Merge pull request #16 from Aignosi/SIENTIAPDE-1199-revisar-e-testar-observabilidade

Sientiapde 1199 revisar e testar observabilidade

laborious/activities/activities.py

@@ -3,7 +3,7 @@ from temporalio import activity, workflow
 with workflow.unsafe.imports_passed_through():
     from sientia_do.temporal.activities.postgres import Postgres
     from sientia_do.notifications.handlers import CoreNotificationHandler as NotificationHandler
-    from sientia_do.temporal.utils.logger import Logger
+    from sientia_do.observability.logger import Logger
     from laborious.activities.mlflow import MLFlow
     from laborious.activities.gates import Gates
     from laborious.activities.opc import OPC

laborious/activities/gates.py

@@ -6,7 +6,7 @@ with workflow.unsafe.imports_passed_through():
     from sientia_do.notifications.handlers import CoreNotificationHandler as NotificationHandler
     from sientia_do.notifications.models import NotificationLevel
     from sientia_do.temporal.activities.base import BaseActivity
-    from sientia_do.temporal.utils.logger import Logger
+    from sientia_do.observability.logger import Logger
     from laborious.utils.filters.mlflow_filters import nan_values_filter, api_error_filter
     from typing import Any
     from laborious.utils.filters.conditional_filters import (
@@ -68,7 +68,7 @@ class Gates(BaseActivity):
         """
         metadata = input_data['metadata']
 
-        self.debug("Performing input gate...", metadata)
+        self.info("Performing input gate...", metadata)
 
         self.debug(f"Input data: {input_data}", metadata)
 
@@ -103,11 +103,11 @@ class Gates(BaseActivity):
 
         for path_flag in path_priority:
             if path_flag in filter_output:
-                self.debug(f"Input gate result: {path_flag}", metadata)
+                self.info(f"Input gate result: {path_flag}", metadata)
                 return path_flag, input_filter_functions['path_confidence'][path_flag], \
                     "Input data with bad quality"
 
-        self.debug("Nothing was filtered by the input gate", metadata)
+        self.info("Nothing was filtered by the input gate", metadata)
         return None, 0, ""
 
     @activity.defn(name="mlflow_response_gate")
@@ -128,7 +128,7 @@ class Gates(BaseActivity):
         """
 
         metadata = input_data['metadata']
-        self.debug("Performing mlflow response gate...", metadata)
+        self.info("Performing mlflow response gate...", metadata)
 
         filters = input_data['filters']
         data = input_data['data']
@@ -169,12 +169,12 @@ class Gates(BaseActivity):
 
         for path_flag in path_priority:
             if path_flag in filter_output:
-                self.debug(
+                self.info(
                     f"Mlflow response gate result: {path_flag}", metadata)
                 return path_flag, mlflow_response_filter_functions['path_confidence'][path_flag], \
                     ", ".join(comments)
 
-        self.debug("Nothing was filtered by the mlflow response gate", metadata)
+        self.info("Nothing was filtered by the mlflow response gate", metadata)
         return None, 0, ""
 
     @activity.defn(name="mlflow_content_gate")
@@ -195,7 +195,7 @@ class Gates(BaseActivity):
         """
 
         metadata = input_data['metadata']
-        self.debug("Performing mlflow content gate...", metadata)
+        self.info("Performing mlflow content gate...", metadata)
 
         filters = input_data['filters']
         data = DataFrame(input_data['data'])
@@ -234,12 +234,12 @@ class Gates(BaseActivity):
 
         for path_flag in path_priority:
             if path_flag in filter_output:
-                self.debug(
+                self.info(
                     f"Mlflow content gate result: {path_flag}", metadata)
                 return path_flag, mlflow_content_filter_functions['path_confidence'][path_flag], \
                     "Transformed data not passed the content filter"
 
-        self.debug("Nothing was filtered by the mlflow content gate", metadata)
+        self.info("Nothing was filtered by the mlflow content gate", metadata)
         return None, 0, ""
 
     @activity.defn(name="format_prediction")
@@ -256,7 +256,7 @@ class Gates(BaseActivity):
             dict: The formatted data.
         """
         metadata = input_data['metadata']
-        self.debug("Formatting prediction...", metadata)
+        self.info("Formatting prediction...", metadata)
 
         data = DataFrame(input_data['data'])
         data['timestamp'] = input_data['timestamp']
@@ -266,6 +266,8 @@ class Gates(BaseActivity):
         data['comments'] = ""
         data = data.sort_values(by='timestamp')
 
+        self.info(f"Prediction formatted: {data.size} rows", metadata)
+
         return data.to_dict()
 
     @activity.defn(name="format_default_prediction")
@@ -287,7 +289,7 @@ class Gates(BaseActivity):
         metadata = input_data['metadata']
         self.debug("Formatting default prediction...", metadata)
 
-        return DataFrame({
+        data = DataFrame({
             'prediction': [0],
             'response_time': [0],
             'timestamp': [input_data['timestamp']],
@@ -295,7 +297,10 @@ class Gates(BaseActivity):
             'prediction_confidence': [input_data['prediction_confidence']],
             'prediction_status': ['Bad'],
             'comments': [input_data['comment']]
-        }).to_dict()
+        })
+
+        self.info(f"Default prediction formatted: {data.size} rows", metadata)
+        return data.to_dict()
 
     @activity.defn(name="get_last_timestamp")
     async def get_last_timestamp(self, input_data: dict[str, Any]) -> str:
@@ -307,9 +312,18 @@ class Gates(BaseActivity):
         Returns:
             str: The last timestamp of the data.
         """
+        metadata = input_data['metadata']
+
+        self.info("Getting last timestamp...", metadata)
+
         data = DataFrame(input_data['data'])
+
         if data.empty:
             return datetime.now().strftime('%Y-%m-%d %H:%M:%S')
+
+        self.info(
+            f"Last timestamp: {max(data['timestamp'].values.tolist())}", metadata)
+
         return max(data['timestamp'].values.tolist())
 
     @activity.defn(name="write_metrics")
@@ -325,6 +339,9 @@ class Gates(BaseActivity):
         prediction_confidence = prediction['prediction_confidence'].values[0]
         response_time = prediction['response_time'].values[0]
 
+        self.info(
+            f"Writing metrics for model {metadata['model_name']}", metadata)
+
         metrics.PREDICTIONS_WRITTEN_COUNT.labels(
             pod_id=self.pod_id,
             model_name=metadata['model_name'],
@@ -342,3 +359,6 @@ class Gates(BaseActivity):
             model_name=metadata['model_name'],
             pipeline_name=metadata['workflow_name']
         ).observe(response_time)
+
+        self.info(
+            f"Metrics written for model {metadata['model_name']}", metadata)

laborious/activities/mlflow.py

@@ -1,3 +1,4 @@
+import json
 from temporalio import activity, workflow
 
 
@@ -5,7 +6,7 @@ with workflow.unsafe.imports_passed_through():
     from sientia_do.temporal.activities.base import BaseActivity
     from sientia_do.notifications.handlers import CoreNotificationHandler as NotificationHandler
     from sientia_do.notifications.models import NotificationLevel
-    from sientia_do.temporal.utils.logger import Logger
+    from sientia_do.observability.logger import Logger
     from laborious.utils.repository.model_repository import MLFlowRepository
     from typing import Any
     import numpy as np
@@ -40,7 +41,7 @@ class MLFlow(BaseActivity):
             dict[str, Any]: The transformed data.
         """
         metadata = input_data['metadata']
-        self.debug('Transforming data...', metadata)
+        self.info('Transforming data...', metadata)
         data = DataFrame(input_data['data'])
         model_name = input_data['model_name']
         model_retention = input_data['model_retention']
@@ -66,8 +67,10 @@ class MLFlow(BaseActivity):
         response_data = self.model_monitoring_repository.transform(
             model_name, data, model_retention)
 
-        self.debug("Response data:", metadata)
+        self.debug("Transform response data:", metadata)
-        self.debug(response_data, metadata)
+        self.debug(json.dumps(response_data, indent=4), metadata)
+
+        self.info("Data transformed successfully", metadata)
 
         return response_data
 
@@ -84,7 +87,7 @@ class MLFlow(BaseActivity):
             dict[str, Any]: The predicted data.
         """
         metadata = input_data['metadata']
-        self.debug('Predicting data...', metadata)
+        self.info('Predicting data...', metadata)
         data = DataFrame(input_data['data'])
         model_name = input_data['model_name']
         model_retention = input_data['model_retention']
@@ -97,7 +100,9 @@ class MLFlow(BaseActivity):
             model_name, data, model_retention)
 
         self.debug("Prediction response data:", metadata)
-        self.debug(response_data, metadata)
+        self.debug(json.dumps(response_data, indent=4), metadata)
+
+        self.info("Prediction completed successfully", metadata)
 
         return response_data
 

laborious/activities/opc.py

@@ -5,7 +5,7 @@ with workflow.unsafe.imports_passed_through():
     from sientia_do.notifications.handlers import CoreNotificationHandler as NotificationHandler
     from sientia_do.notifications.models import NotificationLevel
     from sientia_do.temporal.activities.base import BaseActivity
-    from sientia_do.temporal.utils.logger import Logger
+    from sientia_do.observability.logger import Logger
     from laborious.utils.repository.opc_repository import OpcRepository
     from typing import Any
     import traceback
@@ -115,7 +115,9 @@ class OPC(BaseActivity):
 
     def manage_output_tags(
             self, server_id: str, config: dict[str, Any], data: DataFrame,
-            metadata: dict[str, Any], success: bool) -> bool:
+            metadata: dict[str, Any], success: bool) -> tuple[bool, int]:
+
+        count = 0
         if 'prediction_tags' in config:
             for tag, tag_config in config['prediction_tags'].items():
                 local_success = self.write_data(
@@ -129,6 +131,7 @@ class OPC(BaseActivity):
                 if local_success:
                     self.info(
                         f"Prediction data written to OPC server {server_id} for tag {tag}.", metadata)
+                    count += 1
                 success = success and local_success
 
         if 'confidence_tags' in config:
@@ -144,9 +147,10 @@ class OPC(BaseActivity):
                 if local_success:
                     self.info(
                         f"Confidence data written to OPC server {server_id} for tag {tag}.", metadata)
+                    count += 1
                 success = success and local_success
 
-        return success
+        return success, count
 
     @activity.defn(name='write_opc_data')
     async def write_opc_data(self, input_data: dict[str, Any]) -> dict[Any, Any]:
@@ -168,10 +172,10 @@ class OPC(BaseActivity):
 
         """
         metadata = input_data['metadata']
-        self.debug("Writing data to OPC servers...", metadata)
+        self.info("Writing data to OPC servers...", metadata)
         data = DataFrame(input_data['data'])
         opc_output_config = input_data['opc_output_config']
-        self.debug(data, metadata)
+        self.info(f"Data to write: {data.size} rows", metadata)
 
         success = True
 
@@ -181,8 +185,12 @@ class OPC(BaseActivity):
                 success = False
                 continue
 
-            success = success and self.manage_output_tags(
+            local_success, local_count = self.manage_output_tags(
                 server_id, config, data, metadata, success)
+            success = success and local_success
+
+            self.info(
+                f"Data written to OPC server {server_id}: {local_count} of {len(config['prediction_tags'])} prediction tags and {len(config['confidence_tags'])} confidence tags", metadata)
 
         return self.process_confidence(data, success, metadata)
 

laborious/utils/repository/opc_repository.py

@@ -9,7 +9,7 @@ from asyncua.ua import DataValue, Variant, VariantType, DateTime
 from regex import F
 from sientia_do.notifications.handlers import CoreNotificationHandler as NotificationHandler
 from sientia_do.notifications.models import NotificationLevel
-from sientia_do.temporal.utils.logger import Logger
+from sientia_do.observability.logger import Logger
 from laborious import metrics
 
 data_type_map = {
@@ -55,6 +55,13 @@ class OpcRepository():
         self.client = None
         self.pod_id = pod_id
 
+        self.metadata = {
+            'model_name': '-',
+            'model_id': '-',
+            'workflow_name': 'opc_repository',
+            'schedule_name': '-'
+        }
+
     def set_security(self):
         """
         Configures the security settings for the OPC UA client.
@@ -84,7 +91,7 @@ class OpcRepository():
             self.server_cert_path) if self.server_cert_path else None
 
         self.client.application_uri = self.server_uri
-        self.logger.info('Setting security...')
+        self.logger.custom_info('Setting security...', self.metadata)
         self.client.set_security(
             SecurityPolicyBasic256,
             certificate=str(cert),
@@ -107,7 +114,8 @@ class OpcRepository():
         self.client = Client(self.url)
         if self.cert_path:
             self.set_security()
-        self.logger.info(f'Starting connection to OPC server {self.id}...')
+        self.logger.custom_info(
+            f'Starting connection to OPC server {self.id}...', self.metadata)
         return self.try_connect()
 
     def try_connect(self) -> tuple[bool, dict[str, Any]]:
@@ -124,7 +132,7 @@ class OpcRepository():
             return True, {}
         except Exception as e:
             trace = traceback.format_exc()
-            self.logger.error(trace)
+            self.logger.custom_error(trace, self.metadata)
 
             return False, {
                 "notification_id": f"OPC_CONNECTION_ERROR_{self.id}",
@@ -142,9 +150,11 @@ class OpcRepository():
             return
         try:
             self.client.disconnect()
-            self.logger.info('Disconnected from OPC server')
+            self.logger.custom_info(
+                'Disconnected from OPC server', self.metadata)
         except Exception as e:
-            self.logger.error(f"Failed to disconnect from OPC server: {e}")
+            self.logger.custom_error(
+                f"Failed to disconnect from OPC server: {e}", self.metadata)
         self.client = None
 
     def __del__(self):
@@ -154,7 +164,8 @@ class OpcRepository():
         try:
             self.disconnect()
         except Exception as e:
-            self.logger.error(f"Error in destructor: {e}")
+            self.logger.custom_error(
+                f"Error in destructor: {e}", self.metadata)
 
     def validate_connection(self) -> tuple[bool, dict[str, Any]]:
         """
@@ -171,32 +182,39 @@ class OpcRepository():
             return self.connect()
 
         if self.error_count > 5:
-            self.logger.warning(
+            self.logger.custom_warning(
-                f"OPC server {self.id} will be disconnected due to multiple errors")
+                f"OPC server {self.id} will be disconnected due to multiple errors", self.metadata)
             try:
                 self.disconnect()
             except Exception as e:
                 trace = traceback.format_exc()
-                self.logger.error(f"Failed to disconnect from OPC server: {e}")
+                self.logger.custom_error(
-                self.logger.error(trace)
+                    f"Failed to disconnect from OPC server: {e}", self.metadata)
-            self.logger.info(
+                self.logger.custom_error(trace, self.metadata)
-                f"Attempting to reconnect to OPC server {self.id}...")
+            self.logger.custom_info(
+                f"Attempting to reconnect to OPC server {self.id}...", self.metadata)
             return self.connect()
 
         if hasattr(self.client, 'aio_obj') and self.client.aio_obj.uaclient.protocol is None or \
                 (hasattr(self.client.aio_obj.uaclient, 'protocol') and
                  self.client.aio_obj.uaclient.protocol.state == "closed"):
 
-            self.logger.error(
+            self.logger.custom_error(
-                f"OPC server {self.id} is not connected")
+                f"OPC server {self.id} is not connected", self.metadata)
+
             if self.last_reconnection_time is None or (datetime.now() - self.last_reconnection_time).total_seconds(
             ) > self.reconnection_interval:
                 self.disconnect()
-                self.logger.error(
+                self.logger.custom_info(
-                    f"Trying to reconnect to OPC server {self.id}...")
+                    f"Trying to reconnect to OPC server {self.id}...", self.metadata)
                 return self.connect()
 
-            return False, {}
+            return False, {
+                "notification_id": f"OPC_CONNECTION_AWAITING_RECONNECTION_WINDOW_{self.id}",
+                "message": f"OPC server {self.id} is not connected, waiting for next reconnection window...",
+                "block": "opc_repository",
+                "level": NotificationLevel.WARNING
+            }
 
         return True, {}
 
@@ -244,7 +262,7 @@ class OpcRepository():
 
         data = data_type_map[data_type]['converter'](value)
         logger.custom_info(
-            f'Writing {data} - {type(data)} to {node}', metadata.get('schedule_name', 'N/A'))
+            f'Writing {data} - {type(data)} to {node}', metadata)
         now = datetime.now()
         ua_data = DataValue(
             Variant(data, data_type_map[data_type]['opc_type']),
@@ -280,7 +298,7 @@ class OpcRepository():
 
         except Exception as e:
             trace = traceback.format_exc()
-            logger.custom_error(trace, metadata.get('schedule_name', 'N/A'))
+            logger.custom_error(trace, metadata)
             self.error_count += 1
             return False, {
                 "notification_id": f"OPC_WRITE_DATA_ERROR_{self.id}",

laborious/worker/worker.py

@@ -1,5 +1,5 @@
 from temporalio import workflow, client
-from temporalio.worker import Worker
+from temporalio.worker import Worker, PollerBehaviorAutoscaling
 from temporalio.runtime import Runtime, TelemetryConfig, PrometheusConfig
 
 with workflow.unsafe.imports_passed_through():
@@ -19,7 +19,7 @@ with workflow.unsafe.imports_passed_through():
         build_mongodb_config
     )
     from sientia_do.notifications.handlers import CoreNotificationHandler as NotificationHandler
-    from sientia_do.temporal.utils.logger import get_logger
+    from sientia_do.observability.logger import get_logger
     from laborious import metrics
     from prometheus_client import start_http_server
 
@@ -31,12 +31,20 @@ async def main():
     host = os.getenv('TEMPORAL_HOST', 'localhost:7233')
     logger = get_logger(__name__)
 
-    logger.info(f'Starting Worker with POD_ID: {POD_ID}')
+    metadata = {
+        'pod_id': POD_ID,
+        'model_name': '-',
+        'model_id': '-',
+        'workflow_name': '-',
+        'schedule_name': '-',
+    }
 
-    logger.info("Starting prometheus client...")
+    logger.custom_info(f'Starting Worker with POD_ID: {POD_ID}', metadata)
+
+    logger.custom_info("Starting prometheus client...", metadata)
     start_prometheus_server()
 
-    logger.info('Starting Notification Handler...')
+    logger.custom_info('Starting Notification Handler...', metadata)
 
     mongo_config = build_mongodb_config()
     notification_handler = NotificationHandler(
@@ -46,7 +54,7 @@ async def main():
         project_name=os.getenv('PROJECT_NAME', 'laborious')
     )
 
-    logger.info('Starting Activities...')
+    logger.custom_info('Starting Activities...', metadata)
 
     activities = Activities(
         postgres_config=build_postgres_config(),
@@ -56,7 +64,8 @@ async def main():
         notification_handler=notification_handler
     )
 
-    logger.info(f'Starting SDK Metrics Server on port {SDK_METRICS_PORT}...')
+    logger.custom_info(
+        f'Starting SDK Metrics Server on port {SDK_METRICS_PORT}...', metadata)
 
     new_runtime = Runtime(
         telemetry=TelemetryConfig(
@@ -65,7 +74,7 @@ async def main():
         )
     )
 
-    logger.info('Starting Temporal Client...')
+    logger.custom_info('Starting Temporal Client...', metadata)
 
     temporal_client = await client.Client.connect(
         target_host=host,
@@ -73,7 +82,7 @@ async def main():
         runtime=new_runtime
     )
 
-    logger.info('Starting Workers...')
+    logger.custom_info('Starting Workers...', metadata)
 
     workers = [
         Worker(
@@ -86,11 +95,12 @@ async def main():
                 activities.update_production_model,
                 activities.export_data_to_postgres
             ],
-            max_concurrent_workflow_tasks=100,
+            max_concurrent_workflow_tasks=50,
-            max_concurrent_activities=100,
+            max_concurrent_activities=50,
-            max_concurrent_local_activities=100,
+            max_concurrent_local_activities=50,
-            max_concurrent_workflow_task_polls=100,
+            max_cached_workflows=200,
-            max_cached_workflows=50,
+            workflow_task_poller_behavior=PollerBehaviorAutoscaling(),
+            activity_task_poller_behavior=PollerBehaviorAutoscaling()
         ),
         Worker(
             temporal_client,
@@ -116,11 +126,12 @@ async def main():
                 activities.export_data_to_postgres,
                 activities.write_metrics
             ],
-            max_concurrent_workflow_tasks=100,
+            max_concurrent_workflow_tasks=50,
-            max_concurrent_activities=100,
+            max_concurrent_activities=50,
-            max_concurrent_local_activities=100,
+            max_concurrent_local_activities=50,
-            max_concurrent_workflow_task_polls=100,
+            max_cached_workflows=200,
-            max_cached_workflows=50,
+            workflow_task_poller_behavior=PollerBehaviorAutoscaling(),
+            activity_task_poller_behavior=PollerBehaviorAutoscaling()
         )
     ]
 
@@ -128,14 +139,14 @@ async def main():
     for w in workers:
         handlers.append(w.run())
 
-    logger.info('Workers started successfully')
+    logger.custom_info('Workers started successfully', metadata)
 
     try:
         # This will run the workers and wait for them to complete.
         # If an exception occurs in any of the worker handlers, it will be propagated here.
         await asyncio.gather(*handlers)
     except BaseException as e:  # NOSONAR
-        logger.error(f"An unhandled exception occurred: {e}")
+        logger.custom_error(f"An unhandled exception occurred: {e}", metadata)
     finally:
         if notification_handler:
             notification_handler.shutdown()

laborious/workflows/minimal_retrain.py

@@ -3,7 +3,7 @@ from temporalio import workflow
 with workflow.unsafe.imports_passed_through():
     from laborious.activities.activities import Activities
     from typing import Any
-    from sientia_do.temporal.utils.policies import retry_policy
+    from sientia_do.temporal.policies import retry_policy
     from datetime import timedelta
 
 

laborious/workflows/predictions_batch.py

@@ -3,7 +3,7 @@ from temporalio import workflow
 with workflow.unsafe.imports_passed_through():
     from laborious.activities.activities import Activities
     from typing import Any
-    from sientia_do.temporal.utils.policies import retry_policy
+    from sientia_do.temporal.policies import retry_policy
     from datetime import timedelta
 
 

laborious/workflows/sub_workflows/format_and_export_prediction.py

@@ -4,7 +4,7 @@ with workflow.unsafe.imports_passed_through():
     from laborious.activities.activities import Activities
     from typing import Any
     from datetime import timedelta
-    from sientia_do.temporal.utils.policies import retry_policy
+    from sientia_do.temporal.policies import retry_policy
 
 
 @workflow.defn(name="format_and_export_prediction")

laborious/workflows/sub_workflows/prediction_process.py

@@ -3,7 +3,7 @@ from temporalio import workflow
 with workflow.unsafe.imports_passed_through():
     from laborious.activities.activities import Activities
     from typing import Any
-    from sientia_do.temporal.utils.policies import retry_policy
+    from sientia_do.temporal.policies import retry_policy
     from datetime import timedelta
 
 

requirements.txt

@@ -3,6 +3,6 @@ psycopg2-binary
 sqlalchemy
 asyncua
 redis
-git+ssh://git@github.com/Aignosi/sientia-dataops-library.git@1.3.8
+git+ssh://git@github.com/Aignosi/sientia-dataops-library.git@1.4.1
 git+ssh://git@github.com/Aignosi/sientia-mlops-library.git@0.38.5
 prometheus-client

tests/laborious/activities/test_gates.py

@@ -344,7 +344,6 @@ async def test_format_prediction(gates_activity):
     assert result['prediction_confidence'] == {0: 0.9}
     assert result['prediction_status'] == {0: 'Good'}
     assert result['comments'] == {0: ""}
-    gates_activity.debug.assert_called()
 
 
 @mark.asyncio
@@ -393,7 +392,8 @@ async def test_get_last_timestamp_with_data(gates_activity):
 async def test_get_last_timestamp_no_data(gates_activity):
     # Arrange
     input_data = {
-        'data': {}
+        'data': {},
+        **metadata
     }
 
     # Act

tests/laborious/utils/repository/test_opc_repository.py

@@ -139,8 +139,9 @@ def test_disconnect_error(opc_repository, mock_client):
     mock_client.disconnect.side_effect = Exception("Test error")
     opc_repository.disconnect()
 
-    opc_repository.logger.error.assert_called_once_with(
+    opc_repository.logger.custom_error.assert_called_once_with(
-        "Failed to disconnect from OPC server: Test error"
+        "Failed to disconnect from OPC server: Test error",
+        ANY
     )
     assert opc_repository.client is None
 
@@ -163,9 +164,9 @@ def test_validate_connection_error_count_disconnect_error(opc_repository):
     assert response == opc_repository.connect.return_value
     opc_repository.disconnect.assert_called_once()
     opc_repository.connect.assert_called_once()
-    opc_repository.logger.error.assert_has_calls(
+    opc_repository.logger.custom_error.assert_has_calls(
         [
-            call("Failed to disconnect from OPC server: Test error"),
+            call("Failed to disconnect from OPC server: Test error", ANY),
         ]
     )
 
@@ -182,7 +183,12 @@ def test_validate_connection_lost_not_time_to_reconect(_mock_datetime, opc_repos
 
     response = opc_repository.validate_connection()
     opc_repository.try_connect.assert_not_called()
-    assert response == (False, {})
+    assert response == (False, {
+        "notification_id": f"OPC_CONNECTION_AWAITING_RECONNECTION_WINDOW_{opc_repository.id}",
+        "message": f"OPC server {opc_repository.id} is not connected, waiting for next reconnection window...",
+        "block": "opc_repository",
+        "level": NotificationLevel.WARNING
+    })
 
 
 @patch('laborious.utils.repository.opc_repository.hasattr', return_value=True)

values.yaml

@@ -3,7 +3,7 @@
 # Declare variables to be passed into your templates.
 
 # This will set the replicaset count more information can be found here: https://kubernetes.io/docs/concepts/workloads/controllers/replicaset/
-replicaCount: 3
+replicaCount: 5
 
 # This sets the container image more information can be found here: https://kubernetes.io/docs/concepts/containers/images/
 image:
@@ -11,7 +11,7 @@ image:
   # This sets the pull policy for images.
   pullPolicy: Always
   # Overrides the image tag whose default is the chart appVersion.
-  tag: "0.3.2"
+  tag: "0.4.2"
 
 # This is for the secrets for pulling an image from a private repository more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
 imagePullSecrets:
@@ -151,7 +151,7 @@ env:
   - name: GITHUB_REPO_URL
     value: "git@github.com:Aignosi/sientia-dataops-laborious_temporal.git"
   - name: GITHUB_BRANCH
-    value: "SIENTIAPDE-1169-pensar-e-projetar-testes-de-breakdown-e-performance"
+    value: "SIENTIAPDE-1199-revisar-e-testar-observabilidade"
   - name: PYTHON_APP
     value: "laborious.worker.worker"