update

backend/kanban.py

@@ -19,6 +19,7 @@ import logging
 
 import database as db
 from config import KANBAN_BATCH, MAX_CARD_RETRIES, MAX_CONCURRENT_AGENTS_PER_TOPIC, RETRY_BACKOFF
+from pipeline import AgentInfraError
 
 log = logging.getLogger("creator.kanban")
 
@@ -165,6 +166,12 @@ async def _worker(flow: Flow, spec: Stage, inflight: int, all_stages: list[str])
         flow.active_cards.update(f"{spec.board}:{i}" for i in ids)
         try:
             await spec.process(cards)
+        except AgentInfraError as e:  # 429/Timeout erschöpft → Lauf pausieren, NICHT dead-letter
+            log.warning("kanban %s/%s: infra-pause: %s", topic, spec.stage, e)
+            flow.state["infra_paused"] = True
+            flow.state["infra_error"] = str(e)
+            flow.stop = True
+            flow.wake.set()
         except Exception as e:  # one bad package must not kill the worker → backoff/dead-letter
             log.info("kanban %s/%s: %s: %s", topic, spec.stage, type(e).__name__, e)
             try: