feat(scheduler): persist task state/progress/due_at across restart (#8)

Replace process-start next_run=0 guesses with kv task:state records
(status, due_at, stat_date, progress). Startup recovers stale running,
honors future due_at for delayed retries, and resumes the same
stat_date. Seed only enqueues evening seal; seal force keeps non-seed
ok=1 as progress (keep_scraped). Keeps !7 fail-logging and cleanup retry.

reaction_board/services/snapshot.py

@@ -155,7 +155,10 @@ class SnapshotService:
             raise ValueError(f"日期格式必须是 YYYY-MM-DD: {stat_date!r}")
         seeded = self.repo.kv_get(self.seeded_key(stat_date)) == "1"
         if force:
-            return self.run_videos(date=stat_date, force=True)
+            # 晚间 seal / 续跑：打穿 seed，保留已真实采集的 ok=1 作为进度。
+            return self.run_videos(
+                date=stat_date, force=True, keep_scraped=True,
+            )
 
         completed = self.repo.kv_get(self.completed_key(stat_date)) == "1"
         if seeded and not completed:
@@ -169,6 +172,7 @@ class SnapshotService:
                 finished_at=now,
                 completed=False,
                 already_completed=False,
+                reason="seeded_pending_seal",
             )
         pending = self.repo.pending_snapshot_aids(stat_date)
         if completed and not pending:
@@ -205,8 +209,19 @@ class SnapshotService:
         summary = self.run_videos(date=date, force=force)
         return self.run_fans(date=summary.stat_date, force=force, summary=summary)
 
-    def run_videos(self, *, date: str | None = None, force: bool = False) -> SnapshotSummary:
-        """采集视频七项指标并在全部成功后标记完成日 / 备份。"""
+    def run_videos(
+        self,
+        *,
+        date: str | None = None,
+        force: bool = False,
+        keep_scraped: bool = False,
+    ) -> SnapshotSummary:
+        """采集视频七项指标并在全部成功后标记完成日 / 备份。
+
+        ``force``：忽略完成标记，重跑。
+        ``keep_scraped``：force 时仍跳过非 seed 的 ok=1（seal 断点续跑）；
+        CLI ``--force`` 不传此标志，会重采全部成功行。
+        """
         cfg = self.config_store.get()
         client = self._client()
         now = self._now()
@@ -227,11 +242,19 @@ class SnapshotService:
         summary.total = len(videos)
         for index, aid in enumerate(videos, 1):
             existing = self.repo.get_snapshot(stat_date, aid)
-            if existing is not None and int(existing.get("ok") or 0) == 1 and not force:
-                # 断点续跑：同日已成功则跳过。小时任务刷新过的行也是 ok=1，
-                # 自然覆盖「1 小时内 captured_at 已更新则不再次更新」的要求。
-                summary.skipped += 1
-                continue
+            if existing is not None and int(existing.get("ok") or 0) == 1:
+                src = str(existing.get("src") or "")
+                if keep_scraped and src == "seed":
+                    # seal 续跑：必须打穿克隆壳
+                    pass
+                elif keep_scraped and src != "seed":
+                    summary.skipped += 1
+                    continue
+                elif not force:
+                    # 普通续跑：同日已成功则跳过（含小时任务刚刷新的）
+                    summary.skipped += 1
+                    continue
+                # force 且非 keep_scraped：CLI 全量重采，不 skip
 
             stat, error, unavailable = self._fetch_view(client, aid)
             if unavailable:
@@ -425,6 +448,7 @@ class SnapshotService:
                     completed=False,
                     already_completed=False,
                     fans_skipped=len(cfg.track_fans),
+                    reason="seeded_pending_seal",
                 )
             return self.run_fans(date=stat_date, force=True)
         if not self._pending_fan_mids(stat_date, cfg.track_fans):