fix: database connection stability issues in production

- Add robust connection pool configuration with timeouts and retry settings
- Implement retry logic in maintenance middleware for connection errors
- Increase connection stability with keepAlive and proper timeout values
- Handle "Connection terminated unexpectedly" errors gracefully

This prevents 503 errors when the database connection is temporarily interrupted
and ensures the application can recover from transient connection issues.

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

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

backend/src/middleware/maintenance.js

@@ -5,6 +5,36 @@ let maintenanceMode = false;
 let lastCheck = 0;
 const CACHE_DURATION = 60000; // 1 minute
 
+// Retry configuration for database queries
+const MAX_RETRIES = 3;
+const RETRY_DELAY = 1000; // 1 second
+
+async function queryWithRetry(queryFn, retries = MAX_RETRIES) {
+  for (let i = 0; i < retries; i++) {
+    try {
+      return await queryFn();
+    } catch (error) {
+      if (i === retries - 1) {
+        throw error;
+      }
+      
+      // Check if it's a connection error that might benefit from retry
+      const isConnectionError = 
+        error.message?.includes('Connection terminated') ||
+        error.message?.includes('ECONNREFUSED') ||
+        error.message?.includes('ETIMEDOUT') ||
+        error.code === 'ECONNRESET';
+      
+      if (isConnectionError) {
+        console.warn(`Database connection error, retrying in ${RETRY_DELAY}ms... (attempt ${i + 1}/${retries})`);
+        await new Promise(resolve => setTimeout(resolve, RETRY_DELAY));
+      } else {
+        throw error; // Don't retry non-connection errors
+      }
+    }
+  }
+}
+
 async function checkMaintenanceMode() {
   const now = Date.now();
   
@@ -14,18 +44,21 @@ async function checkMaintenanceMode() {
   }
   
   try {
-    const setting = await db('app_settings')
-      .where('setting_key', 'general_maintenance_mode')
-      .where('setting_type', 'general')
-      .first();
+    const setting = await queryWithRetry(async () => {
+      return await db('app_settings')
+        .where('setting_key', 'general_maintenance_mode')
+        .where('setting_type', 'general')
+        .first();
+    });
     
     maintenanceMode = setting ? (setting.setting_value === 'true' || setting.setting_value === true) : false;
     lastCheck = now;
     
     return maintenanceMode;
   } catch (error) {
-    console.error('Error checking maintenance mode:', error);
-    return false;
+    console.error('Error checking maintenance mode after retries:', error.message);
+    // Return cached value or false if no cache
+    return maintenanceMode;
   }
 }
 
@@ -52,14 +85,19 @@ async function maintenanceMiddleware(req, res, next) {
     return next();
   }
   
-  const inMaintenance = await checkMaintenanceMode();
-  
-  if (inMaintenance && !isAdminRoute) {
-    return res.status(503).json({
-      error: 'Service Unavailable',
-      message: 'The system is currently undergoing maintenance. Please try again later.',
-      maintenance: true
-    });
+  try {
+    const inMaintenance = await checkMaintenanceMode();
+    
+    if (inMaintenance && !isAdminRoute) {
+      return res.status(503).json({
+        error: 'Service Unavailable',
+        message: 'The system is currently undergoing maintenance. Please try again later.',
+        maintenance: true
+      });
+    }
+  } catch (error) {
+    // If we can't check maintenance mode, allow the request to proceed
+    console.error('Failed to check maintenance mode, allowing request:', error.message);
   }
   
   next();