feat: enhance configuration and scheduling for cleanup processes

- Updated `.env.example` to include new environment variables for MinIO and PyPI configuration.
- Refactored `create_cleanup_schedule` to utilize runtime-specific task queues and improve schedule reconciliation logic.
- Enhanced `Activities` class to require a default bucket in MinIO configuration.
- Adjusted `requirements.txt` to specify version for `evidently`.
- Updated tests to reflect changes in schedule creation and configuration handling.

model_manager/worker/worker.py

@@ -5,8 +5,8 @@ It orchestrates Temporal workers, manages task queues, and handles the lifecycle
 model training and cleanup workflows.
 
 The worker supports two task queues:
-- train_model-queue: For ML model training workflows
-- cleanup-queue: For file cleanup workflows
+- train_model-<runtime>-queue: For ML model training workflows
+- cleanup_files-<runtime>-queue: For file cleanup workflows
 
 Key Features:
 - Automatic scaling with PollerBehaviorAutoscaling
@@ -20,8 +20,7 @@ Environment Variables:
 - TEMPORAL_HOST: Temporal server address (default: localhost:7233)
 - TEMPORAL_NAMESPACE: Temporal namespace (default: model-manager)
 - TEMPORAL_USE_TLS: Enable TLS for Temporal connection (default: false)
-- TRAIN_TASK_QUEUE: Task queue for training workflows (default: train_model-queue)
-- CLEANUP_TASK_QUEUE: Task queue for cleanup workflows (default: cleanup-queue)
+- RUNTIME: Runtime identifier used in queue naming (default: single)
 - POD_ID: Kubernetes pod identifier for metrics
 - HTTP_METRICS_PORT: Prometheus metrics server port (default: 9090)
 - HTTP_SDK_METRICS_PORT: Temporal SDK metrics port (default: 9091)
@@ -60,8 +59,20 @@ with workflow.unsafe.imports_passed_through():
 POD_ID = os.getenv('POD_ID')
 RUNTIME = os.getenv('RUNTIME')
 SDK_METRICS_PORT = int(os.getenv('HTTP_SDK_METRICS_PORT', '9091'))
-TRAIN_TASK_QUEUE = os.getenv('TRAIN_TASK_QUEUE', 'train_model-queue')
-CLEANUP_TASK_QUEUE = os.getenv('CLEANUP_TASK_QUEUE', 'cleanup-queue')
+
+
+def _get_runtime(runtime: str | None) -> str:
+    """
+    Resolve runtime using fallback when missing.
+
+    Args:
+     - runtime: str | None, runtime value from environment
+
+    Return:
+     str: normalized runtime value
+    """
+    normalized_runtime = runtime.strip() if runtime else ''
+    return normalized_runtime or 'single'
 
 
 async def main():
@@ -84,8 +95,7 @@ async def main():
         SystemExit: On graceful shutdown or error conditions
     """
 
-    if not RUNTIME:
-        raise ValueError('RUNTIME environment variable is required')
+    runtime = _get_runtime(RUNTIME)
 
     host = os.getenv('TEMPORAL_HOST', 'localhost:7233')
     use_tls = os.getenv('TEMPORAL_USE_TLS', 'false').lower() == 'true'
@@ -93,7 +103,7 @@ async def main():
 
     metadata = {
         'pod_id': POD_ID,
-        'runtime': RUNTIME,
+        'runtime': runtime,
     }
 
     start_prometheus_server(logger, metadata)
@@ -112,7 +122,7 @@ async def main():
 
     metrics_controller = MetricsController(logger=logger)
 
-    logger.custom_info(f'Installing runtime {RUNTIME}', metadata)
+    logger.custom_info(f'Installing runtime {runtime}', metadata)
 
     plugin_store_parameters = build_plugin_store_config()
     plugin_store = PluginStore(
@@ -131,7 +141,7 @@ async def main():
         metrics_controller=metrics_controller,
     )
 
-    await plugin_store.install_runtime(runtime_name=RUNTIME)
+    await plugin_store.install_runtime(runtime_name=runtime)
 
     activities = Activities(
         postgres_config=build_postgres_config(),
@@ -181,7 +191,7 @@ async def main():
             ],
             temporal_client=temporal_client,
             logger=logger,
-            runtime=RUNTIME,
+            runtime=runtime,
         ),
         prepare_worker(
             main_workflow=CleanupFiles,
@@ -191,7 +201,7 @@ async def main():
             ],
             temporal_client=temporal_client,
             logger=logger,
-            runtime=RUNTIME,
+            runtime=runtime,
         ),
     ]