update

backend/pipeline.py

@@ -77,6 +77,15 @@ def _claude_error(label: str, returncode: int, stdout: str, stderr: str) -> str:
     return f"{label} (exit {returncode}, no output)"
 
 
+_INFRA_MARKERS = ("HTTP 429", "HTTP 5", "rate_limit", "Timeout after",
+                  "ConnectError", "ConnectTimeout", "ReadError", "RemoteProtocolError")
+
+
+def _is_infra(err: str) -> bool:
+    """Transport-/Infra-Fehler (retry + pause) statt inhaltlichem Fehlschlag."""
+    return any(m in (err or "") for m in _INFRA_MARKERS)
+
+
 def _gather_error(label: str, results: list) -> str:
     for r in results:
         if isinstance(r, BaseException):
@@ -158,7 +167,8 @@ def _enum_map_schema(key: str, allowed):
 _yesno_schema = _enum_map_schema("relevant", _YESNO)            # triage gate ∈ ja/nein
 
 
-from config import MAX_RESTARTS as _MAX_RESTARTS, HEDGE_NACH_S as _HEDGE_NACH_S  # noqa: E402 — zentral tunebar
+from config import (MAX_RESTARTS as _MAX_RESTARTS, HEDGE_NACH_S as _HEDGE_NACH_S,  # noqa: E402 — zentral tunebar
+                    INFRA_MAX_RETRIES as _INFRA_MAX_RETRIES, INFRA_BACKOFF_BASE as _INFRA_BACKOFF)
 
 
 async def _race(topic: str, label: str, slots: list[dict], quorum: int, timeout: int, provider: str, cancelled=None, *, grace: int | None = None) -> list | None:
@@ -176,6 +186,8 @@ async def _race(topic: str, label: str, slots: list[dict], quorum: int, timeout:
     keeps running until it stands. Returns: `quorum` to `len(slots)` results.
     """
     attempts = {i: 0 for i in range(len(slots))}
+    infra_attempts = {i: 0 for i in range(len(slots))}
+    infra_erschoepft: set[int] = set()
     tasks: dict[asyncio.Task, int] = {}
     keys: dict[asyncio.Task, str] = {}
     born: dict[asyncio.Task, float] = {}
@@ -267,17 +279,32 @@ async def _race(topic: str, label: str, slots: list[dict], quorum: int, timeout:
                         return results
                     continue
 
-                _log(topic, f"{label} {i + 1} (attempt {attempts[i] + 1}): {err}")
+                infra = _is_infra(err)
+                _log(topic, f"{label} {i + 1} (attempt {attempts[i] + 1}{' infra' if infra else ''}): {err}")
                 attempts[i] += 1
                 # If the minimum already stands, restarts are pointless — the restart
                 # would be killed at the grace end anyway. A still-running twin IS the retry.
                 enough = grace is not None and len(results) >= quorum
                 zwilling = any(i2 == i for i2 in tasks.values())
-                if attempts[i] <= _MAX_RESTARTS and not enough and not zwilling and not (cancelled and cancelled()):
+                if enough or zwilling or (cancelled and cancelled()):
+                    continue
+                if infra:
+                    # 429/Timeout/Netz: eigener Zähler + wachsende Pause, dann Eskalation
+                    infra_attempts[i] += 1
+                    if infra_attempts[i] > _INFRA_MAX_RETRIES:
+                        infra_erschoepft.add(i)  # kein Respawn → raise am Quorum-Miss
+                        continue
+                    await asyncio.sleep(_INFRA_BACKOFF * 2 ** (infra_attempts[i] - 1))
+                    spawn(i)
+                elif attempts[i] <= _MAX_RESTARTS:
                     spawn(i)
         if len(results) >= quorum:  # all slots done, minimum stands (only reachable with grace)
             return results
         _log(topic, f"{label}: quorum {quorum} not reached ({len(results)} valid)")
+        if infra_erschoepft:
+            raise AgentInfraError(
+                f"{label}: {len(infra_erschoepft)} Slot(s) nach {_INFRA_MAX_RETRIES} "
+                "Infra-Retries erschöpft (429/Timeout)")
         return None
     finally:
         for task, i in tasks.items():
@@ -300,6 +327,11 @@ class GenContext:
 OK, CANCELLED, FAILED = "ok", "cancelled", "failed"
 
 
+class AgentInfraError(Exception):
+    """Slot nach Infra-Retries erschöpft (429/Timeout). KEIN inhaltliches Urteil —
+    der Aufrufer pausiert den Lauf, nie fail-open."""
+
+
 async def run_single_slot(
     ctx: GenContext, label: str, *,
     key: str, prompt: str, role: str, capabilities: str, payload, timeout: int, on_line=None,