SIENTIAPDE-1350: Implement file cleanup workflow and activities, including MinIO and local directory cleanup, configuration, and metrics.

model_manager/utils/repository/storage_repository.py

@@ -125,3 +125,36 @@ class StorageRepository:
         """
         self.minio_client.delete_object(Bucket=bucket_name, Key=file_name)
         self.logger.info(f'File deleted successfully: {bucket_name}/{file_name}')
+
+    def list_bucket_objects(self, bucket_name: str, max_keys: int = 1000) -> list[str]:
+        """
+        List objects in a MinIO bucket.
+
+        This method uses the MinIO/S3 list_objects_v2 API to retrieve objects
+        from the specified bucket. This is optimized for cleanup operations
+        by using configurable pagination.
+
+        Args:
+            bucket_name: Name of the bucket to list objects from.
+            max_keys: Maximum number of keys per page (default: 1000).
+
+        Returns:
+            List[str]: List of object keys (file names).
+        """
+        # Use list_objects_v2 for efficient pagination
+        paginator = self.minio_client.get_paginator('list_objects_v2')
+
+        pages = paginator.paginate(Bucket=bucket_name, MaxKeys=max_keys)
+
+        objects = []
+        total_count = 0
+
+        for page in pages:
+            if 'Contents' in page:
+                for obj in page['Contents']:
+                    objects.append(obj['Key'])
+                    total_count += 1
+
+        self.logger.info(f'Listed {total_count} objects from bucket {bucket_name}')
+
+        return objects