Update Docker configuration, enhance error handling, and improve logging

- Added health check to the camera management API service in docker-compose.yml for better container reliability.
- Updated installation scripts in Dockerfile to check for existing dependencies before installation, improving efficiency.
- Enhanced error handling in the USDAVisionSystem class to allow partial operation if some components fail to start, preventing immediate shutdown.
- Improved logging throughout the application, including more detailed error messages and critical error handling in the main loop.
- Refactored WebSocketManager and CameraMonitor classes to use debug logging for connection events, reducing log noise.

camera-management-api/usda_vision_system/main.py

@@ -208,23 +208,50 @@ class USDAVisionSystem:
     def run(self) -> None:
         """Run the system (blocking call)"""
         if not self.start():
-            self.logger.error("Failed to start system")
-            return
+            self.logger.error("Failed to start system - some components may not be available")
+            # Don't exit immediately - allow partial operation if some components started
+            # Only exit if critical components failed
+            if not self.running:
+                self.logger.critical("Critical components failed to start - exiting")
+                return
 
         try:
             self.logger.info("System running... Press Ctrl+C to stop")
 
             # Main loop - just keep the system alive
+            consecutive_errors = 0
+            max_consecutive_errors = 10
+            
             while self.running:
-                time.sleep(1)
+                try:
+                    time.sleep(1)
+                    consecutive_errors = 0  # Reset on successful iteration
 
-                # Periodic maintenance tasks could go here
-                # For example: cleanup old recordings, health checks, etc.
+                    # Periodic maintenance tasks could go here
+                    # For example: cleanup old recordings, health checks, etc.
+                    
+                    # Health check: verify critical components are still running
+                    if not self.mqtt_client.is_running():
+                        self.logger.warning("MQTT client stopped running - attempting restart")
+                        try:
+                            self.mqtt_client.start()
+                        except Exception as e:
+                            self.logger.error(f"Failed to restart MQTT client: {e}")
+                            consecutive_errors += 1
+
+                except Exception as e:
+                    consecutive_errors += 1
+                    self.logger.error(f"Error in main loop (consecutive: {consecutive_errors}): {e}", exc_info=True)
+                    
+                    # If too many consecutive errors, exit to prevent infinite crash loop
+                    if consecutive_errors >= max_consecutive_errors:
+                        self.logger.critical(f"Too many consecutive errors ({consecutive_errors}) - shutting down to prevent crash loop")
+                        break
 
         except KeyboardInterrupt:
             self.logger.info("Keyboard interrupt received")
         except Exception as e:
-            self.logger.error(f"Unexpected error in main loop: {e}")
+            self.logger.error(f"Unexpected error in main loop: {e}", exc_info=True)
         finally:
             self.stop()
 
@@ -270,8 +297,14 @@ def main():
 
     try:
         system.run()
+    except KeyboardInterrupt:
+        logging.info("Interrupted by user")
+        sys.exit(0)
     except Exception as e:
-        logging.error(f"Fatal error: {e}")
+        logging.critical(f"Fatal error: {e}", exc_info=True)
+        # Give a moment for logs to flush
+        import time
+        time.sleep(1)
         sys.exit(1)