16a964032e
- Store: messages-Tabelle + append_message/get_recent_messages (mit Mandanten-Schutz) - LLMProvider.complete um history erweitert (openrouter + local bauen system+history+user) - Orchestrator.chat_text reicht den Verlauf ans LLM weiter - chat.py: bei session_id letzte HISTORY_MAX_MESSAGES laden, danach User-/Assistant-Turn speichern - ohne session_id weiterhin zustandslos; ?debug zeigt history_len - Config HISTORY_MAX_MESSAGES (Default 10) - Tests: 32 gruen (3 neue Gedaechtnis-Tests) - Doku aktualisiert (README, BEDIENUNGSANLEITUNG, Architektur) Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
112 lines
3.6 KiB
Python
112 lines
3.6 KiB
Python
from io import BytesIO
|
|
|
|
from fastapi import APIRouter, Depends, HTTPException, Query
|
|
from fastapi.responses import JSONResponse, StreamingResponse
|
|
|
|
from app.config import settings
|
|
from app.errors import RoutingError
|
|
from app.auth import require_user
|
|
from app.store import User, SessionOwnershipError
|
|
from app.dependencies import (
|
|
resolve_route,
|
|
build_orchestrator,
|
|
resolve_output_endpoint,
|
|
get_store,
|
|
)
|
|
from app.schemas import ChatRequest
|
|
|
|
router = APIRouter()
|
|
|
|
|
|
def _route_headers(route) -> dict:
|
|
return {
|
|
"X-Input-Endpoint": route.input_endpoint,
|
|
"X-Output-Endpoint": route.output_endpoint,
|
|
"X-STT-Provider": route.stt_provider,
|
|
"X-LLM-Provider": route.llm_provider,
|
|
"X-TTS-Provider": route.tts_provider,
|
|
}
|
|
|
|
|
|
@router.post("/chat")
|
|
async def chat(
|
|
payload: ChatRequest,
|
|
debug: bool = Query(
|
|
default=False,
|
|
description="Return JSON trace instead of audio response",
|
|
),
|
|
session_id: str | None = Query(
|
|
default=None,
|
|
description="Optional session id to apply a stored route",
|
|
),
|
|
user: User = Depends(require_user),
|
|
):
|
|
overrides = {
|
|
"input_endpoint": payload.input_endpoint,
|
|
"output_endpoint": payload.output_endpoint,
|
|
"language": payload.language,
|
|
"stt_provider": payload.stt_provider,
|
|
"llm_provider": payload.llm_provider,
|
|
"tts_provider": payload.tts_provider,
|
|
}
|
|
voice = payload.voice or settings.openrouter_tts_voice
|
|
|
|
store = get_store()
|
|
|
|
try:
|
|
route = resolve_route(user, session_id, overrides)
|
|
orchestrator = build_orchestrator(route)
|
|
output = await resolve_output_endpoint(route)
|
|
# Gespraechsverlauf laden (nur bei gesetzter session_id -> sonst zustandslos).
|
|
history = (
|
|
store.get_recent_messages(session_id, settings.history_max_messages)
|
|
if session_id
|
|
else []
|
|
)
|
|
except SessionOwnershipError as exc:
|
|
raise HTTPException(status_code=403, detail=str(exc))
|
|
except RoutingError as exc:
|
|
raise HTTPException(status_code=422, detail=str(exc))
|
|
|
|
try:
|
|
trace, audio = await orchestrator.chat_text(
|
|
payload.text,
|
|
language=route.language,
|
|
voice=voice,
|
|
output=output,
|
|
history=history,
|
|
)
|
|
except Exception as exc:
|
|
raise HTTPException(status_code=502, detail=str(exc))
|
|
|
|
# Turn persistieren (User-Eingabe + semantische Antwort) fuer das Gedaechtnis.
|
|
if session_id:
|
|
store.append_message(session_id, user.id, "user", payload.text)
|
|
store.append_message(session_id, user.id, "assistant", trace.semantic_response)
|
|
|
|
if debug:
|
|
return JSONResponse(
|
|
content={
|
|
"ok": True,
|
|
"voice": voice,
|
|
"route": route.as_dict(),
|
|
"history_len": len(history),
|
|
"trace": {
|
|
"raw_transcript": trace.raw_transcript,
|
|
"cleaned_transcript": trace.cleaned_transcript,
|
|
"semantic_response": trace.semantic_response,
|
|
"spoken_response": trace.spoken_response,
|
|
"tts_ready_text": trace.tts_ready_text,
|
|
},
|
|
}
|
|
)
|
|
|
|
headers = {
|
|
"Content-Language": route.language,
|
|
"X-Audio-Format": "pcm",
|
|
"X-Audio-Sample-Rate": "24000",
|
|
"X-Audio-Channels": "1",
|
|
"X-Audio-Sample-Width": "16",
|
|
**_route_headers(route),
|
|
}
|
|
return StreamingResponse(BytesIO(audio), media_type="audio/pcm", headers=headers)
|