fix(sync): 同步链路审计修复——水位边界白拉/全量无超时/群活跃窗判定源

全项目数据同步审计发现四漏洞(前项为证据):

① 消息增量边界白拉(证据:昨夜 wa-messages fetched=53,682 而真实新消息
   仅 321 条,99.4% 是白拉白写的已入库旧消息)——云客 chatRecords/msg-chats
   的 start 参数是 inclusive(返回 ts>=start 含边界),四个消息实体(微信
   1:1/WA 1:1/微信群/WA 群)统一在归一化后过滤 ts<=watermark 的边界行,
   不计数不写库(省 99% 写放大,计数从此反映真实新增)
② full_sync_all.sh 无超时——极端情况(常态 10-20h)拖进次日相位把 02:00
   全量又挤掉(前两天事故同型);加 22h 上限
③ 周日 full-history 无超时——4 实体全历史可能 24h+,必挤周一;单实体
   加 6h 上限
④ 群消息活跃窗判定源是昨晚 full 的 chat_group.last_chat_time 快照——
   「昨天安静、今天突然活跃」的群会被 24h 窗口漏到明晚;4h 序列在
   group-messages 前加 chatroom-stats 全窗(~1min)刷新群活跃判定源

722 测试绿(4h 序列断言 9→10 命令+chatroom-stats 位序)。

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

yunke-server/app/sync/scheduler.py

@@ -602,7 +602,7 @@ class SyncScheduler:
                 if not bash:
                     logger.error("page sync 'full': bash not found on PATH")
                     return
-                commands = [([bash, "scripts/full_sync_all.sh"], None)]  # (args, timeout)——full 不设超时(全量本身 10-20h)
+                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":
                 # 2026-09-10 调度根治(用户报「员工列表时间差 2 天」):
                 # ① 序列头部刷员工账号表(accounts ~1min)——员工列表「数据
@@ -621,6 +621,10 @@ class SyncScheduler:
                     ("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),
@@ -666,7 +670,8 @@ class SyncScheduler:
                             "99999",
                             "--full-history",
                         ],
-                        None,  # 每周对齐不设超时
+                        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
                 ]

yunke-server/scripts/scrape_via_page.py

@@ -763,6 +763,9 @@ 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",
@@ -965,6 +968,9 @@ 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:
@@ -2241,7 +2247,14 @@ 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
@@ -2385,7 +2398,11 @@ 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}")

yunke-server/tests/test_sync_scheduler.py

@@ -589,7 +589,7 @@ async def test_safe_page_run_messages_builds_scrape_command(engine, monkeypatch)
 
     await sched._safe_page_run("messages")
 
-    assert len(commands) == 9
+    assert len(commands) == 10
     for args in commands:
         assert args[1].endswith("scrape_via_page.py")
 
@@ -601,13 +601,14 @@ async def test_safe_page_run_messages_builds_scrape_command(engine, monkeypatch)
     assert entity_of(commands[1]) == "wa-accounts"
     assert entity_of(commands[2]) == "friends"
     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[4:8]:
+    for args in commands:
-        assert entity_of(args) in (
+        if entity_of(args) in ("messages", "wa-messages", "group-messages", "wa-group-messages"):
-            "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"
-        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"