telegram-helper-bot/helper_bot/server_prometheus.py

"""
HTTP server for metrics endpoint integration with centralized Prometheus monitoring.
Provides /metrics endpoint and health check for the bot.
"""

import asyncio
import logging
from aiohttp import web
from typing import Optional
from .utils.metrics import metrics


class MetricsServer:
    """HTTP server for Prometheus metrics and health checks."""
    
    def __init__(self, host: str = '0.0.0.0', port: int = 8080):
        self.host = host
        self.port = port
        self.app = web.Application()
        self.runner: Optional[web.AppRunner] = None
        self.site: Optional[web.TCPSite] = None
        self.logger = logging.getLogger(__name__)
        
        # Настраиваем роуты
        self.app.router.add_get('/metrics', self.metrics_handler)
        self.app.router.add_get('/health', self.health_handler)
    
    async def metrics_handler(self, request: web.Request) -> web.Response:
        """Handle /metrics endpoint for Prometheus scraping."""
        try:
            self.logger.debug("Generating metrics...")
            
            # Проверяем, что metrics доступен
            if not metrics:
                self.logger.error("Metrics object is not available")
                return web.Response(
                    text="Metrics not available",
                    status=500
                )
            
            # Генерируем метрики в формате Prometheus
            metrics_data = metrics.get_metrics()
            self.logger.debug(f"Generated metrics: {len(metrics_data)} bytes")
            
            return web.Response(
                body=metrics_data,
                content_type='text/plain; version=0.0.4'
            )
        except Exception as e:
            self.logger.error(f"Error generating metrics: {e}")
            import traceback
            self.logger.error(f"Traceback: {traceback.format_exc()}")
            return web.Response(
                text=f"Error generating metrics: {e}",
                status=500
            )
    
    async def health_handler(self, request: web.Request) -> web.Response:
        """Handle /health endpoint for health checks."""
        try:
            # Проверяем доступность метрик
            if not metrics:
                return web.Response(
                    text="ERROR: Metrics not available",
                    content_type='text/plain',
                    status=503
                )
            
            # Проверяем, что можем получить метрики
            try:
                metrics_data = metrics.get_metrics()
                if not metrics_data:
                    return web.Response(
                        text="ERROR: Empty metrics",
                        content_type='text/plain',
                        status=503
                    )
            except Exception as e:
                return web.Response(
                    text=f"ERROR: Metrics generation failed: {e}",
                    content_type='text/plain',
                    status=503
                )
            
            return web.Response(
                text="OK",
                content_type='text/plain',
                status=200
            )
        except Exception as e:
            self.logger.error(f"Health check failed: {e}")
            return web.Response(
                text=f"ERROR: Health check failed: {e}",
                content_type='text/plain',
                status=500
            )
    
    async def start(self) -> None:
        """Start the HTTP server."""
        try:
            self.runner = web.AppRunner(self.app)
            await self.runner.setup()
            
            self.site = web.TCPSite(self.runner, self.host, self.port)
            await self.site.start()
            
            self.logger.info(f"Metrics server started on {self.host}:{self.port}")
            self.logger.info("Available endpoints:")
            self.logger.info(f"  - /metrics - Prometheus metrics")
            self.logger.info(f"  - /health - Health check")
            
        except Exception as e:
            self.logger.error(f"Failed to start metrics server: {e}")
            raise
    
    async def stop(self) -> None:
        """Stop the HTTP server."""
        try:
            if self.site:
                await self.site.stop()
                self.logger.info("Metrics server site stopped")
            
            if self.runner:
                await self.runner.cleanup()
                self.logger.info("Metrics server runner cleaned up")
                
        except Exception as e:
            self.logger.error(f"Error stopping metrics server: {e}")
    
    async def __aenter__(self):
        """Async context manager entry."""
        await self.start()
        return self
    
    async def __aexit__(self, exc_type, exc_val, exc_tb):
        """Async context manager exit."""
        await self.stop()


# Глобальный экземпляр сервера для использования в main.py
metrics_server: Optional[MetricsServer] = None


async def start_metrics_server(host: str = '0.0.0.0', port: int = 8080) -> MetricsServer:
    """Start metrics server and return instance."""
    global metrics_server
    metrics_server = MetricsServer(host, port)
    await metrics_server.start()
    return metrics_server


async def stop_metrics_server() -> None:
    """Stop metrics server if running."""
    global metrics_server
    if metrics_server:
        try:
            await metrics_server.stop()
            logger = logging.getLogger(__name__)
            logger.info("Metrics server stopped successfully")
        except Exception as e:
            logger = logging.getLogger(__name__)
            logger.error(f"Error stopping metrics server: {e}")
        finally:
            metrics_server = None