fix(analytics): run_full水位前置防回填窗口漏扫+README/DEPLOY/脚本号收尾

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

yunke-server/app/analytics/sensitive/scanner.py

@@ -165,7 +165,7 @@ async def run_incremental(session: AsyncSession) -> dict:
 
 
 async def run_full(session: AsyncSession) -> dict:
-    """全量回填(CLI 一次性):每词单独扫全库;水位推进同增量。
+    """全量回填(CLI 一次性):每词单独扫全库;水位在扫描前取(见内注)。
 
     每词结果整批取回(MATCH/LIKE 已在服务端预筛成命中行)再分片复用
     _scan_batch——不在未取尽的结果上发新语句/flush(MySQL 驱动会
@@ -178,6 +178,15 @@ async def run_full(session: AsyncSession) -> dict:
         )
     ).scalars().all()
     st = await _get_state(session)
+    # 水位在扫描前取——回填期间新入库的行 fetched_at > 水位,下轮增量自然
+    # 扫到;若在词循环后才取,回填窗口内 commit 的行 fetched_at ≤ 水位,
+    # >= 增量也扫不到(首部署夜间回填与 02:00 全量批写重叠时漏扫)。
+    # >= 边界重扫由 UNIQUE(word_id,msg_id) 去重。
+    new_wm = (
+        await session.execute(sa.select(sa.func.max(Message.fetched_at)))
+    ).scalar_one_or_none()
+    if new_wm is not None:
+        st.last_fetched_at = new_wm
     total_hits = 0
     scanned_rows = 0
     for w in words:
@@ -192,11 +201,6 @@ async def run_full(session: AsyncSession) -> dict:
         for i in range(0, len(rows), 500):
             total_hits += await _scan_batch(session, w, rows[i:i + 500])
             await session.flush()  # 行已 .all() 物化,分片 flush 控挂起对象数
-    new_wm = (
-        await session.execute(sa.select(sa.func.max(Message.fetched_at)))
-    ).scalar_one_or_none()
-    if new_wm is not None:
-        st.last_fetched_at = new_wm
     st.scanned += scanned_rows
     st.hits += total_hits
     st.last_run_at = dt.datetime.now(dt.UTC)