feat(bgp): improve prefix-geo pipeline and collector reliability

backend/app/services/scheduler.py

@@ -18,6 +18,7 @@ from app.services.collectors.registry import collector_registry
 logger = logging.getLogger(__name__)
 
 scheduler = AsyncIOScheduler()
+RUNNING_TASK_GUARD_TIMEOUT_MINUTES = 90
 
 
 async def _update_next_run_at(datasource: DataSource, session) -> None:
@@ -76,6 +77,54 @@ async def run_collector_task(collector_name: str):
             logger.info("Skipping disabled collector: %s", collector_name)
             return
 
+        running_result = await db.execute(
+            select(CollectionTask)
+            .where(
+                CollectionTask.datasource_id == datasource.id,
+                CollectionTask.status == "running",
+            )
+            .order_by(CollectionTask.started_at.desc(), CollectionTask.id.desc())
+            .limit(1)
+        )
+        existing_running = running_result.scalar_one_or_none()
+        if existing_running is not None:
+            now = datetime.now(UTC)
+            started_at = existing_running.started_at
+            if started_at is not None and started_at.tzinfo is None:
+                started_at = started_at.replace(tzinfo=UTC)
+
+            is_stale = (
+                started_at is not None
+                and (now - started_at) > timedelta(minutes=RUNNING_TASK_GUARD_TIMEOUT_MINUTES)
+            )
+            if not is_stale:
+                logger.warning(
+                    "Skipping collector %s trigger because task %s is already running",
+                    collector_name,
+                    existing_running.id,
+                )
+                return
+
+            existing_error = (existing_running.error_message or "").strip()
+            stale_reason = (
+                f"Marked failed automatically after stale running timeout "
+                f"({RUNNING_TASK_GUARD_TIMEOUT_MINUTES}m) in scheduler guard"
+            )
+            existing_running.status = "failed"
+            existing_running.phase = "failed"
+            existing_running.completed_at = now
+            existing_running.error_message = (
+                f"{existing_error}\n{stale_reason}".strip()
+                if existing_error
+                else stale_reason
+            )
+            await db.commit()
+            logger.warning(
+                "Marked stale running task %s as failed before rerun of %s",
+                existing_running.id,
+                collector_name,
+            )
+
         try:
             collector._datasource_id = datasource.id
             logger.info("Running collector: %s (datasource_id=%s)", collector_name, datasource.id)