dschlueter/my_voice_assistant_v3_jamulix
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

feat(1a): Flex-Sprachmodus vollständig entfernen

Browse source 
Sprache ist immer fest. Entfernt: language_mode aus Route/Schema/Config/
Runtime-Config, die Flex-Verzweigung in Orchestrator (effective_language =
language) und ws.py (immer normales transcribe), die "🔄 Flex"-Option im
Frontend samt zugehöriger app.js-Logik (langOverrides, loadMe, Turn-Sprache).

Die generische STT-Methode transcribe_detect bleibt als wiederverwendbare
Infrastruktur erhalten (nicht mehr aufgerufen). Test: Route trägt kein
language_mode mehr. 215 passed.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Dieter Schlüter 2026-06-25 02:51:17 +02:00
commit be5206c7ed
10 changed files with 24 additions and 64 deletions
Download patch file Download diff file Expand all files Collapse all files

28
app/api/ws.py
View file

@ -42,7 +42,6 @@ _OVERRIDE_KEYS = (
"input_endpoint",
"output_endpoint",
"language",
"language_mode",
"stt_provider",
"llm_provider",
"tts_provider",
@ -67,7 +66,7 @@ async def _resolve(user, session_id, options):
async def _run_turn(
websocket, store, user, session_id, route, orchestrator, output, text, options,
detected_language: str | None = None, effective_voice: str | None = None,
effective_voice: str | None = None,
):
"""Faehrt einen Antwort-Turn und streamt die Events an den Client."""
conversation = (
@ -158,8 +157,6 @@ async def _run_turn(
history=llm_context,
on_token=on_token,
on_audio=on_audio,
language_mode=route.language_mode,
detected_language=detected_language,
text_only=text_only,
)
else:
@ -169,8 +166,6 @@ async def _run_turn(
voice=voice,
output=output,
history=llm_context,
language_mode=route.language_mode,
detected_language=detected_language,
text_only=text_only,
)
except Exception as exc:
@ -228,21 +223,9 @@ async def _voice_turn(websocket, store, user, session_id, audio, fmt, options):
return
try:
if route.language_mode == "flex":
# Flex: Sprache auto-erkennen, kein Übersetzen durch Whisper.
transcript, detected_language = await orchestrator.stt.transcribe_detect(
audio, fmt=fmt, language=None
)
# Stimme folgt der erkannten Sprache (Fallback: Routensprache).
effective_voice = voice_for_route(
route.tts_provider, detected_language or route.language, route.voice_gender
)
else:
# Fix: konfigurierte Sprache an Whisper → Whisper übersetzt automatisch.
transcript = await orchestrator.stt.transcribe(audio, fmt=fmt, language=route.language)
detected_language = None
# Stimme folgt der konfigurierten Sprache.
effective_voice = voice_for_route(route.tts_provider, route.language, route.voice_gender)
# Feste Sprache an Whisper → Whisper übersetzt automatisch.
transcript = await orchestrator.stt.transcribe(audio, fmt=fmt, language=route.language)
effective_voice = voice_for_route(route.tts_provider, route.language, route.voice_gender)
except Exception as exc:
await websocket.send_json({"type": "error", "status": 502, "detail": str(exc)})
return
@ -250,7 +233,6 @@ async def _voice_turn(websocket, store, user, session_id, audio, fmt, options):
await websocket.send_json({
"type": "transcript",
"text": transcript,
"detected_language": detected_language,
})
if not transcript or not transcript.strip():
await websocket.send_json({
@ -260,7 +242,7 @@ async def _voice_turn(websocket, store, user, session_id, audio, fmt, options):
return
await _run_turn(
websocket, store, user, session_id, route, orchestrator, output, transcript, options,
detected_language=detected_language, effective_voice=effective_voice,
effective_voice=effective_voice,
)