forecasting/backend/main.py

"""
Forecasting Application — FastAPI Backend
Auth is handled by the central HNF stack cookie (hnf_session).
"""
import logging
import sys
import os
import time
from contextlib import asynccontextmanager

logging.basicConfig(
    level=logging.INFO,
    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
    handlers=[logging.StreamHandler(sys.stdout)]
)

from fastapi import FastAPI
from fastapi.middleware.cors import CORSMiddleware
from sqlalchemy import text

from database import async_engine
from api import (
    forecast, sync, export, budget, accuracy, evolution, crossref,
    explain, config, historical, resos, backtest, sync_bookings,
    resos_sync, reports, special_dates, backup, public, ai_insights,
)
from scheduler import start_scheduler, shutdown_scheduler


@asynccontextmanager
async def lifespan(app: FastAPI):
    # Apply database schema (idempotent CREATE TABLE IF NOT EXISTS)
    # Uses psycopg2 directly — schema.sql contains PL/pgSQL with $1/$2 syntax
    # that SQLAlchemy text() misinterprets as bindparams.
    try:
        import os, psycopg2
        from database import DATABASE_URL
        schema_path = os.path.join(os.path.dirname(__file__), 'schema.sql')
        if os.path.exists(schema_path):
            with open(schema_path) as f:
                sql = f.read()
            conn = psycopg2.connect(DATABASE_URL)
            try:
                conn.autocommit = True
                with conn.cursor() as cur:
                    cur.execute(sql)
                logging.getLogger(__name__).info("Schema applied successfully")
            finally:
                conn.close()
    except Exception as e:
        logging.getLogger(__name__).warning(f"Schema init failed: {e}")

    # Startup: clean up stale scrape batches
    try:
        from services.booking_scraper import cleanup_stale_batches
        from database import SyncSessionLocal
        db = SyncSessionLocal()
        try:
            cleanup_stale_batches(db, max_age_minutes=10)
        finally:
            db.close()
    except Exception as e:
        logging.getLogger(__name__).warning(f"Stale batch cleanup failed: {e}")

    # Startup: mark any sync_log entries stuck as 'running' as failed
    # (these are orphaned by container restarts mid-job)
    try:
        import psycopg2
        from database import DATABASE_URL
        conn = psycopg2.connect(DATABASE_URL)
        try:
            conn.autocommit = True
            with conn.cursor() as cur:
                cur.execute("""
                    UPDATE sync_log
                    SET status = 'failed',
                        completed_at = NOW(),
                        error_message = 'Interrupted by container restart'
                    WHERE status = 'running' AND completed_at IS NULL
                """)
                if cur.rowcount:
                    logging.getLogger(__name__).info(f"Cleared {cur.rowcount} stale sync_log entries")
        finally:
            conn.close()
    except Exception as e:
        logging.getLogger(__name__).warning(f"Stale sync_log cleanup failed: {e}")

    # Ensure ai_insights table exists
    try:
        from database import SyncSessionLocal
        db = SyncSessionLocal()
        try:
            db.execute(text("""
                CREATE TABLE IF NOT EXISTS ai_insights (
                    id SERIAL PRIMARY KEY,
                    generated_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
                    insight_type VARCHAR(50) NOT NULL DEFAULT 'daily_summary',
                    content TEXT NOT NULL,
                    model VARCHAR(100),
                    input_tokens INTEGER,
                    output_tokens INTEGER,
                    data_snapshot JSONB,
                    triggered_by VARCHAR(50) DEFAULT 'scheduler'
                )
            """))
            db.execute(text("""
                CREATE INDEX IF NOT EXISTS idx_ai_insights_generated
                ON ai_insights(generated_at DESC)
            """))
            db.execute(text("""
                ALTER TABLE ai_insights ADD COLUMN IF NOT EXISTS headline TEXT
            """))
            db.commit()
        finally:
            db.close()
    except Exception as e:
        logging.getLogger(__name__).warning(f"AI insights table creation failed: {e}")

    start_scheduler()
    yield
    shutdown_scheduler()


app = FastAPI(
    title="Forecasting API",
    description="Hotel & Restaurant Forecasting Service",
    version="2.0.0",
    lifespan=lifespan,
)
STARTED_AT = str(int(time.time() * 1000))

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

# All routes — nginx strips /forecasting/api/ prefix before reaching here
app.include_router(forecast.router,          prefix="/forecast",          tags=["Forecasts"])
app.include_router(sync.router,              prefix="/sync",              tags=["Data Sync"])
app.include_router(export.router,            prefix="/export",            tags=["Exports"])
app.include_router(budget.router,            prefix="/budget",            tags=["Budgets"])
app.include_router(accuracy.router,          prefix="/accuracy",          tags=["Accuracy"])
app.include_router(evolution.router,         prefix="/evolution",         tags=["Forecast Evolution"])
app.include_router(crossref.router,          prefix="/crossref",          tags=["Cross-Reference"])
app.include_router(explain.router,           prefix="/explain",           tags=["Explainability"])
app.include_router(config.router,            prefix="/config",            tags=["Configuration"])
app.include_router(historical.router,        prefix="/historical",        tags=["Historical Data"])
app.include_router(resos.router,             prefix="/resos",             tags=["Resos Mapping"])
app.include_router(backtest.router,          prefix="/backtest",          tags=["Backtesting"])
app.include_router(sync_bookings.router,     prefix="/sync",              tags=["Data Sync"])
app.include_router(resos_sync.router,        prefix="/sync",              tags=["Data Sync"])
app.include_router(reports.router,           prefix="/reports",           tags=["Reports"])
app.include_router(special_dates.router,     prefix="/settings",          tags=["Settings"])
app.include_router(backup.router,            prefix="/backup",            tags=["Backup & Restore"])
app.include_router(public.router,            prefix="/public",            tags=["Public API"])
app.include_router(ai_insights.router,       prefix="/ai-insights",       tags=["AI Insights"])


@app.get("/health")
async def health_check():
    return {"status": "healthy", "service": "forecasting-api", "version": os.environ.get("BUILD_VERSION", STARTED_AT)}