import asyncio
import logging
import os
import sys
from contextlib import asynccontextmanager

from alembic import command
from alembic.config import Config as AlembicConfig
from fastapi import FastAPI
from fastapi.middleware.cors import CORSMiddleware
from fastapi.staticfiles import StaticFiles

from config import settings

# Настройка логов до импорта приложения: uvicorn ставит свои handlers
# на root-logger, поэтому basicConfig в lifespan уже не срабатывает
# (handlers есть — basicConfig no-op). force=True перебивает.
logging.basicConfig(
    level=getattr(logging, settings.log_level.upper(), logging.INFO),
    format="%(asctime)s %(levelname)-7s %(name)s: %(message)s",
    datefmt="%H:%M:%S",
    handlers=[logging.StreamHandler(sys.stderr)],
    force=True,
)

from services.embeddings import EmbeddingService  # noqa: E402
from services.llm_client import LLMClient  # noqa: E402
from services.vectorstore import VectorStoreService  # noqa: E402

logger = logging.getLogger(__name__)

embedding_service: EmbeddingService | None = None
vectorstore_service: VectorStoreService | None = None
llm_client: LLMClient | None = None


def _run_migrations() -> None:
    """Автоматически подтягиваем схему до последней ревизии при старте."""
    os.makedirs(os.path.dirname(settings.sqlite_path), exist_ok=True)
    cfg = AlembicConfig("alembic.ini")
    command.upgrade(cfg, "head")


@asynccontextmanager
async def lifespan(app: FastAPI):
    global embedding_service, vectorstore_service, llm_client
    logger.info("Running DB migrations…")
    await asyncio.to_thread(_run_migrations)
    logger.info("Loading embedding model: %s", settings.embedding_model)
    embedding_service = EmbeddingService(settings.embedding_model)
    logger.info("Embedding model loaded")
    vectorstore_service = VectorStoreService(
        persist_dir=settings.chroma_persist_dir,
        embedding_service=embedding_service,
    )
    logger.info("ChromaDB initialized at %s", settings.chroma_persist_dir)
    llm_client = LLMClient()
    logger.info("LLM client ready (model=%s)", llm_client.model)
    yield
    logger.info("Shutting down")


app = FastAPI(
    title="Chat Agent for Patients — Tuning Tool",
    description="RAG-ядро и инструмент настройки пациентского чат-агента",
    version="0.1.0",
    lifespan=lifespan,
)

app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
)

from routers import chat, documents, health, query, threads  # noqa: E402

app.include_router(health.router)
app.include_router(documents.router)
app.include_router(query.router)
app.include_router(chat.router)
app.include_router(threads.router)

app.mount("/", StaticFiles(directory="static", html=True), name="static")