feat(group-members): 群列表对账云客总数+群详情成员墙(头像+昵称)

用户报两点:①微信群列表与云客群统计总数不一致(实测云客 1,864 vs 本地
2,012——friend_list/es 时代残留的 148 行 owner 组合已不在 getChatroomList
返回里);②群详情成员列表全是 wxid 无法识别。

- chatroom-stats 全窗模式加对账:名单取满(>=声明 total)才删本地不在
  云客名单里的 chat_group(wechat)行——页脚从此与云客一字不差;短页宁
  可不对账防误删
- backfill_group_members 增强:头像列(消息最新一条 sender_head_url)+
  customer 兜底 UPDATE(member_id=friend_id 命中本司好友补昵称/头像,
  覆盖未发言成员);full_sync 8b 原位生效
- 群详情 drawer 成员墙:头像+昵称网格(群昵称>好友昵称>wxid 回退+wxid
  副行),替代原 memberIds 原始串;仅微信 tab(WA 群成员未派生)

722 后端测试绿,前端构建过。

Co-Authored-By: Claude Code <noreply@anthropic.com>

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
-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）。
+2026-08-20 确认），但群消息的 talker 就是发言成员的 wxid、sender_name/
+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，
-取 max(timestamp) 同行的值）。幂等可重跑；建议在 group-messages 之后执行。
+未发言的成员（被拉进群从没说话）从 customer 表兜底：member_id=friend_id
+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
-# only_full_group_by 拒绝 SQLite 式「max()+裸列」(1055)，窗口写法两库通用
-# 且语义严格（最新一条的昵称），不依赖方言碰巧行为
+# row_number() 窗口取 timestamp 最新一行的 sender_name/sender_head_url：
+# MySQL 8 的 only_full_group_by 拒绝 SQLite 式「max()+裸列」(1055)，窗口
+# 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/scrape_via_page.py

@@ -1779,9 +1779,12 @@ def _normalize_chatroom_stat_row(row: dict, owner_wxid: str) -> dict:
     return rec
 
 
-async def _chatroom_rows(page, dept: str, start_str: str, end_str: str, max_pages: int = 100):
-    """翻完 getChatroomList 一个窗,返回全部行(list)。"""
+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(
@@ -1794,13 +1797,13 @@ async def _chatroom_rows(page, dept: str, start_str: str, end_str: str, max_page
         data = body.get("data") or {}
         rows = data.get("overviews") or []
         rows_all.extend(rows)
-        total = data.get("totalCount") or 0
-        logger.info(f"  chatroom-list page {page_num}: {len(rows)} rows (total {total})")
-        if not rows or page_num * 50 >= (total or 0):
+        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
+    return rows_all, declared or 0
 
 
 async def _owner_alias_map(conn):
@@ -1851,9 +1854,11 @@ async def scrape_chatroom_stats(cookie_str: str, day: str | None = None):
 
     group_recs: list[dict] = []
     stats_recs: list[dict] = []
+    declared = 0
     async with PageScraper(cookie_str) as scraper:
         page = await _open_fetch_page(scraper)
-        for row in await _chatroom_rows(page, dept, start_str, end_str):
+        rows, declared = await _chatroom_rows(page, dept, start_str, end_str)
+        for row in rows:
             rid = row.get("chatRoomId")
             if not rid:
                 continue
@@ -1877,9 +1882,37 @@ async def scrape_chatroom_stats(cookie_str: str, day: str | None = None):
         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:
+        from sqlalchemy import tuple_ as sa_tuple
+
+        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}
+        keep_list = list(keep)
+        async with async_session_maker() as session:
+            for i in range(0, len(keep_list), 500):
+                chunk = keep_list[i:i + 500]
+                res = await session.execute(
+                    sa.delete(ChatGroup).where(
+                        ChatGroup.channel == "wechat",
+                        sa.tuple_(
+                            ChatGroup.owner_account_id, ChatGroup.room_id
+                        ).not_in(sa_tuple(chunk)),
+                    )
+                )
+                pruned += int(res.rowcount or 0)
+            await session.commit()
+
     logger.info(
         f"DONE: chatroom-stats day={day or '全窗'} groups={len(group_recs)} "
-        f"stats_rows={len(stats_recs)}"
+        f"stats_rows={len(stats_recs)} pruned={pruned}"
     )
     return len(group_recs), len(stats_recs)