SIENTIAPDE-2072: bump sientia_do pin to 1.12.2

Picks up the notification timestamp -> native datetime fix.

.github/workflows/quality-gate.yml

@@ -1,15 +1,29 @@
 name: Quality gate
 
 on:
+  push:
+    branches:
+      - main
+      - 'release/**'
+      - 'feature/**'
   pull_request:
     branches:
       - main
+      - 'release/**'
+      - 'feature/**'
     types: [ opened, synchronize, reopened ]
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
 jobs:
   quality-gate:
-    uses: Aignosi/github_workflow_templates/.github/workflows/dataops-module-quality-gate.yml@main
-    permissions: write-all
+    uses: Aignosi/github_workflow_templates/.github/workflows/python-quality-gate.yml@main
+    permissions:
+      contents: read
+      pull-requests: write
+      issues: write
     with:
       project_name: 'laborious'
       repositories: 'sientia-dataops-library, sientia-mlops-library'

README.md

@@ -126,10 +126,15 @@ Laborious uses a Temporal-based architecture with strong separation of concerns
 ### Key Components
 
 #### **Worker (`laborious/worker/worker.py`)**
-- Temporal client setup, worker lifecycle, task queues
+- Temporal client setup, four workers via `sientia_do.temporal.worker.prepare_worker`
+- Runtime-scoped task queues: `{workflow}-{RUNTIME}-queue` for all workflows
 - Metrics server initialization, notification handler setup
 - Graceful shutdown and autoscaling-friendly behavior
 
+**Breaking (schedulers):** drift and simple_metrics queues are no longer `drift-queue` /
+`simple_metrics-queue`. Use `drift-{RUNTIME}-queue` and `simple_metrics-{RUNTIME}-queue`
+matching the worker pod `RUNTIME` env (same as `predictions_batch` / `minimal_retrain`).
+
 #### **Workflows (`laborious/workflows/`)**
 - `predictions_batch.py`: Batch prediction entry point
 - `sub_workflows/prediction_process.py`: Core prediction pipeline
@@ -802,6 +807,7 @@ See [OPC UA Communication](#opc-ua-communication) for semantics, concurrency, an
 |----------|-------------|---------|----------|
 | `TEMPORAL_HOST` | Temporal server address | `localhost:7233` | Yes |
 | `TEMPORAL_NAMESPACE` | Temporal namespace | `laborious` | No |
+| `RUNTIME` | Task queue suffix for all workflows (`{workflow}-{RUNTIME}-queue`) | _(none)_ | Yes |
 | `POSTGRES_HOST` | PostgreSQL hostname | `localhost` | Yes |
 | `POSTGRES_PORT` | PostgreSQL port | `5432` | Yes |
 | `POSTGRES_USER` | PostgreSQL username | `sientia` | Yes |
@@ -1097,8 +1103,7 @@ laborious/
 │       ├── prediction_process.py # Core prediction workflow
 │       └── format_and_export_prediction.py # Export workflow
 ├── worker/                  # Worker implementation
-│   ├── worker.py           # Main worker orchestrator
-│   └── prepare_worker.py   # Worker factory with autoscaling config
+│   └── worker.py           # Main worker orchestrator (uses sientia_do prepare_worker)
 ├── utils/                   # Utility functions
 │   ├── connectors_config.py # Environment-driven config builders
 │   ├── models/             # Data models
@@ -1179,7 +1184,9 @@ export LOG_LEVEL=DEBUG
 ### Scaling Considerations
 
 - **Horizontal Scaling**: Deploy multiple worker instances
-- **Task Queue Distribution**: Use multiple task queues for different workflow types
+- **Task Queue Distribution**: One worker pod per `RUNTIME`; queues are
+  `predictions_batch-{RUNTIME}-queue`, `minimal_retrain-{RUNTIME}-queue`,
+  `drift-{RUNTIME}-queue`, `simple_metrics-{RUNTIME}-queue`
 - **Database Performance**: Optimize indexes and connection pooling
 - **MLFlow Performance**: Configure appropriate model serving resources
 

laborious/activities/activities.py

@@ -164,6 +164,6 @@ class Activities(Storage, MLFlow, Gates, OPC, ModelMetrics, API):
         Storage.close(self)
         MLFlow.close(self)
         Gates.close(self)
-        await OPC.close(self)
+        await OPC.aclose(self)
         ModelMetrics.close(self)
         API.close(self)

laborious/activities/opc.py

@@ -491,7 +491,7 @@ class OPC(SientiaMonitoring):
 
         return data.to_dict()
 
-    async def close(self):
+    async def aclose(self):
         """
         Gracefully shutdown all OPC server connections and cleanup resources.
 

laborious/activities/storage.py

@@ -202,7 +202,8 @@ class Storage(Postgres, MinioManager):
 
     def close(self) -> None:
         """Close Storage resources (MinIO client and Postgres engine)."""
-        Postgres.close(self)
+        if hasattr(self, 'engine'):
+            Postgres.close(self)
         MinioManager.close(self)
 
     def __del__(self):

laborious/utils/repository/model_repository.py

@@ -170,8 +170,19 @@ class MLFlowRepository(SientiaMonitoring):
 
         # Sort by version number to get the latest
         latest_version = max(stage_versions, key=lambda v: int(v.version))
-        run_id = latest_version.source.split('/')
-        return run_id[2]
+        source = latest_version.source
+        if source is None:
+            raise mlflow.exceptions.MlflowException(
+                f"Model '{model_name}' version '{latest_version.version}' in stage '{stage}' "
+                'has no source URI to resolve run ID.'
+            )
+        parts = source.split('/')
+        if len(parts) <= 2 or not parts[2]:
+            raise mlflow.exceptions.MlflowException(
+                f"Model '{model_name}' version '{latest_version.version}' in stage '{stage}' "
+                f"has invalid source URI '{source}' for run ID resolution."
+            )
+        return parts[2]
 
     def get_next_run_name(self, model_name: str) -> str:
         """

laborious/worker/prepare_worker.py

@@ -1,73 +0,0 @@
-import os
-import re
-from collections.abc import Sequence
-from typing import Any
-
-from sientia_do.observability.logger import Logger
-from temporalio.client import Client
-from temporalio.worker import PollerBehaviorAutoscaling, Worker
-
-parameters = [
-    ('MAX_CONCURRENT_WORKFLOW_TASKS', '200'),
-    ('MAX_CONCURRENT_ACTIVITIES', '200'),
-    ('MAX_CONCURRENT_LOCAL_ACTIVITIES', '200'),
-    ('MAX_CACHED_WORKFLOWS', '200'),
-    ('WORKFLOW_POLLER_BEHAVIOUR_MINIMUM', '10'),
-    ('WORKFLOW_POLLER_BEHAVIOUR_INITIAL', '100'),
-    ('WORKFLOW_POLLER_BEHAVIOUR_MAXIMUM', '200'),
-    ('ACTIVITY_POLLER_BEHAVIOUR_MINIMUM', '10'),
-    ('ACTIVITY_POLLER_BEHAVIOUR_INITIAL', '100'),
-    ('ACTIVITY_POLLER_BEHAVIOUR_MAXIMUM', '200'),
-]
-
-
-def camel_to_snake(text: str) -> str:
-    """Convert camelCase or PascalCase to snake_case."""
-    text = re.sub('(.)([A-Z][a-z]+)', r'\1_\2', text)
-    text = re.sub('([a-z0-9])([A-Z])', r'\1_\2', text)
-    return text.lower()
-
-
-def prepare_worker(
-    main_workflow: type,
-    other_workflows: Sequence[type],
-    activities: Sequence[Any],
-    temporal_client: Client,
-    logger: Logger,
-) -> Worker:
-    main_workflow_name = main_workflow.__name__.upper()
-
-    queue_name = f'{camel_to_snake(main_workflow.__name__)}-queue'
-
-    local_workflow_parameters = {}
-
-    for parameter in parameters:
-        local_workflow_parameters[parameter[0]] = int(
-            os.getenv(main_workflow_name + '_' + parameter[0], parameter[1])
-        )
-
-    logger.info(f'Preparing worker for {main_workflow_name} with queue {queue_name}')
-    logger.info(f'Worker runtime config: {local_workflow_parameters}')
-
-    return Worker(
-        temporal_client,
-        task_queue=queue_name,
-        workflows=[main_workflow, *other_workflows],
-        activities=[*activities],
-        max_concurrent_workflow_tasks=local_workflow_parameters['MAX_CONCURRENT_WORKFLOW_TASKS'],
-        max_concurrent_activities=local_workflow_parameters['MAX_CONCURRENT_ACTIVITIES'],
-        max_concurrent_local_activities=local_workflow_parameters[
-            'MAX_CONCURRENT_LOCAL_ACTIVITIES'
-        ],
-        max_cached_workflows=local_workflow_parameters['MAX_CACHED_WORKFLOWS'],
-        workflow_task_poller_behavior=PollerBehaviorAutoscaling(
-            minimum=local_workflow_parameters['WORKFLOW_POLLER_BEHAVIOUR_MINIMUM'],
-            initial=local_workflow_parameters['WORKFLOW_POLLER_BEHAVIOUR_INITIAL'],
-            maximum=local_workflow_parameters['WORKFLOW_POLLER_BEHAVIOUR_MAXIMUM'],
-        ),
-        activity_task_poller_behavior=PollerBehaviorAutoscaling(
-            minimum=local_workflow_parameters['ACTIVITY_POLLER_BEHAVIOUR_MINIMUM'],
-            initial=local_workflow_parameters['ACTIVITY_POLLER_BEHAVIOUR_INITIAL'],
-            maximum=local_workflow_parameters['ACTIVITY_POLLER_BEHAVIOUR_MAXIMUM'],
-        ),
-    )

laborious/worker/worker.py

@@ -5,12 +5,14 @@ This module provides the main worker implementation for the Sientia DataOps Labo
 It orchestrates Temporal workers, manages task queues, and handles the lifecycle of
 prediction and retraining workflows.
 
-The worker supports multiple task queues:
-- predictions_batch-queue: Handles batch prediction workflows (heavy workload)
-  Includes activities for MLFlow, data quality gates, OPC export, PI Web API export, and PostgreSQL
-- minimal_retrain-queue: Handles model retraining workflows
-- drift-queue: Handles drift detection workflows
-- simple_metrics-queue: Handles simple metrics calculation workflows
+The worker supports multiple runtime-scoped task queues (via ``sientia_do.temporal.worker.prepare_worker``):
+- predictions_batch-{runtime}-queue: Batch prediction workflows (heavy workload)
+- minimal_retrain-{runtime}-queue: Model retraining workflows
+- drift-{runtime}-queue: Drift detection workflows
+- simple_metrics-{runtime}-queue: Simple metrics workflows
+
+``RUNTIME`` must be set; it is passed to every ``prepare_worker`` call. Schedulers must use the
+same queue names (breaking change vs legacy ``drift-queue`` / ``simple_metrics-queue``).
 
 Key Features:
 - Resource-based scaling with WorkerTuner (CPU and memory aware)
@@ -21,6 +23,7 @@ Key Features:
 - Multiple worker instances for different workflow types
 
 Environment Variables:
+- RUNTIME: Required non-empty string; suffix for all task queue names
 - TEMPORAL_HOST: Temporal server address (default: localhost:7233)
 - TEMPORAL_NAMESPACE: Temporal namespace (default: laborious)
 - POD_ID: Kubernetes pod identifier for metrics
@@ -40,6 +43,7 @@ with workflow.unsafe.imports_passed_through():
     from prometheus_client import start_http_server
     from sientia_do.notifications.handlers import CoreNotificationHandler as NotificationHandler
     from sientia_do.observability.logger import get_logger
+    from sientia_do.temporal.worker.prepare_worker import prepare_worker
     from sientia_do.utils.connectors_config import (
         build_api_config,
         build_mongodb_config,
@@ -53,7 +57,6 @@ with workflow.unsafe.imports_passed_through():
         build_mlflow_config,
         build_opc_config,
     )
-    from laborious.worker.prepare_worker import prepare_worker
     from laborious.workflows.drift import Drift
     from laborious.workflows.minimal_retrain import MinimalRetrain
     from laborious.workflows.predictions_batch import PredictionsBatch
@@ -100,10 +103,21 @@ async def main():
 
     logger.custom_info(f'Starting Worker with POD_ID: {POD_ID}', metadata)
 
-    logger.custom_info('Starting prometheus client...', metadata)
+    runtime = os.getenv('RUNTIME', '').strip()
+    if not runtime:
+        logger.custom_critical(
+            'RUNTIME environment variable is required and must be non-empty',
+            metadata,
+        )
+        metrics.APP_UP.labels(pod_id=POD_ID).set(0)
+        sys.exit(1)
+
+    metadata_runtime = {**metadata, 'runtime': runtime}
+
+    logger.custom_info('Starting prometheus client...', metadata_runtime)
     start_prometheus_server()
 
-    logger.custom_info('Starting Notification Handler...', metadata)
+    logger.custom_info('Starting Notification Handler...', metadata_runtime)
 
     mongo_config = build_mongodb_config()
     notification_handler = NotificationHandler(
@@ -113,7 +127,7 @@ async def main():
         project_name=os.getenv('PROJECT_NAME', 'laborious'),
     )
 
-    logger.custom_info('Starting Activities...', metadata)
+    logger.custom_info('Starting Activities...', metadata_runtime)
 
     activities = Activities(
         postgres_config=build_postgres_config(),
@@ -125,10 +139,13 @@ async def main():
         notification_handler=notification_handler,
     )
 
-    logger.custom_info('Initializing OPC...', metadata)
+    logger.custom_info('Initializing OPC...', metadata_runtime)
     await activities.init_opc()
 
-    logger.custom_info(f'Starting SDK Metrics Server on port {SDK_METRICS_PORT}...', metadata)
+    logger.custom_info(
+        f'Starting SDK Metrics Server on port {SDK_METRICS_PORT}...',
+        metadata_runtime,
+    )
 
     new_runtime = Runtime(
         telemetry=TelemetryConfig(
@@ -136,7 +153,7 @@ async def main():
         )
     )
 
-    logger.custom_info(f'Starting Temporal Client at {host}...', metadata)
+    logger.custom_info(f'Starting Temporal Client at {host}...', metadata_runtime)
 
     temporal_client = await client.Client.connect(
         target_host=host,
@@ -144,7 +161,7 @@ async def main():
         runtime=new_runtime,
     )
 
-    logger.custom_info('Starting Workers...', metadata)
+    logger.custom_info(f'Starting Workers (runtime={runtime})...', metadata_runtime)
 
     workers = [
         prepare_worker(
@@ -159,6 +176,7 @@ async def main():
                 activities.export_data_to_postgres,
             ],
             logger=logger,
+            runtime=runtime,
         ),
         prepare_worker(
             temporal_client=temporal_client,
@@ -170,6 +188,7 @@ async def main():
                 activities.export_data_to_postgres,
             ],
             logger=logger,
+            runtime=runtime,
         ),
         prepare_worker(
             temporal_client=temporal_client,
@@ -182,6 +201,7 @@ async def main():
                 activities.export_data_to_postgres,
             ],
             logger=logger,
+            runtime=runtime,
         ),
         prepare_worker(
             temporal_client=temporal_client,
@@ -211,6 +231,7 @@ async def main():
                 activities.write_pi_web_api_data,
             ],
             logger=logger,
+            runtime=runtime,
         ),
     ]
 
@@ -218,7 +239,7 @@ async def main():
     for w in workers:
         handlers.append(w.run())
 
-    logger.custom_info('Workers started successfully', metadata)
+    logger.custom_info('Workers started successfully', metadata_runtime)
 
     exit_code = 0
     try:

pyproject.toml

@@ -116,6 +116,12 @@ python_functions = ["test_*"]
 addopts = [
     "-v",
     "--strict-markers",
+    # pytest>=9.1 has a known bug where its unraisableexception plugin crashes
+    # (tracemalloc partially-initialized AttributeError) when 2+ unraisable
+    # exceptions land close together — e.g. "coroutine was never awaited" from
+    # AsyncMock-mocked sync methods (metrics_controller, minio_repository) being
+    # GC'd. Harmless mock artifacts turned into a hard ERROR by the plugin itself.
+    "-p", "no:unraisableexception",
 ]
 markers = [
     "asyncio: marks tests as async",

requirements-light.txt

@@ -1,12 +1,18 @@
 temporalio
 psycopg2-binary
 sqlalchemy
-asyncua
+asyncua==1.0.6
 redis
-git+ssh://git@github.com/Aignosi/sientia-dataops-library.git@1.12.0
+sientia_do>=1.12.2
+mlflow
 prometheus-client
 botocore
 boto3
 s3fs
 pyarrow
-mlflow
+kaleido
+hyperopt
+shap
+pycurl
+scipy<1.14.0
+scikit-learn==1.5.2

requirements-local.txt

@@ -0,0 +1,18 @@
+temporalio
+psycopg2-binary
+sqlalchemy
+asyncua==1.0.6
+redis
+git+ssh://git@github.com/Aignosi/sientia-dataops-library.git@1.12.2
+git+ssh://git@github.com/Aignosi/sientia-model-library.git@0.10.0
+prometheus-client   
+botocore
+boto3
+s3fs
+pyarrow
+kaleido
+hyperopt
+shap
+pycurl
+scipy<1.14.0
+scikit-learn==1.5.2

requirements.txt

@@ -1,10 +1,10 @@
 temporalio
 psycopg2-binary
 sqlalchemy
-asyncua
+asyncua==1.0.6
 redis
-git+ssh://git@github.com/Aignosi/sientia-dataops-library.git@1.10.4
-git+ssh://git@github.com/Aignosi/sientia-mlops-library.git@0.41.0
+sientia_do>=1.12.2
+sientia>0.40.0
 prometheus-client
 botocore
 boto3
@@ -15,4 +15,4 @@ hyperopt
 shap
 pycurl
 scipy<1.14.0
-scikit-learn==1.5.2
+scikit-learn==1.5.2

sonar-project.properties

@@ -1,4 +1,4 @@
-sonar.projectKey=Aignosi_sientia-dataops-laborious_temporal_beaec423-6c42-4f26-8134-b676287b499d
+sonar.projectKey=Aignosi_sientia-dataops-laborious_temporal_ca1a7039-6db9-49e5-be78-54d29bc93e4f
 sonar.projectName=sientia-dataops-laborious_temporal
 sonar.sources=laborious
 sonar.tests=tests

tests/laborious/activities/test_activities.py

@@ -173,7 +173,7 @@ async def test_shutdown(
     mock_mlflow_init,
     mock_storage_init,
 ):
-    mock_opc_init.close = AsyncMock()
+    mock_opc_init.aclose = AsyncMock()
     postgres_config = {
         'host': 'localhost',
         'port': 5432,
@@ -221,7 +221,7 @@ async def test_shutdown(
     )
 
     await activities.shutdown()
-    mock_opc_init.close.assert_called_once()
+    mock_opc_init.aclose.assert_called_once()
     mock_storage_init.close.assert_called_once()
     mock_mlflow_init.close.assert_called_once()
     mock_gates_init.close.assert_called_once()

tests/laborious/activities/test_opc.py

@@ -734,5 +734,5 @@ async def test_validate_server(opc):
 @mark.asyncio
 async def test_close(opc):
     opc.opc_repository['server1'].disconnect = AsyncMock(return_value=True)
-    await opc.close()
+    await opc.aclose()
     opc.opc_repository['server1'].disconnect.assert_called_once()

tests/laborious/utils/repository/test_model_repository.py

@@ -142,6 +142,41 @@ def test_get_model_run_id_success(mlflow_repository):
     assert output == '1'
 
 
+def test_get_model_run_id_missing_source(mlflow_repository):
+    mlflow_repository.client.search_registered_models.return_value = [MagicMock(name='test')]
+
+    mlflow_repository.client.search_model_versions.return_value = [
+        MagicMock(current_stage='Production', version='1', source='runs/test/0'),
+        MagicMock(current_stage='Production', version='2', source=None),
+    ]
+
+    with pytest.raises(mlflow_lib.exceptions.MlflowException) as exc_info:
+        mlflow_repository.get_model_run_id('test')
+
+    assert (
+        str(exc_info.value)
+        == "Model 'test' version '2' in stage 'Production' has no source URI to resolve run ID."
+    )
+
+
+def test_get_model_run_id_invalid_source(mlflow_repository):
+    mlflow_repository.client.search_registered_models.return_value = [MagicMock(name='test')]
+
+    mlflow_repository.client.search_model_versions.return_value = [
+        MagicMock(current_stage='Production', version='1', source='runs/test/0'),
+        MagicMock(current_stage='Production', version='2', source='runs/test'),
+    ]
+
+    with pytest.raises(mlflow_lib.exceptions.MlflowException) as exc_info:
+        mlflow_repository.get_model_run_id('test')
+
+    assert (
+        str(exc_info.value)
+        == "Model 'test' version '2' in stage 'Production' has invalid source URI "
+        "'runs/test' for run ID resolution."
+    )
+
+
 def test_get_next_run_name(mlflow, mlflow_repository):
     mlflow.search_runs.return_value = [1, 2, 3]
     output = mlflow_repository.get_next_run_name('run')

tests/laborious/worker/test_runtime_task_queues.py

@@ -0,0 +1,14 @@
+from sientia_do.temporal.worker.prepare_worker import build_queue_name
+
+from laborious.workflows.drift import Drift
+from laborious.workflows.minimal_retrain import MinimalRetrain
+from laborious.workflows.predictions_batch import PredictionsBatch
+from laborious.workflows.simple_metrics import SimpleMetrics
+
+
+def test_runtime_scoped_queue_names():
+    runtime = 'prod-a'
+    assert build_queue_name(PredictionsBatch.__name__, runtime) == 'predictions_batch-prod-a-queue'
+    assert build_queue_name(MinimalRetrain.__name__, runtime) == 'minimal_retrain-prod-a-queue'
+    assert build_queue_name(Drift.__name__, runtime) == 'drift-prod-a-queue'
+    assert build_queue_name(SimpleMetrics.__name__, runtime) == 'simple_metrics-prod-a-queue'

values.yaml

@@ -1,315 +0,0 @@
-# Default values for sientia-module.
-# This is a YAML-formatted file.
-# 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: 1
-
-# This sets the container image more information can be found here: https://kubernetes.io/docs/concepts/containers/images/
-image:
-  repository: aignosi.azurecr.io/sientia-module
-  # This sets the pull policy for images.
-  pullPolicy: Always
-  # Overrides the image tag whose default is the chart appVersion.
-  tag: "1.1.2"
-
-# 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:
-- name: docker-hub-secret
-# This is to override the chart name.
-nameOverride: "sientia-laborious-legacy-worker"
-fullnameOverride: "sientia-laborious-legacy-worker"
-namespace: sientia
-
-# This section builds out the service account more information can be found here: https://kubernetes.io/docs/concepts/security/service-accounts/
-serviceAccount:
-  # Specifies whether a service account should be created
-  create: true
-  # Automatically mount a ServiceAccount's API credentials?
-  automount: true
-  # Annotations to add to the service account
-  annotations: {}
-  # The name of the service account to use.
-  # If not set and create is true, a name is generated using the fullname template
-  name: "sientia-laborious-legacy-worker"
-
-# This is for setting Kubernetes Annotations to a Pod.
-# For more information checkout: https://kubernetes.io/docs/concepts/overview/working-with-objects/annotations/
-podAnnotations: {}
-# This is for setting Kubernetes Labels to a Pod.
-# For more information checkout: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/
-podLabels: {}
-
-podSecurityContext: {}
-  # fsGroup: 2000
-
-securityContext: {}
-  # capabilities:
-  #   drop:
-  #   - ALL
-  # readOnlyRootFilesystem: true
-  # runAsNonRoot: true
-  # runAsUser: 1000
-
-
-resources:
-  # Resource limits and requests are important for ResourceBasedTuner to work correctly.
-  # The tuner monitors system CPU and memory usage, so proper resource limits must be set.
-  limits:
-    cpu: 2000m  # 2 CPU cores
-    memory: 20Gi  # 20 GB memory
-  requests:
-    cpu: 1000m  # 1 CPU core
-    memory: 2Gi  # 2 GB memory
-
-# This is to setup the liveness and readiness probes more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/
-# This is to setup the liveness and readiness probes more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/
-livenessProbe:
-  exec:
-    command:
-      - sh
-      - -c
-      - |
-        curl -sf http://localhost:9090/metrics | grep -q '^app_up{.*} 1'
-  initialDelaySeconds: 1260
-  periodSeconds: 15
-  timeoutSeconds: 5
-  failureThreshold: 3
-
-readinessProbe:
-  exec:
-    command:
-      - sh
-      - -c
-      - |
-        curl -sf http://localhost:9090/metrics | grep -q '^app_up{.*} 1'
-  initialDelaySeconds: 1200
-  periodSeconds: 10
-  timeoutSeconds: 3
-  failureThreshold: 2
-
-
-
-# This section is for setting up autoscaling more information can be found here: https://kubernetes.io/docs/concepts/workloads/autoscaling/
-autoscaling:
-  enabled: false
-  minReplicas: 1
-  maxReplicas: 100
-  targetCPUUtilizationPercentage: 80
-  # targetMemoryUtilizationPercentage: 80
-
-# Additional volumes on the output Deployment definition.
-volumes: []
-# - name: foo
-#   secret:
-#     secretName: mysecret
-#     optional: false
-
-# Additional volumeMounts on the output Deployment definition.
-volumeMounts: []
-# - name: foo
-#   mountPath: "/etc/foo"
-#   readOnly: true
-
-nodeSelector: {}
-
-tolerations: []
-
-affinity: {}
-
-services:
-  sdk-metrics:
-    enabled: true
-    type: ClusterIP
-    port: 9091
-    targetPort: 9091
-    name: sdk-metrics
-
-  metrics:
-    enabled: true
-    type: ClusterIP
-    port: 9090
-    targetPort: 9090
-    name: metrics
-
-# Configuração do ServiceMonitor para o Prometheus Operator
-# ref: https://github.com/prometheus-operator/prometheus-operator
-serviceMonitor:
-  # Se true, um recurso ServiceMonitor será criado.
-  enabled: true
-  # O intervalo no qual as métricas devem ser coletadas (ex: 30s, 1m).
-  endpoints:
-  - port: metrics
-    path: /metrics
-    interval: 30s
-    relabelings: []
-  - port: sdk-metrics
-    path: /metrics
-    interval: 30s
-    relabelings: []
-
-  additionalLabels:
-    release: kube-prometheus-stack
-  
-
-env:
-  # Entrypoint variables 
-  - name: GITHUB_REPO_URL
-    value: "git@github.com:Aignosi/sientia-dataops-laborious_temporal.git"
-  - name: GITHUB_BRANCH
-    value: "fix/SIENTIAPDE-1811"
-  - name: PYTHON_APP
-    value: "laborious.worker.worker"
-
-  # Application variables
-  - name: POSTGRES_HOST
-    value: "paradedb-rw.paradedb.svc.cluster.local"
-  - name: POSTGRES_PORT
-    value: "5432"
-  - name: POSTGRES_USER
-    value: "postgres"
-  - name: POSTGRES_PASSWORD
-    value: "nFqc81y6kwmr2zuAIx43DhiOosFCVPpeEfTtTWZflkNjB2j1KtEeIANkhFR9mAX3"
-  - name: POSTGRES_DBNAME
-    value: "sientia"
-  - name: POSTGRES_MIN_CONNECTIONS
-    value: "20"
-  # max_connections = number_of_workers * max_concurrent_activities * safety_factor
-  # Example: 4 workers * 50 activities * 0.5 = 100 connections
-  - name: POSTGRES_MAX_CONNECTIONS
-    value: "100"
-
-  - name: MLFLOW_HOST
-    value: "http://sientia-tracker-mlflow-tracking.sientia-tracker.svc.cluster.local"
-  - name: MLFLOW_PORT
-    value: "80"
-  - name: MLFLOW_USERNAME
-    value: "aignosi"
-  - name: MLFLOW_PASSWORD
-    value: "1L0FP50j3ncp123"
-
-  - name: OPC_ID
-    value: "1"
-  - name: OPC_SERVER_NAME
-    value: "default_server"
-  - name: OPC_URL
-    value: "opc.tcp://sientia-opc-simulator-opc.sientia.svc.cluster.local:4840"
-
-
-  - name: LOG_LEVEL
-    value: "DEBUG"
-  - name: HTTP_METRICS_PORT
-    value: "9090"
-  - name: HTTP_SDK_METRICS_PORT
-    value: "9091"
-  - name: PROJECT_NAME
-    value: "sientia-laborious"
-
-  - name: TEMPORAL_HOST
-    value: "temporal-frontend.temporal.svc.cluster.local:7233"
-  - name: TEMPORAL_NAMESPACE
-    value: "laborious"
-
-  - name: MONGODB_USERNAME
-    value: "root"
-  - name: MONGODB_PASSWORD
-    value: "wKZDbMNU1c"
-  - name: MONGODB_URL
-    value: "my-release-mongodb.mongodb.svc.cluster.local:27017"
-  - name: MONGODB_DATABASE
-    value: "sientia"
-  - name: MONGODB_TTL_INDEX_HOURS
-    value: "1"
-
-  - name: MINIO_ENDPOINT_URL
-    value: "minio.minio.svc.cluster.local:9000"
-  - name: MINIO_ACCESS_KEY
-    value: "admin"
-  - name: MINIO_SECRET_KEY
-    value: "LiArt4eNmJ"
-  - name: MINIO_DEFAULT_BUCKET
-    value: "sientia"
-  - name: MINIO_RETENTION_HOURS
-    value: "24"
-  - name: SIENTIA_MINIO_OFFLOAD_THRESHOLD_MEGABYTES
-    value: "0.5"
-
-  # Temporal worker tuning for PredictionsBatch.
-  # IMPORTANT: prefix must be PREDICTIONSBATCH_ (from class name PredictionsBatch).
-  # Keep workflow-task concurrency moderate to reduce task completion races under load.
-  - name: PREDICTIONSBATCH_MAX_CONCURRENT_WORKFLOW_TASKS
-    value: "20"
-  # Allow higher activity parallelism because most activities are I/O-bound, but keep headroom.
-  - name: PREDICTIONSBATCH_MAX_CONCURRENT_ACTIVITIES
-    value: "60"
-  # Keep local activities controlled so they do not monopolize the event loop.
-  - name: PREDICTIONSBATCH_MAX_CONCURRENT_LOCAL_ACTIVITIES
-    value: "20"
-  # Cache enough workflows for reuse without excessive memory growth.
-  - name: PREDICTIONSBATCH_MAX_CACHED_WORKFLOWS
-    value: "200"
-  # Start with one workflow poller to avoid burst contention at startup.
-  - name: PREDICTIONSBATCH_WORKFLOW_POLLER_BEHAVIOUR_MINIMUM
-    value: "3"
-  # Small initial poller count warms up gradually instead of spiking task fetches.
-  - name: PREDICTIONSBATCH_WORKFLOW_POLLER_BEHAVIOUR_INITIAL
-    value: "5"
-  # Cap workflow pollers to limit scheduling pressure and avoid over-polling.
-  - name: PREDICTIONSBATCH_WORKFLOW_POLLER_BEHAVIOUR_MAXIMUM
-    value: "15"
-  # Keep at least two activity pollers so activity queues do not starve during spikes.
-  - name: PREDICTIONSBATCH_ACTIVITY_POLLER_BEHAVIOUR_MINIMUM
-    value: "3"
-  # Moderate initial activity pollers for faster ramp-up with controlled pressure.
-  - name: PREDICTIONSBATCH_ACTIVITY_POLLER_BEHAVIOUR_INITIAL
-    value: "10"
-  # Limit max activity pollers to preserve CPU for workflow-task completion.
-  - name: PREDICTIONSBATCH_ACTIVITY_POLLER_BEHAVIOUR_MAXIMUM
-    value: "30"
-
-  - name: MINIMALRETRAIN_MAX_CONCURRENT_ACTIVITIES
-    value: "1"
-  - name: MINIMALRETRAIN_MAX_CONCURRENT_LOCAL_ACTIVITIES
-    value: "1"
-  - name: MINIMALRETRAIN_MAX_CACHED_WORKFLOWS
-    value: "1"
-  - name: MINIMALRETRAIN_WORKFLOW_POLLER_BEHAVIOUR_MINIMUM
-    value: "1"
-  - name: MINIMALRETRAIN_WORKFLOW_POLLER_BEHAVIOUR_INITIAL
-    value: "1"
-  - name: MINIMALRETRAIN_WORKFLOW_POLLER_BEHAVIOUR_MAXIMUM
-    value: "1"
-  - name: MINIMALRETRAIN_ACTIVITY_POLLER_BEHAVIOUR_MINIMUM
-    value: "1"
-  - name: MINIMALRETRAIN_ACTIVITY_POLLER_BEHAVIOUR_INITIAL
-    value: "1"
-  - name: MINIMALRETRAIN_ACTIVITY_POLLER_BEHAVIOUR_MAXIMUM
-    value: "1"
-
-  - name: PI_WEB_API_BASE_URL
-    value: "https://pivision.votorantimcimentos.com/piwebapi"
-  - name: PI_WEB_API_AUTH_TYPE
-    value: "basic"
-  - name: PI_WEB_API_AUTH_TOKEN
-    valueFrom:
-      secretKeyRef:
-        name: pi-web-api-auth-token
-        key: token
-
-  - name: PYPI_SERVER
-    value: "http://library-distribution-server.library.svc.cluster.local:5000"
-
-ssh:
-  enabled: true
-  secretName: git-ssh-key-sientia-laborious-worker
-  sshPath: /mnt/.ssh
-  knownHostsPath: /mnt/known_hosts
-
-# kubectl create secret docker-registry docker-hub-secret --namespace sientia --docker-server=http://aignosi.azurecr.io --docker-username=aignosi --docker-password=5I5zpQ6sRaHqX1hD3dr+2mo647yO3FRc359/wu6gsP+ACRDRz5mp
-
-# helm upgrade --install sientia-laborious-legacy-worker sientia/sientia-module -n sientia --create-namespace -f ./values.yaml --version 0.6.0
-
-# kubectl create secret generic git-ssh-key-sientia-laborious-worker \
-#   --namespace sientia \
-#   --from-file=ssh-privatekey=git_key \
-#   --type=kubernetes.io/ssh-auth