6422444017
- Fallback-Provider (app/providers/fallback.py) fuer STT/LLM/TTS: Provider-Kette der Reihe nach; Config *_FALLBACK; build_orchestrator baut Ketten (dedupliziert) - LLM-Stream-Fallback nur solange kein Token gesendet wurde - Metriken (app/metrics.py): In-Memory Counter/Timer, keine externe Dependency - HTTP-Middleware (Requests/Latenz/Status je Pfad); Pipeline-Stufen-Timing stt/llm/tts; Fallback-/Fehlerzaehler; GET /api/metrics (JSON + Prometheus) - Tests: 58 gruen (+6); Doku aktualisiert (README, BEDIENUNGSANLEITUNG, Architektur, .env.example) Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
85 lines
3.1 KiB
Python
85 lines
3.1 KiB
Python
"""Fallback-Ketten: versuchen mehrere Provider der Reihe nach.
|
|
|
|
Faellt der primaere Provider aus (Timeout/Fehler), wird transparent der naechste
|
|
versucht. Erfolgreicher Fallback und Provider-Fehler werden als Metrik erfasst.
|
|
"""
|
|
|
|
from collections.abc import AsyncIterator
|
|
|
|
from app.metrics import metrics
|
|
|
|
|
|
class _Chain:
|
|
def __init__(self, module: str, entries: list[tuple[str, object]]):
|
|
self.module = module
|
|
self.entries = entries # [(provider_name, provider), ...]
|
|
|
|
def _on_error(self, name: str) -> None:
|
|
metrics.inc("provider_error_total", {"module": self.module, "provider": name})
|
|
|
|
def _on_fallback(self) -> None:
|
|
metrics.inc("provider_fallback_total", {"module": self.module})
|
|
|
|
|
|
class FallbackSTTProvider(_Chain):
|
|
async def transcribe(self, audio_bytes, fmt, language=None) -> str:
|
|
last_exc = None
|
|
for index, (name, provider) in enumerate(self.entries):
|
|
try:
|
|
result = await provider.transcribe(audio_bytes, fmt, language=language)
|
|
if index > 0:
|
|
self._on_fallback()
|
|
return result
|
|
except Exception as exc: # noqa: BLE001 - bewusst breit fuer Resilienz
|
|
last_exc = exc
|
|
self._on_error(name)
|
|
raise last_exc
|
|
|
|
|
|
class FallbackLLMProvider(_Chain):
|
|
async def complete(self, text, history=None, session_id=None) -> str:
|
|
last_exc = None
|
|
for index, (name, provider) in enumerate(self.entries):
|
|
try:
|
|
result = await provider.complete(text, history=history, session_id=session_id)
|
|
if index > 0:
|
|
self._on_fallback()
|
|
return result
|
|
except Exception as exc: # noqa: BLE001
|
|
last_exc = exc
|
|
self._on_error(name)
|
|
raise last_exc
|
|
|
|
async def stream(self, text, history=None, session_id=None) -> AsyncIterator[str]:
|
|
last_exc = None
|
|
for index, (name, provider) in enumerate(self.entries):
|
|
produced = False
|
|
try:
|
|
async for delta in provider.stream(text, history=history, session_id=session_id):
|
|
produced = True
|
|
yield delta
|
|
if index > 0:
|
|
self._on_fallback()
|
|
return
|
|
except Exception as exc: # noqa: BLE001
|
|
last_exc = exc
|
|
self._on_error(name)
|
|
if produced:
|
|
# Schon Token gesendet -> kein Fallback mehr moeglich.
|
|
raise
|
|
raise last_exc
|
|
|
|
|
|
class FallbackTTSProvider(_Chain):
|
|
async def synthesize(self, text, voice=None, audio_format="pcm") -> bytes:
|
|
last_exc = None
|
|
for index, (name, provider) in enumerate(self.entries):
|
|
try:
|
|
result = await provider.synthesize(text, voice=voice, audio_format=audio_format)
|
|
if index > 0:
|
|
self._on_fallback()
|
|
return result
|
|
except Exception as exc: # noqa: BLE001
|
|
last_exc = exc
|
|
self._on_error(name)
|
|
raise last_exc
|