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

backend/app/api/v1/datasources.py

@@ -17,6 +17,7 @@ from app.models.user import User
 from app.services.scheduler import get_latest_task_id_for_datasource, run_collector_now, sync_datasource_job
 
 router = APIRouter()
+STALE_RUNNING_TASK_TIMEOUT_MINUTES = 90
 
 
 def format_frequency_label(minutes: int) -> str:
@@ -71,7 +72,32 @@ async def get_running_task(db: AsyncSession, datasource_id: int) -> Optional[Col
         .order_by(CollectionTask.started_at.desc())
         .limit(1)
     )
-    return result.scalar_one_or_none()
+    task = result.scalar_one_or_none()
+    if not task:
+        return None
+
+    started_at = task.started_at
+    if started_at is None:
+        return task
+
+    now = datetime.now(timezone.utc)
+    if started_at.tzinfo is None:
+        started_at = started_at.replace(tzinfo=timezone.utc)
+
+    if now - started_at <= timedelta(minutes=STALE_RUNNING_TASK_TIMEOUT_MINUTES):
+        return task
+
+    existing_error = (task.error_message or "").strip()
+    stale_reason = (
+        f"Marked failed automatically after stale running timeout "
+        f"({STALE_RUNNING_TASK_TIMEOUT_MINUTES}m)"
+    )
+    task.status = "failed"
+    task.phase = "failed"
+    task.completed_at = now
+    task.error_message = f"{existing_error}\n{stale_reason}".strip() if existing_error else stale_reason
+    await db.commit()
+    return None
 
 
 @router.get("")