src/main.py

@@ -246,7 +246,14 @@ async def cleanup_expired():
                 )
                 logger.info(f"Lage {incident['id']} archiviert (Aufbewahrung abgelaufen)")
 
-        # Verwaiste running-Einträge bereinigen (> 15 Minuten ohne Abschluss)
+        # Verwaiste running-Einträge bereinigen.
+        # Pruefen auf Pipeline-Fortschritt: legitime Long-Runner (z.B. Translator
+        # nach summary fuer jp_demo mit 200+ Artikeln ~20 Min) duerfen nicht
+        # vorzeitig gekillt werden. Ein Refresh gilt als verwaist, wenn entweder
+        # (a) seit ORPHAN_IDLE_LIMIT Min kein Pipeline-Step Fortschritt zeigte,
+        # oder (b) das harte Limit ORPHAN_HARD_LIMIT Min ueberschritten wurde.
+        ORPHAN_IDLE_LIMIT = 30
+        ORPHAN_HARD_LIMIT = 90
         cursor = await db.execute(
             "SELECT id, incident_id, started_at FROM refresh_log WHERE status = 'running'"
         )
@@ -258,12 +265,46 @@ async def cleanup_expired():
             else:
                 started = started.astimezone(TIMEZONE)
             age_minutes = (now - started).total_seconds() / 60
-            if age_minutes >= 15:
+            if age_minutes < ORPHAN_IDLE_LIMIT:
+                continue
+
+            # Letzter Pipeline-Step-Fortschritt (Start ODER Ende)
+            prog_cursor = await db.execute(
+                """SELECT MAX(COALESCE(completed_at, started_at)) AS last_activity
+                   FROM refresh_pipeline_steps WHERE refresh_log_id = ?""",
+                (orphan["id"],),
+            )
+            prog_row = await prog_cursor.fetchone()
+            last_activity_str = prog_row["last_activity"] if prog_row else None
+
+            is_orphan = False
+            reason = None
+            if age_minutes >= ORPHAN_HARD_LIMIT:
+                is_orphan = True
+                reason = f"Verwaist (>{int(age_minutes)} Min, hartes Limit {ORPHAN_HARD_LIMIT} Min)"
+            elif last_activity_str:
+                last_activity = datetime.fromisoformat(last_activity_str)
+                if last_activity.tzinfo is None:
+                    last_activity = last_activity.replace(tzinfo=TIMEZONE)
+                else:
+                    last_activity = last_activity.astimezone(TIMEZONE)
+                idle_minutes = (now - last_activity).total_seconds() / 60
+                if idle_minutes >= ORPHAN_IDLE_LIMIT:
+                    is_orphan = True
+                    reason = (
+                        f"Verwaist (kein Pipeline-Fortschritt seit {int(idle_minutes)} Min, "
+                        f"gesamt {int(age_minutes)} Min)"
+                    )
+            else:
+                is_orphan = True
+                reason = f"Verwaist (keine Pipeline-Schritte nach {int(age_minutes)} Min)"
+
+            if is_orphan:
                 await db.execute(
                     "UPDATE refresh_log SET status = 'error', completed_at = ?, error_message = ? WHERE id = ?",
-                    (now.strftime('%Y-%m-%d %H:%M:%S'), f"Verwaist (>{int(age_minutes)} Min ohne Abschluss, automatisch bereinigt)", orphan["id"]),
+                    (now.strftime('%Y-%m-%d %H:%M:%S'), reason, orphan["id"]),
                 )
-                logger.warning(f"Verwaisten Refresh #{orphan['id']} für Lage {orphan['incident_id']} bereinigt ({int(age_minutes)} Min)")
+                logger.warning(f"Verwaisten Refresh #{orphan['id']} fuer Lage {orphan['incident_id']} bereinigt: {reason}")
 
         # Alte Notifications bereinigen (> 7 Tage)
         await db.execute("DELETE FROM notifications WHERE created_at < datetime('now', '-7 days')")