fix(scheduler): address !7 REQUEST_CHANGES

- seed: check completed_key before no_source so same-day last_completed
  is already_completed (not 10m retry)
- scheduler: resolve TaskControl ok/error before logging; ok=False logs
  task_fail, not task_ok
- candidate_cleanup: catch failures, record task, retry ~5m like discover

reaction_board/cli.py

@@ -730,10 +730,20 @@ def cmd_run(args, logger: JsonLogger, *, serve_web: bool = False) -> int:
                 return _quiet_window_defer(
                     repo, logger, "candidate_cleanup", started_at=started,
                 )
-            removed = repo.delete_expired_candidates(
-                ttl_days=cfg.schedule.candidate_ttl_days
-            )
-            expired = repo.expire_fav_actions()
+            try:
+                removed = repo.delete_expired_candidates(
+                    ttl_days=cfg.schedule.candidate_ttl_days
+                )
+                expired = repo.expire_fav_actions()
+            except Exception as exc:  # noqa: BLE001  记录后约 5 分钟补跑
+                finished = int(time.time())
+                _record_task(
+                    repo, "candidate_cleanup", ok=False, started_at=started,
+                    finished_at=finished, error=str(exc),
+                )
+                return TaskControl(
+                    ok=False, next_run=_retry_soon(float(finished)), error=str(exc),
+                )
             if removed or expired:
                 repo.bump_cache_version("videos")
             finished = int(time.time())

reaction_board/scheduler.py

@@ -87,11 +87,9 @@ class Scheduler:
                 raw = task.fn()
             except Exception as exc:  # noqa: BLE001  单任务失败不终止调度
                 error = str(exc)
-                self._log("error", "scheduler.task_error", task=task.name, error=error)
             else:
                 if isinstance(raw, TaskControl):
                     control = raw
-                self._log("info", "scheduler.task_ok", task=task.name)
             finished = self._clock()
             if control is not None and control.next_run is not None:
                 task.next_run = float(control.next_run)
@@ -104,6 +102,23 @@ class Scheduler:
                 ok = bool(control.ok) and error is None
                 if control.error and error is None:
                     error = control.error
+            # Skip/fail ≠ success：先定 ok/error，再记 scheduler 日志。
+            if ok:
+                self._log("info", "scheduler.task_ok", task=task.name)
+            elif control is not None:
+                self._log(
+                    "warning",
+                    "scheduler.task_fail",
+                    task=task.name,
+                    error=error,
+                )
+            else:
+                self._log(
+                    "error",
+                    "scheduler.task_error",
+                    task=task.name,
+                    error=error,
+                )
             result = TaskResult(
                 name=task.name,
                 started_at=started,

reaction_board/services/snapshot.py

@@ -538,16 +538,8 @@ class SnapshotService:
             raise ValueError(f"日期格式必须是 YYYY-MM-DD: {stat_date!r}")
 
         summary = SnapshotSummary(stat_date=stat_date, started_at=now)
-        source = self.repo.kv_get("snapshot:last_completed")
-        if not source or source >= stat_date:
-            self._log(
-                "info", "snapshot.seed_skip",
-                stat_date=stat_date, reason="no_source", source=source,
-            )
-            summary.finished_at = self._now()
-            summary.completed = False
-            summary.reason = "no_source"
-            return summary
+        # 目标日已完成：先于 no_source。全站快照当天完成后
+        # last_completed == stat_date，不可误判为无源再 10 分钟重试。
         if self.repo.kv_get(self.completed_key(stat_date)) == "1":
             self._log(
                 "info", "snapshot.seed_skip",
@@ -558,6 +550,16 @@ class SnapshotService:
             summary.already_completed = True
             summary.reason = "already_completed"
             return summary
+        source = self.repo.kv_get("snapshot:last_completed")
+        if not source or source >= stat_date:
+            self._log(
+                "info", "snapshot.seed_skip",
+                stat_date=stat_date, reason="no_source", source=source,
+            )
+            summary.finished_at = self._now()
+            summary.completed = False
+            summary.reason = "no_source"
+            return summary
         if self.repo.kv_get(self.seeded_key(stat_date)) == "1":
             self._log(
                 "info", "snapshot.seed_skip",