"""STT-server — API FastAPI pour les clients STT.

Endpoints :
  GET  /healthz       → état du service
  POST /v1/ask {text} → {reply}   (requête AI, orchestrée vers LiteLLM)
"""

from __future__ import annotations

import httpx
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel

from stt_server import __version__
from stt_server.brain import ask as brain_ask
from stt_server.config import settings

app = FastAPI(title="STT-server", version=__version__)


class AskRequest(BaseModel):
    text: str
    model: str | None = None   # alias LiteLLM ; défaut serveur si absent


class AskReply(BaseModel):
    reply: str
    model: str


@app.get("/healthz")
async def healthz() -> dict:
    return {"status": "ok", "version": __version__}


@app.get("/v1/models")
async def v1_models() -> dict:
    return {"default": settings.model, "available": settings.allowed_models}


@app.post("/v1/ask", response_model=AskReply)
async def v1_ask(req: AskRequest) -> AskReply:
    text = req.text.strip()
    if not text:
        raise HTTPException(status_code=400, detail="text vide")
    model = req.model or settings.model
    if model not in settings.allowed_models:
        raise HTTPException(
            status_code=400,
            detail=f"modèle '{model}' non autorisé ; dispo : {settings.allowed_models}",
        )
    try:
        reply = await brain_ask(text, model)
    except httpx.HTTPError as e:
        raise HTTPException(status_code=502, detail=f"upstream LiteLLM : {e}") from e
    return AskReply(reply=reply, model=model)


def run() -> None:
    """Entrypoint `stt-server` (dev local). En prod : uvicorn via le conteneur."""
    import uvicorn

    uvicorn.run(app, host="0.0.0.0", port=8000)  # noqa: S104 — service interne au cluster