SIENTIAPDE-1307: Implement metrics for training activities and workflow executions, tracking success/failure status.

model_manager/activities/training.py

@@ -18,6 +18,7 @@ with workflow.unsafe.imports_passed_through():
     from sientia_do.observability.metrics_controller import MetricsController
     from sientia_do.observability.sientia_monitoring import SientiaMonitoring
 
+    from model_manager.metrics import ACTIVITY_EXECUTION_TOTAL, WORKFLOW_EXECUTION_TOTAL
     from model_manager.utils.exceptions import ModelTrainingError
     from model_manager.utils.models.train_model_params import TrainModelParams
     from model_manager.utils.repository.model_repository import ModelRepository
@@ -76,6 +77,7 @@ class Training(SientiaMonitoring):
             ValueError, TypeError, KeyError: If validation fails (after sending notification)
         """
         metadata = input_data.get('metadata', {})
+        metrics_status = 'success'
 
         try:
             train_params = TrainModelParams.from_dict(input_data)
@@ -90,6 +92,7 @@ class Training(SientiaMonitoring):
 
             return train_params
         except (ValueError, TypeError, KeyError) as e:
+            metrics_status = 'error'
             error_msg = f'Error validating training parameters: {str(e)}'
             trace = traceback.format_exc()
 
@@ -102,6 +105,13 @@ class Training(SientiaMonitoring):
                 attachment_content=trace,
             )
             raise
+        finally:
+            await self._emit_metrics(
+                metadata=metadata,
+                metrics_status=metrics_status,
+                activity_name='validate_train_params',
+                emit_workflow_metric=(metrics_status == 'error'),
+            )
 
     @activity.defn(name='train_model')
     async def train_model(self, input_data: dict[str, Any]) -> dict[str, str | None]:
@@ -135,6 +145,7 @@ class Training(SientiaMonitoring):
 
         model_trained = False
         model_saved = False
+        metrics_status = 'success'
 
         try:
             with self.storage_repository.fetch_file(
@@ -155,6 +166,8 @@ class Training(SientiaMonitoring):
                     'run_dir': train_result.run_dir,
                 }
         except Exception as e:  # noqa: BLE001
+            metrics_status = 'error'
+
             error_msg = (
                 'Error training model - '
                 f'model_trained={model_trained}, model_saved={model_saved}, '
@@ -176,6 +189,13 @@ class Training(SientiaMonitoring):
                 model_trained=model_trained,
                 model_saved=model_saved,
             ) from e
+        finally:
+            await self._emit_metrics(
+                metadata=metadata,
+                metrics_status=metrics_status,
+                activity_name='train_model',
+                emit_workflow_metric=(metrics_status == 'error'),
+            )
 
     @activity.defn(name='cleanup_resources')
     async def cleanup_resources(self, input_data: dict[str, Any]) -> None:
@@ -196,11 +216,14 @@ class Training(SientiaMonitoring):
         run_dir = input_data.get('run_dir', '')
         bucket_name = input_data.get('bucket_name', '')
         file_name = input_data.get('file_name', '')
+        metrics_status = 'success'
 
         try:
             self.model_repository.cleanup_run_directory(run_dir)
             self.storage_repository.delete_file(bucket_name, file_name)
         except Exception as e:  # noqa: BLE001
+            metrics_status = 'error'
+
             error_msg = (
                 f'Error cleaning up resources - Run directory: {run_dir}, '
                 f'File: {bucket_name}/{file_name}, Error: {str(e)}'
@@ -216,4 +239,46 @@ class Training(SientiaMonitoring):
                 level=NotificationLevel.ERROR,
                 attachment_content=trace,
             )
+
             raise
+        finally:
+            await self._emit_metrics(
+                metadata=metadata,
+                metrics_status=metrics_status,
+                activity_name='cleanup_resources',
+                emit_workflow_metric=True,
+            )
+
+    async def _emit_metrics(
+        self,
+        metadata: dict[str, Any],
+        metrics_status: str,
+        activity_name: str,
+        emit_workflow_metric: bool,
+    ) -> None:
+        """
+        Emit workflow and activity execution metrics.
+
+        Args:
+            metadata: Activity metadata containing pod_id and workflow_name
+            metrics_status: Execution status ('success' or 'error')
+            activity_name: Name of the activity being executed
+        """
+        if emit_workflow_metric:
+            await self.emit_metric(
+                metric_object=WORKFLOW_EXECUTION_TOTAL,
+                tags={
+                    'pod_id': metadata.get('pod_id'),
+                    'workflow_name': metadata.get('workflow_name'),
+                    'status': metrics_status,
+                },
+            )
+
+        await self.emit_metric(
+            metric_object=ACTIVITY_EXECUTION_TOTAL,
+            tags={
+                'pod_id': metadata.get('pod_id'),
+                'activity_name': activity_name,
+                'status': metrics_status,
+            },
+        )

model_manager/metrics.py

@@ -16,7 +16,7 @@ Metric Labels:
 - pod_id: Kubernetes pod identifier for multi-instance deployments
 """
 
-from prometheus_client import Gauge
+from prometheus_client import Counter, Gauge
 
 # Application health metric
 APP_UP = Gauge(
@@ -24,3 +24,15 @@ APP_UP = Gauge(
     'Indicates if the application is running (1) or shutting down (0)',
     ['pod_id'],
 )
+
+WORKFLOW_EXECUTION_TOTAL = Counter(
+    'model_manager_workflow_executions_total',
+    'Total number of workflow executions',
+    ['pod_id', 'workflow_name', 'status'],  # status: success, error
+)
+
+ACTIVITY_EXECUTION_TOTAL = Counter(
+    'model_manager_activity_executions_total',
+    'Total number of activity executions',
+    ['pod_id', 'activity_name', 'status'],  # status: success, error
+)