Add HTTP health check endpoint for container monitoring

Implements a comprehensive health check system using aiohttp to support
container orchestration and external monitoring systems.

Features:
- /health endpoint: Basic liveness check (is process running?)
- /ready endpoint: Readiness check (is bot connected to Discord?)
- /metrics endpoint: Detailed bot metrics (guilds, users, cogs, latency)

Changes:
- Add aiohttp to requirements.txt
- Create health_server.py module with HTTP server
- Update paperdynasty.py to run health server alongside bot
- Update docker-compose.yml with HTTP-based healthcheck
- Fix deploy.sh Docker image name

Benefits:
- Auto-restart on bot hangs/deadlocks
- Foundation for external monitoring (Prometheus, Grafana, etc.)
- Detailed diagnostics for troubleshooting
- Industry-standard health check pattern

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

deploy.sh

@@ -2,7 +2,7 @@
 set -e  # Exit on error
 
 # Configuration
-DOCKER_IMAGE="manticorum67/paper-dynasty"
+DOCKER_IMAGE="manticorum67/paper-dynasty-discordapp"
 REMOTE_HOST="sba-bots"
 REMOTE_PATH="/home/cal/container-data/paper-dynasty"
 DOCKERFILE_PATH="."

health_server.py

@@ -0,0 +1,132 @@
+"""
+HTTP health check server for Paper Dynasty Discord bot.
+
+Provides health and readiness endpoints for container monitoring and orchestration.
+"""
+import asyncio
+import logging
+from typing import Optional
+from aiohttp import web
+import discord
+from discord.ext import commands
+
+logger = logging.getLogger('discord_app.health')
+
+
+class HealthServer:
+    """HTTP server for health checks and metrics."""
+
+    def __init__(self, bot: commands.Bot, host: str = '0.0.0.0', port: int = 8080):
+        """
+        Initialize health server.
+
+        Args:
+            bot: Discord bot instance to monitor
+            host: Host to bind to (default: 0.0.0.0 for container access)
+            port: Port to listen on (default: 8080)
+        """
+        self.bot = bot
+        self.host = host
+        self.port = port
+        self.app = web.Application()
+        self.runner: Optional[web.AppRunner] = None
+        self.site: Optional[web.TCPSite] = None
+
+        # Setup routes
+        self.app.router.add_get('/health', self.health_check)
+        self.app.router.add_get('/ready', self.readiness_check)
+        self.app.router.add_get('/metrics', self.metrics)
+
+    async def health_check(self, request: web.Request) -> web.Response:
+        """
+        Basic liveness check - is the process running?
+
+        Returns 200 if the server is responsive.
+        """
+        return web.json_response({
+            'status': 'healthy',
+            'service': 'paper-dynasty-discord-bot'
+        })
+
+    async def readiness_check(self, request: web.Request) -> web.Response:
+        """
+        Readiness check - is the bot ready to serve requests?
+
+        Returns:
+            200 if bot is connected to Discord
+            503 if bot is not ready
+        """
+        if self.bot.is_ready():
+            return web.json_response({
+                'status': 'ready',
+                'discord_connected': True,
+                'latency_ms': round(self.bot.latency * 1000, 2) if self.bot.latency else None
+            })
+        else:
+            return web.json_response({
+                'status': 'not_ready',
+                'discord_connected': False
+            }, status=503)
+
+    async def metrics(self, request: web.Request) -> web.Response:
+        """
+        Return bot metrics for monitoring.
+
+        Provides detailed information about bot state for external monitoring systems.
+        """
+        metrics_data = {
+            'bot': {
+                'is_ready': self.bot.is_ready(),
+                'is_closed': self.bot.is_closed(),
+                'latency_ms': round(self.bot.latency * 1000, 2) if self.bot.latency else None,
+            },
+            'guilds': {
+                'count': len(self.bot.guilds),
+                'guild_ids': [g.id for g in self.bot.guilds]
+            },
+            'users': {
+                'count': len(self.bot.users)
+            },
+            'cogs': {
+                'loaded': list(self.bot.cogs.keys()),
+                'count': len(self.bot.cogs)
+            }
+        }
+
+        return web.json_response(metrics_data)
+
+    async def start(self):
+        """Start the health check server."""
+        self.runner = web.AppRunner(self.app)
+        await self.runner.setup()
+        self.site = web.TCPSite(self.runner, self.host, self.port)
+        await self.site.start()
+        logger.info(f'Health check server started on {self.host}:{self.port}')
+
+    async def stop(self):
+        """Stop the health check server."""
+        if self.site:
+            await self.site.stop()
+        if self.runner:
+            await self.runner.cleanup()
+        logger.info('Health check server stopped')
+
+
+async def run_health_server(bot: commands.Bot, host: str = '0.0.0.0', port: int = 8080):
+    """
+    Run health server as a background task.
+
+    Args:
+        bot: Discord bot instance
+        host: Host to bind to
+        port: Port to listen on
+    """
+    server = HealthServer(bot, host, port)
+    await server.start()
+
+    # Keep the server running until bot is closed
+    try:
+        while not bot.is_closed():
+            await asyncio.sleep(1)
+    finally:
+        await server.stop()

paperdynasty.py

@@ -8,6 +8,7 @@ import os
 from discord.ext import commands
 
 from in_game.gameplay_models import create_db_and_tables
+from health_server import run_health_server
 
 raw_log_level = os.getenv('LOG_LEVEL')
 if raw_log_level == 'DEBUG':
@@ -100,7 +101,21 @@ async def main():
         except Exception as e:
             logger.error(f'Failed to load cog: {c}')
             logger.error(f'{e}')
+
+    # Start health server and bot concurrently
     async with bot:
-        await bot.start(os.environ.get('BOT_TOKEN', 'NONE'))
+        # Create health server task
+        health_task = asyncio.create_task(run_health_server(bot))
+
+        try:
+            # Start bot (this blocks until bot stops)
+            await bot.start(os.environ.get('BOT_TOKEN', 'NONE'))
+        finally:
+            # Cleanup: cancel health server when bot stops
+            health_task.cancel()
+            try:
+                await health_task
+            except asyncio.CancelledError:
+                pass
 
 asyncio.run(main())

requirements.txt

@@ -10,4 +10,5 @@ pytest
 pytest-asyncio
 pandas
 psycopg2-binary
+aiohttp
 # psycopg[binary]