catalogue_backend/app/main.py

"""
FastAPI application entry point.

Run with:
    uvicorn app.main:app --reload --port 8000

(see backend/README.md / the project documentation for full setup steps)
"""
from __future__ import annotations

import logging
import os
import threading
from contextlib import asynccontextmanager
from pathlib import Path

from fastapi import FastAPI, HTTPException
from fastapi.middleware.cors import CORSMiddleware
from fastapi.staticfiles import StaticFiles
from fastapi.responses import FileResponse

from app.infrastructure.persistence import restore_bundled_assets
from app.infrastructure.settings import API_CORS_ORIGINS
from app.api.routers import health, brands, search, chat, catalog, system
from app.api.routers import stores, discounts, analytics as store_analytics, trending, recommendations, store_admin
from app.api.routers import nutrition, nutrition_admin, upload
from app.api.routers import auth, user_products, admin_train
from app.services.store_db import ensure_store_intelligence_schema
from app.services.nutrition_db import ensure_nutrition_schema

logging.basicConfig(
    level=logging.INFO,
    format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
)
logger = logging.getLogger(__name__)

@asynccontextmanager
async def lifespan(_app: FastAPI):
    """
    Schema checks and auto-seeding, kicked off without blocking startup.

    The work runs on a daemon thread rather than being awaited: it touches
    Postgres, which may be slow or briefly unreachable on a cold boot, and the
    server answering /api/health in under a second is what lets the container
    healthcheck pass while that settles.
    """

    # Runs before the thread below, and synchronously: the seed catalogs and
    # model artifacts have to be in place before the first request can read
    # them, and it is a handful of file copies on first boot, nothing on every
    # boot after that.
    try:
        restore_bundled_assets()
    except Exception as e:
        logger.warning("Could not restore bundled assets: %s", e)

    def _async_init():
        try:
            ensure_store_intelligence_schema()
            ensure_nutrition_schema()
            from app.api.routers.system import _run_background_auto_seed
            _run_background_auto_seed()
        except Exception as e:
            logger.warning("Startup background init warning: %s", e)

    threading.Thread(target=_async_init, daemon=True).start()
    yield


app = FastAPI(
    title="Brand Product Search Engine - RAG API",
    description=(
        "Local, CPU-only RAG API over an Indian FMCG product catalog stored in pgvector. "
        "Includes automated multi-store intelligence, ML discount engines, and nutrition intelligence."
    ),
    version="3.2.0",
    lifespan=lifespan,
)


# When the app is served same-origin (the frontend's nginx proxies /api/* to
# this service), API_CORS_ORIGINS is empty and no cross-origin request is ever
# made. It is populated only when the API is also published on its own host -
# see api.{$DOMAIN} in the Caddyfile.
#
# A wildcard origin and credentialed requests are mutually exclusive under the
# CORS spec: browsers reject `Access-Control-Allow-Origin: *` on any request
# carrying credentials. Sending both is a silent misconfiguration - the server
# looks configured while every browser call fails - so a wildcard turns
# credentials off explicitly and says so in the log.
_allow_credentials = "*" not in API_CORS_ORIGINS
if not _allow_credentials:
    logger.warning(
        "API_CORS_ORIGINS contains '*': disabling allow_credentials, because "
        "browsers reject credentialed cross-origin requests to a wildcard origin. "
        "List the exact origins instead if you need cookies or Authorization headers."
    )

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

# A wrong origin list fails only in the browser, as an opaque "blocked by CORS"
# with a perfectly healthy 200 in the server log - so state the effective list
# at startup, where it can actually be compared against the frontend's URL.
logger.info(
    "CORS allowed origins: %s",
    ", ".join(API_CORS_ORIGINS) if API_CORS_ORIGINS else "(none - same-origin only)",
)
if API_CORS_ORIGINS and all(
    o.startswith(("http://localhost", "http://127.0.0.1")) for o in API_CORS_ORIGINS
):
    logger.warning(
        "API_CORS_ORIGINS lists only localhost origins (%s). If this API is "
        "published on a domain and the frontend is served from a different one, "
        "every browser request will be blocked. Set API_CORS_ORIGINS to the "
        "frontend's exact origin, e.g. https://catalogue.nearle.ai.in",
        ", ".join(API_CORS_ORIGINS),
    )

app.include_router(health.router, prefix="/api")
app.include_router(auth.router, prefix="/api")
app.include_router(user_products.router, prefix="/api")
app.include_router(admin_train.router, prefix="/api")
app.include_router(system.router, prefix="/api")
app.include_router(brands.router, prefix="/api")
app.include_router(search.router, prefix="/api")
app.include_router(chat.router, prefix="/api")
app.include_router(catalog.router, prefix="/api")
app.include_router(stores.router, prefix="/api")
app.include_router(discounts.router, prefix="/api")
app.include_router(store_analytics.router, prefix="/api")
app.include_router(trending.router, prefix="/api")
app.include_router(recommendations.router, prefix="/api")
app.include_router(store_admin.router, prefix="/api")
app.include_router(nutrition.router, prefix="/api")
app.include_router(nutrition_admin.router, prefix="/api")
app.include_router(upload.router, prefix="/api")

# Serve built frontend static files if dist exists (single-port unified
# deployment). Off in the normal setup: the React app is served by its own
# nginx on catalogue.nearle.ai.in and this API answers on
# mcp.catalogue.nearle.ai.in, so no dist/ is present here and the JSON root
# handler at the bottom of this file is what responds to /.
#
# The candidates cover both repo layouts - the sibling checkout is named
# `catalogue_frontend`, and only `frontend` was checked before, so this branch
# could never activate even when a build was sitting right next to it.
# FRONTEND_DIST_DIR overrides both when the build lands somewhere else.
_dist_override = os.getenv("FRONTEND_DIST_DIR", "").strip()
_repo_root = Path(__file__).resolve().parents[2]
_dist_candidates = (
    [Path(_dist_override)]
    if _dist_override
    else [
        _repo_root / "catalogue_frontend" / "dist",
        _repo_root / "frontend" / "dist",
        Path(__file__).resolve().parents[1] / "frontend" / "dist",
    ]
)
FRONTEND_DIST = next(
    (p for p in _dist_candidates if (p / "assets").exists()),
    _dist_candidates[0],
)

if FRONTEND_DIST.exists() and (FRONTEND_DIST / "assets").exists():
    logger.info("Serving built frontend from %s", FRONTEND_DIST)
    app.mount("/assets", StaticFiles(directory=str(FRONTEND_DIST / "assets")), name="assets")

    @app.get("/{full_path:path}")
    def serve_frontend(full_path: str):
        # API and docs paths are served by the routers registered above, so
        # this catch-all only sees them when the path genuinely doesn't exist.
        # Returning None there would answer 200 with a `null` body - an unknown
        # endpoint would look like a successful call to any client. 404 is the
        # honest answer, and it matters now that the API is also reachable
        # directly at api.{$DOMAIN} rather than only behind the frontend.
        if full_path.startswith(("api", "docs", "redoc", "openapi.json")):
            raise HTTPException(status_code=404, detail="Not found")
        file_path = FRONTEND_DIST / full_path
        if file_path.exists() and file_path.is_file():
            return FileResponse(file_path)
        return FileResponse(FRONTEND_DIST / "index.html")
else:
    @app.get("/")
    def root() -> dict:
        return {
            "service": "Brand Product Search Engine - RAG API",
            "docs": "/docs",
            "health": "/api/health",
            "system_status": "/api/system/status",
        }