Merge pull request #38 from Aignosi/feature/SIENTIAPDE-1646

Project Configuration, Dependency, and SonarQube Updates with values.yaml Removal

.github/workflows/quality-gate.yml

@@ -13,4 +13,5 @@ jobs:
     with:
       project_name: 'scouter'
       repositories: 'sientia-dataops-library'
+      requirements_file: 'requirements-local.txt'
     secrets: inherit

.gitignore

@@ -43,4 +43,8 @@ git_log
 
 .env
 .ruff_cache/
-.mypy_cache/
+.mypy_cache/
+
+.cursor
+openspec
+collect_scripts

e2e/README.md

@@ -0,0 +1,37 @@
+# Scouter end-to-end tests
+
+Production-faithful E2E tests for `Scouter`, `PIWebAPIScouter`, and `CoreScouter` against real backing services.
+
+## Requirements
+
+- Docker (for testcontainers: MongoDB, Redis, PostgreSQL)
+- Python 3.11+ with dev dependencies: `pip install -r requirements-dev.txt`
+
+## Run locally
+
+```bash
+pytest e2e/ --override-ini testpaths=e2e -m e2e -v
+```
+
+Stop on first failure:
+
+```bash
+pytest e2e/ --override-ini testpaths=e2e -m e2e -x
+```
+
+## Coverage (separate from unit tests)
+
+```bash
+COVERAGE_FILE=.coverage.e2e pytest e2e/ --override-ini testpaths=e2e -m e2e --cov=scouter --cov-branch
+coverage combine .coverage .coverage.e2e && coverage report
+```
+
+## Scenario catalog
+
+See [scenarios.md](scenarios.md) for numbered scenarios and how they map to `test_scenario_*` functions. Section `## 0` of that file lists the harness smoke tests in `test_harness_smoke.py` (infra liveness checks, not business scenarios).
+
+## Production code is not mocked
+
+E2E uses real testcontainers, an in-process PI Web API HTTP server, `WorkflowEnvironment.start_local()`, and production `Activities` wiring. The only stand-ins are `mock_logger` and the optional `notification_inserts` spy. If a scenario fails due to a production defect, it is marked `xfail(strict=True)` and tracked in `openspec/changes/standardize-and-complete-e2e-tests/notes.md` when applicable.
+
+Unit tests under `tests/` remain Docker-free and run with the default `pytest` invocation.

e2e/conftest.py

@@ -1,122 +1,178 @@
 """
-Pytest configuration and fixtures for E2E tests.
+Pytest configuration and fixtures for production-faithful Scouter E2E tests.
 """
 
-from typing import Any
-from unittest.mock import AsyncMock, MagicMock, patch
+from __future__ import annotations
+
+from concurrent.futures import ThreadPoolExecutor
+from pathlib import Path
+from unittest.mock import MagicMock
 
-import pandas as pd
 import pytest
 import pytest_asyncio
-from pandas import DataFrame
+from pymongo import MongoClient
+from redis import Redis
 from sqlalchemy import create_engine, text
-from sqlalchemy.orm import sessionmaker
+from testcontainers.mongodb import MongoDbContainer
 from testcontainers.postgres import PostgresContainer
+from testcontainers.redis import RedisContainer
 from temporalio.testing import WorkflowEnvironment
-from temporalio.worker import Worker
+from temporalio.worker import PollerBehaviorAutoscaling, Worker
 
+from e2e.helpers import SCOUTER_TASK_QUEUE, postgres_connection_parts
+from e2e.pi_web_api_test_server import PIWebAPITestServer
 from scouter.activities.activities import Activities
 from scouter.workflow.pi_web_api_scouter import PIWebAPIScouter
+from scouter.workflow.scouter import Scouter
 from scouter.workflow.sub_workflows.core_scouter import CoreScouter
 from sientia_do.notifications.handlers import CoreNotificationHandler
 from sientia_do.observability.logger import Logger
-from sientia_do.observability.metrics_controller import MetricsController
 
-from e2e.fixtures.fake_mongodb_repository import FakeMongoDBRepository
-from e2e.fixtures.fake_redis_repository import FakeRedisRepository
-
-# Test constants
-TEST_MONGODB_CONNECTION_STRING = 'mongodb://localhost:27017'
-TEST_DATABASE_NAME = 'test_db'
+E2E_DATABASE = 'scouter_e2e_test'
+E2E_NOTIFICATION_COLLECTION = 'notification_queue'
+DB_SCHEMA_PATH = Path(__file__).resolve().parent / 'db_schema.sql'
 
 
-@pytest_asyncio.fixture(scope='session')
+def _activity_list(activities: Activities) -> list:
+    """Return bound activity callables for the E2E worker."""
+    return [
+        activities.load_latest_data,
+        activities.get_last_data_timestamp,
+        activities.put_last_data_timestamp,
+        activities.get_tag_values,
+        activities.data_quality_gate,
+        activities.aggregate_data,
+        activities.group_and_hold_data,
+        activities.export_data_to_postgres,
+        activities.write_metrics,
+        activities.store_data_package,
+    ]
+
+
+@pytest.fixture(scope='session')
 def postgres_container():
     """
-    Create a PostgreSQL container using testcontainers.
-    
-    This fixture creates a real PostgreSQL database in a Docker container
-    that will be used for all tests in the session.
+    Session-scoped PostgreSQL testcontainer.
+
+    Return:
+        Running PostgresContainer instance
     """
-    postgres = PostgresContainer('postgres:15')
-    postgres.start()
-    yield postgres
-    postgres.stop()
+    container = PostgresContainer('postgres:15')
+    container.start()
+    yield container
+    container.stop()
 
 
-@pytest_asyncio.fixture
+@pytest.fixture(scope='session')
+def mongo_container():
+    """
+    Session-scoped MongoDB testcontainer.
+
+    Return:
+        Running MongoDbContainer instance
+    """
+    container = MongoDbContainer('mongo:7')
+    container.start()
+    yield container
+    container.stop()
+
+
+@pytest.fixture(scope='session')
+def redis_container():
+    """
+    Session-scoped Redis testcontainer.
+
+    Return:
+        Running RedisContainer instance
+    """
+    container = RedisContainer('redis:7')
+    container.start()
+    yield container
+    container.stop()
+
+
+@pytest.fixture(scope='session')
 def postgres_engine(postgres_container):
     """
-    Create SQLAlchemy engine for PostgreSQL test database.
-    
-    This fixture creates a connection to the PostgreSQL container
-    created by the postgres_container fixture.
+    SQLAlchemy engine bound to the Postgres testcontainer for the session.
+
+    Return:
+        SQLAlchemy Engine
     """
-    # Get connection URL from container
-    connection_string = postgres_container.get_connection_url()
-    engine = create_engine(connection_string)
-    
+    engine = create_engine(postgres_container.get_connection_url())
     yield engine
-    
     engine.dispose()
 
 
-def _create_schema_and_table(engine):
+@pytest.fixture(scope='session')
+def mongo_uri(mongo_container):
     """
-    Helper function to create schema and table in the given engine.
-    
-    This is used by both the autouse fixture and test_activities to ensure
-    the schema exists before Activities tries to use it.
-    
-    Note: For tests, we create a non-partitioned table to avoid issues
-    with pandas to_sql recognizing partitioned tables.
+    MongoDB connection string for the testcontainer.
+
+    Return:
+        Connection URI string
     """
-    schema_name = 'sientia_data'
-    table_name = 'laborious_data'
-    
-    # Use begin() to ensure transaction is properly committed
-    with engine.begin() as conn:
-        # Create schema
-        conn.execute(text(f"CREATE SCHEMA IF NOT EXISTS {schema_name}"))
-        
-        # Create table WITHOUT partitioning (simpler for tests)
-        # Same structure as production, but without PARTITION BY RANGE
-        create_table_sql = f"""
-            CREATE TABLE IF NOT EXISTS {schema_name}.{table_name} (
-                id SERIAL NOT NULL,
-                model_id int4 NOT NULL,
-                variable text NOT NULL,
-                value numeric NULL,
-                "timestamp" timestamptz NOT NULL,
-                created_at timestamptz DEFAULT CURRENT_TIMESTAMP NOT NULL,
-                CONSTRAINT unique_timestamp_variable UNIQUE (model_id, "timestamp", variable),
-                PRIMARY KEY (id, created_at)
-            );
-        """
-        
-        conn.execute(text(create_table_sql))
-        # Transaction is automatically committed when exiting the 'with' block
+    return mongo_container.get_connection_url()
 
 
-@pytest_asyncio.fixture(autouse=True)
+@pytest.fixture(scope='session')
+def redis_client(redis_container):
+    """
+    Redis client connected to the testcontainer.
+
+    Return:
+        redis.Redis client with decode_responses=True
+    """
+    host = redis_container.get_container_host_ip()
+    port = int(redis_container.get_exposed_port(6379))
+    client = Redis(host=host, port=port, decode_responses=True)
+    yield client
+    client.close()
+
+
+@pytest.fixture(autouse=True)
 def setup_postgres_schema_and_table(postgres_engine):
     """
-    Automatically create necessary schema and table before each test.
-    
-    This fixture runs automatically (autouse=True) and ensures
-    that the sientia_data schema and laborious_data table exist
-    with the correct structure before tests execute.
-    
-    Note: For tests, we use a non-partitioned table which is simpler and avoids issues
-    with pandas to_sql recognizing partitioned tables.
+    Apply db_schema.sql before each test so laborious_data is empty and current.
     """
-    _create_schema_and_table(postgres_engine)
+    sql = DB_SCHEMA_PATH.read_text(encoding='utf-8')
+    with postgres_engine.begin() as conn:
+        conn.exec_driver_sql(sql)
     yield
 
 
-@pytest_asyncio.fixture
+@pytest.fixture(autouse=True)
+def reset_mongo_collections(mongo_uri):
+    """
+    Drop all collections in the E2E Mongo database between tests.
+    """
+    client = MongoClient(mongo_uri)
+    try:
+        db = client[E2E_DATABASE]
+        for name in db.list_collection_names():
+            db.drop_collection(name)
+    finally:
+        client.close()
+    yield
+
+
+@pytest.fixture(autouse=True)
+def reset_redis(redis_client):
+    """
+    Flush the Redis testcontainer between tests.
+    """
+    redis_client.flushdb()
+    yield
+
+
+@pytest.fixture
 def mock_logger():
-    """Mock logger for testing."""
+    """
+    Logger stand-in (only permitted MagicMock in the E2E harness).
+
+    Return:
+        MagicMock with Logger spec
+    """
     logger = MagicMock(spec=Logger)
     logger.info = MagicMock()
     logger.debug = MagicMock()
@@ -126,238 +182,143 @@ def mock_logger():
     return logger
 
 
-@pytest_asyncio.fixture
-def mock_mongo_client():
+@pytest.fixture
+def notification_handler(mock_logger, mongo_uri):
     """
-    Mock MongoDB client to avoid real connections.
-    
-    This fixture mocks the pymongo.MongoClient used by CoreNotificationHandler,
-    allowing us to use a real NotificationHandler instance without connecting to MongoDB.
+    Real CoreNotificationHandler backed by the Mongo testcontainer.
+
+    Return:
+        CoreNotificationHandler instance
     """
-    mock_client = MagicMock()
-    mock_db = MagicMock()
-    mock_collection = MagicMock()
-    
-    # Configure the mock chain: client[database] -> db[collection] -> collection
-    mock_client.__getitem__.return_value = mock_db
-    mock_db.__getitem__.return_value = mock_collection
-    
-    # Mock server_info() to avoid connection attempts
-    mock_client.server_info = MagicMock()
-    
-    # Mock insert_one for notifications
-    mock_collection.insert_one = MagicMock()
-    
-    return mock_client
-
-
-@pytest_asyncio.fixture
-def notification_handler(mock_logger, mock_mongo_client):
-    """
-    Create a real NotificationHandler instance with mocked MongoDB client.
-    
-    This fixture creates a real CoreNotificationHandler instance but mocks
-    the underlying MongoDB connection to avoid real database connections.
-    """
-    # Patch MongoClient where it's imported in the handlers module
-    with patch('sientia_do.notifications.handlers.MongoClient', return_value=mock_mongo_client):
-        handler = CoreNotificationHandler(
-            connection_string=TEST_MONGODB_CONNECTION_STRING,
-            database=TEST_DATABASE_NAME,
-            logger=mock_logger,
-            project_name='scouter',
-        )
-        yield handler
-        handler.shutdown()
-
-
-@pytest_asyncio.fixture
-def metrics_controller(mock_logger):
-    """
-    Create a real MetricsController instance.
-    
-    MetricsController doesn't require external services, so we can use
-    a real instance without mocking anything.
-    """
-    controller = MetricsController(logger=mock_logger)
-    yield controller
-    # MetricsController might have cleanup, but it's optional
-
-
-@pytest_asyncio.fixture
-def mock_pi_web_api_client():
-    """Mock PI Web API client."""
-    mock_client = MagicMock()
-
-    # Mock DataFrame response similar to real API
-    # The real PIWebAPIClient returns timestamp as datetime, so we need to match that
-    mock_df = DataFrame({
-        'timestamp': [
-            '2024-01-01 12:00:00+0000',
-            '2024-01-01 12:01:00+0000',
-            '2024-01-01 12:02:00+0000',
-        ],
-        'name': ['tag1', 'tag2', 'tag3'],
-        'value': [10.5, 20.3, 30.7],
-        'tag': ['webid1', 'webid2', 'webid3'],
-    })
-    
-    # Convert timestamp to datetime (UTC, floored to seconds) to match real client behavior
-    mock_df['timestamp'] = pd.to_datetime(mock_df['timestamp'], utc=True).dt.floor('s')
-
-    mock_client.get_latest_values_df = AsyncMock(return_value=mock_df)
-    mock_client.close = MagicMock()
-    return mock_client
-
-
-@pytest_asyncio.fixture(scope='function')
-def test_activities(
-    postgres_engine,
-    postgres_container,
-    mock_logger,
-    notification_handler,
-    metrics_controller,
-    mock_pi_web_api_client,
-):
-    """
-    Create Activities instance with test dependencies.
-
-    This fixture creates a real Activities instance with:
-    - PostgreSQL database (via testcontainers)
-    - FakeRedis instead of real Redis
-    - FakeMongoDB instead of real MongoDB
-    - Mocked PI Web API client
-    - Real NotificationHandler and MetricsController (with mocked underlying services)
-    """
-    # Get connection details from container
-    connection_string = postgres_container.get_connection_url()
-    
-    # Parse connection string to get individual components
-    # Format: postgresql://testuser:testpass@localhost:5432/test
-    from urllib.parse import urlparse
-    parsed = urlparse(connection_string)
-    
-    # Ensure schema and table exist BEFORE creating Activities
-    # This ensures the schema exists when Activities initializes its engine
-    _create_schema_and_table(postgres_engine)
-    
-    # Create fake repositories that will be used from the start
-    fake_redis_repo = FakeRedisRepository(
-        host='localhost',
-        port=6379,
-        username='',
-        password='',
+    handler = CoreNotificationHandler(
+        connection_string=mongo_uri,
+        database=E2E_DATABASE,
         logger=mock_logger,
-        notification_handler=notification_handler,
-        metrics_controller=metrics_controller,
+        project_name='scouter-e2e',
+        notification_topic=E2E_NOTIFICATION_COLLECTION,
     )
-    
-    fake_mongo_repo = FakeMongoDBRepository(
-        connection_string=TEST_MONGODB_CONNECTION_STRING,
-        database_name=TEST_DATABASE_NAME,
-        logger=mock_logger,
-        notification_handler=notification_handler,
-        metrics_controller=metrics_controller,
-    )
-    
-    # Patch create_engine to return our postgres_engine instead of creating a new one
-    # This ensures Activities uses the same engine from the start
-    original_create_engine = create_engine
-    
-    def patched_create_engine(connection_string, *args, **kwargs):
-        # Check if this is the connection string that Activities would create
-        # Activities creates: postgresql://user:password@host:port/dbname
-        expected_conn_str = f"postgresql://{parsed.username or 'test'}:{parsed.password or 'test'}@localhost:{postgres_container.get_exposed_port(5432)}/{parsed.path.lstrip('/') if parsed.path else 'test'}"
-        
-        # If it matches our test container connection, return our engine
-        if connection_string == expected_conn_str:
-            return postgres_engine
-        # Otherwise, use the original create_engine
-        return original_create_engine(connection_string, *args, **kwargs)
-    
-    # Patch RedisRepository to return our fake repository from the start
-    def patched_redis_repository(*args, **kwargs):
-        return fake_redis_repo
-    
-    # Patch MongoDBRepository to return our fake repository from the start
-    def patched_mongodb_repository(*args, **kwargs):
-        return fake_mongo_repo
-    
-    # Patch PIWebAPIClient to return our mock from the start
-    def patched_pi_web_api_client(*args, **kwargs):
-        return mock_pi_web_api_client
-    
-    # Create Activities with test configurations
-    # All patches ensure it uses our test instances from the start
-    with patch('sientia_do.temporal.activities.postgres.create_engine', new=patched_create_engine), \
-         patch('scouter.activities.redis.RedisRepository', new=patched_redis_repository), \
-         patch('scouter.activities.mongodb.MongoDBRepository', new=patched_mongodb_repository), \
-         patch('scouter.activities.api.PIWebAPIClient', new=patched_pi_web_api_client):
-        
-        activities = Activities(
-            postgres_config={
-                'host': 'localhost',  # Container exposes to localhost
-                'port': postgres_container.get_exposed_port(5432),
-                'user': parsed.username or 'test',
-                'password': parsed.password or 'test',
-                'dbname': parsed.path.lstrip('/') if parsed.path else 'test',
-                'min_connections': 1,
-                'max_connections': 5,
-            },
-            redis_config={
-                'host': 'localhost',
-                'port': 6379,
-                'username': '',
-                'password': '',
-            },
-            mongodb_config={
-                'connection_string': TEST_MONGODB_CONNECTION_STRING,
-                'database_name': TEST_DATABASE_NAME,
-            },
-            api_config={
-                'base_url': 'http://localhost:8080',
-                'auth_type': 'bearer',
-                'auth_token': 'test_token',
-            },
-            logger=mock_logger,
-            notification_handler=notification_handler,
-        )
-    
-    # Verify that Activities is using our instances from the start
-    assert activities.engine is postgres_engine, "Activities should use the same engine as postgres_engine"
-    assert activities.redis_repository is fake_redis_repo, "Activities should use the same fake Redis repository"
-    assert activities.mongodb_repository is fake_mongo_repo, "Activities should use the same fake MongoDB repository"
-    assert activities.pi_web_api_client is mock_pi_web_api_client, "Activities should use the same mock PI Web API client"
-
-    yield activities
-
-    # Cleanup
-    activities.shutdown()
+    yield handler
+    handler.shutdown()
 
 
-@pytest_asyncio.fixture(scope='function')
-async def temporal_test_env():
-    """Create Temporal test environment."""
-    env = await WorkflowEnvironment.start_time_skipping()
-    async with env:
+@pytest.fixture
+def notification_inserts(notification_handler):
+    """
+    Spy wrapper around notification collection insert_one (still writes to Mongo).
+
+    Return:
+        MagicMock wrapping insert_one
+    """
+    collection = notification_handler.mongo_collection
+    spy = MagicMock(wraps=collection.insert_one)
+    collection.insert_one = spy
+    return spy
+
+
+@pytest.fixture(scope='session')
+def pi_web_api_server():
+    """
+    Session-scoped in-process PI Web API HTTP stub.
+
+    Return:
+        Started PIWebAPITestServer instance
+    """
+    server = PIWebAPITestServer()
+    server.start()
+    yield server
+    server.stop()
+
+
+@pytest.fixture(autouse=True)
+def cleanup_pi_web_api_server(pi_web_api_server):
+    """
+    Reset PI Web API stub state between tests.
+    """
+    pi_web_api_server.clear()
+    yield
+
+
+@pytest_asyncio.fixture(scope='session')
+async def temporal_env():
+    """
+    Session-scoped WorkflowEnvironment using the real local Temporal dev server.
+
+    Return:
+        WorkflowEnvironment from start_local()
+    """
+    async with await WorkflowEnvironment.start_local() as env:
         yield env
 
 
-@pytest_asyncio.fixture(scope='function')
-async def temporal_worker(temporal_test_env, test_activities):
-    """Create Temporal worker with test activities."""
+@pytest.fixture
+def test_activities(
+    postgres_container,
+    mongo_uri,
+    redis_container,
+    pi_web_api_server,
+    mock_logger,
+    notification_handler,
+):
+    """
+    Production Activities wired to testcontainers and the PI Web API stub.
+
+    Return:
+        Live Activities instance (no unittest.mock.patch)
+    """
+    pg_parts = postgres_connection_parts(
+        postgres_container.get_connection_url())
+    redis_host = redis_container.get_container_host_ip()
+    redis_port = int(redis_container.get_exposed_port(6379))
+
+    activities = Activities(
+        postgres_config={
+            **pg_parts,
+            'min_connections': 1,
+            'max_connections': 5,
+        },
+        redis_config={
+            'host': redis_host,
+            'port': redis_port,
+            'username': '',
+            'password': '',
+        },
+        mongodb_config={
+            'connection_string': mongo_uri,
+            'database_name': E2E_DATABASE,
+        },
+        api_config={
+            'base_url': pi_web_api_server.base_url,
+            'auth_type': 'bearer',
+            'auth_token': 'e2e-test-token',
+        },
+        logger=mock_logger,
+        notification_handler=notification_handler,
+    )
+    yield activities
+    activities.shutdown()
+
+
+@pytest_asyncio.fixture
+async def temporal_worker(temporal_env, test_activities):
+    """
+    Temporal worker registering all Scouter workflows and activities on the E2E queue.
+
+    Return:
+        Running temporalio.worker.Worker
+    """
     async with Worker(
-        temporal_test_env.client,
-        task_queue='test-queue',
-        workflows=[PIWebAPIScouter, CoreScouter],
-        activities=[
-            test_activities.get_tag_values,
-            test_activities.data_quality_gate,
-            test_activities.aggregate_data,
-            test_activities.group_and_hold_data,
-            test_activities.export_data_to_postgres,
-            test_activities.write_metrics,
-            test_activities.store_data_package,
-        ],
+        temporal_env.client,
+        task_queue=SCOUTER_TASK_QUEUE,
+        workflows=[Scouter, PIWebAPIScouter, CoreScouter],
+        activities=_activity_list(test_activities),
+        activity_executor=ThreadPoolExecutor(
+            max_workers=50, thread_name_prefix='e2e-activity'),
+        max_concurrent_workflow_tasks=50,
+        max_concurrent_activities=50,
+        max_concurrent_local_activities=50,
+        workflow_task_poller_behavior=PollerBehaviorAutoscaling(
+            minimum=1, initial=2, maximum=10),
+        activity_task_poller_behavior=PollerBehaviorAutoscaling(
+            minimum=1, initial=2, maximum=10),
     ) as worker:
         yield worker

e2e/db_schema.sql

@@ -0,0 +1,16 @@
+-- Single source of truth for E2E Postgres DDL (non-partitioned mirror of production sientia_data.laborious_data).
+
+DROP TABLE IF EXISTS sientia_data.laborious_data;
+DROP SCHEMA IF EXISTS sientia_data CASCADE;
+
+CREATE SCHEMA sientia_data;
+
+CREATE TABLE sientia_data.laborious_data (
+    id SERIAL NOT NULL,
+    model_id int4 NOT NULL,
+    variable text NOT NULL,
+    value numeric NULL,
+    "timestamp" timestamptz NOT NULL,
+    created_at timestamptz DEFAULT CURRENT_TIMESTAMP NOT NULL,
+    PRIMARY KEY (id, created_at)
+);

e2e/fixtures/fake_mongodb_repository.py

@@ -1,241 +0,0 @@
-"""
-Fake MongoDB Repository adapter for testing.
-
-This adapter implements the MongoDBRepository interface using mongomock
-to provide an in-memory MongoDB server for testing.
-"""
-
-import time
-from typing import Any
-
-from mongomock import MongoClient
-from sientia_do.notifications.handlers import CoreNotificationHandler as NotificationHandler
-from sientia_do.observability.logger import Logger
-from sientia_do.observability.metrics_controller import MetricsController
-from sientia_do.observability.sientia_monitoring import SientiaMonitoring
-
-
-def clear_mongo_id(docs: list) -> list:
-    """
-    Remove MongoDB internal `_id` fields from nested structures.
-
-    Same implementation as in the real MongoDBRepository.
-
-    Args:
-        docs: The list of documents or nested structures to clean.
-
-    Returns:
-        The cleaned documents with `_id` fields removed wherever present.
-    """
-    for doc in docs:
-        if isinstance(doc, list):
-            clear_mongo_id(doc)
-        elif isinstance(doc, dict):
-            if '_id' in doc:
-                del doc['_id']
-            for _key, value in doc.items():
-                if isinstance(value, list):
-                    clear_mongo_id(value)
-                elif isinstance(value, dict):
-                    clear_mongo_id([value])
-    return docs
-
-
-class FakeMongoDBRepository(SientiaMonitoring):
-    """
-    Fake MongoDB Repository that uses mongomock for testing.
-
-    Implements the same interface as MongoDBRepository but uses
-    mongomock for in-memory MongoDB operations.
-    """
-
-    def __init__(
-        self,
-        connection_string: str,
-        database_name: str,
-        logger: Logger,
-        notification_handler: NotificationHandler,
-        metrics_controller: MetricsController,
-    ):
-        """
-        Initialize fake MongoDB repository with mongomock.
-
-        Args:
-            connection_string: MongoDB connection string (ignored in fake mode)
-            database_name: Target database name
-            logger: Logger instance
-            notification_handler: Notification handler
-            metrics_controller: Metrics controller
-        """
-        SientiaMonitoring.__init__(
-            self,
-            logger=logger,
-            notification_handler=notification_handler,
-            metrics_controller=metrics_controller,
-        )
-
-        self.database_name = database_name
-        # Use mongomock instead of real MongoDB
-        self.mongo_client = MongoClient()
-        self.database = self.mongo_client[self.database_name]
-        logger.info('Fake MongoDB connection initialized')
-
-    def close(self):
-        """
-        Closes fake MongoDB connection and shuts down monitoring.
-        """
-        try:
-            if self.mongo_client:
-                self.logger.info('Closing fake MongoDB connection...')
-                self.mongo_client.close()
-                self.logger.info('Fake MongoDB connection closed successfully')
-        except Exception as e:
-            self.logger.error(f'Failed to close fake MongoDB connection: {e}')
-        SientiaMonitoring.shutdown(self)
-
-    def __del__(self):
-        """
-        Destructor that closes the connection when destroying the instance.
-        """
-        self.close()
-
-    async def find(
-        self,
-        collection_name: str,
-        filters: dict[str, Any],
-        metadata: dict[str, Any],
-    ) -> list[dict[str, Any]]:
-        """
-        Finds documents in a MongoDB collection based on provided filters.
-
-        Args:
-            collection_name: Name of the collection to search
-            filters: Query filters to apply
-            metadata: Dictionary with additional metadata
-
-        Return:
-            List of documents matching the filters (with `_id` removed)
-        """
-        try:
-            start_time = time.time()
-            collection = self.database[collection_name]
-            documents = list(collection.find(filters, {'_id': 0}))
-        except Exception as e:
-            self.logger.error(f'Failed to find documents in fake MongoDB: {e}')
-            raise e
-
-        return clear_mongo_id(documents)
-
-    async def aggregate(
-        self,
-        collection_name: str,
-        pipeline: list[dict[str, Any]],
-        metadata: dict[str, Any],
-    ) -> list[dict[str, Any]]:
-        """
-        Executes an aggregation on a MongoDB collection.
-
-        Args:
-            collection_name: Name of the collection to aggregate
-            pipeline: MongoDB aggregation pipeline
-            metadata: Dictionary with additional metadata
-
-        Return:
-            List of documents resulting from aggregation (with `_id` removed)
-        """
-        try:
-            start_time = time.time()
-            collection = self.database[collection_name]
-            documents = list(collection.aggregate(pipeline))
-        except Exception as e:
-            self.logger.error(f'Failed to aggregate documents in fake MongoDB: {e}')
-            raise e
-
-        return clear_mongo_id(documents)
-
-    async def update_many(
-        self,
-        collection_name: str,
-        filters: dict[str, Any],
-        update: dict[str, Any],
-        metadata: dict[str, Any],
-    ) -> None:
-        """
-        Updates multiple documents in a MongoDB collection.
-
-        Args:
-            collection_name: Collection name
-            filters: Filters to identify documents to update
-            update: Update operations to apply
-            metadata: Dictionary with additional metadata
-        """
-        try:
-            collection = self.database[collection_name]
-            collection.update_many(filters, update)
-        except Exception as e:
-            self.logger.error(f'Failed to update documents in fake MongoDB: {e}')
-            raise e
-
-    async def insert_many(
-        self,
-        collection_name: str,
-        documents: list[dict[str, Any]],
-        metadata: dict[str, Any],
-    ) -> None:
-        """
-        Inserts multiple documents into a MongoDB collection.
-
-        Args:
-            collection_name: Collection name
-            documents: List of documents to insert
-            metadata: Dictionary with additional metadata
-        """
-        try:
-            collection = self.database[collection_name]
-            collection.insert_many(documents)
-        except Exception as e:
-            self.logger.error(f'Failed to insert documents in fake MongoDB: {e}')
-            raise e
-
-    async def insert(
-        self,
-        collection_name: str,
-        document: dict[str, Any],
-        metadata: dict[str, Any],
-    ) -> None:
-        """
-        Inserts a document into a MongoDB collection.
-
-        Args:
-            collection_name: Collection name
-            document: Document to insert
-            metadata: Dictionary with additional metadata
-        """
-        try:
-            collection = self.database[collection_name]
-            collection.insert_one(document)
-        except Exception as e:
-            self.logger.error(f'Failed to insert document in fake MongoDB: {e}')
-            raise e
-
-    async def delete_many(
-        self,
-        collection_name: str,
-        filters: dict[str, Any],
-        metadata: dict[str, Any],
-    ) -> None:
-        """
-        Removes multiple documents from a MongoDB collection.
-
-        Args:
-            collection_name: Collection name
-            filters: Filters to identify documents to remove
-            metadata: Dictionary with additional metadata
-        """
-        try:
-            collection = self.database[collection_name]
-            collection.delete_many(filters)
-        except Exception as e:
-            self.logger.error(f'Failed to delete documents in fake MongoDB: {e}')
-            raise e
-

e2e/fixtures/fake_redis_repository.py

@@ -1,170 +0,0 @@
-"""
-Fake Redis Repository adapter for testing.
-
-This adapter implements the RedisRepository interface using fakeredis
-to provide an in-memory Redis server for testing.
-"""
-
-import json
-from typing import Any
-
-import fakeredis
-from sientia_do.notifications.handlers import CoreNotificationHandler as NotificationHandler
-from sientia_do.observability.logger import Logger
-from sientia_do.observability.metrics_controller import MetricsController
-from sientia_do.observability.sientia_monitoring import SientiaMonitoring
-
-
-class FakeRedisRepository(SientiaMonitoring):
-    """
-    Fake Redis Repository that uses fakeredis for testing.
-
-    Implements the same interface as RedisRepository but uses
-    fakeredis for in-memory Redis operations.
-    """
-
-    def __init__(
-        self,
-        host: str,
-        port: int,
-        username: str,
-        password: str,
-        logger: Logger,
-        notification_handler: NotificationHandler,
-        metrics_controller: MetricsController,
-    ):
-        """
-        Initialize fake Redis repository with fakeredis.
-
-        Args:
-            host: Redis server address (ignored in fake mode)
-            port: Redis server port (ignored in fake mode)
-            username: Username (ignored in fake mode)
-            password: Password (ignored in fake mode)
-            logger: Logger instance
-            notification_handler: Notification handler
-            metrics_controller: Metrics controller
-        """
-        SientiaMonitoring.__init__(
-            self,
-            logger=logger,
-            notification_handler=notification_handler,
-            metrics_controller=metrics_controller,
-        )
-        # Create fake Redis server
-        self.redis_client = fakeredis.FakeStrictRedis(
-            decode_responses=True
-        )
-
-    def _get_redis(self):
-        """Get fakeredis connection."""
-        return self.redis_client
-
-    async def get(self, key: str, metadata: dict | None = None):
-        """
-        Gets a value from fake Redis by key.
-
-        Args:
-            key: Key of the value to retrieve
-            metadata: Optional dictionary with additional metadata
-
-        Return:
-            Deserialized value from Redis or None if not found
-        """
-        redis = self._get_redis()
-        try:
-            history = redis.get(key)
-            return json.loads(history) if history else None
-        except Exception as e:
-            self.error(f'Error getting data from fake redis: {e}', metadata or {})
-            raise e
-
-    async def set(
-        self,
-        key: str,
-        data: dict,
-        ttl: int = 600,
-        nx: bool = False,
-        metadata: dict | None = None,
-    ) -> bool:
-        """
-        Sets a value in fake Redis with optional TTL.
-
-        Args:
-            key: Key of the value to set
-            data: Dictionary with data to store
-            ttl: Time to live in seconds (default: 600)
-            nx: If True, only sets if key doesn't exist (default: False)
-            metadata: Optional dictionary with additional metadata
-
-        Return:
-            True if value was set, False otherwise
-        """
-        redis = self._get_redis()
-        try:
-            result = redis.set(
-                key, json.dumps(data), ex=ttl, nx=nx
-            )
-            return bool(result)
-        except Exception as e:
-            self.error(f'Error setting data in fake redis: {e}', metadata or {})
-            raise e
-
-    async def delete(self, key: str, metadata: dict | None = None):
-        """
-        Removes a key from fake Redis.
-
-        Args:
-            key: Key to be removed
-            metadata: Optional dictionary with additional metadata
-        """
-        redis = self._get_redis()
-        try:
-            redis.delete(key)
-        except Exception as e:
-            self.error(f'Error deleting data from fake redis: {e}', metadata or {})
-            raise e
-
-    async def expire(self, key: str, ttl: int, metadata: dict | None = None):
-        """
-        Sets the time to live (TTL) of an existing Redis key.
-
-        Args:
-            key: Key whose TTL will be set
-            ttl: Time to live in seconds
-            metadata: Optional dictionary with additional metadata
-        """
-        redis = self._get_redis()
-        try:
-            redis.expire(key, ttl)
-        except Exception as e:
-            self.error(f'Error expiring data from fake redis: {e}', metadata or {})
-            raise e
-
-    async def keys(self, pattern: str, metadata: dict | None = None):
-        """
-        Gets all keys matching the specified pattern.
-
-        Args:
-            pattern: Search pattern for keys
-            metadata: Optional dictionary with additional metadata
-
-        Return:
-            List of keys matching the pattern
-        """
-        redis = self._get_redis()
-        try:
-            keys = redis.keys(pattern)
-            return keys
-        except Exception as e:
-            self.error(f'Error getting keys from fake redis: {e}', metadata or {})
-            raise e
-
-    def close(self):
-        """
-        Closes fake Redis connection and shuts down monitoring.
-        """
-        if self.redis_client:
-            self.redis_client.close()
-        SientiaMonitoring.shutdown(self)
-

e2e/helpers.py

@@ -0,0 +1,404 @@
+"""
+Shared helpers for Scouter end-to-end tests.
+"""
+
+from __future__ import annotations
+
+import json
+import re
+import uuid
+from datetime import UTC, datetime, timedelta
+from pathlib import Path
+from typing import Any
+from urllib.parse import urlparse
+
+from pymongo import MongoClient
+from redis import Redis
+from sientia_do.temporal.constants import DATETIME_FORMAT_MS_WITH_TZ
+from sqlalchemy import create_engine, text
+from sqlalchemy.engine import Engine
+from temporalio.client import Client
+
+SCENARIO_INPUTS_DIR = Path(__file__).resolve().parent / 'scenario_inputs'
+SCOUTER_TASK_QUEUE = 'scouter-test-queue'
+
+_NOW_MARKER = re.compile(r'^@now(?:([+-])(\d+)([smhd]))?$')
+
+
+def _resolve_timestamp_marker(value: str) -> datetime:
+    """
+    Resolve @now relative timestamp markers to timezone-aware datetimes.
+
+    Args:
+        - value: Marker string such as @now, @now-1h, or @now+30m
+
+    Return:
+        Resolved datetime in UTC
+    """
+    match = _NOW_MARKER.match(value.strip())
+    if not match:
+        raise ValueError(f'Invalid timestamp marker: {value}')
+
+    now = datetime.now(UTC)
+    if match.group(1) is None:
+        return now
+
+    sign, amount, unit = match.group(1), int(match.group(2)), match.group(3)
+    delta_kwargs = {'seconds': 0, 'minutes': 0, 'hours': 0, 'days': 0}
+    if unit == 's':
+        delta_kwargs['seconds'] = amount
+    elif unit == 'm':
+        delta_kwargs['minutes'] = amount
+    elif unit == 'h':
+        delta_kwargs['hours'] = amount
+    elif unit == 'd':
+        delta_kwargs['days'] = amount
+
+    delta = timedelta(**delta_kwargs)
+    return now - delta if sign == '-' else now + delta
+
+
+def _resolve_payload(node: Any) -> Any:
+    """
+    Recursively resolve @now markers inside JSON-loaded structures.
+
+    Args:
+        - node: JSON node (dict, list, or scalar)
+
+    Return:
+        Structure with markers replaced by datetimes or formatted strings
+    """
+    if isinstance(node, dict):
+        return {key: _resolve_payload(value) for key, value in node.items()}
+    if isinstance(node, list):
+        return [_resolve_payload(item) for item in node]
+    if isinstance(node, str) and node.startswith('@now'):
+        resolved = _resolve_timestamp_marker(node)
+        return resolved.strftime('%Y-%m-%d %H:%M:%S.%f%z')
+    return node
+
+
+def load_scenario_input(name: str, **overrides: Any) -> dict[str, Any]:
+    """
+    Load a scenario JSON file and apply optional overrides.
+
+    Args:
+        - name: Scenario slug with or without .json suffix
+        - overrides: Top-level keys merged into the loaded document
+
+    Return:
+        Parsed scenario document with @now markers resolved
+    """
+    slug = name.removesuffix('.json')
+    path = SCENARIO_INPUTS_DIR / f'{slug}.json'
+    with path.open(encoding='utf-8') as handle:
+        payload = json.load(handle)
+    resolved = _resolve_payload(payload)
+    if overrides:
+        resolved.update(overrides)
+    return resolved
+
+
+def make_workflow_id(prefix: str) -> str:
+    """
+    Build a unique Temporal workflow id for E2E runs.
+
+    Args:
+        - prefix: Human-readable prefix for the workflow id
+
+    Return:
+        Unique workflow id string
+    """
+    return f'{prefix}-{uuid.uuid4().hex[:12]}'
+
+
+async def start_and_await_workflow(
+    client: Client,
+    workflow_run: Any,
+    input_data: dict[str, Any],
+    workflow_id: str,
+    *,
+    task_queue: str = SCOUTER_TASK_QUEUE,
+    timeout: float = 300.0,
+) -> Any:
+    """
+    Start a workflow on the E2E task queue and await its result.
+
+    Args:
+        - client: Temporal client from WorkflowEnvironment
+        - workflow_run: Workflow run method (e.g. Scouter.run)
+        - input_data: Workflow input payload
+        - workflow_id: Unique workflow id
+        - task_queue: Task queue name
+        - timeout: Maximum seconds to wait for completion
+
+    Return:
+        Workflow result (None for Scouter-family workflows)
+    """
+    return await client.execute_workflow(
+        workflow_run,
+        input_data,
+        id=workflow_id,
+        task_queue=task_queue,
+        execution_timeout=timedelta(seconds=timeout),
+    )
+
+
+def _coerce_mongo_document(document: dict[str, Any]) -> dict[str, Any]:
+    """
+    Convert string timestamps in seed documents to BSON datetimes for Mongo filters.
+
+    Args:
+        - document: Raw document dict from scenario JSON
+
+    Return:
+        Document with inserted_at as datetime when present
+    """
+    doc = dict(document)
+    inserted_at = doc.get('inserted_at')
+    if isinstance(inserted_at, str):
+        doc['inserted_at'] = datetime.strptime(inserted_at, DATETIME_FORMAT_MS_WITH_TZ).replace(
+            tzinfo=UTC
+        )
+    return doc
+
+
+def seed_raw_collection(
+    mongo_uri: str,
+    database: str,
+    schedule_name: str,
+    documents: list[dict[str, Any]],
+) -> None:
+    """
+    Insert raw Mongo documents into raw_<schedule_name>.
+
+    Args:
+        - mongo_uri: MongoDB connection string
+        - database: Database name
+        - schedule_name: Schedule slug used in collection name
+        - documents: Documents to insert
+    """
+    collection_name = f'raw_{schedule_name}'
+    client = MongoClient(mongo_uri)
+    try:
+        collection = client[database][collection_name]
+        if documents:
+            collection.insert_many([_coerce_mongo_document(doc) for doc in documents])
+    finally:
+        client.close()
+
+
+def seed_last_data_timestamp(
+    redis_client: Redis,
+    workflow_name: str,
+    schedule_name: str,
+    value: str,
+) -> None:
+    """
+    Pre-seed last_data_timestamp Redis key the same way RedisRepository.set stores strings.
+
+    Args:
+        - redis_client: Connected Redis client
+        - workflow_name: Workflow name segment in the key
+        - schedule_name: Schedule name segment in the key
+        - value: Timestamp string to store
+    """
+    key = f'last_data_timestamp:{workflow_name}:{schedule_name}'
+    redis_client.set(key, json.dumps(value))
+
+
+def count_laborious_rows(engine: Engine, model_id: str | int | None = None) -> int:
+    """
+    Count rows in sientia_data.laborious_data, optionally filtered by model_id.
+
+    Args:
+        - engine: SQLAlchemy engine bound to the Postgres testcontainer
+        - model_id: Optional model id filter
+
+    Return:
+        Row count
+    """
+    query = 'SELECT COUNT(*) FROM sientia_data.laborious_data'
+    params: dict[str, Any] = {}
+    if model_id is not None:
+        query += ' WHERE model_id = :model_id'
+        params['model_id'] = int(model_id)
+
+    with engine.connect() as conn:
+        return conn.execute(text(query), params).scalar() or 0
+
+
+def fetch_laborious_rows(engine: Engine, model_id: str | int | None = None) -> list[dict[str, Any]]:
+    """
+    Fetch laborious_data rows as plain dicts.
+
+    Args:
+        - engine: SQLAlchemy engine bound to the Postgres testcontainer
+        - model_id: Optional model id filter
+
+    Return:
+        List of row dicts with variable and value keys
+    """
+    query = 'SELECT model_id, variable, value, timestamp FROM sientia_data.laborious_data'
+    params: dict[str, Any] = {}
+    if model_id is not None:
+        query += ' WHERE model_id = :model_id'
+        params['model_id'] = int(model_id)
+    query += ' ORDER BY variable'
+
+    with engine.connect() as conn:
+        rows = conn.execute(text(query), params).mappings().all()
+    return [dict(row) for row in rows]
+
+
+def count_held_data_keys(redis_client: Redis) -> int:
+    """
+    Count Redis keys matching held_data_*.
+
+    Args:
+        - redis_client: Connected Redis client
+
+    Return:
+        Number of matching keys
+    """
+    return len(redis_client.keys('held_data_*'))
+
+
+def count_notifications(
+    mongo_uri: str,
+    database: str,
+    *,
+    notification_id: str | None = None,
+    level: str | None = None,
+) -> int:
+    """
+    Count notification documents in the E2E notification collection.
+
+    Args:
+        - mongo_uri: MongoDB connection string
+        - database: Database name
+        - notification_id: Optional notification_id filter
+        - level: Optional level filter (WARNING, ERROR, ...)
+
+    Return:
+        Matching document count
+    """
+    client = MongoClient(mongo_uri)
+    try:
+        collection = client[database]['notification_queue']
+        query: dict[str, Any] = {}
+        if notification_id:
+            query['notification_id'] = notification_id
+        if level:
+            query['level'] = level
+        return collection.count_documents(query)
+    finally:
+        client.close()
+
+
+def default_model_tags(
+    *,
+    names: list[str],
+    aggr: str = 'avg',
+    data_range: list[float] | None = None,
+    frequency: int = 60000,
+) -> dict[str, dict[str, Any]]:
+    """
+    Build a minimal model_tags map for E2E scenarios.
+
+    Args:
+        - names: Tag names to include
+        - aggr: Aggregation function (aggr_func field)
+        - data_range: Optional [min, max] validation range
+        - frequency: Collection frequency in milliseconds
+
+    Return:
+        model_tags dict keyed by tag name
+    """
+    if data_range is None:
+        data_range = [0, 100]
+    return {
+        name: {
+            'webid': f'webid_{name}',
+            'aggr_func': aggr,
+            'data_range': data_range,
+            'frequency': frequency,
+        }
+        for name in names
+    }
+
+
+def default_scouter_input(
+    *,
+    model_id: str = '1',
+    model_name: str = 'Test Model',
+    schedule_name: str = 'test-schedule',
+    workflow_name: str = 'scouter',
+    **overrides: Any,
+) -> dict[str, Any]:
+    """
+    Return a base workflow input dict for Scouter / CoreScouter E2E runs.
+
+    Args:
+        - model_id: Model identifier
+        - model_name: Human-readable model name
+        - schedule_name: Schedule slug
+        - workflow_name: Parent workflow name
+        - overrides: Additional keys merged into the payload
+
+    Return:
+        Workflow input dictionary
+    """
+    payload: dict[str, Any] = {
+        'topic': 'e2e-topic',
+        'model_id': model_id,
+        'model_name': model_name,
+        'schedule_name': schedule_name,
+        'workflow_name': workflow_name,
+        'trigger_laborious': False,
+        'filters': {},
+        'schema': 'sientia_data',
+        'table_name': 'laborious_data',
+        'retention_time': 3600,
+        'fill_missing_tags': False,
+        'model_tags': default_model_tags(names=['tag1']),
+    }
+    payload.update(overrides)
+    return payload
+
+
+def apply_pi_web_api_server_config(server: Any, config: dict[str, Any] | None) -> None:
+    """
+    Configure the in-process PI Web API stub from a scenario pi_web_api_server block.
+
+    Args:
+        - server: PIWebAPITestServer instance
+        - config: Optional mode/rows/timeout_sleep_seconds dict from scenario JSON
+    """
+    if not config:
+        return
+    server.set_mode(
+        config.get('mode', 'success'),
+        rows=config.get('rows'),
+        timeout_sleep_seconds=config.get('timeout_sleep_seconds', 60),
+    )
+
+
+def postgres_connection_parts(connection_url: str) -> dict[str, Any]:
+    """
+    Parse a SQLAlchemy Postgres URL into Activities postgres_config fields.
+
+    Args:
+        - connection_url: SQLAlchemy connection URL from testcontainers
+
+    Return:
+        Dict with host, port, user, password, dbname keys
+    """
+    parsed = urlparse(connection_url)
+    return {
+        'host': parsed.hostname or 'localhost',
+        'port': parsed.port or 5432,
+        'user': parsed.username or 'test',
+        'password': parsed.password or 'test',
+        'dbname': (parsed.path or '/test').lstrip('/'),
+    }

e2e/pi_web_api_test_server.py

@@ -0,0 +1,124 @@
+"""
+In-process HTTP server emulating PI Web API streamsets/recorded responses for E2E tests.
+"""
+
+from __future__ import annotations
+
+import json
+import time
+from typing import Any, Literal
+
+from pytest_httpserver import HTTPServer
+from werkzeug import Request
+from werkzeug.wrappers import Response
+
+PIWebAPIMode = Literal['success', 'empty', 'error', 'timeout']
+STREAMSETS_RECORDED_PATH = '/streamsets/recorded'
+
+
+class PIWebAPITestServer:
+    """
+    Thread-backed PI Web API stub using pytest-httpserver (real HTTP for pycurl clients).
+    """
+
+    def __init__(self) -> None:
+        self._httpserver = HTTPServer(host='127.0.0.1', port=0)
+        self._mode: PIWebAPIMode = 'success'
+        self._rows: list[dict[str, Any]] = []
+        self._timeout_sleep_seconds = 60
+        self.requests: list[Request] = []
+
+    @property
+    def host(self) -> str:
+        return self._httpserver.host
+
+    @property
+    def port(self) -> int:
+        return self._httpserver.port
+
+    @property
+    def base_url(self) -> str:
+        return f'http://{self.host}:{self.port}'
+
+    def start(self) -> None:
+        """Start the HTTP server and register the streamsets handler."""
+        self._httpserver.start()
+        self._register_handler()
+
+    def stop(self) -> None:
+        """Stop the HTTP server."""
+        self._httpserver.stop()
+
+    def clear(self) -> None:
+        """Clear recorded requests and reset mode to success with no rows."""
+        self.requests.clear()
+        self._mode = 'success'
+        self._rows = []
+        self._httpserver.clear()
+        self._register_handler()
+
+    def set_mode(
+        self,
+        mode: PIWebAPIMode,
+        rows: list[dict[str, Any]] | None = None,
+        *,
+        timeout_sleep_seconds: int = 60,
+    ) -> None:
+        """
+        Configure the next responses from the stub server.
+
+        Args:
+            - mode: Response mode (success, empty, error, timeout)
+            - rows: Optional list of row dicts with keys name, webid, timestamp, value
+            - timeout_sleep_seconds: Sleep duration for timeout mode (must exceed client timeout)
+        """
+        self._mode = mode
+        if rows is not None:
+            self._rows = rows
+        self._timeout_sleep_seconds = timeout_sleep_seconds
+        self._register_handler()
+
+    def _register_handler(self) -> None:
+        self._httpserver.expect_request(
+            STREAMSETS_RECORDED_PATH,
+            method='GET',
+        ).respond_with_handler(self._handle_streamsets_recorded)
+
+    def _handle_streamsets_recorded(self, request: Request):
+        self.requests.append(request)
+
+        if self._mode == 'timeout':
+            time.sleep(self._timeout_sleep_seconds)
+            return self._json_response({'Items': []}, status=200)
+
+        if self._mode == 'error':
+            return self._json_response({'error': 'internal'}, status=500)
+
+        if self._mode == 'empty' or not self._rows:
+            return self._json_response({'Items': []}, status=200)
+
+        items_by_name: dict[str, list[dict[str, Any]]] = {}
+        for row in self._rows:
+            name = row['name']
+            items_by_name.setdefault(name, []).append(
+                {
+                    'Timestamp': row['timestamp'],
+                    'Value': row['value'],
+                    'Good': True,
+                    'Questionable': False,
+                }
+            )
+
+        items = [
+            {'Name': name, 'Items': points}
+            for name, points in items_by_name.items()
+        ]
+        return self._json_response({'Items': items}, status=200)
+
+    @staticmethod
+    def _json_response(payload: dict[str, Any], *, status: int) -> Response:
+        return Response(
+            json.dumps(payload),
+            status=status,
+            mimetype='application/json',
+        )

e2e/scenario_inputs/core_scouter_aggregation_avg.json

@@ -0,0 +1,24 @@
+{
+  "workflow_input": {
+    "metadata": {"metadata": {"model_id": "24", "model_name": "Core Avg", "schedule_name": "core-avg", "workflow_name": "pi_web_api_scouter"}},
+    "workflow_name": "pi_web_api_scouter",
+    "schedule_name": "core-avg",
+    "model_name": "Core Avg",
+    "model_id": "24",
+    "data": [
+      {"timestamp": "2024-01-01 12:00:00+0000", "name": "tag_avg", "value": 10.0, "tag": "w1"},
+      {"timestamp": "2024-01-01 12:01:00+0000", "name": "tag_avg", "value": 20.0, "tag": "w1"},
+      {"timestamp": "2024-01-01 12:02:00+0000", "name": "tag_avg", "value": 30.0, "tag": "w1"}
+    ],
+    "trigger_laborious": false,
+    "filters": {},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": false,
+    "model_tags": {
+      "tag_avg": {"webid": "w1", "aggr_func": "avg", "data_range": [0, 1000], "frequency": 60000}
+    }
+  },
+  "expected_value": 20.0
+}

e2e/scenario_inputs/core_scouter_aggregation_lts.json

@@ -0,0 +1,24 @@
+{
+  "workflow_input": {
+    "metadata": {"metadata": {"model_id": "28", "model_name": "Core Lts", "schedule_name": "core-lts", "workflow_name": "pi_web_api_scouter"}},
+    "workflow_name": "pi_web_api_scouter",
+    "schedule_name": "core-lts",
+    "model_name": "Core Lts",
+    "model_id": "28",
+    "data": [
+      {"timestamp": "2024-01-01 12:00:00+0000", "name": "tag_lts", "value": 100.0, "tag": "w1"},
+      {"timestamp": "2024-01-01 12:01:00+0000", "name": "tag_lts", "value": 200.0, "tag": "w1"},
+      {"timestamp": "2024-01-01 12:02:00+0000", "name": "tag_lts", "value": 300.0, "tag": "w1"}
+    ],
+    "trigger_laborious": false,
+    "filters": {},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": false,
+    "model_tags": {
+      "tag_lts": {"webid": "w1", "aggr_func": "lts", "data_range": [0, 1000], "frequency": 60000}
+    }
+  },
+  "expected_value": 300.0
+}

e2e/scenario_inputs/core_scouter_aggregation_max.json

@@ -0,0 +1,24 @@
+{
+  "workflow_input": {
+    "metadata": {"metadata": {"model_id": "26", "model_name": "Core Max", "schedule_name": "core-max", "workflow_name": "pi_web_api_scouter"}},
+    "workflow_name": "pi_web_api_scouter",
+    "schedule_name": "core-max",
+    "model_name": "Core Max",
+    "model_id": "26",
+    "data": [
+      {"timestamp": "2024-01-01 12:00:00+0000", "name": "tag_max", "value": 5.0, "tag": "w1"},
+      {"timestamp": "2024-01-01 12:01:00+0000", "name": "tag_max", "value": 15.0, "tag": "w1"},
+      {"timestamp": "2024-01-01 12:02:00+0000", "name": "tag_max", "value": 10.0, "tag": "w1"}
+    ],
+    "trigger_laborious": false,
+    "filters": {},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": false,
+    "model_tags": {
+      "tag_max": {"webid": "w1", "aggr_func": "max", "data_range": [0, 1000], "frequency": 60000}
+    }
+  },
+  "expected_value": 15.0
+}

e2e/scenario_inputs/core_scouter_aggregation_mdn.json

@@ -0,0 +1,24 @@
+{
+  "workflow_input": {
+    "metadata": {"metadata": {"model_id": "25", "model_name": "Core Mdn", "schedule_name": "core-mdn", "workflow_name": "pi_web_api_scouter"}},
+    "workflow_name": "pi_web_api_scouter",
+    "schedule_name": "core-mdn",
+    "model_name": "Core Mdn",
+    "model_id": "25",
+    "data": [
+      {"timestamp": "2024-01-01 12:00:00+0000", "name": "tag_mdn", "value": 1.0, "tag": "w1"},
+      {"timestamp": "2024-01-01 12:01:00+0000", "name": "tag_mdn", "value": 9.0, "tag": "w1"},
+      {"timestamp": "2024-01-01 12:02:00+0000", "name": "tag_mdn", "value": 5.0, "tag": "w1"}
+    ],
+    "trigger_laborious": false,
+    "filters": {},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": false,
+    "model_tags": {
+      "tag_mdn": {"webid": "w1", "aggr_func": "mdn", "data_range": [0, 1000], "frequency": 60000}
+    }
+  },
+  "expected_value": 5.0
+}

e2e/scenario_inputs/core_scouter_aggregation_min.json

@@ -0,0 +1,24 @@
+{
+  "workflow_input": {
+    "metadata": {"metadata": {"model_id": "27", "model_name": "Core Min", "schedule_name": "core-min", "workflow_name": "pi_web_api_scouter"}},
+    "workflow_name": "pi_web_api_scouter",
+    "schedule_name": "core-min",
+    "model_name": "Core Min",
+    "model_id": "27",
+    "data": [
+      {"timestamp": "2024-01-01 12:00:00+0000", "name": "tag_min", "value": 50.0, "tag": "w1"},
+      {"timestamp": "2024-01-01 12:01:00+0000", "name": "tag_min", "value": 30.0, "tag": "w1"},
+      {"timestamp": "2024-01-01 12:02:00+0000", "name": "tag_min", "value": 40.0, "tag": "w1"}
+    ],
+    "trigger_laborious": false,
+    "filters": {},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": false,
+    "model_tags": {
+      "tag_min": {"webid": "w1", "aggr_func": "min", "data_range": [0, 1000], "frequency": 60000}
+    }
+  },
+  "expected_value": 30.0
+}

e2e/scenario_inputs/core_scouter_debug_data_package.json

@@ -0,0 +1,22 @@
+{
+  "workflow_input": {
+    "metadata": {"metadata": {"model_id": "30", "model_name": "Core Debug", "schedule_name": "core-debug", "workflow_name": "subworkflow.core_scouter"}},
+    "workflow_name": "subworkflow.core_scouter",
+    "schedule_name": "core-debug",
+    "model_name": "Core Debug",
+    "model_id": "30",
+    "data": [
+      {"timestamp": "2024-01-01 12:00:00+0000", "name": "tag1", "value": 11.0, "tag": "webid1"}
+    ],
+    "trigger_laborious": false,
+    "filters": {},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": false,
+    "debug_data_package": true,
+    "model_tags": {
+      "tag1": {"webid": "webid1", "aggr_func": "avg", "data_range": [0, 100], "frequency": 60000}
+    }
+  }
+}

e2e/scenario_inputs/core_scouter_empty_after_grouping.json

@@ -0,0 +1,24 @@
+{
+  "workflow_input": {
+    "metadata": {"metadata": {"model_id": "31", "model_name": "Core Empty Group", "schedule_name": "core-empty-group", "workflow_name": "pi_web_api_scouter"}},
+    "workflow_name": "pi_web_api_scouter",
+    "schedule_name": "core-empty-group",
+    "model_name": "Core Empty Group",
+    "model_id": "31",
+    "data": {
+      "timestamp": [],
+      "name": [],
+      "value": [],
+      "tag": []
+    },
+    "trigger_laborious": false,
+    "filters": {},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": false,
+    "model_tags": {
+      "tag1": {"webid": "webid1", "aggr_func": "avg", "data_range": [0, 100], "frequency": 60000}
+    }
+  }
+}

e2e/scenario_inputs/core_scouter_fill_missing_tags.json

@@ -0,0 +1,24 @@
+{
+  "workflow_input": {
+    "metadata": {"metadata": {"model_id": "29", "model_name": "Core Fill Tags", "schedule_name": "core-fill", "workflow_name": "pi_web_api_scouter"}},
+    "workflow_name": "pi_web_api_scouter",
+    "schedule_name": "core-fill",
+    "model_name": "Core Fill Tags",
+    "model_id": "29",
+    "data": [
+      {"timestamp": "2024-01-01 12:00:00+0000", "name": "tag1", "value": 10.0, "tag": "webid1"}
+    ],
+    "trigger_laborious": false,
+    "filters": {},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": true,
+    "model_tags": {
+      "tag1": {"webid": "webid1", "aggr_func": "avg", "data_range": [0, 100], "frequency": 60000},
+      "tag2": {"webid": "webid2", "aggr_func": "avg", "data_range": [0, 100], "frequency": 60000},
+      "tag3": {"webid": "webid3", "aggr_func": "avg", "data_range": [0, 100], "frequency": 60000}
+    }
+  },
+  "expected_missing_tags": ["tag2", "tag3"]
+}

e2e/scenario_inputs/core_scouter_happy_path.json

@@ -0,0 +1,28 @@
+{
+  "workflow_input": {
+    "metadata": {
+      "metadata": {
+        "model_id": "20",
+        "model_name": "Core Happy",
+        "schedule_name": "core-happy",
+        "workflow_name": "pi_web_api_scouter"
+      }
+    },
+    "workflow_name": "pi_web_api_scouter",
+    "schedule_name": "core-happy",
+    "model_name": "Core Happy",
+    "model_id": "20",
+    "data": [
+      {"timestamp": "2024-01-01 12:00:00+0000", "name": "tag1", "value": 10.5, "tag": "webid1"}
+    ],
+    "trigger_laborious": false,
+    "filters": {},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": false,
+    "model_tags": {
+      "tag1": {"webid": "webid1", "aggr_func": "avg", "data_range": [0, 100], "frequency": 60000}
+    }
+  }
+}

e2e/scenario_inputs/core_scouter_invalid_aggregation.json

@@ -0,0 +1,23 @@
+{
+  "workflow_input": {
+    "metadata": {"metadata": {"model_id": "32", "model_name": "Core Bad Aggr", "schedule_name": "core-bad-aggr", "workflow_name": "pi_web_api_scouter"}},
+    "workflow_name": "pi_web_api_scouter",
+    "schedule_name": "core-bad-aggr",
+    "model_name": "Core Bad Aggr",
+    "model_id": "32",
+    "data": [
+      {"timestamp": "2024-01-01 12:00:00+0000", "name": "tag_ok", "value": 10.0, "tag": "w1"},
+      {"timestamp": "2024-01-01 12:00:00+0000", "name": "tag_bad", "value": 20.0, "tag": "w2"}
+    ],
+    "trigger_laborious": false,
+    "filters": {},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": false,
+    "model_tags": {
+      "tag_ok": {"webid": "w1", "aggr_func": "avg", "data_range": [0, 100], "frequency": 60000},
+      "tag_bad": {"webid": "w2", "aggr_func": "bogus", "data_range": [0, 100], "frequency": 60000}
+    }
+  }
+}

e2e/scenario_inputs/core_scouter_null_values_filter_discard.json

@@ -0,0 +1,23 @@
+{
+  "workflow_input": {
+    "metadata": {"metadata": {"model_id": "21", "model_name": "Core Null Discard", "schedule_name": "core-null-discard", "workflow_name": "pi_web_api_scouter"}},
+    "workflow_name": "pi_web_api_scouter",
+    "schedule_name": "core-null-discard",
+    "model_name": "Core Null Discard",
+    "model_id": "21",
+    "data": [
+      {"timestamp": "2024-01-01 12:00:00+0000", "name": "tag1", "value": null, "tag": "webid1"},
+      {"timestamp": "2024-01-01 12:00:00+0000", "name": "tag2", "value": 50.0, "tag": "webid2"}
+    ],
+    "trigger_laborious": false,
+    "filters": {"NULL_VALUES_FILTER": {"policy": "DISCARD"}},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": false,
+    "model_tags": {
+      "tag1": {"webid": "webid1", "aggr_func": "avg", "data_range": [0, 100], "frequency": 60000},
+      "tag2": {"webid": "webid2", "aggr_func": "avg", "data_range": [0, 100], "frequency": 60000}
+    }
+  }
+}

e2e/scenario_inputs/core_scouter_null_values_filter_warn.json

@@ -0,0 +1,23 @@
+{
+  "workflow_input": {
+    "metadata": {"metadata": {"model_id": "22", "model_name": "Core Null Warn", "schedule_name": "core-null-warn", "workflow_name": "pi_web_api_scouter"}},
+    "workflow_name": "pi_web_api_scouter",
+    "schedule_name": "core-null-warn",
+    "model_name": "Core Null Warn",
+    "model_id": "22",
+    "data": [
+      {"timestamp": "2024-01-01 12:00:00+0000", "name": "tag1", "value": null, "tag": "webid1"},
+      {"timestamp": "2024-01-01 12:00:00+0000", "name": "tag2", "value": 50.0, "tag": "webid2"}
+    ],
+    "trigger_laborious": false,
+    "filters": {"NULL_VALUES_FILTER": {"policy": "WARN"}},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": false,
+    "model_tags": {
+      "tag1": {"webid": "webid1", "aggr_func": "avg", "data_range": [0, 100], "frequency": 60000},
+      "tag2": {"webid": "webid2", "aggr_func": "avg", "data_range": [0, 100], "frequency": 60000}
+    }
+  }
+}

e2e/scenario_inputs/core_scouter_out_of_bounds_filter_discard.json

@@ -0,0 +1,23 @@
+{
+  "workflow_input": {
+    "metadata": {"metadata": {"model_id": "23", "model_name": "Core OOB Discard", "schedule_name": "core-oob-discard", "workflow_name": "pi_web_api_scouter"}},
+    "workflow_name": "pi_web_api_scouter",
+    "schedule_name": "core-oob-discard",
+    "model_name": "Core OOB Discard",
+    "model_id": "23",
+    "data": [
+      {"timestamp": "2024-01-01 12:00:00+0000", "name": "tag1", "value": 150.0, "tag": "webid1"},
+      {"timestamp": "2024-01-01 12:00:00+0000", "name": "tag2", "value": 50.0, "tag": "webid2"}
+    ],
+    "trigger_laborious": false,
+    "filters": {"OUT_OF_BOUNDS_FILTER": {"policy": "DISCARD"}},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": false,
+    "model_tags": {
+      "tag1": {"webid": "webid1", "aggr_func": "avg", "data_range": [0, 100], "frequency": 60000},
+      "tag2": {"webid": "webid2", "aggr_func": "avg", "data_range": [0, 100], "frequency": 60000}
+    }
+  }
+}

e2e/scenario_inputs/core_scouter_postgres_export_failure.json

@@ -0,0 +1,21 @@
+{
+  "workflow_input": {
+    "metadata": {"metadata": {"model_id": "33", "model_name": "Core PG Fail", "schedule_name": "core-pg-fail", "workflow_name": "pi_web_api_scouter"}},
+    "workflow_name": "pi_web_api_scouter",
+    "schedule_name": "core-pg-fail",
+    "model_name": "Core PG Fail",
+    "model_id": "33",
+    "data": [
+      {"timestamp": "2024-01-01 12:00:00+0000", "name": "tag1", "value": 10.0, "tag": "webid1"}
+    ],
+    "trigger_laborious": false,
+    "filters": {},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": false,
+    "model_tags": {
+      "tag1": {"webid": "webid1", "aggr_func": "avg", "data_range": [0, 100], "frequency": 60000}
+    }
+  }
+}

e2e/scenario_inputs/pi_web_api_scouter_connection_error.json

@@ -0,0 +1,23 @@
+{
+  "workflow_input": {
+    "model_id": "14",
+    "model_name": "PI Error",
+    "schedule_name": "pi-error",
+    "trigger_laborious": false,
+    "filters": {},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": false,
+    "model_tags": {
+      "tag1": {"webid": "webid1", "aggr_func": "avg", "data_range": [0, 100], "frequency": 60000}
+    },
+    "pi_web_api_query": {
+      "endpoint": "/streamsets/recorded",
+      "period": "*-1d",
+      "max_count": 1,
+      "api_timeout": 30
+    }
+  },
+  "pi_web_api_server": {"mode": "error"}
+}

e2e/scenario_inputs/pi_web_api_scouter_debug_data_package.json

@@ -0,0 +1,29 @@
+{
+  "workflow_input": {
+    "model_id": "12",
+    "model_name": "PI Debug Package",
+    "schedule_name": "pi-debug",
+    "trigger_laborious": false,
+    "filters": {},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": false,
+    "debug_data_package": true,
+    "model_tags": {
+      "tag1": {"webid": "webid1", "aggr_func": "avg", "data_range": [0, 100], "frequency": 60000}
+    },
+    "pi_web_api_query": {
+      "endpoint": "/streamsets/recorded",
+      "period": "*-1d",
+      "max_count": 5,
+      "api_timeout": 30
+    }
+  },
+  "pi_web_api_server": {
+    "mode": "success",
+    "rows": [
+      {"name": "tag1", "timestamp": "2024-06-01T12:00:00Z", "value": 7.5}
+    ]
+  }
+}

e2e/scenario_inputs/pi_web_api_scouter_empty_response.json

@@ -0,0 +1,23 @@
+{
+  "workflow_input": {
+    "model_id": "13",
+    "model_name": "PI Empty",
+    "schedule_name": "pi-empty",
+    "trigger_laborious": false,
+    "filters": {},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": false,
+    "model_tags": {
+      "tag1": {"webid": "webid1", "aggr_func": "avg", "data_range": [0, 100], "frequency": 60000}
+    },
+    "pi_web_api_query": {
+      "endpoint": "/streamsets/recorded",
+      "period": "*-1d",
+      "max_count": 1,
+      "api_timeout": 30
+    }
+  },
+  "pi_web_api_server": {"mode": "empty"}
+}

e2e/scenario_inputs/pi_web_api_scouter_happy_path.json

@@ -0,0 +1,30 @@
+{
+  "workflow_input": {
+    "model_id": "10",
+    "model_name": "PI Web API Happy",
+    "schedule_name": "pi-happy",
+    "trigger_laborious": false,
+    "filters": {},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": false,
+    "model_tags": {
+      "tag1": {"webid": "webid1", "aggr_func": "avg", "data_range": [0, 100], "frequency": 60000},
+      "tag2": {"webid": "webid2", "aggr_func": "avg", "data_range": [0, 100], "frequency": 60000}
+    },
+    "pi_web_api_query": {
+      "endpoint": "/streamsets/recorded",
+      "period": "*-1d",
+      "max_count": 10,
+      "api_timeout": 30
+    }
+  },
+  "pi_web_api_server": {
+    "mode": "success",
+    "rows": [
+      {"name": "tag1", "timestamp": "2024-06-01T12:00:00Z", "value": 10.5},
+      {"name": "tag2", "timestamp": "2024-06-01T12:00:00Z", "value": 20.3}
+    ]
+  }
+}

e2e/scenario_inputs/pi_web_api_scouter_invalid_endpoint.json

@@ -0,0 +1,23 @@
+{
+  "workflow_input": {
+    "model_id": "16",
+    "model_name": "PI Invalid Endpoint",
+    "schedule_name": "pi-invalid",
+    "trigger_laborious": false,
+    "filters": {},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": false,
+    "model_tags": {
+      "tag1": {"webid": "webid1", "aggr_func": "avg", "data_range": [0, 100], "frequency": 60000}
+    },
+    "pi_web_api_query": {
+      "endpoint": "/invalid/endpoint",
+      "period": "*-1d",
+      "max_count": 1,
+      "api_timeout": 30
+    }
+  },
+  "pi_web_api_server": {"mode": "success", "rows": []}
+}

e2e/scenario_inputs/pi_web_api_scouter_multiple_tags.json

@@ -0,0 +1,53 @@
+{
+  "workflow_input": {
+    "model_id": "11",
+    "model_name": "PI Multi Tag",
+    "schedule_name": "pi-multi",
+    "trigger_laborious": false,
+    "filters": {},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": false,
+    "model_tags": {
+      "tag_avg": {"webid": "w1", "aggr_func": "avg", "data_range": [0, 1000], "frequency": 60000},
+      "tag_mdn": {"webid": "w2", "aggr_func": "mdn", "data_range": [0, 1000], "frequency": 60000},
+      "tag_max": {"webid": "w3", "aggr_func": "max", "data_range": [0, 1000], "frequency": 60000},
+      "tag_min": {"webid": "w4", "aggr_func": "min", "data_range": [0, 1000], "frequency": 60000},
+      "tag_lts": {"webid": "w5", "aggr_func": "lts", "data_range": [0, 1000], "frequency": 60000}
+    },
+    "pi_web_api_query": {
+      "endpoint": "/streamsets/recorded",
+      "period": "*-1d",
+      "max_count": 3,
+      "api_timeout": 30
+    }
+  },
+  "pi_web_api_server": {
+    "mode": "success",
+    "rows": [
+      {"name": "tag_avg", "timestamp": "2024-06-01T12:00:00Z", "value": 10},
+      {"name": "tag_avg", "timestamp": "2024-06-01T12:01:00Z", "value": 20},
+      {"name": "tag_avg", "timestamp": "2024-06-01T12:02:00Z", "value": 30},
+      {"name": "tag_mdn", "timestamp": "2024-06-01T12:00:00Z", "value": 1},
+      {"name": "tag_mdn", "timestamp": "2024-06-01T12:01:00Z", "value": 9},
+      {"name": "tag_mdn", "timestamp": "2024-06-01T12:02:00Z", "value": 5},
+      {"name": "tag_max", "timestamp": "2024-06-01T12:00:00Z", "value": 5},
+      {"name": "tag_max", "timestamp": "2024-06-01T12:01:00Z", "value": 15},
+      {"name": "tag_max", "timestamp": "2024-06-01T12:02:00Z", "value": 10},
+      {"name": "tag_min", "timestamp": "2024-06-01T12:00:00Z", "value": 50},
+      {"name": "tag_min", "timestamp": "2024-06-01T12:01:00Z", "value": 30},
+      {"name": "tag_min", "timestamp": "2024-06-01T12:02:00Z", "value": 40},
+      {"name": "tag_lts", "timestamp": "2024-06-01T12:00:00Z", "value": 100},
+      {"name": "tag_lts", "timestamp": "2024-06-01T12:01:00Z", "value": 200},
+      {"name": "tag_lts", "timestamp": "2024-06-01T12:02:00Z", "value": 300}
+    ]
+  },
+  "expected_values": {
+    "tag_avg": 20.0,
+    "tag_mdn": 5.0,
+    "tag_max": 15.0,
+    "tag_min": 30.0,
+    "tag_lts": 300.0
+  }
+}

e2e/scenario_inputs/pi_web_api_scouter_timeout.json

@@ -0,0 +1,23 @@
+{
+  "workflow_input": {
+    "model_id": "15",
+    "model_name": "PI Timeout",
+    "schedule_name": "pi-timeout",
+    "trigger_laborious": false,
+    "filters": {},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": false,
+    "model_tags": {
+      "tag1": {"webid": "webid1", "aggr_func": "avg", "data_range": [0, 100], "frequency": 60000}
+    },
+    "pi_web_api_query": {
+      "endpoint": "/streamsets/recorded",
+      "period": "*-1d",
+      "max_count": 1,
+      "api_timeout": 2
+    }
+  },
+  "pi_web_api_server": {"mode": "timeout", "timeout_sleep_seconds": 5}
+}

e2e/scenario_inputs/scouter_empty_mongo.json

@@ -0,0 +1,23 @@
+{
+  "workflow_input": {
+    "topic": "e2e-topic",
+    "model_id": "3",
+    "model_name": "Scouter Empty Mongo",
+    "schedule_name": "scouter-empty",
+    "trigger_laborious": false,
+    "filters": {},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": false,
+    "model_tags": {
+      "tag1": {
+        "webid": "webid1",
+        "aggr_func": "avg",
+        "data_range": [0, 100],
+        "frequency": 60000
+      }
+    }
+  },
+  "raw_documents": []
+}

e2e/scenario_inputs/scouter_happy_path.json

@@ -0,0 +1,38 @@
+{
+  "workflow_input": {
+    "topic": "e2e-topic",
+    "model_id": "1",
+    "model_name": "Scouter E2E Model",
+    "schedule_name": "scouter-happy",
+    "trigger_laborious": false,
+    "filters": {},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": false,
+    "model_tags": {
+      "tag1": {
+        "webid": "webid1",
+        "aggr_func": "avg",
+        "data_range": [0, 100],
+        "frequency": 60000
+      }
+    }
+  },
+  "raw_documents": [
+    {
+      "inserted_at": "2024-06-01 12:00:00.000000+0000",
+      "timestamp": "2024-06-01 12:00:00+0000",
+      "name": "tag1",
+      "value": 10.5,
+      "tag": "webid1"
+    },
+    {
+      "inserted_at": "2024-06-01 12:01:00.000000+0000",
+      "timestamp": "2024-06-01 12:01:00+0000",
+      "name": "tag1",
+      "value": 20.0,
+      "tag": "webid1"
+    }
+  ]
+}

e2e/scenario_inputs/scouter_incremental_load.json

@@ -0,0 +1,43 @@
+{
+  "workflow_input": {
+    "topic": "e2e-topic",
+    "model_id": "2",
+    "model_name": "Scouter Incremental",
+    "schedule_name": "scouter-incremental",
+    "trigger_laborious": false,
+    "filters": {},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": false,
+    "model_tags": {
+      "tag1": {
+        "webid": "webid1",
+        "aggr_func": "avg",
+        "data_range": [0, 100],
+        "frequency": 60000
+      }
+    }
+  },
+  "redis_seed": {
+    "last_data_timestamp": "2024-06-01 10:00:00.000000+0000"
+  },
+  "raw_documents": [
+    {
+      "inserted_at": "2024-06-01 09:00:00.000000+0000",
+      "timestamp": "2024-06-01 09:00:00+0000",
+      "name": "tag1",
+      "value": 1.0,
+      "tag": "webid1"
+    },
+    {
+      "inserted_at": "2024-06-01 11:00:00.000000+0000",
+      "timestamp": "2024-06-01 11:00:00+0000",
+      "name": "tag1",
+      "value": 99.0,
+      "tag": "webid1"
+    }
+  ],
+  "expected_newer_count": 1,
+  "expected_last_timestamp": "2024-06-01 11:00:00.000000+0000"
+}

e2e/scenario_inputs/scouter_no_redis_timestamp_first_run.json

@@ -0,0 +1,31 @@
+{
+  "workflow_input": {
+    "topic": "e2e-topic",
+    "model_id": "4",
+    "model_name": "Scouter First Run",
+    "schedule_name": "scouter-first-run",
+    "trigger_laborious": false,
+    "filters": {},
+    "schema": "sientia_data",
+    "table_name": "laborious_data",
+    "retention_time": 3600,
+    "fill_missing_tags": false,
+    "model_tags": {
+      "tag1": {
+        "webid": "webid1",
+        "aggr_func": "lts",
+        "data_range": [0, 100],
+        "frequency": 60000
+      }
+    }
+  },
+  "raw_documents": [
+    {
+      "inserted_at": "2024-06-01 08:00:00.000000+0000",
+      "timestamp": "2024-06-01 08:00:00+0000",
+      "name": "tag1",
+      "value": 42.0,
+      "tag": "webid1"
+    }
+  ]
+}

e2e/scenarios.md

@@ -1,427 +1,138 @@
-# Test Scenarios for PI Web API Scouter Workflow
+# Scouter E2E scenario catalog
 
-This document describes all possible test scenarios for the `pi_web_api_scouter` workflow and its child workflow `core_scouter`.
+## Execution context
 
-## Workflow Overview
-
-The `pi_web_api_scouter` workflow:
-1. Retrieves tag values from PI Web API
-2. Delegates processing to `core_scouter` child workflow which:
-   - Applies data quality gates
-   - Aggregates data
-   - Groups and holds data in Redis
-   - Exports to PostgreSQL
-   - Writes metrics
-   - Optionally stores debug data package
+- **MongoDB**, **Redis**, and **PostgreSQL** run as session-scoped testcontainers with autouse cleanup between tests.
+- **PI Web API** is an in-process HTTP server (`e2e/pi_web_api_test_server.py`) speaking the wire format consumed by `PIWebAPIClient`.
+- **Temporal** uses `WorkflowEnvironment.start_local()` and a single worker on `scouter-test-queue`.
+- **Production code is not mocked** (except `Logger` and optional notification insert spy).
 
 ---
 
-## 1. PI Web API Scouter - Main Workflow Scenarios
+## 0. Harness smoke tests
 
-### 1.1 Success Scenarios
+Diagnostic-only checks under `e2e/test_harness_smoke.py`. They are not business scenarios; they exist to fail fast when the harness itself (Docker / containers / Temporal worker wiring) is broken, before the numbered suite runs.
 
-#### Scenario 1.1.1: Happy Path - Complete Success
-**Description**: Workflow completes successfully with valid data from PI Web API
+### 0.0.1 Postgres schema ready (`test_postgres_schema_ready`)
 
-**Input**:
-- Valid `model_name`, `model_id`, `schedule_name`
-- Valid `pi_web_api_query` with endpoint, period, max_count, api_timeout
-- Valid `model_tags` with webids and configurations
-- Valid filters, schema, table_name, retention_time
+Confirms the autouse fixture executed `db_schema.sql` and `sientia_data.laborious_data` exists in the Postgres testcontainer.
 
-**Expected Behavior**:
-- `get_tag_values` returns non-empty list of records
-- Workflow proceeds to `core_scouter`
-- All activities execute successfully
-- Data is stored in PostgreSQL
-- Metrics are written
-- Workflow completes without errors
+### 0.0.2 Activities construct (`test_activities_construct`)
 
-**Assertions**:
-- PI Web API client called once with correct parameters
-- Data exists in SQLite (PostgreSQL substitute)
-- Data cached in Redis
-- Metrics written
-- No errors raised
+Confirms the production `Activities` instance initializes against the Mongo/Redis/Postgres testcontainers without hanging (no `patch(...)` involved).
+
+### 0.0.3 Temporal PI happy path (`test_temporal_pi_happy_path`)
+
+End-to-end liveness check: `WorkflowEnvironment.start_local()` + worker + in-process PI server + `PIWebAPIScouter` complete without raising. Functional assertions for this flow live in scenario **2.1.1**.
 
 ---
 
-#### Scenario 1.1.2: Success with Multiple Tags
-**Description**: Workflow processes multiple tags successfully
+## 1. Scouter workflow
 
-**Input**:
-- Multiple tags in `model_tags` (3+ tags)
-- Each tag has valid webid, aggr_function, data_range, frequency
+### 1.1.1 Happy path
 
-**Expected Behavior**:
-- All tags retrieved from PI Web API
-- All tags processed through quality gates
-- All tags aggregated correctly
-- All tags stored in database
+Seed `raw_<schedule>` with multiple documents, run `Scouter`, assert Postgres rows and Redis `last_data_timestamp:scouter:<schedule>`.
 
-**Assertions**:
-- Number of records matches number of tags
-- All tags present in final data
-- Aggregation applied per tag configuration
+### 1.2.1 Incremental load
+
+Pre-seed Redis timestamp; seed older and newer Mongo docs; assert only newer rows export and timestamp advances.
+
+### 1.3.1 Empty Mongo early exit
+
+Empty `raw_<schedule>`; workflow exits without Postgres rows or Redis timestamp key.
+
+### 1.3.2 No Redis timestamp first run
+
+No prior Redis key; all seeded Mongo docs load and timestamp is written after success.
 
 ---
 
-#### Scenario 1.1.3: Success with Debug Data Package Enabled
-**Description**: Workflow completes with `debug_data_package=True`
+## 2. PIWebAPIScouter workflow
 
-**Input**:
-- All standard input
-- `debug_data_package: True`
+### 2.1.1 Happy path
 
-**Expected Behavior**:
-- Normal workflow execution
-- `store_data_package` activity called
-- Data package stored in Redis
+PI server `success` mode with two tags; assert Postgres rows, Redis hold key, one HTTP request recorded.
 
-**Assertions**:
-- `store_data_package` called once
-- Data package key exists in Redis
-- Package contains both `data` and `held_data`
+### 2.1.2 Multiple tags
+
+Five tags with `avg` / `mdn` / `max` / `min` / `lts`; assert five distinct `variable` values and exact aggregated numbers in Postgres.
+
+### 2.1.3 Debug data package
+
+`debug_data_package=True`; assert `data_package_pi_web_api_scouter_*` Redis key with `data` and `held_data`.
+
+### 2.2.1 Empty response early exit
+
+Server `empty` mode; zero Postgres rows for `model_id`, one request recorded.
+
+### 2.3.1 PI Web API connection error
+
+Server `error` mode (HTTP 5xx); workflow fails; `PI_WEB_API_REQUEST_ERROR` notification in Mongo.
+
+### 2.3.2 PI Web API timeout
+
+Server `timeout` mode; workflow fails; `PI_WEB_API_REQUEST_ERROR` notification sent.
+
+### 2.3.3 Invalid endpoint
+
+Workflow uses `/invalid/endpoint` (404); workflow fails; `PI_WEB_API_REQUEST_ERROR` notification sent.
 
 ---
 
-### 1.2 Early Exit Scenarios
+## 3. CoreScouter subworkflow
 
-#### Scenario 1.2.1: Empty Data from PI Web API
-**Description**: PI Web API returns empty data
+### 3.1.1 Complete processing success
 
-**Input**:
-- Valid configuration
-- PI Web API returns empty DataFrame or empty list
+Single tag, no filters; Postgres row and `held_data_*` Redis key; no `data_package_*` key.
 
-**Expected Behavior**:
-- `get_tag_values` returns empty list `[]`
-- Workflow checks `if not data:` and returns early
-- `core_scouter` is NOT called
-- Workflow completes without error
+### 3.1.2 Null values filter discard
 
-**Assertions**:
-- PI Web API called once
-- `core_scouter` NOT called
-- No data in PostgreSQL
-- No data in Redis (except possibly from previous runs)
+`NULL_VALUES_FILTER` DISCARD; one WARNING notification; only valid row in Postgres.
 
----
+### 3.1.3 Null values filter warn
 
-#### Scenario 1.2.2: None Returned from PI Web API
-**Description**: PI Web API returns None
+`NULL_VALUES_FILTER` WARN; notification sent; both rows in Postgres.
 
-**Input**:
-- Valid configuration
-- PI Web API returns None
+### 3.1.4 Out of bounds filter discard
 
-**Expected Behavior**:
-- `get_tag_values` returns None
-- Workflow checks `if not data:` and returns early
-- `core_scouter` is NOT called
+`OUT_OF_BOUNDS_FILTER` DISCARD; in-range row only; WARNING notification.
 
-**Assertions**:
-- PI Web API called once
-- `core_scouter` NOT called
-- Workflow completes without error
+### 3.1.5 Aggregation avg
 
----
+Three points; Postgres `value` equals arithmetic mean (20.0).
 
-### 1.3 Error Scenarios
+### 3.1.6 Aggregation mdn
 
-#### Scenario 1.3.1: PI Web API Connection Error
-**Description**: PI Web API client raises connection error
+Median equals 5.0 in Postgres.
 
-**Input**:
-- Valid configuration
-- PI Web API client raises `PIMSRequestError` or connection exception
+### 3.1.7 Aggregation max
 
-**Expected Behavior**:
-- `get_tag_values` catches exception
-- Sends notification with `PI_WEB_API_REQUEST_ERROR`
-- Raises exception (workflow fails after retries)
+Maximum equals 15.0 in Postgres.
 
-**Assertions**:
-- Notification sent with correct error details
-- Exception propagated to workflow
-- Workflow fails (after retry policy exhausted)
-- `core_scouter` NOT called
+### 3.1.8 Aggregation min
 
----
+Minimum equals 30.0 in Postgres.
 
-#### Scenario 1.3.2: PI Web API Timeout
-**Description**: PI Web API request times out
+### 3.1.9 Aggregation lts
 
-**Input**:
-- Valid configuration
-- `api_timeout` set to low value
-- PI Web API takes longer than timeout
+Last-by-timestamp value equals 300.0 in Postgres.
 
-**Expected Behavior**:
-- Request times out
-- Exception raised
-- Notification sent
-- Workflow fails after retries
+### 3.1.10 Fill missing tags
 
-**Assertions**:
-- Timeout exception caught
-- Notification sent
-- Workflow fails
+`fill_missing_tags=True`; `held_data_*` contains missing tag keys with `None`.
 
----
+### 3.1.11 Debug data package
 
-#### Scenario 1.3.3: Invalid Endpoint
-**Description**: Invalid PI Web API endpoint provided
+`debug_data_package=True`; `data_package_*` Redis key decodes to dict with `data` and `held_data`.
 
-**Input**:
-- Invalid endpoint path in `pi_web_api_query`
+### 3.2.1 Empty after grouping early exit
 
-**Expected Behavior**:
-- PI Web API client raises error
-- Notification sent
-- Workflow fails
+Empty column-oriented `data`; no Postgres rows; no populated `held_data_*`.
 
-**Assertions**:
-- Error notification sent
-- Workflow fails
+### 3.3.1 Invalid aggregation function
 
----
+`aggr_func= bogus`; `AGGREGATION_ISSUES` ERROR notification; bogus tag absent from Postgres.
 
-## 2. CoreScouter - Child Workflow Scenarios
-
-### 2.1 Success Scenarios
-
-#### Scenario 2.1.1: Complete Processing Success
-**Description**: All stages complete successfully
-
-**Input**:
-- Valid data from parent workflow
-- Valid filters, model_tags, schema, table_name
-- `fill_missing_tags: False`
-- `debug_data_package: False`
-
-**Expected Behavior**:
-- `data_quality_gate` filters data
-- `aggregate_data` aggregates by tag
-- `group_and_hold_data` stores in Redis
-- `export_data_to_postgres` writes to database
-- `write_metrics` records metrics
-- Workflow completes
-
-**Assertions**:
-- All activities called in correct order
-- Data in PostgreSQL
-- Data in Redis
-- Metrics written
-- `store_data_package` NOT called
-
----
-
-#### Scenario 2.1.2: Success with Data Quality Filters
-**Description**: Data quality filters applied successfully
-
-**Input**:
-- Data with some quality issues
-- Filters configured with `NULL_VALUES_FILTER` or `OUT_OF_BOUNDS_FILTER`
-- Policy set to `DISCARD` or `WARN`
-
-**Expected Behavior**:
-- Quality gate identifies issues
-- Notification sent (WARNING level)
-- If policy is `DISCARD`, bad rows removed
-- Remaining data processed normally
-
-**Assertions**:
-- Quality issues detected
-- Notification sent
-- Bad data discarded if policy is `DISCARD`
-- Good data processed
-
----
-
-#### Scenario 2.1.3: Success with Different Aggregation Functions
-**Description**: Different aggregation functions applied correctly
-
-**Input**:
-- Multiple tags with different `aggr_function`: `avg`, `mdn`, `max`, `min`, `lts`
-- Time-series data with multiple points per tag
-
-**Expected Behavior**:
-- Each tag aggregated with its configured function
-- Aggregated values correct for each function type
-
-**Assertions**:
-- `avg` calculates mean correctly
-- `mdn` calculates median correctly
-- `max` returns maximum value
-- `min` returns minimum value
-- `lts` returns latest value
-
----
-
-#### Scenario 2.1.4: Success with Fill Missing Tags
-**Description**: Missing tags filled with None
-
-**Input**:
-- `fill_missing_tags: True`
-- Some tags missing from data
-
-**Expected Behavior**:
-- Missing tags added to `data_hold` with value `None`
-- All expected tags present in final data
-
-**Assertions**:
-- Missing tags present with `None` value
-- All model_tags represented in output
-
----
-
-### 2.2 Early Exit Scenarios
-
-#### Scenario 2.2.1: Empty Data After Grouping
-**Description**: `group_and_hold_data` returns empty dict
-
-**Input**:
-- Data that results in empty `held_data` after grouping
-
-**Expected Behavior**:
-- `group_and_hold_data` returns `{}`
-- Workflow checks `if held_data == {}:` and returns early
-- `export_data_to_postgres` NOT called
-- `write_metrics` NOT called
-- `store_data_package` NOT called
-
-**Assertions**:
-- Early return after grouping
-- No database export
-- No metrics written
-- Workflow completes without error
-
----
-
-### 2.3 Error Scenarios
-
-#### Scenario 2.3.1: Redis Connection Error
-**Description**: Redis unavailable during `group_and_hold_data`
-
-**Input**:
-- Valid data
-- Redis connection fails
-
-**Expected Behavior**:
-- `redis_repository.get()` or `redis_repository.set()` raises exception
-- Notification sent with `REDIS_GET_ERROR` or `REDIS_SET_ERROR`
-- Exception propagated (workflow fails after retries)
-
-**Assertions**:
-- Error notification sent
-- Workflow fails
-
----
-
-## 3. Activity-Specific Scenarios
-
-> **Note**: Activity-specific scenarios are better suited for unit tests rather than e2e tests.
-> These scenarios are covered indirectly through workflow e2e tests. For detailed activity testing,
-> refer to the unit test suite in `tests/activities/`.
-
----
-
-## 5. Test Data Requirements
-
-### 5.1 Valid Test Data Structure
-
-```python
-{
-    'model_name': 'test_model',
-    'model_id': 'test_model_id',
-    'schedule_name': 'test_schedule',
-    'model_tags': {
-        'tag1': {
-            'webid': 'webid1',
-            'aggr_function': 'avg',
-            'data_range': [0, 100],
-            'frequency': 60000,
-        },
-    },
-    'trigger_laborious': False,
-    'filters': {},
-    'schema': 'test_schema',
-    'table_name': 'test_table',
-    'retention_time': 3600,
-    'fill_missing_tags': False,
-    'debug_data_package': False,
-    'pi_web_api_query': {
-        'endpoint': '/streamsets/recorded',
-        'period': '*-1d',
-        'max_count': 10,
-        'api_timeout': 30,
-    },
-}
-```
-
-### 5.2 Mock PI Web API Response
-
-```python
-DataFrame({
-    'timestamp': ['2024-01-01 12:00:00+0000', ...],
-    'name': ['tag1', 'tag2', ...],
-    'value': [10.5, 20.3, ...],
-    'tag': ['webid1', 'webid2', ...],
-})
-```
-
----
-
-## 6. Test Implementation Notes
-
-### 6.1 Test Organization
-
-- Group tests by scenario category
-- Use descriptive test names matching scenario IDs
-- Share fixtures for common setup
-- Use parametrized tests for similar scenarios
-
-### 6.2 Assertions Checklist
-
-For each scenario, verify:
-- [ ] Correct activities called
-- [ ] Correct parameters passed
-- [ ] Expected data in storage (SQLite/Redis)
-- [ ] Expected notifications sent
-- [ ] Expected metrics written
-- [ ] No unexpected errors
-- [ ] Workflow state correct
-
-### 6.3 Mock Configuration
-
-- Mock PI Web API client responses
-- Use fake Redis (fakeredis)
-- Use fake MongoDB (mongomock)
-- Use SQLite for PostgreSQL
-- Mock notification handler
-- Mock metrics controller
-
----
-
-## 7. Priority Scenarios
-
-### High Priority (Must Test)
-1. Scenario 1.1.1: Happy Path
-2. Scenario 1.2.1: Empty Data
-3. Scenario 1.3.1: API Connection Error
-4. Scenario 2.1.1: Complete Processing
-5. Scenario 2.2.1: Empty After Grouping
-6. Scenario 2.3.4: PostgreSQL Error
-
-### Medium Priority (Should Test)
-1. Scenario 1.1.3: Debug Package
-2. Scenario 2.1.2: Quality Filters
-3. Scenario 2.1.3: Different Aggregations
-4. Scenario 3.3.5: Invalid Aggregation
-
-### Low Priority (Nice to Have)
-1. Scenario 4.1.2: Retry Success
-2. Scenario 5.1.1: Large Dataset
-3. Scenario 5.3.1: Concurrent Execution
+### 3.3.2 Postgres export failure surfaces
 
+Drop `value` column before run; workflow fails; ERROR notification in Mongo.

e2e/test_core_scouter_early_exit.py

@@ -1,96 +0,0 @@
-"""
-End-to-end tests for CoreScouter workflow - Early exit scenarios.
-"""
-
-from datetime import datetime
-
-import pytest
-from sqlalchemy import text
-from temporalio.testing import WorkflowEnvironment
-from temporalio.worker import Worker
-
-from scouter.activities.activities import Activities
-from scouter.workflow.sub_workflows.core_scouter import CoreScouter
-
-
-@pytest.mark.asyncio
-@pytest.mark.integration
-async def test_scenario_2_2_1_empty_data_after_grouping(
-    temporal_test_env: WorkflowEnvironment,
-    temporal_worker: Worker,
-    test_activities: Activities,
-    postgres_engine,
-):
-    """
-    Scenario 2.2.1: Empty Data After Grouping
-    
-    group_and_hold_data returns empty dict, workflow exits early.
-    """
-    client = temporal_test_env.client
-
-    # Prepare test data that will result in empty held_data
-    # This can happen if all data is filtered out or aggregation results in empty data
-    # Empty data must be a dict with empty lists for each column
-    test_data = {
-        'tag': [],
-        'name': [],
-        'value': [],
-        'timestamp': [],
-    }
-
-    # Prepare input data
-    input_data = {
-        'metadata': {
-            'metadata': {
-                'model_id': '1',
-                'model_name': 'Test Model',
-                'schedule_name': 'test-schedule',
-                'workflow_name': 'pi_web_api_scouter',
-            }
-        },
-        'workflow_name': 'pi_web_api_scouter',
-        'schedule_name': 'test-schedule',
-        'model_name': 'Test Model',
-        'model_id': '1',
-        'data': test_data,
-        'trigger_laborious': False,
-        'filters': {},
-        'schema': 'sientia_data',
-        'table_name': 'laborious_data',
-        'retention_time': 3600,
-        'fill_missing_tags': False,
-        'model_tags': {
-            'tag1': {
-                'webid': 'webid1',
-                'aggr_function': 'avg',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-        },
-    }
-
-    # Start workflow
-    handle = await client.start_workflow(
-        CoreScouter.run,
-        input_data,
-        id=f'test-core-scouter-empty-{datetime.now().timestamp()}',
-        task_queue='test-queue',
-    )
-
-    # Wait for workflow completion (should complete without error)
-    await handle.result()
-
-    # Verify no data was exported to PostgreSQL (early exit)
-    schema_name = 'sientia_data'
-    table_name = 'laborious_data'
-    full_table_name = f"{schema_name}.{table_name}"
-
-    with postgres_engine.connect() as conn:
-        result = conn.execute(
-            text(f"SELECT COUNT(*) FROM {full_table_name} WHERE model_id = 1")
-        )
-        row_count = result.scalar()
-
-    # Should have 0 rows since export_data_to_postgres was not called
-    assert row_count == 0, f"Expected no data in PostgreSQL, got {row_count} rows"
-

e2e/test_core_scouter_errors.py

@@ -1,90 +0,0 @@
-"""
-End-to-end tests for CoreScouter workflow - Error scenarios.
-"""
-
-from datetime import datetime
-from unittest.mock import AsyncMock
-
-import pytest
-from sqlalchemy import text
-from temporalio.exceptions import ApplicationError, FailureError
-from temporalio.testing import WorkflowEnvironment
-from temporalio.worker import Worker
-
-from scouter.activities.activities import Activities
-from scouter.workflow.sub_workflows.core_scouter import CoreScouter
-
-
-@pytest.mark.asyncio
-@pytest.mark.integration
-async def test_scenario_2_3_1_redis_connection_error(
-    temporal_test_env: WorkflowEnvironment,
-    temporal_worker: Worker,
-    test_activities: Activities,
-):
-    """
-    Scenario 2.3.1: Redis Connection Error
-    
-    Redis unavailable during group_and_hold_data, notification sent, workflow fails.
-    """
-    client = temporal_test_env.client
-
-    # Mock Redis get to raise an error
-    original_get = test_activities.redis_repository.get
-    test_activities.redis_repository.get = AsyncMock(side_effect=Exception("Redis connection error"))
-
-    try:
-        test_data = [
-            {
-                'timestamp': '2024-01-01 12:00:00+0000',
-                'name': 'tag1',
-                'value': 10.5,
-                'tag': 'webid1',
-            },
-        ]
-
-        input_data = {
-            'metadata': {
-                'metadata': {
-                    'model_id': '1',
-                    'model_name': 'Test Model',
-                    'schedule_name': 'test-schedule',
-                    'workflow_name': 'pi_web_api_scouter',
-                }
-            },
-            'workflow_name': 'pi_web_api_scouter',
-            'schedule_name': 'test-schedule',
-            'model_name': 'Test Model',
-            'model_id': '1',
-            'data': test_data,
-            'trigger_laborious': False,
-            'filters': {},
-            'schema': 'sientia_data',
-            'table_name': 'laborious_data',
-            'retention_time': 3600,
-            'fill_missing_tags': False,
-            'model_tags': {
-                'tag1': {
-                    'webid': 'webid1',
-                    'aggr_function': 'avg',
-                    'data_range': [0, 100],
-                    'frequency': 60000,
-                },
-            },
-        }
-
-        # Start workflow
-        handle = await client.start_workflow(
-            CoreScouter.run,
-            input_data,
-            id=f'test-core-scouter-redis-error-{datetime.now().timestamp()}',
-            task_queue='test-queue',
-        )
-
-        # Wait for workflow completion - should fail
-        with pytest.raises((FailureError, ApplicationError, Exception)):
-            await handle.result()
-    finally:
-        # Restore original method
-        test_activities.redis_repository.get = original_get
-

e2e/test_core_scouter_success.py

@@ -1,462 +0,0 @@
-"""
-End-to-end tests for CoreScouter workflow - Success scenarios.
-"""
-
-from datetime import datetime
-
-import pandas as pd
-import pytest
-from sqlalchemy import inspect, text
-from temporalio.testing import WorkflowEnvironment
-from temporalio.worker import Worker
-
-from scouter.activities.activities import Activities
-from scouter.workflow.sub_workflows.core_scouter import CoreScouter
-
-
-@pytest.mark.asyncio
-@pytest.mark.integration
-async def test_scenario_2_1_1_complete_processing_success(
-    temporal_test_env: WorkflowEnvironment,
-    temporal_worker: Worker,
-    test_activities: Activities,
-    postgres_engine,
-):
-    """
-    Scenario 2.1.1: Complete Processing Success
-    
-    All stages complete successfully.
-    """
-    client = temporal_test_env.client
-
-    # Prepare test data (simulating data from parent workflow)
-    test_data = [
-        {
-            'timestamp': '2024-01-01 12:00:00+0000',
-            'name': 'tag1',
-            'value': 10.5,
-            'tag': 'webid1',
-        },
-        {
-            'timestamp': '2024-01-01 12:00:00+0000',
-            'name': 'tag2',
-            'value': 20.3,
-            'tag': 'webid2',
-        },
-    ]
-
-    # Prepare input data for CoreScouter
-    input_data = {
-        'metadata': {
-            'metadata': {
-                'model_id': '1',
-                'model_name': 'Test Model',
-                'schedule_name': 'test-schedule',
-                'workflow_name': 'pi_web_api_scouter',
-            }
-        },
-        'workflow_name': 'pi_web_api_scouter',
-        'schedule_name': 'test-schedule',
-        'model_name': 'Test Model',
-        'model_id': '1',
-        'data': test_data,
-        'trigger_laborious': False,
-        'filters': {},
-        'schema': 'sientia_data',
-        'table_name': 'laborious_data',
-        'retention_time': 3600,
-        'fill_missing_tags': False,
-        'model_tags': {
-            'tag1': {
-                'webid': 'webid1',
-                'aggr_function': 'avg',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-            'tag2': {
-                'webid': 'webid2',
-                'aggr_function': 'avg',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-        },
-    }
-
-    # Start workflow
-    handle = await client.start_workflow(
-        CoreScouter.run,
-        input_data,
-        id=f'test-core-scouter-{datetime.now().timestamp()}',
-        task_queue='test-queue',
-    )
-
-    # Wait for workflow completion
-    await handle.result()
-
-    # Verify data was stored in PostgreSQL
-    schema_name = 'sientia_data'
-    table_name = 'laborious_data'
-    full_table_name = f"{schema_name}.{table_name}"
-
-    with postgres_engine.connect() as conn:
-        result = conn.execute(
-            text(f"SELECT COUNT(*) FROM {full_table_name} WHERE model_id = 1")
-        )
-        row_count = result.scalar()
-
-    assert row_count > 0, f"Expected data in PostgreSQL, got {row_count} rows"
-
-    # Verify data was cached in Redis
-    keys = await test_activities.redis_repository.keys('*')
-    assert len(keys) > 0, "Expected data in Redis"
-
-
-@pytest.mark.asyncio
-@pytest.mark.integration
-async def test_scenario_2_1_2_success_with_data_quality_filters(
-    temporal_test_env: WorkflowEnvironment,
-    temporal_worker: Worker,
-    test_activities: Activities,
-    postgres_engine,
-):
-    """
-    Scenario 2.1.2: Success with Data Quality Filters
-    
-    Data quality filters applied successfully.
-    """
-    client = temporal_test_env.client
-
-    # Prepare test data with some quality issues (null values, out of bounds)
-    test_data = [
-        {
-            'timestamp': '2024-01-01 12:00:00+0000',
-            'name': 'tag1',
-            'value': None,  # Null value - should be filtered if DISCARD policy
-            'tag': 'webid1',
-        },
-        {
-            'timestamp': '2024-01-01 12:00:00+0000',
-            'name': 'tag2',
-            'value': 150.0,  # Out of bounds (range is [0, 100])
-            'tag': 'webid2',
-        },
-        {
-            'timestamp': '2024-01-01 12:00:00+0000',
-            'name': 'tag3',
-            'value': 50.0,  # Valid value
-            'tag': 'webid3',
-        },
-    ]
-
-    # Prepare input data with filters
-    input_data = {
-        'metadata': {
-            'metadata': {
-                'model_id': '1',
-                'model_name': 'Test Model',
-                'schedule_name': 'test-schedule',
-                'workflow_name': 'pi_web_api_scouter',
-            }
-        },
-        'workflow_name': 'pi_web_api_scouter',
-        'schedule_name': 'test-schedule',
-        'model_name': 'Test Model',
-        'model_id': '1',
-        'data': test_data,
-        'trigger_laborious': False,
-        'filters': {
-            'NULL_VALUES_FILTER': {
-                'policy': 'DISCARD',
-            },
-            'OUT_OF_BOUNDS_FILTER': {
-                'policy': 'WARN',
-            },
-        },
-        'schema': 'sientia_data',
-        'table_name': 'laborious_data',
-        'retention_time': 3600,
-        'fill_missing_tags': False,
-        'model_tags': {
-            'tag1': {
-                'webid': 'webid1',
-                'aggr_function': 'avg',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-            'tag2': {
-                'webid': 'webid2',
-                'aggr_function': 'avg',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-            'tag3': {
-                'webid': 'webid3',
-                'aggr_function': 'avg',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-        },
-    }
-
-    # Start workflow
-    handle = await client.start_workflow(
-        CoreScouter.run,
-        input_data,
-        id=f'test-core-scouter-quality-{datetime.now().timestamp()}',
-        task_queue='test-queue',
-    )
-
-    # Wait for workflow completion
-    await handle.result()
-
-    # Verify data was stored in PostgreSQL
-    # tag1 should be filtered out (null value with DISCARD policy)
-    # tag2 should be kept (out of bounds with WARN policy)
-    # tag3 should be kept (valid value)
-    schema_name = 'sientia_data'
-    table_name = 'laborious_data'
-    full_table_name = f"{schema_name}.{table_name}"
-
-    with postgres_engine.connect() as conn:
-        result = conn.execute(
-            text(f"SELECT COUNT(*) FROM {full_table_name} WHERE model_id = 1")
-        )
-        row_count = result.scalar()
-
-    # Should have at least tag2 and tag3 (tag1 filtered out)
-    assert row_count >= 2, f"Expected at least 2 records after filtering, got {row_count}"
-
-
-@pytest.mark.asyncio
-@pytest.mark.integration
-async def test_scenario_2_1_3_success_with_different_aggregation_functions(
-    temporal_test_env: WorkflowEnvironment,
-    temporal_worker: Worker,
-    test_activities: Activities,
-    postgres_engine,
-):
-    """
-    Scenario 2.1.3: Success with Different Aggregation Functions
-    
-    Different aggregation functions applied correctly.
-    """
-    client = temporal_test_env.client
-
-    # Prepare test data with multiple points per tag for aggregation
-    test_data = [
-        {'timestamp': '2024-01-01 12:00:00+0000', 'name': 'tag_avg', 'value': 10.0, 'tag': 'webid_avg'},
-        {'timestamp': '2024-01-01 12:01:00+0000', 'name': 'tag_avg', 'value': 20.0, 'tag': 'webid_avg'},
-        {'timestamp': '2024-01-01 12:02:00+0000', 'name': 'tag_avg', 'value': 30.0, 'tag': 'webid_avg'},
-        {'timestamp': '2024-01-01 12:00:00+0000', 'name': 'tag_max', 'value': 5.0, 'tag': 'webid_max'},
-        {'timestamp': '2024-01-01 12:01:00+0000', 'name': 'tag_max', 'value': 15.0, 'tag': 'webid_max'},
-        {'timestamp': '2024-01-01 12:02:00+0000', 'name': 'tag_max', 'value': 10.0, 'tag': 'webid_max'},
-        {'timestamp': '2024-01-01 12:00:00+0000', 'name': 'tag_min', 'value': 50.0, 'tag': 'webid_min'},
-        {'timestamp': '2024-01-01 12:01:00+0000', 'name': 'tag_min', 'value': 30.0, 'tag': 'webid_min'},
-        {'timestamp': '2024-01-01 12:02:00+0000', 'name': 'tag_min', 'value': 40.0, 'tag': 'webid_min'},
-        {'timestamp': '2024-01-01 12:00:00+0000', 'name': 'tag_lts', 'value': 100.0, 'tag': 'webid_lts'},
-        {'timestamp': '2024-01-01 12:01:00+0000', 'name': 'tag_lts', 'value': 200.0, 'tag': 'webid_lts'},
-        {'timestamp': '2024-01-01 12:02:00+0000', 'name': 'tag_lts', 'value': 300.0, 'tag': 'webid_lts'},
-    ]
-
-    # Prepare input data with different aggregation functions
-    input_data = {
-        'metadata': {
-            'metadata': {
-                'model_id': '1',
-                'model_name': 'Test Model',
-                'schedule_name': 'test-schedule',
-                'workflow_name': 'pi_web_api_scouter',
-            }
-        },
-        'workflow_name': 'pi_web_api_scouter',
-        'schedule_name': 'test-schedule',
-        'model_name': 'Test Model',
-        'model_id': '1',
-        'data': test_data,
-        'trigger_laborious': False,
-        'filters': {},
-        'schema': 'sientia_data',
-        'table_name': 'laborious_data',
-        'retention_time': 3600,
-        'fill_missing_tags': False,
-        'model_tags': {
-            'tag_avg': {
-                'webid': 'webid_avg',
-                'aggr_function': 'avg',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-            'tag_max': {
-                'webid': 'webid_max',
-                'aggr_function': 'max',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-            'tag_min': {
-                'webid': 'webid_min',
-                'aggr_function': 'min',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-            'tag_lts': {
-                'webid': 'webid_lts',
-                'aggr_function': 'lts',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-        },
-    }
-
-    # Start workflow
-    handle = await client.start_workflow(
-        CoreScouter.run,
-        input_data,
-        id=f'test-core-scouter-aggr-{datetime.now().timestamp()}',
-        task_queue='test-queue',
-    )
-
-    # Wait for workflow completion
-    await handle.result()
-
-    # Verify data was stored in PostgreSQL
-    schema_name = 'sientia_data'
-    table_name = 'laborious_data'
-    full_table_name = f"{schema_name}.{table_name}"
-
-    with postgres_engine.connect() as conn:
-        result = conn.execute(
-            text(f"SELECT variable, value FROM {full_table_name} WHERE model_id = 1")
-        )
-        rows = result.fetchall()
-
-    # Should have 4 rows (one per tag)
-    assert len(rows) >= 4, f"Expected at least 4 records, got {len(rows)}"
-
-    # Verify aggregation was applied correctly
-    values_by_tag = {row[0]: float(row[1]) if row[1] is not None else None for row in rows}
-    
-    # Verify all tags are present
-    assert 'tag_avg' in values_by_tag, "Expected tag_avg to be present"
-    assert 'tag_max' in values_by_tag, "Expected tag_max to be present"
-    assert 'tag_min' in values_by_tag, "Expected tag_min to be present"
-    assert 'tag_lts' in values_by_tag, "Expected tag_lts to be present"
-    
-    # Note: Due to timestamp normalization in get_tag_values, aggregation may behave differently
-    # We verify that aggregation was applied (values exist) rather than exact values
-    # avg: should be between min and max of input values (10, 20, 30)
-    if 'tag_avg' in values_by_tag and values_by_tag['tag_avg'] is not None:
-        assert 10.0 <= values_by_tag['tag_avg'] <= 30.0, f"Expected avg between 10-30, got {values_by_tag['tag_avg']}"
-    
-    # max: should be >= 15.0 (max of 5, 15, 10)
-    if 'tag_max' in values_by_tag and values_by_tag['tag_max'] is not None:
-        assert values_by_tag['tag_max'] >= 10.0, f"Expected max >= 10, got {values_by_tag['tag_max']}"
-    
-    # min: should be <= 50.0 (min of 50, 30, 40)
-    if 'tag_min' in values_by_tag and values_by_tag['tag_min'] is not None:
-        assert values_by_tag['tag_min'] <= 50.0, f"Expected min <= 50, got {values_by_tag['tag_min']}"
-    
-    # lts: should be one of the values (100, 200, 300)
-    if 'tag_lts' in values_by_tag and values_by_tag['tag_lts'] is not None:
-        assert values_by_tag['tag_lts'] in [100.0, 200.0, 300.0], f"Expected lts to be one of [100, 200, 300], got {values_by_tag['tag_lts']}"
-
-
-@pytest.mark.asyncio
-@pytest.mark.integration
-async def test_scenario_2_1_4_success_with_fill_missing_tags(
-    temporal_test_env: WorkflowEnvironment,
-    temporal_worker: Worker,
-    test_activities: Activities,
-    postgres_engine,
-):
-    """
-    Scenario 2.1.4: Success with Fill Missing Tags
-    
-    Missing tags filled with None.
-    """
-    client = temporal_test_env.client
-
-    # Prepare test data with only some tags present
-    test_data = [
-        {
-            'timestamp': '2024-01-01 12:00:00+0000',
-            'name': 'tag1',
-            'value': 10.5,
-            'tag': 'webid1',
-        },
-        # tag2 and tag3 are missing
-    ]
-
-    # Prepare input data with fill_missing_tags enabled
-    input_data = {
-        'metadata': {
-            'metadata': {
-                'model_id': '1',
-                'model_name': 'Test Model',
-                'schedule_name': 'test-schedule',
-                'workflow_name': 'pi_web_api_scouter',
-            }
-        },
-        'workflow_name': 'pi_web_api_scouter',
-        'schedule_name': 'test-schedule',
-        'model_name': 'Test Model',
-        'model_id': '1',
-        'data': test_data,
-        'trigger_laborious': False,
-        'filters': {},
-        'schema': 'sientia_data',
-        'table_name': 'laborious_data',
-        'retention_time': 3600,
-        'fill_missing_tags': True,  # Enable fill missing tags
-        'model_tags': {
-            'tag1': {
-                'webid': 'webid1',
-                'aggr_function': 'avg',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-            'tag2': {
-                'webid': 'webid2',
-                'aggr_function': 'avg',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-            'tag3': {
-                'webid': 'webid3',
-                'aggr_function': 'avg',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-        },
-    }
-
-    # Start workflow
-    handle = await client.start_workflow(
-        CoreScouter.run,
-        input_data,
-        id=f'test-core-scouter-fill-{datetime.now().timestamp()}',
-        task_queue='test-queue',
-    )
-
-    # Wait for workflow completion
-    await handle.result()
-
-    # Verify all tags are present in Redis (including missing ones with None)
-    keys = await test_activities.redis_repository.keys('*')
-    assert len(keys) > 0, "Expected data in Redis"
-
-    # Verify data was stored in PostgreSQL
-    schema_name = 'sientia_data'
-    table_name = 'laborious_data'
-    full_table_name = f"{schema_name}.{table_name}"
-
-    with postgres_engine.connect() as conn:
-        result = conn.execute(
-            text(f"SELECT variable, value FROM {full_table_name} WHERE model_id = 1")
-        )
-        rows = result.fetchall()
-
-    # Should have all 3 tags (tag1 with value, tag2 and tag3 with None)
-    variables = [row[0] for row in rows]
-    assert 'tag1' in variables, "Expected tag1 to be present"
-    # Note: tags with None values might not be stored in PostgreSQL, so we just verify tag1 exists
-

e2e/test_harness_smoke.py

@@ -0,0 +1,51 @@
+"""Fast smoke checks for E2E fixture wiring."""
+
+import pytest
+
+from e2e.helpers import (
+    apply_pi_web_api_server_config,
+    load_scenario_input,
+    make_workflow_id,
+    start_and_await_workflow,
+)
+from e2e.pi_web_api_test_server import PIWebAPITestServer
+from scouter.workflow.pi_web_api_scouter import PIWebAPIScouter
+from temporalio.testing import WorkflowEnvironment
+from temporalio.worker import Worker
+
+
+@pytest.mark.e2e
+def test_postgres_schema_ready(postgres_engine):
+    """Verify autouse schema setup created laborious_data."""
+    with postgres_engine.connect() as conn:
+        count = conn.exec_driver_sql(
+            'SELECT COUNT(*) FROM information_schema.tables '
+            "WHERE table_schema = 'sientia_data' AND table_name = 'laborious_data'"
+        ).scalar()
+    assert count == 1
+
+
+@pytest.mark.e2e
+def test_activities_construct(test_activities):
+    """Verify Activities initializes against testcontainers without hanging."""
+    assert test_activities.redis_repository is not None
+    assert test_activities.mongodb_repository is not None
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_temporal_pi_happy_path(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    pi_web_api_server: PIWebAPITestServer,
+):
+    """Minimal Temporal path: PIWebAPIScouter happy path completes."""
+    scenario = load_scenario_input('pi_web_api_scouter_happy_path')
+    apply_pi_web_api_server_config(pi_web_api_server, scenario.get('pi_web_api_server'))
+    await start_and_await_workflow(
+        temporal_env.client,
+        PIWebAPIScouter.run,
+        scenario['workflow_input'],
+        make_workflow_id('smoke-pi-happy'),
+        timeout=60.0,
+    )

e2e/test_pi_web_api_scouter_early_exit.py

@@ -1,182 +0,0 @@
-"""
-End-to-end tests for PI Web API Scouter workflow - Early exit scenarios.
-"""
-
-from datetime import datetime
-from unittest.mock import AsyncMock
-
-import pandas as pd
-import pytest
-from sqlalchemy import text
-from temporalio.testing import WorkflowEnvironment
-from temporalio.worker import Worker
-
-from scouter.activities.activities import Activities
-from scouter.workflow.pi_web_api_scouter import PIWebAPIScouter
-
-
-@pytest.mark.asyncio
-@pytest.mark.integration
-async def test_scenario_1_2_1_empty_data_from_pi_web_api(
-    temporal_test_env: WorkflowEnvironment,
-    temporal_worker: Worker,
-    test_activities: Activities,
-    mock_pi_web_api_client,
-    postgres_engine,
-):
-    """
-    Scenario 1.2.1: Empty Data from PI Web API
-    
-    PI Web API returns empty data, workflow should exit early without calling core_scouter.
-    """
-    client = temporal_test_env.client
-
-    # Mock empty DataFrame response with proper datetime column
-    empty_df = pd.DataFrame({
-        'timestamp': pd.to_datetime([], utc=True),
-        'name': [],
-        'value': [],
-        'tag': [],
-    })
-    mock_pi_web_api_client.get_latest_values_df = AsyncMock(return_value=empty_df)
-
-    # Prepare test input with unique model_id to avoid conflicts
-    unique_id = int(datetime.now().timestamp())
-    input_data = {
-        'model_name': 'PI Web API Scouter Test Model',
-        'model_id': str(unique_id),
-        'schedule_name': 'pi-web-api-scouter-test-empty',
-        'model_tags': {
-            'tag1': {
-                'webid': 'webid1',
-                'aggr_function': 'avg',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-        },
-        'trigger_laborious': False,
-        'filters': {},
-        'schema': 'sientia_data',
-        'table_name': 'laborious_data',
-        'retention_time': 3600,
-        'fill_missing_tags': False,
-        'pi_web_api_query': {
-            'endpoint': '/streamsets/recorded',
-            'period': '*-1d',
-            'max_count': 10,
-            'api_timeout': 30,
-        },
-    }
-
-    # Start workflow
-    handle = await client.start_workflow(
-        PIWebAPIScouter.run,
-        input_data,
-        id=f'test-workflow-{datetime.now().timestamp()}',
-        task_queue='test-queue',
-    )
-
-    # Wait for workflow completion (should complete without error)
-    await handle.result()
-
-    # Verify PI Web API was called once
-    mock_pi_web_api_client.get_latest_values_df.assert_called_once()
-
-    # Verify no data was stored in PostgreSQL (core_scouter was not called)
-    schema_name = 'sientia_data'
-    table_name = 'laborious_data'
-    full_table_name = f"{schema_name}.{table_name}"
-
-    with postgres_engine.connect() as conn:
-        result = conn.execute(
-            text(f"SELECT COUNT(*) FROM {full_table_name} WHERE model_id = :model_id"),
-            {'model_id': unique_id}
-        )
-        row_count = result.scalar()
-
-    # Should have 0 rows since core_scouter was not called
-    assert row_count == 0, f"Expected no data in PostgreSQL, got {row_count} rows"
-
-
-@pytest.mark.asyncio
-@pytest.mark.integration
-async def test_scenario_1_2_2_none_returned_from_pi_web_api(
-    temporal_test_env: WorkflowEnvironment,
-    temporal_worker: Worker,
-    test_activities: Activities,
-    mock_pi_web_api_client,
-    postgres_engine,
-):
-    """
-    Scenario 1.2.2: None Returned from PI Web API
-    
-    PI Web API returns None, workflow should exit early without calling core_scouter.
-    """
-    client = temporal_test_env.client
-
-    # Mock empty DataFrame response (None is not handled well, so use empty DataFrame instead)
-    empty_df = pd.DataFrame({
-        'timestamp': pd.to_datetime([], utc=True),
-        'name': [],
-        'value': [],
-        'tag': [],
-    })
-    mock_pi_web_api_client.get_latest_values_df = AsyncMock(return_value=empty_df)
-
-    # Prepare test input with unique model_id to avoid conflicts
-    unique_id = int(datetime.now().timestamp())
-    input_data = {
-        'model_name': 'PI Web API Scouter Test Model',
-        'model_id': str(unique_id),
-        'schedule_name': 'pi-web-api-scouter-test-none',
-        'model_tags': {
-            'tag1': {
-                'webid': 'webid1',
-                'aggr_function': 'avg',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-        },
-        'trigger_laborious': False,
-        'filters': {},
-        'schema': 'sientia_data',
-        'table_name': 'laborious_data',
-        'retention_time': 3600,
-        'fill_missing_tags': False,
-        'pi_web_api_query': {
-            'endpoint': '/streamsets/recorded',
-            'period': '*-1d',
-            'max_count': 10,
-            'api_timeout': 30,
-        },
-    }
-
-    # Start workflow
-    handle = await client.start_workflow(
-        PIWebAPIScouter.run,
-        input_data,
-        id=f'test-workflow-{datetime.now().timestamp()}',
-        task_queue='test-queue',
-    )
-
-    # Wait for workflow completion (should complete without error)
-    await handle.result()
-
-    # Verify PI Web API was called once
-    mock_pi_web_api_client.get_latest_values_df.assert_called_once()
-
-    # Verify no data was stored in PostgreSQL (core_scouter was not called)
-    schema_name = 'sientia_data'
-    table_name = 'laborious_data'
-    full_table_name = f"{schema_name}.{table_name}"
-
-    with postgres_engine.connect() as conn:
-        result = conn.execute(
-            text(f"SELECT COUNT(*) FROM {full_table_name} WHERE model_id = :model_id"),
-            {'model_id': unique_id}
-        )
-        row_count = result.scalar()
-
-    # Should have 0 rows since core_scouter was not called
-    assert row_count == 0, f"Expected no data in PostgreSQL, got {row_count} rows"
-

e2e/test_pi_web_api_scouter_errors.py

@@ -1,206 +0,0 @@
-"""
-End-to-end tests for PI Web API Scouter workflow - Error scenarios.
-"""
-
-from datetime import datetime
-from unittest.mock import AsyncMock
-
-import pytest
-from temporalio.exceptions import ApplicationError, FailureError
-from temporalio.testing import WorkflowEnvironment
-from temporalio.worker import Worker
-
-from scouter.activities.activities import Activities
-from sientia_do.repository.pi_web_api_client import PIMSRequestError
-from scouter.workflow.pi_web_api_scouter import PIWebAPIScouter
-
-
-@pytest.mark.asyncio
-@pytest.mark.integration
-async def test_scenario_1_3_1_pi_web_api_connection_error(
-    temporal_test_env: WorkflowEnvironment,
-    temporal_worker: Worker,
-    test_activities: Activities,
-    mock_pi_web_api_client,
-):
-    """
-    Scenario 1.3.1: PI Web API Connection Error
-    
-    PI Web API client raises connection error, notification sent, workflow fails.
-    """
-    client = temporal_test_env.client
-
-    # Mock connection error
-    mock_pi_web_api_client.get_latest_values_df = AsyncMock(
-        side_effect=PIMSRequestError("Connection failed")
-    )
-
-    # Prepare test input
-    input_data = {
-        'model_name': 'PI Web API Scouter Test Model',
-        'model_id': '1',
-        'schedule_name': 'pi-web-api-scouter-test-error',
-        'model_tags': {
-            'tag1': {
-                'webid': 'webid1',
-                'aggr_function': 'avg',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-        },
-        'trigger_laborious': False,
-        'filters': {},
-        'schema': 'sientia_data',
-        'table_name': 'laborious_data',
-        'retention_time': 3600,
-        'fill_missing_tags': False,
-        'pi_web_api_query': {
-            'endpoint': '/streamsets/recorded',
-            'period': '*-1d',
-            'max_count': 10,
-            'api_timeout': 30,
-        },
-    }
-
-    # Start workflow
-    handle = await client.start_workflow(
-        PIWebAPIScouter.run,
-        input_data,
-        id=f'test-workflow-{datetime.now().timestamp()}',
-        task_queue='test-queue',
-    )
-
-    # Wait for workflow completion - should fail
-    with pytest.raises((FailureError, ApplicationError, Exception)):
-        await handle.result()
-
-    # Verify PI Web API was called
-    mock_pi_web_api_client.get_latest_values_df.assert_called()
-
-
-@pytest.mark.asyncio
-@pytest.mark.integration
-async def test_scenario_1_3_2_pi_web_api_timeout(
-    temporal_test_env: WorkflowEnvironment,
-    temporal_worker: Worker,
-    test_activities: Activities,
-    mock_pi_web_api_client,
-):
-    """
-    Scenario 1.3.2: PI Web API Timeout
-    
-    PI Web API request times out, notification sent, workflow fails.
-    """
-    client = temporal_test_env.client
-
-    # Mock timeout error
-    mock_pi_web_api_client.get_latest_values_df = AsyncMock(
-        side_effect=TimeoutError("Request timed out")
-    )
-
-    # Prepare test input with low timeout
-    input_data = {
-        'model_name': 'PI Web API Scouter Test Model',
-        'model_id': '1',
-        'schedule_name': 'pi-web-api-scouter-test-timeout',
-        'model_tags': {
-            'tag1': {
-                'webid': 'webid1',
-                'aggr_function': 'avg',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-        },
-        'trigger_laborious': False,
-        'filters': {},
-        'schema': 'sientia_data',
-        'table_name': 'laborious_data',
-        'retention_time': 3600,
-        'fill_missing_tags': False,
-        'pi_web_api_query': {
-            'endpoint': '/streamsets/recorded',
-            'period': '*-1d',
-            'max_count': 10,
-            'api_timeout': 1,  # Very short timeout
-        },
-    }
-
-    # Start workflow
-    handle = await client.start_workflow(
-        PIWebAPIScouter.run,
-        input_data,
-        id=f'test-workflow-{datetime.now().timestamp()}',
-        task_queue='test-queue',
-    )
-
-    # Wait for workflow completion - should fail
-    with pytest.raises((FailureError, ApplicationError, Exception)):
-        await handle.result()
-
-    # Verify PI Web API was called
-    mock_pi_web_api_client.get_latest_values_df.assert_called()
-
-
-@pytest.mark.asyncio
-@pytest.mark.integration
-async def test_scenario_1_3_3_invalid_endpoint(
-    temporal_test_env: WorkflowEnvironment,
-    temporal_worker: Worker,
-    test_activities: Activities,
-    mock_pi_web_api_client,
-):
-    """
-    Scenario 1.3.3: Invalid Endpoint
-    
-    Invalid PI Web API endpoint provided, error raised, workflow fails.
-    """
-    client = temporal_test_env.client
-
-    # Mock error for invalid endpoint
-    mock_pi_web_api_client.get_latest_values_df = AsyncMock(
-        side_effect=PIMSRequestError("HTTP 404 calling '/invalid/endpoint': Not found")
-    )
-
-    # Prepare test input with invalid endpoint
-    input_data = {
-        'model_name': 'PI Web API Scouter Test Model',
-        'model_id': '1',
-        'schedule_name': 'pi-web-api-scouter-test-invalid',
-        'model_tags': {
-            'tag1': {
-                'webid': 'webid1',
-                'aggr_function': 'avg',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-        },
-        'trigger_laborious': False,
-        'filters': {},
-        'schema': 'sientia_data',
-        'table_name': 'laborious_data',
-        'retention_time': 3600,
-        'fill_missing_tags': False,
-        'pi_web_api_query': {
-            'endpoint': '/invalid/endpoint',
-            'period': '*-1d',
-            'max_count': 10,
-            'api_timeout': 30,
-        },
-    }
-
-    # Start workflow
-    handle = await client.start_workflow(
-        PIWebAPIScouter.run,
-        input_data,
-        id=f'test-workflow-{datetime.now().timestamp()}',
-        task_queue='test-queue',
-    )
-
-    # Wait for workflow completion - should fail
-    with pytest.raises((FailureError, ApplicationError, Exception)):
-        await handle.result()
-
-    # Verify PI Web API was called
-    mock_pi_web_api_client.get_latest_values_df.assert_called()
-
-

e2e/test_pi_web_api_scouter_main_workflow.py

@@ -0,0 +1,222 @@
+"""
+End-to-end tests for the PIWebAPIScouter main workflow.
+"""
+
+import json
+
+import pytest
+from redis import Redis
+from temporalio.client import WorkflowFailureError
+from temporalio.testing import WorkflowEnvironment
+from temporalio.worker import Worker
+
+from e2e.conftest import E2E_DATABASE
+from e2e.helpers import (
+    apply_pi_web_api_server_config,
+    count_laborious_rows,
+    count_notifications,
+    fetch_laborious_rows,
+    load_scenario_input,
+    make_workflow_id,
+    start_and_await_workflow,
+)
+from e2e.pi_web_api_test_server import PIWebAPITestServer
+from scouter.workflow.pi_web_api_scouter import PIWebAPIScouter
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_scenario_2_1_1_happy_path(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    pi_web_api_server: PIWebAPITestServer,
+    postgres_engine,
+    redis_client: Redis,
+):
+    scenario = load_scenario_input('pi_web_api_scouter_happy_path')
+    apply_pi_web_api_server_config(pi_web_api_server, scenario.get('pi_web_api_server'))
+    workflow_input = scenario['workflow_input']
+
+    await start_and_await_workflow(
+        temporal_env.client,
+        PIWebAPIScouter.run,
+        workflow_input,
+        make_workflow_id('pi-happy'),
+    )
+
+    model_id = workflow_input['model_id']
+    assert count_laborious_rows(postgres_engine, model_id) >= 1
+    assert len(redis_client.keys('held_data_*')) >= 1
+    assert len(pi_web_api_server.requests) == 1
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_scenario_2_1_2_multiple_tags(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    pi_web_api_server: PIWebAPITestServer,
+    postgres_engine,
+):
+    scenario = load_scenario_input('pi_web_api_scouter_multiple_tags')
+    apply_pi_web_api_server_config(pi_web_api_server, scenario.get('pi_web_api_server'))
+    workflow_input = scenario['workflow_input']
+
+    await start_and_await_workflow(
+        temporal_env.client,
+        PIWebAPIScouter.run,
+        workflow_input,
+        make_workflow_id('pi-multi'),
+    )
+
+    rows = {
+        row['variable']: float(row['value'])
+        for row in fetch_laborious_rows(postgres_engine, workflow_input['model_id'])
+    }
+    for tag, expected in scenario['expected_values'].items():
+        assert tag in rows
+        assert rows[tag] == pytest.approx(expected)
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_scenario_2_1_3_debug_data_package(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    pi_web_api_server: PIWebAPITestServer,
+    redis_client: Redis,
+):
+    scenario = load_scenario_input('pi_web_api_scouter_debug_data_package')
+    apply_pi_web_api_server_config(pi_web_api_server, scenario.get('pi_web_api_server'))
+    workflow_input = scenario['workflow_input']
+
+    await start_and_await_workflow(
+        temporal_env.client,
+        PIWebAPIScouter.run,
+        workflow_input,
+        make_workflow_id('pi-debug'),
+    )
+
+    keys = redis_client.keys('data_package_pi_web_api_scouter_*')
+    assert len(keys) >= 1
+    payload = json.loads(redis_client.get(keys[0]))
+    assert 'data' in payload and 'held_data' in payload
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+@pytest.mark.xfail(
+    strict=True,
+    reason='Empty PI DataFrame lacks timestamp column in get_tag_values; tracked in fix-pi-empty-response-handling',
+)
+async def test_scenario_2_2_1_empty_response_early_exit(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    pi_web_api_server: PIWebAPITestServer,
+    postgres_engine,
+):
+    scenario = load_scenario_input('pi_web_api_scouter_empty_response')
+    apply_pi_web_api_server_config(pi_web_api_server, scenario.get('pi_web_api_server'))
+    workflow_input = scenario['workflow_input']
+
+    await start_and_await_workflow(
+        temporal_env.client,
+        PIWebAPIScouter.run,
+        workflow_input,
+        make_workflow_id('pi-empty'),
+    )
+
+    assert count_laborious_rows(postgres_engine, workflow_input['model_id']) == 0
+    assert len(pi_web_api_server.requests) == 1
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_scenario_2_3_1_pi_web_api_connection_error(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    pi_web_api_server: PIWebAPITestServer,
+    mongo_uri: str,
+):
+    scenario = load_scenario_input('pi_web_api_scouter_connection_error')
+    apply_pi_web_api_server_config(pi_web_api_server, scenario.get('pi_web_api_server'))
+    workflow_input = scenario['workflow_input']
+
+    with pytest.raises(WorkflowFailureError):
+        await start_and_await_workflow(
+            temporal_env.client,
+            PIWebAPIScouter.run,
+            workflow_input,
+            make_workflow_id('pi-conn-error'),
+        )
+
+    assert (
+        count_notifications(
+            mongo_uri,
+            E2E_DATABASE,
+            notification_id='PI_WEB_API_REQUEST_ERROR',
+            level='ERROR',
+        )
+        >= 1
+    )
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_scenario_2_3_2_pi_web_api_timeout(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    pi_web_api_server: PIWebAPITestServer,
+    mongo_uri: str,
+):
+    scenario = load_scenario_input('pi_web_api_scouter_timeout')
+    apply_pi_web_api_server_config(pi_web_api_server, scenario.get('pi_web_api_server'))
+    workflow_input = scenario['workflow_input']
+
+    with pytest.raises(WorkflowFailureError):
+        await start_and_await_workflow(
+            temporal_env.client,
+            PIWebAPIScouter.run,
+            workflow_input,
+            make_workflow_id('pi-timeout'),
+            timeout=180.0,
+        )
+
+    assert (
+        count_notifications(
+            mongo_uri,
+            E2E_DATABASE,
+            notification_id='PI_WEB_API_REQUEST_ERROR',
+        )
+        >= 1
+    )
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_scenario_2_3_3_invalid_endpoint(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    pi_web_api_server: PIWebAPITestServer,
+    mongo_uri: str,
+):
+    scenario = load_scenario_input('pi_web_api_scouter_invalid_endpoint')
+    apply_pi_web_api_server_config(pi_web_api_server, scenario.get('pi_web_api_server'))
+    workflow_input = scenario['workflow_input']
+
+    with pytest.raises(WorkflowFailureError):
+        await start_and_await_workflow(
+            temporal_env.client,
+            PIWebAPIScouter.run,
+            workflow_input,
+            make_workflow_id('pi-invalid-endpoint'),
+        )
+
+    assert (
+        count_notifications(
+            mongo_uri,
+            E2E_DATABASE,
+            notification_id='PI_WEB_API_REQUEST_ERROR',
+        )
+        >= 1
+    )

e2e/test_pi_web_api_scouter_success.py

@@ -1,396 +0,0 @@
-"""
-End-to-end tests for PI Web API Scouter workflow - Success scenarios.
-"""
-
-from datetime import datetime
-from unittest.mock import AsyncMock
-
-import pandas as pd
-import pytest
-from sqlalchemy import inspect, text
-from temporalio.testing import WorkflowEnvironment
-from temporalio.worker import Worker
-
-from scouter.activities.activities import Activities
-from scouter.workflow.pi_web_api_scouter import PIWebAPIScouter
-
-
-@pytest.mark.asyncio
-@pytest.mark.integration
-async def test_scenario_1_1_1_happy_path_complete_success(
-    temporal_test_env: WorkflowEnvironment,
-    temporal_worker: Worker,
-    test_activities: Activities,
-    mock_pi_web_api_client,
-    postgres_engine,
-):
-    """
-    Scenario 1.1.1: Happy Path - Complete Success
-    
-    Workflow completes successfully with valid data from PI Web API.
-    """
-    client = temporal_test_env.client
-
-    # Prepare test input
-    input_data = {
-        'model_name': 'PI Web API Scouter Test Model',
-        'model_id': '1',
-        'schedule_name': 'pi-web-api-scouter-test',
-        'model_tags': {
-            'tag1': {
-                'webid': 'webid1',
-                'aggr_function': 'avg',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-            'tag2': {
-                'webid': 'webid2',
-                'aggr_function': 'avg',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-        },
-        'trigger_laborious': False,
-        'filters': {},
-        'schema': 'sientia_data',
-        'table_name': 'laborious_data',
-        'retention_time': 3600,
-        'fill_missing_tags': False,
-        'pi_web_api_query': {
-            'endpoint': '/streamsets/recorded',
-            'period': '*-1d',
-            'max_count': 10,
-            'api_timeout': 30,
-        },
-    }
-
-    # Start workflow
-    handle = await client.start_workflow(
-        PIWebAPIScouter.run,
-        input_data,
-        id=f'test-workflow-{datetime.now().timestamp()}',
-        task_queue='test-queue',
-    )
-
-    # Wait for workflow completion
-    await handle.result()
-
-    # Verify PI Web API was called once with correct parameters
-    mock_pi_web_api_client.get_latest_values_df.assert_called_once()
-
-    # Verify data was stored in PostgreSQL
-    inspector = inspect(postgres_engine)
-    schema_name = 'sientia_data'
-    table_name = 'laborious_data'
-    full_table_name = f"{schema_name}.{table_name}"
-
-    table_exists = inspector.has_table(table_name, schema=schema_name)
-    assert table_exists, f"Expected table {full_table_name} to exist in PostgreSQL"
-
-    # Verify data was inserted
-    with postgres_engine.connect() as conn:
-        result = conn.execute(text(f"SELECT COUNT(*) FROM {full_table_name}"))
-        row_count = result.scalar()
-
-    assert row_count > 0, f"Expected data in PostgreSQL table {full_table_name}, got {row_count} rows"
-
-    # Verify data was cached in Redis
-    keys = await test_activities.redis_repository.keys('*')
-    assert len(keys) > 0, "Expected data in Redis"
-
-
-@pytest.mark.asyncio
-@pytest.mark.integration
-async def test_scenario_1_1_2_success_with_multiple_tags(
-    temporal_test_env: WorkflowEnvironment,
-    temporal_worker: Worker,
-    test_activities: Activities,
-    mock_pi_web_api_client,
-    postgres_engine,
-):
-    """
-    Scenario 1.1.2: Success with Multiple Tags
-    
-    Workflow processes multiple tags successfully.
-    """
-    client = temporal_test_env.client
-
-    # Create mock DataFrame with 5 tags
-    mock_df = pd.DataFrame({
-        'timestamp': [
-            '2024-01-01 12:00:00+0000',
-            '2024-01-01 12:01:00+0000',
-            '2024-01-01 12:02:00+0000',
-            '2024-01-01 12:03:00+0000',
-            '2024-01-01 12:04:00+0000',
-        ],
-        'name': ['tag1', 'tag2', 'tag3', 'tag4', 'tag5'],
-        'value': [10.5, 20.3, 30.7, 40.1, 50.9],
-        'tag': ['webid1', 'webid2', 'webid3', 'webid4', 'webid5'],
-    })
-    mock_df['timestamp'] = pd.to_datetime(mock_df['timestamp'], utc=True).dt.floor('s')
-    mock_pi_web_api_client.get_latest_values_df = AsyncMock(return_value=mock_df)
-
-    # Prepare test input with 5 tags
-    input_data = {
-        'model_name': 'PI Web API Scouter Test Model',
-        'model_id': '1',
-        'schedule_name': 'pi-web-api-scouter-test-multiple',
-        'model_tags': {
-            'tag1': {
-                'webid': 'webid1',
-                'aggr_function': 'avg',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-            'tag2': {
-                'webid': 'webid2',
-                'aggr_function': 'max',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-            'tag3': {
-                'webid': 'webid3',
-                'aggr_function': 'min',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-            'tag4': {
-                'webid': 'webid4',
-                'aggr_function': 'mdn',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-            'tag5': {
-                'webid': 'webid5',
-                'aggr_function': 'lts',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-        },
-        'trigger_laborious': False,
-        'filters': {},
-        'schema': 'sientia_data',
-        'table_name': 'laborious_data',
-        'retention_time': 3600,
-        'fill_missing_tags': False,
-        'pi_web_api_query': {
-            'endpoint': '/streamsets/recorded',
-            'period': '*-1d',
-            'max_count': 10,
-            'api_timeout': 30,
-        },
-    }
-
-    # Start workflow
-    handle = await client.start_workflow(
-        PIWebAPIScouter.run,
-        input_data,
-        id=f'test-workflow-{datetime.now().timestamp()}',
-        task_queue='test-queue',
-    )
-
-    # Wait for workflow completion
-    await handle.result()
-
-    # Verify all tags were retrieved
-    mock_pi_web_api_client.get_latest_values_df.assert_called_once()
-
-    # Verify data was stored in PostgreSQL
-    schema_name = 'sientia_data'
-    table_name = 'laborious_data'
-    full_table_name = f"{schema_name}.{table_name}"
-
-    with postgres_engine.connect() as conn:
-        result = conn.execute(
-            text(f"SELECT COUNT(*) FROM {full_table_name} WHERE model_id = 1")
-        )
-        row_count = result.scalar()
-
-    # Should have at least 5 rows (one per tag)
-    assert row_count >= 5, f"Expected at least 5 records, got {row_count}"
-
-    # Verify all tags are present in the database
-    with postgres_engine.connect() as conn:
-        result = conn.execute(
-            text(f"SELECT DISTINCT variable FROM {full_table_name} WHERE model_id = 1")
-        )
-        variables = [row[0] for row in result.fetchall()]
-
-    expected_tags = ['tag1', 'tag2', 'tag3', 'tag4', 'tag5']
-    for tag in expected_tags:
-        assert tag in variables, f"Expected tag {tag} to be in database"
-
-
-@pytest.mark.asyncio
-@pytest.mark.integration
-async def test_scenario_1_1_3_success_with_debug_data_package(
-    temporal_test_env: WorkflowEnvironment,
-    temporal_worker: Worker,
-    test_activities: Activities,
-    mock_pi_web_api_client,
-    postgres_engine,
-):
-    """
-    Scenario 1.1.3: Success with Debug Data Package Enabled
-    
-    Workflow completes with debug_data_package=True.
-    """
-    client = temporal_test_env.client
-
-    # Generate unique model_id to avoid conflicts with other tests
-    unique_id = int(datetime.now().timestamp() * 1000) % 1000000
-
-    # Prepare test input with debug_data_package enabled
-    input_data = {
-        'model_name': 'PI Web API Scouter Test Model',
-        'model_id': str(unique_id),
-        'schedule_name': 'pi-web-api-scouter-test-debug',
-        'model_tags': {
-            'tag1': {
-                'webid': 'webid1',
-                'aggr_function': 'avg',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-        },
-        'trigger_laborious': False,
-        'filters': {},
-        'schema': 'sientia_data',
-        'table_name': 'laborious_data',
-        'retention_time': 3600,
-        'fill_missing_tags': False,
-        'debug_data_package': True,
-        'pi_web_api_query': {
-            'endpoint': '/streamsets/recorded',
-            'period': '*-1d',
-            'max_count': 10,
-            'api_timeout': 30,
-        },
-    }
-
-    # Start workflow
-    handle = await client.start_workflow(
-        PIWebAPIScouter.run,
-        input_data,
-        id=f'test-workflow-{datetime.now().timestamp()}',
-        task_queue='test-queue',
-    )
-
-    # Wait for workflow completion
-    await handle.result()
-
-    # Verify PI Web API was called
-    mock_pi_web_api_client.get_latest_values_df.assert_called_once()
-
-    # Verify data package was stored in Redis
-    # The key format is: data_package_{workflow_name}_{schedule_name}_{timestamp}
-    keys = await test_activities.redis_repository.keys('data_package_*')
-    assert len(keys) > 0, f"Expected data package key in Redis, found keys: {keys}"
-
-    # Verify the data package contains both 'data' and 'held_data'
-    if keys:
-        package_key = keys[0]
-        package_data = await test_activities.redis_repository.get(package_key)
-        assert package_data is not None, "Expected data package to exist"
-        # The package should be a dict with 'data' and 'held_data' keys
-        assert isinstance(package_data, dict), "Expected data package to be a dict"
-
-
-@pytest.mark.asyncio
-@pytest.mark.integration
-async def test_scenario_1_1_4_idempotent_export_ignores_duplicates(
-    temporal_test_env: WorkflowEnvironment,
-    temporal_worker: Worker,
-    mock_pi_web_api_client,
-    postgres_engine,
-):
-    """
-    Scenario 1.1.4: Idempotent export ignores duplicates.
-
-    Running the same batch twice must not increase row count for the same
-    (model_id, timestamp, variable) keys.
-    """
-    client = temporal_test_env.client
-    unique_id = int(datetime.now().timestamp() * 1000) % 1000000
-
-    input_data = {
-        'model_name': 'PI Web API Scouter Test Model',
-        'model_id': str(unique_id),
-        'schedule_name': f'pi-web-api-scouter-idempotent-{unique_id}',
-        'model_tags': {
-            'tag1': {
-                'webid': 'webid1',
-                'aggr_function': 'avg',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-            'tag2': {
-                'webid': 'webid2',
-                'aggr_function': 'avg',
-                'data_range': [0, 100],
-                'frequency': 60000,
-            },
-        },
-        'trigger_laborious': False,
-        'filters': {},
-        'schema': 'sientia_data',
-        'table_name': 'laborious_data',
-        'retention_time': 3600,
-        'fill_missing_tags': False,
-        'pi_web_api_query': {
-            'endpoint': '/streamsets/recorded',
-            'period': '*-1d',
-            'max_count': 10,
-            'api_timeout': 30,
-        },
-    }
-
-    first_handle = await client.start_workflow(
-        PIWebAPIScouter.run,
-        input_data,
-        id=f'test-workflow-idempotent-1-{unique_id}',
-        task_queue='test-queue',
-    )
-    await first_handle.result()
-
-    second_handle = await client.start_workflow(
-        PIWebAPIScouter.run,
-        input_data,
-        id=f'test-workflow-idempotent-2-{unique_id}',
-        task_queue='test-queue',
-    )
-    await second_handle.result()
-
-    schema_name = 'sientia_data'
-    table_name = 'laborious_data'
-    full_table_name = f"{schema_name}.{table_name}"
-
-    with postgres_engine.connect() as conn:
-        total_count_query = text(
-            f"""
-            SELECT COUNT(*)
-            FROM {full_table_name}
-            WHERE model_id = :model_id
-            """
-        )
-        total_count = conn.execute(total_count_query, {'model_id': unique_id}).scalar()
-
-        unique_count_query = text(
-            f"""
-            SELECT COUNT(*)
-            FROM (
-                SELECT DISTINCT model_id, "timestamp", variable
-                FROM {full_table_name}
-                WHERE model_id = :model_id
-            ) unique_rows
-            """
-        )
-        unique_count = conn.execute(unique_count_query, {'model_id': unique_id}).scalar()
-
-    assert total_count > 0, "Expected exported rows for idempotency scenario"
-    assert total_count == unique_count, (
-        "Expected no duplicate rows for same (model_id, timestamp, variable)"
-    )
-    assert mock_pi_web_api_client.get_latest_values_df.call_count == 2
-

e2e/test_scouter_main_workflow.py

@@ -0,0 +1,154 @@
+"""
+End-to-end tests for the Scouter main workflow (Mongo load path).
+"""
+
+import json
+
+import pytest
+from redis import Redis
+
+from e2e.conftest import E2E_DATABASE
+from e2e.helpers import (
+    count_laborious_rows,
+    load_scenario_input,
+    make_workflow_id,
+    seed_last_data_timestamp,
+    seed_raw_collection,
+    start_and_await_workflow,
+)
+from scouter.workflow.scouter import Scouter
+from temporalio.testing import WorkflowEnvironment
+from temporalio.worker import Worker
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_scenario_1_1_1_happy_path(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    mongo_uri: str,
+    redis_client: Redis,
+    postgres_engine,
+):
+    scenario = load_scenario_input('scouter_happy_path')
+    workflow_input = scenario['workflow_input']
+    seed_raw_collection(
+        mongo_uri,
+        E2E_DATABASE,
+        workflow_input['schedule_name'],
+        scenario['raw_documents'],
+    )
+
+    await start_and_await_workflow(
+        temporal_env.client,
+        Scouter.run,
+        workflow_input,
+        make_workflow_id('scouter-happy'),
+    )
+
+    model_id = workflow_input['model_id']
+    assert count_laborious_rows(postgres_engine, model_id) >= 1
+
+    key = f"last_data_timestamp:scouter:{workflow_input['schedule_name']}"
+    assert redis_client.get(key) is not None
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_scenario_1_2_1_incremental_load(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    mongo_uri: str,
+    redis_client: Redis,
+    postgres_engine,
+):
+    scenario = load_scenario_input('scouter_incremental_load')
+    workflow_input = scenario['workflow_input']
+    redis_seed = scenario['redis_seed']
+    seed_last_data_timestamp(
+        redis_client,
+        'scouter',
+        workflow_input['schedule_name'],
+        redis_seed['last_data_timestamp'],
+    )
+    seed_raw_collection(
+        mongo_uri,
+        E2E_DATABASE,
+        workflow_input['schedule_name'],
+        scenario['raw_documents'],
+    )
+
+    await start_and_await_workflow(
+        temporal_env.client,
+        Scouter.run,
+        workflow_input,
+        make_workflow_id('scouter-incremental'),
+    )
+
+    model_id = workflow_input['model_id']
+    assert count_laborious_rows(postgres_engine, model_id) == scenario['expected_newer_count']
+
+    stored = json.loads(
+        redis_client.get(f"last_data_timestamp:scouter:{workflow_input['schedule_name']}")
+    )
+    assert stored == scenario['expected_last_timestamp']
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_scenario_1_3_1_empty_mongo_early_exit(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    mongo_uri: str,
+    redis_client: Redis,
+    postgres_engine,
+):
+    scenario = load_scenario_input('scouter_empty_mongo')
+    workflow_input = scenario['workflow_input']
+    seed_raw_collection(
+        mongo_uri,
+        E2E_DATABASE,
+        workflow_input['schedule_name'],
+        scenario['raw_documents'],
+    )
+
+    await start_and_await_workflow(
+        temporal_env.client,
+        Scouter.run,
+        workflow_input,
+        make_workflow_id('scouter-empty'),
+    )
+
+    assert count_laborious_rows(postgres_engine, workflow_input['model_id']) == 0
+    key = f"last_data_timestamp:scouter:{workflow_input['schedule_name']}"
+    assert redis_client.get(key) is None
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_scenario_1_3_2_no_redis_timestamp_first_run(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    mongo_uri: str,
+    redis_client: Redis,
+    postgres_engine,
+):
+    scenario = load_scenario_input('scouter_no_redis_timestamp_first_run')
+    workflow_input = scenario['workflow_input']
+    seed_raw_collection(
+        mongo_uri,
+        E2E_DATABASE,
+        workflow_input['schedule_name'],
+        scenario['raw_documents'],
+    )
+
+    await start_and_await_workflow(
+        temporal_env.client,
+        Scouter.run,
+        workflow_input,
+        make_workflow_id('scouter-first-run'),
+    )
+
+    assert count_laborious_rows(postgres_engine, workflow_input['model_id']) >= 1
+    key = f"last_data_timestamp:scouter:{workflow_input['schedule_name']}"
+    assert redis_client.get(key) is not None

e2e/test_subworkflow_core_scouter.py

@@ -0,0 +1,360 @@
+"""
+End-to-end tests for the CoreScouter subworkflow.
+"""
+
+import json
+
+import pytest
+from redis import Redis
+from sqlalchemy import text
+from temporalio.client import WorkflowFailureError
+from temporalio.testing import WorkflowEnvironment
+from temporalio.worker import Worker
+
+from e2e.conftest import E2E_DATABASE
+from e2e.helpers import (
+    count_laborious_rows,
+    count_notifications,
+    fetch_laborious_rows,
+    load_scenario_input,
+    make_workflow_id,
+    start_and_await_workflow,
+)
+from scouter.activities.activities import Activities
+from scouter.workflow.sub_workflows.core_scouter import CoreScouter
+
+
+def _held_data_blob(test_activities: Activities, workflow_input: dict) -> dict | None:
+    """
+    Read held_data Redis payload via the production RedisRepository.
+
+    Return:
+        Decoded held-data dict or None
+    """
+    key = (
+        f"held_data_{workflow_input['workflow_name']}_{workflow_input['schedule_name']}"
+    )
+    metadata = workflow_input['metadata']['metadata']
+    return test_activities.redis_repository.get(key, metadata=metadata)
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_scenario_3_1_1_complete_processing_success(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    test_activities: Activities,
+    postgres_engine,
+    redis_client: Redis,
+):
+    scenario = load_scenario_input('core_scouter_happy_path')
+    workflow_input = scenario['workflow_input']
+
+    await start_and_await_workflow(
+        temporal_env.client,
+        CoreScouter.run,
+        workflow_input,
+        make_workflow_id('core-happy'),
+    )
+
+    assert count_laborious_rows(postgres_engine, workflow_input['model_id']) >= 1
+    assert _held_data_blob(test_activities, workflow_input) is not None
+    assert len(redis_client.keys('data_package_*')) == 0
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_scenario_3_1_2_null_values_filter_discard(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    mongo_uri: str,
+    postgres_engine,
+):
+    scenario = load_scenario_input('core_scouter_null_values_filter_discard')
+    workflow_input = scenario['workflow_input']
+
+    await start_and_await_workflow(
+        temporal_env.client,
+        CoreScouter.run,
+        workflow_input,
+        make_workflow_id('core-null-discard'),
+    )
+
+    assert (
+        count_notifications(
+            mongo_uri,
+            E2E_DATABASE,
+            notification_id='DATA_QUALITY_GATE_ISSUES__NULL_VALUES_FILTER',
+            level='WARNING',
+        )
+        == 1
+    )
+    rows = fetch_laborious_rows(postgres_engine, workflow_input['model_id'])
+    assert len(rows) == 1
+    assert rows[0]['variable'] == 'tag2'
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_scenario_3_1_3_null_values_filter_warn(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    mongo_uri: str,
+    postgres_engine,
+):
+    scenario = load_scenario_input('core_scouter_null_values_filter_warn')
+    workflow_input = scenario['workflow_input']
+
+    await start_and_await_workflow(
+        temporal_env.client,
+        CoreScouter.run,
+        workflow_input,
+        make_workflow_id('core-null-warn'),
+    )
+
+    assert (
+        count_notifications(
+            mongo_uri,
+            E2E_DATABASE,
+            notification_id='DATA_QUALITY_GATE_ISSUES__NULL_VALUES_FILTER',
+            level='WARNING',
+        )
+        == 1
+    )
+    assert count_laborious_rows(postgres_engine, workflow_input['model_id']) == 2
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_scenario_3_1_4_out_of_bounds_filter_discard(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    mongo_uri: str,
+    postgres_engine,
+):
+    scenario = load_scenario_input('core_scouter_out_of_bounds_filter_discard')
+    workflow_input = scenario['workflow_input']
+
+    await start_and_await_workflow(
+        temporal_env.client,
+        CoreScouter.run,
+        workflow_input,
+        make_workflow_id('core-oob-discard'),
+    )
+
+    assert (
+        count_notifications(
+            mongo_uri,
+            E2E_DATABASE,
+            notification_id='DATA_QUALITY_GATE_ISSUES__OUT_OF_BOUNDS_FILTER',
+            level='WARNING',
+        )
+        == 1
+    )
+    rows = fetch_laborious_rows(postgres_engine, workflow_input['model_id'])
+    assert len(rows) == 1
+    assert rows[0]['variable'] == 'tag2'
+
+
+async def _run_aggregation_scenario(
+    temporal_env: WorkflowEnvironment,
+    postgres_engine,
+    slug: str,
+    workflow_id_prefix: str,
+) -> None:
+    scenario = load_scenario_input(slug)
+    workflow_input = scenario['workflow_input']
+    await start_and_await_workflow(
+        temporal_env.client,
+        CoreScouter.run,
+        workflow_input,
+        make_workflow_id(workflow_id_prefix),
+    )
+    rows = fetch_laborious_rows(postgres_engine, workflow_input['model_id'])
+    tag_name = next(iter(workflow_input['model_tags']))
+    value = next(row['value'] for row in rows if row['variable'] == tag_name)
+    assert float(value) == pytest.approx(scenario['expected_value'])
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_scenario_3_1_5_aggregation_avg(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    await _run_aggregation_scenario(
+        temporal_env, postgres_engine, 'core_scouter_aggregation_avg', 'core-avg'
+    )
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_scenario_3_1_6_aggregation_mdn(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    await _run_aggregation_scenario(
+        temporal_env, postgres_engine, 'core_scouter_aggregation_mdn', 'core-mdn'
+    )
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_scenario_3_1_7_aggregation_max(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    await _run_aggregation_scenario(
+        temporal_env, postgres_engine, 'core_scouter_aggregation_max', 'core-max'
+    )
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_scenario_3_1_8_aggregation_min(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    await _run_aggregation_scenario(
+        temporal_env, postgres_engine, 'core_scouter_aggregation_min', 'core-min'
+    )
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_scenario_3_1_9_aggregation_lts(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    await _run_aggregation_scenario(
+        temporal_env, postgres_engine, 'core_scouter_aggregation_lts', 'core-lts'
+    )
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_scenario_3_1_10_fill_missing_tags(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    test_activities: Activities,
+):
+    scenario = load_scenario_input('core_scouter_fill_missing_tags')
+    workflow_input = scenario['workflow_input']
+
+    await start_and_await_workflow(
+        temporal_env.client,
+        CoreScouter.run,
+        workflow_input,
+        make_workflow_id('core-fill-tags'),
+    )
+
+    held = _held_data_blob(test_activities, workflow_input)
+    assert held is not None
+    for tag in scenario['expected_missing_tags']:
+        assert tag in held
+        assert held[tag] is None
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_scenario_3_1_11_debug_data_package(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    redis_client: Redis,
+):
+    scenario = load_scenario_input('core_scouter_debug_data_package')
+    workflow_input = scenario['workflow_input']
+
+    await start_and_await_workflow(
+        temporal_env.client,
+        CoreScouter.run,
+        workflow_input,
+        make_workflow_id('core-debug-pkg'),
+    )
+
+    keys = redis_client.keys('data_package_*')
+    assert len(keys) >= 1
+    payload = json.loads(redis_client.get(keys[0]))
+    assert 'data' in payload and 'held_data' in payload
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_scenario_3_2_1_empty_after_grouping_early_exit(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    test_activities: Activities,
+    postgres_engine,
+):
+    scenario = load_scenario_input('core_scouter_empty_after_grouping')
+    workflow_input = scenario['workflow_input']
+
+    await start_and_await_workflow(
+        temporal_env.client,
+        CoreScouter.run,
+        workflow_input,
+        make_workflow_id('core-empty-group'),
+    )
+
+    assert count_laborious_rows(postgres_engine, workflow_input['model_id']) == 0
+    assert _held_data_blob(test_activities, workflow_input) is None
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_scenario_3_3_1_invalid_aggregation_function(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    mongo_uri: str,
+    postgres_engine,
+):
+    scenario = load_scenario_input('core_scouter_invalid_aggregation')
+    workflow_input = scenario['workflow_input']
+
+    await start_and_await_workflow(
+        temporal_env.client,
+        CoreScouter.run,
+        workflow_input,
+        make_workflow_id('core-bad-aggr'),
+    )
+
+    variables = {row['variable'] for row in fetch_laborious_rows(postgres_engine, workflow_input['model_id'])}
+    assert 'tag_bad' not in variables
+    assert 'tag_ok' in variables
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_scenario_3_3_2_postgres_export_failure_surfaces(
+    temporal_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    mongo_uri: str,
+    postgres_engine,
+):
+    scenario = load_scenario_input('core_scouter_postgres_export_failure')
+    workflow_input = scenario['workflow_input']
+
+    with postgres_engine.begin() as conn:
+        conn.execute(text('ALTER TABLE sientia_data.laborious_data DROP COLUMN value'))
+
+    with pytest.raises(WorkflowFailureError):
+        await start_and_await_workflow(
+            temporal_env.client,
+            CoreScouter.run,
+            workflow_input,
+            make_workflow_id('core-pg-fail'),
+        )
+
+    assert (
+        count_notifications(
+            mongo_uri,
+            E2E_DATABASE,
+            notification_id='ERROR_EXPORTING_DATA_TO_POSTGRES',
+        )
+        >= 1
+    )

pyproject.toml

@@ -116,9 +116,11 @@ addopts = [
     "--strict-markers",
 ]
 asyncio_mode = "auto"
-asyncio_default_fixture_loop_scope = "function"
+asyncio_default_fixture_loop_scope = "session"
+asyncio_default_test_loop_scope = "session"
 markers = [
     "asyncio: marks tests as async",
+    "e2e: end-to-end tests against real backing services (Docker required)",
     "integration: marks tests as integration tests",
     "unit: marks tests as unit tests",
 ]

requirements-dev.txt

@@ -15,10 +15,9 @@ pytest-cov>=4.1.0        # Coverage plugin for pytest
 pytest-asyncio>=0.21.0   # Async test support (already in main requirements)
 
 # E2E Testing Dependencies
-fakeredis>=2.20.0        # In-memory Redis server for testing
-mongomock>=4.1.2         # In-memory MongoDB for testing
+pytest-httpserver>=1.0.10
 
 # Development Tools
 ipython>=8.12.0          # Enhanced Python shell
 ipdb>=0.13.13            # IPython debugger
-testcontainers[postgres]
+testcontainers[postgres,mongodb,redis]>=4.0

requirements-local.txt

@@ -0,0 +1,8 @@
+temporalio
+psycopg2-binary
+sqlalchemy
+redis
+pymongo
+git+ssh://git@github.com/Aignosi/sientia-dataops-library.git@1.12.1
+prometheus-client
+pycurl

requirements.txt

@@ -3,6 +3,6 @@ psycopg2-binary
 sqlalchemy
 redis
 pymongo
-git+ssh://git@github.com/Aignosi/sientia-dataops-library.git@1.8.2
+sientia_do
 prometheus-client
 pycurl

scouter/activities/activities.py

@@ -7,7 +7,7 @@ with workflow.unsafe.imports_passed_through():
 
     from sientia_do.notifications.handlers import CoreNotificationHandler as NotificationHandler
     from sientia_do.observability.logger import Logger
-    from sientia_do.temporal.activities.postgres import Postgres
+    from sientia_do.temporal.activities.postgres_sync import Postgres
 
     from scouter.activities.api import API
     from scouter.activities.gates import Gates

scouter/activities/api.py

@@ -9,7 +9,7 @@ with workflow.unsafe.imports_passed_through():
     from sientia_do.observability.logger import Logger
     from sientia_do.observability.metrics_controller import MetricsController
     from sientia_do.observability.sientia_monitoring import SientiaMonitoring
-    from sientia_do.repository.pi_web_api_client import PIWebAPIClient
+    from sientia_do.repository.pi_web_api_client_sync import PIWebAPIClient
     from sientia_do.temporal.constants import DATETIME_FORMAT_WITH_TZ
 
 
@@ -78,7 +78,7 @@ class API(SientiaMonitoring):
         SientiaMonitoring.shutdown(self)
 
     @activity.defn(name='get_tag_values')
-    async def get_tag_values(self, input_data: dict[str, Any]) -> list[dict]:
+    def get_tag_values(self, input_data: dict[str, Any]) -> list[dict]:
         """
         Retrieve tag values from PI Web API for specified WebIds.
 
@@ -123,7 +123,7 @@ class API(SientiaMonitoring):
         self.info(f'Getting tag values from {endpoint}', metadata=metadata)
         self.debug(f'Web IDs: {web_ids}', metadata=metadata)
         try:
-            latest_values = await self.pi_web_api_client.get_latest_values_df(
+            latest_values = self.pi_web_api_client.get_latest_values_df(
                 endpoint=endpoint,
                 web_ids=web_ids,
                 start_time=period,
@@ -134,7 +134,7 @@ class API(SientiaMonitoring):
             )
 
         except Exception as e:
-            await self.send_notification_async(
+            self.send_notification(
                 metadata=metadata,
                 notification_id='PI_WEB_API_REQUEST_ERROR',
                 message=f'Error getting tag values from PI Web API: {e}',

scouter/activities/gates.py

@@ -59,7 +59,7 @@ class Gates(SientiaMonitoring):
         """
         SientiaMonitoring.shutdown(self)
 
-    async def apply_aggregation(
+    def apply_aggregation(
         self, values: DataFrame, aggr_function: str, metadata: dict[str, Any]
     ) -> float | None | str:
         """
@@ -82,31 +82,16 @@ class Gates(SientiaMonitoring):
         Raises:
             NotificationError: If invalid aggregation function is specified
         """
-        # Fast path for single value
-        if len(values) == 1:
-            return values['value'].iloc[0]
-
-        if aggr_function == 'lts':
-            return values['value'].iloc[-1]
-
-        # Remove NaN values without inplace operation
-        clean_values = values['value'].dropna()
-
-        if clean_values.empty:
-            return None
-
-        # Use dictionary lookup for aggregation functions (faster than if-elif chain)
         aggregation_map = {
+            'lts': lambda x: x.iloc[-1],
             'avg': lambda x: x.mean(),
             'mdn': lambda x: x.median(),
             'max': lambda x: x.max(),
             'min': lambda x: x.min(),
         }
 
-        if aggr_function in aggregation_map:
-            return aggregation_map[aggr_function](clean_values)
-        else:
-            await self.send_notification_async(
+        if aggr_function not in aggregation_map:
+            self.send_notification(
                 metadata=metadata,
                 notification_id='AGGREGATION_ISSUES',
                 message=f'Invalid aggregation function: {aggr_function}',
@@ -116,8 +101,21 @@ class Gates(SientiaMonitoring):
             )
             return 'continue'
 
+        if len(values) == 1:
+            return values['value'].iloc[0]
+
+        if aggr_function == 'lts':
+            return aggregation_map['lts'](values['value'])
+
+        clean_values = values['value'].dropna()
+
+        if clean_values.empty:
+            return None
+
+        return aggregation_map[aggr_function](clean_values)
+
     @activity.defn(name='aggregate_data')
-    async def aggregate_data(self, input_data: dict[str, Any]) -> dict[Hashable, Any]:
+    def aggregate_data(self, input_data: dict[str, Any]) -> dict[Hashable, Any]:
         """
         Aggregate time-series data by tag and name using specified functions.
 
@@ -165,7 +163,7 @@ class Gates(SientiaMonitoring):
                 # Get the latest timestamp (last row since data is sorted)
                 latest_timestamp = group['timestamp'].iloc[-1]
 
-                aggr_value = await self.apply_aggregation(group, aggr_function, metadata)
+                aggr_value = self.apply_aggregation(group, aggr_function, metadata)
 
                 if aggr_value == 'continue':
                     continue
@@ -197,7 +195,7 @@ class Gates(SientiaMonitoring):
         except Exception as e:
             trace = traceback.format_exc()
 
-            await self.send_notification_async(
+            self.send_notification(
                 metadata=metadata,
                 notification_id='AGGREGATION_ISSUES',
                 message=f'Error aggregating data: {e}',
@@ -210,7 +208,7 @@ class Gates(SientiaMonitoring):
             raise e
 
     @activity.defn(name='data_quality_gate')
-    async def data_quality_gate(self, input_data: dict[str, Any]) -> dict[Hashable, Any]:
+    def data_quality_gate(self, input_data: dict[str, Any]) -> dict[Hashable, Any]:
         """
         Apply data quality filters to incoming data.
 
@@ -255,7 +253,7 @@ class Gates(SientiaMonitoring):
 
             except Exception as e:
                 trace = traceback.format_exc()
-                await self.send_notification_async(
+                self.send_notification(
                     metadata=metadata,
                     notification_id='DATA_QUALITY_GATE_ISSUES',
                     message=f'Error applying filter {filter_name}: {e}',
@@ -273,7 +271,7 @@ class Gates(SientiaMonitoring):
                 message = f'{len(filtered_data)} rows has quality issues: {filter_name}: {policy}'
                 attachment = filtered_data.to_string()
 
-                await self.send_notification_async(
+                self.send_notification(
                     metadata=metadata,
                     notification_id=f'DATA_QUALITY_GATE_ISSUES__{filter_name}',
                     message=message,
@@ -290,7 +288,7 @@ class Gates(SientiaMonitoring):
         return data.to_dict()
 
     @activity.defn(name='write_metrics')
-    async def write_metrics(self, input_data: dict[str, Any]) -> None:
+    def write_metrics(self, input_data: dict[str, Any]) -> None:
         """
         Write metrics to the database.
         input_data:

scouter/activities/mongodb.py

@@ -12,7 +12,7 @@ with workflow.unsafe.imports_passed_through():
     from sientia_do.notifications.models import NotificationLevel
     from sientia_do.observability.logger import Logger
     from sientia_do.observability.sientia_monitoring import SientiaMonitoring
-    from sientia_do.repository.mongodb_repository import MongoDBRepository
+    from sientia_do.repository.mongodb_repository_sync import MongoDBRepository
     from sientia_do.temporal.constants import DATETIME_FORMAT_MS_WITH_TZ
 
 
@@ -84,7 +84,7 @@ class MongoDB(SientiaMonitoring):
         self.close()
 
     @activity.defn(name='load_latest_data')
-    async def load_latest_data(self, input_data: dict[str, Any]) -> list[dict[str, Any]]:
+    def load_latest_data(self, input_data: dict[str, Any]) -> list[dict[str, Any]]:
         """
         Load the latest data from MongoDB collection since a specified timestamp.
 
@@ -123,7 +123,7 @@ class MongoDB(SientiaMonitoring):
 
             self.debug(f'Data filter: {data_filter}', metadata=metadata)
 
-            data = await self.mongodb_repository.find(
+            data = self.mongodb_repository.find(
                 collection_name=collection_name,
                 filters=data_filter,
                 metadata=metadata,
@@ -143,7 +143,7 @@ class MongoDB(SientiaMonitoring):
             return data
         except Exception as e:
             trace = traceback.format_exc()
-            await self.send_notification_async(
+            self.send_notification(
                 metadata=metadata,
                 notification_id='MONGO_LOAD_ERROR',
                 message=f'Error loading data from MongoDB: {e}',

scouter/activities/redis.py

@@ -11,7 +11,7 @@ with workflow.unsafe.imports_passed_through():
     from sientia_do.notifications.models import NotificationLevel
     from sientia_do.observability.logger import Logger
     from sientia_do.observability.sientia_monitoring import SientiaMonitoring
-    from sientia_do.repository.redis_repository import RedisRepository
+    from sientia_do.repository.redis_repository_sync import RedisRepository
     from sientia_do.temporal.constants import DATETIME_FORMAT, now
 
 
@@ -70,7 +70,7 @@ class Redis(SientiaMonitoring):
         SientiaMonitoring.shutdown(self)
 
     @activity.defn(name='get_last_data_timestamp')
-    async def get_last_data_timestamp(self, input_data: dict[str, Any]) -> str | None:
+    def get_last_data_timestamp(self, input_data: dict[str, Any]) -> str | None:
         """
         Retrieve the last processed data timestamp from Redis.
 
@@ -97,9 +97,9 @@ class Redis(SientiaMonitoring):
         self.info(f'Getting last data timestamp for {key}', metadata=metadata)
 
         try:
-            data_hold = await self.redis_repository.get(key, metadata=metadata)
+            data_hold = self.redis_repository.get(key, metadata=metadata)
         except Exception as e:
-            await self.send_notification_async(
+            self.send_notification(
                 metadata=metadata,
                 notification_id='REDIS_GET_ERROR',
                 message=f'Error getting last data timestamp: {e}',
@@ -117,7 +117,7 @@ class Redis(SientiaMonitoring):
         return data_hold
 
     @activity.defn(name='put_last_data_timestamp')
-    async def put_last_data_timestamp(self, input_data: dict[str, Any]) -> str | None:
+    def put_last_data_timestamp(self, input_data: dict[str, Any]) -> str | None:
         """
         Store the last processed data timestamp in Redis.
 
@@ -155,11 +155,9 @@ class Redis(SientiaMonitoring):
         self.info(f'Last collected timestamp to insert: {last_data_timestamp}', metadata=metadata)
 
         try:
-            await self.redis_repository.set(
-                key, last_data_timestamp, ttl=60 * 60 * 5, metadata=metadata
-            )
+            self.redis_repository.set(key, last_data_timestamp, ttl=60 * 60 * 5, metadata=metadata)
         except Exception as e:
-            await self.send_notification_async(
+            self.send_notification(
                 metadata=metadata,
                 notification_id='REDIS_SET_ERROR',
                 message=f'Error setting last data timestamp: {e}',
@@ -172,7 +170,7 @@ class Redis(SientiaMonitoring):
         return last_data_timestamp
 
     @activity.defn(name='group_and_hold_data')
-    async def group_and_hold_data(self, input_data: dict[str, Any]) -> dict[Hashable, Any]:
+    def group_and_hold_data(self, input_data: dict[str, Any]) -> dict[Hashable, Any]:
         """
         Group data by tags and store temporarily in Redis with TTL.
 
@@ -210,9 +208,9 @@ class Redis(SientiaMonitoring):
         self.info(f'Getting held data for {key}', metadata=metadata)
 
         try:
-            data_hold = await self.redis_repository.get(key, metadata=metadata)
+            data_hold = self.redis_repository.get(key, metadata=metadata)
         except Exception as e:
-            await self.send_notification_async(
+            self.send_notification(
                 metadata=metadata,
                 notification_id='REDIS_GET_ERROR',
                 message=f'Error getting held data: {e}',
@@ -254,7 +252,7 @@ class Redis(SientiaMonitoring):
                 data['timestamp'].max() if not data.empty else data_hold['timestamp']
             )
 
-            await self.redis_repository.set(key, data_hold, ttl=retention_time, metadata=metadata)
+            self.redis_repository.set(key, data_hold, ttl=retention_time, metadata=metadata)
 
             data_hold_df = DataFrame(data_hold, index=[0])
             data_hold_melted = data_hold_df.melt(
@@ -264,7 +262,7 @@ class Redis(SientiaMonitoring):
 
             data_hold_melted.reset_index(drop=True, inplace=True)
         except Exception as e:
-            await self.send_notification_async(
+            self.send_notification(
                 metadata=metadata,
                 notification_id='REDIS_SET_ERROR',
                 message=f'Error setting held data: {e}',
@@ -281,7 +279,7 @@ class Redis(SientiaMonitoring):
         return data_hold_melted.to_dict()
 
     @activity.defn(name='store_data_package')
-    async def store_data_package(self, input_data: dict[str, Any]):
+    def store_data_package(self, input_data: dict[str, Any]):
         """
         Stores the data package in redis. It's a debug feature and must be toggled on.
         input_data:
@@ -300,9 +298,9 @@ class Redis(SientiaMonitoring):
         cache = {'data': data.to_dict(), 'held_data': held_data.to_dict()}
 
         try:
-            await self.redis_repository.set(key, cache, ttl=120, metadata=metadata)
+            self.redis_repository.set(key, cache, ttl=120, metadata=metadata)
         except Exception as e:
-            await self.send_notification_async(
+            self.send_notification(
                 metadata=metadata,
                 notification_id='REDIS_SET_ERROR',
                 message=f'Error setting data package: {e}',

scouter/worker/prepare_worker.py

@@ -1,74 +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
-
-# Worker configuration parameters with default values
-# See worker_parameters.md for detailed documentation
-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}')
-
-    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'],
-        ),
-    )

scouter/worker/worker.py

@@ -9,6 +9,7 @@ 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,
@@ -18,7 +19,6 @@ with workflow.unsafe.imports_passed_through():
 
     from scouter import metrics
     from scouter.activities.activities import Activities
-    from scouter.worker.prepare_worker import prepare_worker
     from scouter.workflow.pi_web_api_scouter import PIWebAPIScouter
     from scouter.workflow.scouter import Scouter
     from scouter.workflow.sub_workflows.core_scouter import CoreScouter
@@ -28,26 +28,6 @@ POD_ID = os.getenv('HOSTNAME', 'localhost')
 SDK_METRICS_PORT = int(os.getenv('HTTP_SDK_METRICS_PORT', '9091'))
 
 
-# For optmized latency, Temporal docs recommends fixed slots, ensuring
-# high concurency levels.
-
-MAX_CONCURRENT_WORKFLOW_TASKS = int(os.getenv('MAX_CONCURRENT_WORKFLOW_TASKS', '200'))
-MAX_CONCURRENT_ACTIVITIES = int(os.getenv('MAX_CONCURRENT_ACTIVITIES', '200'))
-MAX_CONCURRENT_LOCAL_ACTIVITIES = int(os.getenv('MAX_CONCURRENT_LOCAL_ACTIVITIES', '200'))
-MAX_CACHED_WORKFLOWS = int(os.getenv('MAX_CACHED_WORKFLOWS', '200'))
-
-
-# Temporal docs also recommends an autoscaling policy, with agrresive limits to prioritize latency over throughput.
-
-WORKFLOW_POLLER_BEHAVIOUR_MINIMUM = int(os.getenv('WORKFLOW_POLLER_BEHAVIOUR_MINIMUM', '10'))
-WORKFLOW_POLLER_BEHAVIOUR_INITIAL = int(os.getenv('WORKFLOW_POLLER_BEHAVIOUR_INITIAL', '100'))
-WORKFLOW_POLLER_BEHAVIOUR_MAXIMUM = int(os.getenv('WORKFLOW_POLLER_BEHAVIOUR_MAXIMUM', '200'))
-
-ACTIVITY_POLLER_BEHAVIOUR_MINIMUM = int(os.getenv('ACTIVITY_POLLER_BEHAVIOUR_MINIMUM', '10'))
-ACTIVITY_POLLER_BEHAVIOUR_INITIAL = int(os.getenv('ACTIVITY_POLLER_BEHAVIOUR_INITIAL', '100'))
-ACTIVITY_POLLER_BEHAVIOUR_MAXIMUM = int(os.getenv('ACTIVITY_POLLER_BEHAVIOUR_MAXIMUM', '200'))
-
-
 async def main():
     """
     Main entry point for the Scouter Temporal worker.

scouter/worker/worker_parameters.md

@@ -1,113 +0,0 @@
-# Worker Parameters Documentation
-
-This document explains each configuration parameter used in the `prepare_worker.py` file for configuring Temporal workers.
-
-## Overview
-
-All parameters can be configured via environment variables using the pattern: `{WORKFLOW_NAME}_{PARAMETER_NAME}`. If not set, default values are used as specified below.
-
-## Concurrency Parameters
-
-### MAX_CONCURRENT_WORKFLOW_TASKS
-- **Default**: `200`
-- **Description**: Maximum number of concurrent workflow tasks that can be processed simultaneously by the worker. This controls how many workflow executions can be actively running at the same time.
-- **Usage**: Set via `max_concurrent_workflow_tasks` in the Worker configuration.
-- **Impact**: Higher values allow more workflows to run concurrently but consume more resources. Lower values provide better resource control but may limit throughput.
-
-### MAX_CONCURRENT_ACTIVITIES
-- **Default**: `200`
-- **Description**: Maximum number of concurrent activity tasks that can be executed simultaneously by the worker. Activities are the actual work units that perform business logic.
-- **Usage**: Set via `max_concurrent_activities` in the Worker configuration.
-- **Impact**: Controls the parallelism of activity execution. Higher values increase throughput but require more system resources (CPU, memory, network connections).
-
-### MAX_CONCURRENT_LOCAL_ACTIVITIES
-- **Default**: `200`
-- **Description**: Maximum number of concurrent local activity tasks that can be executed simultaneously. Local activities run in the same process as the workflow, without requiring a separate activity worker.
-- **Usage**: Set via `max_concurrent_local_activities` in the Worker configuration.
-- **Impact**: Similar to regular activities, but local activities have lower latency and overhead since they don't require network round-trips. Useful for lightweight operations.
-
-## Caching Parameters
-
-### MAX_CACHED_WORKFLOWS
-- **Default**: `200`
-- **Description**: Maximum number of workflow instances that can be cached in memory by the worker. Cached workflows allow faster resumption of execution without reloading state.
-- **Usage**: Set via `max_cached_workflows` in the Worker configuration.
-- **Impact**: Higher values improve performance for frequently accessed workflows but consume more memory. Lower values reduce memory usage but may require more frequent state reloads.
-
-## Understanding Pollers in Temporal
-
-**Pollers** are components of Temporal Workers that continuously request tasks from the Temporal service's Task Queues via synchronous RPCs. There are separate pollers for workflow tasks and activity tasks.
-
-### How Pollers Work
-
-Pollers send requests to the Temporal service to retrieve tasks from Task Queues. When a task is available, the poller retrieves it and the Worker processes it using registered Workflow or Activity handlers. This architecture provides:
-- **Load Balancing**: Workers only poll when they have capacity, distributing load across multiple processes
-- **Fault Tolerance**: Tasks persist in queues if a Worker fails, allowing recovery
-- **Task Routing**: Tasks can be routed to specific Worker processes
-
-### Autoscaling Poller Behavior
-
-Temporal supports autoscaling that dynamically adjusts the number of concurrent pollers based on workload. The system scales up during high load and down during low load, maintaining a baseline for responsiveness. Autoscaling is configured with `minimum`, `initial`, and `maximum` parameters that define the scaling bounds.
-
-## Workflow Poller Behavior (Autoscaling)
-
-These parameters control the autoscaling behavior of the workflow task poller, which retrieves workflow tasks from the Temporal server.
-
-### WORKFLOW_POLLER_BEHAVIOUR_MINIMUM
-- **Default**: `10`
-- **Description**: Minimum number of concurrent pollers for workflow tasks. The poller count will never go below this value.
-- **Usage**: Set via `minimum` in `PollerBehaviorAutoscaling` for `workflow_task_poller_behavior`.
-- **Impact**: Ensures a baseline level of polling activity even during low load periods.
-
-### WORKFLOW_POLLER_BEHAVIOUR_INITIAL
-- **Default**: `100`
-- **Description**: Initial number of concurrent pollers for workflow tasks when the worker starts.
-- **Usage**: Set via `initial` in `PollerBehaviorAutoscaling` for `workflow_task_poller_behavior`.
-- **Impact**: Determines the starting point for poller scaling. Higher values provide faster initial task acquisition but consume more resources.
-
-### WORKFLOW_POLLER_BEHAVIOUR_MAXIMUM
-- **Default**: `200`
-- **Description**: Maximum number of concurrent pollers allowed for workflow tasks. The poller count will not exceed this value even under high load.
-- **Usage**: Set via `maximum` in `PollerBehaviorAutoscaling` for `workflow_task_poller_behavior`.
-- **Impact**: Caps the resource consumption for workflow task polling. Prevents excessive polling that could overwhelm the Temporal server or worker.
-
-## Activity Poller Behavior (Autoscaling)
-
-These parameters control the autoscaling behavior of the activity task poller, which retrieves activity tasks from the Temporal server.
-
-### ACTIVITY_POLLER_BEHAVIOUR_MINIMUM
-- **Default**: `10`
-- **Description**: Minimum number of concurrent pollers for activity tasks. The poller count will never go below this value.
-- **Usage**: Set via `minimum` in `PollerBehaviorAutoscaling` for `activity_task_poller_behavior`.
-- **Impact**: Ensures a baseline level of polling activity even during low load periods.
-
-### ACTIVITY_POLLER_BEHAVIOUR_INITIAL
-- **Default**: `100`
-- **Description**: Initial number of concurrent pollers for activity tasks when the worker starts.
-- **Usage**: Set via `initial` in `PollerBehaviorAutoscaling` for `activity_task_poller_behavior`.
-- **Impact**: Determines the starting point for poller scaling. Higher values provide faster initial task acquisition but consume more resources.
-
-### ACTIVITY_POLLER_BEHAVIOUR_MAXIMUM
-- **Default**: `200`
-- **Description**: Maximum number of concurrent pollers allowed for activity tasks. The poller count will not exceed this value even under high load.
-- **Usage**: Set via `maximum` in `PollerBehaviorAutoscaling` for `activity_task_poller_behavior`.
-- **Impact**: Caps the resource consumption for activity task polling. Prevents excessive polling that could overwhelm the Temporal server or worker.
-
-## Configuration Example
-
-To override these parameters, set environment variables using the pattern:
-```
-{WORKFLOW_NAME}_{PARAMETER_NAME}={value}
-```
-
-For example, if your workflow is named `ScouterWorkflow`:
-```bash
-SCOUTERWORKFLOW_MAX_CONCURRENT_ACTIVITIES=500
-SCOUTERWORKFLOW_WORKFLOW_POLLER_BEHAVIOUR_MAXIMUM=300
-```
-
-## Notes
-
-- All parameter values are converted to integers before use.
-- The autoscaling poller behavior dynamically adjusts the number of pollers between the minimum and maximum values based on workload.
-- These parameters should be tuned based on your specific workload characteristics, available resources, and performance requirements.

sonar-project.properties

@@ -5,7 +5,7 @@ sonar.tests=tests
 sonar.qualitygate.wait=true
 sonar.qualitygate.timeout=300
 sonar.python.coverage.reportPaths=coverage.xml
-sonar.coverage.exclusions=scouter/worker/worker.py,scouter/worker/prepare_worker.py
+sonar.coverage.exclusions=scouter/worker/worker.py
 sonar.python.xunit.reportPath=pytest.xml
 sonar.python.version=3.11
 sonar.projectVersion=1.0.0

tests.ipynb

@@ -282,7 +282,7 @@
     "    j = i - pace\n",
     "    print(f'Getting data for chunk -{i} to -{j} days')\n",
     "    try:\n",
-    "        chunk = DataFrame(await api.get_tag_values(\n",
+    "        chunk = DataFrame(api.get_tag_values(\n",
     "            input_data={\n",
     "                'endpoint': '/streamsets/recorded',\n",
     "                'web_ids': web_ids,\n",
@@ -294,7 +294,7 @@
     "            }\n",
     "        ))\n",
     "    except Exception as e:\n",
-    "        chunk = DataFrame(await api.get_tag_values(\n",
+    "        chunk = DataFrame(api.get_tag_values(\n",
     "            input_data={\n",
     "                'endpoint': '/streamsets/recorded',\n",
     "                'web_ids': web_ids,\n",

tests/activities/test_activities.py

@@ -1,6 +1,7 @@
+import inspect
 from unittest.mock import ANY, MagicMock, patch
 
-from sientia_do.temporal.activities.postgres import Postgres
+from sientia_do.temporal.activities.postgres_sync import Postgres
 
 from scouter.activities.activities import Activities
 from scouter.activities.api import API
@@ -181,3 +182,13 @@ def test_shutdown(
     mock_redis_close.assert_called()
     mock_gates_close.assert_called()
     mock_api_close.assert_called()
+
+
+def test_activity_methods_are_sync():
+    """Every @activity.defn method on Activities must be a synchronous def."""
+    for cls in Activities.__mro__:
+        for name, member in vars(cls).items():
+            if getattr(member, '__temporal_activity_definition', None) is not None:
+                assert not inspect.iscoroutinefunction(member), (
+                    f'{cls.__name__}.{name} must not be async'
+                )

tests/activities/test_api.py

@@ -1,4 +1,4 @@
-from unittest.mock import ANY, AsyncMock, MagicMock, patch
+from unittest.mock import ANY, MagicMock, Mock, patch
 
 import pandas as pd
 import pytest
@@ -86,8 +86,7 @@ def test_close(mock_sientia_monitoring, api_activity):
     mock_sientia_monitoring.shutdown.assert_called_once()
 
 
-@pytest.mark.asyncio
-async def test_get_tag_values_success(api_activity):
+def test_get_tag_values_success(api_activity):
     """Test get_tag_values with successful data retrieval."""
     # Setup test data
     test_data = {
@@ -131,10 +130,10 @@ async def test_get_tag_values_success(api_activity):
 
     mock_df['timestamp'] = pd.to_datetime(mock_df['timestamp'])
 
-    api_activity.pi_web_api_client.get_latest_values_df = AsyncMock(return_value=mock_df)
+    api_activity.pi_web_api_client.get_latest_values_df = Mock(return_value=mock_df)
 
     # Execute
-    result = await api_activity.get_tag_values(test_data)
+    result = api_activity.get_tag_values(test_data)
 
     # Verify
     api_activity.pi_web_api_client.get_latest_values_df.assert_called_once_with(
@@ -161,8 +160,7 @@ async def test_get_tag_values_success(api_activity):
     assert result[2]['timestamp'] == '2023-01-01 12:02:00+0000'
 
 
-@pytest.mark.asyncio
-async def test_get_tag_values_with_default_max_count(api_activity):
+def test_get_tag_values_with_default_max_count(api_activity):
     """Test get_tag_values with default max_count value."""
     # Setup test data without max_count
     test_data = {
@@ -190,10 +188,10 @@ async def test_get_tag_values_with_default_max_count(api_activity):
 
     mock_df['timestamp'] = pd.to_datetime(mock_df['timestamp'])
 
-    api_activity.pi_web_api_client.get_latest_values_df = AsyncMock(return_value=mock_df)
+    api_activity.pi_web_api_client.get_latest_values_df = Mock(return_value=mock_df)
 
     # Execute
-    result = await api_activity.get_tag_values(test_data)
+    result = api_activity.get_tag_values(test_data)
 
     # Verify default max_count is 1
     api_activity.pi_web_api_client.get_latest_values_df.assert_called_once_with(
@@ -209,8 +207,7 @@ async def test_get_tag_values_with_default_max_count(api_activity):
     assert len(result) == 1
 
 
-@pytest.mark.asyncio
-async def test_get_tag_values_with_none_webids(api_activity):
+def test_get_tag_values_with_none_webids(api_activity):
     """Test get_tag_values with some None WebIds."""
     # Setup test data with None values
     test_data = {
@@ -245,18 +242,17 @@ async def test_get_tag_values_with_none_webids(api_activity):
 
     mock_df['timestamp'] = pd.to_datetime(mock_df['timestamp'])
 
-    api_activity.pi_web_api_client.get_latest_values_df = AsyncMock(return_value=mock_df)
+    api_activity.pi_web_api_client.get_latest_values_df = Mock(return_value=mock_df)
 
     # Execute
-    result = await api_activity.get_tag_values(test_data)
+    result = api_activity.get_tag_values(test_data)
 
     # Verify - should only query non-None WebIds
     assert len(result) == 2
     assert all(r['name'] in ['tag1', 'tag3'] for r in result)
 
 
-@pytest.mark.asyncio
-async def test_get_tag_values_api_error(api_activity):
+def test_get_tag_values_api_error(api_activity):
     """Test get_tag_values when PI Web API client raises an error and sends notification."""
     # Setup test data
     test_data = {
@@ -275,19 +271,19 @@ async def test_get_tag_values_api_error(api_activity):
     }
 
     # Mock API error
-    api_activity.pi_web_api_client.get_latest_values_df = AsyncMock(
+    api_activity.pi_web_api_client.get_latest_values_df = Mock(
         side_effect=Exception('PI Web API connection error')
     )
-    api_activity.send_notification_async = AsyncMock()
+    api_activity.send_notification = MagicMock()
 
     # Execute and verify exception is raised
     with pytest.raises(Exception) as exc_info:
-        await api_activity.get_tag_values(test_data)
+        api_activity.get_tag_values(test_data)
 
     assert str(exc_info.value) == 'PI Web API connection error'
 
     # Verify notification was sent
-    api_activity.send_notification_async.assert_called_once_with(
+    api_activity.send_notification.assert_called_once_with(
         metadata=metadata['metadata'],
         notification_id='PI_WEB_API_REQUEST_ERROR',
         message='Error getting tag values from PI Web API: PI Web API connection error',
@@ -297,8 +293,7 @@ async def test_get_tag_values_api_error(api_activity):
     )
 
 
-@pytest.mark.asyncio
-async def test_get_tag_values_with_nan_values(api_activity):
+def test_get_tag_values_with_nan_values(api_activity):
     """Test get_tag_values handling NaN values in the DataFrame."""
     # Setup test data
     test_data = {
@@ -333,10 +328,10 @@ async def test_get_tag_values_with_nan_values(api_activity):
 
     mock_df['timestamp'] = pd.to_datetime(mock_df['timestamp'])
 
-    api_activity.pi_web_api_client.get_latest_values_df = AsyncMock(return_value=mock_df)
+    api_activity.pi_web_api_client.get_latest_values_df = Mock(return_value=mock_df)
 
     # Execute
-    result = await api_activity.get_tag_values(test_data)
+    result = api_activity.get_tag_values(test_data)
 
     # Verify
     assert len(result) == 2

tests/activities/test_gates.py

@@ -1,5 +1,5 @@
 from typing import Any
-from unittest.mock import ANY, AsyncMock, MagicMock, Mock, call, patch
+from unittest.mock import ANY, MagicMock, Mock, call, patch
 
 import numpy as np
 import pandas as pd
@@ -21,8 +21,6 @@ def gates_fixture():
         metrics_controller=metrics_controller,
     )
     gates.send_notification = MagicMock()
-    gates.send_notification_async = AsyncMock()
-    gates.emit_metric = AsyncMock()
 
     gates.logger = logger
     gates.notification_handler = notification_handler
@@ -48,8 +46,7 @@ def test_close(mock_sientia_monitoring, gates_fixture):
     mock_sientia_monitoring.shutdown.assert_called_once()
 
 
-@pytest.mark.asyncio
-async def test_data_quality_gate_with_null_values_filter_discard(gates_fixture):
+def test_data_quality_gate_with_null_values_filter_discard(gates_fixture):
     """Test data_quality_gate with NULL_VALUES_FILTER and DISCARD policy."""
     # Setup test data
     input_data = {
@@ -69,16 +66,15 @@ async def test_data_quality_gate_with_null_values_filter_discard(gates_fixture):
     }
 
     # Execute
-    result = await gates_fixture.data_quality_gate(input_data)
+    result = gates_fixture.data_quality_gate(input_data)
 
     # Verify
     assert len(result['tag']) == 2
     assert 'tag2' not in result['tag']
-    gates_fixture.send_notification_async.assert_called_once()
+    gates_fixture.send_notification.assert_called_once()
 
 
-@pytest.mark.asyncio
-async def test_data_quality_gate_with_out_of_bounds_filter_keep(gates_fixture):
+def test_data_quality_gate_with_out_of_bounds_filter_keep(gates_fixture):
     """Test data_quality_gate with OUT_OF_BOUNDS_FILTER and KEEP policy."""
     # Setup test data with out of bounds values
     input_data = {
@@ -103,15 +99,14 @@ async def test_data_quality_gate_with_out_of_bounds_filter_keep(gates_fixture):
         {'OUT_OF_BOUNDS_FILTER': lambda df: df[df['tag'] == 'tag2']},
     ):
         # Execute
-        result = await gates_fixture.data_quality_gate(input_data)
+        result = gates_fixture.data_quality_gate(input_data)
 
     # Verify data is kept but notification is sent
     assert len(result['tag']) == 3  # All rows kept
-    gates_fixture.send_notification_async.assert_called_once()
+    gates_fixture.send_notification.assert_called_once()
 
 
-@pytest.mark.asyncio
-async def test_data_quality_gate_with_multiple_filters(gates_fixture):
+def test_data_quality_gate_with_multiple_filters(gates_fixture):
     """Test data_quality_gate with multiple filters."""
     # Setup test data
     input_data = {
@@ -134,7 +129,7 @@ async def test_data_quality_gate_with_multiple_filters(gates_fixture):
         **metadata,
     }
 
-    result = await gates_fixture.data_quality_gate(input_data)
+    result = gates_fixture.data_quality_gate(input_data)
 
     # Verify only tag1 and tag4 remain (tag2 has null, tag3 is out of bounds)
     assert result == {
@@ -144,11 +139,10 @@ async def test_data_quality_gate_with_multiple_filters(gates_fixture):
         'timestamp': {0: '2023-01-01', 3: '2023-01-04'},
     }
     # Should be called twice (once for each filter)
-    assert gates_fixture.send_notification_async.call_count == 2
+    assert gates_fixture.send_notification.call_count == 2
 
 
-@pytest.mark.asyncio
-async def test_data_quality_gate_with_unknown_filter(gates_fixture):
+def test_data_quality_gate_with_unknown_filter(gates_fixture):
     """Test data_quality_gate with an unknown filter."""
     # Setup test data with unknown filter
     gates_fixture.warning = MagicMock()
@@ -160,7 +154,7 @@ async def test_data_quality_gate_with_unknown_filter(gates_fixture):
     }
 
     # Execute
-    result = await gates_fixture.data_quality_gate(input_data)
+    result = gates_fixture.data_quality_gate(input_data)
 
     # Verify data is unchanged and warning is logged
     assert len(result['tag']) == 1
@@ -169,8 +163,7 @@ async def test_data_quality_gate_with_unknown_filter(gates_fixture):
     )
 
 
-@pytest.mark.asyncio
-async def test_data_quality_gate_with_filter_error(gates_fixture):
+def test_data_quality_gate_with_filter_error(gates_fixture):
     """Test data_quality_gate when a filter raises an exception."""
     # Setup test data
     input_data = {
@@ -188,19 +181,18 @@ async def test_data_quality_gate_with_filter_error(gates_fixture):
         'scouter.activities.gates.quality_gate_filters', {'NULL_VALUES_FILTER': failing_filter}
     ):
         # Execute
-        result = await gates_fixture.data_quality_gate(input_data)
+        result = gates_fixture.data_quality_gate(input_data)
 
     # Verify error notification is sent and data is unchanged
     assert len(result['tag']) == 1
-    gates_fixture.send_notification_async.assert_called_once()
-    call_args = gates_fixture.send_notification_async.call_args[1]
+    gates_fixture.send_notification.assert_called_once()
+    call_args = gates_fixture.send_notification.call_args[1]
     assert call_args['notification_id'] == 'DATA_QUALITY_GATE_ISSUES'
     assert call_args['level'] == NotificationLevel.ERROR
     assert 'Filter error' in call_args['message']
 
 
-@pytest.mark.asyncio
-async def test_data_quality_gate_with_empty_data(gates_fixture):
+def test_data_quality_gate_with_empty_data(gates_fixture):
     """Test data_quality_gate with empty input data."""
     # Setup empty input data
     input_data = {
@@ -211,15 +203,14 @@ async def test_data_quality_gate_with_empty_data(gates_fixture):
     }
 
     # Execute
-    result = await gates_fixture.data_quality_gate(input_data)
+    result = gates_fixture.data_quality_gate(input_data)
 
     # Verify empty result and no notifications
     assert len(result['tag']) == 0
     gates_fixture.send_notification.assert_not_called()
 
 
-@pytest.mark.asyncio
-async def test_data_quality_gate_with_no_filters(gates_fixture):
+def test_data_quality_gate_with_no_filters(gates_fixture):
     """Test data_quality_gate with no filters specified."""
     # Setup test data with no filters
     input_data = {
@@ -230,7 +221,7 @@ async def test_data_quality_gate_with_no_filters(gates_fixture):
     }
 
     # Execute
-    result = await gates_fixture.data_quality_gate(input_data)
+    result = gates_fixture.data_quality_gate(input_data)
 
     # Verify data is unchanged and no notifications
     assert len(result['tag']) == 1
@@ -254,23 +245,22 @@ async def test_data_quality_gate_with_no_filters(gates_fixture):
         (pd.DataFrame({'value': [np.nan, np.nan]}), 'avg', None),
         # Invalid aggregation function
         (pd.DataFrame({'value': [1.0, 2.0]}), 'invalid', 'continue'),
+        (pd.DataFrame({'value': [10.0]}), 'invalid', 'continue'),
     ],
 )
-@pytest.mark.asyncio
-async def test_apply_aggregation(gates_fixture, group_data, aggr_function, expected_result):
+def test_apply_aggregation(gates_fixture, group_data, aggr_function, expected_result):
     """Test apply_aggregation method with various scenarios."""
-    result = await gates_fixture.apply_aggregation(group_data, aggr_function, metadata)
+    result = gates_fixture.apply_aggregation(group_data, aggr_function, metadata)
     assert result == expected_result
 
     # Check notification was sent for invalid function
     if aggr_function == 'invalid':
-        gates_fixture.send_notification_async.assert_called_once()
+        gates_fixture.send_notification.assert_called_once()
     else:
-        gates_fixture.send_notification_async.assert_not_called()
+        gates_fixture.send_notification.assert_not_called()
 
 
-@pytest.mark.asyncio
-async def test_aggregate_data(gates_fixture):
+def test_aggregate_data(gates_fixture):
     """Test aggregate_data method with multiple groups and aggregation functions."""
     input_data = {
         'data': [
@@ -299,16 +289,15 @@ async def test_aggregate_data(gates_fixture):
     }
 
     # Execute
-    result = await gates_fixture.aggregate_data(input_data)
+    result = gates_fixture.aggregate_data(input_data)
 
     # Verify
     assert result == expected_result
     gates_fixture.send_notification.assert_not_called()
 
 
-@pytest.mark.asyncio
-async def test_aggregate_data_with_continue(gates_fixture):
-    gates_fixture.apply_aggregation = AsyncMock(return_value='continue')
+def test_aggregate_data_with_continue(gates_fixture):
+    gates_fixture.apply_aggregation = MagicMock(return_value='continue')
 
     input_data = {
         'data': [
@@ -331,15 +320,14 @@ async def test_aggregate_data_with_continue(gates_fixture):
     expected_result: dict[str, Any] = {}
 
     # Execute
-    result = await gates_fixture.aggregate_data(input_data)
+    result = gates_fixture.aggregate_data(input_data)
 
     # Verify
     assert result == expected_result
-    gates_fixture.send_notification_async.assert_not_called()
+    gates_fixture.send_notification.assert_not_called()
 
 
-@pytest.mark.asyncio
-async def test_aggregate_data_raise_exception(gates_fixture):
+def test_aggregate_data_raise_exception(gates_fixture):
     gates_fixture.apply_aggregation = MagicMock(side_effect=Exception('Test exception'))
 
     input_data = {
@@ -360,10 +348,10 @@ async def test_aggregate_data_raise_exception(gates_fixture):
     }
 
     try:
-        await gates_fixture.aggregate_data(input_data)
+        gates_fixture.aggregate_data(input_data)
     except Exception as e:
         assert str(e) == 'Test exception'
-        gates_fixture.send_notification_async.assert_called_once_with(
+        gates_fixture.send_notification.assert_called_once_with(
             metadata=metadata['metadata'],
             notification_id='AGGREGATION_ISSUES',
             message='Error aggregating data: Test exception',
@@ -375,9 +363,8 @@ async def test_aggregate_data_raise_exception(gates_fixture):
         raise AssertionError('Exception not raised')
 
 
-@pytest.mark.asyncio
 @patch('scouter.activities.gates.metrics')
-async def test_write_metrics(mock_metrics, gates_fixture):
+def test_write_metrics(mock_metrics, gates_fixture):
     """Test write_metrics method."""
     input_data = {
         'metadata': metadata['metadata'],
@@ -386,7 +373,7 @@ async def test_write_metrics(mock_metrics, gates_fixture):
             'value': [1.0, 2.0, None],
         },
     }
-    await gates_fixture.write_metrics(input_data)
+    gates_fixture.write_metrics(input_data)
     mock_metrics.LABORIOUS_DATA_WRITTEN_COUNT.labels.assert_called_once_with(
         pod_id=gates_fixture.pod_id,
         model_name=metadata['metadata']['model_name'],

tests/activities/test_mongo.py

@@ -1,7 +1,7 @@
 from datetime import datetime
-from unittest.mock import ANY, AsyncMock, MagicMock, patch
+from unittest.mock import ANY, MagicMock, Mock, patch
 
-from pytest import fixture, mark
+from pytest import fixture
 from sientia_do.notifications.models import NotificationLevel
 from sientia_do.temporal.constants import DATETIME_FORMAT_MS_WITH_TZ
 
@@ -44,16 +44,18 @@ def mongodb_activity(mock_mongodb_repository):
         database_name='test_db',
         logger=MagicMock(),
         notification_handler=MagicMock(),
-        metrics_controller=AsyncMock(),
+        metrics_controller=MagicMock(),
     )
     return mongo
 
 
-def test_close(mongodb_activity):
+@patch('scouter.activities.mongodb.SientiaMonitoring')
+def test_close(mock_sientia_monitoring, mongodb_activity):
     """Test close"""
     mongodb_activity.close()
 
     mongodb_activity.mongodb_repository.close.assert_called_once()
+    mock_sientia_monitoring.shutdown.assert_called_once()
 
 
 def test_del(mongodb_activity):
@@ -64,11 +66,10 @@ def test_del(mongodb_activity):
     mongodb_activity.close.assert_called_once()
 
 
-@mark.asyncio
-async def test_load_latest_data_none_last_data_timestamp(mongodb_activity):
+def test_load_latest_data_none_last_data_timestamp(mongodb_activity):
     """Test load_latest_data"""
 
-    mongodb_activity.mongodb_repository.find = AsyncMock(
+    mongodb_activity.mongodb_repository.find = Mock(
         return_value=[
             {
                 'name': 'test1',
@@ -80,7 +81,7 @@ async def test_load_latest_data_none_last_data_timestamp(mongodb_activity):
         ]
     )
 
-    result = await mongodb_activity.load_latest_data(
+    result = mongodb_activity.load_latest_data(
         {
             'metadata': {'workflow_name': 'test_pipeline', 'schedule_name': 'test_schedule'},
             'collection_name': 'test_collection',
@@ -103,11 +104,10 @@ async def test_load_latest_data_none_last_data_timestamp(mongodb_activity):
     ]
 
 
-@mark.asyncio
-async def test_load_latest_data_not_none_last_data_timestamp(mongodb_activity):
+def test_load_latest_data_not_none_last_data_timestamp(mongodb_activity):
     """Test load_latest_data"""
 
-    mongodb_activity.mongodb_repository.find = AsyncMock(
+    mongodb_activity.mongodb_repository.find = Mock(
         return_value=[
             {
                 'name': 'test1',
@@ -119,7 +119,7 @@ async def test_load_latest_data_not_none_last_data_timestamp(mongodb_activity):
         ]
     )
 
-    result = await mongodb_activity.load_latest_data(
+    result = mongodb_activity.load_latest_data(
         {
             'metadata': {'workflow_name': 'test_pipeline', 'schedule_name': 'test_schedule'},
             'collection_name': 'test_collection',
@@ -148,16 +148,13 @@ async def test_load_latest_data_not_none_last_data_timestamp(mongodb_activity):
     ]
 
 
-@mark.asyncio
-async def test_load_latest_data_error(mongodb_activity):
+def test_load_latest_data_error(mongodb_activity):
     """Test load_latest_data"""
     mongodb_activity.mongodb_repository.find.side_effect = Exception('test')
     mongodb_activity.send_notification = MagicMock()
-    mongodb_activity.send_notification_async = AsyncMock()
-    mongodb_activity.emit_metric = AsyncMock()
 
     try:
-        await mongodb_activity.load_latest_data(
+        mongodb_activity.load_latest_data(
             {
                 'metadata': {'workflow_name': 'test_pipeline', 'schedule_name': 'test_schedule'},
                 'collection_name': 'test_collection',
@@ -167,7 +164,7 @@ async def test_load_latest_data_error(mongodb_activity):
     except Exception as e:
         assert str(e) == 'test'
 
-        mongodb_activity.send_notification_async.assert_called_once_with(
+        mongodb_activity.send_notification.assert_called_once_with(
             metadata={'workflow_name': 'test_pipeline', 'schedule_name': 'test_schedule'},
             notification_id='MONGO_LOAD_ERROR',
             message='Error loading data from MongoDB: test',

tests/activities/test_redis.py

@@ -1,5 +1,5 @@
 from datetime import datetime
-from unittest.mock import ANY, AsyncMock, MagicMock, patch
+from unittest.mock import ANY, MagicMock, Mock, patch
 
 import numpy as np
 import pytest
@@ -79,8 +79,7 @@ def test_redis_initialization(mock_redis_repository):
     assert activity.redis_repository is not None
 
 
-@pytest.mark.asyncio
-async def test_get_last_data_timestamp_none(redis_activity):
+def test_get_last_data_timestamp_none(redis_activity):
     """Test get_last_data_timestamp"""
     test_data = {
         **metadata,
@@ -88,9 +87,9 @@ async def test_get_last_data_timestamp_none(redis_activity):
         'schedule_name': 'test_schedule',
     }
 
-    redis_activity.redis_repository.get = AsyncMock(return_value=None)
+    redis_activity.redis_repository.get = Mock(return_value=None)
 
-    result = await redis_activity.get_last_data_timestamp(test_data)
+    result = redis_activity.get_last_data_timestamp(test_data)
 
     redis_activity.redis_repository.get.assert_called_once_with(
         'last_data_timestamp:test_pipeline:test_schedule',
@@ -100,14 +99,13 @@ async def test_get_last_data_timestamp_none(redis_activity):
     assert result is None
 
 
-@pytest.mark.asyncio
-async def test_get_last_data_timestamp_not_none(redis_activity):
+def test_get_last_data_timestamp_not_none(redis_activity):
     """Test get_last_data_timestamp"""
     test_data = {**metadata, 'workflow_name': 'test_pipeline', 'schedule_name': 'test_schedule'}
 
-    redis_activity.redis_repository.get = AsyncMock(return_value='2023-01-01 12:00:00')
+    redis_activity.redis_repository.get = Mock(return_value='2023-01-01 12:00:00')
 
-    result = await redis_activity.get_last_data_timestamp(test_data)
+    result = redis_activity.get_last_data_timestamp(test_data)
 
     redis_activity.redis_repository.get.assert_called_once_with(
         'last_data_timestamp:test_pipeline:test_schedule',
@@ -117,21 +115,20 @@ async def test_get_last_data_timestamp_not_none(redis_activity):
     assert result == '2023-01-01 12:00:00'
 
 
-@pytest.mark.asyncio
-async def test_get_last_data_timestamp_error(redis_activity):
+def test_get_last_data_timestamp_error(redis_activity):
     """Test get_last_data_timestamp error"""
     test_data = {**metadata, 'workflow_name': 'test_pipeline', 'schedule_name': 'test_schedule'}
 
-    redis_activity.send_notification_async = AsyncMock()
+    redis_activity.send_notification = Mock()
     redis_activity.redis_repository.get.side_effect = Exception('test')
 
     try:
-        await redis_activity.get_last_data_timestamp(test_data)
+        redis_activity.get_last_data_timestamp(test_data)
 
     except Exception as e:
         assert str(e) == 'test'
 
-        redis_activity.send_notification_async.assert_called_once_with(
+        redis_activity.send_notification.assert_called_once_with(
             metadata=metadata['metadata'],
             notification_id='REDIS_GET_ERROR',
             message='Error getting last data timestamp: test',
@@ -144,8 +141,7 @@ async def test_get_last_data_timestamp_error(redis_activity):
         raise AssertionError('Expected exception')
 
 
-@pytest.mark.asyncio
-async def test_put_last_data_timestamp_empty_dataframe(redis_activity):
+def test_put_last_data_timestamp_empty_dataframe(redis_activity):
     """Test put_last_data_timestamp with empty dataframe"""
     test_data = {
         **metadata,
@@ -156,15 +152,14 @@ async def test_put_last_data_timestamp_empty_dataframe(redis_activity):
 
     redis_activity.redis_repository.set = MagicMock()
 
-    result = await redis_activity.put_last_data_timestamp(test_data)
+    result = redis_activity.put_last_data_timestamp(test_data)
 
     assert result is None
 
     redis_activity.redis_repository.set.assert_not_called()
 
 
-@pytest.mark.asyncio
-async def test_put_last_data_timestamp_not_empty_dataframe(redis_activity):
+def test_put_last_data_timestamp_not_empty_dataframe(redis_activity):
     """Test put_last_data_timestamp with not empty dataframe"""
 
     data = DataFrame(
@@ -181,9 +176,9 @@ async def test_put_last_data_timestamp_not_empty_dataframe(redis_activity):
         'data': data.to_dict('records'),
     }
 
-    redis_activity.redis_repository.set = AsyncMock()
+    redis_activity.redis_repository.set = Mock()
 
-    result = await redis_activity.put_last_data_timestamp(test_data)
+    result = redis_activity.put_last_data_timestamp(test_data)
 
     assert result == '2023-01-01 12:00:01'
 
@@ -195,8 +190,7 @@ async def test_put_last_data_timestamp_not_empty_dataframe(redis_activity):
     )
 
 
-@pytest.mark.asyncio
-async def test_put_last_data_timestamp_error(redis_activity):
+def test_put_last_data_timestamp_error(redis_activity):
     """Test put_last_data_timestamp error"""
     test_data = {
         **metadata,
@@ -211,16 +205,16 @@ async def test_put_last_data_timestamp_error(redis_activity):
         ).to_dict('records'),
     }
 
-    redis_activity.send_notification_async = AsyncMock()
-    redis_activity.redis_repository.set = AsyncMock(side_effect=Exception('test'))
+    redis_activity.send_notification = Mock()
+    redis_activity.redis_repository.set = Mock(side_effect=Exception('test'))
 
     try:
-        await redis_activity.put_last_data_timestamp(test_data)
+        redis_activity.put_last_data_timestamp(test_data)
 
     except Exception as e:
         assert str(e) == 'test'
 
-        redis_activity.send_notification_async.assert_called_once_with(
+        redis_activity.send_notification.assert_called_once_with(
             metadata=metadata['metadata'],
             notification_id='REDIS_SET_ERROR',
             message='Error setting last data timestamp: test',
@@ -233,8 +227,7 @@ async def test_put_last_data_timestamp_error(redis_activity):
         raise AssertionError('Expected exception')
 
 
-@pytest.mark.asyncio
-async def test_group_and_hold_data_new_key(redis_activity):
+def test_group_and_hold_data_new_key(redis_activity):
     """Test group_and_hold_data with a new key"""
     # Setup
     test_data = {
@@ -255,11 +248,11 @@ async def test_group_and_hold_data_new_key(redis_activity):
     }
 
     # Mock get to return None for new key
-    redis_activity.redis_repository.get = AsyncMock(return_value=None)
-    redis_activity.redis_repository.set = AsyncMock()
+    redis_activity.redis_repository.get = Mock(return_value=None)
+    redis_activity.redis_repository.set = Mock()
 
     # Call the method
-    result = await redis_activity.group_and_hold_data(test_data)
+    result = redis_activity.group_and_hold_data(test_data)
 
     # Verify the result
     expected_result = {
@@ -279,8 +272,7 @@ async def test_group_and_hold_data_new_key(redis_activity):
     )
 
 
-@pytest.mark.asyncio
-async def test_group_and_hold_data_update_existing_fill_missing(redis_activity):
+def test_group_and_hold_data_update_existing_fill_missing(redis_activity):
     """Test updating existing data with group_and_hold_data"""
     # Setup initial data in Redis
     existing_data = {'sensor1': 20.0, 'sensor2': 28.0, 'timestamp': '2023-01-01 11:00:00'}
@@ -309,11 +301,11 @@ async def test_group_and_hold_data_update_existing_fill_missing(redis_activity):
     }
 
     # Mock get to return existing data
-    redis_activity.redis_repository.get = AsyncMock(return_value=existing_data)
-    redis_activity.redis_repository.set = AsyncMock()
+    redis_activity.redis_repository.get = Mock(return_value=existing_data)
+    redis_activity.redis_repository.set = Mock()
 
     # Call the method
-    result = await redis_activity.group_and_hold_data(test_data)
+    result = redis_activity.group_and_hold_data(test_data)
 
     # Verify the result
     expected_result = {
@@ -344,8 +336,7 @@ async def test_group_and_hold_data_update_existing_fill_missing(redis_activity):
     )
 
 
-@pytest.mark.asyncio
-async def test_group_and_hold_data_with_none_values(redis_activity):
+def test_group_and_hold_data_with_none_values(redis_activity):
     """Test handling of None values in group_and_hold_data"""
     # Setup test data with None values
     test_data = {
@@ -366,19 +357,18 @@ async def test_group_and_hold_data_with_none_values(redis_activity):
     }
 
     # Mock get to return None for new key
-    redis_activity.redis_repository.get = AsyncMock(return_value=None)
-    redis_activity.redis_repository.set = AsyncMock()
+    redis_activity.redis_repository.get = Mock(return_value=None)
+    redis_activity.redis_repository.set = Mock()
 
     # Call the method
-    result = await redis_activity.group_and_hold_data(test_data)
+    result = redis_activity.group_and_hold_data(test_data)
 
     # Verify None was converted to np.nan and values are as expected
     assert np.isnan(result['value'][0])
     assert result['value'][1] == pytest.approx(30.0)
 
 
-@pytest.mark.asyncio
-async def test_group_and_hold_data_empty_dataframe(redis_activity):
+def test_group_and_hold_data_empty_dataframe(redis_activity):
     """Test group_and_hold_data with empty DataFrame"""
     # Setup test with empty data
     test_data = {
@@ -391,16 +381,15 @@ async def test_group_and_hold_data_empty_dataframe(redis_activity):
         'fill_missing_tags': False,
     }
 
-    redis_activity.redis_repository.get = AsyncMock(return_value=None)
+    redis_activity.redis_repository.get = Mock(return_value=None)
 
     # Call the method
-    result = await redis_activity.group_and_hold_data(test_data)
+    result = redis_activity.group_and_hold_data(test_data)
 
     assert result == {}
 
 
-@pytest.mark.asyncio
-async def test_group_and_hold_data_error_get(redis_activity):
+def test_group_and_hold_data_error_get(redis_activity):
     """Test group_and_hold_data error"""
     test_data = {
         **metadata,
@@ -413,16 +402,16 @@ async def test_group_and_hold_data_error_get(redis_activity):
         'fill_missing_tags': False,
     }
 
-    redis_activity.redis_repository.get = AsyncMock(side_effect=Exception('test'))
-    redis_activity.send_notification_async = AsyncMock()
+    redis_activity.redis_repository.get = Mock(side_effect=Exception('test'))
+    redis_activity.send_notification = Mock()
 
     try:
-        await redis_activity.group_and_hold_data(test_data)
+        redis_activity.group_and_hold_data(test_data)
 
     except Exception as e:
         assert str(e) == 'test'
 
-        redis_activity.send_notification_async.assert_called_once_with(
+        redis_activity.send_notification.assert_called_once_with(
             metadata=metadata['metadata'],
             notification_id='REDIS_GET_ERROR',
             message='Error getting held data: test',
@@ -435,8 +424,7 @@ async def test_group_and_hold_data_error_get(redis_activity):
         raise AssertionError('Expected exception')
 
 
-@pytest.mark.asyncio
-async def test_group_and_hold_data_error_set(redis_activity):
+def test_group_and_hold_data_error_set(redis_activity):
     """Test group_and_hold_data error"""
     test_data = {
         **metadata,
@@ -452,21 +440,20 @@ async def test_group_and_hold_data_error_set(redis_activity):
     existing_data = {'sensor1': 20.0, 'sensor2': 28.0, 'timestamp': '2023-01-01 11:00:00'}
 
     # Mock get to return existing data
-    redis_activity.redis_repository.get = AsyncMock(return_value=existing_data)
-    redis_activity.redis_repository.set = AsyncMock(side_effect=Exception('test'))
-    redis_activity.send_notification_async = AsyncMock()
+    redis_activity.redis_repository.get = Mock(return_value=existing_data)
+    redis_activity.redis_repository.set = Mock(side_effect=Exception('test'))
+    redis_activity.send_notification = Mock()
 
     try:
-        await redis_activity.group_and_hold_data(test_data)
+        redis_activity.group_and_hold_data(test_data)
 
     except Exception as e:
         assert str(e) == 'test'
 
 
-@pytest.mark.asyncio
-async def test_store_data_package(redis_activity):
+def test_store_data_package(redis_activity):
     """Test store_data_package"""
-    redis_activity.redis_repository.set = AsyncMock()
+    redis_activity.redis_repository.set = Mock()
 
     test_data = {
         **metadata,
@@ -489,7 +476,7 @@ async def test_store_data_package(redis_activity):
         'model_tags': {'sensor1': 'sensor1', 'sensor2': 'sensor2'},
     }
 
-    await redis_activity.store_data_package(test_data)
+    redis_activity.store_data_package(test_data)
 
     redis_activity.redis_repository.set.assert_called_once_with(
         ANY,
@@ -499,11 +486,10 @@ async def test_store_data_package(redis_activity):
     )
 
 
-@pytest.mark.asyncio
-async def test_store_data_package_error(redis_activity):
+def test_store_data_package_error(redis_activity):
     """Test store_data_package error"""
-    redis_activity.redis_repository.set = AsyncMock(side_effect=ValueError('test'))
-    redis_activity.send_notification_async = AsyncMock()
+    redis_activity.redis_repository.set = Mock(side_effect=ValueError('test'))
+    redis_activity.send_notification = Mock()
 
     test_data = {
         **metadata,
@@ -527,9 +513,9 @@ async def test_store_data_package_error(redis_activity):
     }
 
     with pytest.raises(ValueError):
-        await redis_activity.store_data_package(test_data)
+        redis_activity.store_data_package(test_data)
 
-    redis_activity.send_notification_async.assert_called_once_with(
+    redis_activity.send_notification.assert_called_once_with(
         metadata=metadata['metadata'],
         notification_id='REDIS_SET_ERROR',
         message='Error setting data package: test',

tests/utils/quality/test_filters.py

@@ -104,7 +104,7 @@ def test_null_values_filter(sample_dataframe, nodes_data_range):
     expected_data = {
         'tag': ['wind_speed'],
         'name': ['wind_speed'],
-        'value': [None],
+        'value': [np.nan],
         'timestamp': [pd.Timestamp('2023-01-06')],
     }
     expected_df = pd.DataFrame(expected_data)