sientia-dataops-laborious-legacy/laborious/worker/worker.py

"""
Laborious Worker Module

This module provides the main worker implementation for the Sientia DataOps Laborious system.
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)
- minimal_retrain-queue: Handles model retraining workflows
- drift-queue: Handles drift detection workflows
- simple_metrics-queue: Handles simple metrics calculation workflows

Key Features:
- Resource-based scaling with WorkerTuner (CPU and memory aware)
- Automatic polling scaling with PollerBehaviorAutoscaling
- Prometheus metrics integration
- Comprehensive error handling and logging
- Graceful shutdown with cleanup
- Multiple worker instances for different workflow types

Environment Variables:
- TEMPORAL_HOST: Temporal server address (default: localhost:7233)
- TEMPORAL_NAMESPACE: Temporal namespace (default: laborious)
- 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)
- PROJECT_NAME: Project name for notifications (default: laborious)

Tuner Configuration (Resource-based scaling):
- TUNER_TARGET_MEMORY_USAGE: Target memory usage (0.0-1.0, default: 0.75)
- TUNER_TARGET_CPU_USAGE: Target CPU usage (0.0-1.0, default: 0.80)
- TUNER_WORKFLOW_MIN_SLOTS: Minimum workflow slots (default: 5)
- TUNER_WORKFLOW_MAX_SLOTS: Maximum workflow slots (default: 50)
- TUNER_ACTIVITY_MIN_SLOTS: Minimum activity slots (default: 5)
- TUNER_ACTIVITY_MAX_SLOTS: Maximum activity slots (default: 50)
- TUNER_WORKFLOW_RAMP_THROTTLE_MS: Workflow ramp throttle in ms (default: 100)
- TUNER_ACTIVITY_RAMP_THROTTLE_MS: Activity ramp throttle in ms (default: 50)

Poller Configuration:
- POLLER_MINIMUM: Minimum number of pollers (default: 1)
- POLLER_MAXIMUM: Maximum number of pollers (default: 10)
- POLLER_INITIAL: Initial number of pollers (default: 2)
"""


from temporalio import client, workflow
from temporalio.runtime import PrometheusConfig, Runtime, TelemetryConfig
from temporalio.worker import (
    PollerBehaviorAutoscaling,
    ResourceBasedSlotConfig,
    Worker,
    WorkerTuner,
)

with workflow.unsafe.imports_passed_through():
    import asyncio
    import sys
    from datetime import timedelta

    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 laborious import metrics
    from laborious.activities.activities import Activities
    from laborious.utils.connectors_config import (
        build_minio_config,
        build_mlflow_config,
        build_mongodb_config,
        build_opc_config,
        build_postgres_config,
    )
    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
    from laborious.workflows.sub_workflows.format_and_export_prediction import (
        FormatAndExportPrediction,
    )
    from laborious.workflows.sub_workflows.prediction_process import PredictionProcess
    import os

POD_ID = os.getenv('POD_ID')
SDK_METRICS_PORT = int(os.getenv('HTTP_SDK_METRICS_PORT', '9091'))


def create_resource_tuner() -> WorkerTuner:
    """Create a resource-based tuner from environment variables."""
    target_memory = float(os.getenv('TUNER_TARGET_MEMORY_USAGE', '0.75'))
    target_cpu = float(os.getenv('TUNER_TARGET_CPU_USAGE', '0.50'))
    workflow_min = int(os.getenv('TUNER_WORKFLOW_MIN_SLOTS', '5'))
    workflow_max = int(os.getenv('TUNER_WORKFLOW_MAX_SLOTS', '50'))
    activity_min = int(os.getenv('TUNER_ACTIVITY_MIN_SLOTS', '5'))
    activity_max = int(os.getenv('TUNER_ACTIVITY_MAX_SLOTS', '50'))
    local_activity_min = int(os.getenv('TUNER_LOCAL_ACTIVITY_MIN_SLOTS', '1'))
    local_activity_max = int(os.getenv('TUNER_LOCAL_ACTIVITY_MAX_SLOTS', '30'))
    workflow_ramp = int(os.getenv('TUNER_WORKFLOW_RAMP_THROTTLE_MS', '100'))
    activity_ramp = int(os.getenv('TUNER_ACTIVITY_RAMP_THROTTLE_MS', '50'))
    local_activity_ramp = int(os.getenv('TUNER_LOCAL_ACTIVITY_RAMP_THROTTLE_MS', '50'))

    return WorkerTuner.create_resource_based(
        target_memory_usage=target_memory,
        target_cpu_usage=target_cpu,
        workflow_config=ResourceBasedSlotConfig(
            minimum_slots=workflow_min,
            maximum_slots=workflow_max,
            ramp_throttle=timedelta(milliseconds=workflow_ramp),
        ),
        activity_config=ResourceBasedSlotConfig(
            minimum_slots=activity_min,
            maximum_slots=activity_max,
            ramp_throttle=timedelta(milliseconds=activity_ramp),
        ),
        local_activity_config=ResourceBasedSlotConfig(
            minimum_slots=local_activity_min,
            maximum_slots=local_activity_max,
            ramp_throttle=timedelta(milliseconds=local_activity_ramp),
        ),
    )


def create_poller_behavior() -> PollerBehaviorAutoscaling:
    """Create poller behavior from environment variables."""
    minimum = int(os.getenv('POLLER_MINIMUM', '1'))
    maximum = int(os.getenv('POLLER_MAXIMUM', '10'))
    initial = int(os.getenv('POLLER_INITIAL', '2'))
    return PollerBehaviorAutoscaling(minimum=minimum, maximum=maximum, initial=initial)


async def main():
    """
    Main entry point for the Laborious worker application.

    This function initializes and starts all components of the worker:
    1. Sets up logging and metadata
    2. Starts Prometheus metrics server
    3. Initializes notification handler
    4. Creates and configures activities
    5. Initializes OPC connections
    6. Starts Temporal client and workers
    7. Manages worker lifecycle and graceful shutdown

    The function runs indefinitely until interrupted or an error occurs.
    On error, it performs cleanup and exits with a non-zero status code.

    Raises:
        Exception: Any unhandled exception during worker execution
        SystemExit: On graceful shutdown or error conditions
    """
    host = os.getenv('TEMPORAL_HOST', 'localhost:7233')
    logger = get_logger(__name__)

    metadata = {
        'pod_id': POD_ID,
        'model_name': '-',
        'model_id': '-',
        'workflow_name': '-',
        'schedule_name': '-',
    }

    logger.custom_info(f'Starting Worker with POD_ID: {POD_ID}', metadata)

    logger.custom_info('Starting prometheus client...', metadata)
    start_prometheus_server()

    logger.custom_info('Starting Notification Handler...', metadata)

    mongo_config = build_mongodb_config()
    notification_handler = NotificationHandler(
        connection_string=mongo_config['connection_string'],
        database=mongo_config['database_name'],
        logger=logger,
        project_name=os.getenv('PROJECT_NAME', 'laborious'),
    )

    logger.custom_info('Starting Activities...', metadata)

    activities = Activities(
        postgres_config=build_postgres_config(),
        mlflow_config=build_mlflow_config(),
        minio_config=build_minio_config(),
        opc_config=build_opc_config(),
        logger=logger,
        notification_handler=notification_handler,
    )

    logger.custom_info('Initializing OPC...', metadata)
    await activities.init_opc()

    logger.custom_info(f'Starting SDK Metrics Server on port {SDK_METRICS_PORT}...', metadata)

    new_runtime = Runtime(
        telemetry=TelemetryConfig(
            metrics=PrometheusConfig(bind_address=f'0.0.0.0:{SDK_METRICS_PORT}')
        )
    )

    logger.custom_info(f'Starting Temporal Client at {host}...', metadata)

    temporal_client = await client.Client.connect(
        target_host=host,
        namespace=os.getenv('TEMPORAL_NAMESPACE', 'laborious'),
        runtime=new_runtime,
    )

    logger.custom_info('Starting Workers...', metadata)

    tuner = create_resource_tuner()
    poller = create_poller_behavior()

    workers = [
        Worker(
            temporal_client,
            task_queue='minimal_retrain-queue',
            workflows=[MinimalRetrain],
            activities=[
                activities.load_custom_query,
                activities.query_to_minio,
                activities.retrain_model,
                activities.update_production_model,
                activities.format_retrain_report,
                activities.export_data_to_postgres,
            ],
            tuner=tuner,
            max_cached_workflows=2,
            workflow_task_poller_behavior=poller,
            activity_task_poller_behavior=poller,
        ),
        Worker(
            temporal_client,
            task_queue='drift-queue',
            workflows=[Drift],
            activities=[
                activities.load_custom_query,
                activities.get_reference_data,
                activities.calculate_drift,
                activities.export_data_to_postgres,
            ],
            tuner=tuner,
            max_cached_workflows=2,
            workflow_task_poller_behavior=poller,
            activity_task_poller_behavior=poller,
        ),
        Worker(
            temporal_client,
            task_queue='simple_metrics-queue',
            workflows=[SimpleMetrics],
            activities=[
                activities.load_custom_query,
                activities.calculate_simple_metrics,
                activities.export_data_to_postgres,
            ],
            tuner=tuner,
            max_cached_workflows=2,
            workflow_task_poller_behavior=poller,
            activity_task_poller_behavior=poller,
        ),
        Worker(
            temporal_client,
            task_queue='predictions_batch-queue',
            workflows=[PredictionsBatch, PredictionProcess, FormatAndExportPrediction],
            activities=[
                # MLFlow
                activities.request_predict,
                activities.request_transform,
                # Gates
                activities.input_gate,
                activities.mlflow_response_gate,
                activities.mlflow_content_gate,
                activities.format_transformed_data,
                activities.format_prediction,
                activities.format_default_prediction,
                activities.get_last_timestamp,
                # OPC
                activities.write_opc_data,
                # Postgres
                activities.load_custom_query,
                activities.repeat_last_prediction,
                activities.export_data_to_postgres,
                activities.write_metrics,
            ],
            tuner=tuner,
            max_cached_workflows=200,
            workflow_task_poller_behavior=poller,
            activity_task_poller_behavior=poller,
        ),
    ]

    handlers = []
    for w in workers:
        handlers.append(w.run())

    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.custom_error(f'An unhandled exception occurred: {e}', metadata)
    finally:
        if notification_handler:
            notification_handler.shutdown()
        if activities:
            await activities.shutdown()
        # Exit with a non-zero status code to indicate failure to Kubernetes
        metrics.APP_UP.labels(pod_id=POD_ID).set(0)  # Mark app as DOWN
        sys.exit(1)


def start_prometheus_server():
    """
    Starts the Prometheus metrics server for monitoring and observability.

    This function initializes the Prometheus HTTP server on the configured port
    and sets the application health metric to indicate the service is running.

    The server exposes metrics that can be scraped by Prometheus for monitoring
    the health and performance of the Laborious worker.

    Environment Variables:
        HTTP_METRICS_PORT: Port for the metrics server (default: 9090)
        POD_ID: Pod identifier for metrics labeling

    Raises:
        SystemExit: If the metrics server fails to start
    """
    try:
        port = int(os.getenv('HTTP_METRICS_PORT', 9090))
        start_http_server(port)
        print(f'Prometheus server started on port {port}.')
        metrics.APP_UP.labels(pod_id=POD_ID).set(1)  # Mark app as UP
    except Exception as e:
        print(f'Failed to start Prometheus server: {e}')
        os._exit(1)


if __name__ == '__main__':
    asyncio.run(main())