await session.commit()
             logger.info(
-                f"  [{i+1}/{len(accounts)}] {wa_uid[:18]}..: declared={declared} rows={len(rows)}"
+                f"  [{i+1}/{len(accounts)}] {wa_uid[:18]}..: declared={declared} "
+                f"rows={len(rows)} pruned={pruned}"
             )
             await asyncio.sleep(2 + (i % 3))
 
@@ -1607,6 +1727,200 @@ async def scrape_wa_groups(cookie_str: str, max_pages: int = 200):
     return total_fetched, total_upserted
 
 
+# ---------------------------------------------------------------------------
+# 微信群统计 getChatroomList(2026-09-09 真机探明,云客同款数据源)
+#
+# 云客「沟通→微信号管理→微信群统计」页(/cms/wechat/wechatgroup)数据源:
+# POST /wechatweb/chatroom/getChatroomList(form-urlencoded)
+#   departmentId + startTime/endTime('YYYY-MM-DD HH:MM:SS' 时间窗) + 分页;
+# 信封 data.overviews[] + totalCount(1,854 行,员工×群维度)。
+# 行含:真 memberCount(群成员数量——friend_list/es 的 friendNum 其实是
+# 员工好友数,旧映射存反了)、remark(群备注)、员工微信(wechatId=微信号
+# alias/wechatNickName/头像)、员工信息(userName/userPhone)、以及**窗内**
+# addMembers/lossMembers(新增/退出成员数,任意窗实时算)。
+#
+# 本地无成员进出事件流 → add/loss 只能按天积累:每夜抓「当日窗」落
+# chat_group_member_stats 日行,页面任意日窗=按天求和(历史无数据)。
+# ---------------------------------------------------------------------------
+
+CHATROOM_LIST_PATH = "/wechatweb/chatroom/getChatroomList"
+
+
+def _normalize_chatroom_stat_row(row: dict, owner_wxid: str) -> dict:
+    """getChatroomList 行 → ChatGroup 补列记录。
+
+    只放该端点有的字段——未出现的列不参与 upsert 的 UPDATE 子句,
+    friend_list/es 抓的群主信息等旧值得以保留。
+    """
+    rec = {
+        "room_id": row.get("chatRoomId"),
+        "channel": "wechat",
+        "owner_account_id": owner_wxid,
+        "room_name": row.get("chatRoomName"),
+        # 真群成员数(修正:旧源 friendNum 是「员工好友数」被误存此列)
+        "member_count": row.get("memberCount"),
+        "head_image_url": row.get("headImageUrl"),
+        "owner_account_nickname": row.get("wechatNickName"),
+        "owner_user_id": row.get("userId"),
+        "owner_user_phone": row.get("userPhone"),
+        "message_count": row.get("messageCount"),
+        "own_message_count": row.get("ownMessageCount"),
+        "add_members": row.get("addMembers"),  # 本窗快照(日窗=当日进出)
+        "loss_members": row.get("lossMembers"),
+        "last_chat_time": row.get("lastChatTime"),
+        "update_time": row.get("updateTime"),
+        "raw_json": row,
+    }
+    # 群备注:getChatroomList 行通常无 remark 键(云客页面也显示 -);有才写,
+    # 无则不放该键——upsert 不更新未出现的列,friend_list/es 来源的
+    # friendWxRemark 备注得以保留
+    if row.get("remark"):
+        rec["group_remark"] = row["remark"]
+    return rec
+
+
+async def _chatroom_rows(
+    page, dept: str, start_str: str, end_str: str, max_pages: int = 100
+) -> tuple[list[dict], int]:
+    """翻完 getChatroomList 一个窗,返回 (全部行, 云客声明 total)。"""
+    rows_all: list[dict] = []
+    declared = 0
+    page_num = 1
+    while page_num <= max_pages:
+        body = await _browser_fetch(
+            page, CHATROOM_LIST_PATH,
+            form_body={
+                "departmentId": dept, "startTime": start_str, "endTime": end_str,
+                "pageNum": page_num, "pageSize": 50,
+            },
+        )
+        data = body.get("data") or {}
+        rows = data.get("overviews") or []
+        rows_all.extend(rows)
+        declared = data.get("totalCount") or declared
+        logger.info(f"  chatroom-list page {page_num}: {len(rows)} rows (total {declared})")
+        if not rows or page_num * 50 >= (declared or 0):
+            break
+        page_num += 1
+        await asyncio.sleep(1.2)
+    return rows_all, declared or 0
+
+
+async def _owner_alias_map(conn):
+    """wechat_account 的 alias/nick_name → wx_id 映射。
+
+    getChatroomList 行的 wechatId 是员工**微信号**(alias,如 Nancyjade)
+    而非 wxId,owner 归属需经此解析;miss 时回退存原值(不影响其余列)。
+    """
+    from sqlalchemy import text as sa_text
+
+    result = await conn.execute(sa_text(
+        "SELECT alias, nick_name, wx_id FROM wechat_account "
+        "WHERE wx_id IS NOT NULL AND wx_id != ''"
+    ))
+    mapping: dict[str, str] = {}
+    for alias, nick, wx in result.fetchall():
+        if alias:
+            mapping[str(alias)] = wx
+        if nick:
+            mapping.setdefault(str(nick), wx)
+    return mapping
+
+
+async def scrape_chatroom_stats(cookie_str: str, day: str | None = None):
+    """getChatroomList 抓取(云客微信群统计同款)。
+
+    * ``day=None``:全窗(2020 起)——chat_group 档案补列基线(真成员数/
+      群备注/员工信息列;add/loss 存全窗快照);
+    * ``day='YYYY-MM-DD'``:单日窗——落 chat_group_member_stats 当日行
+      (页面任意日窗的新增/退出=按天求和)。
+    """
+    import datetime as _dt
+
+    from app.db.base import async_engine
+    from app.storage.repos import upsert_chat_group, upsert_chat_group_member_stats
+
+    dept = await _root_dept_id()
+    async with async_engine.connect() as conn:
+        alias_map = await _owner_alias_map(conn)
+
+    if day:
+        start_str, end_str = f"{day} 00:00:00", f"{day} 23:59:59"
+        day_key = int(day.replace("-", ""))
+    else:
+        start_str = "2020-01-01 00:00:00"
+        end_str = f"{_dt.date.today()} 23:59:59"
+        day_key = None
+
+    group_recs: list[dict] = []
+    stats_recs: list[dict] = []
+    declared = 0
+    async with PageScraper(cookie_str) as scraper:
+        page = await _open_fetch_page(scraper)
+        rows, declared = await _chatroom_rows(page, dept, start_str, end_str)
+        for row in rows:
+            rid = row.get("chatRoomId")
+            if not rid:
+                continue
+            owner_wxid = (
+                alias_map.get(str(row.get("wechatId") or ""))
+                or alias_map.get(str(row.get("wechatNickName") or ""))
+                or str(row.get("wechatId") or "")
+            )
+            group_recs.append(_normalize_chatroom_stat_row(row, owner_wxid))
+            if day_key is not None:
+                stats_recs.append({
+                    "channel": "wechat",
+                    "owner_account_id": owner_wxid,
+                    "room_id": rid,
+                    "day": day_key,
+                    "added": row.get("addMembers") or 0,
+                    "lost": row.get("lossMembers") or 0,
+                })
+
+    if group_recs:
+        await _upsert_all(upsert_chat_group, group_recs)
+    if stats_recs:
+        await _upsert_all(upsert_chat_group_member_stats, stats_recs)
+
+    # 对账(2026-09-10,全窗模式):删掉本地有而云客名单里没有的 chat_group 行
+    # ——friend_list/es 时代的残留行(owner 组合已不在 getChatroomList 返回,
+    # 实测多 148 行致页脚与云客不一致)。名单取满(>=声明 total)才删,防短页
+    # 误删;只动 wechat(WA 群另一来源);GroupMember 按 room 共享不动。
+    pruned = 0
+    if day_key is None and group_recs and declared and len(group_recs) >= declared:
+        import sqlalchemy as sa
+
+        from app.db.base import async_session_maker
+        from app.db.models import ChatGroup
+
+        keep = {(r["owner_account_id"], r["room_id"]) for r in group_recs}
+        async with async_session_maker() as session:
+            local = (await session.execute(
+                sa.select(ChatGroup.owner_account_id, ChatGroup.room_id)
+                .where(ChatGroup.channel == "wechat")
+            )).all()
+            stale = [(o, r) for (o, r) in local if (o, r) not in keep]
+            for owner, room in stale:
+                # 逐行删(差集常态 0~几行;不用 tuple IN——asyncmy 对其参数
+                # 形态挑剔,实测 TypeError)
+                await session.execute(
+                    sa.delete(ChatGroup).where(
+                        ChatGroup.channel == "wechat",
+                        ChatGroup.owner_account_id == owner,
+                        ChatGroup.room_id == room,
+                    )
+                )
+            pruned = len(stale)
+            await session.commit()
+
+    logger.info(
+        f"DONE: chatroom-stats day={day or '全窗'} groups={len(group_recs)} "
+        f"stats_rows={len(stats_recs)} pruned={pruned}"
+    )
+    return len(group_recs), len(stats_recs)
+
+
 # ---------------------------------------------------------------------------
 # 员工朋友圈 Moments (browser fetch, per employee)
 # ---------------------------------------------------------------------------
@@ -1962,7 +2276,7 @@ async def scrape_voice_clips(cookie_str: str, max_employees: int = 200, page_siz
 # ---------------------------------------------------------------------------
 
 
-async def scrape_wa_messages(cookie_str: str, max_conversations: int = 100, full_history: bool = False):
+async def scrape_wa_messages(cookie_str: str, max_conversations: int = 100, full_history: bool = False, active_window_hours: int | None = None):
     """Scrape WhatsApp chat records via browser fetch POST
     /qqweb/WhatsAppUser/chatRecords (JSON body {uid, friendUid, start, end}).
 
@@ -1977,7 +2291,14 @@ async def scrape_wa_messages(cookie_str: str, max_conversations: int = 100, full
     from app.scraper.whatsapp import _is_wa_divider, _normalize_whatsapp_message
     from app.storage.repos import upsert_messages
 
-    conversations = await _discover_conversations("whatsapp", "wa_voice_call")
+    conversations = await _discover_conversations(
+        "whatsapp", "wa_voice_call",
+        active_since_ms=(
+            int((__import__("time").time() - active_window_hours * 3600) * 1000)
+            if active_window_hours else None
+        ),
+        exclude_scanned_empty=not full_history,
+    )
     watermarks = await _conversation_watermarks("whatsapp")
     cust_activity = await _customer_activity("whatsapp")
 
@@ -2023,7 +2344,14 @@ async def scrape_wa_messages(cookie_str: str, max_conversations: int = 100, full
                     msgs = data.get("messages") or []
                     for row in msgs:
                         if isinstance(row, dict) and not _is_wa_divider(row):
-                            records.append(_normalize_whatsapp_message(row))
+                            rec = _normalize_whatsapp_message(row)
+                            # 增量模式过滤边界旧消息:云客 start 参数是 inclusive
+                            # (返回 ts>=start 含边界),不过滤则每对话白拉数条已
+                            # 入库旧消息(2026-09-10 实测一夜 fetched 53,682 仅
+                            # 321 条真新,99% 白写)。
+                            if watermark and (rec.get("timestamp") or 0) <= watermark:
+                                continue
+                            records.append(rec)
                     if not data.get("hasLast"):
                         break
                     # 增量触底停:翻到已同步区
@@ -2054,6 +2382,8 @@ async def scrape_wa_messages(cookie_str: str, max_conversations: int = 100, full
                 continue
 
             total_fetched += len(records)
+            if not records:
+                await _mark_scan_empty("whatsapp_conv_empty", f"{uid}:{friend_uid}")
             if records:
                 # upsert_messages 收整列表(逐条版 _upsert_all 会把 dict 迭代成
                 # key 字符串 → TypeError, 2026-08-19 WA 阶段首条即崩的根因)
@@ -2100,7 +2430,7 @@ def _normalize_wa_group_message(record: dict) -> dict:
     return rec
 
 
-async def scrape_wa_group_messages(cookie_str: str, max_groups: int = 500, full_history: bool = False):
+async def scrape_wa_group_messages(cookie_str: str, max_groups: int = 500, full_history: bool = False, active_window_hours: int | None = None):
     """WA 群消息:浏览器 fetch chatRecords,friendUid 直接传 @g.us 群 id
     (真机确认 2026-08-20,与微信群的 msg/chats+roomId 同套路)。
 
@@ -2114,11 +2444,16 @@ async def scrape_wa_group_messages(cookie_str: str, max_groups: int = 500, full_
     from app.storage.repos import upsert_messages
     from sqlalchemy import text as sa_text
 
+    active_since_ms = (
+        int((__import__("time").time() - active_window_hours * 3600) * 1000)
+        if active_window_hours else None
+    )
     async with async_engine.connect() as conn:
         result = await conn.execute(sa_text(
             "SELECT owner_account_id, room_id FROM chat_group "
             "WHERE channel='whatsapp' AND owner_account_id IS NOT NULL "
-        ))
+            "AND (:t IS NULL OR last_chat_time IS NULL OR last_chat_time >= :t)"
+        ), {"t": active_since_ms})
         groups = [(row[0], row[1]) for row in result.fetchall()]
 
     room_wms = await _room_watermarks()
@@ -2162,7 +2497,11 @@ async def scrape_wa_group_messages(cookie_str: str, max_groups: int = 500, full_
                             for row in rows:
                                 if not isinstance(row, dict) or _is_wa_divider(row):
                                     continue
-                                records.append(_normalize_wa_group_message(row))
+                                rec = _normalize_wa_group_message(row)
+                                # 增量模式过滤边界旧消息(同 1:1,2026-09-10)
+                                if watermark and (rec.get("timestamp") or 0) <= watermark:
+                                    continue
+                                records.append(rec)
 
                     except Exception as e:
                         logger.warning(f"  [{i+1}] {str(owner_id)[:18]}:{str(room_id)[:18]} failed: {e}")
@@ -2277,6 +2616,7 @@ async def main():
             "wa-accounts",   # WA员工账号 (waBusiness/userlist interception)
             "wa-friends",    # WA客户 (waBusiness/friendlist interception)
             "wa-groups",     # WA群 (browser fetch businessFriendList type=1)
+            "chatroom-stats", # 微信群统计 (getChatroomList 带窗,云客同款)
             "voice-calls",   # 语音通话记录 (voice-call-list + wavoicecalllist)
             "voice-clips",   # 长语音 (browser fetch call/list per employee)
             "wa-messages",   # WA消息 (browser fetch chatRecords per conversation)
@@ -2291,6 +2631,9 @@ async def main():
     parser.add_argument("--max-pages", type=int, default=200, help="列表翻页上限 (accounts/wa-accounts/wa-friends/voice-calls/moments)")
     parser.add_argument("--batch-size", type=int, default=50, help="媒体下载批次大小 (media)")
     parser.add_argument("--full-history", action="store_true", help="消息类实体强制全量翻历史(默认增量水位)")
+    parser.add_argument("--active-window-hours", type=int, default=None,
+                        help="只扫近 N 小时活跃的对话(4h 增量模式传 24;未扫过的对话不受限;默认不过滤=全量发现)")
+    parser.add_argument("--day", type=str, default=None, help="chatroom-stats:单日窗 YYYY-MM-DD(落按天进出表);缺省=全窗档案基线")
     args = parser.parse_args()
 
     cookie = _load_cookie()
@@ -2313,9 +2656,9 @@ async def _dispatch_entity(args, cookie: str) -> None:
     elif args.entity == "groups":
         await scrape_groups(cookie, args.max_employees)
     elif args.entity == "messages":
-        await scrape_messages(cookie, args.max_conversations, args.full_history)
+        await scrape_messages(cookie, args.max_conversations, args.full_history, args.active_window_hours)
     elif args.entity == "group-messages":
-        await scrape_group_messages(cookie, args.max_conversations, args.full_history)
+        await scrape_group_messages(cookie, args.max_conversations, args.full_history, args.active_window_hours)
     elif args.entity == "accounts":
         await scrape_accounts(cookie, args.max_pages)
     elif args.entity == "wa-accounts":
@@ -2324,14 +2667,16 @@ async def _dispatch_entity(args, cookie: str) -> None:
         await scrape_wa_friends(cookie, args.max_pages)
     elif args.entity == "wa-groups":
         await scrape_wa_groups(cookie, args.max_pages)
+    elif args.entity == "chatroom-stats":
+        await scrape_chatroom_stats(cookie, args.day)
     elif args.entity == "voice-calls":
         await scrape_voice_calls(cookie, args.max_pages)
     elif args.entity == "voice-clips":
         await scrape_voice_clips(cookie, args.max_employees)
     elif args.entity == "wa-messages":
-        await scrape_wa_messages(cookie, args.max_conversations, args.full_history)
+        await scrape_wa_messages(cookie, args.max_conversations, args.full_history, args.active_window_hours)
     elif args.entity == "wa-group-messages":
-        await scrape_wa_group_messages(cookie, args.max_conversations, args.full_history)
+        await scrape_wa_group_messages(cookie, args.max_conversations, args.full_history, args.active_window_hours)
     elif args.entity == "moments":
         await scrape_moments(cookie, args.max_pages)
     elif args.entity == "media":

yunke-server/tests/conftest.py

@@ -112,3 +112,22 @@ async def make_client() -> AsyncIterator[
             await client.aclose()
             await engine.dispose()
         app.dependency_overrides.clear()
+
+
+@pytest.fixture
+async def make_session() -> AsyncIterator[AsyncSession]:
+    """独立内存 SQLite AsyncSession(不挂 API 依赖)——存储层/管理域测试用。
+
+    与 make_client 共用 StaticPool 单连接模式;每个测试独享全新 schema。
+    """
+    engine = create_async_engine(
+        "sqlite+aiosqlite:///:memory:",
+        poolclass=StaticPool,
+        connect_args={"check_same_thread": False},
+    )
+    async with engine.begin() as conn:
+        await conn.run_sync(Base.metadata.create_all)
+    SessionLocal = async_sessionmaker(engine, expire_on_commit=False)
+    async with SessionLocal() as s:
+        yield s
+    await engine.dispose()

yunke-server/tests/test_api_customers.py

@@ -148,3 +148,113 @@ async def test_q_escapes_like_wildcards(make_client):
     # 只命中字面含 "100%" 的行;不因 % 通配漏扩到 "1001"
     assert body["total"] == 1
     assert [it["friend_id"] for it in body["items"]] == ["wx_pct"]
+
+
+# ---------------------------------------------------------------------------
+# owner 维度读 customer_account_link(共享好友,2026-09-08)
+# ---------------------------------------------------------------------------
+
+async def _seed_links(session):
+    from app.db.models import CustomerAccountLink as L
+
+    # 档案路径的旧行:共享好友 f_shared 档案 last-wins 挂在 wx_b 名下
+    session.add_all([
+        L(channel="wechat", owner_account_id="wx_a", friend_id="f_shared",
+          friend_remark="A的备注", friend_nickname="共享客户", last_chat_time=2000,
+          send_num=3, receive_num=1, from_type=1),
+        L(channel="wechat", owner_account_id="wx_b", friend_id="f_shared",
+          friend_remark="B的备注", friend_nickname="共享客户", last_chat_time=1000),
+        L(channel="wechat", owner_account_id="wx_a", friend_id="f_only_a",
+          friend_nickname="A独有", last_chat_time=3000),
+    ])
+    await session.commit()
+
+
+async def test_owner_filter_reads_links(make_client):
+    """owner 过滤走 link:共享好友在两个员工名下各出现,备注各是各的。"""
+    client = await make_client(_seed_links)
+    r_a = await client.get("/api/customers", params={
+        "channel": "wechat", "owner_account_id": "wx_a"})
+    assert r_a.status_code == 200
+    body_a = r_a.json()
+    assert body_a["total"] == 2
+    by_id = {it["friend_id"]: it for it in body_a["items"]}
+    # 排序:last_chat_time desc
+    assert [it["friend_id"] for it in body_a["items"]] == ["f_only_a", "f_shared"]
+    assert by_id["f_shared"]["friend_remark"] == "A的备注"
+    assert by_id["f_shared"]["send_num"] == 3
+    assert by_id["f_shared"]["from_type"] == 1
+
+    r_b = await client.get("/api/customers", params={
+        "channel": "wechat", "owner_account_id": "wx_b"})
+    body_b = r_b.json()
+    assert body_b["total"] == 1
+    assert body_b["items"][0]["friend_remark"] == "B的备注"
+
+
+async def test_owner_filter_q_and_friend_id_on_links(make_client):
+    """link 路径的 q 四列搜索 + friend_id 精确查找(聊天窗名字解析用)。"""
+    client = await make_client(_seed_links)
+    r = await client.get("/api/customers", params={
+        "channel": "wechat", "owner_account_id": "wx_a", "q": "A的备注"})
+    assert r.status_code == 200
+    body = r.json()
+    assert [it["friend_id"] for it in body["items"]] == ["f_shared"]
+
+    r2 = await client.get("/api/customers", params={
+        "channel": "wechat", "owner_account_id": "wx_a", "friend_id": "f_shared"})
+    body2 = r2.json()
+    assert body2["total"] == 1
+    assert body2["items"][0]["friend_nickname"] == "共享客户"
+
+
+async def test_owner_filter_with_dept_falls_back_to_archive(make_client):
+    """owner+department 组合回退档案路径(旧行为;link 不解析部门)。"""
+    from app.db.models import Customer as C, Staff as S
+
+    async def seed(session):
+        await _seed_links(session)
+        session.add(S(user_id="u1", name="员工", dept_id="d1"))
+        session.add(C(channel="wechat", owner_account_id="wx_a",
+                      friend_id="f_archived", user_id="u1"))
+        await session.commit()
+
+    client = await make_client(seed)
+    r = await client.get("/api/customers", params={
+        "channel": "wechat", "owner_account_id": "wx_a", "department_id": "d1"})
+    assert r.status_code == 200
+    body = r.json()
+    # 档案路径:只命中 user_id 属于 d1 的档案行(link 行不带 user_id)
+    assert [it["friend_id"] for it in body["items"]] == ["f_archived"]
+
+
+async def test_owner_link_path_carries_archive_raw_json(make_client):
+    """link 路径按 friend_id 带出档案 raw_json(2026-09-09 WA 列表修复)。
+
+    WA 客户列表大量列只存在于 raw_json(userName/salePhone/createTime 等),
+    link 快照没存——不带 raw_json 时整表列空白。
+    """
+    from app.db.models import Customer as C, CustomerAccountLink as L
+
+    async def seed(session):
+        session.add_all([
+            # 档案行挂在别的员工名下(共享),raw_json 里带员工侧 camelCase 字段
+            C(channel="whatsapp", friend_id="f1@s.whatsapp.net",
+              owner_account_id="wx_other", friend_nickname="Nick",
+              raw_json={"userName": "员工WA名", "salePhone": "13800000000",
+                        "uid": "15600000000@s.whatsapp.net", "createTime": 1700000000000}),
+            L(channel="whatsapp", owner_account_id="wa_me",
+              friend_id="f1@s.whatsapp.net", friend_nickname="Nick", last_chat_time=100),
+        ])
+        await session.commit()
+
+    client = await make_client(seed)
+    r = await client.get("/api/customers", params={
+        "channel": "whatsapp", "owner_account_id": "wa_me"})
+    assert r.status_code == 200
+    body = r.json()
+    assert body["total"] == 1
+    it = body["items"][0]
+    assert it["friend_nickname"] == "Nick"          # link 快照
+    assert it["raw_json"]["userName"] == "员工WA名"  # 档案 raw_json 带出
+    assert it["raw_json"]["salePhone"] == "13800000000"

yunke-server/tests/test_api_export.py

@@ -1,16 +1,19 @@
-"""Tests for GET /api/export/chat-html — 导出 1:1/群聊天为自包含 HTML。
+"""Tests for GET /api/export/chat-html(+zip) — 导出 1:1/群聊天为自包含 HTML。
 
 对齐云客微信客户/群列表「导出HTML聊天记录」：按 (channel, owner, talker_id|room_id)
 拉消息（可选 start/end 时间范围），渲染为左右气泡 HTML 作为 attachment 返回下载。
+zip 版:员工客户页勾选多个客户批量「导出聊天记录」(2026-09-08)。
 """
 
 from __future__ import annotations
 
 import functools
+import io
+import zipfile
 from sqlalchemy.ext.asyncio import AsyncSession
 
-from app.api.routers.export import EXPORT_MAX_ROWS
+from app.api.routers.export import EXPORT_MAX_ROWS, ZIP_MAX_CONVS
-from app.db.models import Message
+from app.db.models import Customer, Message
 
 
 async def _seed(session: AsyncSession) -> None:
@@ -160,3 +163,91 @@ async def test_export_group_ignores_owner_mismatch(make_client):
     assert r.status_code == 200
     assert "群消息1" in r.text
     assert "群消息2" in r.text
+
+
+# ---------------------------------------------------------------------------
+# GET /api/export/chat-html-zip — 批量导出(2026-09-08 员工客户页)
+# ---------------------------------------------------------------------------
+
+async def _seed_zip(session: AsyncSession) -> None:
+    """两个客户各几条 DM + 一条同 talker 的群消息(不应混入 DM zip)。"""
+    session.add_all([
+        Customer(channel="wechat", owner_account_id="wx_owner", friend_id="f1",
+                 friend_nickname="小蜜", friend_remark="蜜姐"),
+        Customer(channel="wechat", owner_account_id="wx_owner", friend_id="f2",
+                 friend_nickname="老王"),
+        Customer(channel="wechat", owner_account_id="wx_owner", friend_id="f3",
+                 friend_nickname='坏/名字<>:"|'),
+        Message(msg_id="z1", channel="wechat", owner_account_id="wx_owner",
+                talker_id="f1", room_id=None, text="f1你好", timestamp=1000,
+                is_send=False, type="text", type_raw=1),
+        Message(msg_id="z2", channel="wechat", owner_account_id="wx_owner",
+                talker_id="f2", room_id=None, text="f2在吗", timestamp=2000,
+                is_send=True, type="text", type_raw=1),
+        Message(msg_id="z3", channel="wechat", owner_account_id="wx_owner",
+                talker_id="f2", room_id=None, text="f2更早", timestamp=500,
+                is_send=True, type="text", type_raw=1),
+        # f1 名下的群消息:room_id 有值,zip 的 DM 查询必须排除
+        Message(msg_id="z4", channel="wechat", owner_account_id="wx_owner",
+                talker_id="f1", room_id="g@chatroom", text="群内消息不进zip",
+                timestamp=3000, is_send=True, type="text", type_raw=1),
+    ])
+    await session.commit()
+
+
+def _zip_entries(r) -> dict[str, str]:
+    assert r.headers["content-type"].startswith("application/zip")
+    with zipfile.ZipFile(io.BytesIO(r.content)) as zf:
+        return {name: zf.read(name).decode("utf-8") for name in zf.namelist()}
+
+
+async def test_zip_two_conversations_with_display_names(make_client):
+    """zip 含两个会话 HTML;文件名取备注>昵称;群消息不混入。"""
+    client = await make_client(_seed_zip)
+    r = await client.get("/api/export/chat-html-zip", params={
+        "channel": "wechat", "owner_account_id": "wx_owner",
+        "talker_ids": "f1,f2"})
+    assert r.status_code == 200
+    assert "attachment" in r.headers["content-disposition"]
+    entries = _zip_entries(r)
+    assert sorted(entries) == ["01_蜜姐.html", "02_老王.html"]
+    assert "f1你好" in entries["01_蜜姐.html"]
+    assert "f2在吗" in entries["02_老王.html"]
+    # DM 查询排除 room 消息
+    assert "群内消息不进zip" not in "".join(entries.values())
+
+
+async def test_zip_time_range_filter(make_client):
+    """start/end 同样作用于 zip 内每个会话。"""
+    client = await make_client(_seed_zip)
+    r = await client.get("/api/export/chat-html-zip", params={
+        "channel": "wechat", "owner_account_id": "wx_owner",
+        "talker_ids": "f2", "start": 1000})
+    assert r.status_code == 200
+    entries = _zip_entries(r)
+    assert "f2在吗" in entries["01_老王.html"]
+    assert "f2更早" not in entries["01_老王.html"]
+
+
+async def test_zip_filename_sanitized_and_fallback(make_client):
+    """非法字符客户名清洗;无 customer 行的 talker 回退 friend_id。"""
+    client = await make_client(_seed_zip)
+    r = await client.get("/api/export/chat-html-zip", params={
+        "channel": "wechat", "owner_account_id": "wx_owner",
+        "talker_ids": "f3,f_unknown"})
+    assert r.status_code == 200
+    names = sorted(_zip_entries(r))
+    assert names[0].startswith("01_") and "/" not in names[0] and "<" not in names[0]
+    assert names[1] == "02_f_unknown.html"
+
+
+async def test_zip_rejects_empty_and_over_limit(make_client):
+    """空列表/超上限 422,防误传。"""
+    client = await make_client(_seed_zip)
+    r_empty = await client.get("/api/export/chat-html-zip", params={
+        "channel": "wechat", "owner_account_id": "wx_owner", "talker_ids": " , "})
+    assert r_empty.status_code == 422
+    many = ",".join(f"t{i}" for i in range(ZIP_MAX_CONVS + 1))
+    r_many = await client.get("/api/export/chat-html-zip", params={
+        "channel": "wechat", "owner_account_id": "wx_owner", "talker_ids": many})
+    assert r_many.status_code == 422

yunke-server/tests/test_api_groups.py

@@ -64,17 +64,19 @@ async def _seed(session: AsyncSession) -> None:
 
 
 async def test_default_list_returns_all_ordered_desc(make_client):
-    """No filters -> 3 groups, ordered by ``last_chat_time desc`` (nulls last)."""
+    """No filters -> 3 groups;微信排序=owner 二进制字符串升序分组+room_id
+    升序(云客群统计同款,2026-09-10 终判:区分大小写,大写排小写前)。
+    owner 序:wa_owner_1 < wx_owner_1 < wx_owner_2 → [wa_room_x, room_a, room_b]。
+    """
     client = await make_client(_seed)
     r = await client.get("/api/groups")
     assert r.status_code == 200
     body = r.json()
     assert body["total"] == 3
-    # 2000, 1000, null -> [room_a, room_b, wa_room_x]
     assert [it["room_id"] for it in body["items"]] == [
+        "wa_room_x@s.whatsapp.net",
         "room_a@chatroom",
         "room_b@chatroom",
-        "wa_room_x@s.whatsapp.net",
     ]
     for key in (
         "room_id",
@@ -344,3 +346,79 @@ async def test_q_room_name_substring_filter(make_client):
     # 空串 -> 不过滤
     r3 = await client.get("/api/groups", params={"q": ""})
     assert r3.json()["total"] == 3
+
+
+# ---------------------------------------------------------------------------
+# 微信群统计扩展(2026-09-09):统计时段窗聚合 + 员工列 + 群备注/最新消息筛选
+# ---------------------------------------------------------------------------
+
+async def _seed_stat(session: AsyncSession) -> None:
+    from app.db.models import ChatGroupMemberStats, MsgDailyStats, Staff, WechatAccount
+
+    session.add_all([
+        WechatAccount(wx_id="wx_owner_1", nick_name="玉", alias="Nancyjade",
+                      user_id="u_wx_1", raw_json={"headImageUrl": "http://a/h.png"}),
+        Staff(user_id="u_wx_1", name="聂玉婷", phone="18500000000"),
+        ChatGroup(room_id="stat_room@chatroom", channel="wechat", room_name="统计群",
+                  owner_account_id="wx_owner_1", owner_user_id="u_wx_1",
+                  member_count=46, group_remark="VIP群", last_chat_time=5000),
+        # 窗内两天日行(0907+0908):沟通 3+4=7 条
+        MsgDailyStats(channel="wechat", owner_account_id="wx_owner_1", peer_kind="room",
+                      peer_id="stat_room@chatroom", day=20260907, send_cnt=1, recv_cnt=2),
+        MsgDailyStats(channel="wechat", owner_account_id="wx_owner_1", peer_kind="room",
+                      peer_id="stat_room@chatroom", day=20260908, send_cnt=2, recv_cnt=2),
+        # 窗外日行(0901)不应计入
+        MsgDailyStats(channel="wechat", owner_account_id="wx_owner_1", peer_kind="room",
+                      peer_id="stat_room@chatroom", day=20260901, send_cnt=99, recv_cnt=99),
+        # 窗内进出:0907 +2/-1
+        ChatGroupMemberStats(channel="wechat", owner_account_id="wx_owner_1",
+                             room_id="stat_room@chatroom", day=20260907, added=2, lost=1),
+    ])
+    await session.commit()
+
+
+async def test_group_window_aggregates_and_staff_columns(make_client):
+    """msg_start/msg_end 窗内三聚合 + 员工微信/员工信息关联列。"""
+    client = await make_client(_seed_stat)
+    # 2026-09-07 ~ 2026-09-09(上海日 20260907..20260909,UTC ms)
+    r = await client.get("/api/groups", params={
+        "channel": "wechat", "room_id": "stat_room@chatroom",
+        "msg_start": 1788758400000, "msg_end": 1789017600000,
+    })
+    assert r.status_code == 200
+    it = r.json()["items"][0]
+    assert it["window_msg_count"] == 7      # 窗内日行求和,0901 排除
+    assert it["window_added"] == 2
+    assert it["window_lost"] == 1
+    assert it["group_remark"] == "VIP群"
+    assert it["staff_nickname"] == "玉"
+    assert it["staff_wx_alias"] == "Nancyjade"
+    assert it["staff_avatar"] == "http://a/h.png"
+    assert it["staff_name"] == "聂玉婷"
+    assert it["staff_phone"] == "18500000000"
+
+    # 无窗请求 → 聚合三列为 None(不误显 0)
+    r2 = await client.get("/api/groups", params={
+        "channel": "wechat", "room_id": "stat_room@chatroom"})
+    it2 = r2.json()["items"][0]
+    assert it2["window_msg_count"] is None
+    assert it2["window_added"] is None
+
+
+async def test_group_remark_and_last_window_filters(make_client):
+    """群备注子串 + 最新消息时间段过滤。"""
+    client = await make_client(_seed_stat)
+    r = await client.get("/api/groups", params={
+        "channel": "wechat", "group_remark": "VIP"})
+    assert [i["room_id"] for i in r.json()["items"]] == ["stat_room@chatroom"]
+    r2 = await client.get("/api/groups", params={
+        "channel": "wechat", "group_remark": "不存在"})
+    assert r2.json()["total"] == 0
+
+    # last_chat_time=5000 → last_start=4000 命中,last_start=6000 排除
+    r3 = await client.get("/api/groups", params={
+        "channel": "wechat", "last_start": 4000, "last_end": 9999})
+    assert "stat_room@chatroom" in [i["room_id"] for i in r3.json()["items"]]
+    r4 = await client.get("/api/groups", params={
+        "channel": "wechat", "last_start": 6000, "last_end": 9999})
+    assert r4.json()["total"] == 0

yunke-server/tests/test_api_sessions.py

@@ -5,7 +5,7 @@ import time
 
 from sqlalchemy.ext.asyncio import AsyncSession
 
-from app.db.models import ChatGroup, Customer, Message
+from app.db.models import ChatGroup, Customer, CustomerAccountLink, Message
 
 OWNER = "wx_owner_s"
 CH = "wechat"
@@ -45,6 +45,40 @@ async def test_sessions_friend_and_group(make_client):
     assert g["name"] == "群一号" and g["today_count"] == 1
 
 
+async def test_sessions_shared_friend_name_from_link(make_client):
+    """共享好友昵称读 link 快照(2026-09-09):档案行挂在别的员工名下时,
+    会话列表此前回退显示 wxid;link 表每账号一行,回填后都有昵称。
+    """
+
+    async def seed(session: AsyncSession) -> None:
+        session.add_all([
+            # OWNER 与共享好友 t_shared 有会话
+            Message(msg_id="sh1", channel=CH, owner_account_id=OWNER, talker_id="t_shared",
+                    room_id=None, is_send=True, timestamp=_NOW, type="text", type_raw=1, text="x"),
+            # 档案行(last-wins)挂在别的员工名下——按 owner 查档案必然查空
+            Customer(friend_id="t_shared", channel=CH,
+                     owner_account_id="wx_other", friend_nickname="A**郑"),
+            # OWNER 名下的 per-owner link 快照
+            CustomerAccountLink(channel=CH, owner_account_id=OWNER, friend_id="t_shared",
+                                friend_nickname="A**郑", friend_remark=None),
+        ])
+        await session.commit()
+
+    client = await make_client(seed)
+    r = await client.get("/api/sessions", params={"owner_account_id": OWNER, "channel": CH})
+    assert r.status_code == 200
+    by = {s.get("talker_id"): s for s in r.json()["sessions"]}
+    assert by["t_shared"]["name"] == "A**郑"
+
+
+async def test_sessions_name_falls_back_to_archive_without_link(make_client):
+    """link 未覆盖的好友回退档案路径(空表过渡安全)。"""
+    client = await make_client(_seed)
+    r = await client.get("/api/sessions", params={"owner_account_id": OWNER, "channel": CH})
+    by = {s.get("talker_id"): s for s in r.json()["sessions"]}
+    assert by["t1"]["name"] == "Alice"  # 档案行在 OWNER 名下
+
+
 async def test_sessions_sorted_by_last_chat_time_desc(make_client):
     client = await make_client(_seed)
     body = (await client.get("/api/sessions", params={"owner_account_id": OWNER})).json()

yunke-server/tests/test_api_staff_stats.py

@@ -5,7 +5,14 @@ import time
 
 from sqlalchemy.ext.asyncio import AsyncSession
 
-from app.db.models import ChatGroup, Customer, Message, PhoneCall, WechatAccount
+from app.db.models import (
+    ChatGroup,
+    Customer,
+    CustomerAccountLink,
+    Message,
+    PhoneCall,
+    WechatAccount,
+)
 
 OWNER = "wxid_o"
 UID = "U32HEX"  # 员工 userId(32位HEX)——phone_call.user_id 存的是它,不是 wxId!
@@ -39,6 +46,11 @@ async def _seed_counts(s: AsyncSession) -> None:
     # 删除/拉黑(现存量口径,忽略窗口)
     s.add(Customer(friend_id="c9", channel="wechat", owner_account_id=OWNER, delete_flag=1))
     s.add(Customer(friend_id="c8", channel="wechat", owner_account_id=OWNER, is_block=True))
+    # link 行(生产抓取经 upsert_customer 成对写;新客户/删除统计读 link)
+    s.add(CustomerAccountLink(channel="wechat", owner_account_id=OWNER, friend_id="c1", add_time=IN))
+    s.add(CustomerAccountLink(channel="wechat", owner_account_id=OWNER, friend_id="c2"))
+    s.add(CustomerAccountLink(channel="wechat", owner_account_id=OWNER, friend_id="c3", add_time=1_000))
+    s.add(CustomerAccountLink(channel="wechat", owner_account_id=OWNER, friend_id="c9", delete_flag=1))
     # 语音通话: user_id 是 32HEX 非 wxId!另 seed 一条直存 wxId 的(不计,锁死 join 口径)
     s.add(PhoneCall(call_id="pc1", channel="voice_call", user_id=UID,
                     start_call_time=IN + 4, call_number="c1"))
@@ -78,6 +90,9 @@ async def test_counts_default_window_last_7_days(make_client):
         s.add(Customer(friend_id="c_now", channel="wechat", owner_account_id=OWNER, add_time=now))
         s.add(Customer(friend_id="c_old", channel="wechat", owner_account_id=OWNER,
                        add_time=now - 8 * DAY))
+        s.add(CustomerAccountLink(channel="wechat", owner_account_id=OWNER, friend_id="c_now", add_time=now))
+        s.add(CustomerAccountLink(channel="wechat", owner_account_id=OWNER, friend_id="c_old",
+                                  add_time=now - 8 * DAY))
         s.add(PhoneCall(call_id="pc_now", channel="voice_call", user_id=UID,
                         start_call_time=now, call_number="c_now"))
         s.add(PhoneCall(call_id="pc_old", channel="voice_call", user_id=UID,
@@ -127,6 +142,12 @@ async def test_detail_new_customers_fields(make_client):
         s.add(Customer(friend_id="c2", channel="wechat", owner_account_id=OWNER, add_time=None,
                        friend_nickname="兜底客"))
         s.add(Customer(friend_id="c3", channel="wechat", owner_account_id=OWNER, add_time=1_000))
+        s.add(CustomerAccountLink(channel="wechat", owner_account_id=OWNER, friend_id="c1", add_time=IN,
+                                  friend_nickname="牛牛", friend_remark="大客户",
+                                  head_image_url="http://a/1.png"))
+        s.add(CustomerAccountLink(channel="wechat", owner_account_id=OWNER, friend_id="c2",
+                                  friend_nickname="兜底客"))
+        s.add(CustomerAccountLink(channel="wechat", owner_account_id=OWNER, friend_id="c3", add_time=1_000))
         s.add(Message(msg_id="m1", channel="wechat", owner_account_id=OWNER, talker_id="c2",
                       timestamp=IN - 5))
         await s.commit()
@@ -238,6 +259,9 @@ async def test_detail_del_and_blocked_fields(make_client):
         s.add(Customer(friend_id="c_ok", channel="wechat", owner_account_id=OWNER))
         s.add(Customer(friend_id="c_other", channel="wechat", owner_account_id="wxid_other",
                        delete_flag=1))
+        # 删除读 link:c_del 补 link 行;is_block 保持档案(c_blk 不补)
+        s.add(CustomerAccountLink(channel="wechat", owner_account_id=OWNER, friend_id="c_del",
+                                  delete_flag=1, friend_nickname="已删客"))
         s.add(Customer(friend_id="c_fine", channel="wechat", owner_account_id=OWNER,
                        delete_flag=0, is_block=False))
         await s.commit()
@@ -394,3 +418,32 @@ async def test_new_customers_fallback_first_msg_before_window(make_client):
     assert r_count.status_code == r_detail.status_code == 200
     assert r_count.json()["new_customers"] == 0
     assert r_detail.json()["rows"] == []
+
+
+async def test_new_customers_counts_shared_friend_via_link(make_client):
+    """共享好友(档案挂别的员工名下)凭 link 行计入新客户(2026-09-09 口径修复)。
+
+    旧档案口径下 c_shared 对 OWNER 不可见(add_time 在窗内也不计);切 link
+    后按 per-owner 关系计数,与云客按员工统计一致。
+    """
+
+    async def seed(s: AsyncSession) -> None:
+        s.add(WechatAccount(wx_id=OWNER, user_id=UID))
+        # 档案行(last-wins)挂在别的员工名下
+        s.add(Customer(friend_id="c_shared", channel="wechat",
+                       owner_account_id="wxid_other", add_time=IN))
+        # OWNER 名下的 link 关系
+        s.add(CustomerAccountLink(channel="wechat", owner_account_id=OWNER,
+                                  friend_id="c_shared", add_time=IN))
+        await s.commit()
+
+    client = await make_client(seed)
+    r = await client.get(
+        "/api/staff-stats",
+        params={"wechat_id": OWNER, "kind": "new_customers",
+                "start": WIN_START, "end": WIN_END},
+    )
+    assert r.status_code == 200
+    body = r.json()
+    assert [row["talker_id"] for row in body["rows"]] == ["c_shared"]
+    assert len(body["rows"]) == 1

yunke-server/tests/test_employee_metrics.py

@@ -0,0 +1,269 @@
+"""employee_call_daily / employee_metric_daily 生成判别测试(批次A Task5/6)。
+
+判据(v2 §1.1 #2/#5、§1.2 #9、§1.3 #11):
+- 通话无渠道维,独立小表;接通=duration>0;followup=24h 内任一账号有消息;
+- 幽灵员工(owner 映射不上/不在 staff)过滤;
+- 宽表消息计数 friend-only;串类与 fact 同源。
+"""
+import datetime as dt
+from zoneinfo import ZoneInfo
+
+import sqlalchemy as sa
+
+from app.db.models import (
+    Customer,
+    EmployeeCallDaily,
+    EmployeeMetricDaily,
+    FirstReplyFact,
+    Message,
+    MsgDailyStats,
+    PhoneCall,
+    Staff,
+    WechatAccount,
+    WhatsappAccount,
+)
+from app.storage.employee_metrics import recompute_call_days, recompute_metric_days
+
+_SH = ZoneInfo("Asia/Shanghai")
+
+
+def _ts(*args) -> int:
+    return int(dt.datetime(*args, tzinfo=_SH).timestamp() * 1000)
+
+
+async def _seed_org(session):
+    session.add(Staff(user_id="u1", name="张三", is_on_job=True))
+    session.add(WechatAccount(wx_id="wx1", user_id="u1"))
+    # 第二个微信号:验证 followup「任一账号」语义(owner-IN 而非单账号)
+    session.add(WechatAccount(wx_id="wx2", user_id="u1"))
+    # WA 账号:验证 wa_voice_call 渠道收窄正例
+    session.add(WhatsappAccount(uid="wa1", user_id="u1"))
+    await session.commit()
+
+
+async def test_call_daily_aggregates(make_session):
+    s = make_session
+    await _seed_org(s)
+    s.add(PhoneCall(call_id="c1", channel="voice_call", user_id="u1",
+                    call_number="p1", start_call_time=_ts(2026, 9, 1, 10, 0),
+                    call_duration=120))
+    s.add(PhoneCall(call_id="c2", channel="voice_call", user_id="u1",
+                    call_number="p2", start_call_time=_ts(2026, 9, 1, 15, 0),
+                    call_duration=0))  # 未接通
+    # c3:WA 语音,接通,窗口内有 WA 消息 → followup 正例(渠道收窄匹配)
+    s.add(PhoneCall(call_id="c3", channel="wa_voice_call", user_id="u1",
+                    call_number="p3", start_call_time=_ts(2026, 9, 1, 10, 0),
+                    call_duration=60))
+    # c4:微信语音,接通,但窗口内只有 WA 消息 → followup 反例(渠道收窄)
+    s.add(PhoneCall(call_id="c4", channel="voice_call", user_id="u1",
+                    call_number="p4", start_call_time=_ts(2026, 9, 1, 10, 0),
+                    call_duration=90))
+    # c1 后 2h 员工**另一微信号 wx2** 有跟进消息(任一账号语义:owner-IN)
+    s.add(Message(msg_id="f1", channel="wechat", owner_account_id="wx2",
+                  talker_id="p1", timestamp=_ts(2026, 9, 1, 12, 0),
+                  is_send=True, type="text", text="跟进"))
+    # c2(未接通)后 1h 有消息:即使任一方向也不算 followup(仅已接通判定)
+    s.add(Message(msg_id="f2", channel="wechat", owner_account_id="wx1",
+                  talker_id="p2", timestamp=_ts(2026, 9, 1, 16, 0),
+                  is_send=False, type="text", text="客户回拨?"))
+    # c3 后 2h WA 账号有消息 → 正例
+    s.add(Message(msg_id="f3", channel="whatsapp", owner_account_id="wa1",
+                  talker_id="p3", timestamp=_ts(2026, 9, 1, 12, 0),
+                  is_send=True, type="text", text="wa 跟进"))
+    # c4(voice_call→wechat)窗口内只有 WA 消息 → 不匹配渠道,反例
+    s.add(Message(msg_id="f4", channel="whatsapp", owner_account_id="wa1",
+                  talker_id="p4", timestamp=_ts(2026, 9, 1, 12, 0),
+                  is_send=True, type="text", text="错渠道"))
+    await s.commit()
+    n = await recompute_call_days(s, [20260901])
+    await s.commit()
+    assert n == 1
+    row = (await s.execute(sa.select(EmployeeCallDaily))).scalar_one()
+    assert row.call_count == 4
+    assert row.call_seconds == 270  # 120+0+60+90;duration 单位=秒(Task0 已核实)
+    assert row.answered_call_count == 3  # c1/c3/c4
+    # c1(wx2 任一账号)+ c3(wa 渠道正例);c2 未接通守卫、c4 渠道收窄反例
+    assert row.call_followup_count == 2
+
+
+async def test_call_daily_ignores_unknown_staff(make_session):
+    s = make_session
+    await _seed_org(s)
+    s.add(PhoneCall(call_id="c9", channel="phone_call", user_id="ghost",
+                    call_number="p9", start_call_time=_ts(2026, 9, 1, 10, 0),
+                    call_duration=60))
+    await s.commit()
+    await recompute_call_days(s, [20260901])
+    await s.commit()
+    assert (await s.execute(
+        sa.select(sa.func.count()).select_from(EmployeeCallDaily))).scalar_one() == 0
+
+
+async def _seed_msg_rows(s, *, day=20260901, channel="wechat", owner="wx1",
+                         kind="friend", peer="p1", send=3, recv=2):
+    s.add(MsgDailyStats(channel=channel, owner_account_id=owner, peer_kind=kind,
+                        peer_id=peer, day=day, send_cnt=send, recv_cnt=recv))
+    await s.commit()
+
+
+async def test_metric_daily_friend_only_caliber(make_session):
+    """口径判别(v2 §1.1 #2 防线):room 行不进消息计数/串列,只进 active_rooms。"""
+    s = make_session
+    await _seed_org(s)
+    await _seed_msg_rows(s, send=3, recv=2, kind="friend", peer="p1")
+    await _seed_msg_rows(s, send=10, recv=0, kind="room", peer="r1")
+    # friend 会话给一条消息供串扫描(无消息则无串)
+    s.add(Message(msg_id="p1-0", channel="wechat", owner_account_id="wx1",
+                  talker_id="p1", timestamp=_ts(2026, 9, 1, 10, 0),
+                  is_send=False, type="text", text="q"))
+    await s.commit()
+    await recompute_metric_days(s, [20260901])
+    await s.commit()
+    row = (await s.execute(sa.select(EmployeeMetricDaily))).scalar_one()
+    assert row.msg_sent == 3 and row.msg_recv == 2      # room 的 10 不进
+    assert row.active_rooms == 1
+    assert row.cust_threads == 1 and row.threads_answered == 0  # 未回复串
+    assert row.first_reply_p50_ms is None and row.first_reply_p90_ms is None  # 空样本→None(≠0)
+
+
+async def test_metric_daily_ghost_filtered(make_session):
+    s = make_session
+    await _seed_org(s)
+    await _seed_msg_rows(s, owner="wx-ghost", peer="pg")
+    await recompute_metric_days(s, [20260901])
+    await s.commit()
+    assert (await s.execute(
+        sa.select(sa.func.count()).select_from(EmployeeMetricDaily))).scalar_one() == 0
+
+
+async def test_metric_daily_same_source_as_fact(make_session):
+    """同源判别(v2 §1.1 #5 防线):
+    1) threads_answered ≡ fact 行数(同归属日);
+    2) 多日未回串宽表 threads < 日切 cust_threads 之和(分母不再膨胀);
+    3) 幂等。"""
+    from app.storage.first_reply_facts import recompute_pairs
+    s = make_session
+    await _seed_org(s)
+    # 客户 D1 10:00、D1 20:00、D2 09:00 三条消息,始终未回 → 1 个跨日串
+    rows = [(_ts(2026, 9, 1, 10, 0), False), (_ts(2026, 9, 1, 20, 0), False),
+            (_ts(2026, 9, 2, 9, 0), False)]
+    for i, (ts, is_send) in enumerate(rows):
+        s.add(Message(msg_id=f"g{i}", channel="wechat", owner_account_id="wx1",
+                      talker_id="pg", timestamp=ts, is_send=is_send,
+                      type="text", text="x"))
+    # 日切口径的 msg_daily_stats:D1、D2 各计一个未回串(供对照)
+    await _seed_msg_rows(s, day=20260901, peer="pg", send=0, recv=2)
+    await _seed_msg_rows(s, day=20260902, peer="pg", send=0, recv=1)
+    await s.commit()
+    await recompute_pairs(s, [("wechat", "wx1", "pg")])
+    await s.commit()
+    await recompute_metric_days(s, [20260901, 20260902])
+    await s.commit()
+    got = {r.day: r for r in (
+        await s.execute(sa.select(EmployeeMetricDaily))).scalars().all()}
+    # 1) fact 行数=0(未回),宽表 threads_answered 也=0 且同源
+    assert (await s.execute(
+        sa.select(sa.func.count()).select_from(FirstReplyFact))).scalar_one() == 0
+    # 2) 跨日串只归属 D2;日切 D1+D2=2,宽表合计=1
+    assert got[20260901].cust_threads == 0
+    assert got[20260902].cust_threads == 1
+    # 3) 幂等
+    await recompute_metric_days(s, [20260901, 20260902])
+    await s.commit()
+    assert len((await s.execute(
+        sa.select(EmployeeMetricDaily))).scalars().all()) == 2
+
+
+async def test_metric_daily_same_source_as_fact_answered(make_session):
+    """同源判别正向路径(v2 §1.1 #5):被回串——threads_answered ≡ fact 行数,
+    单样本 p50=p90=fr_ms(锁分位非 None 映射)。"""
+    from app.storage.first_reply_facts import recompute_pairs
+    s = make_session
+    await _seed_org(s)
+    # 客户 10:00 提问,员工 10:25 回复 → fr=25min,串末条归属 09-01
+    fr_ms = 25 * 60 * 1000
+    s.add(Message(msg_id="an0", channel="wechat", owner_account_id="wx1",
+                  talker_id="pa", timestamp=_ts(2026, 9, 1, 10, 0),
+                  is_send=False, type="text", text="q"))
+    s.add(Message(msg_id="an1", channel="wechat", owner_account_id="wx1",
+                  talker_id="pa", timestamp=_ts(2026, 9, 1, 10, 25),
+                  is_send=True, type="text", text="a"))
+    await _seed_msg_rows(s, day=20260901, peer="pa", send=1, recv=1)
+    await s.commit()
+    await recompute_pairs(s, [("wechat", "wx1", "pa")])
+    await s.commit()
+    await recompute_metric_days(s, [20260901])
+    await s.commit()
+    n_facts = (await s.execute(
+        sa.select(sa.func.count()).select_from(FirstReplyFact))).scalar_one()
+    row = (await s.execute(sa.select(EmployeeMetricDaily))).scalar_one()
+    assert row.cust_threads == 1
+    assert row.threads_answered == 1 == n_facts
+    assert row.fr_sum_ms == fr_ms
+    assert row.first_reply_p50_ms == fr_ms == row.first_reply_p90_ms
+
+
+async def test_metric_daily_lifecycle_counts(make_session):
+    """生命周期列:cooling/dormant/reactivated 判定进宽表。"""
+    s = make_session
+    await _seed_org(s)
+    # 客户 pc:D1 有互动后静默(历史≥5 条) → as_of=10-10 为 dormant;
+    # 10-11 回流 → 该日 reactivated
+    s.add(Customer(friend_id="pc", channel="wechat", owner_account_id="wx1",
+                   delete_flag=0))
+    hist = []
+    for h in range(9, 17):  # D1 8 条消息(≥5)
+        hist.append((_ts(2026, 9, 1, h, 0), h % 2 == 0))
+    for i, (ts, is_send) in enumerate(hist):
+        s.add(Message(msg_id=f"lc{i}", channel="wechat", owner_account_id="wx1",
+                      talker_id="pc", timestamp=ts, is_send=is_send,
+                      type="text", text="x"))
+    await _seed_msg_rows(s, day=20260901, peer="pc", send=4, recv=4)
+    await s.commit()
+    # D41(10-11)客户回流一条
+    s.add(Message(msg_id="lc-b", channel="wechat", owner_account_id="wx1",
+                  talker_id="pc", timestamp=_ts(2026, 10, 11, 9, 0),
+                  is_send=False, type="text", text="back"))
+    await _seed_msg_rows(s, day=20261011, peer="pc", send=0, recv=1)
+    await s.commit()
+    from app.storage.first_reply_facts import recompute_pairs
+    await recompute_pairs(s, [("wechat", "wx1", "pc")])
+    await recompute_metric_days(s, [20261010, 20261011])
+    await s.commit()
+    got = {r.day: r for r in (
+        await s.execute(sa.select(EmployeeMetricDaily))).scalars().all()}
+    assert got[20261010].dormant_customer_count == 1   # 39 天静默+历史 8 条
+    assert got[20261011].reactivated_customer_count == 1  # 当日回流且 gap>30
+
+
+async def test_metric_daily_lifecycle_hist_point_in_time(make_session):
+    """hist 时点语义判别:回填历史日 M,沉睡门槛只计 ≤M 的消息。
+
+    客户 pd:X=09-01 共 2 条 + Y=10-02 共 3 条(全历史 5 条):
+    - M=10-01(X+30,<Y):gap≥30 达沉睡判定,但 hist_asof=2 < 5 → None
+      (全历史口径 hist=5 会把 M 误判 dormant——M 之后的消息虚增);
+    - D=11-01(Y+30):hist_asof=5 ≥ 5 → dormant。"""
+    s = make_session
+    await _seed_org(s)
+    s.add(Customer(friend_id="pd", channel="wechat", owner_account_id="wx1",
+                   delete_flag=0))
+    for i, (day, h, is_send) in enumerate([
+        (20260901, 10, False), (20260901, 11, True),            # X 2 条
+        (20261002, 10, False), (20261002, 11, True), (20261002, 12, False),  # Y 3 条
+    ]):
+        s.add(Message(msg_id=f"pd{i}", channel="wechat", owner_account_id="wx1",
+                      talker_id="pd",
+                      timestamp=_ts(day // 10000, day // 100 % 100, day % 100, h, 0),
+                      is_send=is_send, type="text", text="x"))
+    await _seed_msg_rows(s, day=20260901, peer="pd", send=1, recv=1)
+    await _seed_msg_rows(s, day=20261002, peer="pd", send=1, recv=2)
+    # M 是无消息日:state=None 时纯生命周期源不出行,补一条 room 行撑出
+    # 宽表行,让 dormant==0 有断言落点
+    await _seed_msg_rows(s, day=20261001, kind="room", peer="r1", send=1, recv=0)
+    await s.commit()
+    await recompute_metric_days(s, [20261001, 20261101])
+    await s.commit()
+    got = {r.day: r for r in (
+        await s.execute(sa.select(EmployeeMetricDaily))).scalars().all()}
+    assert got[20261001].dormant_customer_count == 0  # hist_asof=2<5 → None
+    assert got[20261101].dormant_customer_count == 1  # hist_asof=5 ≥ 5

yunke-server/tests/test_first_reply_facts.py

@@ -0,0 +1,202 @@
+"""first_reply_fact 跨日精确串算法判别测试(批次A Task3)。
+
+四个核心判据(v2 §1.1 #1/#5、§9):
+1. 跨夜串必须产生样本(日切口径丢失的场景);
+2. 多日未回串只计一次、归属末条日(日切会按天重复计——分母膨胀);
+3. 同源:threads_answered ≡ fact 行数(按归属日);
+4. is_send=None 不参与串判定(与 _thread_stats 一致)。
+
+评审修正补判据:
+5. 同毫秒 F,T,F,T 交换 → reply_msg_id 进 PK 去重,不撞主键(原崩溃回归);
+6. 同毫秒并列按 (ts, msg_id) 定序,结果确定不随 SQL 等键序抖动。
+"""
+import datetime as dt
+from zoneinfo import ZoneInfo
+
+import sqlalchemy as sa
+
+from app.db.models import FirstReplyFact, Message, MsgDailyStats
+from app.storage.first_reply_facts import (
+    all_friend_pairs,
+    compute_conversation,
+    recompute_pairs,
+)
+
+_SH = ZoneInfo("Asia/Shanghai")
+
+
+def _ts(*args) -> int:
+    return int(dt.datetime(*args, tzinfo=_SH).timestamp() * 1000)
+
+
+# ---------------------------- 纯函数 ----------------------------
+
+def test_overnight_thread_recovered():
+    """客户 23:00 发→员工次日 9:00 回:fr_ms≈10h,归属 D1(v2 §1.1 #1)。"""
+    facts, agg = compute_conversation(
+        [(_ts(2026, 9, 1, 23, 0), False, "f1"),
+         (_ts(2026, 9, 2, 9, 0), True, "t1")]
+    )
+    assert len(facts) == 1
+    assert facts[0].fr_ms == 10 * 3600 * 1000
+    assert facts[0].day == 20260901
+    assert agg[20260901].answered == 1
+
+
+def test_multiday_open_thread_counts_once_at_end_day():
+    """客户消息跨 D1/D2 无回复:1 个串归属 D2;日切口径会 D1、D2 各计 1。"""
+    facts, agg = compute_conversation(
+        [(_ts(2026, 9, 1, 10, 0), False, "f1"), (_ts(2026, 9, 1, 20, 0), False, "f2"),
+         (_ts(2026, 9, 2, 9, 0), False, "f3")]
+    )
+    assert facts == []
+    assert 20260901 not in agg
+    assert agg[20260902].threads == 1 and agg[20260902].answered == 0
+
+
+def test_reply_closes_thread_and_opens_new():
+    """员工回复后客户再发=新串;串内多条客户消息取末条为 end。"""
+    facts, agg = compute_conversation(
+        [(_ts(2026, 9, 1, 10, 0), False, "f1"), (_ts(2026, 9, 1, 10, 5), False, "f2"),
+         (_ts(2026, 9, 1, 10, 30), True, "t1"),          # 回复1:fr=30-10:05=25min
+         (_ts(2026, 9, 1, 11, 0), False, "f3"),
+         (_ts(2026, 9, 1, 12, 0), True, "t2")])           # 回复2:fr=12:00-11:00=60min
+    assert len(facts) == 2
+    assert facts[0].fr_ms == 25 * 60 * 1000
+    assert agg[20260901].threads == 2 and agg[20260901].answered == 2
+    assert agg[20260901].fr_sum_ms == 85 * 60 * 1000  # 25min + 60min
+
+
+def test_unknown_direction_ignored():
+    facts, _agg = compute_conversation(
+        [(_ts(2026, 9, 1, 10, 0), False, "f1"), (_ts(2026, 9, 1, 10, 10), None, "u1"),
+         (_ts(2026, 9, 1, 10, 20), True, "t1")]
+    )
+    assert len(facts) == 1  # None 不打断串:仍视为对 10:00 串的回复
+
+
+def test_staff_message_outside_thread_is_noop():
+    facts, agg = compute_conversation(
+        [(_ts(2026, 9, 1, 9, 0), True, "t1"), (_ts(2026, 9, 1, 10, 0), True, "t2")]
+    )
+    assert facts == [] and agg == {}
+
+
+def test_unsorted_rows_raise_or_documented():
+    """调用方契约:rows 须升序。乱序输入行为未定义——文档断言 + 防御排序
+    在 load_conversation 里做(与 summary.py 惯例一致)。"""
+    # 纯函数不做防御(性能);落库路径负责排序。此处仅锁定契约注释。
+    import app.storage.first_reply_facts as m
+    assert "升序" in m.compute_conversation.__doc__
+
+
+def test_tie_break_by_msg_id_deterministic():
+    """同毫秒 [F(m1), T(m2)]:按 (ts, msg_id) 定序 F 在前 → 1 个被回串;
+    同一 multiset 无论入参顺序,排序后结果一致(SQL 等键序未定义,不能
+    随查询抖动)。"""
+    same = _ts(2026, 9, 1, 10, 0)
+    rows = [(same, False, "m1"), (same, True, "m2")]
+    ordered = sorted(rows, key=lambda r: (r[0], r[2]))
+    assert ordered[0][2] == "m1"  # F(m1) 先于 T(m2)
+    facts, agg = compute_conversation(ordered)
+    assert len(facts) == 1 and facts[0].reply_msg_id == "m2"
+    assert agg[20260901].answered == 1
+    shuffled = [rows[1], rows[0]]  # 同一 multiset,入参顺序相反
+    facts2, agg2 = compute_conversation(
+        sorted(shuffled, key=lambda r: (r[0], r[2])))
+    assert facts2 == facts and agg2 == agg
+
+
+# ---------------------------- 落库 ----------------------------
+
+async def _seed_conversation(session, *, channel="wechat", owner="wx1",
+                             peer="p1", rows):
+    for ts, is_send, msg_id in rows:
+        session.add(Message(msg_id=msg_id, channel=channel,
+                            owner_account_id=owner, talker_id=peer,
+                            timestamp=ts, is_send=is_send, type="text",
+                            text="x"))
+    session.add(MsgDailyStats(channel=channel, owner_account_id=owner,
+                              peer_kind="friend", peer_id=peer,
+                              day=20260901, send_cnt=1, recv_cnt=1))
+    await session.commit()
+
+
+async def test_recompute_pairs_persists_and_idempotent(make_session):
+    s = make_session
+    await _seed_conversation(
+        s, rows=[(_ts(2026, 9, 1, 23, 0), False, "p1-f0"),
+                 (_ts(2026, 9, 2, 9, 0), True, "p1-t1")])
+    n = await recompute_pairs(s, [("wechat", "wx1", "p1")])
+    await s.commit()
+    assert n == 1
+    rows = (await s.execute(sa.select(FirstReplyFact))).scalars().all()
+    assert len(rows) == 1 and rows[0].fr_ms == 10 * 3600 * 1000
+    assert rows[0].reply_msg_id == "p1-t1"
+    # 幂等:重跑不重复
+    await recompute_pairs(s, [("wechat", "wx1", "p1")])
+    await s.commit()
+    assert len((await s.execute(sa.select(FirstReplyFact))).scalars().all()) == 1
+
+
+async def test_same_ms_ftft_two_distinct_facts(make_session):
+    """同毫秒 F,T,F,T 交换:两个样本 (thread_end_ts, reply_ts) 完全并列
+    ——reply_msg_id 进 PK 去重后恰好 2 行(评审复现的主键冲突回归)。"""
+    s = make_session
+    same = _ts(2026, 9, 1, 10, 0)
+    await _seed_conversation(s, rows=[
+        (same, False, "m1"), (same, True, "m2"),
+        (same, False, "m3"), (same, True, "m4"),
+    ])
+    n = await recompute_pairs(s, [("wechat", "wx1", "p1")])
+    await s.commit()
+    assert n == 1
+    rows = (await s.execute(sa.select(FirstReplyFact))).scalars().all()
+    assert len(rows) == 2
+    assert {r.reply_msg_id for r in rows} == {"m2", "m4"}
+
+
+async def test_recompute_pairs_replaces_stale(make_session):
+    """会话追加消息后重算,旧样本被替换(delete+insert 语义)。"""
+    s = make_session
+    await _seed_conversation(
+        s, rows=[(_ts(2026, 9, 1, 10, 0), False, "p1-f0"),
+                 (_ts(2026, 9, 1, 11, 0), True, "p1-t1")])
+    await recompute_pairs(s, [("wechat", "wx1", "p1")])
+    await s.commit()
+    s.add(Message(msg_id="p1-new", channel="wechat", owner_account_id="wx1",
+                  talker_id="p1", timestamp=_ts(2026, 9, 1, 12, 0),
+                  is_send=False, type="text", text="y"))
+    await s.commit()
+    await recompute_pairs(s, [("wechat", "wx1", "p1")])
+    await s.commit()
+    rows = (await s.execute(sa.select(FirstReplyFact))).scalars().all()
+    assert len(rows) == 1  # 新串未回,只剩旧样本
+
+
+async def test_recompute_pairs_empty_conversation(make_session):
+    """stats 行在但 message 无合格行(空会话/全被过滤):删旧行不插新——
+    delete+insert 语义对空会话同样成立(幂等清空)。"""
+    s = make_session
+    s.add(MsgDailyStats(channel="wechat", owner_account_id="wx1",
+                        peer_kind="friend", peer_id="p1", day=20260901))
+    # 预置历史残留 fact,重算后应被清掉
+    s.add(FirstReplyFact(channel="wechat", owner_account_id="wx1", peer_id="p1",
+                         thread_end_ts=_ts(2026, 9, 1, 10, 0),
+                         reply_ts=_ts(2026, 9, 1, 11, 0), reply_msg_id="stale",
+                         day=20260901, fr_ms=3600 * 1000))
+    await s.commit()
+    n = await recompute_pairs(s, [("wechat", "wx1", "p1")])
+    await s.commit()
+    assert n == 1
+    assert (await s.execute(sa.select(FirstReplyFact))).scalars().all() == []
+
+
+async def test_all_friend_pairs_only_friend(make_session):
+    s = make_session
+    s.add(MsgDailyStats(channel="wechat", owner_account_id="wx1",
+                        peer_kind="room", peer_id="r1", day=20260901))
+    s.add(MsgDailyStats(channel="wechat", owner_account_id="wx1",
+                        peer_kind="friend", peer_id="p1", day=20260901))
+    await s.commit()
+    assert await all_friend_pairs(s) == [("wechat", "wx1", "p1")]

yunke-server/tests/test_lifecycle.py

@@ -0,0 +1,72 @@
+"""客户生命周期判定纯函数测试(批次A Task4)。
+
+口径(v2 §1.1 #3 + v1 §21 默认,已用户确认):新客 7 天、沉睡 30 天、
+历史≥5 条才算沉睡(对齐 churn real min_msgs=5)。analytics 现有页
+(churn/客户资产)暂不切换(口径差异 v2 §5 标注),不动 636 既有测试。
+"""
+
+from app.analytics.lifecycle import DORMANT_DAYS, MIN_HISTORY_MSGS, NEW_DAYS, classify, day_add
+
+
+def test_constants_locked_to_confirmed_defaults():
+    assert NEW_DAYS == 7 and DORMANT_DAYS == 30 and MIN_HISTORY_MSGS == 5
+
+
+def test_new_customer():
+    # 首次沟通在 7 天窗口内
+    assert (
+        classify(first_day=20260901, last_day=20260903, prev_day=None, as_of=20260905, hist_msgs=2)
+        == "new"
+    )
+    # 窗口边界:as_of-6=20260830 含当天共 7 天 → new;再早一天 → 非 new
+    assert classify(20260830, 20260830, None, 20260905, 100) == "new"
+    assert classify(20260829, 20260829, None, 20260905, 100) == "cooling"
+
+
+def test_reactivated_requires_gap_over_30d():
+    # 当日回流且前次间隔>30 天
+    assert (
+        classify(
+            first_day=20260101, last_day=20260905, prev_day=20260801, as_of=20260905, hist_msgs=50
+        )
+        == "reactivated"
+    )
+    # 间隔仅 9 天 → 只是 active
+    assert (
+        classify(
+            first_day=20260101, last_day=20260905, prev_day=20260827, as_of=20260905, hist_msgs=50
+        )
+        == "active"
+    )
+    # 间隔恰好 30 天 → 严格 >30 不算回流,落回 active
+    assert (
+        classify(
+            first_day=20260101, last_day=20260905, prev_day=20260806, as_of=20260905, hist_msgs=50
+        )
+        == "active"
+    )
+    # 回流必须当日互动:前次间隔 31 天(>30)但 last_day=as_of-1 → 不算回流,按 gap=1 落 active
+    assert classify(20260101, 20260904, 20260804, 20260905, 50) == "active"
+
+
+def test_active_cooling_dormant_boundaries():
+    f, m = 20260101, 100
+    assert classify(f, 20260830, None, 20260905, m) == "active"  # 6 天
+    assert classify(f, 20260829, None, 20260905, m) == "cooling"  # 7 天
+    assert classify(f, 20260807, None, 20260905, m) == "cooling"  # 29 天
+    assert classify(f, 20260806, None, 20260905, m) == "dormant"  # 30 天
+
+
+def test_dormant_requires_history():
+    # ≥30 天无互动但历史<5 条:不计入任何状态(None)
+    assert classify(20260101, 20260806, None, 20260905, 4) is None
+    assert classify(20260101, 20260806, None, 20260905, 5) == "dormant"
+
+
+def test_no_interaction_returns_none():
+    assert classify(None, None, None, 20260905, 0) is None
+
+
+def test_day_add():
+    assert day_add(20260831, 1) == 20260901
+    assert day_add(20260901, -7) == 20260825

yunke-server/tests/test_management_anomalies.py

@@ -0,0 +1,229 @@
+"""管理域确定性异常规则判别测试(批次B Task B3,v1 §5.4 异常卡片)。"""
+import json
+
+import pytest
+
+from app.management.anomalies import detect_anomalies
+from app.management.employee_metrics import PeriodMetrics
+from app.management.metric_definitions import DEFAULT_SCORE_CONFIG
+
+
+def _pm(**overrides):
+    """全零/None 默认的 PeriodMetrics 构造器(22 字段,覆盖式改)。
+
+    与 test_management_scoring._pm 同式(测试间不共享 helper,复制保持独立)。
+    """
+    base = {
+        "user_id": "u1", "days_with_data": 0, "msg_sent": 0, "msg_recv": 0,
+        "cust_threads": 0, "threads_answered": 0, "fr_sum_ms": 0,
+        "fr_p50_ms": None, "fr_p90_ms": None,
+        "reply_2h_count": 0, "reply_24h_count": 0,
+        "active_friends": 0, "active_rooms_avg": 0.0,
+        "new_customer": 0, "cooling_customer": 0, "dormant_customer": 0,
+        "end_active_friends": 0, "reactivated_customer": 0,
+        "call_count": 0, "call_seconds": 0, "answered_call": 0,
+        "call_followup": 0,
+    }
+    base.update(overrides)
+    return PeriodMetrics(**base)
+
+
+def _detect(cur, base, *, n_days=7, user_id="u1", config=None):
+    return detect_anomalies(
+        user_id, cur, base, n_days=n_days,
+        config=config if config is not None else DEFAULT_SCORE_CONFIG)
+
+
+# ---- 1. reply_p90_worsened ----
+
+def test_p90_worsened_warning_with_pct():
+    """×1.6 → warning;标题百分比=(160-100)/100=60%;affected=未回串数。"""
+    cur = _pm(cust_threads=20, threads_answered=12, fr_p90_ms=9_600_000)   # 160min
+    base = _pm(cust_threads=40, threads_answered=40, fr_p90_ms=6_000_000)  # 100min
+    cards = _detect(cur, base)
+    assert [c["rule_code"] for c in cards] == ["reply_p90_worsened"]
+    c = cards[0]
+    assert c["severity"] == "warning"
+    assert c["title"] == "回复 P90 较个人基线上升 60%"
+    assert c["current_value"] == 9_600_000
+    assert c["baseline_value"] == 6_000_000
+    assert c["unit"] == "ms"
+    assert c["sample_size"] == 20
+    assert c["affected_count"] == 8  # 20 串 - 12 已回 = 期内未回串数
+    assert c["drilldown"] == {"type": "metric",
+                              "query": {"metric_code": "first_reply_p90",
+                                        "user_id": "u1"}}
+
+
+def test_p90_worsened_critical_at_3x():
+    cur = _pm(cust_threads=20, threads_answered=20, fr_p90_ms=18_000_000)
+    base = _pm(cust_threads=40, threads_answered=40, fr_p90_ms=6_000_000)
+    cards = _detect(cur, base)
+    assert len(cards) == 1
+    assert cards[0]["severity"] == "critical"
+    assert "上升 200%" in cards[0]["title"]
+
+
+def test_p90_boundaries_strict_compare():
+    """×1.5 恰好 → 严格大于不成立不触发;×2.5 恰好 → warning 非 critical;
+    threads 恰好 = soft(10) → ≥soft 触发。"""
+    base = _pm(cust_threads=40, fr_p90_ms=6_000_000)
+    assert _detect(_pm(cust_threads=20, fr_p90_ms=9_000_000), base) == []
+    cards = _detect(_pm(cust_threads=20, fr_p90_ms=15_000_000), base)
+    assert [c["severity"] for c in cards] == ["warning"]
+    cards = _detect(_pm(cust_threads=10, fr_p90_ms=9_600_000), base)
+    assert [c["rule_code"] for c in cards] == ["reply_p90_worsened"]
+
+
+def test_p90_below_soft_threads_not_fired():
+    cur = _pm(cust_threads=5, fr_p90_ms=9_600_000)  # <soft 10
+    base = _pm(cust_threads=40, threads_answered=40, fr_p90_ms=6_000_000)
+    assert _detect(cur, base) == []
+
+
+# ---- 2. 基线缺失 ----
+
+def test_baseline_none_all_rules_silent():
+    """新员工无个人基线:即便 p90 恶化/活动骤降/过载形态俱在也不出卡。"""
+    cur = _pm(cust_threads=20, threads_answered=5, fr_p90_ms=30_000_000,
+              active_friends=85, msg_sent=10, msg_recv=10)
+    assert _detect(cur, None) == []
+
+
+# ---- 3. reply_rate_dropped ----
+
+def test_reply_rate_dropped_warning():
+    """0.8→0.5(0.5 < 0.7×0.8=0.56)→ warning;百分比 37.5%→38%。"""
+    cur = _pm(cust_threads=20, reply_2h_count=10, threads_answered=15)   # 0.5
+    base = _pm(cust_threads=40, reply_2h_count=32, threads_answered=40)  # 0.8
+    cards = _detect(cur, base)
+    assert [c["rule_code"] for c in cards] == ["reply_rate_dropped"]
+    c = cards[0]
+    assert c["severity"] == "warning"
+    assert c["title"] == "2h 回复率较个人基线下降 38%"
+    assert c["current_value"] == pytest.approx(0.5)
+    assert c["baseline_value"] == pytest.approx(0.8)
+    assert c["unit"] == "0-1"
+    assert c["sample_size"] == 20
+    assert c["affected_count"] == 5
+    assert c["drilldown"] == {"type": "metric",
+                              "query": {"metric_code": "unreplied",
+                                        "user_id": "u1"}}
+
+
+def test_reply_rate_small_drop_not_fired():
+    """0.8→0.6(0.6 ≥ 0.56)→ 不触发。"""
+    cur = _pm(cust_threads=20, reply_2h_count=12)   # 0.6
+    base = _pm(cust_threads=40, reply_2h_count=32)  # 0.8
+    assert _detect(cur, base) == []
+
+
+def test_rate_baseline_no_threads_not_fired():
+    """基线无串样本 → 基线率 None → 不判(基线值 None 不触发)。"""
+    cur = _pm(cust_threads=20, reply_2h_count=0)
+    base = _pm(cust_threads=0)  # derive → reply_2h_rate None
+    assert _detect(cur, base) == []
+
+
+# ---- 4. activity_drop ----
+
+def test_activity_drop_triggered():
+    """当前 7 天日均 10 < 基线 28 天日均 30×0.5=15 → warning。"""
+    cur = _pm(msg_sent=40, msg_recv=30, active_friends=25)      # 70/7=10 条/天
+    base = _pm(msg_sent=600, msg_recv=240, days_with_data=20)   # 840/28=30 条/天
+    cards = _detect(cur, base)
+    assert [c["rule_code"] for c in cards] == ["activity_drop"]
+    c = cards[0]
+    assert c["severity"] == "warning"
+    assert c["title"] == "日均消息量较个人基线下降 67%"  # 66.7→67
+    assert c["current_value"] == pytest.approx(10.0)
+    assert c["baseline_value"] == pytest.approx(30.0)
+    assert c["unit"] == "条"
+    assert c["sample_size"] == 25
+    assert c["affected_count"] == 25
+    assert c["drilldown"] == {"type": "employee", "query": {"user_id": "u1"}}
+
+
+def test_activity_drop_sparse_baseline_not_fired():
+    """基线 days_with_data=3 < min_days(5) → 基线不可比,不触发。"""
+    base = _pm(msg_sent=600, msg_recv=240, days_with_data=3)
+    cur = _pm(msg_sent=40, msg_recv=30)
+    assert _detect(cur, base) == []
+
+
+# ---- 5. workload_overload ----
+
+def test_workload_overload_triggered():
+    cards = _detect(_pm(active_friends=85), _pm())
+    assert [c["rule_code"] for c in cards] == ["workload_overload"]
+    c = cards[0]
+    assert c["severity"] == "warning"
+    assert c["title"] == "活跃客户 85 人超过负载上限 80 人"
+    assert c["current_value"] == 85
+    assert c["baseline_value"] is None  # 规则与个人基线无关,阈值在 band 配置
+    assert c["unit"] == "人"
+    assert c["sample_size"] == 85
+    assert c["affected_count"] == 85
+    assert c["drilldown"] == {"type": "employee", "query": {"user_id": "u1"}}
+
+
+def test_workload_overload_at_limit_not_fired():
+    assert _detect(_pm(active_friends=80), _pm()) == []  # 严格大于上限
+
+
+# ---- 6. 配置驱动与组合 ----
+
+def test_thresholds_read_from_config():
+    """soft_threads/band high 改配置即改判——阈值不硬编码。"""
+    cfg = json.loads(json.dumps(DEFAULT_SCORE_CONFIG))
+    cfg["sample_guards"]["soft_threads"] = 25
+    cfg["dimensions"]["workload"]["metrics"]["active_friends_band"]["high"] = 90
+    cur = _pm(cust_threads=20, fr_p90_ms=9_600_000, active_friends=85)
+    base = _pm(cust_threads=40, fr_p90_ms=6_000_000)
+    # threads 20 < soft25 → p90/rate 不评;85 ≤ 90 → 不 overload
+    assert _detect(cur, base, config=cfg) == []
+
+
+def test_multiple_rules_stack_in_order():
+    """p90 ×5 critical + activity 骤降 + overload 90>80 同时触发,按规则表序输出;
+    两侧回复率同为 0(0<0 不成立)→ rate 规则不触发。"""
+    cur = _pm(cust_threads=30, threads_answered=10, fr_p90_ms=30_000_000,
+              active_friends=90, msg_sent=10, msg_recv=10)
+    base = _pm(cust_threads=60, threads_answered=60, fr_p90_ms=6_000_000,
+               msg_sent=600, msg_recv=240, days_with_data=20)
+    cards = _detect(cur, base)
+    assert [c["rule_code"] for c in cards] == [
+        "reply_p90_worsened", "activity_drop", "workload_overload"]
+    assert cards[0]["severity"] == "critical"
+
+
+def test_card_structure_all_fields():
+    """单卡 12 字段齐全且类型正确(v1 §5.4)。"""
+    cur = _pm(cust_threads=20, reply_2h_count=20, threads_answered=12,
+              fr_p90_ms=9_600_000, active_friends=30,
+              msg_sent=80, msg_recv=30)  # 日均 110/7≈15.7 ≥ 15 → activity 不触发
+    base = _pm(cust_threads=40, reply_2h_count=40, threads_answered=40,
+               fr_p90_ms=6_000_000, active_friends=30,
+               msg_sent=600, msg_recv=240, days_with_data=20)
+    cards = _detect(cur, base, user_id="u9")
+    assert len(cards) == 1
+    c = cards[0]
+    assert set(c) == {
+        "rule_code", "severity", "employee_user_id", "title",
+        "current_value", "baseline_value", "unit", "sample_size",
+        "affected_count", "reason", "drilldown", "suggested_action",
+    }
+    assert isinstance(c["rule_code"], str)
+    assert c["severity"] in ("warning", "critical")
+    assert c["employee_user_id"] == "u9"
+    assert isinstance(c["title"], str) and c["title"]
+    assert isinstance(c["current_value"], (int, float))
+    assert c["baseline_value"] is None or isinstance(
+        c["baseline_value"], (int, float))
+    assert isinstance(c["unit"], str)
+    assert isinstance(c["sample_size"], int)
+    assert isinstance(c["affected_count"], int)
+    assert isinstance(c["reason"], str) and c["reason"]
+    assert set(c["drilldown"]) == {"type", "query"}
+    assert isinstance(c["drilldown"]["query"], dict)
+    assert isinstance(c["suggested_action"], str) and c["suggested_action"]

yunke-server/tests/test_management_api.py

@@ -0,0 +1,744 @@
+"""管理 API 六只读端点判别测试(批次B Task B4)。
+
+覆盖:
+- 参数校验:422(缺 start / 跨度>366 / 日历非法 / drilldown 白名单外 /
+  page_size>100)、404(employees/{ghost}、drilldown 员工不存在);
+- dashboard 各段齐全与关键数值(kpis/communication_trend/service_trend/
+  lifecycle/dimension_summary/anomalies/action_summary/data_as_of/
+  metric_version);批次D 补:prev_kpis 环比块+msg_delta(含前窗零数据
+  →None)与 anomalies employee_name enrich(详情端点不带);
+- employees:默认分页 20/total/critical 优先默认排序/channel=wechat 时
+  whatsapp-only 员工消失/keyword/status/min_days 不足→insufficient_sample;
+- detail:账号清单+metrics 全字段+score 完整明细+anomalies+prev/baseline;
+- sections:五段各有 trend 数组与四对比;
+- drilldown:p90 分页与 fr_ms desc/unreplied 按 owner 过滤/cooling-dormant
+  生命周期判定(已删客户剔除)/call_followup 列表+期聚合摘要;
+- metric-definitions:trial 标记/口径说明/config_source 回退。
+"""
+import copy
+import datetime as dt
+from zoneinfo import ZoneInfo
+
+from app.db.models import (
+    Customer,
+    EmployeeCallDaily,
+    EmployeeMetricDaily,
+    EmployeeScoreConfig,
+    FirstReplyFact,
+    Message,
+    MsgDailyStats,
+    PhoneCall,
+    Staff,
+    WechatAccount,
+    WhatsappAccount,
+)
+from app.management.metric_definitions import DEFAULT_SCORE_CONFIG
+
+_SH = ZoneInfo("Asia/Shanghai")
+
+START, END = 20260901, 20260905  # 当前窗 5 天(min_days=5 恰好够)
+
+
+def _ts(*args) -> int:
+    return int(dt.datetime(*args, tzinfo=_SH).timestamp() * 1000)
+
+
+def _mday(day, *, channel="wechat", user_id="u1", metric_version="v1", **kw):
+    cols = {
+        "msg_sent": 0, "msg_recv": 0, "active_friends": 0, "active_rooms": 0,
+        "cust_threads": 0, "threads_answered": 0, "fr_sum_ms": 0,
+        "new_customer_count": 0, "cooling_customer_count": 0,
+        "dormant_customer_count": 0, "reactivated_customer_count": 0,
+        "data_complete": True,
+    }
+    cols.update(kw)
+    return EmployeeMetricDaily(
+        day=day, channel=channel, user_id=user_id,
+        metric_version=metric_version, **cols
+    )
+
+
+def _fact(fr_ms, *, channel="wechat", owner="wx1", peer="p1", day=20260901, i=0):
+    end = _ts(day // 10000, day // 100 % 100, day % 100, 10, 0) + i * 60_000
+    return FirstReplyFact(
+        channel=channel, owner_account_id=owner, peer_id=peer,
+        thread_end_ts=end, reply_ts=end + fr_ms,
+        reply_msg_id=f"{owner}-{peer}-m{i}", day=day, fr_ms=fr_ms,
+    )
+
+
+async def _seed_common(s):
+    """三员工全量种子:u1(微信,2 warning)/u2(双渠道,1 critical+1 warning)/
+    u3(仅 WhatsApp,无异常)——支撑 dashboard/employees/detail/sections/
+    drilldown 全部判据。"""
+    for uid, name, onjob in (("u1", "张三", True), ("u2", "李四", True),
+                             ("u3", "王五", False)):
+        s.add(Staff(user_id=uid, name=name, is_on_job=onjob))
+    s.add(WechatAccount(wx_id="wx1", user_id="u1", nick_name="张三的微信",
+                        user_name="张三"))
+    s.add(WechatAccount(wx_id="wx2", user_id="u2"))
+    s.add(WhatsappAccount(uid="wa2", user_id="u2"))
+    s.add(WhatsappAccount(uid="wa3", user_id="u3"))
+
+    # ---- 当前窗宽表(0901-0905)----
+    for d in range(1, 6):
+        s.add(_mday(20260900 + d, user_id="u1", msg_sent=1, cust_threads=2,
+                    threads_answered=2, fr_sum_ms=240_000, active_friends=3,
+                    active_rooms=1, cooling_customer_count=2,
+                    dormant_customer_count=1,
+                    first_reply_p50_ms=110_000, first_reply_p90_ms=220_000))
+        s.add(_mday(20260900 + d, user_id="u2", msg_sent=10, msg_recv=10,
+                    cust_threads=2, threads_answered=2, fr_sum_ms=1_200_000,
+                    active_friends=4, cooling_customer_count=1,
+                    reactivated_customer_count=1))
+        s.add(_mday(20260900 + d, channel="whatsapp", user_id="u3",
+                    msg_sent=5, msg_recv=5, cust_threads=1, active_friends=1))
+    # ---- 基线窗宽表(0827-0831,u1 高日均触发 activity_drop)----
+    for d in range(27, 32):
+        s.add(_mday(20260800 + d, user_id="u1", msg_sent=14, msg_recv=14))
+        s.add(_mday(20260800 + d, user_id="u2", msg_sent=5, msg_recv=5))
+
+    # ---- fact:当前窗(u1 120s warning / u2 600s critical)+ 基线 60s ----
+    s.add(_fact(120_000, peer="pA", day=20260901, i=0))
+    s.add(_fact(120_000, peer="pB", day=20260902, i=1))
+    s.add(_fact(600_000, owner="wx2", peer="pC", day=20260901, i=2))
+    s.add(_fact(600_000, owner="wx2", peer="pD", day=20260902, i=3))
+    for owner, peer, day, i in (("wx1", "pA", 20260827, 10),
+                                ("wx1", "pB", 20260828, 11),
+                                ("wx2", "pC", 20260827, 12),
+                                ("wx2", "pD", 20260828, 13)):
+        s.add(_fact(60_000, owner=owner, peer=peer, day=day, i=i))
+
+    # ---- msg_daily_stats:活跃客户 distinct + data_as_of + 未回候选 ----
+    s.add(MsgDailyStats(channel="wechat", owner_account_id="wx1",
+                        peer_kind="friend", peer_id="p1", day=20260901,
+                        send_cnt=0, recv_cnt=1, last_ts=_ts(2026, 9, 1, 10, 0),
+                        last_is_send=False))
+    s.add(MsgDailyStats(channel="wechat", owner_account_id="wx1",
+                        peer_kind="friend", peer_id="p2", day=20260902,
+                        send_cnt=1, recv_cnt=0, last_ts=_ts(2026, 9, 2, 10, 0),
+                        last_is_send=True))
+    s.add(MsgDailyStats(channel="wechat", owner_account_id="wx2",
+                        peer_kind="friend", peer_id="p3", day=20260901,
+                        send_cnt=2, recv_cnt=0, last_ts=_ts(2026, 9, 1, 11, 0),
+                        last_is_send=True))
+    s.add(MsgDailyStats(channel="whatsapp", owner_account_id="wa3",
+                        peer_kind="friend", peer_id="p4", day=20260903,
+                        send_cnt=1, recv_cnt=0, last_ts=_ts(2026, 9, 3, 9, 0),
+                        last_is_send=True))
+    # drilldown cooling/dormant 客户互动史(全历史,窗外):
+    # f1 末次 0801(gap 35, hist 12)→ dormant;f2 末次 0825(gap 11)→ cooling
+    for day, n in ((20260701, 6), (20260801, 6)):
+        s.add(MsgDailyStats(channel="wechat", owner_account_id="wx1",
+                            peer_kind="friend", peer_id="f1", day=day,
+                            send_cnt=n, recv_cnt=0,
+                            last_ts=_ts(day // 10000, day // 100 % 100,
+                                        day % 100, 10, 0),
+                            last_is_send=True))
+    for day in (20260801, 20260825):
+        s.add(MsgDailyStats(channel="wechat", owner_account_id="wx1",
+                            peer_kind="friend", peer_id="f2", day=day,
+                            send_cnt=2, recv_cnt=2,
+                            last_ts=_ts(2026, 8, day % 100, 11, 0),
+                            last_is_send=True))
+
+    # ---- 客户档案(f9 已删,须被 drilldown 剔除)----
+    s.add(Customer(friend_id="f1", channel="wechat", owner_account_id="wx1",
+                   friend_nickname="客户一", user_id="u1", delete_flag=0))
+    s.add(Customer(friend_id="f2", channel="wechat", owner_account_id="wx1",
+                   friend_nickname="客户二", user_id="u1", delete_flag=0))
+    s.add(Customer(friend_id="f9", channel="wechat", owner_account_id="wx1",
+                   friend_nickname="已删客户", user_id="u1", delete_flag=1))
+
+    # ---- 未回候选 p1 的尾部消息(unreplied 决赛圈点查)----
+    s.add(Message(msg_id="m-p1", channel="wechat", owner_account_id="wx1",
+                  talker_id="p1", is_send=False, type="text", text="在吗",
+                  timestamp=_ts(2026, 9, 1, 10, 0)))
+
+    # ---- 通话 ----
+    s.add(EmployeeCallDaily(day=20260901, user_id="u1", call_count=2,
+                            call_seconds=100, answered_call_count=1,
+                            call_followup_count=1))
+    s.add(EmployeeCallDaily(day=20260902, user_id="u2", call_count=1,
+                            call_seconds=60, answered_call_count=1,
+                            call_followup_count=0))
+    s.add(PhoneCall(call_id="c1", channel="voice_call", user_id="u1",
+                    start_call_time=_ts(2026, 9, 1, 15, 0), call_duration=120,
+                    call_number="13800000001"))
+    s.add(PhoneCall(call_id="c2", channel="voice_call", user_id="u1",
+                    start_call_time=_ts(2026, 9, 2, 15, 0), call_duration=0,
+                    call_number="13800000002"))
+    await s.commit()
+
+
+# ---------------------------------------------------------------- 参数与错误
+
+
+async def test_dashboard_missing_start_422(make_client):
+    async def seed(s):
+        await _seed_common(s)
+
+    client = await make_client(seed)
+    r = await client.get("/api/management/dashboard", params={"end": END})
+    assert r.status_code == 422
+
+
+async def test_dashboard_span_and_calendar_422(make_client):
+    async def seed(s):
+        await _seed_common(s)
+
+    client = await make_client(seed)
+    r = await client.get("/api/management/dashboard",
+                         params={"start": 20250101, "end": 20261231})
+    assert r.status_code == 422
+    r = await client.get("/api/management/dashboard",
+                         params={"start": 20260230, "end": 20260905})
+    assert r.status_code == 422  # 日历非法(2 月 30 日)
+    r = await client.get("/api/management/dashboard",
+                         params={"start": 20260906, "end": 20260901})
+    assert r.status_code == 422  # start > end
+
+
+async def test_drilldown_unknown_metric_422(make_client):
+    async def seed(s):
+        await _seed_common(s)
+
+    client = await make_client(seed)
+    r = await client.get("/api/management/employees/u1/drilldown",
+                         params={"metric_code": "bogus",
+                                 "start": START, "end": END})
+    assert r.status_code == 422
+    assert "unknown metric_code" in r.json()["detail"]
+
+
+async def test_employees_page_size_over_100_422(make_client):
+    async def seed(s):
+        await _seed_common(s)
+
+    client = await make_client(seed)
+    r = await client.get("/api/management/employees",
+                         params={"start": START, "end": END,
+                                 "page_size": 101})
+    assert r.status_code == 422
+
+
+async def test_employee_detail_404(make_client):
+    async def seed(s):
+        await s.commit()
+
+    client = await make_client(seed)
+    r = await client.get("/api/management/employees/ghost",
+                         params={"start": START, "end": END})
+    assert r.status_code == 404
+
+
+async def test_drilldown_employee_404(make_client):
+    async def seed(s):
+        await s.commit()
+
+    client = await make_client(seed)
+    r = await client.get("/api/management/employees/ghost/drilldown",
+                         params={"metric_code": "unreplied",
+                                 "start": START, "end": END})
+    assert r.status_code == 404
+
+
+# ---------------------------------------------------------------- dashboard
+
+
+async def test_dashboard_structure_and_kpis(make_client):
+    async def seed(s):
+        await _seed_common(s)
+
+    client = await make_client(seed)
+    r = await client.get("/api/management/dashboard",
+                         params={"channel": "all", "start": START, "end": END})
+    assert r.status_code == 200
+    body = r.json()
+    for key in ("scope", "data_as_of", "metric_version", "kpis",
+                "communication_trend", "service_trend", "lifecycle",
+                "dimension_summary", "anomalies", "action_summary",
+                "config_source", "caliber_notes"):
+        assert key in body, key
+    assert body["metric_version"] == "v1"
+    assert body["config_source"] == "default"
+    assert body["scope"] == {"channel": "all", "start": START, "end": END,
+                             "compare": "previous"}
+    assert body["data_as_of"] == _ts(2026, 9, 3, 9, 0)
+
+    k = body["kpis"]
+    # 活跃客户=PM distinct 求和(u1:2 + u2:1 + u3:1)
+    assert k["active_customers"] == 4
+    assert k["active_employees"] == 3
+    assert k["msg_total"] == 155  # u1 5 + u2 100 + u3 50
+    assert k["cust_threads"] == 25  # 10 + 10 + 5
+    assert k["threads_answered"] == 20  # 10 + 10 + 0
+    assert k["call_count"] == 3
+    assert k["call_seconds"] == 160
+    assert k["answered_call"] == 2
+    # 期末存量:u1 cooling2/dormant1 + u2 cooling1;reactivated 期内求和 u2 5
+    assert body["lifecycle"] == {"new": 0, "cooling": 3, "dormant": 1,
+                                 "reactivated": 5}
+    assert k["lifecycle"] == body["lifecycle"]
+
+    # 前窗环比(批次D):prev 窗 0827-0831 与基线窗种子重叠——
+    # u1(14+14)×5 + u2(5+5)×5 = 190;宽表无 active_friends/串列 → 0
+    pk = body["prev_kpis"]
+    assert set(pk) == {"active_customers", "active_employees",
+                       "msg_total", "cust_threads"}
+    assert pk == {"active_customers": 0, "active_employees": 2,
+                  "msg_total": 190, "cust_threads": 0}
+    assert body["msg_delta"] == round((155 - 190) / 190, 3)  # -0.184
+
+    # 趋势逐日 5 点;0901 = u1(1)+u2(20)+u3(10) 消息,宽表 active 合计 8,通话 2
+    trend = body["communication_trend"]
+    assert [t["day"] for t in trend] == [20260901 + i for i in range(5)]
+    assert trend[0]["msg_total"] == 31
+    assert trend[0]["active_customers"] == 8
+    assert trend[0]["call_cnt"] == 2
+    assert trend[1]["call_cnt"] == 1
+    assert trend[4] == {"day": 20260905, "msg_total": 31,
+                        "active_customers": 8, "call_cnt": 0}
+
+    # 服务趋势:0901 fact [120k, 600k] → p50=120k/p90=600k;
+    # reply_2h_rate = 2/5(两串均 ≤2h——600s=10min / 宽表当日串 5)
+    st = {t["day"]: t for t in body["service_trend"]}
+    assert st[20260901]["fr_p50_ms"] == 120_000
+    assert st[20260901]["fr_p90_ms"] == 600_000
+    assert st[20260901]["reply_2h_rate"] == 0.4
+    assert st[20260903]["fr_p50_ms"] is None  # 无 fact 日
+    assert st[20260903]["reply_2h_rate"] == 0.0  # 分母有串、分子 0
+
+    # 维度摘要:5 维全员计数,总数=员工数 3
+    dims = body["dimension_summary"]
+    assert set(dims) == {"customer", "service", "action", "workload", "risk"}
+    for d in dims.values():
+        assert d["scored_count"] + d["insufficient_count"] + d["pending_count"] == 3
+        assert "avg_score" in d
+
+    # 异常:critical 在前(u2),warning 其后按 affected_count desc;
+    # dashboard 卡片 enrich employee_name(批次D,前端跳员工详情用)
+    anoms = body["anomalies"]
+    assert anoms[0]["severity"] == "critical"
+    assert anoms[0]["employee_user_id"] == "u2"
+    assert anoms[0]["employee_name"] == "李四"
+    assert all(a["severity"] == "critical" for a in anoms[:1])
+    assert all(a["severity"] == "warning" for a in anoms[1:])
+    assert all(a["employee_name"] == "张三" for a in anoms[1:])
+
+    assert body["action_summary"] == {"unreplied_2h": 1, "churn_real_30d": 0,
+                                      "sensitive_pending": 0}
+
+
+async def test_dashboard_prev_zero_no_delta(make_client):
+    """前窗无数据(whatsapp 视图前窗零宽表)→ prev_kpis 四键全 0、
+    msg_delta None(prev=0 不算环比,None 而非 0/负∞)。"""
+    async def seed(s):
+        await _seed_common(s)
+
+    client = await make_client(seed)
+    r = await client.get("/api/management/dashboard",
+                         params={"channel": "whatsapp", "start": START,
+                                 "end": END})
+    assert r.status_code == 200
+    body = r.json()
+    assert body["kpis"]["msg_total"] == 50  # 仅 u3 的 whatsapp 宽表
+    assert body["prev_kpis"] == {"active_customers": 0,
+                                 "active_employees": 0, "msg_total": 0,
+                                 "cust_threads": 0}
+    assert body["msg_delta"] is None
+
+
+# ---------------------------------------------------------------- employees
+
+
+async def test_employees_default_sort_and_paging(make_client):
+    async def seed(s):
+        await _seed_common(s)
+
+    client = await make_client(seed)
+    r = await client.get("/api/management/employees",
+                         params={"channel": "all", "start": START, "end": END})
+    assert r.status_code == 200
+    body = r.json()
+    assert body["total"] == 3
+    assert body["page"] == 1
+    assert body["page_size"] == 20
+    assert body["metric_version"] == "v1"
+    assert body["config_source"] == "default"
+    assert len(body["rows"]) == 3
+
+    # 默认 anomaly_severity 排序:含 critical 的 u2 在最前
+    # (u2=1 critical——基线无串样本率不可算,rate 规则不触发;u1=2 warning)
+    ids = [row["user_id"] for row in body["rows"]]
+    assert ids == ["u2", "u1", "u3"]
+    u2, u1, u3 = body["rows"]
+    assert u2["anomaly_count"] == 1 and u2["anomaly_weight"] == 2
+    assert u1["anomaly_count"] == 2 and u1["anomaly_weight"] == 2
+    assert u3["anomaly_count"] == 0 and u3["anomaly_weight"] == 0
+
+    # 行结构:metrics 全字段 / comparisons 四值 / score 摘要
+    assert u1["name"] == "张三" and u1["is_on_job"] is True
+    assert u1["metrics"]["cust_threads"] == 10
+    assert u1["metrics"]["end_active_friends"] == 3
+    # M3:comparisons 键域=源指标名(与 sections 端点一致;band 配置 code
+    # 映射为其 spec.metric——active_friends/call_count,不出现 *_band)
+    assert set(u1["comparisons"]) >= {
+        "active_share", "reply_2h_rate", "reply_24h_rate", "fr_p90_ms",
+        "active_friends", "call_count"}
+    assert "active_friends_band" not in u1["comparisons"]
+    assert "call_band" not in u1["comparisons"]
+    for c in u1["comparisons"].values():
+        assert set(c) == {"current", "prev", "baseline", "median"}
+    assert u1["comparisons"]["fr_p90_ms"]["current"] == 120_000
+    assert u1["comparisons"]["fr_p90_ms"]["baseline"] == 60_000
+    assert set(u1["score"]["dimensions"]) == {
+        "customer", "service", "action", "workload", "risk"}
+    for d in u1["score"]["dimensions"].values():
+        assert set(d) == {"score", "status"}
+    assert u1["score"]["trial"] is True
+    assert u1["score"]["score_status"] == "scored"  # 5 天数据 ≥ min_days
+
+
+async def test_employees_channel_filter(make_client):
+    async def seed(s):
+        await _seed_common(s)
+
+    client = await make_client(seed)
+    r = await client.get("/api/management/employees",
+                         params={"channel": "wechat", "start": START,
+                                 "end": END})
+    ids = [row["user_id"] for row in r.json()["rows"]]
+    assert ids == ["u2", "u1"]  # u3 仅 WhatsApp,wechat 视图消失
+    r = await client.get("/api/management/employees",
+                         params={"channel": "whatsapp", "start": START,
+                                 "end": END})
+    ids = [row["user_id"] for row in r.json()["rows"]]
+    assert ids == ["u2", "u3"]  # u1 无 WA 账号
+
+
+async def test_employees_keyword(make_client):
+    async def seed(s):
+        await _seed_common(s)
+
+    client = await make_client(seed)
+    r = await client.get("/api/management/employees",
+                         params={"start": START, "end": END, "keyword": "张"})
+    assert [row["user_id"] for row in r.json()["rows"]] == ["u1"]
+    r = await client.get("/api/management/employees",
+                         params={"start": START, "end": END, "keyword": "U3"})
+    assert [row["user_id"] for row in r.json()["rows"]] == ["u3"]
+
+
+async def test_employees_status_filter(make_client):
+    async def seed(s):
+        await _seed_common(s)
+
+    client = await make_client(seed)
+    r = await client.get("/api/management/employees",
+                         params={"start": START, "end": END,
+                                 "status": "on_job"})
+    assert [row["user_id"] for row in r.json()["rows"]] == ["u2", "u1"]
+    r = await client.get("/api/management/employees",
+                         params={"start": START, "end": END,
+                                 "status": "offline"})
+    assert [row["user_id"] for row in r.json()["rows"]] == ["u3"]
+
+
+async def test_employees_min_days_insufficient(make_client):
+    """B2 评审遗留接线:days_with_data < min_days → score_status 覆盖
+    insufficient_sample,但可评明细(total_score)保留展示。"""
+
+    async def seed(s):
+        s.add(Staff(user_id="u9", name="赵九", is_on_job=True))
+        s.add(WechatAccount(wx_id="wx9", user_id="u9"))
+        # 仅 2 天宽表数据(< min_days=5),但串样本 30 ≥ min_threads 可评分
+        for d in (1, 2):
+            s.add(_mday(20260900 + d, user_id="u9", cust_threads=15,
+                        threads_answered=15, fr_sum_ms=900_000,
+                        active_friends=10))
+        s.add(_fact(60_000, owner="wx9", peer="q1", day=20260901, i=0))
+        s.add(_fact(60_000, owner="wx9", peer="q2", day=20260902, i=1))
+        for i in range(6):  # 6 个 distinct peer → workload band 可评
+            s.add(MsgDailyStats(channel="wechat", owner_account_id="wx9",
+                                peer_kind="friend", peer_id=f"q{i}",
+                                day=20260901, send_cnt=1, recv_cnt=0,
+                                last_ts=_ts(2026, 9, 1, 12, 0),
+                                last_is_send=True))
+        await s.commit()
+
+    client = await make_client(seed)
+    r = await client.get("/api/management/employees",
+                         params={"start": START, "end": END})
+    assert r.status_code == 200
+    row = r.json()["rows"][0]
+    assert row["user_id"] == "u9"
+    assert row["metrics"]["days_with_data"] == 2
+    assert row["score"]["score_status"] == "insufficient_sample"
+    assert row["score"]["total_score"] is not None  # 明细保留展示
+
+
+async def test_employees_db_score_config_guard(make_client):
+    """config_source=db 路径:激活配置的 min_days=9 生效——u1 五天数据
+    在默认配置(min_days=5)下 scored,在 DB 配置下翻为 insufficient_sample。"""
+
+    async def seed(s):
+        await _seed_common(s)
+        cfg = copy.deepcopy(DEFAULT_SCORE_CONFIG)
+        cfg["version"] = "v1-test"
+        cfg["name"] = "评审测试配置"
+        cfg["sample_guards"]["min_days"] = 9
+        s.add(EmployeeScoreConfig(version="v1-test", name="评审测试配置",
+                                  status="active", config_json=cfg,
+                                  created_by="test"))
+        await s.commit()
+
+    client = await make_client(seed)
+    r = await client.get("/api/management/employees",
+                         params={"channel": "all", "start": START,
+                                 "end": END})
+    assert r.status_code == 200
+    body = r.json()
+    assert body["config_source"] == "db"
+    u1 = next(row for row in body["rows"] if row["user_id"] == "u1")
+    assert u1["metrics"]["days_with_data"] == 5
+    assert u1["score"]["score_status"] == "insufficient_sample"  # 5 < 9
+    assert u1["score"]["total_score"] is not None
+
+
+# ---------------------------------------------------------------- detail
+
+
+async def test_employee_detail_full(make_client):
+    async def seed(s):
+        await _seed_common(s)
+
+    client = await make_client(seed)
+    r = await client.get("/api/management/employees/u1",
+                         params={"channel": "all", "start": START, "end": END})
+    assert r.status_code == 200
+    body = r.json()
+    assert body["user_id"] == "u1"
+    assert body["name"] == "张三"
+    assert body["accounts"] == [
+        {"channel": "wechat", "account_id": "wx1",
+         "nick_name": "张三的微信", "user_name": "张三"}]
+    # metrics 全字段(22 列 namedtuple)
+    assert len(body["metrics"]) == 22
+    assert body["metrics"]["cust_threads"] == 10
+    # score 完整明细:dimensions 含逐指标 metrics;metrics_detail 扁平
+    assert body["score"]["dimensions"]["service"]["metrics"]["fr_p90_ms"][
+        "score"] == 100.0
+    assert body["score"]["metrics_detail"]["fr_p90_ms"]["value"] == 120_000
+    assert body["score"]["metrics_detail"]["reply_2h_rate"]["value"] == 0.2
+    assert body["score"]["metrics_detail"]["fr_p90_ms"]["baseline"] == 60_000
+    # anomalies + prev/baseline 原始值(prev 窗 0827-0831 与基线窗重叠:
+    # 5 天 × msg_sent 14 = 70);详情端点 anomalies 不带 employee_name
+    # (自指无意义,仅 dashboard enrich)
+    assert len(body["anomalies"]) == 2
+    assert all(a["severity"] == "warning" for a in body["anomalies"])
+    assert all("employee_name" not in a for a in body["anomalies"])
+    assert body["prev"]["msg_sent"] == 70
+    assert body["baseline"]["msg_sent"] == 70
+    assert body["data_as_of"] == _ts(2026, 9, 3, 9, 0)
+
+
+# ---------------------------------------------------------------- sections
+
+
+async def test_employee_sections(make_client):
+    async def seed(s):
+        await _seed_common(s)
+
+    client = await make_client(seed)
+    base = "/api/management/employees/u1/metrics"
+    for section in ("overview", "service", "customer", "workload", "calls"):
+        r = await client.get(base, params={
+            "section": section, "channel": "wechat",
+            "start": START, "end": END})
+        assert r.status_code == 200, section
+        body = r.json()
+        assert body["section"] == section
+        assert len(body["trend"]) == 5  # 全窗口逐日(含零填充)
+        assert all("day" in t for t in body["trend"])
+        assert body["comparisons"]["reply_2h_rate"]["current"] == 0.2
+        assert set(body["comparisons"]["reply_2h_rate"]) == {
+            "current", "prev", "baseline", "median"}
+
+    r = await client.get(base, params={"section": "service",
+                                       "channel": "wechat",
+                                       "start": START, "end": END})
+    body = r.json()
+    assert body["metrics"]["cust_threads"] == 10
+    assert body["metrics"]["reply_2h_count"] == 2
+    t0 = body["trend"][0]
+    assert t0 == {"day": 20260901, "cust_threads": 2, "threads_answered": 2,
+                  "fr_sum_ms": 240_000, "first_reply_p50_ms": 110_000,
+                  "first_reply_p90_ms": 220_000}
+
+    r = await client.get(base, params={"section": "calls", "channel": "all",
+                                       "start": START, "end": END})
+    calls = {t["day"]: t for t in r.json()["trend"]}
+    assert calls[20260901]["call_count"] == 2
+    assert calls[20260901]["call_followup_count"] == 1
+    assert calls[20260905]["call_count"] == 0  # 零填充
+    assert r.json()["metrics"]["call_count"] == 2
+
+
+# ---------------------------------------------------------------- drilldown
+
+
+async def test_drilldown_fr_p90(make_client):
+    async def seed(s):
+        await _seed_common(s)
+
+    client = await make_client(seed)
+    url = "/api/management/employees/u2/drilldown"
+    r = await client.get(url, params={
+        "metric_code": "first_reply_p90", "channel": "all",
+        "start": START, "end": END, "page": 1, "page_size": 1})
+    assert r.status_code == 200
+    body = r.json()
+    assert body["total"] == 2
+    assert len(body["items"]) == 1
+    item = body["items"][0]
+    # fr_ms desc + 同值按日 desc 决胜:0902 的 pD 在前
+    assert item["fr_ms"] == 600_000
+    assert item["peer_id"] == "pD"
+    assert item["channel"] == "wechat"
+    assert item["owner_account_id"] == "wx2"
+    assert item["chat_hint"] == {"owner_account_id": "wx2", "talker_id": "pD"}
+    r = await client.get(url, params={
+        "metric_code": "first_reply_p90", "channel": "all",
+        "start": START, "end": END, "page": 2, "page_size": 1})
+    assert r.json()["items"][0]["peer_id"] == "pC"
+    # u2 的 WA 账号无 fact 行
+    r = await client.get(url, params={
+        "metric_code": "first_reply_p50", "channel": "whatsapp",
+        "start": START, "end": END})
+    assert r.json()["total"] == 0
+
+
+async def test_drilldown_unreplied(make_client):
+    async def seed(s):
+        await _seed_common(s)
+
+    client = await make_client(seed)
+    r = await client.get("/api/management/employees/u1/drilldown",
+                         params={"metric_code": "unreplied",
+                                 "channel": "wechat",
+                                 "start": START, "end": END})
+    assert r.status_code == 200
+    body = r.json()
+    assert body["total"] == 1  # p1(wx1)进入,u1 过滤后
+    assert body["items"][0]["peer_id"] == "p1"
+    assert body["items"][0]["owner_account_id"] == "wx1"
+    # u2 名下无未回候选(p3 尾部为员工消息)
+    r = await client.get("/api/management/employees/u2/drilldown",
+                         params={"metric_code": "unreplied",
+                                 "channel": "wechat",
+                                 "start": START, "end": END})
+    assert r.json()["total"] == 0
+
+
+async def test_drilldown_lifecycle_customers(make_client):
+    async def seed(s):
+        await _seed_common(s)
+
+    client = await make_client(seed)
+    r = await client.get("/api/management/employees/u1/drilldown",
+                         params={"metric_code": "cooling_customers",
+                                 "channel": "all",
+                                 "start": START, "end": END})
+    assert r.status_code == 200
+    body = r.json()
+    assert body["total"] == 1  # f2 降温;f1 沉睡、f9 已删
+    assert body["items"][0] == {"friend_id": "f2", "channel": "wechat",
+                                "nickname": "客户二",
+                                "last_day": 20260825, "state": "cooling"}
+
+    r = await client.get("/api/management/employees/u1/drilldown",
+                         params={"metric_code": "dormant_customers",
+                                 "channel": "all",
+                                 "start": START, "end": END})
+    body = r.json()
+    assert body["total"] == 1
+    assert body["items"][0]["friend_id"] == "f1"
+    assert body["items"][0]["state"] == "dormant"
+
+
+async def test_drilldown_shared_customer_history(make_client):
+    """I1:共享/换归属客户——互动史挂在他人账号(wx2)名下而 Customer.owner
+    =wx1:历史按 (channel, peer) 键控跨 owner 合并(对齐批次A _lifecycle_daily
+    的 peer 键控口径),客户不丢、历史完整(hist 12 ≥ 5 判沉睡)。"""
+
+    async def seed(s):
+        await _seed_common(s)
+        for day, month in ((20260701, 7), (20260801, 8)):
+            s.add(MsgDailyStats(channel="wechat", owner_account_id="wx2",
+                                peer_kind="friend", peer_id="f3", day=day,
+                                send_cnt=3, recv_cnt=3,
+                                last_ts=_ts(2026, month, day % 100, 12, 0),
+                                last_is_send=True))
+        s.add(Customer(friend_id="f3", channel="wechat",
+                       owner_account_id="wx1", friend_nickname="共享客户",
+                       user_id="u1", delete_flag=0))
+        await s.commit()
+
+    client = await make_client(seed)
+    r = await client.get("/api/management/employees/u1/drilldown",
+                         params={"metric_code": "dormant_customers",
+                                 "channel": "all",
+                                 "start": START, "end": END})
+    body = r.json()
+    assert body["total"] == 2  # f1 + f3(历史全在 wx2 名下也不丢)
+    f3 = next(i for i in body["items"] if i["friend_id"] == "f3")
+    assert f3 == {"friend_id": "f3", "channel": "wechat",
+                  "nickname": "共享客户",
+                  "last_day": 20260801, "state": "dormant"}
+    # 归属口径仍是 Customer.owner(wx1):u2(wx2)名下看不到
+    r = await client.get("/api/management/employees/u2/drilldown",
+                         params={"metric_code": "dormant_customers",
+                                 "channel": "all",
+                                 "start": START, "end": END})
+    assert r.json()["total"] == 0
+
+
+async def test_drilldown_call_followup(make_client):
+    async def seed(s):
+        await _seed_common(s)
+
+    client = await make_client(seed)
+    r = await client.get("/api/management/employees/u1/drilldown",
+                         params={"metric_code": "call_followup",
+                                 "channel": "all",
+                                 "start": START, "end": END})
+    assert r.status_code == 200
+    body = r.json()
+    assert body["total"] == 2
+    # start_call_time desc:c2(0902)在前
+    assert [i["call_id"] for i in body["items"]] == ["c2", "c1"]
+    assert set(body["items"][0]) == {
+        "call_id", "channel", "call_number", "start_call_time",
+        "call_duration"}
+    assert body["summary"] == {"call_count": 2, "call_seconds": 100,
+                               "answered_call_count": 1,
+                               "call_followup_count": 1}
+
+
+# ------------------------------------------------------- metric-definitions
+
+
+async def test_metric_definitions(make_client):
+    async def seed(s):
+        await _seed_common(s)
+
+    client = await make_client(seed)
+    r = await client.get("/api/management/metric-definitions")
+    assert r.status_code == 200
+    body = r.json()
+    assert body["definitions"]["cust_threads"]["unit"] == "串"
+    assert body["score_config"]["trial"] is True
+    assert body["score_config"]["dimensions"]["risk"]["status"] == "pending_data"
+    assert body["config_source"] == "default"  # 未种子配置→回退默认
+    assert "1:1" in body["caliber_notes"]

yunke-server/tests/test_management_models.py

@@ -0,0 +1,139 @@
+"""管理域 6 张新表的模型冒烟测试(批次A Task1)。
+
+只验证:建表可用、主键/唯一约束生效、默认值正确。业务逻辑在
+first_reply_facts / employee_metrics 的测试里。
+"""
+import pytest
+import sqlalchemy as sa
+from sqlalchemy.exc import IntegrityError
+
+from app.db.models import (
+    EmployeeCallDaily,
+    EmployeeMetricDaily,
+    EmployeeScoreConfig,
+    EmployeeScoreSnapshot,
+    FirstReplyFact,
+    ManagementFollowup,
+)
+
+
+async def test_first_reply_fact_roundtrip(make_session):
+    s = make_session
+    s.add(FirstReplyFact(channel="wechat", owner_account_id="wx1", peer_id="p1",
+                         thread_end_ts=1_700_000_000_000,
+                         reply_ts=1_700_000_600_000, reply_msg_id="m1",
+                         day=20260901, fr_ms=600_000))
+    await s.commit()
+    val = (await s.execute(sa.select(FirstReplyFact.fr_ms))).scalar_one()
+    assert val == 600_000
+
+
+async def test_first_reply_fact_unique_sample(make_session):
+    s = make_session
+    kwargs = {"channel": "wechat", "owner_account_id": "wx1", "peer_id": "p1",
+              "thread_end_ts": 1, "reply_ts": 2, "reply_msg_id": "m1",
+              "day": 20260901, "fr_ms": 1}
+    s.add(FirstReplyFact(**kwargs))
+    await s.commit()
+    s.add(FirstReplyFact(**kwargs))
+    with pytest.raises(IntegrityError):
+        await s.commit()
+
+
+async def test_metric_daily_versioning_coexists(make_session):
+    s = make_session
+    for v in ("v1", "v2"):
+        s.add(EmployeeMetricDaily(day=20260901, channel="wechat",
+                                  user_id="u1", metric_version=v))
+    await s.commit()
+    n = (await s.execute(
+        sa.select(sa.func.count()).select_from(EmployeeMetricDaily))).scalar_one()
+    assert n == 2
+
+
+async def test_metric_daily_defaults_zero_not_none(make_session):
+    s = make_session
+    s.add(EmployeeMetricDaily(day=20260901, channel="wechat", user_id="u1"))
+    await s.commit()
+    row = (await s.execute(sa.select(EmployeeMetricDaily))).scalar_one()
+    assert row.msg_sent == 0 and row.cust_threads == 0 and row.fr_sum_ms == 0
+    assert row.metric_version == "v1"
+    assert row.data_complete is False or row.data_complete == 0  # SQLite 0/1
+
+
+async def test_metric_daily_pk_duplicate_rejected(make_session):
+    """同 (day, channel, user_id, metric_version) 复合主键防重。
+
+    Task 6 delete+insert 幂等重算的安全网:版本内重复落表直接 IntegrityError。
+    """
+    s = make_session
+    s.add(EmployeeMetricDaily(day=20260901, channel="wechat", user_id="u1"))
+    await s.commit()
+    s.add(EmployeeMetricDaily(day=20260901, channel="wechat", user_id="u1"))
+    with pytest.raises(IntegrityError):
+        await s.commit()
+
+
+async def test_call_daily_roundtrip(make_session):
+    s = make_session
+    s.add(EmployeeCallDaily(day=20260901, user_id="u1", call_count=2,
+                            call_seconds=164, answered_call_count=1,
+                            call_followup_count=1))
+    await s.commit()
+    row = (await s.execute(sa.select(EmployeeCallDaily))).scalar_one()
+    assert row.call_seconds == 164
+
+
+async def test_call_daily_pk_duplicate_rejected(make_session):
+    s = make_session
+    s.add(EmployeeCallDaily(day=20260901, user_id="u1"))
+    await s.commit()
+    s.add(EmployeeCallDaily(day=20260901, user_id="u1"))
+    with pytest.raises(IntegrityError):
+        await s.commit()
+
+
+async def test_score_config_version_unique(make_session):
+    s = make_session
+    s.add(EmployeeScoreConfig(version="v1.0", name="一期试算",
+                              config_json={"dimensions": {}}))
+    await s.commit()
+    s.add(EmployeeScoreConfig(version="v1.0", name="重复",
+                              config_json={}))
+    with pytest.raises(IntegrityError):
+        await s.commit()
+
+
+async def test_score_config_config_json_not_null(make_session):
+    """config_json NOT NULL——注解与 DDL 一致(修复:去掉 | None)。
+
+    注意 JSON 列语义:Python None 经 JSON 序列化变成字符串 'null' 而非
+    SQL NULL,不会违反约束;测 NOT NULL 须用 sa.null() 显式发 SQL NULL。
+    """
+    s = make_session
+    s.add(EmployeeScoreConfig(version="v1.0", name="空配置",
+                              config_json=sa.null()))
+    with pytest.raises(IntegrityError):
+        await s.commit()
+
+
+async def test_snapshot_batch_user_unique(make_session):
+    s = make_session
+    common = {"snapshot_batch_id": "b1", "period_type": "week",
+              "period_start": 20260901, "period_end": 20260907,
+              "score_config_version": "v1.0", "metric_version": "v1",
+              "data_as_of": 20260907}
+    s.add(EmployeeScoreSnapshot(user_id="u1", **common))
+    await s.commit()
+    s.add(EmployeeScoreSnapshot(user_id="u1", **common))
+    with pytest.raises(IntegrityError):
+        await s.commit()
+
+
+async def test_followup_defaults(make_session):
+    s = make_session
+    s.add(ManagementFollowup(employee_user_id="u1", source_type="manual"))
+    await s.commit()
+    row = (await s.execute(sa.select(ManagementFollowup))).scalar_one()
+    assert row.status == "open"
+    assert row.created_at is not None

yunke-server/tests/test_management_period_metrics.py

@@ -0,0 +1,300 @@
+"""管理域期聚合查询判别测试(批次B Task B1)。
+
+判据(v2 §3 / B1 规格):
+- 分位=fact 表最近邻秩 ceil(q·n) 精确值(整除算术,无 ceil 方言坑),
+  多账号/跨渠道样本按员工合并;
+- 宽表 SUM 按 (day∈窗, metric_version='v1', channel) 过滤;
+  active_rooms_avg 摊到全窗天数(含无数据日);
+- 期末生命周期存量=每 (user, channel) 最新 ≤end 行,跨渠道相加;
+- distinct 活跃客户=窗内 (uid, peer) 去重(peer_kind='friend')——
+  同一员工多账号的共享客户只计 1(与宽表日值口径一致);
+- 窗口工具:闭区间 day_range/等长前窗/28 天个人基线窗;
+- 幽灵员工(不在 staff)过滤;user_ids 交集;通话恒全渠道。
+"""
+import datetime as dt
+from zoneinfo import ZoneInfo
+
+from app.db.models import (
+    EmployeeCallDaily,
+    EmployeeMetricDaily,
+    FirstReplyFact,
+    MsgDailyStats,
+    Staff,
+    WechatAccount,
+    WhatsappAccount,
+)
+from app.management.employee_metrics import (
+    PeriodMetrics,
+    baseline_window,
+    day_range,
+    period_metrics,
+    prev_window,
+    team_medians,
+)
+
+_SH = ZoneInfo("Asia/Shanghai")
+
+
+def _ts(*args) -> int:
+    return int(dt.datetime(*args, tzinfo=_SH).timestamp() * 1000)
+
+
+async def _seed_org(s, users=("u1", "u2")):
+    for u in users:
+        s.add(Staff(user_id=u, name=u, is_on_job=True))
+    s.add(WechatAccount(wx_id="wx1", user_id="u1"))
+    s.add(WechatAccount(wx_id="wx2", user_id="u2"))
+    await s.commit()
+
+
+def _mday(day, *, channel="wechat", user_id="u1", metric_version="v1", **kw):
+    cols = {
+        "msg_sent": 0, "msg_recv": 0, "active_friends": 0, "active_rooms": 0,
+        "cust_threads": 0, "threads_answered": 0, "fr_sum_ms": 0,
+        "new_customer_count": 0, "cooling_customer_count": 0,
+        "dormant_customer_count": 0, "reactivated_customer_count": 0,
+        "data_complete": True,
+    }
+    cols.update(kw)
+    return EmployeeMetricDaily(
+        day=day, channel=channel, user_id=user_id,
+        metric_version=metric_version, **cols
+    )
+
+
+def _fact(fr_ms, *, channel="wechat", owner="wx1", peer="p1", day=20260901, i=0):
+    end = _ts(2026, 9, 1, 10, 0) + i * 60_000
+    return FirstReplyFact(
+        channel=channel, owner_account_id=owner, peer_id=peer,
+        thread_end_ts=end, reply_ts=end + fr_ms,
+        reply_msg_id=f"{owner}-{peer}-m{i}", day=day, fr_ms=fr_ms,
+    )
+
+
+async def test_percentile_exact(make_session):
+    """5 样本 p50=180s/p90=300s(ceil(2.5)=3、ceil(4.5)=5,1-based);
+    2 样本 p50=10s/p90=20s;窗外行不参与。"""
+    s = make_session
+    await _seed_org(s)
+    for i, sec in enumerate([60, 120, 180, 240, 300]):
+        s.add(_fact(sec * 1000, i=i))
+    for i, sec in enumerate([10, 20]):
+        s.add(_fact(sec * 1000, owner="wx2", peer="q1", i=i))
+    # 窗外(0906>end)长尾:混入则 p90=999s
+    s.add(_fact(999_000, i=9, day=20260906))
+    await s.commit()
+    m = await period_metrics(s, 20260901, 20260905, "wechat")
+    assert m["u1"].fr_p50_ms == 180_000
+    assert m["u1"].fr_p90_ms == 300_000
+    assert m["u2"].fr_p50_ms == 10_000
+    assert m["u2"].fr_p90_ms == 20_000
+
+
+async def test_period_sums_vs_daily_rows(make_session):
+    """宽表两天行 SUM 正确;days_with_data=2;active_rooms_avg 摊到全窗
+    5 天(含无数据日);channel/metric_version/窗外行都不计。"""
+    s = make_session
+    await _seed_org(s)
+    s.add(_mday(20260901, msg_sent=3, msg_recv=5, cust_threads=2,
+                threads_answered=1, fr_sum_ms=7_000, active_rooms=4,
+                reactivated_customer_count=1))
+    s.add(_mday(20260903, msg_sent=4, msg_recv=6, cust_threads=3,
+                threads_answered=2, fr_sum_ms=11_000, active_rooms=6,
+                reactivated_customer_count=2))
+    # 反例三连:错渠道 / 错版本 / 窗外
+    s.add(_mday(20260901, channel="whatsapp", msg_sent=100))
+    s.add(_mday(20260901, metric_version="v2", msg_sent=200))
+    s.add(_mday(20260906, msg_sent=400))
+    await s.commit()
+    m = await period_metrics(s, 20260901, 20260905, "wechat")
+    u1 = m["u1"]
+    assert u1.msg_sent == 7
+    assert u1.msg_recv == 11
+    assert u1.cust_threads == 5
+    assert u1.threads_answered == 3
+    assert u1.fr_sum_ms == 18_000
+    assert u1.days_with_data == 2
+    assert u1.active_rooms_avg == 2.0  # (4+6)/5 全窗天数,非 2 有数据日
+    assert u1.reactivated_customer == 3
+
+
+async def test_end_of_period_stock(make_session):
+    """期末存量=每渠道最新 ≤end 行:窗 [0901,0903] 取 0901 行、
+    [0901,0905] 取 0905 行;channel=None 跨渠道相加(4+2=6)。
+    end_active_friends 同源同行:wechat 7 + whatsapp 3 → 10(评分
+    active_share 分子,与周期 distinct 的 active_friends 字段不同口径)。"""
+    s = make_session
+    await _seed_org(s)
+    s.add(_mday(20260901, new_customer_count=1, cooling_customer_count=2,
+                dormant_customer_count=3, active_friends=7))
+    s.add(_mday(20260905, dormant_customer_count=4, active_friends=7))
+    s.add(_mday(20260905, channel="whatsapp", dormant_customer_count=2,
+                active_friends=3))
+    await s.commit()
+
+    m1 = await period_metrics(s, 20260901, 20260903, "wechat")
+    assert m1["u1"].new_customer == 1
+    assert m1["u1"].cooling_customer == 2
+    assert m1["u1"].dormant_customer == 3
+    assert m1["u1"].end_active_friends == 7  # 渠道内最新行(0901)的值
+
+    m2 = await period_metrics(s, 20260901, 20260905, "wechat")
+    assert m2["u1"].dormant_customer == 4  # wechat 渠道内最新行
+    assert m2["u1"].new_customer == 0
+    assert m2["u1"].end_active_friends == 7
+
+    m3 = await period_metrics(s, 20260901, 20260905, None)
+    assert m3["u1"].dormant_customer == 6  # wechat 4 + whatsapp 2
+    assert m3["u1"].end_active_friends == 10  # wechat 7 + whatsapp 3
+
+
+async def test_distinct_active_cross_day(make_session):
+    """同 peer 两天两行只计 1;room 行与幽灵 owner 不计。"""
+    s = make_session
+    await _seed_org(s)
+    for day, peer in [(20260901, "p1"), (20260902, "p1"), (20260902, "p2")]:
+        s.add(MsgDailyStats(channel="wechat", owner_account_id="wx1",
+                            peer_kind="friend", peer_id=peer, day=day))
+    # room 行不计入活跃客户
+    s.add(MsgDailyStats(channel="wechat", owner_account_id="wx1",
+                        peer_kind="room", peer_id="r1", day=20260902))
+    # 幽灵 owner(account_map 无映射)不计
+    s.add(MsgDailyStats(channel="wechat", owner_account_id="wx9",
+                        peer_kind="friend", peer_id="p9", day=20260902))
+    await s.commit()
+    m = await period_metrics(s, 20260901, 20260902, "wechat")
+    assert m["u1"].active_friends == 2
+
+
+async def test_active_friends_shared_peer_across_accounts(make_session):
+    """多账号共享客户去重:u1 的 wx1/wx3 都会话 p1 → active_friends=1
+    (账号归并到员工后按 peer 去重,非 (owner, peer) 双计)。"""
+    s = make_session
+    await _seed_org(s)
+    s.add(WechatAccount(wx_id="wx3", user_id="u1"))
+    await s.commit()
+    for owner in ("wx1", "wx3"):
+        s.add(MsgDailyStats(channel="wechat", owner_account_id=owner,
+                            peer_kind="friend", peer_id="p1", day=20260901))
+    await s.commit()
+    m = await period_metrics(s, 20260901, 20260905, "wechat")
+    assert m["u1"].active_friends == 1
+    assert m["u2"].active_friends == 0
+
+
+def test_window_helpers():
+    # day_range 闭区间 + 月末边界
+    assert day_range(20260901, 20260903) == [20260901, 20260902, 20260903]
+    assert day_range(20260831, 20260901) == [20260831, 20260901]
+    # prev_window 等长紧邻前窗(7 天窗 → 7 天窗;单日 → 单日)
+    assert prev_window(20260908, 20260914) == (20260901, 20260907)
+    assert prev_window(20260901, 20260901) == (20260831, 20260831)
+    # baseline_window:紧邻窗前 28 天([0915] → [0818, 0914])
+    assert baseline_window(20260915) == (20260818, 20260914)
+
+
+async def test_ghost_and_channel_none(make_session):
+    """幽灵(不在 staff)宽表行/fact 行不计;channel=None 合并两渠道
+    amap——u1(wx1+wa1)的宽表 SUM 与 fact 分位都跨渠道归并;
+    无数据员工(u2)也以零值行出现。"""
+    s = make_session
+    await _seed_org(s)
+    s.add(WhatsappAccount(uid="wa1", user_id="u1"))
+    # 账号存在但映射到非 staff 用户 → 幽灵
+    s.add(WechatAccount(wx_id="wxg", user_id="ghost"))
+    await s.commit()
+
+    s.add(_mday(20260901, msg_sent=3))
+    s.add(_mday(20260901, channel="whatsapp", msg_sent=4))
+    s.add(_mday(20260901, user_id="ghost", msg_sent=50))
+    s.add(_fact(100_000, owner="wx1", i=0))
+    s.add(_fact(300_000, channel="whatsapp", owner="wa1", peer="w1", i=1))
+    s.add(_fact(50_000, owner="wxg", i=2))
+    await s.commit()
+
+    m = await period_metrics(s, 20260901, 20260905, None)
+    assert set(m) == {"u1", "u2"}  # ghost 不在;零数据 u2 在
+    u1 = m["u1"]
+    assert u1.msg_sent == 7  # 两渠道行都归 u1
+    assert u1.days_with_data == 1  # 双渠道同日只计 1 天(DISTINCT day)
+    assert u1.fr_p50_ms == 100_000  # [100s,300s] 合并后 ceil(0.5*2)=1
+    assert u1.fr_p90_ms == 300_000  # ceil(0.9*2)=2
+    assert u1.reply_2h_count == 2
+    assert u1.reply_24h_count == 2
+    assert m["u2"].msg_sent == 0
+    assert m["u2"].fr_p50_ms is None
+
+
+async def test_reply_counts(make_session):
+    """fr=90min/3h/25h → 2h_count=1、24h_count=2(2h 是 24h 的子集)。"""
+    s = make_session
+    await _seed_org(s)
+    s.add(_fact(5_400_000, i=0))    # 90min ≤2h
+    s.add(_fact(10_800_000, i=1))   # 3h ∈(2h,24h]
+    s.add(_fact(90_000_000, i=2))   # 25h >24h
+    await s.commit()
+    m = await period_metrics(s, 20260901, 20260905, "wechat")
+    assert m["u1"].reply_2h_count == 1
+    assert m["u1"].reply_24h_count == 2
+    assert m["u2"].reply_2h_count == 0
+
+
+async def test_user_ids_filter_and_calls(make_session):
+    """user_ids 与 staff 求交(未知 id 剔除/空集→{});通话四列按窗 SUM
+    且不受 channel 参数影响(无渠道维,恒全渠道)。"""
+    s = make_session
+    await _seed_org(s)
+    s.add(_mday(20260901, user_id="u1", msg_sent=1))
+    s.add(_mday(20260901, user_id="u2", msg_sent=2))
+    s.add(EmployeeCallDaily(day=20260901, user_id="u1", call_count=3,
+                            call_seconds=600, answered_call_count=2,
+                            call_followup_count=1))
+    s.add(EmployeeCallDaily(day=20260902, user_id="u1", call_count=1,
+                            call_seconds=60, answered_call_count=1,
+                            call_followup_count=0))
+    s.add(EmployeeCallDaily(day=20260901, user_id="u2", call_count=9))
+    await s.commit()
+
+    m = await period_metrics(s, 20260901, 20260905, "wechat", user_ids=["u1", "nobody"])
+    assert set(m) == {"u1"}
+    assert m["u1"].msg_sent == 1
+    u1 = m["u1"]
+    assert u1.call_count == 4
+    assert u1.call_seconds == 660
+    assert u1.answered_call == 3
+    assert u1.call_followup == 1
+
+    empty = await period_metrics(s, 20260901, 20260905, "wechat", user_ids=[])
+    assert empty == {}
+
+    # channel="whatsapp" 时通话仍计入(恒全渠道)
+    mwa = await period_metrics(s, 20260901, 20260905, "whatsapp")
+    assert mwa["u1"].call_count == 4
+
+
+def test_team_medians():
+    """奇数样本取中位、偶数取均值;None 剔除;全 None → None;user_id 不参与。"""
+
+    def _pm(**kw):
+        base = dict(zip(PeriodMetrics._fields, [None] * len(PeriodMetrics._fields)))
+        base.update(user_id="x", days_with_data=0, msg_sent=0, msg_recv=0,
+                    cust_threads=0, threads_answered=0, fr_sum_ms=0,
+                    reply_2h_count=0, reply_24h_count=0, active_friends=0,
+                    active_rooms_avg=0.0, new_customer=0, cooling_customer=0,
+                    dormant_customer=0, reactivated_customer=0,
+                    call_count=0, call_seconds=0, answered_call=0,
+                    call_followup=0)
+        base.update(kw)
+        return PeriodMetrics(**base)
+
+    metrics = {
+        "u1": _pm(user_id="u1", msg_sent=10, fr_p50_ms=None),
+        "u2": _pm(user_id="u2", msg_sent=20, fr_p50_ms=100),
+        "u3": _pm(user_id="u3", msg_sent=30, fr_p50_ms=200),
+    }
+    med = team_medians(metrics)
+    assert med["msg_sent"] == 20
+    assert med["fr_p50_ms"] == 150.0  # None 剔除后 [100,200] 均值
+    assert "user_id" not in med
+    assert team_medians({})["msg_sent"] is None
+    assert team_medians({"u1": _pm()})["fr_p50_ms"] is None

yunke-server/tests/test_management_scoring.py

@@ -0,0 +1,315 @@
+"""管理域评分配置/引擎判别测试(批次B Task B2)。"""
+import json
+
+import sqlalchemy as sa
+
+from app.db.models import EmployeeScoreConfig
+from app.management.employee_metrics import PeriodMetrics
+from app.management.metric_definitions import (
+    DEFAULT_SCORE_CONFIG,
+    METRIC_DEFINITIONS,
+    validate_config,
+)
+from app.management.scoring import normalize, score_employee
+
+
+def test_config_weights_sum_and_structure():
+    dims = DEFAULT_SCORE_CONFIG["dimensions"]
+    assert sum(d["weight"] for d in dims.values()) == 100
+    # 一期 pending_data 的维度不参与试算
+    available = [d for d in dims.values() if d.get("status") != "pending_data"]
+    assert sum(d["weight"] for d in available) == 70  # 30+25+15
+    assert dims["action"]["status"] == "pending_data"
+    assert dims["risk"]["status"] == "pending_data"
+
+
+def test_config_normalization_declared():
+    assert DEFAULT_SCORE_CONFIG["normalization"] == "available_only_rescale"
+
+
+def test_validate_config_rejects_bad_weight_sum():
+    bad = json.loads(json.dumps(DEFAULT_SCORE_CONFIG))  # deep copy
+    bad["dimensions"]["service"]["weight"] = 26  # 总和 101
+    problems = validate_config(bad)
+    assert any("权重" in p for p in problems)
+
+
+def test_metric_definitions_cover_scored_metrics():
+    # 每个参与评分的 metric_code 都有元数据(名称/单位/方向)
+    for dim in DEFAULT_SCORE_CONFIG["dimensions"].values():
+        for code in dim.get("metrics", {}):
+            # band 型指标的 key 带 _band 后缀,spec 里有 metric 字段:
+            spec = dim["metrics"][code]
+            src = spec.get("metric", code)
+            assert src in METRIC_DEFINITIONS
+            m = METRIC_DEFINITIONS[src]
+            assert m["name"] and m["unit"] and m["direction"] in (1, -1)
+
+
+async def test_seed_and_idempotent(make_session):
+    from app.management.metric_definitions import _seed_score_config  # 纯会话函数
+    s = make_session
+    v1 = await _seed_score_config(s)
+    await s.commit()
+    assert v1 == "v1.0"
+    rows = (await s.execute(sa.select(EmployeeScoreConfig))).scalars().all()
+    assert len(rows) == 1 and rows[0].status == "active"
+    # 幂等:已存在同版本返回 None 不新建
+    assert await _seed_score_config(s) is None
+    await s.commit()
+    assert len((await s.execute(sa.select(EmployeeScoreConfig))).scalars().all()) == 1
+
+
+# ---- 评分引擎(Task B2) ----
+
+def _pm(**overrides):
+    """全零/None 默认的 PeriodMetrics 构造器(22 字段,覆盖式改)。"""
+    base = {
+        "user_id": "u1", "days_with_data": 0, "msg_sent": 0, "msg_recv": 0,
+        "cust_threads": 0, "threads_answered": 0, "fr_sum_ms": 0,
+        "fr_p50_ms": None, "fr_p90_ms": None,
+        "reply_2h_count": 0, "reply_24h_count": 0,
+        "active_friends": 0, "active_rooms_avg": 0.0,
+        "new_customer": 0, "cooling_customer": 0, "dormant_customer": 0,
+        "end_active_friends": 0, "reactivated_customer": 0,
+        "call_count": 0, "call_seconds": 0, "answered_call": 0,
+        "call_followup": 0,
+    }
+    base.update(overrides)
+    return PeriodMetrics(**base)
+
+
+def _full_marks(**overrides):
+    """三可用维度全满分:率 1.0/fr 10min/占比 0.6/两 band 区间内,样本全 ok。"""
+    full = dict(
+        cust_threads=50, reply_2h_count=50, reply_24h_count=50,
+        fr_p90_ms=600_000,                          # 10min ≤ 30min 满分线
+        end_active_friends=9, cooling_customer=3, dormant_customer=3,  # 9/15=0.6
+        active_friends=50,                          # band [5,80] 内且样本 ok
+        call_count=20,                              # band [1,200] 内
+    )
+    full.update(overrides)
+    return _pm(**full)
+
+
+def test_normalize_target_three_segments():
+    spec = {"type": "target", "floor": 0.40, "target": 0.85}
+    assert normalize(spec, 0.20) == 0.0    # ≤floor
+    assert normalize(spec, 0.40) == 0.0    # floor 处 0
+    assert normalize(spec, 0.625) == 50.0  # 中点 50
+    assert normalize(spec, 0.85) == 100.0  # target 处 100
+    assert normalize(spec, 0.99) == 100.0  # ≥target 截断
+    assert normalize(spec, None) is None   # 无值≠0 分
+
+
+def test_normalize_reverse_ends_and_midpoint():
+    spec = {"type": "reverse", "target_ms": 1_800_000, "floor_ms": 14_400_000}
+    assert normalize(spec, 1_800_000) == 100.0   # 30min 满分
+    assert normalize(spec, 600_000) == 100.0     # 更快也封顶 100
+    assert normalize(spec, 8_100_000) == 50.0    # (30min+4h) 中点 50
+    assert normalize(spec, 14_400_000) == 0.0    # 4h 0 分
+    assert normalize(spec, 28_800_000) == 0.0    # 更慢截断 0
+    assert normalize(spec, None) is None
+
+
+def test_normalize_band_three_segments():
+    spec = {"type": "band", "metric": "active_friends", "low": 5, "high": 80,
+            "basis": "period_distinct"}
+    assert normalize(spec, 3) is None       # <low 负载不足→不评分
+    assert normalize(spec, 4.9) is None
+    assert normalize(spec, 5) == 100.0      # 含下限
+    assert normalize(spec, 80) == 100.0     # 含上限
+    assert normalize(spec, 81) == 80.0      # 超上限 80 不再加
+    assert normalize(spec, 500) == 80.0
+    assert normalize(spec, None) is None
+
+
+def test_zero_threads_rates_none_not_zero():
+    """cust_threads=0 → 回复率无值(None),不是 0%;service 维度 pending。"""
+    res = score_employee(DEFAULT_SCORE_CONFIG, _pm(cust_threads=0))
+    for code in ("reply_2h_rate", "reply_24h_rate"):
+        md = res["metrics_detail"][code]
+        assert md["value"] is None
+        assert md["score"] is None
+    assert res["dimensions"]["service"]["status"] == "pending"
+
+
+def test_insufficient_sample_employee():
+    """cust_threads=5(<soft 10):service 维度 insufficient(率有值 0.0 但
+    不评分);customer 期末无存量 pending;workload 样本 af=0 也不足——
+    可用维度=0 → 整员工不评分。"""
+    res = score_employee(DEFAULT_SCORE_CONFIG, _pm(cust_threads=5))
+    assert res["dimensions"]["service"]["status"] == "insufficient"
+    assert res["dimensions"]["service"]["score"] is None
+    assert res["dimensions"]["customer"]["status"] == "pending"
+    assert res["dimensions"]["workload"]["status"] == "insufficient"
+    assert res["total_score"] is None
+    assert res["grade"] is None
+    assert res["score_status"] == "insufficient_sample"
+    md = res["metrics_detail"]["reply_2h_rate"]
+    assert md["value"] == 0.0 and md["score"] is None
+    assert md["sample_size"] == 5 and md["sample_status"] == "insufficient"
+
+
+def test_low_confidence_still_scored():
+    """cust_threads=15 ∈ [soft10, min30):照评但逐指标 low_confidence。"""
+    cur = _pm(cust_threads=15, reply_2h_count=15, reply_24h_count=15,
+              fr_p90_ms=600_000)
+    res = score_employee(DEFAULT_SCORE_CONFIG, cur)
+    svc = res["dimensions"]["service"]
+    assert svc["status"] == "scored" and svc["score"] == 100.0
+    for code in ("reply_2h_rate", "reply_24h_rate", "fr_p90_ms"):
+        assert svc["metrics"][code]["sample_status"] == "low_confidence"
+        assert svc["metrics"][code]["score"] == 100.0
+    # 仅 service 可用(25/25)→ 重归一后仍满分
+    assert res["score_status"] == "scored"
+    assert res["total_score"] == 100
+
+
+def test_full_marks_rescale_100_of_70():
+    """三可用维度(权重 30+25+15=70)全满分 → 100/70 重归一 = 100,A。"""
+    res = score_employee(DEFAULT_SCORE_CONFIG, _full_marks())
+    assert res["dimensions"]["customer"]["score"] == 100.0
+    assert res["dimensions"]["service"]["score"] == 100.0
+    assert res["dimensions"]["workload"]["score"] == 100.0
+    assert res["total_score"] == 100
+    assert res["grade"] == "A"
+    assert res["score_status"] == "scored"
+    # 部分:service 满分但 active_share=0(floor 下)→ (0+25+15)/70=57 → E
+    res2 = score_employee(
+        DEFAULT_SCORE_CONFIG,
+        _full_marks(end_active_friends=1, cooling_customer=10,
+                    dormant_customer=10),  # 1/21≈0.05 ≤ floor 0.20 → 0 分
+    )
+    assert res2["total_score"] == 57
+    assert res2["grade"] == "E"
+
+
+def test_pending_dimensions_not_scored():
+    """action/risk 一期 pending_data:status=pending、无 metrics、不参与归一。"""
+    res = score_employee(DEFAULT_SCORE_CONFIG, _full_marks())
+    for key in ("action", "risk"):
+        d = res["dimensions"][key]
+        assert d["status"] == "pending"
+        assert d["score"] is None
+        assert "metrics" not in d
+    scored_w = sum(d["weight"] for d in res["dimensions"].values()
+                   if d["status"] == "scored")
+    assert scored_w == 70  # pending 的 30 权重不进分母
+
+
+def test_active_share_derivation():
+    """end_active 6/(6+cooling3+dormant1)=0.6 → 达 target 线 100 分。"""
+    cur = _pm(cust_threads=50, end_active_friends=6,
+              cooling_customer=3, dormant_customer=1)
+    res = score_employee(DEFAULT_SCORE_CONFIG, cur)
+    md = res["metrics_detail"]["active_share"]
+    assert md["value"] == 0.6
+    assert md["score"] == 100.0
+    assert res["dimensions"]["customer"]["score"] == 100.0
+    assert md["sample_status"] == "ok"
+
+
+def test_metrics_detail_four_compare_slots():
+    """value/prev/baseline/median 四对比位透出;band 明细的 median 按
+    源指标名(active_friends)取 team;单位/名称来自元数据。"""
+    cur = _pm(cust_threads=40, reply_2h_count=30, reply_24h_count=38,
+              fr_p90_ms=600_000, end_active_friends=6, cooling_customer=3,
+              dormant_customer=1, active_friends=40, call_count=10)
+    prev = _pm(cust_threads=40, reply_2h_count=20, reply_24h_count=30,
+               fr_p90_ms=3_600_000, end_active_friends=3, cooling_customer=6,
+               dormant_customer=1, active_friends=20, call_count=5)
+    base = _pm(cust_threads=40, reply_2h_count=10)
+    team = {"reply_2h_rate": 0.7, "active_friends": 33.0}
+    res = score_employee(DEFAULT_SCORE_CONFIG, cur, baseline=base,
+                         team=team, prev=prev)
+    md = res["metrics_detail"]["reply_2h_rate"]
+    assert md["value"] == 0.75
+    assert md["prev"] == 0.5
+    assert md["baseline"] == 0.25
+    assert md["median"] == 0.7
+    assert md["unit"] == "0-1"
+    assert md["name"] == "2h回复率"
+    # band 型明细键=配置 code,median 按源指标名查 team
+    band = res["metrics_detail"]["active_friends_band"]
+    assert band["median"] == 33.0
+    assert band["unit"] == "人"
+    assert res["metrics_detail"]["fr_p90_ms"]["prev"] == 3_600_000
+    assert res["metrics_detail"]["active_share"]["prev"] == 0.3  # 3/(3+6+1)
+
+
+def test_trial_flag_from_config():
+    """试算标记透传:默认配置恒 True(v2 §0 全默认+试算)。"""
+    res = score_employee(DEFAULT_SCORE_CONFIG, _pm())
+    assert res["trial"] is True
+    # 标记来自 config 而非写死——正式版翻 False 只需改配置
+    no_trial = json.loads(json.dumps(DEFAULT_SCORE_CONFIG))
+    no_trial["trial"] = False
+    assert score_employee(no_trial, _pm())["trial"] is False
+
+
+def test_validate_config_threshold_shapes():
+    """阈值形状四查:type 合法/target floor<target/reverse 先后/band 区间。
+    默认配置自身必须通过。"""
+    assert validate_config(DEFAULT_SCORE_CONFIG) == []
+
+    def _bad(mutate):
+        cfg = json.loads(json.dumps(DEFAULT_SCORE_CONFIG))
+        mutate(cfg["dimensions"])
+        return cfg
+
+    bad_type = _bad(lambda d: d["workload"]["metrics"]["call_band"]
+                    .update(type="linear"))
+    assert any("call_band" in p and "类型非法" in p
+               for p in validate_config(bad_type))
+
+    bad_target = _bad(lambda d: d["customer"]["metrics"]["active_share"]
+                      .update(floor=0.70))  # floor>target 0.60
+    assert any("active_share" in p and "floor<target" in p
+               for p in validate_config(bad_target))
+
+    bad_reverse = _bad(lambda d: d["service"]["metrics"]["fr_p90_ms"]
+                       .update(target_ms=20_000_000))  # > floor_ms 14.4M
+    assert any("fr_p90_ms" in p and "target_ms<floor_ms" in p
+               for p in validate_config(bad_reverse))
+
+    bad_band = _bad(lambda d: d["workload"]["metrics"]["call_band"]
+                    .update(low=300))  # low>high 200
+    assert any("call_band" in p and "low<high" in p
+               for p in validate_config(bad_band))
+
+
+def test_validate_config_grade_bounds_shape():
+    """grade_bounds 须含 A/B/C/D 且严格降序(B4 DB 配置加载预埋)。"""
+    missing = json.loads(json.dumps(DEFAULT_SCORE_CONFIG))  # deep copy
+    del missing["grade_bounds"]["A"]
+    assert any("grade_bounds" in p for p in validate_config(missing))
+
+    non_desc = json.loads(json.dumps(DEFAULT_SCORE_CONFIG))
+    non_desc["grade_bounds"].update(A=80, B=90)  # A<B 非降序
+    assert any("grade_bounds" in p and "严格降序" in p
+               for p in validate_config(non_desc))
+
+
+def test_validate_config_cross_dimension_code_unique():
+    """同指标 code 出现于两维度:metrics_detail 扁平 dict 会碰撞,须报问题。"""
+    dup = json.loads(json.dumps(DEFAULT_SCORE_CONFIG))  # deep copy
+    # 把 customer 维的 active_share 整个抄进 service 维 → code 跨维度重复
+    dup["dimensions"]["service"]["metrics"]["active_share"] = \
+        dup["dimensions"]["customer"]["metrics"]["active_share"]
+    assert any("active_share" in p and "重复" in p for p in validate_config(dup))
+
+
+def test_validate_config_source_name_unique():
+    """两个 code 指向同一源指标:comparisons 按源名建键会静默覆盖,须报问题。"""
+    dup = json.loads(json.dumps(DEFAULT_SCORE_CONFIG))
+    # service 里造一个不同 code 但同指向 active_friends 的 band(源名冲突)
+    dup["dimensions"]["service"]["metrics"]["load_band"] = {
+        "type": "band", "metric": "active_friends", "low": 1, "high": 50,
+    }
+    assert any("同一源指标 active_friends" in p for p in validate_config(dup))
+
+
+def test_validate_config_default_config_clean():
+    """默认配置自身必须全绿(空问题列表)。"""
+    assert validate_config(DEFAULT_SCORE_CONFIG) == []

yunke-server/tests/test_repos.py

@@ -25,6 +25,7 @@ from app.db.base import Base
 from app.db.models import (
     ChatGroup,
     Customer,
+    CustomerAccountLink,
     Department,
     GroupMember,
     Message,
@@ -39,6 +40,7 @@ from app.storage.repos import (
     _build_column_values,
     _coerce_bool,
     _coerce_int,
+    prune_customer_links,
     upsert_chat_group,
     upsert_customer,
     upsert_customers,
@@ -107,6 +109,116 @@ def test_coerce_int_returns_none_for_non_numeric_string():
 # ---------------------------------------------------------------------------
 
 
+async def test_upsert_customer_shared_friend_maintains_links():
+    """共享好友:档案全局单行(last-wins),link 每个账号各一行(2026-09-08)。
+
+    同一 friend_id 先后在 ownerA/ownerB 名下 upsert——customer 只有一行
+    且归属=后写;customer_account_link 两行,各自带自己的备注快照与
+    fromType(来自 raw_json)。
+    """
+    engine = await _make_engine()
+    try:
+        SessionLocal = async_sessionmaker(engine, expire_on_commit=False)
+        async with SessionLocal() as session:
+            base = {
+                "friend_id": "wxid_shared",
+                "channel": "wechat",
+                "friend_nickname": "共享客户",
+                "phone": "13800000000",
+                "send_num": 10,
+                "receive_num": 4,
+            }
+            await upsert_customer(session, {
+                **base, "owner_account_id": "wx_a",
+                "friend_remark": "A的备注", "raw_json": {"fromType": 1},
+            })
+            await session.commit()
+            await upsert_customer(session, {
+                **base, "owner_account_id": "wx_b",
+                "friend_remark": "B的备注", "raw_json": {"fromType": 2},
+            })
+            await session.commit()
+
+            custs = (await session.execute(
+                sa.select(Customer).execution_options(populate_existing=True)
+            )).scalars().all()
+            assert len(custs) == 1
+            assert custs[0].owner_account_id == "wx_b"  # 档案 last-wins
+
+            links = (await session.execute(
+                sa.select(CustomerAccountLink).execution_options(populate_existing=True)
+            )).scalars().all()
+            assert {(l.owner_account_id, l.friend_remark) for l in links} == {
+                ("wx_a", "A的备注"), ("wx_b", "B的备注"),
+            }
+            by_owner = {l.owner_account_id: l for l in links}
+            assert by_owner["wx_a"].from_type == 1
+            assert by_owner["wx_b"].from_type == 2
+            assert by_owner["wx_a"].send_num == 10
+            assert by_owner["wx_a"].phone == "13800000000"
+    finally:
+        await engine.dispose()
+
+
+async def test_upsert_customer_without_owner_skips_link():
+    """无 owner_account_id 的档案 upsert(理论路径)只写 customer,不碰 link。"""
+    engine = await _make_engine()
+    try:
+        SessionLocal = async_sessionmaker(engine, expire_on_commit=False)
+        async with SessionLocal() as session:
+            await upsert_customer(session, {
+                "friend_id": "wxid_solo", "channel": "wechat",
+            })
+            await session.commit()
+            n_links = (await session.execute(
+                sa.select(sa.func.count()).select_from(CustomerAccountLink)
+            )).scalar_one()
+            assert n_links == 0
+    finally:
+        await engine.dispose()
+
+
+async def test_prune_customer_links_removes_departed():
+    """对账:保留名单外的 link 被删;空名单删光;他人名下不动。"""
+    engine = await _make_engine()
+    try:
+        SessionLocal = async_sessionmaker(engine, expire_on_commit=False)
+        async with SessionLocal() as session:
+            for owner, fid in [("wx_a", "f1"), ("wx_a", "f2"), ("wx_a", "f3"),
+                               ("wx_b", "f2")]:
+                await upsert_customer(session, {
+                    "friend_id": fid, "channel": "wechat",
+                    "owner_account_id": owner,
+                })
+            await session.commit()
+
+            deleted = await prune_customer_links(
+                session, channel="wechat", owner_account_id="wx_a",
+                keep_friend_ids=["f1", "f3"],
+            )
+            await session.commit()
+            assert deleted == 1
+
+            left = (await session.execute(
+                sa.select(CustomerAccountLink.friend_id, CustomerAccountLink.owner_account_id)
+            )).all()
+            assert set(left) == {("f1", "wx_a"), ("f3", "wx_a"), ("f2", "wx_b")}
+
+            # 空名单=该账号全部删除(wx_b 的保留)
+            deleted_all = await prune_customer_links(
+                session, channel="wechat", owner_account_id="wx_a",
+                keep_friend_ids=[],
+            )
+            await session.commit()
+            assert deleted_all == 2
+            left2 = (await session.execute(
+                sa.select(CustomerAccountLink.friend_id, CustomerAccountLink.owner_account_id)
+            )).all()
+            assert set(left2) == {("f2", "wx_b")}
+    finally:
+        await engine.dispose()
+
+
 async def test_upsert_customer_is_idempotent_and_updates_version():
     """Upsert same friend_id twice with different version -> 1 row, version updated."""
     engine = await _make_engine()

yunke-server/tests/test_scheduler_analytics_tick.py

@@ -1,4 +1,4 @@
-"""_analytics_tick:滚动刷新 + 增量扫描 + 异常吞掉(数据分析板块 v1, T11)。
+"""_analytics_tick:滚动刷新 + 增量扫描 + 管理域滚动段 + 异常吞掉(v1 T11;批次F F1)。
 
 行为测试是底线——start() 的 job 注册断言在 test_sync_scheduler.py 的
 注册测试里同步更新(那里 spy 断言 add_job 全集)。
@@ -15,6 +15,7 @@ from sqlalchemy.pool import StaticPool
 
 from app.db.base import Base
 from app.db.models import MsgDailyStats, SensitiveWord, StatDailyStaff
+from app.storage.staff_summary import rolling_days
 from app.storage.summary import day_key
 from app.sync.scheduler import SyncScheduler
 
@@ -74,3 +75,110 @@ async def test_analytics_tick_swallows_errors(sched_engine, monkeypatch, caplog)
     with caplog.at_level(logging.ERROR, logger="app.sync.scheduler"):
         await sch._analytics_tick()  # 不抛
     assert any("analytics tick failed" in r.getMessage() for r in caplog.records)
+
+
+async def _seed_today(sched_engine) -> int:
+    """seed 当日一条 wechat friend 会话 + 敏感词,返回 seed 用的 day 键。"""
+    _, maker = sched_engine
+    today = day_key(int(time.time() * 1000))
+    async with maker() as s:
+        s.add(MsgDailyStats(channel="wechat", owner_account_id="wx1",
+                            peer_kind="friend", peer_id="t1", day=today,
+                            send_cnt=1, recv_cnt=0, last_ts=1756950000000,
+                            last_is_send=True))
+        s.add(SensitiveWord(word="私单"))
+        await s.commit()
+    return today
+
+
+async def test_tick_calls_management_chain_in_order(sched_engine, monkeypatch):
+    """两段链完整顺序:recompute_days → scan → pairs_active_in_days →
+    recompute_pairs → recompute_metric_days → recompute_call_days。
+
+    记录桩替换全部六个上游——_analytics_tick 段内函数延迟 import,
+    monkeypatch 模块属性即命中(惯例见 test_analytics_tick_swallows_errors)。
+    """
+    engine, maker = sched_engine
+    calls: list[str] = []
+
+    def rec(name: str, ret):
+        async def _stub(*args, **kwargs):
+            calls.append(name)
+            return ret
+        return _stub
+
+    monkeypatch.setattr("app.storage.staff_summary.recompute_days",
+                        rec("recompute_days", 0))
+    monkeypatch.setattr("app.analytics.sensitive.scanner.run_incremental",
+                        rec("scan", {"scanned": 0, "hits": 0}))
+    monkeypatch.setattr("app.storage.first_reply_facts.pairs_active_in_days",
+                        rec("pairs_active_in_days", []))
+    monkeypatch.setattr("app.storage.first_reply_facts.recompute_pairs",
+                        rec("recompute_pairs", 0))
+    monkeypatch.setattr("app.storage.employee_metrics.recompute_metric_days",
+                        rec("recompute_metric_days", 0))
+    monkeypatch.setattr("app.storage.employee_metrics.recompute_call_days",
+                        rec("recompute_call_days", 0))
+
+    sch = SyncScheduler(engine=engine, session_maker=maker)
+    await sch._analytics_tick()
+    assert calls == [
+        "recompute_days", "scan",                                   # 段1
+        "pairs_active_in_days", "recompute_pairs",                  # 段2
+        "recompute_metric_days", "recompute_call_days",
+    ]
+
+
+async def test_tick_management_failure_isolated(sched_engine, monkeypatch, caplog):
+    """段2 失败隔离:recompute_metric_days 抛 RuntimeError → ①tick 不抛;
+    ②记 "management metrics tick failed";③段1 已提交的 StatDailyStaff
+    不被段2 回滚(两段独立事务)。
+    """
+    engine, maker = sched_engine
+    await _seed_today(sched_engine)
+
+    async def _boom(*args, **kwargs):
+        raise RuntimeError("boom")
+
+    monkeypatch.setattr("app.storage.employee_metrics.recompute_metric_days", _boom)
+    sch = SyncScheduler(engine=engine, session_maker=maker)
+    with caplog.at_level(logging.ERROR, logger="app.sync.scheduler"):
+        await sch._analytics_tick()  # ①不抛
+    assert any(  # ②段2 独立记日志
+        "management metrics tick failed" in r.getMessage() for r in caplog.records
+    )
+    async with maker() as s:  # ③段1 结果已提交
+        n = (await s.execute(
+            select(func.count()).select_from(StatDailyStaff)
+        )).scalar_one()
+        assert n >= 1
+
+
+async def test_tick_management_rolling_window(sched_engine, monkeypatch):
+    """管理域三函数收到的 days == rolling_days(today, 3)(长度 3,当日+前
+    两天),且与 staff 段捕获的窗口一致(两段共用函数顶提取的同一 today)。
+    """
+    engine, maker = sched_engine
+    got: dict[str, list[int]] = {}
+
+    def cap(name: str, ret):
+        async def _stub(session, days, *args, **kwargs):
+            got[name] = list(days)
+            return ret
+        return _stub
+
+    monkeypatch.setattr("app.storage.staff_summary.recompute_days",
+                        cap("staff", 0))
+    monkeypatch.setattr("app.storage.first_reply_facts.pairs_active_in_days",
+                        cap("pairs", []))
+    monkeypatch.setattr("app.storage.employee_metrics.recompute_metric_days",
+                        cap("wide", 0))
+    monkeypatch.setattr("app.storage.employee_metrics.recompute_call_days",
+                        cap("call", 0))
+
+    sch = SyncScheduler(engine=engine, session_maker=maker)
+    await sch._analytics_tick()
+
+    rd = rolling_days(day_key(int(time.time() * 1000)), 3)
+    assert len(rd) == 3  # 当日 + 前两天
+    assert got["staff"] == got["pairs"] == got["wide"] == got["call"] == rd

yunke-server/tests/test_sync_scheduler.py

@@ -572,7 +572,12 @@ async def test_safe_page_run_full_invokes_bash_full_sync(engine, monkeypatch):
 
 
 async def test_safe_page_run_messages_builds_scrape_command(engine, monkeypatch):
-    """messages job = friends→wa-friends→四类消息→moments 浅扫的命令序列。"""
+    """messages job = accounts→friends→四类消息(活跃窗)→moments 浅扫的命令序列。
+
+    2026-09-10 调度根治:头部刷员工账号表(员工列表时间最多滞后 4h);
+    消息实体只扫近 24h 活跃对话(--active-window-hours 24,防序列 15h+
+    挤死 full);陈旧对话每日 full 兜底。
+    """
     sched = SyncScheduler(engine=engine, max_conversations_per_run=123)
     commands: list[list[str]] = []
 
@@ -584,22 +589,26 @@ async def test_safe_page_run_messages_builds_scrape_command(engine, monkeypatch)
 
     await sched._safe_page_run("messages")
 
-    # 2026-08-21: messages job 是 friends→wa-friends→四类消息的命令序列,
+    assert len(commands) == 10
-    # 每条都调 scrape_via_page.py;2026-08-25 末尾追加 moments 浅扫
-    assert len(commands) == 7
     for args in commands:
         assert args[1].endswith("scrape_via_page.py")
 
     def entity_of(args: list[str]) -> str:
         return args[args.index("--entity") + 1]
 
-    assert entity_of(commands[0]) == "friends"
+    # 头部:账号刷新(员工列表「数据更新/最新消息时间」来源)
-    assert entity_of(commands[1]) == "wa-friends"
+    assert entity_of(commands[0]) == "accounts"
-    for args in commands[2:6]:
+    assert entity_of(commands[1]) == "wa-accounts"
-        assert entity_of(args) in (
+    assert entity_of(commands[2]) == "friends"
-            "messages", "wa-messages", "group-messages", "wa-group-messages",
+    assert entity_of(commands[3]) == "wa-friends"
-        )
+    # 群消息前刷群活跃(chatroom-stats 全窗——群活跃窗判定源,2026-09-10)
+    entities_seq = [entity_of(a) for a in commands]
+    assert entities_seq.index("chatroom-stats") < entities_seq.index("group-messages")
+    # 四类消息:24h 活跃窗(2026-09-10 根治调度堵塞)
+    for args in commands:
+        if entity_of(args) in ("messages", "wa-messages", "group-messages", "wa-group-messages"):
             assert args[args.index("--max-conversations") + 1] == "99999"
+            assert args[args.index("--active-window-hours") + 1] == "24"
     # moments 浅扫在序列末尾:每员工最多 3 页
     moments_cmd = commands[-1]
     assert entity_of(moments_cmd) == "moments"

yunkes/src/api/index.ts

@@ -178,6 +178,14 @@ export interface GroupQuery {
   room_id?: string
   /** 群名称模糊搜索(通讯录群 tab 搜索框)。 */
   q?: string
+  /** 群备注子串(微信群统计筛选)。 */
+  group_remark?: string
+  /** 最新消息时间段(ms,含端点)。 */
+  last_start?: number
+  last_end?: number
+  /** 统计时段(ms,含端点)——窗内输出沟通消息数/新增/退出成员数聚合。 */
+  msg_start?: number
+  msg_end?: number
   page?: number
   page_size?: number
 }
@@ -191,6 +199,11 @@ export function getGroups(query: GroupQuery = {}): Promise<Page<Group>> {
       user_id: query.user_id,
       room_id: query.room_id,
       q: query.q,
+      group_remark: query.group_remark,
+      last_start: query.last_start,
+      last_end: query.last_end,
+      msg_start: query.msg_start,
+      msg_end: query.msg_end,
       page: query.page ?? 1,
       page_size: query.page_size ?? 20,
     }),

yunkes/src/api/management.ts

@@ -0,0 +1,107 @@
+// 经营管理板块 API(批次C)。契约以批次B终评冻结面为准:
+// None≠0(无样本分位/率=null);scope.channel 回显原值;drilldown 白名单六值。
+// 已对照批次B as-built(management.py/api_assembly.py)逐键核对:
+// - dashboard 另有 caliber_notes(总述口径说明,Record<string,string>)
+// - drilldown 各分支均返回 page/page_size/scope(与 items/total 同层)
+// - first_reply_* 行含 chat_hint(owner+talker 直达聊天记录)
+// - lifecycle 行 nickname 恒非空(后端 friend_nickname→remark→friend_id 兜底)
+import { getJson } from './client'
+import type { Channel } from './types'
+
+export type MgmtChannel = 'all' | Channel
+export type CompareMode = 'previous' | 'personal_baseline' | 'team_median'
+export type DrilldownCode =
+  | 'first_reply_p90' | 'first_reply_p50' | 'unreplied'
+  | 'cooling_customers' | 'dormant_customers' | 'call_followup'
+
+export interface MgmtScope { channel: MgmtChannel; start: number; end: number; compare?: CompareMode; view?: string; user_id?: string; metric_code?: string }
+export interface Kpis {
+  active_customers: number; active_employees: number
+  msg_total: number; cust_threads: number; threads_answered: number
+  call_count: number; call_seconds: number; answered_call: number
+  lifecycle: { new: number; cooling: number; dormant: number; reactivated: number }
+}
+export interface CommTrendPoint { day: number; msg_total: number; active_customers: number; call_cnt: number }
+export interface SvcTrendPoint { day: number; fr_p50_ms: number | null; fr_p90_ms: number | null; reply_2h_rate: number | null }
+export interface DimSummary { [dim: string]: { name: string; weight: number; scored_count: number; pending_count: number; insufficient_count: number; avg_score: number | null } }
+export interface AnomalyCard {
+  rule_code: string; severity: 'critical' | 'warning'; employee_user_id: string
+  // dashboard 端点 enrich(批次D,跳员工详情用);员工详情端点不带
+  employee_name?: string
+  title: string; current_value: number; baseline_value: number | null; unit: string
+  sample_size: number; affected_count: number; reason: string
+  drilldown: { type: string; query: { metric_code?: string; user_id?: string } }
+  suggested_action: string
+}
+export interface DashboardResp {
+  scope: MgmtScope; data_as_of: number | null; metric_version: string; config_source: 'db' | 'default'
+  kpis: Kpis
+  // 前窗环比块(批次D):prev 窗同式聚合;可选防御旧缓存响应
+  prev_kpis?: Pick<Kpis, 'active_customers' | 'active_employees' | 'msg_total' | 'cust_threads'>
+  msg_delta?: number | null // (msg_total-prev)/prev,prev=0 → null;客户端三卡自算,此键备用
+  communication_trend: CommTrendPoint[]
+  service_trend: SvcTrendPoint[]
+  lifecycle: Kpis['lifecycle']
+  dimension_summary: DimSummary
+  anomalies: AnomalyCard[]
+  action_summary: { unreplied_2h: number; churn_real_30d: number; sensitive_pending: number }
+  caliber_notes: Record<string, string>
+}
+export interface EmployeeRow {
+  user_id: string; name: string | null; is_on_job: boolean | null
+  // metrics=PeriodMetrics._asdict():数值字段外的 user_id 键是字符串(透传
+  // 字段,UI 取身份用顶层 row.user_id,动态取数只碰数值键)
+  metrics: Record<string, number | null>
+  comparisons: Record<string, { current: number | null; prev: number | null; baseline: number | null; median: number | null }>
+  score: { total_score: number | null; grade: string | null; score_status: string; trial: boolean; dimensions: Record<string, { score: number | null; status: string }> }
+  anomaly_count: number; anomaly_weight: number
+}
+export interface EmployeesResp { total: number; page: number; page_size: number; rows: EmployeeRow[]; scope: MgmtScope; data_as_of: number | null; metric_version: string; config_source: 'db' | 'default' }
+export interface FactDrillRow { day: number; channel: string; owner_account_id: string; peer_id: string; thread_end_ts: number; reply_ts: number; fr_ms: number; chat_hint: { owner_account_id: string; talker_id: string } }
+export interface LifecycleDrillRow { friend_id: string; channel: string; nickname: string; last_day: number; state: string }
+export interface CallDrillRow { call_id: string; channel: string; call_number: string | null; start_call_time: number; call_duration: number }
+export interface DrilldownResp { total: number; page: number; page_size: number; scope: MgmtScope; items: Record<string, unknown>[]; note?: string; truncated?: boolean; summary?: Record<string, number> }
+export interface MetricDefsResp {
+  definitions: Record<string, { name: string; unit: string; direction: number; caliber?: string; formula?: string }>
+  score_config: { version: string; name: string; trial: boolean; normalization: string; sample_guards: Record<string, number>; grade_bounds: Record<string, number>; dimensions: Record<string, { name: string; weight: number; status?: string }> }
+  caliber_notes: string
+  config_source: 'db' | 'default'
+}
+
+export const getDashboard = (channel: MgmtChannel, start: number, end: number, compare: CompareMode = 'previous') =>
+  getJson<DashboardResp>('/management/dashboard', { channel, start, end, compare })
+export const getEmployees = (params: Record<string, unknown>) =>
+  getJson<EmployeesResp>('/management/employees', params)
+export const getEmployeeDrilldown = (userId: string, metricCode: DrilldownCode, start: number, end: number, channel: MgmtChannel, page = 1, pageSize = 20) =>
+  getJson<DrilldownResp>(`/management/employees/${userId}/drilldown`, { metric_code: metricCode, start, end, channel, page, page_size: pageSize })
+export const getMetricDefs = () => getJson<MetricDefsResp>('/management/metric-definitions')
+
+// ---- 批次D:员工详情 + 分段指标(契约已真机 8000 抽查核对,见上) ----
+export interface EmployeeAccount { channel: string; account_id: string; nick_name: string | null; user_name: string | null }
+export interface ScoreMetricDetail { value: number | null; prev: number | null; baseline: number | null; median: number | null; sample_size: number; sample_status: string; score: number | null; unit: string; name: string }
+// formula_note 在 dimensions[dim].metrics[code] 上(scoring 维度级明细),不在 metrics_detail
+export interface EmployeeDetailResp {
+  user_id: string; name: string | null; is_on_job: boolean | null
+  accounts: EmployeeAccount[]
+  metrics: Record<string, number | string | null>
+  score: {
+    total_score: number | null; grade: string | null; score_status: string; trial: boolean
+    dimensions: Record<string, { name: string; weight: number; score: number | null; status: string; metrics?: Record<string, { value: number | null; score: number | null; sample_size: number; sample_status: string; formula_note?: string }> }>
+    metrics_detail: Record<string, ScoreMetricDetail>
+  }
+  anomalies: AnomalyCard[]
+  prev: Record<string, number | string | null> | null
+  baseline: Record<string, number | string | null> | null
+  scope: MgmtScope; data_as_of: number | null; metric_version: string; config_source: 'db' | 'default'
+}
+export interface SectionResp {
+  section: string; metrics: Record<string, number | null>
+  trend: Record<string, number | null>[]
+  comparisons: Record<string, { current: number | null; prev: number | null; baseline: number | null; median: number | null }>
+  scope: MgmtScope; data_as_of: number | null; metric_version: string
+}
+export type MetricsSection = 'overview' | 'service' | 'customer' | 'workload' | 'calls'
+export const getEmployeeDetail = (userId: string, channel: MgmtChannel, start: number, end: number) =>
+  getJson<EmployeeDetailResp>(`/management/employees/${userId}`, { channel, start, end })
+export const getEmployeeMetrics = (userId: string, section: MetricsSection, channel: MgmtChannel, start: number, end: number) =>
+  getJson<SectionResp>(`/management/employees/${userId}/metrics`, { section, channel, start, end })

yunkes/src/api/types.ts

@@ -33,6 +33,12 @@ export interface Customer {
   /** 今日发送/接收条数(本地消息聚合,对齐云客今日口径)。 */
   send_today?: number | null
   receive_today?: number | null
+  /** 累计发送/接收条数(同步自云客 friend 记录 sendNum/receiveNum;员工客户页列)。 */
+  send_num?: number | null
+  receive_num?: number | null
+  /** 云客数据来源代码(customer_account_link 员工维度路径直读;档案路径空,
+   *  前端回退 raw_json.fromType)。 */
+  from_type?: number | null
   /** ms epoch of friend add time (from raw_json.addTime). */
   add_time?: number | null
   message_count?: number | null
@@ -107,6 +113,19 @@ export interface Group {
   friend_count?: number | null
   /** 建群时间 ms-epoch */
   create_time?: number | null
+  /** 群备注(微信群统计页;getChatroomList.remark,2026-09-09) */
+  group_remark?: string | null
+  /** 员工微信列(getChatroomList 同款):昵称/微信号/头像 */
+  staff_nickname?: string | null
+  staff_wx_alias?: string | null
+  staff_avatar?: string | null
+  /** 员工信息列:姓名/手机(staff 关联) */
+  staff_name?: string | null
+  staff_phone?: string | null
+  /** 统计时段窗内聚合(仅请求带 msg_start/msg_end 时非 null) */
+  window_msg_count?: number | null
+  window_added?: number | null
+  window_lost?: number | null
   /**
    * Verbatim upstream chatroom record (camelCase keys: chatRoomId/chatRoomName,
    * memberCount/memberIds, headImageUrl, wechatId/wechatNickName, userName/

yunkes/src/components/management/AnomalyList.vue

@@ -0,0 +1,136 @@
+<template>
+  <el-table
+    v-loading="loading"
+    :data="anomalies"
+    :row-class-name="rowClass"
+    @row-click="onRowClick"
+  >
+    <el-table-column label="级别" width="70" align="center">
+      <template #default="{ row }">
+        <el-tag v-if="row.severity === 'critical'" type="danger" size="small">严重</el-tag>
+        <el-tag v-else type="warning" size="small">关注</el-tag>
+      </template>
+    </el-table-column>
+    <el-table-column label="异常" min-width="240">
+      <template #default="{ row }">
+        <div class="cell-title">{{ row.title }}</div>
+        <div v-if="showEmployee" class="cell-emp">
+          <el-link
+            type="primary"
+            underline="never"
+            @click.stop="goEmployee(row)"
+          >{{ row.employee_name || row.employee_user_id.slice(0, 8) }}</el-link>
+        </div>
+        <div class="cell-sub">{{ row.reason }}</div>
+      </template>
+    </el-table-column>
+    <el-table-column label="当前值" width="150">
+      <template #default="{ row }">
+        <div>{{ formatValue(row.current_value, row.unit) }}</div>
+        <div class="cell-sub">
+          {{ row.baseline_value === null ? '无基线' : `基线 ${formatValue(row.baseline_value, row.unit)}` }}
+        </div>
+      </template>
+    </el-table-column>
+    <el-table-column label="样本" prop="sample_size" align="right" width="80" />
+    <el-table-column label="影响" align="right" width="90">
+      <template #default="{ row }">
+        <span :class="{ 'affected-hot': row.affected_count >= 50 }">{{ row.affected_count }}</span>
+      </template>
+    </el-table-column>
+    <el-table-column label="建议动作" min-width="180" show-overflow-tooltip>
+      <template #default="{ row }">
+        <span class="cell-sub">{{ row.suggested_action }}</span>
+      </template>
+    </el-table-column>
+    <template #empty>
+      <el-empty description="暂无异常" :image-size="60" />
+    </template>
+  </el-table>
+</template>
+
+<script setup lang="ts">
+// 异常榜(批次C 驾驶舱):后端 AnomalyCard[] 平铺表——级别 tag/标题+员工行
+// (showEmployee,批次D:employee_name 链接→员工详情,.stop 防触发行下钻)
+// +原因/单位感知当前值+基线/样本/影响(≥50 红显)/建议动作。行 click 打开
+// 下钻抽屉(emit drill,抽屉自治加载);critical 整行淡红底提示优先处置。
+// 纯展示+事件,不取数。
+import { useRoute, useRouter } from 'vue-router'
+import { formatMsDuration, formatRatio } from '@/utils/format'
+import type { AnomalyCard } from '@/api/management'
+
+// showEmployee(默认 true):驾驶舱异常榜显示员工行;员工详情页复用本组件
+// 传 false(自指链接无意义)
+withDefaults(
+  defineProps<{
+    anomalies: AnomalyCard[]
+    loading?: boolean
+    showEmployee?: boolean
+  }>(),
+  { showEmployee: true },
+)
+
+const emit = defineEmits<{
+  (e: 'drill', card: AnomalyCard): void
+}>()
+
+const route = useRoute()
+const router = useRouter()
+
+// 员工链接:带当前 URL query(channel/start/end/compare 随行,与列表
+// goDetail 带窗进详情同语义);detail 页对白名单外 query 键不敏感
+function goEmployee(row: AnomalyCard): void {
+  router.push({
+    path: `/management/employees/${row.employee_user_id}`,
+    query: route.query,
+  })
+}
+
+// 单位感知格式化:ms→时长,0-1→比率,其余千分位(与指标口径字典 unit 对齐)
+function formatValue(v: number, unit: string): string {
+  if (unit === 'ms') return formatMsDuration(v)
+  if (unit === '0-1') return formatRatio(v)
+  return v.toLocaleString()
+}
+
+function rowClass({ row }: { row: AnomalyCard }): string {
+  return row.severity === 'critical'
+    ? 'anomaly-critical-row yk-clickable-row'
+    : 'yk-clickable-row'
+}
+
+function onRowClick(row: AnomalyCard): void {
+  emit('drill', row)
+}
+</script>
+
+<style scoped>
+/* critical 行整行淡红底(优先处置);hover 深一档由 EP 行 hover 自带 */
+:deep(.el-table .anomaly-critical-row) {
+  background-color: var(--el-color-danger-light-9);
+}
+:deep(.el-table .anomaly-critical-row:hover > td.el-table__cell) {
+  background-color: var(--el-color-danger-light-8);
+}
+.cell-title {
+  font-size: 13px;
+  color: var(--el-text-color-primary);
+}
+.cell-emp {
+  font-size: 12px;
+  margin-top: 2px;
+  line-height: 1.4;
+}
+.cell-emp .el-link {
+  font-size: 12px;
+}
+.cell-sub {
+  font-size: 12px;
+  color: var(--el-text-color-secondary);
+  margin-top: 2px;
+}
+.affected-hot {
+  color: var(--el-color-danger);
+  font-weight: 600;
+}
+</style>

yunkes/src/components/management/DataAsOfBadge.vue

@@ -0,0 +1,49 @@
+<template>
+  <span class="data-asof">
+    <el-tag v-if="asOfText" size="small" type="info" effect="plain">数据截至 {{ asOfText }}</el-tag>
+    <el-tag v-else size="small" type="info">无数据</el-tag>
+    <el-tag
+      v-if="metricVersion"
+      size="small"
+      effect="plain"
+      class="asof-tag"
+      :title="configSource === 'db' ? '口径配置：自定义(数据库)' : '口径配置：默认'"
+    >口径 {{ metricVersion }}</el-tag>
+    <el-tag v-if="trial" size="small" type="warning" class="asof-tag">试算</el-tag>
+  </span>
+</template>
+
+<script setup lang="ts">
+// 数据截至角标(批次C 驾驶舱/员工页共用):数据时间 + 指标版本 + 试算标记。
+// 纯展示——数据由父级从 dashboard/employees 载荷透传(data_as_of/metric_version/
+// trial/config_source),不自行请求。configSource 无独立标签(避免噪音),
+// 挂在口径版本 tag 的 title 提示上。
+import { computed } from 'vue'
+import { formatTime } from '@/utils/format'
+
+const props = defineProps<{
+  dataAsOf?: number | null
+  metricVersion?: string
+  trial?: boolean
+  configSource?: 'db' | 'default'
+}>()
+
+// ms 时间戳 → `YYYY-MM-DD HH:mm`(formatTime 去秒);缺失/非法 → 灰 tag「无数据」
+const asOfText = computed(() => {
+  const v = props.dataAsOf
+  if (v == null || !Number.isFinite(v) || v <= 0) return ''
+  return formatTime(v).slice(0, 16)
+})
+</script>
+
+<style scoped>
+.data-asof {
+  display: inline-flex;
+  align-items: center;
+  gap: 6px;
+  white-space: nowrap;
+}
+.asof-tag {
+  margin-left: 0;
+}
+</style>

yunkes/src/components/management/EmployeeCompareDrawer.vue

@@ -0,0 +1,169 @@
+<template>
+  <el-drawer
+    :model-value="modelValue"
+    title="员工对比"
+    size="620px"
+    @update:model-value="emit('update:modelValue', $event)"
+  >
+    <!-- v1 §6.6:对比只呈现可验证差异,不产生优劣结论(管理者需被提醒) -->
+    <el-alert
+      type="info"
+      :closable="false"
+      title="同口径同时窗对比，仅呈现可验证差异，不产生优劣结论"
+      class="cmp-alert"
+    />
+
+    <!-- ① 维度对比:三可用维度,每人一行横向 bar(0-100;无样本灰「--」) -->
+    <div v-for="dim in DIMS" :key="dim.key" class="dim-block">
+      <div class="dim-title">{{ dim.label }}</div>
+      <div v-for="r in rows" :key="r.user_id" class="dim-row">
+        <span class="dim-name" :title="r.user_id">{{ displayName(r) }}</span>
+        <template v-if="dimScore(r, dim.key) !== null">
+          <div class="dim-track">
+            <div class="dim-bar" :style="{ width: `${dimScore(r, dim.key)}%` }" />
+          </div>
+          <span class="dim-score">{{ Math.round(dimScore(r, dim.key) ?? 0) }}</span>
+        </template>
+        <span v-else class="dim-na">--</span>
+      </div>
+    </div>
+
+    <!-- ② 关键指标表:行=指标,列=每人 -->
+    <el-table :data="metricRows" size="small" border class="cmp-table">
+      <el-table-column prop="label" label="指标" min-width="96" />
+      <el-table-column
+        v-for="r in rows"
+        :key="r.user_id"
+        align="right"
+        min-width="88"
+      >
+        <template #header>
+          <span :title="r.user_id">{{ displayName(r) }}</span>
+        </template>
+        <template #default="{ row }">{{ row.values[r.user_id] }}</template>
+      </el-table-column>
+    </el-table>
+  </el-drawer>
+</template>
+
+<script setup lang="ts">
+// 员工对比抽屉(批次D):总览页勾选 2-5 人后并排看维度分与关键指标。
+// 只读展示——数据来自已选行快照(EmployeeRow),不二次请求;口径/时窗与
+// 总览页完全一致(同载荷),故顶部钉 v1 §6.6 提示:仅呈现可验证差异。
+import { computed } from 'vue'
+import type { EmployeeRow } from '@/api/management'
+import { formatMsDuration, formatRatio } from '@/utils/format'
+
+const props = defineProps<{
+  modelValue: boolean
+  /** 已勾选行(2-5,由父级按钮门槛保证);行是勾选时的快照,翻页/重查不影响 */
+  rows: EmployeeRow[]
+}>()
+
+const emit = defineEmits<{
+  (e: 'update:modelValue', v: boolean): void
+}>()
+
+// 一期可用三维度(action/risk pending_data 不参与)
+const DIMS = [
+  { key: 'customer', label: '客户经营' },
+  { key: 'service', label: '服务质量' },
+  { key: 'workload', label: '工作负载' },
+] as const
+
+function displayName(r: EmployeeRow): string {
+  return r.name || r.user_id.slice(0, 8)
+}
+
+function dimScore(r: EmployeeRow, key: string): number | null {
+  return r.score.dimensions[key]?.score ?? null
+}
+
+// metrics 取数值键(user_id 透传键是字符串,typeof 守卫掉)
+function num(r: EmployeeRow, key: string): number | null {
+  const v = r.metrics[key]
+  return typeof v === 'number' ? v : null
+}
+
+function ratio(numV: number | null, den: number | null): string {
+  if (!den) return '--' // 分母 0/null → 无率(严格区分 0%)
+  return formatRatio(numV == null ? null : numV / den)
+}
+
+interface CmpMetricRow {
+  label: string
+  values: Record<string, string>
+}
+
+const metricRows = computed<CmpMetricRow[]>(() => {
+  const mk = (label: string, fmt: (r: EmployeeRow) => string): CmpMetricRow => {
+    const values: Record<string, string> = {}
+    for (const r of props.rows) values[r.user_id] = fmt(r)
+    return { label, values }
+  }
+  return [
+    mk('活跃客户', (r) => String(num(r, 'active_friends') ?? '--')),
+    mk('消息量', (r) => String((num(r, 'msg_sent') ?? 0) + (num(r, 'msg_recv') ?? 0))),
+    mk('首响P90', (r) => formatMsDuration(num(r, 'fr_p90_ms'))),
+    mk('2h回复率', (r) => ratio(num(r, 'reply_2h_count'), num(r, 'cust_threads'))),
+    mk('异常数', (r) => String(r.anomaly_count)),
+  ]
+})
+</script>
+
+<style scoped>
+.cmp-alert {
+  margin-bottom: 16px;
+}
+.dim-block {
+  margin-bottom: 16px;
+}
+.dim-title {
+  font-size: 13px;
+  font-weight: 600;
+  color: var(--el-text-color-primary);
+  margin-bottom: 6px;
+}
+.dim-row {
+  display: flex;
+  align-items: center;
+  gap: 8px;
+  margin-bottom: 4px;
+}
+.dim-name {
+  width: 88px;
+  flex: none;
+  font-size: 13px;
+  color: var(--el-text-color-regular);
+  overflow: hidden;
+  text-overflow: ellipsis;
+  white-space: nowrap;
+}
+.dim-track {
+  flex: 1;
+  height: 12px;
+  border-radius: 6px;
+  background: var(--el-fill-color-light);
+  overflow: hidden;
+}
+.dim-bar {
+  height: 100%;
+  border-radius: 6px;
+  background: var(--el-color-primary);
+}
+.dim-score {
+  width: 28px;
+  flex: none;
+  text-align: right;
+  font-size: 12px;
+  color: var(--el-text-color-regular);
+}
+.dim-na {
+  flex: 1;
+  font-size: 12px;
+  color: var(--el-text-color-placeholder);
+}
+.cmp-table {
+  margin-top: 4px;
+}
+</style>

yunkes/src/components/management/ManagementFilterBar.vue

@@ -0,0 +1,111 @@
+<template>
+  <div class="mgmt-filter-bar">
+    <el-radio-group :model-value="channel" @change="onChannelChange">
+      <el-radio-button v-for="c in CHANNELS" :key="c.value" :value="c.value">{{ c.label }}</el-radio-button>
+    </el-radio-group>
+
+    <el-select
+      v-model="preset"
+      class="preset-select"
+      placeholder="近30天"
+      @change="onPresetChange"
+    >
+      <el-option-group label="常用">
+        <el-option label="今日" value="today" />
+        <el-option label="昨日" value="yesterday" />
+        <el-option label="近7天" value="last7" />
+        <el-option label="近30天" value="last30" />
+      </el-option-group>
+      <el-option-group label="日历">
+        <el-option label="本周" value="thisWeek" />
+        <el-option label="上周" value="lastWeek" />
+        <el-option label="本月" value="thisMonth" />
+        <el-option label="上月" value="lastMonth" />
+      </el-option-group>
+      <el-option label="自定义" value="custom" />
+    </el-select>
+
+    <!-- 自定义区间:daterange 自保证 start≤end,选完才 emit;value-format
+         直接给 yyyymmdd 字符串,转 number 走 URL 真源 -->
+    <el-date-picker
+      v-if="preset === 'custom'"
+      v-model="customRange"
+      type="daterange"
+      size="small"
+      range-separator="至"
+      start-placeholder="开始日期"
+      end-placeholder="结束日期"
+      value-format="YYYYMMDD"
+      :clearable="false"
+      style="width: 240px"
+      @change="onCustomRange"
+    />
+
+    <div class="spacer" />
+    <el-button text type="primary" @click="emit('open-defs')">指标口径</el-button>
+    <slot name="aside" />
+  </div>
+</template>
+
+<script setup lang="ts">
+// 管理页统一筛选栏(批次C):渠道 + 时间预设/自定义区间 + 指标口径入口。
+// 受控组件——channel/start/end 来自父级(useManagementFilters 的 URL 真源
+// computed),变更只 emit apply(patch) 由父写回 URL,组件不实例化 composable
+// (只 import CHANNELS/presetRange 常量,避免二次 useRoute/useRouter)。
+//
+// 预设选中值:内部 ref 记用户最近选择,初始 null 显示 placeholder「近30天」,
+// 不与 URL 双向同步(URL 直接访问无 start/end 时默认即 last30,placeholder
+// 恰好如实)。非 custom 预设把 presetRange 计算出的具体日期 emit 给父——
+// URL 真源可分享/刷新,且选中项与实际窗口一致(composable 的默认(last30)
+// 无法表达 last7/本月/上月,只清 start/end 会静默回落 30 天窗)。
+import { ref } from 'vue'
+import { CHANNELS, presetRange, type Preset } from '@/composables/useManagementFilters'
+
+defineProps<{
+  channel: string
+  start: number
+  end: number
+  /** 预留(对比模式选择器未上),父级透传保持 props 面完整 */
+  compare?: string
+}>()
+
+const emit = defineEmits<{
+  (e: 'apply', patch: { channel?: string; start?: number; end?: number }): void
+  (e: 'open-defs'): void
+}>()
+
+// 用户最近选择的预设;null = 未选(placeholder 近30天)。custom 选完后保持,
+// 日期改动走 onCustomRange 增量 emit。
+const preset = ref<Preset | null>(null)
+const customRange = ref<[string, string] | null>(null)
+
+function onChannelChange(v: string | number | boolean): void {
+  emit('apply', { channel: String(v) })
+}
+
+function onPresetChange(v: string): void {
+  if (v === 'custom') return // 等 daterange 选完区间再 emit
+  emit('apply', presetRange(v as Preset))
+}
+
+function onCustomRange(): void {
+  const r = customRange.value
+  if (!r?.[0] || !r?.[1]) return // 未选完区间不请求
+  emit('apply', { start: Number(r[0]), end: Number(r[1]) })
+}
+</script>
+
+<style scoped>
+.mgmt-filter-bar {
+  display: flex;
+  align-items: center;
+  gap: 12px;
+  flex-wrap: wrap;
+}
+.preset-select {
+  width: 120px;
+}
+.spacer {
+  flex: 1;
+}
+</style>

yunkes/src/components/management/ManagementKpiCard.vue

@@ -0,0 +1,94 @@
+<template>
+  <el-card shadow="never" class="kpi-card" :class="{ link: !!to }" @click="onClick">
+    <div class="kpi-label">{{ label }}</div>
+    <div class="kpi-value" :class="{ danger }">
+      {{ valueText }}<span v-if="unit && value !== null" class="kpi-unit">{{ unit }}</span>
+    </div>
+    <div v-if="deltaText" class="kpi-delta" :class="deltaClass">
+      环比{{ deltaText }}
+    </div>
+    <div v-if="hint" class="kpi-hint">{{ hint }}</div>
+  </el-card>
+</template>
+
+<script setup lang="ts">
+// 经营管理 KPI 卡:label 上小灰字 + 主值大号字(千分位/unit 后缀/danger 红)
+// + 环比行(批次D,delta prop)+ hint 下小灰字。to 存在时整卡可点
+// (hover 手型)跳转——纯展示+导航,不取数。null 值语义(无样本)显 `--`,
+// 由父级决定传 null。
+import { computed } from 'vue'
+import { useRouter } from 'vue-router'
+
+const props = defineProps<{
+  label: string
+  value: number | null
+  unit?: string
+  hint?: string
+  to?: string
+  danger?: boolean
+  // 较前窗环比 (cur-prev)/prev:null/undefined/NaN(前窗缺数据)不显示。
+  // 只支持升好语义(升绿↓红)——本批接入三卡(活跃客户/活跃员工/消息量)
+  // 均为越高越好;将来若有降好指标(如首响时长)需先加方向语义位
+  delta?: number | null
+}>()
+
+const router = useRouter()
+
+const valueText = computed(() => (props.value === null ? '--' : props.value.toLocaleString()))
+
+const deltaText = computed(() => {
+  if (props.delta == null || !Number.isFinite(props.delta)) return null
+  const arrow = props.delta > 0 ? '↑' : props.delta < 0 ? '↓' : '→'
+  return `${arrow}${(Math.abs(props.delta) * 100).toFixed(1)}%`
+})
+const deltaClass = computed(() =>
+  props.delta == null || !Number.isFinite(props.delta)
+    ? ''
+    : props.delta > 0 ? 'up' : props.delta < 0 ? 'down' : 'flat')
+
+function onClick(): void {
+  if (props.to) router.push(props.to)
+}
+</script>
+
+<style scoped>
+.kpi-card.link {
+  cursor: pointer;
+}
+.kpi-label {
+  color: var(--el-text-color-secondary);
+  font-size: 13px;
+}
+.kpi-value {
+  font-size: 26px;
+  font-weight: 600;
+  margin: 6px 0 2px;
+  color: var(--el-text-color-primary);
+}
+.kpi-value.danger {
+  color: var(--el-color-danger);
+}
+.kpi-unit {
+  font-size: 13px;
+  font-weight: 400;
+  color: var(--el-text-color-secondary);
+  margin-left: 2px;
+}
+.kpi-delta {
+  font-size: 12px;
+  margin-bottom: 2px;
+}
+.kpi-delta.up {
+  color: var(--el-color-success);
+}
+.kpi-delta.down {
+  color: var(--el-color-danger);
+}
+.kpi-delta.flat {
+  color: var(--el-text-color-secondary);
+}
+.kpi-hint {
+  font-size: 11px;
+  color: var(--el-text-color-secondary);
+}
+</style>

yunkes/src/components/management/MetricDefsDrawer.vue

@@ -0,0 +1,199 @@
+<template>
+  <el-drawer
+    :model-value="modelValue"
+    title="指标口径"
+    direction="rtl"
+    size="480px"
+    @update:model-value="onVisible"
+  >
+    <div v-loading="loading">
+      <el-alert v-if="error" type="error" :title="error" :closable="false" class="defs-alert" />
+
+      <template v-if="defs">
+        <!-- 三方口径差异总述(管理域 vs 现有看板) -->
+        <el-alert type="info" :closable="false" show-icon class="defs-alert">
+          <div class="caliber-text">{{ defs.caliber_notes }}</div>
+        </el-alert>
+
+        <!-- 评分配置摘要:版本/名称/试算/来源 + 样本门槛/等级线 + 维度权重 -->
+        <div class="cfg-card">
+          <div class="cfg-head">
+            <b>{{ defs.score_config.name }}</b>
+            <el-tag size="small" effect="plain">v{{ defs.score_config.version }}</el-tag>
+            <el-tag v-if="defs.score_config.trial" size="small" type="warning">试算</el-tag>
+            <el-tag size="small" :type="defs.config_source === 'db' ? 'primary' : 'info'" effect="plain">
+              {{ defs.config_source === 'db' ? '自定义配置' : '默认配置' }}
+            </el-tag>
+          </div>
+          <div class="cfg-row">样本门槛:{{ guardsText }}</div>
+          <div class="cfg-row">等级线:{{ gradesText }}(低于 D 线为 E)</div>
+          <el-table :data="dims" size="small" class="dims-table">
+            <el-table-column prop="name" label="维度" min-width="110" />
+            <el-table-column label="权重" width="70" align="right">
+              <template #default="{ row }">{{ row.weight }}%</template>
+            </el-table-column>
+            <el-table-column label="状态" width="90" align="center">
+              <template #default="{ row }">
+                <el-tag v-if="row.status === 'pending_data'" size="small" type="info">待数据</el-tag>
+                <el-tag v-else size="small" type="success">可用</el-tag>
+              </template>
+            </el-table-column>
+          </el-table>
+        </div>
+
+        <!-- 指标定义:19 项平铺(端点不按维度分组),按 code 字母序逐项展示 -->
+        <div v-for="[code, d] in defsSorted" :key="code" class="def-item">
+          <div class="def-head">
+            <b>{{ d.name }}</b>
+            <code class="def-code">{{ code }}</code>
+            <span class="def-unit">{{ d.unit }}</span>
+            <el-tag size="small" :type="d.direction === 1 ? 'success' : 'warning'">
+              {{ d.direction === 1 ? '越大越好' : '越小越好' }}
+            </el-tag>
+          </div>
+          <pre v-if="d.formula" class="def-formula">{{ d.formula }}</pre>
+          <div v-if="d.caliber" class="def-caliber">{{ d.caliber }}</div>
+        </div>
+      </template>
+    </div>
+  </el-drawer>
+</template>
+
+<script setup lang="ts">
+// 指标口径抽屉(批次C):口径字典 + 当前评分配置。打开时拉取
+// /management/metric-definitions 并缓存一次(口径变化走配置版本,会话内
+// 不重拉)。definitions 为平铺 19 项(dimensions 只有名称/权重),不做按
+// 维度分组,按 code 字母序逐项列:名称+单位+方向 tag+formula+caliber。
+import { computed, ref, watch } from 'vue'
+import { getMetricDefs, type MetricDefsResp } from '@/api/management'
+
+const props = defineProps<{ modelValue: boolean }>()
+
+const emit = defineEmits<{
+  (e: 'update:modelValue', v: boolean): void
+}>()
+
+const loading = ref(false)
+const error = ref('')
+const defs = ref<MetricDefsResp | null>(null)
+let loaded = false // 缓存一次:首次打开拉取,后续打开直接用
+
+// 打开时取数;成功后缓存(口径变化走配置版本,会话内不重拉),
+// 失败(无 defs 且有 error)则重开抽屉时再试一次
+watch(
+  () => props.modelValue,
+  (visible) => {
+    if (visible && (!loaded || (!defs.value && error.value))) load()
+  },
+)
+
+async function load(): Promise<void> {
+  loaded = true // 请求已发出即视为已加载,失败不反复自动重试
+  loading.value = true
+  error.value = ''
+  try {
+    defs.value = await getMetricDefs()
+  } catch (e) {
+    error.value = e instanceof Error ? e.message : String(e)
+  } finally {
+    loading.value = false
+  }
+}
+
+function onVisible(v: boolean): void {
+  emit('update:modelValue', v)
+}
+
+// 平铺定义按 code 字母序(中文环境 code 恒为 ASCII,localeCompare 稳定)
+const defsSorted = computed(() =>
+  Object.entries(defs.value?.definitions ?? {}).sort(([a], [b]) => a.localeCompare(b)),
+)
+
+// 配置维度行(仅名称/权重/状态)
+const dims = computed(() =>
+  Object.entries(defs.value?.score_config.dimensions ?? {}).map(([key, d]) => ({
+    key,
+    name: d.name,
+    weight: d.weight,
+    status: d.status,
+  })),
+)
+
+const guardsText = computed(() => {
+  const g = defs.value?.score_config.sample_guards ?? {}
+  return Object.entries(g).map(([k, v]) => `${k} ≥ ${v}`).join(' · ') || '--'
+})
+
+const gradesText = computed(() => {
+  const gb = defs.value?.score_config.grade_bounds ?? {}
+  return Object.entries(gb).map(([g, v]) => `${g} ≥ ${v}`).join(' · ') || '--'
+})
+</script>
+
+<style scoped>
+.defs-alert {
+  margin-bottom: 12px;
+}
+.caliber-text {
+  font-size: 12px;
+  line-height: 1.6;
+  white-space: normal;
+}
+.cfg-card {
+  border: 1px solid var(--el-border-color-lighter);
+  border-radius: 6px;
+  padding: 12px;
+  margin-bottom: 16px;
+}
+.cfg-head {
+  display: flex;
+  align-items: center;
+  gap: 8px;
+  flex-wrap: wrap;
+  margin-bottom: 8px;
+}
+.cfg-row {
+  font-size: 12px;
+  color: var(--el-text-color-secondary);
+  margin-bottom: 4px;
+}
+.dims-table {
+  margin-top: 8px;
+}
+.def-item {
+  padding: 10px 0;
+  border-bottom: 1px solid var(--el-border-color-lighter);
+}
+.def-head {
+  display: flex;
+  align-items: center;
+  gap: 8px;
+  flex-wrap: wrap;
+}
+.def-code {
+  font-size: 12px;
+  color: var(--el-text-color-secondary);
+  background: var(--el-fill-color-light);
+  padding: 1px 6px;
+  border-radius: 3px;
+}
+.def-unit {
+  font-size: 12px;
+  color: var(--el-text-color-secondary);
+}
+.def-formula {
+  margin: 6px 0 0;
+  padding: 6px 10px;
+  font-size: 12px;
+  background: var(--el-fill-color-light);
+  border-radius: 4px;
+  white-space: pre-wrap;
+  word-break: break-all;
+}
+.def-caliber {
+  margin-top: 6px;
+  font-size: 12px;
+  color: var(--el-text-color-secondary);
+  line-height: 1.6;
+}
+</style>

yunkes/src/components/management/MetricDrilldownDrawer.vue

@@ -0,0 +1,369 @@
+<template>
+  <el-drawer
+    :model-value="modelValue"
+    :title="card?.title ?? '指标下钻'"
+    direction="rtl"
+    size="760px"
+    @update:model-value="onVisible"
+  >
+    <!-- 无 metric_code 或 drilldown.type==='employee':员工维度异常,下钻
+         明细属批次D 员工分析页——先给原因/建议动作兜底 -->
+    <template v-if="unsupported">
+      <el-empty description="员工分析页批次D上线，此类异常先看建议动作" :image-size="80" />
+      <div v-if="card" class="fallback">
+        <div class="fallback-label">原因</div>
+        <div class="fallback-text">{{ card.reason }}</div>
+        <div class="fallback-label">建议动作</div>
+        <div class="fallback-text">{{ card.suggested_action }}</div>
+      </div>
+    </template>
+
+    <template v-else>
+      <el-alert v-if="error" type="error" :title="error" :closable="false" class="drill-alert" />
+      <el-alert v-if="resp?.note" type="info" :title="resp.note" :closable="false" class="drill-alert" />
+      <el-alert
+        v-if="resp?.truncated"
+        type="warning"
+        title="候选超500，列表可能不全"
+        :closable="false"
+        class="drill-alert"
+      />
+
+      <!-- call_followup:期聚合摘要(期通话/接通/跟进) -->
+      <div v-if="kind === 'calls' && resp?.summary" class="call-summary">
+        <div class="sum-item">
+          <span class="sum-num">{{ resp.summary.call_count ?? 0 }}</span>
+          <span class="sum-label">期通话</span>
+        </div>
+        <div class="sum-item">
+          <span class="sum-num">{{ resp.summary.answered_call_count ?? 0 }}</span>
+          <span class="sum-label">接通</span>
+        </div>
+        <div class="sum-item">
+          <span class="sum-num">{{ resp.summary.call_followup_count ?? 0 }}</span>
+          <span class="sum-label">跟进</span>
+        </div>
+      </div>
+
+      <!-- 首响分位:逐串证据行(后端已按 fr_ms desc),行 click 跳聊天 -->
+      <el-table
+        v-if="kind === 'first_reply'"
+        v-loading="loading"
+        :data="frRows"
+        :row-class-name="clickableRow"
+        @row-click="onFrRowClick"
+      >
+        <el-table-column prop="peer_id" label="客户" min-width="140" show-overflow-tooltip />
+        <el-table-column label="渠道" width="90" align="center">
+          <template #default="{ row }">
+            <el-tag size="small" :type="row.channel === 'whatsapp' ? 'success' : 'primary'">
+              {{ chTag(row.channel) }}
+            </el-tag>
+          </template>
+        </el-table-column>
+        <el-table-column label="串末条时间" width="170">
+          <template #default="{ row }">{{ formatTime(row.thread_end_ts) }}</template>
+        </el-table-column>
+        <el-table-column label="回复时间" width="170">
+          <template #default="{ row }">{{ formatTime(row.reply_ts) }}</template>
+        </el-table-column>
+        <el-table-column label="首响时长" align="right" min-width="110">
+          <template #default="{ row }">{{ formatMsDuration(row.fr_ms) }}</template>
+        </el-table-column>
+      </el-table>
+
+      <!-- 未回串:等待中的客户,行 click 跳聊天(带 msgid 定位最后一条客户消息) -->
+      <el-table
+        v-else-if="kind === 'unreplied'"
+        v-loading="loading"
+        :data="unrepliedRows"
+        :row-class-name="clickableRow"
+        @row-click="onUnrepliedRowClick"
+      >
+        <el-table-column prop="peer_id" label="客户" min-width="140" show-overflow-tooltip />
+        <el-table-column label="渠道" width="90" align="center">
+          <template #default="{ row }">
+            <el-tag size="small" :type="row.channel === 'whatsapp' ? 'success' : 'primary'">
+              {{ chTag(row.channel) }}
+            </el-tag>
+          </template>
+        </el-table-column>
+        <el-table-column label="等待时长" width="140">
+          <template #default="{ row }">{{ formatMsDuration(row.wait_ms) }}</template>
+        </el-table-column>
+        <el-table-column label="预览" min-width="220" show-overflow-tooltip>
+          <template #default="{ row }">{{ row.preview ?? '' }}</template>
+        </el-table-column>
+      </el-table>
+
+      <!-- 降温/沉睡客户名单。lifecycle 行没有 owner_account_id(互动史按
+           (channel,peer) 跨 owner 合并,归属不定)——不提供跳转,批次D 员工
+           分析页补员工账号维度的直达入口 -->
+      <el-table v-else-if="kind === 'lifecycle'" v-loading="loading" :data="lifecycleRows">
+        <el-table-column prop="nickname" label="客户" min-width="160" show-overflow-tooltip />
+        <el-table-column label="渠道" width="90" align="center">
+          <template #default="{ row }">
+            <el-tag size="small" :type="row.channel === 'whatsapp' ? 'success' : 'primary'">
+              {{ chTag(row.channel) }}
+            </el-tag>
+          </template>
+        </el-table-column>
+        <el-table-column label="最后互动日" width="120">
+          <template #default="{ row }">{{ fmtDay(row.last_day) }}</template>
+        </el-table-column>
+        <el-table-column label="状态" width="90" align="center">
+          <template #default="{ row }">
+            <el-tag v-if="row.state === 'dormant'" size="small" type="danger">沉睡</el-tag>
+            <el-tag v-else-if="row.state === 'cooling'" size="small" type="warning">降温</el-tag>
+            <el-tag v-else size="small" type="info">{{ row.state }}</el-tag>
+          </template>
+        </el-table-column>
+      </el-table>
+
+      <!-- 通话跟进:窗口通话列表(通话无渠道过滤维度,后端恒全渠道) -->
+      <el-table v-else-if="kind === 'calls'" v-loading="loading" :data="callRows">
+        <el-table-column label="时间" width="180">
+          <template #default="{ row }">{{ formatTime(row.start_call_time) }}</template>
+        </el-table-column>
+        <el-table-column label="类型" width="120">
+          <template #default="{ row }">{{ callTypeLabel(row.channel) }}</template>
+        </el-table-column>
+        <el-table-column label="号码" min-width="140">
+          <template #default="{ row }">{{ row.call_number ?? '--' }}</template>
+        </el-table-column>
+        <el-table-column label="时长(秒)" align="right" min-width="100">
+          <template #default="{ row }">{{ formatCallDuration(row.call_duration) }}</template>
+        </el-table-column>
+      </el-table>
+
+      <el-pagination
+        :current-page="page"
+        :page-size="PAGE_SIZE"
+        :total="resp?.total ?? 0"
+        layout="total, prev, pager, next"
+        class="pager"
+        @current-change="onPageChange"
+      />
+    </template>
+  </el-drawer>
+</template>
+
+<script setup lang="ts">
+// 指标下钻抽屉(批次C):点异常卡按 metric_code 调 drilldown 白名单端点,
+// 四种明细形态——首响逐串证据/未回串/降温·沉睡名单/通话跟进。抽屉自治
+// 加载(打开即取数,后端分页);员工维度异常(drilldown.type==='employee')
+// 无 metric_code,给批次D 占位 + 原因/建议动作兜底。行 click 跳聊天:
+// WA→ChatTimeline(/chat/whatsapp/{owner}/{peer}),微信→员工聊天窗 single
+// tab(/staff-chat/{owner}/single/{peer},项目惯例路由名跳转,路径等价)。
+import { computed, ref, watch } from 'vue'
+import { useRouter } from 'vue-router'
+import {
+  getEmployeeDrilldown,
+  type AnomalyCard,
+  type DrilldownCode,
+  type DrilldownResp,
+  type MgmtChannel,
+} from '@/api/management'
+import { callTypeLabel, formatCallDuration, formatMsDuration, formatTime } from '@/utils/format'
+
+const props = defineProps<{
+  modelValue: boolean
+  userId: string
+  card: AnomalyCard | null
+  start: number
+  end: number
+  channel: MgmtChannel
+}>()
+
+const emit = defineEmits<{
+  (e: 'update:modelValue', v: boolean): void
+}>()
+
+const router = useRouter()
+
+const PAGE_SIZE = 20
+const page = ref(1)
+const loading = ref(false)
+const error = ref('')
+const resp = ref<DrilldownResp | null>(null)
+
+let seq = 0 // 竞态守卫:快速换卡/翻页时旧响应作废(项目惯例)
+
+// drilldown 白名单(与后端 _DRILLDOWN_CODES 一致;白名单外按不支持兜底)
+const DRILL_CODES: readonly string[] = [
+  'first_reply_p50', 'first_reply_p90', 'unreplied',
+  'cooling_customers', 'dormant_customers', 'call_followup',
+]
+
+const metricCode = computed<DrilldownCode | null>(() => {
+  const c = props.card?.drilldown.query.metric_code
+  return c && DRILL_CODES.includes(c) ? (c as DrilldownCode) : null
+})
+
+// 员工维度异常(无 metric_code / type==='employee')→ 批次D 占位兜底
+const unsupported = computed(
+  () => !metricCode.value || props.card?.drilldown.type === 'employee',
+)
+
+type Kind = 'first_reply' | 'unreplied' | 'lifecycle' | 'calls'
+const kind = computed<Kind | null>(() => {
+  switch (metricCode.value) {
+    case 'first_reply_p50':
+    case 'first_reply_p90':
+      return 'first_reply'
+    case 'unreplied':
+      return 'unreplied'
+    case 'cooling_customers':
+    case 'dormant_customers':
+      return 'lifecycle'
+    case 'call_followup':
+      return 'calls'
+    default:
+      return null
+  }
+})
+
+// 打开(或换卡重开)即取数;start/end/channel 变化由父级在抽屉关闭时发生,
+// 下次打开经 visible 变化自然重查
+watch(
+  () => [props.modelValue, props.card] as const,
+  ([visible]) => {
+    if (visible && !unsupported.value) {
+      page.value = 1
+      load()
+    }
+  },
+)
+
+async function load(): Promise<void> {
+  if (!metricCode.value) return
+  const my = ++seq
+  loading.value = true
+  error.value = ''
+  try {
+    const r = await getEmployeeDrilldown(
+      props.userId, metricCode.value, props.start, props.end,
+      props.channel, page.value, PAGE_SIZE,
+    )
+    if (my !== seq) return
+    resp.value = r
+  } catch (e) {
+    if (my === seq) error.value = e instanceof Error ? e.message : String(e)
+  } finally {
+    // 过期请求不清 loading(新一轮还在飞)也不覆盖 error
+    if (my === seq) loading.value = false
+  }
+}
+
+// 分页翻页:vue-tsc strict 不推 inline-arrow 参数,单列包装(项目惯例)
+function onPageChange(p: number): void {
+  page.value = p
+  load()
+}
+
+function onVisible(v: boolean): void {
+  emit('update:modelValue', v)
+}
+
+// ---- 各分支行类型(items 是 Record<string,unknown>[],按白名单端点形状收窄) ----
+
+type FrRow = {
+  day: number; channel: string; owner_account_id: string; peer_id: string
+  thread_end_ts: number; reply_ts: number; fr_ms: number
+}
+type UnrepliedRow = {
+  peer_id: string; channel: string; owner_account_id: string
+  last_ts: number; wait_ms: number; preview?: string; msg_id?: string
+}
+type LifecycleRow = { friend_id: string; channel: string; nickname: string; last_day: number; state: string }
+type CallRow = { call_id: string; channel: string; call_number: string | null; start_call_time: number; call_duration: number }
+
+const frRows = computed<FrRow[]>(() =>
+  kind.value === 'first_reply' ? (resp.value?.items ?? []) as FrRow[] : [])
+const unrepliedRows = computed<UnrepliedRow[]>(() =>
+  kind.value === 'unreplied' ? (resp.value?.items ?? []) as UnrepliedRow[] : [])
+const lifecycleRows = computed<LifecycleRow[]>(() =>
+  kind.value === 'lifecycle' ? (resp.value?.items ?? []) as LifecycleRow[] : [])
+const callRows = computed<CallRow[]>(() =>
+  kind.value === 'calls' ? (resp.value?.items ?? []) as CallRow[] : [])
+
+// ---- 展示辅助 ----
+
+// 渠道短标签:异常下钻列窄,微信/WA 两字(全称 channelLabel 留给宽列页面)
+const CHANNEL_TAG: Record<string, string> = { wechat: '微信', whatsapp: 'WA' }
+const chTag = (c: string): string => CHANNEL_TAG[c] ?? c
+
+// yyyymmdd(20260810)→ 2026-08-10:最后互动日跨月/年,保留完整年份
+const fmtDay = (d: number): string =>
+  `${String(d).slice(0, 4)}-${String(d).slice(4, 6)}-${String(d).slice(6, 8)}`
+
+// ---- 行点击跳聊天 ----
+
+function goChat(owner: string, peer: string, channel: string, msgId?: string): void {
+  if (channel === 'whatsapp') {
+    router.push({ name: 'chat', params: { channel: 'whatsapp', ownerId: owner, talkerId: peer } })
+    return
+  }
+  router.push({
+    name: 'staff-chat',
+    params: { ownerId: owner, tab: 'single', talkerId: peer },
+    query: msgId ? { msgid: msgId } : undefined,
+  })
+}
+
+// owner 理论恒非空(fact/未回清单均来自 owner 维度查询),防御判空不亏
+function clickableRow({ row }: { row: { owner_account_id?: string } }): string {
+  return row.owner_account_id ? 'yk-clickable-row' : ''
+}
+
+function onFrRowClick(row: FrRow): void {
+  goChat(row.owner_account_id, row.peer_id, row.channel)
+}
+
+// 微信跳转带 ?msgid= 定位最后一条客户消息(同 UnrepliedView 惯例)
+function onUnrepliedRowClick(row: UnrepliedRow): void {
+  if (!row.owner_account_id) return
+  goChat(row.owner_account_id, row.peer_id, row.channel, row.msg_id)
+}
+</script>
+
+<style scoped>
+.drill-alert {
+  margin-bottom: 12px;
+}
+.call-summary {
+  display: flex;
+  gap: 32px;
+  margin-bottom: 12px;
+}
+.sum-item {
+  display: flex;
+  flex-direction: column;
+  align-items: center;
+}
+.sum-num {
+  font-size: 22px;
+  font-weight: 600;
+}
+.sum-label {
+  font-size: 12px;
+  color: var(--el-text-color-secondary);
+}
+.fallback {
+  margin-top: 8px;
+}
+.fallback-label {
+  font-size: 12px;
+  color: var(--el-text-color-secondary);
+  margin: 12px 0 4px;
+}
+.fallback-text {
+  font-size: 13px;
+  color: var(--el-text-color-primary);
+}
+.pager {
+  margin-top: 12px;
+  display: flex;
+  justify-content: flex-end;
+}
+</style>

yunkes/src/composables/__tests__/useManagementFilters.spec.ts

@@ -0,0 +1,139 @@
+// useManagementFilters 单测(vitest)。本文件不进 app 构建/类型检查
+// (tsconfig.app.json exclude __tests__,vitest 自行解析类型),
+// `npm run test` 执行。
+//
+// composable 依赖 vue-router 注入,仓库无先例;node 环境(无 DOM),
+// 选用 createApp + app.use(router) + app.runWithContext() 提供真实
+// route/router 注入,不 mock、不挂载组件。
+import { describe, expect, it, vi } from 'vitest'
+import { createApp } from 'vue'
+import { createMemoryHistory, createRouter } from 'vue-router'
+import { presetRange, useManagementFilters } from '../useManagementFilters'
+
+/** 建一个带 memory 路由的 filters 实例;query 为初始 URL query。 */
+async function setup(query: Record<string, string> = {}) {
+  const router = createRouter({
+    history: createMemoryHistory(),
+    routes: [{ path: '/', component: { render: () => null } }],
+  })
+  const app = createApp({ render: () => null })
+  app.use(router)
+  await router.push({ path: '/', query })
+  const filters = app.runWithContext(() => useManagementFilters())
+  return { router, filters }
+}
+
+const D = (ymdNum: number) => new Date(Math.floor(ymdNum / 10000), (Math.floor(ymdNum / 100) % 100) - 1, ymdNum % 100)
+
+describe('presetRange(注入 today,确定性日期)', () => {
+  it('last7 → 含今天共 7 天(2026-09-10 → 20260904..20260910)', () => {
+    expect(presetRange('last7', D(20260910))).toEqual({ start: 20260904, end: 20260910 })
+  })
+
+  it('last30 → 30 天窗(2026-09-10 → 20260812..20260910)', () => {
+    expect(presetRange('last30', D(20260910))).toEqual({ start: 20260812, end: 20260910 })
+  })
+
+  it('thisMonth → 月初到今天(2026-09-10 → 20260901..20260910)', () => {
+    expect(presetRange('thisMonth', D(20260910))).toEqual({ start: 20260901, end: 20260910 })
+  })
+
+  it('lastMonth → 上月整月(2026-08-15 → 20260701..20260731,31 天月)', () => {
+    expect(presetRange('lastMonth', D(20260815))).toEqual({ start: 20260701, end: 20260731 })
+  })
+
+  it('lastMonth 30 天月(2026-07-15 → 20260601..20260630)', () => {
+    expect(presetRange('lastMonth', D(20260715))).toEqual({ start: 20260601, end: 20260630 })
+  })
+
+  it('lastMonth 跨年(2026-01-15 → 20251201..20251231)', () => {
+    expect(presetRange('lastMonth', D(20260115))).toEqual({ start: 20251201, end: 20251231 })
+  })
+
+  it('today → 今天单日(2026-09-10 → 20260910..20260910)', () => {
+    expect(presetRange('today', D(20260910))).toEqual({ start: 20260910, end: 20260910 })
+  })
+
+  it('yesterday → 昨日单日(2026-09-10 → 20260909..20260909)', () => {
+    expect(presetRange('yesterday', D(20260910))).toEqual({ start: 20260909, end: 20260909 })
+  })
+
+  it('thisWeek 周中(2026-07-02 周四 → 周一到今天 20260629..20260702)', () => {
+    expect(presetRange('thisWeek', D(20260702))).toEqual({ start: 20260629, end: 20260702 })
+  })
+
+  it('thisWeek 周一当天 → 单日(2026-06-29 周一 → 20260629..20260629)', () => {
+    expect(presetRange('thisWeek', D(20260629))).toEqual({ start: 20260629, end: 20260629 })
+  })
+
+  it('lastWeek 跨月边界(2026-07-02 周四 → 上周一..上周日 20260622..20260628)', () => {
+    expect(presetRange('lastWeek', D(20260702))).toEqual({ start: 20260622, end: 20260628 })
+  })
+
+  it('custom → 今天单日兜底(2026-09-10 → 20260910..20260910)', () => {
+    expect(presetRange('custom', D(20260910))).toEqual({ start: 20260910, end: 20260910 })
+  })
+})
+
+describe('useManagementFilters(URL query 为真源)', () => {
+  it('空 query → channel=all / start,end=last30 默认 / compare=previous', async () => {
+    const { filters } = await setup()
+    expect(filters.channel.value).toBe('all')
+    expect(filters.compare.value).toBe('previous')
+    // 默认值与 presetRange('last30')(真实今天)同源,同日执行必一致
+    expect(filters.start.value).toBe(presetRange('last30').start)
+    expect(filters.end.value).toBe(presetRange('last30').end)
+  })
+
+  it('合法 query → 原样读出(wechat / 日期 / team_median)', async () => {
+    const { filters } = await setup({
+      channel: 'wechat',
+      start: '20250101',
+      end: '20250131',
+      compare: 'team_median',
+    })
+    expect(filters.channel.value).toBe('wechat')
+    expect(filters.start.value).toBe(20250101)
+    expect(filters.end.value).toBe(20250131)
+    expect(filters.compare.value).toBe('team_median')
+  })
+
+  it('非法 query 值 → 回退默认(channel=xx / start=abc / end=19990101 早于下限 / compare=foo)', async () => {
+    const { filters } = await setup({ channel: 'xx', start: 'abc', end: '19990101', compare: 'foo' })
+    expect(filters.channel.value).toBe('all')
+    expect(filters.compare.value).toBe('previous')
+    expect(filters.start.value).toBe(presetRange('last30').start)
+    expect(filters.end.value).toBe(presetRange('last30').end)
+  })
+
+  it('apply({channel}) → query 更新且其余参数保留', async () => {
+    const { router, filters } = await setup({ compare: 'team_median' })
+    filters.apply({ channel: 'whatsapp' })
+    await vi.waitFor(() => expect(router.currentRoute.value.query.channel).toBe('whatsapp'))
+    expect(filters.channel.value).toBe('whatsapp')
+    // 未 patch 的 compare 原样保留
+    expect(router.currentRoute.value.query.compare).toBe('team_median')
+    expect(filters.compare.value).toBe('team_median')
+  })
+
+  it('applyPreset(预设) → 清掉 query 里的 start/end,默认值(仍为 last30)生效', async () => {
+    const { router, filters } = await setup({ start: '20250101', end: '20250131', channel: 'wechat' })
+    filters.applyPreset('last7')
+    await vi.waitFor(() => expect(router.currentRoute.value.query.start).toBeUndefined())
+    expect(router.currentRoute.value.query.end).toBeUndefined()
+    // channel 不在清理范围,保留
+    expect(filters.channel.value).toBe('wechat')
+    // 清掉后回退默认(last30,与真实今天同源)
+    expect(filters.start.value).toBe(presetRange('last30').start)
+    expect(filters.end.value).toBe(presetRange('last30').end)
+  })
+
+  it("applyPreset('custom', {...}) → query 带具体日期", async () => {
+    const { router, filters } = await setup()
+    filters.applyPreset('custom', { start: 20260101, end: 20260131 })
+    await vi.waitFor(() => expect(router.currentRoute.value.query.start).toBe('20260101'))
+    expect(router.currentRoute.value.query.end).toBe('20260131')
+    expect(filters.start.value).toBe(20260101)
+    expect(filters.end.value).toBe(20260131)
+  })
+})

yunkes/src/composables/useManagementFilters.ts

@@ -0,0 +1,91 @@
+// 管理页统一筛选(URL query 为真源——刷新/分享保持)。批次C:驾驶舱用;
+// 批次D 员工页复用(view 等额外参数由页面自行挂 query)。
+import { computed } from 'vue'
+import { useRoute, useRouter } from 'vue-router'
+
+export type Preset = 'today' | 'yesterday' | 'last7' | 'last30' | 'thisWeek' | 'lastWeek' | 'thisMonth' | 'lastMonth' | 'custom'
+export const CHANNELS = [
+  { value: 'all', label: '全部渠道' },
+  { value: 'wechat', label: '微信' },
+  { value: 'whatsapp', label: 'WhatsApp' },
+] as const
+
+function ymd(d: Date): number {
+  return d.getFullYear() * 10000 + (d.getMonth() + 1) * 100 + d.getDate()
+}
+function addDays(d: Date, n: number): Date {
+  const x = new Date(d)
+  x.setDate(x.getDate() + n)
+  return x
+}
+
+/** 预设 → [start,end] yyyymmdd。 */
+export function presetRange(p: Preset, today = new Date()): { start: number; end: number } {
+  const t0 = new Date(today.getFullYear(), today.getMonth(), today.getDate())
+  // 周一为一周起点(getDay 周日=0 → 偏移成周一=0..周日=6)
+  const dow = (t0.getDay() + 6) % 7
+  switch (p) {
+    case 'today':
+      return { start: ymd(t0), end: ymd(t0) }
+    case 'yesterday':
+      return { start: ymd(addDays(t0, -1)), end: ymd(addDays(t0, -1)) }
+    case 'thisWeek':
+      // 周一..今天;周一当天即单日
+      return { start: ymd(addDays(t0, -dow)), end: ymd(t0) }
+    case 'lastWeek': {
+      const monday = addDays(t0, -dow - 7)
+      return { start: ymd(monday), end: ymd(addDays(monday, 6)) }
+    }
+    case 'last7':
+      return { start: ymd(addDays(t0, -6)), end: ymd(t0) }
+    case 'last30':
+      return { start: ymd(addDays(t0, -29)), end: ymd(t0) }
+    case 'thisMonth':
+      return { start: ymd(new Date(t0.getFullYear(), t0.getMonth(), 1)), end: ymd(t0) }
+    case 'lastMonth': {
+      const first = new Date(t0.getFullYear(), t0.getMonth() - 1, 1)
+      const last = new Date(t0.getFullYear(), t0.getMonth(), 0)
+      return { start: ymd(first), end: ymd(last) }
+    }
+  }
+  // custom/未知:今天单日
+  return { start: ymd(t0), end: ymd(t0) }
+}
+
+export function useManagementFilters() {
+  const route = useRoute()
+  const router = useRouter()
+
+  const channel = computed<'all' | 'wechat' | 'whatsapp'>(() => {
+    const v = route.query.channel
+    return v === 'wechat' || v === 'whatsapp' ? v : 'all'
+  })
+  const start = computed(() => {
+    const v = Number(route.query.start)
+    return Number.isFinite(v) && v >= 20000101 && v <= 99991231 ? v : presetRange('last30').start
+  })
+  const end = computed(() => {
+    const v = Number(route.query.end)
+    return Number.isFinite(v) && v >= 20000101 && v <= 99991231 ? v : presetRange('last30').end
+  })
+  const compare = computed(() => {
+    const v = route.query.compare
+    return v === 'personal_baseline' || v === 'team_median' ? v : 'previous'
+  })
+
+  function apply(patch: Record<string, string | number | undefined>) {
+    const q: Record<string, string> = {}
+    for (const [k, v] of Object.entries({ ...route.query, ...patch })) {
+      if (v !== undefined && v !== null && v !== '') q[k] = String(v)
+    }
+    router.replace({ query: q })
+  }
+
+  // 预设切换:清掉 start/end 让默认值生效,custom 则带具体日期
+  function applyPreset(p: Preset, custom?: { start: number; end: number }) {
+    if (p === 'custom' && custom) apply({ start: custom.start, end: custom.end })
+    else apply({ start: undefined, end: undefined })
+  }
+
+  return { channel, start, end, compare, apply, applyPreset, presetRange }
+}

yunkes/src/layouts/MainLayout.vue

@@ -11,9 +11,11 @@ const channelStore = useChannelStore()
 
 // `el-menu` with `router` mode; we drive `default-active` from the current path
 // so the active item highlights on load and on browser back/forward.
+// 带参路由(路径与菜单 index 不等)按 route.name 映射父菜单路径。
 const activeMenu = computed(() => {
   if (route.name === 'chat') return '/customers'
   if (route.name === 'group-chat') return '/groups'
+  if (route.name === 'management-employees-detail') return '/management/employees'
   return route.path
 })
 
@@ -99,6 +101,19 @@ function logout(): void {
             全局搜索
           </el-menu-item>
 
+          <!-- 经营管理 -->
+          <el-sub-menu index="management">
+            <template #title>
+              <span class="yk-sidenav__group">经营管理</span>
+            </template>
+            <el-menu-item index="/management/dashboard" @click="goPlain('/management/dashboard')">
+              管理驾驶舱
+            </el-menu-item>
+            <el-menu-item index="/management/employees" @click="goPlain('/management/employees')">
+              员工分析
+            </el-menu-item>
+          </el-sub-menu>
+
           <!-- 数据分析 -->
           <el-sub-menu index="analytics">
             <template #title>

yunkes/src/router/index.ts

@@ -92,6 +92,31 @@ const routes: RouteRecordRaw[] = [
     component: () => import('@/views/analytics/SensitiveView.vue'),
     meta: { title: '敏感词' },
   },
+  {
+    // 经营管理板块(批次C):驾驶舱;员工分析/考核快照批次D/E再加
+    path: '/management/dashboard',
+    name: 'management-dashboard',
+    component: () => import('@/views/management/ManagementDashboardView.vue'),
+    meta: { title: '管理驾驶舱' },
+  },
+  {
+    // 员工分析(批次D):四视图总览;详情路由 /management/employees/{user_id}
+    // 由批次D后续任务补挂(D2)
+    path: '/management/employees',
+    name: 'management-employees',
+    component: () => import('@/views/management/EmployeeAnalyticsView.vue'),
+    meta: { title: '员工分析' },
+  },
+  {
+    // 员工详情(批次D2):总览页姓名下钻;query 真源 channel/start/end/section
+    // (section=当前页签,刷新回到该页签)。静态路由 /management/employees
+    // 先注册,带参路由在后——vue-router 按注册序精确匹配,静态优先命中。
+    path: '/management/employees/:userId',
+    name: 'management-employees-detail',
+    component: () => import('@/views/management/EmployeeAnalyticsDetailView.vue'),
+    props: true,
+    meta: { title: '员工分析详情' },
+  },
   {
     path: '/chat/:channel/:ownerId/:talkerId?',
     name: 'chat',
@@ -117,6 +142,15 @@ const routes: RouteRecordRaw[] = [
     props: true,
     meta: { title: '员工聊天窗口' },
   },
+  {
+    // 员工客户列表(2026-09-08 对齐云客员工详情):员工列表「好友数/微信群数」
+    // 账号维度下钻,与全局 /customers 分离; ?name= 直带员工显示名(直链自动解析)
+    path: '/staff-friends/:ownerId/:tab(customers|groups)?',
+    name: 'staff-friends',
+    component: () => import('@/views/StaffFriends.vue'),
+    props: true,
+    meta: { title: '员工客户列表' },
+  },
   {
     // 登录页(public:未登录可进;守卫据此放行)
     path: '/login',

yunkes/src/utils/csvExport.ts

@@ -10,6 +10,9 @@
  *     ],
  *     filename: '微信客户列表',
  *   })
+ *
+ * Optional `preamble: string[]` writes comment lines (口径/窗口注释等) before
+ * the header — each line occupies the first column of its own row.
  */
 
 export interface CsvColumn<T> {
@@ -30,6 +33,12 @@ export interface ExportOptions<T> {
   pageSize?: number
   /** Max rows to export (safety cap, default 10000) */
   maxRows?: number
+  /**
+   * Optional comment lines written before the header row (batch D: management
+   * employee CSV carries caliber/window notes so the export is self-describing
+   * outside the app). Each line becomes a single-cell row in the first column.
+   */
+  preamble?: string[]
 }
 
 function escapeCsv(value: string | number | null | undefined): string {
@@ -43,7 +52,7 @@ function escapeCsv(value: string | number | null | undefined): string {
 }
 
 export async function exportListToCsv<T>(options: ExportOptions<T>): Promise<{ rows: number; filename: string }> {
-  const { fetchPage, columns, filename, pageSize = 100, maxRows = 10000 } = options
+  const { fetchPage, columns, filename, pageSize = 100, maxRows = 10000, preamble } = options
 
   // Fetch all pages
   const allRows: T[] = []
@@ -68,7 +77,7 @@ export async function exportListToCsv<T>(options: ExportOptions<T>): Promise<{ r
       return escapeCsv(val as string | number | null | undefined)
     }).join(',')
   )
-  const csv = '' + header + '\n' + lines.join('\n') // BOM for Excel Chinese support
+  const csv = '' + [...(preamble ?? []).map((p) => escapeCsv(p)), header, ...lines].join('\n') // BOM for Excel Chinese support
 
   // Trigger download
   const blob = new Blob([csv], { type: 'text/csv;charset=utf-8' })

yunkes/src/utils/format.ts

@@ -55,6 +55,28 @@ export function formatDuration(seconds?: number | null): string {
   return `${m}'${String(rem).padStart(2, '0')}"`
 }
 
+// ---------------------------------------------------------------------------
+// 经营管理板块共享格式化(批次C)——自 DashboardView 本地 fmtFr/fmtPct 提升,
+// 驾驶舱 KPI / 异常榜 / 下钻抽屉与旧看板共用同一展示口径。
+// ---------------------------------------------------------------------------
+
+/**
+ * 毫秒时长 → `<1h 显「X分Y秒」/ ≥1h 显「X小时Y分」`;null(无样本)显 `-`。
+ * 与 formatDuration(秒,聊天气泡口径)区分:此处是指标口径(首响等)。
+ */
+export function formatMsDuration(ms?: number | null): string {
+  if (ms == null) return '-'
+  const totalSec = Math.round(ms / 1000)
+  const mins = Math.floor(totalSec / 60)
+  if (mins < 60) return `${mins}分${totalSec % 60}秒`
+  return `${Math.floor(mins / 60)}小时${mins % 60}分`
+}
+
+/** 比率(0-1) → 百分比 1 位小数(回复率/接通率等);null 显 `-`。 */
+export function formatRatio(r?: number | null): string {
+  return r == null ? '-' : `${(r * 100).toFixed(1)}%`
+}
+
 /** Friendly label for a Channel value. */
 export function channelLabel(channel?: string | null): string {
   switch (channel) {

yunkes/src/utils/groupFields.ts

@@ -77,7 +77,7 @@ export const GROUP_FIELD_GROUPS: GroupFieldGroup[] = [
   },
   {
     title: '成员',
-    keys: ['memberCount', 'memberIds'],
+    keys: ['memberCount'],  // memberIds 原始串由群详情成员墙替代(2026-09-10)
   },
   {
     title: '归属微信与群主',
@@ -105,7 +105,11 @@ export const GROUP_FIELD_GROUPS: GroupFieldGroup[] = [
 ]
 
 /** Every key already surfaced via a group (so 其他 can skip duplicates). */
-const KNOWN_KEYS = new Set(GROUP_FIELD_GROUPS.flatMap((g) => g.keys))
+const KNOWN_KEYS = new Set([
+  ...GROUP_FIELD_GROUPS.flatMap((g) => g.keys),
+  // 原始 wxid 串由群详情成员墙替代,不在任何区(含「其他」)显示(2026-09-10)
+  'memberIds',
+])
 
 /** Resolve the 中文 label for a raw_json key (falls back to the key). */
 export function fieldLabel(key: string): string {

yunkes/src/views/ChatTimeline.vue

@@ -53,6 +53,13 @@ const channelTyped = computed(() => props.channel as Channel)
 /** True when this timeline is a group chat (drives the query + title). */
 const isGroup = computed(() => !!props.roomId)
 
+/**
+ * 专注模式(?bare=1):群统计等列表入口的「查看详情」——隐藏会话侧栏,
+ * 对齐云客群详情页(无好友/群列表,纯聊天记录窗)。员工聊天窗口入口
+ * (不带 bare)侧栏常驻(2026-09-09 修复保持)。
+ */
+const isBare = computed(() => route.query.bare === '1')
+
 /** 当前会话类型(高亮 sidebar + 驱动空态)。账号级入口(无 talkerId/roomId)→ null。 */
 const activeType = computed<'friend' | 'group' | null>(() =>
   isGroup.value ? 'group' : props.talkerId ? 'friend' : null,
@@ -342,8 +349,13 @@ onMounted(() => {
 <template>
   <div class="yk-chat">
     <div class="yk-chat__body">
+      <!-- 侧栏常驻(含群聊路由):好友/群列表随时可切,对齐云客聊天窗体验。
+           旧版 v-if="!isGroup" 在群路由下藏侧栏,点群后「好友列表/群列表」
+           消失(2026-09-09 用户报);onSelectSession 本就双类型导航。
+           bare 模式(群统计「查看详情」入口)例外——纯聊天记录窗无侧栏,
+           对齐云客群详情页(2026-09-10 用户反馈)。 -->
       <ChatSidebar
-        v-if="!isGroup"
+        v-if="!isBare"
         :channel="channelTyped"
         :owner-id="props.ownerId"
         :active-type="activeType"

yunkes/src/views/CustomerList.vue

@@ -43,6 +43,20 @@ function freshTabState(pageSize = 5): TabState {
 /** 云客口径客户合计(分渠道,Σ员工好友数声明值,含云客索引重复;页脚对齐云客)。 */
 const declaredTotals = ref<{ wechat: number | null; whatsapp: number | null }>({ wechat: null, whatsapp: null })
 
+/** 列表过滤是否生效(部门/员工)——生效时计数与分页必须用真实 total,声明口径是
+ * 全局值不吃过滤:员工列表点「好友数」跳入时曾把 8956 当分页总数,列表却只有
+ * 该员工的 9 条,翻页按全部客户算(2026-09-08 用户报「不是员工下面的好友列表」)。 */
+const filtered = computed(
+  () => departmentId.value !== null || ownerId.value !== null,
+)
+
+/** 展示用总数:无过滤时对齐云客声明口径(产品定调),有过滤时回到真实结果数。 */
+function displayTotal(tab: TabKey): number {
+  return !filtered.value && declaredTotals.value[tab] !== null
+    ? (declaredTotals.value[tab] as number)
+    : tabState[tab].total
+}
+
 async function loadDeclaredTotal(): Promise<void> {
   try {
     const r = await getCustomerDeclaredTotal()
@@ -440,7 +454,7 @@ onMounted(() => {
       <div>
         <h2 style="margin: 0 0 4px; font-size: 16px">{{ activeTab === 'wechat' ? '微信' : 'WhatsApp' }}客户列表</h2>
         <span class="yk-customers__sub">
-          共 {{ declaredTotals[activeTab] !== null ? declaredTotals[activeTab] : tabState[activeTab].total }} 条
+          共 {{ displayTotal(activeTab) }} 条
           <template v-if="departmentName"> · 部门：{{ departmentName }}</template>
           <template v-if="ownerId"> · 员工账号：{{ ownerId }}</template>
         </span>
@@ -589,7 +603,7 @@ onMounted(() => {
             :current-page="tabState.wechat.page"
             :page-size="tabState.wechat.pageSize"
             :page-sizes="[5, 10, 20, 50, 100]"
-            :total="declaredTotals.wechat ?? tabState.wechat.total"
+            :total="displayTotal('wechat')"
             layout="total, sizes, prev, pager, next, jumper"
             background
             @current-change="onWechatPageChange"
@@ -726,7 +740,7 @@ onMounted(() => {
             :current-page="tabState.whatsapp.page"
             :page-size="tabState.whatsapp.pageSize"
             :page-sizes="[5, 10, 20, 50, 100]"
-            :total="declaredTotals.whatsapp ?? tabState.whatsapp.total"
+            :total="displayTotal('whatsapp')"
             layout="total, sizes, prev, pager, next, jumper"
             background
             @current-change="onWhatsappPageChange"

yunkes/src/views/GroupList.vue

@@ -3,14 +3,12 @@ import { computed, onMounted, reactive, ref, watch } from 'vue'
 import { useRoute, useRouter } from 'vue-router'
 import { ElMessage } from 'element-plus'
 import { Download } from '@element-plus/icons-vue'
-import { getGroups } from '@/api'
+import { getAccounts, getGroupMembers, getGroups } from '@/api'
-import { downloadBlob } from '@/api/client'
+import type { Account, Channel, Group, GroupMember } from '@/api/types'
-import type { Channel, Group } from '@/api/types'
 import { useChannelStore } from '@/stores/channel'
 import { channelLabel, formatTime } from '@/utils/format'
 import { exportListToCsv } from '@/utils/csvExport'
 import { buildGroupSections, readField } from '@/utils/groupFields'
-import { fromTypeLabel } from '@/utils/customerFields'
 
 /**
  * 群列表 — channel-tabbed view mirroring 云客「沟通」板块的群列表.
@@ -84,10 +82,6 @@ function cellNum(row: Group, camelKey: string, fallback = 0): number {
   const v = cell(row, camelKey)
   return typeof v === 'number' && Number.isFinite(v) ? v : fallback
 }
-/** 数据来源列：fromType 代码→文案（复用 customerFields.fromTypeLabel）。 */
-function fromTypeText(row: Group): string {
-  return fromTypeLabel(cell(row, 'fromType'))
-}
 function imageCell(row: Group, camelKey: string): string | undefined {
   const v = cell(row, camelKey)
   return typeof v === 'string' && v !== '' ? v : undefined
@@ -108,7 +102,16 @@ async function loadTab(ch: TabKey): Promise<void> {
       channel: ch,
       page: st.page,
       page_size: st.pageSize,
-      owner_account_id: ownerId.value ?? undefined,
+      owner_account_id: ch === 'wechat' ? (staffOwner.value || ownerId.value) || undefined : ownerId.value ?? undefined,
+      // 微信群统计筛选(云客「微信群统计」同款,2026-09-09)
+      ...(ch === 'wechat'
+        ? {
+            q: gName.value.trim() || undefined,
+            group_remark: gRemark.value.trim() || undefined,
+            ...(lastRange.value ? { last_start: dayStart(lastRange.value[0]), last_end: dayEnd(lastRange.value[1]) } : {}),
+            ...(statRange.value ? { msg_start: dayStart(statRange.value[0]), msg_end: dayEnd(statRange.value[1]) } : {}),
+          }
+        : {}),
     })
     st.items = res.items
     st.total = res.total
@@ -120,6 +123,47 @@ async function loadTab(ch: TabKey): Promise<void> {
     st.loading = false
   }
 }
+
+// ---- 微信群统计筛选(云客同款:统计时段/最新消息时间段/群名称/群备注/员工) ----
+function defaultStatRange(): [Date, Date] {
+  // 云客默认近 7 天(截图 09-03→09-09)
+  const end = new Date()
+  const start = new Date(end.getTime() - 6 * 86_400_000)
+  return [start, end]
+}
+const statRange = ref<[Date, Date] | null>(defaultStatRange())
+const lastRange = ref<[Date, Date] | null>(null)
+const gName = ref('')
+const gRemark = ref('')
+/** 员工筛选(下拉;入口 query 的 owner_account_id 作初值,选择后接管)。 */
+const staffOwner = ref<string>(ownerId.value ?? '')
+const staffOptions = ref<Account[]>([])
+
+function dayStart(d: Date): number {
+  const x = new Date(d)
+  x.setHours(0, 0, 0, 0)
+  return x.getTime()
+}
+function dayEnd(d: Date): number {
+  const x = new Date(d)
+  x.setHours(23, 59, 59, 999)
+  return x.getTime()
+}
+
+async function loadStaffOptions(): Promise<void> {
+  try {
+    const res = await getAccounts({ channel: 'wechat', page: 1, page_size: 100 })
+    staffOptions.value = res.items
+    if (ownerId.value && !staffOwner.value) staffOwner.value = ownerId.value
+  } catch {
+    // 静默降级:员工筛选为空
+  }
+}
+
+function onSearch(): void {
+  tabState.wechat.page = 1
+  loadTab('wechat')
+}
 function handlePageChange(ch: TabKey, p: number): void {
   tabState[ch].page = p
   loadTab(ch)
@@ -145,6 +189,9 @@ function viewChat(row: Group): void {
   router.push({
     name: 'group-chat',
     params: { channel: row.channel, ownerId: row.owner_account_id, roomId: row.room_id },
+    // bare=专注模式:无会话侧栏,对齐云客群详情页(2026-09-10)。
+    // 员工聊天窗口入口不带 bare,侧栏常驻。
+    query: row.channel === 'wechat' ? { bare: '1' } : undefined,
   })
 }
 /** drawer 内「查看聊天记录」入口：drawerGroup 是 ref<Group|null>，模板嵌套不保证窄化，用 wrapper 守卫。 */
@@ -154,28 +201,6 @@ function viewChatFromDrawer(): void {
   viewChat(row)
 }
 
-/**
- * 微信群「导出HTML聊天记录」→ 后端 /api/export/chat-html（room_id）。
- * 云客群列表导出按钮直接导出，无时间选择 modal（仅微信客户有「请选择时间」）。
- * WA 群 tab 无此操作（云客 WA 群列表无导出）。
- */
-async function exportGroupHtml(row: Group): Promise<void> {
-  if (!row.owner_account_id || !row.room_id) {
-    ElMessage.warning('该群缺少归属账号/群标识，无法导出')
-    return
-  }
-  try {
-    await downloadBlob('/export/chat-html', {
-      channel: row.channel,
-      owner_account_id: row.owner_account_id,
-      room_id: row.room_id,
-    })
-    ElMessage.success('导出已开始')
-  } catch (e) {
-    ElMessage.error(`导出失败，请稍后重试：${(e as Error).message}`)
-  }
-}
-
 // ---- header 导出：当前 tab 渠道全量群 CSV（含当前员工筛选） ----
 const exporting = ref(false)
 
@@ -222,9 +247,35 @@ function clearOwnerFilter(): void {
 }
 
 // ---- drawer ----
+// 群成员墙(2026-09-10):点开群详情拉 members,渲染头像+昵称(消息派生群昵称
+// 优先,customer 好友昵称兜底,都没有回退 wxid)。
+const drawerMembers = ref<GroupMember[]>([])
+const membersLoading = ref(false)
+
+async function loadDrawerMembers(roomId: string): Promise<void> {
+  drawerMembers.value = []
+  membersLoading.value = true
+  try {
+    drawerMembers.value = await getGroupMembers(roomId)
+  } catch {
+    drawerMembers.value = [] // 静默:成员区空态
+  } finally {
+    membersLoading.value = false
+  }
+}
+
+function memberLabel(m: GroupMember): string {
+  return m.nickname || m.display_name || m.member_id
+}
+
 function openDrawer(row: Group): void {
   drawerGroup.value = row
   drawerOpen.value = true
+  if (row.channel === 'wechat') {
+    loadDrawerMembers(row.room_id)
+  } else {
+    drawerMembers.value = []
+  }
 }
 const drawerSections = computed(() =>
   drawerGroup.value ? buildGroupSections(drawerGroup.value) : [],
@@ -262,6 +313,7 @@ watch(
 )
 
 onMounted(() => {
+  loadStaffOptions()
   loadTab(activeTab.value)
 })
 </script>
@@ -287,9 +339,52 @@ onMounted(() => {
     </div>
 
     <!-- ============================================================
-         微信群 — 7 列，对齐云客 wechatdetail/2/{wxId}.
+         微信群统计 — 对齐云客「沟通→微信号管理→微信群统计」
+         (/cms/wechat/wechatgroup,2026-09-09 真机对齐)。
+         统计时段窗内:沟通消息数=本地日汇总;新增/退出成员数=按天进出表
+         求和(上线日起积累,历史日期为 0)。
          ============================================================ -->
     <template v-if="activeTab === 'wechat'">
+        <div class="yk-groups__statfilters">
+          <div class="yk-groups__filterrow">
+            <span class="yk-groups__flabel">数据统计时段：</span>
+            <el-date-picker
+              v-model="statRange"
+              type="daterange"
+              value-format="YYYY-MM-DD"
+              range-separator="→"
+              start-placeholder="开始日期"
+              end-placeholder="结束日期"
+              size="small"
+              style="width: 260px"
+            />
+            <span class="yk-groups__flabel" style="margin-left: 16px">最新消息时间段：</span>
+            <el-date-picker
+              v-model="lastRange"
+              type="daterange"
+              value-format="YYYY-MM-DD"
+              range-separator="→"
+              start-placeholder="开始日期"
+              end-placeholder="结束日期"
+              size="small"
+              style="width: 260px"
+              clearable
+            />
+          </div>
+          <div class="yk-groups__filterrow">
+            <el-input v-model="gName" placeholder="请输入群名称" size="small" clearable style="width: 180px" @keyup.enter="onSearch" />
+            <el-input v-model="gRemark" placeholder="请输入群备注" size="small" clearable style="width: 180px" @keyup.enter="onSearch" />
+            <el-select v-model="staffOwner" placeholder="员工微信昵称" size="small" clearable filterable style="width: 200px">
+              <el-option
+                v-for="a in staffOptions"
+                :key="a.account_id"
+                :label="a.nickname || a.user_name || a.account_id"
+                :value="a.account_id"
+              />
+            </el-select>
+            <el-button type="primary" size="small" @click="onSearch">查 询</el-button>
+          </div>
+        </div>
         <el-alert
           v-if="tabState.wechat.errorMsg"
           :title="tabState.wechat.errorMsg"
@@ -309,40 +404,55 @@ onMounted(() => {
           empty-text="暂无微信群数据"
           @row-click="openDrawer"
         >
-          <el-table-column label="群信息" min-width="180">
+          <el-table-column label="群信息" min-width="200">
-            <template #default="{ row }">
-              <div class="yk-staffinfo__nick" :title="cellText(row, 'chatRoomName')">{{ cellText(row, 'chatRoomName') }}</div>
-            </template>
-          </el-table-column>
-          <el-table-column label="数据来源" min-width="110">
-            <template #default="{ row }">{{ fromTypeText(row) }}</template>
-          </el-table-column>
-          <el-table-column label="群主信息" min-width="180">
             <template #default="{ row }">
               <div class="yk-group-owner">
-                <el-avatar :size="36" :src="imageCell(row, 'ownerImage') || undefined" shape="circle">
+                <el-avatar :size="34" :src="row.head_image_url || undefined" shape="circle">
-                  {{ (cellText(row, 'ownerName') || '?').slice(0, 1) }}
+                  {{ (row.room_name || '?').slice(0, 1) }}
                 </el-avatar>
                 <div class="yk-group-owner__meta">
-                  <div class="yk-staffinfo__nick">{{ cellText(row, 'ownerName') }}</div>
+                  <div class="yk-staffinfo__nick">{{ row.room_name || '--' }}</div>
-                  <div class="yk-staffinfo__muted">{{ cellText(row, 'realName') }}</div>
                 </div>
               </div>
             </template>
           </el-table-column>
-          <el-table-column label="群成员数量" width="110" align="right">
+          <el-table-column label="群备注" min-width="110">
-            <template #default="{ row }">{{ cellNum(row, 'memberCount') }}</template>
+            <template #default="{ row }">{{ row.group_remark || '-' }}</template>
           </el-table-column>
-          <el-table-column label="群成员好友数量" width="130" align="right">
+          <el-table-column label="员工微信" min-width="170">
-            <template #default="{ row }">{{ cellNum(row, 'friendCount') }}</template>
-          </el-table-column>
-          <el-table-column label="消息数量" width="100" align="right">
-            <template #default="{ row }">{{ cellNum(row, 'messageCount') }}</template>
-          </el-table-column>
-          <el-table-column label="操作" width="220" fixed="right" align="center">
             <template #default="{ row }">
-              <el-button link type="primary" size="small" @click.stop="viewChat(row)">查看聊天记录</el-button>
+              <div class="yk-group-owner">
-              <el-button link type="primary" size="small" @click.stop="exportGroupHtml(row)">导出HTML聊天记录</el-button>
+                <el-avatar :size="34" :src="row.staff_avatar || undefined" shape="square">
+                  {{ (row.staff_nickname || '?').slice(0, 1) }}
+                </el-avatar>
+                <div class="yk-group-owner__meta">
+                  <div class="yk-staffinfo__nick">{{ row.staff_nickname || '--' }}</div>
+                  <div class="yk-staffinfo__muted">{{ row.staff_wx_alias || row.owner_account_id || '' }}</div>
+                </div>
+              </div>
+            </template>
+          </el-table-column>
+          <el-table-column label="员工信息" min-width="150">
+            <template #default="{ row }">
+              <div class="yk-staffinfo__nick">{{ row.staff_name || '--' }}</div>
+              <div class="yk-staffinfo__muted">{{ row.staff_phone || '' }}</div>
+            </template>
+          </el-table-column>
+          <el-table-column label="群成员数量" width="105" align="right">
+            <template #default="{ row }">{{ row.member_count ?? '-' }}</template>
+          </el-table-column>
+          <el-table-column label="新增成员数" width="105" align="right">
+            <template #default="{ row }">{{ row.window_added ?? '-' }}</template>
+          </el-table-column>
+          <el-table-column label="退出成员数" width="105" align="right">
+            <template #default="{ row }">{{ row.window_lost ?? '-' }}</template>
+          </el-table-column>
+          <el-table-column label="沟通消息数" width="105" align="right">
+            <template #default="{ row }">{{ row.window_msg_count ?? '-' }}</template>
+          </el-table-column>
+          <el-table-column label="操作" width="110" fixed="right" align="center">
+            <template #default="{ row }">
+              <el-button link type="primary" size="small" @click.stop="viewChat(row)">查看详情</el-button>
             </template>
           </el-table-column>
         </el-table>
@@ -465,6 +575,26 @@ onMounted(() => {
             </div>
           </div>
         </div>
+        <!-- 群成员墙:头像+昵称(群昵称>好友昵称兜底>wxid),替代原始 memberIds 串 -->
+        <div v-if="drawerGroup.channel === 'wechat'" class="yk-drawer__section">
+          <el-divider content-position="left">
+            群成员（{{ drawerMembers.length || (drawerGroup.member_count ?? 0) }}）
+          </el-divider>
+          <div v-loading="membersLoading" class="yk-members">
+            <div v-if="!membersLoading && drawerMembers.length === 0" class="yk-members__empty">
+              暂无成员数据（群消息派生，发过言/是本司好友的成员可识别）
+            </div>
+            <div v-for="m in drawerMembers" :key="m.member_id" class="yk-members__item">
+              <el-avatar :size="34" :src="m.avatar || undefined">
+                {{ memberLabel(m).slice(0, 1) }}
+              </el-avatar>
+              <div class="yk-members__meta">
+                <div class="yk-members__name" :title="memberLabel(m)">{{ memberLabel(m) }}</div>
+                <div v-if="memberLabel(m) !== m.member_id" class="yk-members__id">{{ m.member_id }}</div>
+              </div>
+            </div>
+          </div>
+        </div>
         <div v-for="section in drawerSections" :key="section.title" class="yk-drawer__section">
           <el-divider content-position="left">{{ section.title }}</el-divider>
           <dl class="yk-drawer__kv">
@@ -513,4 +643,46 @@ onMounted(() => {
 .yk-group-owner__meta {
   min-width: 0;
 }
+
+/* 群成员墙:头像+昵称网格(2026-09-10) */
+.yk-members {
+  display: grid;
+  grid-template-columns: repeat(auto-fill, minmax(150px, 1fr));
+  gap: 10px;
+  max-height: 320px;
+  overflow-y: auto;
+  min-height: 48px;
+}
+.yk-members__empty {
+  grid-column: 1 / -1;
+  color: var(--el-text-color-secondary);
+  font-size: 12px;
+  padding: 8px 0;
+}
+.yk-members__item {
+  display: flex;
+  align-items: center;
+  gap: 8px;
+  min-width: 0;
+}
+.yk-members__meta {
+  min-width: 0;
+  display: flex;
+  flex-direction: column;
+  line-height: 1.35;
+}
+.yk-members__name {
+  font-size: 13px;
+  overflow: hidden;
+  text-overflow: ellipsis;
+  white-space: nowrap;
+}
+.yk-members__id {
+  font-size: 11px;
+  color: var(--el-text-color-secondary);
+  overflow: hidden;
+  text-overflow: ellipsis;
+  white-space: nowrap;
+}
+
 </style>

yunkes/src/views/StaffFriends.vue

@@ -0,0 +1,587 @@
+<script setup lang="ts">
+/**
+ * 员工客户列表页(2026-09-08,对齐云客员工详情客户列表,用户截图版式)。
+ *
+ * 入口:员工列表行内「好友数/微信群数」(微信行)——账号维度下钻,与全局
+ * 客户列表(/customers)分离:固定 owner 过滤、微信客户/微信群两 tab、
+ * 搜索(昵称/微信号/备注名/手机号)、勾选批量「导出聊天记录」(服务端打
+ * zip,每会话一个 HTML)、行内查看/导出聊天记录(沿用 staff-chat 与
+ * /export/chat-html)。
+ *
+ * 列口径:发送/接收条数用 Customer.send_num/receive_num(云客 friend 记录
+ * 累计值,与截图同源);分页用真实过滤 total(本页恒有 owner 过滤,不存在
+ * 全局声明口径问题)。
+ */
+import { computed, onMounted, ref, watch } from 'vue'
+import { useRoute, useRouter } from 'vue-router'
+import { ElMessage } from 'element-plus'
+import { ArrowLeft } from '@element-plus/icons-vue'
+import { getAccounts, getCustomers, getGroups } from '@/api'
+import { downloadBlob } from '@/api/client'
+import type { Account, Customer, Group } from '@/api/types'
+import { exportListToCsv } from '@/utils/csvExport'
+import { formatTime } from '@/utils/format'
+import { fromTypeLabel, readField } from '@/utils/customerFields'
+
+const props = defineProps<{
+  /** 归属员工账号(wechatId) */
+  ownerId: string
+  /** customers=微信客户 tab(默认) / groups=微信群 tab */
+  tab?: string
+}>()
+
+const route = useRoute()
+const router = useRouter()
+
+const activeTab = ref<'customers' | 'groups'>(props.tab === 'groups' ? 'groups' : 'customers')
+
+// ---- 员工名:入口 query ?name= 直带;直链/刷新时经 /api/accounts 解析 ----
+const staffName = ref<string | null>(
+  route.query.name ? String(route.query.name) : null,
+)
+const resolvedName = ref<string | null>(null)
+const displayTitle = computed(() => staffName.value ?? resolvedName.value ?? props.ownerId)
+
+async function resolveName(): Promise<void> {
+  if (staffName.value) return
+  try {
+    const res = await getAccounts({ channel: 'wechat', page: 1, page_size: 100 })
+    const hit = res.items.find((a: Account) => a.account_id === props.ownerId)
+    resolvedName.value = hit?.nickname || hit?.user_name || null
+  } catch {
+    // 静默降级:标题显示 ownerId
+  }
+}
+
+// ---- 搜索(作用于当前 tab;/api/customers 与 /api/groups 均支持 q) ----
+const keyword = ref('')
+
+// ---- 微信客户 tab ----
+const customers = ref<Customer[]>([])
+const custTotal = ref(0)
+const custPage = ref(1)
+const custPageSize = ref(10)
+const custLoading = ref(false)
+const custError = ref<string | null>(null)
+
+// ---- 微信群 tab ----
+const groups = ref<Group[]>([])
+const groupTotal = ref(0)
+const groupPage = ref(1)
+const groupPageSize = ref(10)
+const groupLoading = ref(false)
+const groupError = ref<string | null>(null)
+
+async function loadCustomers(): Promise<void> {
+  custLoading.value = true
+  custError.value = null
+  try {
+    const res = await getCustomers({
+      channel: 'wechat',
+      owner_account_id: props.ownerId,
+      q: keyword.value.trim() || undefined,
+      page: custPage.value,
+      page_size: custPageSize.value,
+    })
+    customers.value = res.items
+    custTotal.value = res.total
+  } catch (e) {
+    custError.value = (e as Error).message
+    ElMessage.error(`客户列表加载失败：${(e as Error).message}`)
+  } finally {
+    custLoading.value = false
+  }
+}
+
+async function loadGroups(): Promise<void> {
+  groupLoading.value = true
+  groupError.value = null
+  try {
+    const res = await getGroups({
+      channel: 'wechat',
+      owner_account_id: props.ownerId,
+      q: keyword.value.trim() || undefined,
+      page: groupPage.value,
+      page_size: groupPageSize.value,
+    })
+    groups.value = res.items
+    groupTotal.value = res.total
+  } catch (e) {
+    groupError.value = (e as Error).message
+    ElMessage.error(`群列表加载失败：${(e as Error).message}`)
+  } finally {
+    groupLoading.value = false
+  }
+}
+
+function onSearch(): void {
+  custPage.value = 1
+  groupPage.value = 1
+  clearSelection()
+  if (activeTab.value === 'customers') loadCustomers()
+  else loadGroups()
+}
+
+// tab 切换:懒加载目标 tab(搜索词共享);URL param 同步,便于直链/刷新。
+function onTabChange(t: 'customers' | 'groups'): void {
+  clearSelection()
+  router.replace({
+    name: 'staff-friends',
+    params: { ownerId: props.ownerId, tab: t === 'groups' ? 'groups' : 'customers' },
+    query: route.query.name ? { name: String(route.query.name) } : undefined,
+  })
+  if (t === 'customers') {
+    if (customers.value.length === 0 && custTotal.value === 0) loadCustomers()
+  } else {
+    if (groups.value.length === 0 && groupTotal.value === 0) loadGroups()
+  }
+}
+
+// ---- 勾选 + 批量导出聊天记录(服务端 zip) ----
+const selected = ref<Customer[]>([])
+
+function onSelectionChange(rows: Customer[]): void {
+  selected.value = rows
+}
+
+function clearSelection(): void {
+  selected.value = []
+  custTableRef.value?.clearSelection()
+}
+const custTableRef = ref<{
+  clearSelection: () => void
+} | null>(null)
+
+const ZIP_LIMIT = 50
+const batchExporting = ref(false)
+
+async function exportChatZip(): Promise<void> {
+  if (selected.value.length === 0) return
+  if (selected.value.length > ZIP_LIMIT) {
+    ElMessage.warning(`一次最多导出 ${ZIP_LIMIT} 个会话，请减少勾选`)
+    return
+  }
+  batchExporting.value = true
+  try {
+    await downloadBlob('/export/chat-html-zip', {
+      channel: 'wechat',
+      owner_account_id: props.ownerId,
+      talker_ids: selected.value.map((c) => c.friend_id).join(','),
+    })
+    ElMessage.success(`已导出 ${selected.value.length} 个会话的聊天记录`)
+  } catch (e) {
+    ElMessage.error(`批量导出失败：${(e as Error).message}`)
+  } finally {
+    batchExporting.value = false
+  }
+}
+
+// ---- 行内:查看聊天记录 → 员工聊天窗口(single/group tab) ----
+function viewChat(row: Customer): void {
+  router.push({
+    name: 'staff-chat',
+    params: { ownerId: props.ownerId, tab: 'single', talkerId: row.friend_id },
+  })
+}
+
+function viewGroupChat(row: Group): void {
+  router.push({
+    name: 'staff-chat',
+    params: { ownerId: props.ownerId, tab: 'group', talkerId: row.room_id },
+  })
+}
+
+// ---- 行内:导出HTML聊天记录(可选时间范围,沿用全局客户列表的弹窗模式) ----
+const exportOpen = ref(false)
+const exportRow = ref<Customer | null>(null)
+// value-format="X" 绑秒级 unix 字符串;confirm 时 *1000 转毫秒。
+const exportRange = ref<[string, string] | null>(null)
+
+function openExport(row: Customer): void {
+  exportRow.value = row
+  exportRange.value = null
+  exportOpen.value = true
+}
+
+async function confirmExport(): Promise<void> {
+  const row = exportRow.value
+  if (!row) return
+  const params: Record<string, unknown> = {
+    channel: 'wechat',
+    owner_account_id: props.ownerId,
+    talker_id: row.friend_id,
+  }
+  if (exportRange.value) {
+    params.start = Number(exportRange.value[0]) * 1000
+    params.end = Number(exportRange.value[1]) * 1000
+  }
+  exportOpen.value = false
+  try {
+    await downloadBlob('/export/chat-html', params)
+    ElMessage.success('导出已开始')
+  } catch (e) {
+    ElMessage.error(`导出失败，请稍后重试：${(e as Error).message}`)
+  }
+}
+
+// ---- 导出 CSV(当前 tab + 搜索词 + owner 过滤) ----
+const exporting = ref(false)
+
+async function exportCsv(): Promise<void> {
+  exporting.value = true
+  try {
+    if (activeTab.value === 'customers') {
+      const r = await exportListToCsv<Customer>({
+        fetchPage: (page, pageSize) =>
+          getCustomers({
+            channel: 'wechat',
+            owner_account_id: props.ownerId,
+            q: keyword.value.trim() || undefined,
+            page,
+            page_size: pageSize,
+          }),
+        columns: [
+          { key: 'friend_nickname', label: '客户昵称' },
+          { key: 'friend_id', label: '微信号' },
+          { key: 'friend_remark', label: '备注名' },
+          { key: 'from_type', label: '数据来源', format: (r) => fromTypeLabel(readField(r, 'fromType')) },
+          {
+            key: 'last_chat_time',
+            label: '最近沟通时间',
+            format: (r) => (r.last_chat_time ? formatTime(r.last_chat_time) : '-'),
+          },
+          { key: 'send_num', label: '发送条数', format: (r) => r.send_num ?? '-' },
+          { key: 'receive_num', label: '接收条数', format: (r) => r.receive_num ?? '-' },
+        ],
+        filename: `微信客户_${props.ownerId}`,
+      })
+      ElMessage.success(`已导出 ${r.rows} 行`)
+    } else {
+      const r = await exportListToCsv<Group>({
+        fetchPage: (page, pageSize) =>
+          getGroups({
+            channel: 'wechat',
+            owner_account_id: props.ownerId,
+            q: keyword.value.trim() || undefined,
+            page,
+            page_size: pageSize,
+          }),
+        columns: [
+          { key: 'room_name', label: '群名称' },
+          { key: 'room_id', label: '群ID' },
+          { key: 'owner_name', label: '群主昵称' },
+          { key: 'owner_wxid', label: '群主wxId' },
+          { key: 'member_count', label: '群成员数量' },
+          { key: 'message_count', label: '消息数量' },
+        ],
+        filename: `微信群_${props.ownerId}`,
+      })
+      ElMessage.success(`已导出 ${r.rows} 行`)
+    }
+  } catch (e) {
+    ElMessage.error(`导出失败：${(e as Error).message}`)
+  } finally {
+    exporting.value = false
+  }
+}
+
+// ---- 展示 helper ----
+function avatarUrl(c: Customer): string | undefined {
+  const v = readField(c, 'friendHeadImageUrl')
+  return typeof v === 'string' && v !== '' ? v : undefined
+}
+
+function groupAvatarUrl(g: Group): string | undefined {
+  const v = g.raw_json?.headImageUrl
+  return typeof v === 'string' && v !== '' ? v : undefined
+}
+
+function initials(c: Customer): string {
+  const nick = c.friend_nickname || c.friend_id
+  return nick ? nick.slice(0, 1).toUpperCase() : '?'
+}
+
+function groupInitials(g: Group): string {
+  const n = g.room_name || g.room_id
+  return n ? n.slice(0, 1) : '?'
+}
+
+function goBack(): void {
+  if (window.history.length > 1) router.back()
+  else router.push({ path: '/staff', query: { channel: 'wechat' } })
+}
+
+// ---- 生命周期 + 路由参数变化(同组件不同员工切换) ----
+watch(
+  () => [props.ownerId, props.tab] as const,
+  () => {
+    activeTab.value = props.tab === 'groups' ? 'groups' : 'customers'
+    resetAndLoad()
+  },
+)
+
+function resetAndLoad(): void {
+  custPage.value = 1
+  groupPage.value = 1
+  clearSelection()
+  loadCustomers()
+  if (activeTab.value === 'groups') loadGroups()
+}
+
+onMounted(() => {
+  resolveName()
+  loadCustomers()
+  if (activeTab.value === 'groups') loadGroups()
+})
+</script>
+
+<template>
+  <div class="sf-page">
+    <!-- 头部:返回 + 员工名 + 两 tab + 搜索/导出行 -->
+    <div class="sf-header">
+      <div class="sf-header__title">
+        <el-button :icon="ArrowLeft" circle size="small" @click="goBack" />
+        <h1>{{ displayTitle }}</h1>
+        <span class="sf-header__sub">微信号：{{ ownerId }}</span>
+      </div>
+      <el-tabs v-model="activeTab" class="sf-tabs" @tab-change="onTabChange($event as 'customers' | 'groups')">
+        <el-tab-pane label="微信客户" name="customers" />
+        <el-tab-pane label="微信群" name="groups" />
+      </el-tabs>
+      <div class="sf-toolbar">
+        <el-input
+          v-model="keyword"
+          class="sf-search"
+          placeholder="支持微信昵称、微信号、备注名、手机号搜索"
+          clearable
+          @keyup.enter="onSearch"
+          @clear="onSearch"
+        />
+        <el-button type="primary" @click="onSearch">查询</el-button>
+        <el-button :loading="exporting" @click="exportCsv">导出</el-button>
+        <el-button
+          v-if="activeTab === 'customers'"
+          :disabled="selected.length === 0"
+          :loading="batchExporting"
+          @click="exportChatZip"
+        >
+          导出聊天记录{{ selected.length > 0 ? `(${selected.length})` : '' }}
+        </el-button>
+      </div>
+    </div>
+
+    <!-- 微信客户表 -->
+    <div v-show="activeTab === 'customers'" class="sf-card" v-loading="custLoading">
+      <el-alert v-if="custError" :title="`客户列表加载失败：${custError}`" type="error" show-icon :closable="false" />
+      <el-table
+        ref="custTableRef"
+        :data="customers"
+        row-key="friend_id"
+        empty-text="该员工暂无客户"
+        @selection-change="onSelectionChange"
+      >
+        <el-table-column type="selection" width="42" reserve-selection />
+        <el-table-column label="客户微信" min-width="220">
+          <template #default="{ row }">
+            <div class="sf-wechat">
+              <el-avatar :size="36" :src="avatarUrl(row)" shape="square">
+                {{ initials(row) }}
+              </el-avatar>
+              <div class="sf-wechat__meta">
+                <span class="sf-wechat__nick">{{ row.friend_nickname || '--' }}</span>
+                <span class="sf-wechat__id">{{ row.friend_id }}</span>
+              </div>
+            </div>
+          </template>
+        </el-table-column>
+        <el-table-column label="数据来源" width="110">
+          <template #default="{ row }">{{ fromTypeLabel(row.from_type ?? readField(row, 'fromType')) }}</template>
+        </el-table-column>
+        <el-table-column label="客户备注名" min-width="120">
+          <template #default="{ row }">{{ row.friend_remark || '-' }}</template>
+        </el-table-column>
+        <el-table-column label="最近沟通时间" width="170">
+          <template #default="{ row }">{{ row.last_chat_time ? formatTime(row.last_chat_time) : '-' }}</template>
+        </el-table-column>
+        <el-table-column label="发送条数" width="95" align="right">
+          <template #default="{ row }">{{ row.send_num ?? '-' }}</template>
+        </el-table-column>
+        <el-table-column label="接收条数" width="95" align="right">
+          <template #default="{ row }">{{ row.receive_num ?? '-' }}</template>
+        </el-table-column>
+        <el-table-column label="操作" width="160" fixed="right">
+          <template #default="{ row }">
+            <div class="sf-actions">
+              <el-button link type="primary" size="small" @click="viewChat(row)">查看聊天记录</el-button>
+              <el-button link type="primary" size="small" @click="openExport(row)">导出HTML聊天记录</el-button>
+            </div>
+          </template>
+        </el-table-column>
+      </el-table>
+      <div class="sf-pager">
+        <el-pagination
+          :current-page="custPage"
+          :page-size="custPageSize"
+          :page-sizes="[10, 20, 50]"
+          :total="custTotal"
+          layout="total, sizes, prev, pager, next"
+          @current-change="(p: number) => { custPage = p; loadCustomers() }"
+          @size-change="(s: number) => { custPageSize = s; custPage = 1; loadCustomers() }"
+        />
+      </div>
+    </div>
+
+    <!-- 微信群表 -->
+    <div v-show="activeTab === 'groups'" class="sf-card" v-loading="groupLoading">
+      <el-alert v-if="groupError" :title="`群列表加载失败：${groupError}`" type="error" show-icon :closable="false" />
+      <el-table :data="groups" row-key="room_id" empty-text="该员工暂无群">
+        <el-table-column label="群名称" min-width="240">
+          <template #default="{ row }">
+            <div class="sf-wechat">
+              <el-avatar :size="36" :src="groupAvatarUrl(row)" shape="square">
+                {{ groupInitials(row) }}
+              </el-avatar>
+              <div class="sf-wechat__meta">
+                <span class="sf-wechat__nick">{{ row.room_name || '--' }}</span>
+                <span class="sf-wechat__id">{{ row.room_id }}</span>
+              </div>
+            </div>
+          </template>
+        </el-table-column>
+        <el-table-column label="群主" min-width="150">
+          <template #default="{ row }">
+            <div class="sf-wechat__meta">
+              <span>{{ row.owner_name || '-' }}</span>
+              <span v-if="row.owner_wxid" class="sf-wechat__id">{{ row.owner_wxid }}</span>
+            </div>
+          </template>
+        </el-table-column>
+        <el-table-column label="群成员数量" width="110" align="right">
+          <template #default="{ row }">{{ row.member_count ?? '-' }}</template>
+        </el-table-column>
+        <el-table-column label="消息数量" width="100" align="right">
+          <template #default="{ row }">{{ row.message_count ?? '-' }}</template>
+        </el-table-column>
+        <el-table-column label="最近消息时间" width="170">
+          <template #default="{ row }">{{ row.last_chat_time ? formatTime(row.last_chat_time) : '-' }}</template>
+        </el-table-column>
+        <el-table-column label="操作" width="130" fixed="right">
+          <template #default="{ row }">
+            <el-button link type="primary" size="small" @click="viewGroupChat(row)">查看群聊记录</el-button>
+          </template>
+        </el-table-column>
+      </el-table>
+      <div class="sf-pager">
+        <el-pagination
+          :current-page="groupPage"
+          :page-size="groupPageSize"
+          :page-sizes="[10, 20, 50]"
+          :total="groupTotal"
+          layout="total, sizes, prev, pager, next"
+          @current-change="(p: number) => { groupPage = p; loadGroups() }"
+          @size-change="(s: number) => { groupPageSize = s; groupPage = 1; loadGroups() }"
+        />
+      </div>
+    </div>
+
+    <!-- 行内导出时间范围弹窗(对齐全局客户列表) -->
+    <el-dialog v-model="exportOpen" title="导出HTML聊天记录" width="420px">
+      <el-date-picker
+        v-model="exportRange"
+        type="datetimerange"
+        value-format="X"
+        range-separator="至"
+        start-placeholder="开始时间"
+        end-placeholder="结束时间"
+        style="width: 100%"
+      />
+      <template #footer>
+        <el-button @click="exportOpen = false">取消</el-button>
+        <el-button type="primary" @click="confirmExport">导出</el-button>
+      </template>
+    </el-dialog>
+  </div>
+</template>
+
+<style scoped>
+.sf-page {
+  padding: 12px;
+  display: flex;
+  flex-direction: column;
+  gap: 12px;
+  height: 100%;
+  overflow: auto;
+}
+.sf-header {
+  background: #fff;
+  border-radius: 8px;
+  padding: 12px 16px 0;
+}
+.sf-header__title {
+  display: flex;
+  align-items: center;
+  gap: 10px;
+}
+.sf-header__title h1 {
+  margin: 0;
+  font-size: 17px;
+}
+.sf-header__sub {
+  color: var(--el-text-color-secondary);
+  font-size: 12px;
+}
+.sf-toolbar {
+  display: flex;
+  align-items: center;
+  gap: 8px;
+  padding: 10px 0 12px;
+}
+.sf-search {
+  width: 340px;
+}
+.sf-card {
+  background: #fff;
+  border-radius: 8px;
+  padding: 12px 16px;
+  flex: 1;
+  min-height: 0;
+}
+.sf-wechat {
+  display: flex;
+  align-items: center;
+  gap: 10px;
+}
+.sf-wechat__meta {
+  display: flex;
+  flex-direction: column;
+  line-height: 1.4;
+  min-width: 0;
+}
+.sf-wechat__nick {
+  font-weight: 500;
+  overflow: hidden;
+  text-overflow: ellipsis;
+  white-space: nowrap;
+}
+.sf-wechat__id {
+  color: var(--el-text-color-secondary);
+  font-size: 12px;
+  overflow: hidden;
+  text-overflow: ellipsis;
+  white-space: nowrap;
+}
+.sf-actions {
+  display: flex;
+  flex-direction: column;
+  align-items: flex-start;
+  gap: 2px;
+}
+.sf-actions .el-button + .el-button {
+  margin-left: 0;
+}
+.sf-pager {
+  display: flex;
+  justify-content: flex-end;
+  padding-top: 12px;
+}
+</style>

yunkes/src/views/StaffList.vue

@@ -239,6 +239,16 @@ function waSerial(index: number): number {
 // ---------------------------------------------------------------------------
 
 function viewCustomers(row: Account): void {
+  // 微信行 → 员工客户列表独立页(2026-09-08 对齐云客员工详情,账号维度
+  // 下钻:两 tab/搜索/批量导出);WA 行保持全局客户列表(该页暂仅微信)。
+  if (row.channel === 'wechat') {
+    router.push({
+      name: 'staff-friends',
+      params: { ownerId: row.account_id, tab: 'customers' },
+      query: { name: row.nickname || row.user_name || '' },
+    })
+    return
+  }
   channelStore.setChannel(row.channel)
   router.push({
     path: '/customers',
@@ -247,6 +257,15 @@ function viewCustomers(row: Account): void {
 }
 
 function viewGroups(row: Account): void {
+  // 同上:微信群数 → 员工客户列表的群 tab;WA 保持原路径。
+  if (row.channel === 'wechat') {
+    router.push({
+      name: 'staff-friends',
+      params: { ownerId: row.account_id, tab: 'groups' },
+      query: { name: row.nickname || row.user_name || '' },
+    })
+    return
+  }
   channelStore.setChannel(row.channel)
   if (row.channel === 'whatsapp') {
     // WA:对齐云客,群列表在客户列表页的子 tab(2026-08-24)

yunkes/src/views/analytics/DashboardView.vue

@@ -143,16 +143,16 @@
           <template #default="{ row }">{{ fmt(row.first_contact_cnt) }}</template>
         </el-table-column>
         <el-table-column label="首响" align="right">
-          <template #default="{ row }">{{ fmtFr(row.fr_avg_ms) }}</template>
+          <template #default="{ row }">{{ formatMsDuration(row.fr_avg_ms) }}</template>
         </el-table-column>
         <el-table-column label="回复率" align="right">
-          <template #default="{ row }">{{ fmtPct(row.reply_rate) }}</template>
+          <template #default="{ row }">{{ formatRatio(row.reply_rate) }}</template>
         </el-table-column>
         <el-table-column label="通话时长" align="right">
           <template #default="{ row }">{{ fmtDur(row.call_seconds) }}</template>
         </el-table-column>
         <el-table-column label="接通率" align="right">
-          <template #default="{ row }">{{ fmtPct(row.answer_rate) }}</template>
+          <template #default="{ row }">{{ formatRatio(row.answer_rate) }}</template>
         </el-table-column>
         <el-table-column label="删粉/拉黑" align="right">
           <template #default="{ row }">{{ fmtDelBlocked(row) }}</template>
@@ -187,7 +187,7 @@ import {
   type StaffRankingRow,
 } from '@/api/analytics'
 import { useChart } from '@/composables/useChart'
-import { formatTimeShort } from '@/utils/format'
+import { formatMsDuration, formatRatio, formatTimeShort } from '@/utils/format'
 
 const router = useRouter()
 
@@ -295,16 +295,8 @@ const fmt = (n: number | undefined | null) => (n ?? 0).toLocaleString()
 const assets = computed<CustomerAssets | null>(() => data.value?.customer_assets ?? null)
 
 // ── 排行新列格式化 ──
-// 首响:<1h 显「X分Y秒」,≥1h 显「X小时Y分」;null(无样本)显 '-'
+// 首响/百分比用共享版(formatMsDuration/formatRatio,utils/format——批次C
-const fmtFr = (ms: number | null) => {
+// 驾驶舱组件同口径,原本地 fmtFr/fmtPct 已提升去重)
-  if (ms == null) return '-'
-  const totalSec = Math.round(ms / 1000)
-  const mins = Math.floor(totalSec / 60)
-  if (mins < 60) return `${mins}分${totalSec % 60}秒`
-  return `${Math.floor(mins / 60)}小时${mins % 60}分`
-}
-// 百分比 1 位小数(回复率/接通率);null 显 '-'
-const fmtPct = (v: number | null) => (v == null ? '-' : `${(v * 100).toFixed(1)}%`)
 // 通话时长(秒):<1h 显「X分」,否则「X小时Y分」;0/null 显 '-'
 const fmtDur = (s: number | null) => {
   if (!s) return '-'

yunkes/src/views/management/EmployeeAnalyticsView.vue

@@ -0,0 +1,726 @@
+<template>
+  <div class="emp-analytics">
+    <!-- 筛选栏:渠道/时间(URL 真源)+口径入口;aside=对比模式选择器。
+         compare 仅客户端显示态:employees 行恒带四对比(current/prev/
+         baseline/median),后端 employees 端点也无 compare 入参 -->
+    <ManagementFilterBar
+      :channel="channel"
+      :start="start"
+      :end="end"
+      :compare="compare"
+      @apply="apply"
+      @open-defs="defsVisible = true"
+    >
+      <template #aside>
+        <el-select
+          :model-value="compare"
+          class="compare-select"
+          @change="onCompareChange"
+        >
+          <el-option label="对比:上期" value="previous" />
+          <el-option label="对比:个人基线" value="personal_baseline" />
+          <el-option label="对比:团队中位数" value="team_median" />
+        </el-select>
+      </template>
+    </ManagementFilterBar>
+
+    <!-- 工具行:关键词(防抖)/在职状态/四视图;口径入口在筛选栏自带 -->
+    <div class="toolbar">
+      <el-input
+        v-model="keywordInput"
+        placeholder="姓名/ID"
+        clearable
+        :prefix-icon="Search"
+        class="kw-input"
+      />
+      <el-select :model-value="status" class="status-select" @change="onStatusChange">
+        <el-option label="全部" value="all" />
+        <el-option label="在职" value="on_job" />
+        <el-option label="离线" value="offline" />
+      </el-select>
+      <el-radio-group :model-value="view" @change="onViewChange">
+        <el-radio-button value="management">管理概览</el-radio-button>
+        <el-radio-button value="workload">工作负载</el-radio-button>
+        <el-radio-button value="service">服务质量</el-radio-button>
+        <el-radio-button value="customer">客户经营</el-radio-button>
+      </el-radio-group>
+      <div class="spacer" />
+      <el-button
+        type="primary"
+        :disabled="selectedRows.length < 2 || selectedRows.length > 5"
+        @click="compareVisible = true"
+      >对比已选 ({{ selectedRows.length }})</el-button>
+      <el-button :loading="exporting" @click="exportCsv">导出CSV</el-button>
+      <!-- trial 常显:载荷无页面级 trial 键,批次C/D 评分处于试算期(同驾驶舱) -->
+      <DataAsOfBadge
+        :data-as-of="resp?.data_as_of ?? null"
+        :metric-version="resp?.metric_version"
+        :trial="true"
+        :config-source="resp?.config_source"
+      />
+    </div>
+
+    <!-- 错误态:alert+重试;resp 不清空,保留上次成功数据 -->
+    <el-alert v-if="loadError" type="error" :closable="false" class="top-alert">
+      <template #title>
+        <span>{{ loadError }}</span>
+        <el-button size="small" type="primary" class="retry-btn" @click="load">重试</el-button>
+      </template>
+    </el-alert>
+
+    <!-- 主表:服务端排序/分页(sortable=custom,数据恒随 URL 查询);
+         列组随视图切换;多选(跨页保留)供对比抽屉。非排序列头 hover 提示,
+         关键列头「?」点击开指标口径抽屉 -->
+    <el-table
+      ref="tableRef"
+      v-loading="loading"
+      :data="rows"
+      row-key="user_id"
+      :default-sort="defaultSort"
+      @selection-change="onSelectionChange"
+      @sort-change="onSortChange"
+    >
+      <el-table-column type="selection" width="42" reserve-selection />
+      <el-table-column label="姓名" min-width="150">
+        <template #default="{ row }">
+          <!-- 带窗进详情:goDetail 随行 channel/start/end/compare(D3) -->
+          <el-link type="primary" underline="never" @click="goDetail(row)">
+            {{ row.name || row.user_id }}
+          </el-link>
+          <div class="uid">{{ row.user_id }}</div>
+        </template>
+      </el-table-column>
+      <el-table-column width="64">
+        <template #header>
+          <el-tooltip content="该列不支持服务端排序" placement="top"><span>在职</span></el-tooltip>
+        </template>
+        <template #default="{ row }">
+          <el-tag v-if="row.is_on_job === true" size="small" type="success">在职</el-tag>
+          <el-tag v-else-if="row.is_on_job === false" size="small" type="info">离职</el-tag>
+          <span v-else class="dim">--</span>
+        </template>
+      </el-table-column>
+
+      <!-- ── 管理概览:评分/异常/规模/维度 ── -->
+      <template v-if="view === 'management'">
+        <el-table-column
+          prop="total_score"
+          width="120"
+          sortable="custom"
+          :sort-orders="['descending', 'ascending']"
+        >
+          <template #header>
+            <span>综合分
+              <el-tooltip content="查看指标口径" placement="top">
+                <el-icon class="hd-q" @click.stop="defsVisible = true"><QuestionFilled /></el-icon>
+              </el-tooltip>
+            </span>
+          </template>
+          <template #default="{ row }">
+            <el-tooltip
+              v-if="row.score.score_status === 'insufficient_sample'"
+              content="样本不足·不参与考核"
+              placement="top"
+            >
+              <span class="dim">--</span>
+            </el-tooltip>
+            <span v-else class="score-cell">
+              {{ Math.round(row.score.total_score ?? 0) }}
+              <el-tag
+                v-if="row.score.grade"
+                size="small"
+                :type="gradeType(row.score.grade)"
+                class="grade-tag"
+              >{{ row.score.grade }}</el-tag>
+              <span v-if="row.score.trial" class="trial-mark" title="试算期评分">试</span>
+            </span>
+          </template>
+        </el-table-column>
+        <el-table-column
+          prop="anomaly_severity"
+          label="异常"
+          width="90"
+          sortable="custom"
+          :sort-orders="['descending', 'ascending']"
+        >
+          <template #default="{ row }">
+            <span :class="row.anomaly_count > 0 ? 'anomaly-hot' : 'dim'">{{ row.anomaly_count }}</span>
+            <div v-if="row.anomaly_count > 0" class="cell-sub">权重 {{ row.anomaly_weight }}</div>
+          </template>
+        </el-table-column>
+        <el-table-column
+          prop="active_friends"
+          width="100"
+          sortable="custom"
+          :sort-orders="['descending', 'ascending']"
+        >
+          <template #header>
+            <span>活跃客户
+              <el-tooltip content="查看指标口径" placement="top">
+                <el-icon class="hd-q" @click.stop="defsVisible = true"><QuestionFilled /></el-icon>
+              </el-tooltip>
+            </span>
+          </template>
+          <template #default="{ row }">{{ fmtInt(num(row, 'active_friends')) }}</template>
+        </el-table-column>
+        <el-table-column min-width="100">
+          <template #header>
+            <el-tooltip content="该列不支持服务端排序" placement="top"><span>消息量</span></el-tooltip>
+          </template>
+          <template #default="{ row }">{{ fmtInt(msgTotal(row)) }}</template>
+        </el-table-column>
+        <el-table-column min-width="110">
+          <template #header>
+            <el-tooltip content="该列不支持服务端排序" placement="top"><span>串/被回</span></el-tooltip>
+          </template>
+          <template #default="{ row }">
+            {{ fmtInt(num(row, 'cust_threads')) }} / {{ fmtInt(num(row, 'threads_answered')) }}
+          </template>
+        </el-table-column>
+        <el-table-column min-width="90">
+          <template #header>
+            <el-tooltip content="该列不支持服务端排序" placement="top"><span>客户经营</span></el-tooltip>
+          </template>
+          <template #default="{ row }">
+            <span :class="dimScore(row, 'customer') == null ? 'dim' : ''">{{ dimScoreText(row, 'customer') }}</span>
+          </template>
+        </el-table-column>
+        <el-table-column min-width="90">
+          <template #header>
+            <el-tooltip content="该列不支持服务端排序" placement="top"><span>服务质量</span></el-tooltip>
+          </template>
+          <template #default="{ row }">
+            <span :class="dimScore(row, 'service') == null ? 'dim' : ''">{{ dimScoreText(row, 'service') }}</span>
+          </template>
+        </el-table-column>
+        <el-table-column min-width="90">
+          <template #header>
+            <el-tooltip content="该列不支持服务端排序" placement="top"><span>工作负载</span></el-tooltip>
+          </template>
+          <template #default="{ row }">
+            <span :class="dimScore(row, 'workload') == null ? 'dim' : ''">{{ dimScoreText(row, 'workload') }}</span>
+          </template>
+        </el-table-column>
+      </template>
+
+      <!-- ── 工作负载:规模/消息/通话/串 ── -->
+      <template v-else-if="view === 'workload'">
+        <el-table-column
+          prop="active_friends"
+          width="100"
+          sortable="custom"
+          :sort-orders="['descending', 'ascending']"
+        >
+          <template #header>
+            <span>活跃客户
+              <el-tooltip content="查看指标口径" placement="top">
+                <el-icon class="hd-q" @click.stop="defsVisible = true"><QuestionFilled /></el-icon>
+              </el-tooltip>
+            </span>
+          </template>
+          <template #default="{ row }">{{ fmtInt(num(row, 'active_friends')) }}</template>
+        </el-table-column>
+        <el-table-column min-width="100">
+          <template #header>
+            <el-tooltip content="该列不支持服务端排序" placement="top"><span>活跃群(日均)</span></el-tooltip>
+          </template>
+          <template #default="{ row }">{{ fmtAvg(num(row, 'active_rooms_avg')) }}</template>
+        </el-table-column>
+        <el-table-column min-width="130">
+          <template #header>
+            <el-tooltip content="该列不支持服务端排序" placement="top"><span>消息发/收</span></el-tooltip>
+          </template>
+          <template #default="{ row }">
+            {{ fmtInt(num(row, 'msg_sent')) }} / {{ fmtInt(num(row, 'msg_recv')) }}
+          </template>
+        </el-table-column>
+        <el-table-column min-width="130">
+          <template #header>
+            <el-tooltip content="该列不支持服务端排序" placement="top"><span>通话量/时长</span></el-tooltip>
+          </template>
+          <template #default="{ row }">
+            {{ fmtInt(num(row, 'call_count')) }} / {{ fmtSec(num(row, 'call_seconds')) }}
+          </template>
+        </el-table-column>
+        <el-table-column
+          prop="cust_threads"
+          label="串"
+          width="80"
+          sortable="custom"
+          :sort-orders="['descending', 'ascending']"
+        >
+          <template #default="{ row }">{{ fmtInt(num(row, 'cust_threads')) }}</template>
+        </el-table-column>
+      </template>
+
+      <!-- ── 服务质量:首响分位/回复率/被回串 ── -->
+      <template v-else-if="view === 'service'">
+        <el-table-column min-width="110">
+          <template #header>
+            <el-tooltip content="该列不支持服务端排序" placement="top"><span>首响P50</span></el-tooltip>
+          </template>
+          <template #default="{ row }">{{ formatMsDuration(num(row, 'fr_p50_ms')) }}</template>
+        </el-table-column>
+        <el-table-column min-width="110">
+          <template #header>
+            <span>
+              <el-tooltip content="该列不支持服务端排序" placement="top"><span>首响P90</span></el-tooltip>
+              <el-tooltip content="查看指标口径" placement="top">
+                <el-icon class="hd-q" @click.stop="defsVisible = true"><QuestionFilled /></el-icon>
+              </el-tooltip>
+            </span>
+          </template>
+          <template #default="{ row }">{{ formatMsDuration(num(row, 'fr_p90_ms')) }}</template>
+        </el-table-column>
+        <el-table-column min-width="100">
+          <template #header>
+            <el-tooltip content="该列不支持服务端排序" placement="top"><span>2h回复率</span></el-tooltip>
+          </template>
+          <template #default="{ row }">{{ replyRate(row, 'reply_2h_count') }}</template>
+        </el-table-column>
+        <el-table-column min-width="110">
+          <template #header>
+            <el-tooltip content="该列不支持服务端排序" placement="top"><span>24h回复率</span></el-tooltip>
+          </template>
+          <template #default="{ row }">{{ replyRate(row, 'reply_24h_count') }}</template>
+        </el-table-column>
+        <el-table-column min-width="110">
+          <template #header>
+            <el-tooltip content="该列不支持服务端排序" placement="top"><span>被回/串</span></el-tooltip>
+          </template>
+          <template #default="{ row }">
+            {{ fmtInt(num(row, 'threads_answered')) }} / {{ fmtInt(num(row, 'cust_threads')) }}
+          </template>
+        </el-table-column>
+      </template>
+
+      <!-- ── 客户经营:生命周期四态+活跃占比 ── -->
+      <template v-else>
+        <el-table-column min-width="80">
+          <template #header>
+            <el-tooltip content="该列不支持服务端排序" placement="top"><span>新客</span></el-tooltip>
+          </template>
+          <template #default="{ row }">{{ fmtInt(num(row, 'new_customer')) }}</template>
+        </el-table-column>
+        <el-table-column min-width="80">
+          <template #header>
+            <el-tooltip content="该列不支持服务端排序" placement="top"><span>降温</span></el-tooltip>
+          </template>
+          <template #default="{ row }">{{ fmtInt(num(row, 'cooling_customer')) }}</template>
+        </el-table-column>
+        <el-table-column min-width="100">
+          <template #header>
+            <span>
+              <el-tooltip content="该列不支持服务端排序" placement="top"><span>沉睡(期末)</span></el-tooltip>
+              <el-tooltip content="查看指标口径" placement="top">
+                <el-icon class="hd-q" @click.stop="defsVisible = true"><QuestionFilled /></el-icon>
+              </el-tooltip>
+            </span>
+          </template>
+          <template #default="{ row }">{{ fmtInt(num(row, 'dormant_customer')) }}</template>
+        </el-table-column>
+        <el-table-column min-width="100">
+          <template #header>
+            <el-tooltip content="该列不支持服务端排序" placement="top"><span>回流(期内)</span></el-tooltip>
+          </template>
+          <template #default="{ row }">{{ fmtInt(num(row, 'reactivated_customer')) }}</template>
+        </el-table-column>
+        <el-table-column min-width="100">
+          <template #header>
+            <el-tooltip content="该列不支持服务端排序" placement="top"><span>活跃占比</span></el-tooltip>
+          </template>
+          <template #default="{ row }">{{ activeShare(row) }}</template>
+        </el-table-column>
+      </template>
+
+      <template #empty>
+        <el-empty :image-size="72" description="无匹配员工——调整关键词/状态" />
+      </template>
+    </el-table>
+
+    <el-pagination
+      :current-page="page"
+      :page-size="PAGE_SIZE"
+      :total="total"
+      layout="total, prev, pager, next"
+      class="pager"
+      @current-change="onPageChange"
+    />
+
+    <!-- 对比抽屉(2-5 行)与指标口径抽屉(自缓存) -->
+    <EmployeeCompareDrawer v-model="compareVisible" :rows="selectedRows" />
+    <MetricDefsDrawer v-model="defsVisible" />
+  </div>
+</template>
+
+<script setup lang="ts">
+// 员工总览(经营管理批次D):四视图列组共用 /management/employees 行集,
+// 服务端排序(仅 综合分/异常/活跃客户/串 四列)+ 服务端分页,query 全量
+// 真源(view/keyword/status/sort_by/sort_order/page),刷新/分享保持。
+// 多选 2-5 人开对比抽屉;CSV 导出当前视图列并带口径注释前置行。
+import { computed, ref, watch } from 'vue'
+import { useRoute, useRouter } from 'vue-router'
+import { ElMessage, type TableInstance } from 'element-plus'
+// QuestionFilled 全局已注册(main.ts 全量挂载),显式导入与项目其他页一致
+import { QuestionFilled, Search } from '@element-plus/icons-vue'
+import {
+  getEmployees,
+  type EmployeeRow,
+  type EmployeesResp,
+} from '@/api/management'
+import { useManagementFilters } from '@/composables/useManagementFilters'
+import { exportListToCsv, type CsvColumn } from '@/utils/csvExport'
+import { formatMsDuration, formatRatio } from '@/utils/format'
+import ManagementFilterBar from '@/components/management/ManagementFilterBar.vue'
+import DataAsOfBadge from '@/components/management/DataAsOfBadge.vue'
+import MetricDefsDrawer from '@/components/management/MetricDefsDrawer.vue'
+import EmployeeCompareDrawer from '@/components/management/EmployeeCompareDrawer.vue'
+
+const PAGE_SIZE = 20
+type EmpView = 'management' | 'workload' | 'service' | 'customer'
+type SortBy = 'anomaly_severity' | 'total_score' | 'active_friends' | 'cust_threads'
+const VIEW_VALUES: readonly EmpView[] = ['management', 'workload', 'service', 'customer']
+const SORT_BY_VALUES: readonly SortBy[] = ['anomaly_severity', 'total_score', 'active_friends', 'cust_threads']
+
+const route = useRoute()
+const router = useRouter()
+const { channel, start, end, compare, apply } = useManagementFilters()
+
+// ── 页面级 query 真源(白名单外回默认;与后端 Literal 校验同域) ──
+const view = computed<EmpView>(() =>
+  VIEW_VALUES.includes(route.query.view as EmpView) ? (route.query.view as EmpView) : 'management')
+const keyword = computed(() => (typeof route.query.keyword === 'string' ? route.query.keyword.trim() : ''))
+const status = computed<'all' | 'on_job' | 'offline'>(() =>
+  route.query.status === 'on_job' || route.query.status === 'offline' ? route.query.status : 'all')
+const sortBy = computed<SortBy>(() =>
+  SORT_BY_VALUES.includes(route.query.sort_by as SortBy) ? (route.query.sort_by as SortBy) : 'anomaly_severity')
+const sortOrder = computed<'asc' | 'desc'>(() => (route.query.sort_order === 'asc' ? 'asc' : 'desc'))
+const page = computed(() => {
+  const n = Number(route.query.page)
+  return Number.isInteger(n) && n >= 1 ? n : 1
+})
+
+// ── 加载(seq 守卫沿用驾驶舱/ChurnView 模式) ──
+const resp = ref<EmployeesResp | null>(null)
+const loading = ref(false)
+const loadError = ref<string | null>(null)
+let seq = 0
+
+function queryParams(over: Record<string, unknown> = {}): Record<string, unknown> {
+  return {
+    channel: channel.value,
+    start: start.value,
+    end: end.value,
+    view: view.value,
+    keyword: keyword.value || undefined,
+    status: status.value,
+    sort_by: sortBy.value,
+    sort_order: sortOrder.value,
+    page: page.value,
+    page_size: PAGE_SIZE,
+    ...over,
+  }
+}
+
+async function load(): Promise<void> {
+  const my = ++seq
+  loading.value = true
+  loadError.value = null
+  try {
+    const r = await getEmployees(queryParams())
+    if (my !== seq) return
+    resp.value = r
+  } catch (e) {
+    // 失败保留上次成功数据,仅标记 error 供 alert+重试
+    if (my === seq) loadError.value = e instanceof Error ? e.message : String(e)
+  } finally {
+    if (my === seq) loading.value = false
+  }
+}
+
+watch([channel, start, end, view, keyword, status, sortBy, sortOrder, page], load, { immediate: true })
+
+const rows = computed<EmployeeRow[]>(() => resp.value?.rows ?? [])
+const total = computed(() => resp.value?.total ?? 0)
+
+// ── 工具行交互(全部写回 URL;筛选变化重置分页) ──
+const keywordInput = ref(keyword.value)
+let kwTimer: ReturnType<typeof setTimeout> | undefined
+watch(keywordInput, (v) => {
+  if (kwTimer) clearTimeout(kwTimer)
+  kwTimer = setTimeout(() => {
+    if ((v.trim() || '') !== keyword.value) apply({ keyword: v.trim() || undefined, page: undefined })
+  }, 300)
+})
+// 外部导航(回退/直链)同步输入框显示
+watch(keyword, (v) => {
+  if (v !== keywordInput.value.trim()) keywordInput.value = v
+})
+
+function onStatusChange(v: string | number | boolean): void {
+  apply({ status: v === 'all' ? undefined : String(v), page: undefined })
+}
+
+// 切视图:列组变化,排序回默认(异常降序)、回第一页
+function onViewChange(v: string | number | boolean): void {
+  apply({ view: String(v), sort_by: undefined, sort_order: undefined, page: undefined })
+}
+
+function onCompareChange(v: string | number | boolean): void {
+  apply({ compare: v === 'previous' ? undefined : String(v) })
+}
+
+function onPageChange(p: number): void {
+  apply({ page: p === 1 ? undefined : p })
+}
+
+// ── 服务端排序:el-table custom 模式(全仓首个),prop 即后端 sort_by 值 ──
+const tableRef = ref<TableInstance>()
+const defaultSort = computed(() => ({
+  prop: sortBy.value,
+  order: sortOrder.value === 'asc' ? ('ascending' as const) : ('descending' as const),
+}))
+
+function onSortChange({ prop, order }: { prop: string; order: 'ascending' | 'descending' | null }): void {
+  const by = SORT_BY_VALUES.find((v) => v === prop)
+  if (!by || !order) return // :sort-orders 两态,order 不会 null,防御
+  apply({ sort_by: by, sort_order: order === 'ascending' ? 'asc' : 'desc', page: undefined })
+}
+
+// URL 驱动的排序/视图变化(回退/切视图重置/直链)同步表头指示:sort() 对
+// custom 列只设指示不本地排序(EP watcher sortData 对字符串 sortable 直接
+// 返回原数据);prop 在当前视图无该列时为无害 no-op
+watch([view, sortBy, sortOrder], ([, by, order]) => {
+  tableRef.value?.sort(by, order === 'asc' ? 'ascending' : 'descending')
+}, { flush: 'post' })
+
+// ── 取数/格式化(metrics 数值键;user_id 透传键是字符串,typeof 守卫) ──
+function num(r: EmployeeRow, key: string): number | null {
+  const v = r.metrics[key]
+  return typeof v === 'number' ? v : null
+}
+function fmtInt(v: number | null | undefined): string {
+  return v == null ? '--' : v.toLocaleString()
+}
+function fmtAvg(v: number | null | undefined): string {
+  return v == null ? '--' : v.toLocaleString('zh-CN', { maximumFractionDigits: 1 })
+}
+function fmtSec(s: number | null): string {
+  return s && s > 0 ? formatMsDuration(s * 1000) : '-'
+}
+function msgTotal(r: EmployeeRow): number {
+  return (num(r, 'msg_sent') ?? 0) + (num(r, 'msg_recv') ?? 0)
+}
+function replyRate(r: EmployeeRow, countKey: 'reply_2h_count' | 'reply_24h_count'): string {
+  const den = num(r, 'cust_threads')
+  if (!den) return '--' // 分母 0/null → 无率(严格区分 0%)
+  return formatRatio((num(r, countKey) ?? 0) / den)
+}
+function activeShare(r: EmployeeRow): string {
+  const ea = num(r, 'end_active_friends') ?? 0
+  const den = ea + (num(r, 'cooling_customer') ?? 0) + (num(r, 'dormant_customer') ?? 0)
+  return den > 0 ? formatRatio(ea / den) : '--'
+}
+function dimScore(r: EmployeeRow, key: string): number | null {
+  return r.score.dimensions[key]?.score ?? null
+}
+function dimScoreText(r: EmployeeRow, key: string): string {
+  const s = dimScore(r, key)
+  return s == null ? '--' : String(Math.round(s))
+}
+const GRADE_TYPES: Record<string, 'success' | 'primary' | 'warning' | 'danger' | 'info'> = {
+  A: 'success', B: 'primary', C: 'warning', D: 'danger', E: 'info',
+}
+function gradeType(g: string | null): 'success' | 'primary' | 'warning' | 'danger' | 'info' {
+  return (g && GRADE_TYPES[g]) || 'info'
+}
+
+// 带窗进详情(D3):channel/start/end/compare 随行——列表口径延续到详情页;
+// view/keyword/status/sort_by/sort_order/page 是列表态,不带(详情页只认
+// channel/start/end/compare/section,其余键即使带上也被白名单忽略)
+function goDetail(row: EmployeeRow): void {
+  const query: Record<string, string> = {}
+  for (const key of ['channel', 'start', 'end', 'compare'] as const) {
+    const v = route.query[key]
+    if (typeof v === 'string' && v !== '') query[key] = v
+  }
+  router.push({ name: 'management-employees-detail', params: { userId: row.user_id }, query })
+}
+
+// ── 多选 → 对比抽屉(reserve-selection 跨页/重查保留;行是勾选时快照) ──
+const selectedRows = ref<EmployeeRow[]>([])
+const compareVisible = ref(false)
+// 指标口径抽屉(列头「?」与筛选栏「指标口径」共用)
+const defsVisible = ref(false)
+
+function onSelectionChange(sel: EmployeeRow[]): void {
+  selectedRows.value = sel
+}
+
+// ── CSV:当前视图列全量翻页导出,preamble 写口径/窗口注释(Excel 首列) ──
+const exporting = ref(false)
+
+const csvColumns = computed<CsvColumn<EmployeeRow>[]>(() => {
+  const base: CsvColumn<EmployeeRow>[] = [
+    { key: 'name', label: '姓名', format: (r) => r.name ?? r.user_id },
+    { key: 'user_id', label: 'ID' },
+    {
+      key: 'is_on_job',
+      label: '在职',
+      format: (r) => (r.is_on_job === true ? '在职' : r.is_on_job === false ? '离职' : '--'),
+    },
+  ]
+  const dimCol = (key: string, label: string): CsvColumn<EmployeeRow> => ({
+    key: `dim_${key}`, label, format: (r) => dimScoreText(r, key),
+  })
+  if (view.value === 'management') {
+    return base.concat([
+      {
+        key: 'total_score',
+        label: '综合分',
+        format: (r) =>
+          r.score.score_status === 'insufficient_sample' || r.score.total_score == null
+            ? '--(样本不足)'
+            : String(Math.round(r.score.total_score)),
+      },
+      { key: 'grade', label: '等级', format: (r) => r.score.grade ?? '--' },
+      { key: 'anomaly_count', label: '异常数', format: (r) => String(r.anomaly_count) },
+      { key: 'anomaly_weight', label: '异常权重', format: (r) => String(r.anomaly_weight) },
+      { key: 'active_friends', label: '活跃客户', format: (r) => fmtInt(num(r, 'active_friends')) },
+      { key: 'msg_total', label: '消息量', format: (r) => fmtInt(msgTotal(r)) },
+      { key: 'cust_threads', label: '串', format: (r) => fmtInt(num(r, 'cust_threads')) },
+      { key: 'threads_answered', label: '被回', format: (r) => fmtInt(num(r, 'threads_answered')) },
+      dimCol('customer', '客户经营分'),
+      dimCol('service', '服务质量分'),
+      dimCol('workload', '工作负载分'),
+    ])
+  }
+  if (view.value === 'workload') {
+    return base.concat([
+      { key: 'active_friends', label: '活跃客户', format: (r) => fmtInt(num(r, 'active_friends')) },
+      { key: 'active_rooms_avg', label: '活跃群(日均)', format: (r) => fmtAvg(num(r, 'active_rooms_avg')) },
+      { key: 'msg_sent', label: '消息发', format: (r) => fmtInt(num(r, 'msg_sent')) },
+      { key: 'msg_recv', label: '消息收', format: (r) => fmtInt(num(r, 'msg_recv')) },
+      { key: 'call_count', label: '通话量', format: (r) => fmtInt(num(r, 'call_count')) },
+      { key: 'call_seconds', label: '通话秒', format: (r) => String(num(r, 'call_seconds') ?? 0) },
+      { key: 'cust_threads', label: '串', format: (r) => fmtInt(num(r, 'cust_threads')) },
+    ])
+  }
+  if (view.value === 'service') {
+    return base.concat([
+      { key: 'fr_p50_ms', label: '首响P50', format: (r) => formatMsDuration(num(r, 'fr_p50_ms')) },
+      { key: 'fr_p90_ms', label: '首响P90', format: (r) => formatMsDuration(num(r, 'fr_p90_ms')) },
+      { key: 'reply_2h_rate', label: '2h回复率', format: (r) => replyRate(r, 'reply_2h_count') },
+      { key: 'reply_24h_rate', label: '24h回复率', format: (r) => replyRate(r, 'reply_24h_count') },
+      { key: 'threads_answered', label: '被回', format: (r) => fmtInt(num(r, 'threads_answered')) },
+      { key: 'cust_threads', label: '串', format: (r) => fmtInt(num(r, 'cust_threads')) },
+    ])
+  }
+  return base.concat([
+    { key: 'new_customer', label: '新客', format: (r) => fmtInt(num(r, 'new_customer')) },
+    { key: 'cooling_customer', label: '降温', format: (r) => fmtInt(num(r, 'cooling_customer')) },
+    { key: 'dormant_customer', label: '沉睡(期末)', format: (r) => fmtInt(num(r, 'dormant_customer')) },
+    { key: 'reactivated_customer', label: '回流(期内)', format: (r) => fmtInt(num(r, 'reactivated_customer')) },
+    { key: 'active_share', label: '活跃占比', format: (r) => activeShare(r) },
+  ])
+})
+
+async function exportCsv(): Promise<void> {
+  if (!total.value) {
+    ElMessage.warning('当前列表为空，无数据可导出')
+    return
+  }
+  exporting.value = true
+  try {
+    const result = await exportListToCsv<EmployeeRow>({
+      // 适配器:getEmployees 返回 {rows,total} → csvExport 期望 {items,total}
+      fetchPage: (p, size) =>
+        getEmployees(queryParams({ page: p, page_size: size })).then((r) => ({ items: r.rows, total: r.total })),
+      columns: csvColumns.value,
+      filename: `员工分析_${view.value}_${channel.value}`,
+      preamble: [
+        '口径:1:1私聊·跨日精确串(与数据看板混合口径不同)',
+        `窗口:${start.value}-${end.value} 渠道:${channel.value}`,
+        `评分为试算(${resp.value?.metric_version ?? 'v1.0'})·样本不足员工不计分`,
+      ],
+    })
+    ElMessage.success(`已导出 ${result.rows} 条`)
+  } catch (e) {
+    ElMessage.error(`导出失败：${e instanceof Error ? e.message : String(e)}`)
+  } finally {
+    exporting.value = false
+  }
+}
+</script>
+
+<style scoped>
+.toolbar {
+  display: flex;
+  align-items: center;
+  gap: 12px;
+  flex-wrap: wrap;
+  margin-top: 12px;
+}
+.kw-input {
+  width: 200px;
+}
+.compare-select {
+  width: 150px;
+}
+.status-select {
+  width: 90px;
+}
+.spacer {
+  flex: 1;
+}
+.top-alert {
+  margin-top: 12px;
+}
+.retry-btn {
+  margin-left: 12px;
+}
+.uid {
+  font-size: 12px;
+  color: var(--el-text-color-secondary);
+  overflow: hidden;
+  text-overflow: ellipsis;
+  white-space: nowrap;
+}
+.dim {
+  color: var(--el-text-color-placeholder);
+}
+.score-cell {
+  white-space: nowrap;
+}
+.grade-tag {
+  margin-left: 4px;
+}
+.trial-mark {
+  margin-left: 2px;
+  font-size: 10px;
+  color: var(--el-color-warning);
+  vertical-align: super;
+}
+.anomaly-hot {
+  color: var(--el-color-danger);
+  font-weight: 600;
+}
+.cell-sub {
+  font-size: 12px;
+  color: var(--el-text-color-secondary);
+}
+.hd-q {
+  margin-left: 2px;
+  color: var(--el-text-color-secondary);
+  cursor: pointer;
+  vertical-align: -2px;
+}
+.hd-q:hover {
+  color: var(--el-color-primary);
+}
+.pager {
+  margin-top: 12px;
+  display: flex;
+  justify-content: flex-end;
+}
+</style>

yunkes/src/views/management/ManagementDashboardView.vue

@@ -0,0 +1,537 @@
+<template>
+  <div class="mgmt-dash">
+    <!-- 筛选栏:渠道/时间(URL query 真源)+口径入口;aside=数据截至角标 -->
+    <ManagementFilterBar
+      :channel="channel"
+      :start="start"
+      :end="end"
+      :compare="compare"
+      @apply="apply"
+      @open-defs="defsVisible = true"
+    >
+      <template #aside>
+        <!-- trial 常显:dashboard 载荷无 trial 键(评分配置层字段),批次C/D
+             评分处于试算期(v2 §0 全默认+试算),批次E 转正时随配置联动 -->
+        <DataAsOfBadge
+          :data-as-of="resp?.data_as_of ?? null"
+          :metric-version="resp?.metric_version"
+          :trial="true"
+          :config-source="resp?.config_source"
+        />
+      </template>
+    </ManagementFilterBar>
+
+    <!-- 错误态:alert+重试;resp 不清空,保留上次成功数据 -->
+    <el-alert v-if="loadError" type="error" :closable="false" class="dash-alert">
+      <template #title>
+        <span>{{ loadError }}</span>
+        <el-button size="small" type="primary" class="retry-btn" @click="load">重试</el-button>
+      </template>
+    </el-alert>
+
+    <!-- 空态:窗口内无任何业务数据(数据截至角标同步显「无数据」) -->
+    <el-alert
+      v-if="noData"
+      type="info"
+      title="该窗口无数据——试试调整时间范围"
+      :closable="false"
+      class="dash-alert"
+    />
+
+    <!-- 六 KPI 卡:两行三卡(≥768px 三列/窄屏两列);后三卡行动入口直达处置页 -->
+    <el-row :gutter="12" class="block-row kpi-row" v-loading="loading">
+      <el-col :xs="12" :sm="8">
+        <ManagementKpiCard
+          label="活跃客户"
+          :value="kpis?.active_customers ?? null"
+          :delta="deltaOf('active_customers')"
+          unit="人"
+          :hint="threadsHint"
+        />
+      </el-col>
+      <el-col :xs="12" :sm="8">
+        <ManagementKpiCard
+          label="活跃员工"
+          :value="kpis?.active_employees ?? null"
+          :delta="deltaOf('active_employees')"
+          unit="人"
+          hint="期内有数据天数>0 口径"
+        />
+      </el-col>
+      <el-col :xs="12" :sm="8">
+        <!-- tooltip 说明混合 vs 1:1 口径差异,hover 才展开,卡面 hint 保持一行 -->
+        <el-tooltip
+          placement="top"
+          content="管理域消息量仅统计 1:1 私聊消息;「数据分析·数据看板」为私聊+群聊混合口径,两者数值不可直接对比"
+        >
+          <ManagementKpiCard
+            label="消息量"
+            :value="kpis?.msg_total ?? null"
+            :delta="deltaOf('msg_total')"
+            unit="条"
+            hint="1:1口径·与数据看板口径不同"
+          />
+        </el-tooltip>
+      </el-col>
+      <el-col :xs="12" :sm="8">
+        <ManagementKpiCard
+          label="待回复"
+          :value="actions?.unreplied_2h ?? null"
+          unit="人"
+          hint="当前时点指标·不随所选窗口"
+          :danger="(actions?.unreplied_2h ?? 0) > 0"
+          to="/analytics/unreplied"
+        />
+      </el-col>
+      <el-col :xs="12" :sm="8">
+        <ManagementKpiCard
+          label="即将流失"
+          :value="actions?.churn_real_30d ?? null"
+          unit="人"
+          to="/analytics/churn"
+        />
+      </el-col>
+      <el-col :xs="12" :sm="8">
+        <ManagementKpiCard
+          label="风险待处理"
+          :value="actions?.sensitive_pending ?? null"
+          unit="条"
+          hint="当前时点指标·不随所选窗口"
+          to="/analytics/sensitive"
+        />
+      </el-col>
+    </el-row>
+
+    <!-- 双趋势图:左沟通量(消息线+通话柱双 y 轴),右服务质量(首响分位线+回复率右轴) -->
+    <el-row :gutter="12" class="block-row">
+      <el-col :xs="24" :md="12">
+        <el-card shadow="never" class="chart-card" v-loading="loading">
+          <template #header>客户沟通趋势</template>
+          <div ref="commEl" class="chart"></div>
+        </el-card>
+      </el-col>
+      <el-col :xs="24" :md="12">
+        <el-card shadow="never" class="chart-card" v-loading="loading">
+          <template #header>服务质量趋势</template>
+          <div ref="svcEl" class="chart"></div>
+        </el-card>
+      </el-col>
+    </el-row>
+
+    <!-- 双条形图:左生命周期四态(横向),右员工维度均分(0-100,无样本灰) -->
+    <el-row :gutter="12" class="block-row">
+      <el-col :xs="24" :md="12">
+        <el-card shadow="never" class="chart-card" v-loading="loading">
+          <template #header>生命周期分布</template>
+          <div ref="lifeEl" class="chart"></div>
+        </el-card>
+      </el-col>
+      <el-col :xs="24" :md="12">
+        <el-card shadow="never" class="chart-card" v-loading="loading">
+          <template #header>员工维度分布</template>
+          <div ref="dimsEl" class="chart"></div>
+        </el-card>
+      </el-col>
+    </el-row>
+
+    <!-- 异常榜:critical 在前(后端已排);点行开下钻抽屉,两次点击到事实 -->
+    <el-card shadow="never" class="block-row anomaly-card" v-loading="loading">
+      <template #header>
+        异常榜
+        <span class="anomaly-sub">按严重度排序 · 点行查看明细</span>
+      </template>
+      <AnomalyList :anomalies="resp?.anomalies ?? []" :loading="loading" @drill="onDrill" />
+    </el-card>
+
+    <!-- 下钻抽屉:metric 类异常逐串/逐行明细,行点击跳聊天;employee 类批次D 占位 -->
+    <MetricDrilldownDrawer
+      v-model="drillVisible"
+      :card="drillCard"
+      :user-id="drillCard?.employee_user_id ?? ''"
+      :start="start"
+      :end="end"
+      :channel="channel"
+    />
+
+    <!-- 指标口径抽屉:19 项定义+评分配置,自缓存 -->
+    <MetricDefsDrawer v-model="defsVisible" />
+  </div>
+</template>
+
+<script setup lang="ts">
+// 管理驾驶舱(经营管理板块批次C首页):筛选(URL query 真源)→ 六 KPI →
+// 双趋势(沟通量/服务质量)→ 生命周期四态 + 员工维度均分 → 异常榜(下钻
+// 抽屉两次点击到事实)。管理者 5 分钟看整体:先 KPI 判断总体,异常卡
+// 直达事实。载荷 /management/dashboard 单往返;compare 仅回显(对比值
+// 批次D 员工表格呈现)。seq 守卫/双图 useChart/格式化均沿用项目惯例。
+import { computed, ref, watch } from 'vue'
+import {
+  getDashboard,
+  type AnomalyCard,
+  type DashboardResp,
+} from '@/api/management'
+import { useManagementFilters } from '@/composables/useManagementFilters'
+import { useChart } from '@/composables/useChart'
+import { formatMsDuration, formatRatio } from '@/utils/format'
+import ManagementFilterBar from '@/components/management/ManagementFilterBar.vue'
+import ManagementKpiCard from '@/components/management/ManagementKpiCard.vue'
+import DataAsOfBadge from '@/components/management/DataAsOfBadge.vue'
+import AnomalyList from '@/components/management/AnomalyList.vue'
+import MetricDrilldownDrawer from '@/components/management/MetricDrilldownDrawer.vue'
+import MetricDefsDrawer from '@/components/management/MetricDefsDrawer.vue'
+
+// ── 筛选(URL query 为真源,刷新/分享保持)与加载 ──
+const { channel, start, end, compare, apply } = useManagementFilters()
+
+const resp = ref<DashboardResp | null>(null)
+const loading = ref(false)
+const loadError = ref<string | null>(null)
+
+let seq = 0 // 竞态守卫:筛选快速切换时旧响应作废(项目惯例)
+
+async function load(): Promise<void> {
+  const my = ++seq
+  loading.value = true
+  loadError.value = null
+  try {
+    const r = await getDashboard(channel.value, start.value, end.value, compare.value)
+    if (my !== seq) return
+    resp.value = r
+  } catch (e) {
+    // 失败保留上次成功数据(resp 不清空),仅标记 error 供 alert+重试
+    if (my === seq) loadError.value = e instanceof Error ? e.message : String(e)
+  } finally {
+    // 过期请求不清 loading(新一轮还在飞)也不覆盖 error
+    if (my === seq) loading.value = false
+  }
+}
+
+// immediate 首帧即取数,替代 onMounted;筛选任一变化重查
+watch([channel, start, end, compare], load, { immediate: true })
+
+const kpis = computed(() => resp.value?.kpis ?? null)
+const actions = computed(() => resp.value?.action_summary ?? null)
+
+// 三 KPI 卡环比(批次D):客户端统一按 (cur-prev)/prev 自 prev_kpis 计算
+// (数据同载荷都在;后端 msg_delta 备用未用)。prev_kpis 缺失(旧缓存
+// 响应)或 prev=0(前窗无数据)→ null 不显示
+function deltaOf(key: 'active_customers' | 'active_employees' | 'msg_total'): number | null {
+  const k = resp.value?.kpis
+  const p = resp.value?.prev_kpis
+  if (!k || !p || !p[key]) return null
+  return (k[key] - p[key]) / p[key]
+}
+
+// 活跃客户辅助行:串/被回(口径与 KPI 同载荷,管理域跨日精确串)
+const threadsHint = computed(() => {
+  const k = kpis.value
+  if (!k) return undefined
+  return `串 ${k.cust_threads.toLocaleString()} · 被回 ${k.threads_answered.toLocaleString()}`
+})
+
+// 空态:核心 KPI 全 0(趋势按日脚手架恒非空,以 KPI 判空才可靠)
+const noData = computed(() => {
+  const k = kpis.value
+  if (!k || loadError.value) return false
+  return !k.active_customers && !k.active_employees && !k.msg_total && !k.call_count
+})
+
+// ── 异常下钻 ──
+const drillVisible = ref(false)
+const drillCard = ref<AnomalyCard | null>(null)
+const defsVisible = ref(false)
+
+function onDrill(card: AnomalyCard): void {
+  drillCard.value = card
+  drillVisible.value = true
+}
+
+// ── 图表(四张,容器恒在 DOM——useChart 只 init 一次,不 v-if) ──
+const commEl = ref<HTMLElement | null>(null)
+const svcEl = ref<HTMLElement | null>(null)
+const lifeEl = ref<HTMLElement | null>(null)
+const dimsEl = ref<HTMLElement | null>(null)
+const { render: renderComm } = useChart(commEl)
+const { render: renderSvc } = useChart(svcEl)
+const { render: renderLife } = useChart(lifeEl)
+const { render: renderDims } = useChart(dimsEl)
+
+// yyyymmdd(20260810)→ 08-10 短格式(轴/tooltip 共用)
+const shortDay = (d: number): string => `${String(d).slice(4, 6)}-${String(d).slice(6)}`
+// 大数压缩:轴刻度统一 1.1万 口径(与 DashboardView 一致)
+const compact = (n: number): string =>
+  n >= 10000 ? `${(n / 10000).toFixed(1)}万` : n.toLocaleString()
+// 服务质量左轴刻度:ms → 紧凑时长(轴上省秒,tooltip 仍用 formatMsDuration)
+const fmtMsAxis = (v: number): string =>
+  v >= 3_600_000 ? `${(v / 3_600_000).toFixed(1)}时` : `${Math.round(v / 60_000)}分`
+// X 轴 ~6 个刻度(30 个日期全排会挤成一串不可读)
+const axisInterval = (n: number): number => Math.max(0, Math.ceil(n / 6) - 1)
+
+const AXIS_LABEL = { color: '#909399' }
+const SPLIT_LINE = { lineStyle: { type: 'solid' as const, color: '#f0f1f3' } }
+
+function drawComm(): void {
+  const t = resp.value?.communication_trend
+  if (!t || !t.length) return
+  const labels = t.map((p) => shortDay(p.day))
+  renderComm({
+    grid: { left: 56, right: 56, top: 40, bottom: 28 },
+    tooltip: { trigger: 'axis', valueFormatter: (v: unknown) => compact(Number(v)) },
+    legend: { data: ['消息量', '通话量'], top: 4, itemWidth: 14, textStyle: { color: '#606266' } },
+    xAxis: {
+      type: 'category',
+      data: labels,
+      axisLabel: { interval: axisInterval(labels.length), hideOverlap: true, ...AXIS_LABEL },
+      axisLine: { lineStyle: { color: '#dcdfe6' } },
+      axisTick: { show: false },
+    },
+    yAxis: [
+      {
+        type: 'value',
+        name: '消息量',
+        axisLabel: { formatter: (v: number) => compact(v), ...AXIS_LABEL },
+        splitLine: SPLIT_LINE,
+      },
+      {
+        type: 'value',
+        name: '通话量',
+        axisLabel: { formatter: (v: number) => compact(v), ...AXIS_LABEL },
+        splitLine: { show: false },
+      },
+    ],
+    series: [
+      {
+        name: '消息量',
+        type: 'line',
+        smooth: true,
+        yAxisIndex: 0,
+        lineStyle: { width: 2, color: '#409EFF' },
+        itemStyle: { color: '#409EFF' },
+        areaStyle: { opacity: 0.1, color: '#409EFF' },
+        showSymbol: false,
+        data: t.map((p) => p.msg_total),
+      },
+      {
+        name: '通话量',
+        type: 'bar',
+        yAxisIndex: 1,
+        barMaxWidth: 12,
+        itemStyle: { color: '#67C23A', borderRadius: [3, 3, 0, 0] },
+        data: t.map((p) => p.call_cnt),
+      },
+    ],
+  })
+}
+
+// 服务质量 tooltip:ms→时长/率→百分比(null 显 '-',与断点语义一致)
+interface TipParam { marker?: string; seriesName?: string; value?: number | null; axisValueLabel?: string }
+function svcTooltip(ps: unknown): string {
+  const arr = (Array.isArray(ps) ? ps : [ps]) as TipParam[]
+  if (!arr.length) return ''
+  const rows = arr.map((p) => {
+    const v = typeof p.value === 'number' ? p.value : null
+    const text = v === null ? '-' : p.seriesName === '2h回复率' ? formatRatio(v) : formatMsDuration(v)
+    return `<div>${p.marker ?? ''}${p.seriesName}: ${text}</div>`
+  })
+  return `<div>${arr[0].axisValueLabel ?? ''}</div>${rows.join('')}`
+}
+
+function drawSvc(): void {
+  const t = resp.value?.service_trend
+  if (!t || !t.length) return
+  const labels = t.map((p) => shortDay(p.day))
+  renderSvc({
+    grid: { left: 56, right: 56, top: 40, bottom: 28 },
+    tooltip: { trigger: 'axis', formatter: svcTooltip },
+    legend: {
+      data: ['首响中位', '首响九分位', '2h回复率'],
+      top: 4, itemWidth: 14, textStyle: { color: '#606266' },
+    },
+    xAxis: {
+      type: 'category',
+      data: labels,
+      axisLabel: { interval: axisInterval(labels.length), hideOverlap: true, ...AXIS_LABEL },
+      axisLine: { lineStyle: { color: '#dcdfe6' } },
+      axisTick: { show: false },
+    },
+    yAxis: [
+      {
+        type: 'value',
+        name: '首响',
+        axisLabel: { formatter: fmtMsAxis, ...AXIS_LABEL },
+        splitLine: SPLIT_LINE,
+      },
+      {
+        // 右轴 0-1 率:不单列双轴则率线贴底不可读
+        type: 'value',
+        name: '2h回复率',
+        min: 0,
+        max: 1,
+        axisLabel: { formatter: (v: number) => formatRatio(v), ...AXIS_LABEL },
+        splitLine: { show: false },
+      },
+    ],
+    series: [
+      // null(无样本日)=断点:connectNulls:false 显式钉死,不跨缺口连线
+      {
+        name: '首响中位',
+        type: 'line', smooth: true, showSymbol: false, connectNulls: false,
+        lineStyle: { width: 2 },
+        data: t.map((p) => p.fr_p50_ms),
+      },
+      {
+        name: '首响九分位',
+        type: 'line', smooth: true, showSymbol: false, connectNulls: false,
+        lineStyle: { width: 2 },
+        data: t.map((p) => p.fr_p90_ms),
+      },
+      {
+        name: '2h回复率',
+        type: 'line', smooth: true, showSymbol: false, connectNulls: false,
+        yAxisIndex: 1,
+        lineStyle: { width: 2, color: '#67C23A' },
+        itemStyle: { color: '#67C23A' },
+        data: t.map((p) => p.reply_2h_rate),
+      },
+    ],
+  })
+}
+
+// 生命周期四态:横向条形(名义类别,状态色——新客蓝/降温橙/沉睡红/回流绿)
+const LIFE_META = [
+  { key: 'new', label: '新客', color: '#409EFF' },
+  { key: 'cooling', label: '降温', color: '#E6A23C' },
+  { key: 'dormant', label: '沉睡', color: '#F56C6C' },
+  { key: 'reactivated', label: '回流', color: '#67C23A' },
+] as const
+
+function drawLife(): void {
+  const lc = resp.value?.lifecycle
+  if (!lc) return
+  renderLife({
+    grid: { left: 8, right: 48, top: 8, bottom: 8, containLabel: true },
+    tooltip: { trigger: 'item', valueFormatter: (v: unknown) => compact(Number(v)) },
+    xAxis: {
+      type: 'value',
+      axisLabel: { formatter: (v: number) => compact(v), ...AXIS_LABEL },
+      splitLine: SPLIT_LINE,
+    },
+    yAxis: {
+      type: 'category',
+      inverse: true, // 新客在顶部(生命周期顺序)
+      data: LIFE_META.map((m) => m.label),
+      axisTick: { show: false },
+      axisLine: { show: false },
+      axisLabel: { color: '#606266' },
+    },
+    series: [
+      {
+        type: 'bar',
+        barWidth: 14,
+        itemStyle: { borderRadius: [0, 4, 4, 0] },
+        label: {
+          show: true,
+          position: 'right',
+          formatter: (p: { value: unknown }) => compact(Number(p.value)),
+          color: '#606266',
+          fontSize: 11,
+        },
+        data: LIFE_META.map((m) => ({ value: lc[m.key], itemStyle: { color: m.color } })),
+      },
+    ],
+  })
+}
+
+// 员工维度分布:pending_data 维(action/risk)恒无 scored/insufficient 计数,
+// 以计数>0 过滤,只留真实参与评分的维度(customer/service/workload)
+const dimRows = computed(() =>
+  Object.entries(resp.value?.dimension_summary ?? {})
+    .filter(([, d]) => d.scored_count > 0 || d.insufficient_count > 0)
+    .map(([key, d]) => ({ key, ...d })),
+)
+
+function dimsTooltip(p: { dataIndex?: number }): string {
+  const r = p.dataIndex != null ? dimRows.value[p.dataIndex] : undefined
+  if (!r) return ''
+  const avg = r.avg_score === null ? '-' : Math.round(r.avg_score)
+  return (
+    `<div>${r.name}</div>` +
+    `<div>均分 ${avg}(权重 ${r.weight}%)</div>` +
+    `<div>已评分 ${r.scored_count} · 样本不足 ${r.insufficient_count} · 待数据 ${r.pending_count}</div>`
+  )
+}
+
+function drawDims(): void {
+  const rows = dimRows.value
+  if (!rows.length) return
+  renderDims({
+    grid: { left: 40, right: 16, top: 24, bottom: 28, containLabel: true },
+    tooltip: { trigger: 'item', formatter: dimsTooltip },
+    xAxis: {
+      type: 'category',
+      data: rows.map((r) => r.name),
+      axisTick: { show: false },
+      axisLine: { lineStyle: { color: '#dcdfe6' } },
+      axisLabel: { color: '#606266' },
+    },
+    yAxis: {
+      type: 'value',
+      min: 0,
+      max: 100, // 维度分定义域 0-100
+      axisLabel: AXIS_LABEL,
+      splitLine: SPLIT_LINE,
+    },
+    series: [
+      {
+        type: 'bar',
+        barWidth: 28,
+        itemStyle: { borderRadius: [3, 3, 0, 0] },
+        label: {
+          show: true,
+          position: 'top',
+          formatter: (p: { dataIndex: number; value: unknown }) =>
+            (rows[p.dataIndex]?.avg_score ?? null) === null ? '-' : compact(Number(p.value)),
+          color: '#606266',
+          fontSize: 11,
+        },
+        data: rows.map((r) =>
+          r.avg_score === null
+            // 无样本维度(全员未评):0 值灰条——有位置但不冒充分数
+            ? { value: 0, itemStyle: { color: '#c0c4cc' } }
+            : { value: Math.round(r.avg_score), itemStyle: { color: '#409EFF' } },
+        ),
+      },
+    ],
+  })
+}
+
+// post:等 DOM 更新后再画,保证首帧容器已挂载;resp 单源,四图同刷
+watch(resp, () => { drawComm(); drawSvc(); drawLife(); drawDims() }, { flush: 'post' })
+</script>
+
+<style scoped>
+.dash-alert {
+  margin-top: 12px;
+}
+.retry-btn {
+  margin-left: 12px;
+}
+.block-row {
+  margin-top: 16px;
+}
+.kpi-row {
+  min-height: 100px;
+}
+.chart-card :deep(.el-card__body) {
+  padding: 12px 16px 8px;
+}
+.chart {
+  height: 300px;
+}
+.anomaly-sub {
+  margin-left: 8px;
+  font-size: 12px;
+  font-weight: 400;
+  color: var(--el-text-color-secondary);
+}
+</style>