fix: tighten datasource trigger guards

backend/app/api/v1/datasources.py

@@ -93,16 +93,20 @@ async def get_running_task(db: AsyncSession, datasource_id: int) -> Optional[Col
     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()
+    datasource = await db.get(DataSource, datasource_id)
+    if datasource is not None:
+        await fail_and_rollback_stale_running_task(db, datasource, task)
+    else:
+        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
 
 
@@ -170,6 +174,73 @@ async def rollback_orphaned_running_task(
     await db.commit()
 
 
+async def fail_and_rollback_stale_running_task(
+    db: AsyncSession,
+    datasource: DataSource,
+    running_task: CollectionTask,
+) -> None:
+    snapshot_result = await db.execute(
+        select(DataSnapshot)
+        .where(
+            DataSnapshot.datasource_id == datasource.id,
+            DataSnapshot.task_id == running_task.id,
+        )
+        .order_by(DataSnapshot.id.desc())
+        .limit(1)
+    )
+    snapshot = snapshot_result.scalar_one_or_none()
+
+    await db.execute(CollectedData.__table__.delete().where(CollectedData.task_id == running_task.id))
+
+    await db.execute(
+        text(
+            """
+            UPDATE collected_data
+            SET is_current = FALSE
+            WHERE source = :source
+            """
+        ),
+        {"source": datasource.source},
+    )
+
+    if snapshot is not None:
+        snapshot.status = "failed"
+        snapshot.is_current = False
+        snapshot.completed_at = datetime.now(timezone.utc)
+        summary = dict(snapshot.summary or {})
+        summary["rollback"] = True
+        summary["rollback_reason"] = "stale_running_task_timeout"
+        snapshot.summary = summary
+
+        if snapshot.parent_snapshot_id is not None:
+            parent_snapshot = await db.get(DataSnapshot, snapshot.parent_snapshot_id)
+            if parent_snapshot:
+                parent_snapshot.is_current = True
+            await db.execute(
+                text(
+                    """
+                    UPDATE collected_data
+                    SET is_current = TRUE
+                    WHERE snapshot_id = :snapshot_id
+                    """
+                ),
+                {"snapshot_id": snapshot.parent_snapshot_id},
+            )
+
+    existing_error = (running_task.error_message or "").strip()
+    stale_reason = (
+        f"Marked failed automatically after stale running timeout "
+        f"({STALE_RUNNING_TASK_TIMEOUT_MINUTES}m); incomplete writes rolled back"
+    )
+    running_task.status = "failed"
+    running_task.phase = "failed"
+    running_task.completed_at = datetime.now(timezone.utc)
+    running_task.error_message = f"{existing_error}\n{stale_reason}".strip() if existing_error else stale_reason
+    datasource.last_status = "failed"
+    datasource.last_run_at = datetime.now(timezone.utc)
+    await db.commit()
+
+
 @router.get("")
 async def list_datasources(
     module: Optional[str] = None,
@@ -504,6 +575,7 @@ async def clear_datasource_data(
 async def get_task_status(
     source_id: str,
     task_id: Optional[int] = None,
+    current_user: User = Depends(get_current_user),
     db: AsyncSession = Depends(get_db),
 ):
     datasource = await get_datasource_record(db, source_id)