SIENTIAPDE-1717: Remove MinIO cleanup functionality and associated components. This change streamlines the cleanup workflow to focus solely on local temporary directories, removes the ModelTrainingError exception, and updates related configurations, documentation, and tests.

model_manager/workflows/cleanup_files.py

@@ -1,5 +1,5 @@
 """
-Cleanup workflow for removing stale files from MinIO and local filesystem.
+Cleanup workflow for removing local filesystem.
 
 This module provides a Temporal cron workflow that runs daily to clean up
 temporary files and directories older than the configured retention period.
@@ -13,11 +13,9 @@ with workflow.unsafe.imports_passed_through():
     from typing import Any
 
     from model_manager.activities.activities import Activities
-    from model_manager.workflows.train_model import POD_ID, network_retry_policy, no_retry_policy
+    from model_manager.workflows.train_model import POD_ID, no_retry_policy
 
-    TIMEOUT_CLEANUP_MINIO = int(os.getenv('TIMEOUT_CLEANUP_MINIO', '300'))
     TIMEOUT_CLEANUP_LOCAL = int(os.getenv('TIMEOUT_CLEANUP_LOCAL', '120'))
-    DEFAULT_CLEANUP_BUCKET = os.getenv('DEFAULT_CLEANUP_BUCKET', 'model-training')
 
 
 @workflow.defn(name='cleanup_files')
@@ -26,7 +24,6 @@ class CleanupFiles:
     Cleanup workflow for removing stale files.
 
     This workflow cleans up:
-    - MinIO files with timestamp prefixes
     - Local temporary directories with timestamp suffixes
 
     The workflow is designed to be simple and robust, with error handling
@@ -38,17 +35,10 @@ class CleanupFiles:
         """
         Execute the cleanup workflow.
 
-        This method orchestrates the cleanup of MinIO files and local directories
+        This method orchestrates the cleanup of local directories
         in sequence. No exception handling is needed as activities handle their
         own errors and notifications.
-
-        Args:
-            input_data: Workflow configuration containing optional:
-                - bucket_name (str): Bucket to clean (defaults to environment variable)
         """
-        # Get bucket name from input or environment
-        bucket_name = input_data.get('bucket_name', DEFAULT_CLEANUP_BUCKET)
-
         # Default temp path for local cleanup
         temp_path = 'model_manager/reports/temp'
 
@@ -60,17 +50,6 @@ class CleanupFiles:
             }
         }
 
-        # Execute MinIO cleanup
-        await workflow.execute_activity_method(
-            Activities.cleanup_minio_files,
-            {
-                **metadata,
-                'bucket_name': bucket_name,
-            },
-            retry_policy=network_retry_policy,
-            start_to_close_timeout=timedelta(seconds=TIMEOUT_CLEANUP_MINIO),
-        )
-
         # Execute local directory cleanup
         await workflow.execute_activity_method(
             Activities.cleanup_temp_directories,

model_manager/workflows/train_model.py

@@ -20,7 +20,6 @@ with workflow.unsafe.imports_passed_through():
 
     from model_manager.activities.activities import Activities
     from model_manager.activities.experiment_tracking import UpdateType
-    from model_manager.utils.exceptions import ModelTrainingError
     from model_manager.utils.models.experiment_status import ExperimentStatus
     from model_manager.utils.models.train_model_params import TrainModelParams
 
@@ -117,10 +116,7 @@ class TrainModel:
         )
 
         await self._cleanup_resources(
-            experiment_run_id=experiment_run_id,
             run_dir=(train_result.get('run_dir') or ''),
-            bucket_name=train_params.bucket_name,
-            file_name=train_params.file_name,
             metadata=metadata,
         )
 
@@ -246,27 +242,17 @@ class TrainModel:
                 metadata=metadata,
                 experiment_run_id=experiment_run_id,
                 update_type=UpdateType.MODEL_SAVED,
-                status=ExperimentStatus.TRACKING_SENT,
+                status=ExperimentStatus.TRAINING_SUCCESS,
                 run_name=train_result.get('run_name'),
             )
 
             return train_result
         except Exception as e:
-            # Mapear flags -> status
-            # False/False: erro no treino
-            # True/False: erro ao salvar (MLflow)
-            # False/True: estado inconsistente, tratar como erro de treino
-            # True/True: não deveria cair aqui; tratar como erro genérico de treino
-            status = ExperimentStatus.TRAINING_ERROR
-
-            if isinstance(e, ModelTrainingError) and (e.model_trained and not e.model_saved):
-                status = ExperimentStatus.TRACKING_SEND_ERROR
-
             await self._update_experiment_run(
                 metadata=metadata,
                 experiment_run_id=experiment_run_id,
                 update_type=UpdateType.STATUS_WITH_ERROR,
-                status=status,
+                status=ExperimentStatus.TRAINING_ERROR,
                 error_message=self._extract_error_message(e),
             )
 
@@ -274,56 +260,27 @@ class TrainModel:
 
     async def _cleanup_resources(
         self,
-        experiment_run_id: int,
         run_dir: str,
-        bucket_name: str,
-        file_name: str,
         metadata: dict[str, Any],
     ) -> None:
         """
-        Cleanup resources and delete file from MinIO.
+        Cleanup resources.
 
-        This method removes the temporary run directory via activity and deletes
-        the training file from MinIO. On success, updates DB status to FILE_DELETED.
-        On error, updates DB status to FILE_DELETE_ERROR.
+        This method removes the temporary run directory via activity.
 
         Args:
-            saved_result: TrainModelResult with run_dir and params information
-            experiment_run_id: Validated experiment run ID
+            run_dir: Temporary directory to remove
             metadata: Workflow execution metadata
-
-        Raises:
-            Exception: If cleanup fails (after updating DB status)
         """
-        try:
-            await workflow.execute_activity_method(
-                Activities.cleanup_resources,
-                {
-                    **metadata,
-                    'run_dir': run_dir,
-                    'bucket_name': bucket_name,
-                    'file_name': file_name,
-                },
-                retry_policy=network_retry_policy,
-                start_to_close_timeout=timedelta(seconds=TIMEOUT_DELETE_FILE),
-            )
-
-            await self._update_experiment_run(
-                metadata=metadata,
-                experiment_run_id=experiment_run_id,
-                update_type=UpdateType.STATUS,
-                status=ExperimentStatus.FILE_DELETED,
-            )
-        except Exception as e:
-            await self._update_experiment_run(
-                metadata=metadata,
-                experiment_run_id=experiment_run_id,
-                update_type=UpdateType.STATUS_WITH_ERROR,
-                status=ExperimentStatus.FILE_DELETE_ERROR,
-                error_message=self._extract_error_message(e),
-            )
-
-            raise
+        await workflow.execute_activity_method(
+            Activities.cleanup_resources,
+            {
+                **metadata,
+                'run_dir': run_dir,
+            },
+            retry_policy=network_retry_policy,
+            start_to_close_timeout=timedelta(seconds=TIMEOUT_DELETE_FILE),
+        )
 
     async def _update_experiment_run(
         self,