SIENTIAPDE-1350: Configure separate task queues for train and cleanup workers, update sientia-dataops-library to 1.6.1 and refactor prometheus server startup to use logger.

tests/worker/test_worker.py

@@ -109,14 +109,18 @@ def test_sdk_metrics_port_from_env():
 @patch('model_manager.worker.worker.POD_ID', 'test-pod-123')
 @patch('model_manager.worker.worker.start_http_server')
 @patch('model_manager.worker.worker.metrics')
-def test_start_prometheus_server_success(mock_metrics, mock_start_http_server, mock_env_vars):
+def test_start_prometheus_server_success(
+    mock_metrics, mock_start_http_server, mock_env_vars, mock_logger
+):
     """Test successful Prometheus server startup."""
     from model_manager.worker.worker import start_prometheus_server
 
     mock_app_up = Mock()
     mock_metrics.APP_UP.labels.return_value = mock_app_up
 
-    start_prometheus_server()
+    metadata = {'pod_id': 'test-pod-123', 'workflow_name': 'train_model'}
+
+    start_prometheus_server(mock_logger, metadata)
 
     # Verify HTTP server started
     mock_start_http_server.assert_called_once_with(9090)
@@ -124,11 +128,12 @@ def test_start_prometheus_server_success(mock_metrics, mock_start_http_server, m
     # Verify APP_UP metric was set to 1
     mock_metrics.APP_UP.labels.assert_called_once_with(pod_id='test-pod-123')
     mock_app_up.set.assert_called_once_with(1)
+    mock_logger.custom_info.assert_called_once()
 
 
 @patch('model_manager.worker.worker.start_http_server')
 @patch('model_manager.worker.worker.metrics')
-def test_start_prometheus_server_custom_port(mock_metrics, mock_start_http_server):
+def test_start_prometheus_server_custom_port(mock_metrics, mock_start_http_server, mock_logger):
     """Test Prometheus server startup with custom port."""
     from model_manager.worker.worker import start_prometheus_server
 
@@ -136,7 +141,9 @@ def test_start_prometheus_server_custom_port(mock_metrics, mock_start_http_serve
         mock_app_up = Mock()
         mock_metrics.APP_UP.labels.return_value = mock_app_up
 
-        start_prometheus_server()
+        metadata = {'pod_id': 'custom-pod', 'workflow_name': 'train_model'}
+
+        start_prometheus_server(mock_logger, metadata)
 
         mock_start_http_server.assert_called_once_with(8080)
 
@@ -145,17 +152,20 @@ def test_start_prometheus_server_custom_port(mock_metrics, mock_start_http_serve
 @patch('model_manager.worker.worker.metrics')
 @patch('model_manager.worker.worker.os._exit')
 def test_start_prometheus_server_failure(
-    mock_exit, mock_metrics, mock_start_http_server, mock_env_vars
+    mock_exit, mock_metrics, mock_start_http_server, mock_env_vars, mock_logger
 ):
     """Test Prometheus server startup failure."""
     from model_manager.worker.worker import start_prometheus_server
 
     mock_start_http_server.side_effect = OSError('Port already in use')
 
-    start_prometheus_server()
+    metadata = {'pod_id': 'test-pod-123', 'workflow_name': 'train_model'}
 
-    # Verify exit was called with code 1
+    start_prometheus_server(mock_logger, metadata)
+
+    # Verify exit was called with code 1 e log crítico emitido
     mock_exit.assert_called_once_with(1)
+    mock_logger.custom_critical.assert_called_once()
 
 
 @pytest.mark.asyncio
@@ -234,7 +244,7 @@ async def test_main_successful_startup(
     mock_notification_handler_class.assert_called_once()
     mock_activities_class.assert_called_once()
     mock_client_class.connect.assert_called_once()
-    # Agora sao criados dois Workers: um para train_model-queue e outro para cleanup-queue
+    # Agora são criados dois Workers: um para train_model-queue e outro para cleanup-queue
     assert mock_worker_class.call_count == 2
 
     # Verify cleanup was performed
@@ -523,7 +533,7 @@ def test_worker_module_docstring():
 @patch('model_manager.worker.worker.start_http_server')
 @patch('model_manager.worker.worker.metrics')
 def test_start_prometheus_server_prints_success(
-    mock_metrics, mock_start_http_server, capsys, mock_env_vars
+    mock_metrics, mock_start_http_server, capsys, mock_env_vars, mock_logger
 ):
     """Test that start_prometheus_server prints success message."""
     from model_manager.worker.worker import start_prometheus_server
@@ -531,25 +541,29 @@ def test_start_prometheus_server_prints_success(
     mock_app_up = Mock()
     mock_metrics.APP_UP.labels.return_value = mock_app_up
 
-    start_prometheus_server()
+    metadata = {'pod_id': 'test-pod-123', 'workflow_name': 'train_model'}
 
-    captured = capsys.readouterr()
-    assert 'Prometheus server started on port 9090' in captured.out
+    start_prometheus_server(mock_logger, metadata)
+
+    # Agora a mensagem é enviada via logger
+    mock_logger.custom_info.assert_called_once()
 
 
 @patch('model_manager.worker.worker.start_http_server')
 @patch('model_manager.worker.worker.metrics')
 @patch('model_manager.worker.worker.os._exit')
 def test_start_prometheus_server_prints_failure(
-    mock_exit, mock_metrics, mock_start_http_server, capsys, mock_env_vars
+    mock_exit, mock_metrics, mock_start_http_server, capsys, mock_env_vars, mock_logger
 ):
     """Test that start_prometheus_server prints failure message."""
     from model_manager.worker.worker import start_prometheus_server
 
     mock_start_http_server.side_effect = Exception('Test error')
 
-    start_prometheus_server()
+    metadata = {'pod_id': 'test-pod-123', 'workflow_name': 'train_model'}
 
-    captured = capsys.readouterr()
-    assert 'Failed to start Prometheus server' in captured.out
-    assert 'Test error' in captured.out
+    start_prometheus_server(mock_logger, metadata)
+
+    # Agora o erro é logado via logger crítico
+    mock_logger.custom_critical.assert_called_once()
+    mock_exit.assert_called_once_with(1)