1ce8b9d3a7
Enhance environment configuration and update dependencies - Added new environment variables for PluginStore and MLflow configuration in `.env.example`, including `RUNTIME`, `STORE_BASE_URL`, `STORE_OWNER`, `STORE_REPO`, `STORE_BRANCH`, `STORE_USERNAME`, `STORE_PASSWORD`, `STORE_CACHE_TTL_SECONDS`, `PYPI_SERVER`, `PYPI_USERNAME`, and `PYPI_PASSWORD`. - Updated `git-requirements-mapping.txt` to reflect changes in repository names. - Modified `requirements-light.txt` and `requirements.txt` to upgrade `sientia-dataops-library` to version 1.12.0 and `sientia-mlops-library` to version 0.8.1. - Updated `values.yaml` to include new environment variables for worker runtime and PluginStore configuration. - Refactored E2E tests to utilize new MLflow repository stubs and PluginStore mocks for improved testing accuracy.
543 lines
17 KiB
Python
543 lines
17 KiB
Python
"""
|
|
Pytest configuration and fixtures for E2E tests.
|
|
"""
|
|
|
|
from unittest.mock import AsyncMock, MagicMock, patch
|
|
from io import BytesIO
|
|
|
|
import pandas as pd
|
|
import pytest
|
|
import pytest_asyncio
|
|
from sqlalchemy import create_engine, text
|
|
from testcontainers.minio import MinioContainer
|
|
from testcontainers.postgres import PostgresContainer
|
|
from temporalio.testing import WorkflowEnvironment
|
|
from temporalio.worker import Worker
|
|
|
|
from laborious.activities.activities import Activities
|
|
from laborious.workflows.predictions_batch import PredictionsBatch
|
|
from laborious.workflows.sub_workflows.prediction_process import PredictionProcess
|
|
from laborious.workflows.sub_workflows.format_and_export_prediction import FormatAndExportPrediction
|
|
from sientia_do.notifications.handlers import CoreNotificationHandler
|
|
from sientia_do.observability.logger import Logger
|
|
from sientia_do.observability.metrics_controller import MetricsController
|
|
|
|
# Test constants
|
|
TEST_MONGODB_CONNECTION_STRING = 'mongodb://localhost:27017'
|
|
TEST_DATABASE_NAME = 'test_db'
|
|
|
|
|
|
@pytest_asyncio.fixture(scope='session')
|
|
def minio_container():
|
|
"""
|
|
MinIO S3-compatible storage for E2E tests that exercise real offload uploads.
|
|
"""
|
|
minio = MinioContainer()
|
|
minio.start()
|
|
yield minio
|
|
minio.stop()
|
|
|
|
|
|
@pytest_asyncio.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.
|
|
"""
|
|
postgres = PostgresContainer('postgres:15')
|
|
postgres.start()
|
|
yield postgres
|
|
postgres.stop()
|
|
|
|
|
|
@pytest_asyncio.fixture
|
|
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.
|
|
"""
|
|
engine = create_engine(postgres_container.get_connection_url())
|
|
|
|
yield engine
|
|
|
|
engine.dispose()
|
|
|
|
|
|
def _create_schema_and_tables(engine):
|
|
"""
|
|
Helper function to create schema and tables in the given engine.
|
|
|
|
Creates predictions_schema with:
|
|
- laborious_data: Input data table for queries
|
|
- predictions: Output predictions table
|
|
- transformed_data: Output transformed data table
|
|
"""
|
|
# Use begin() to ensure transaction is properly committed
|
|
with engine.begin() as conn:
|
|
# Create predictions_schema
|
|
conn.execute(text("CREATE SCHEMA IF NOT EXISTS predictions_schema"))
|
|
|
|
# Create laborious_data table (input data from sensors)
|
|
create_laborious_data_sql = """
|
|
CREATE TABLE IF NOT EXISTS predictions_schema.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 NOT NULL,
|
|
PRIMARY KEY (id)
|
|
);
|
|
"""
|
|
conn.execute(text(create_laborious_data_sql))
|
|
|
|
# Create predictions table
|
|
create_predictions_sql = """
|
|
CREATE TABLE if not exists predictions_schema.predictions (
|
|
id SERIAL NOT NULL ,
|
|
model_id int4 NOT NULL,
|
|
prediction numeric NULL,
|
|
prediction_confidence numeric NOT NULL,
|
|
response_time numeric NOT NULL,
|
|
prediction_status text NOT NULL,
|
|
"timestamp" timestamptz NOT NULL,
|
|
created_at timestamptz DEFAULT CURRENT_TIMESTAMP NOT NULL,
|
|
"comments" text NULL,
|
|
PRIMARY KEY (id, created_at)
|
|
);
|
|
"""
|
|
conn.execute(text(create_predictions_sql))
|
|
|
|
# Create transformed_data table
|
|
create_transformed_sql = """
|
|
CREATE TABLE IF NOT EXISTS predictions_schema.transformed_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)
|
|
);
|
|
"""
|
|
conn.execute(text(create_transformed_sql))
|
|
|
|
|
|
@pytest_asyncio.fixture(autouse=True)
|
|
def setup_postgres_schema_and_tables(postgres_engine):
|
|
"""
|
|
Automatically create necessary schema and tables before each test.
|
|
|
|
This fixture runs automatically (autouse=True) and ensures
|
|
that the predictions_schema and tables exist with the correct structure.
|
|
"""
|
|
_create_schema_and_tables(postgres_engine)
|
|
yield
|
|
|
|
|
|
@pytest_asyncio.fixture
|
|
def mock_logger():
|
|
"""Mock logger for testing."""
|
|
def message(message):
|
|
print(f"[LOG] {message}")
|
|
def custom_message(message, _metadata={}):
|
|
print(f"[LOG] {message}")
|
|
logger = MagicMock()
|
|
logger.info = MagicMock(
|
|
side_effect=message
|
|
)
|
|
logger.debug = MagicMock(
|
|
side_effect=message
|
|
)
|
|
logger.error = MagicMock(
|
|
side_effect=message
|
|
)
|
|
logger.warning = MagicMock(
|
|
side_effect=message
|
|
)
|
|
logger.custom_info = MagicMock(
|
|
side_effect=custom_message
|
|
)
|
|
logger.custom_debug = MagicMock(
|
|
side_effect=custom_message
|
|
)
|
|
logger.custom_error = MagicMock(
|
|
side_effect=custom_message
|
|
)
|
|
logger.custom_warning = MagicMock(
|
|
side_effect=custom_message
|
|
)
|
|
return logger
|
|
|
|
|
|
@pytest_asyncio.fixture
|
|
def mock_mongo_client():
|
|
"""
|
|
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.
|
|
"""
|
|
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.fixture
|
|
def notification_inserts(mock_mongo_client):
|
|
"""
|
|
Mongo insert_one mock used by CoreNotificationHandler for notification persistence.
|
|
|
|
Yields:
|
|
MagicMock for insert_one, reset before each test.
|
|
"""
|
|
mock_db = mock_mongo_client.__getitem__.return_value
|
|
mock_collection = mock_db.__getitem__.return_value
|
|
mock_collection.insert_one.reset_mock()
|
|
yield mock_collection.insert_one
|
|
|
|
|
|
@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='laborious',
|
|
)
|
|
yield handler
|
|
handler.shutdown()
|
|
|
|
|
|
@pytest_asyncio.fixture
|
|
def metrics_controller(mock_logger):
|
|
"""Create a real MetricsController instance."""
|
|
return MetricsController(logger=mock_logger)
|
|
|
|
|
|
@pytest_asyncio.fixture
|
|
def mock_minio_repository():
|
|
"""Mock MinIO repository for object storage operations."""
|
|
mock_repo = MagicMock()
|
|
|
|
# Provide at least valid parquet bytes so that MinioDataFramePayload.retrieve()
|
|
# can decode the payload if offloading is exercised in an integration scenario.
|
|
parquet_df = pd.DataFrame({'a': [1]})
|
|
parquet_buffer = BytesIO()
|
|
parquet_df.to_parquet(parquet_buffer, engine='pyarrow', index=True)
|
|
parquet_bytes = parquet_buffer.getvalue()
|
|
|
|
# sientia_do MinioRepository API
|
|
mock_repo.bucket = 'test-bucket'
|
|
mock_repo.upload_file = AsyncMock(
|
|
side_effect=lambda file_bytes, relative_key, content_type='application/octet-stream', bucket=None, metadata=None: {
|
|
'minio_object_name': f'sientia/streamlit-connectors/{relative_key}',
|
|
'original_filename': relative_key.rsplit('/', 1)[-1],
|
|
'uploaded_at': '2024-01-01T00:00:00Z',
|
|
'sha256_hash': 'deadbeef',
|
|
}
|
|
)
|
|
mock_repo.download_file = AsyncMock(return_value=parquet_bytes)
|
|
mock_repo.list_objects = AsyncMock(return_value=[])
|
|
mock_repo.delete_file = AsyncMock()
|
|
mock_repo.close = MagicMock()
|
|
|
|
return mock_repo
|
|
|
|
|
|
@pytest_asyncio.fixture
|
|
def mock_pi_web_api_repository():
|
|
"""Mock PI Web API repository for PI Web API operations."""
|
|
mock_repo = MagicMock()
|
|
|
|
async def _write_value(web_ids, value, metadata=None, **kwargs):
|
|
"""
|
|
Mirror successful PI writes: one response item per requested web_id.
|
|
|
|
write_pi_web_api_data passes the list into process_pi_web_api_response (not a
|
|
wrapped {'Items': ...} envelope).
|
|
"""
|
|
return [{'WebId': wid, 'Errors': []} for wid in web_ids]
|
|
|
|
mock_repo.write_value = AsyncMock(side_effect=_write_value)
|
|
mock_repo.close = MagicMock()
|
|
return mock_repo
|
|
|
|
@pytest_asyncio.fixture
|
|
def mock_opc_repository():
|
|
"""Mock OPC repository for OPC operations."""
|
|
mock_repo = MagicMock()
|
|
mock_repo.write_data = AsyncMock(
|
|
return_value=(True, {'response_time': 0.1})
|
|
)
|
|
mock_repo.disconnect = AsyncMock()
|
|
return mock_repo
|
|
|
|
@pytest_asyncio.fixture
|
|
def patch_create_engine(postgres_engine):
|
|
"""Patch create_engine to return test postgres_engine."""
|
|
with patch('sientia_do.temporal.activities.postgres.create_engine', return_value=postgres_engine):
|
|
yield
|
|
|
|
|
|
@pytest_asyncio.fixture
|
|
def patch_minio_repository(mock_minio_repository):
|
|
"""Patch MinioRepository to return mock."""
|
|
# Patch where Activities resolves the symbol (import binds the original class).
|
|
with patch('laborious.activities.activities.MinioRepository', return_value=mock_minio_repository):
|
|
yield
|
|
|
|
@pytest_asyncio.fixture
|
|
def patch_pi_web_api_repository(mock_pi_web_api_repository):
|
|
"""Patch PI Web API client to return mock."""
|
|
with patch('laborious.activities.api.PIWebAPIClient', return_value=mock_pi_web_api_repository):
|
|
yield
|
|
|
|
|
|
@pytest_asyncio.fixture
|
|
def plugin_store_stub():
|
|
"""
|
|
PluginStore stub for Activities construction.
|
|
|
|
Runtime installation happens in the worker process; activities only hold a reference.
|
|
"""
|
|
|
|
return MagicMock()
|
|
|
|
|
|
@pytest_asyncio.fixture
|
|
def mlflow_repository_stub():
|
|
"""
|
|
SientiaMLflowRepository stub that returns a SientiaModel-like wrapper for E2E tests.
|
|
|
|
Transform/predict mirror the legacy sklearn/pyfunc mock behavior using pandas outputs.
|
|
"""
|
|
|
|
repo = MagicMock()
|
|
|
|
def _transform_side_effect(data: pd.DataFrame):
|
|
result = pd.DataFrame(
|
|
{
|
|
'feature_1': [0.234] * len(data),
|
|
'feature_2': [0.783] * len(data),
|
|
}
|
|
)
|
|
result.index = data.index
|
|
return result, {}
|
|
|
|
def _predict_side_effect(_params: dict, data: pd.DataFrame):
|
|
pred = pd.DataFrame([0.5] * len(data), columns=['placeholder'])
|
|
pred.index = data.index
|
|
return pred, {}
|
|
|
|
wrapper = MagicMock()
|
|
wrapper.transform.side_effect = _transform_side_effect
|
|
wrapper.predict.side_effect = _predict_side_effect
|
|
|
|
repo.get_cached_model = MagicMock(return_value=wrapper)
|
|
repo.stub_wrapper = wrapper
|
|
repo._client = MagicMock()
|
|
return repo
|
|
|
|
|
|
@pytest_asyncio.fixture(scope='function')
|
|
async def test_activities(
|
|
postgres_engine,
|
|
postgres_container,
|
|
mock_logger,
|
|
notification_handler,
|
|
metrics_controller,
|
|
mock_minio_repository,
|
|
patch_create_engine,
|
|
patch_minio_repository,
|
|
mlflow_repository_stub,
|
|
plugin_store_stub,
|
|
patch_pi_web_api_repository,
|
|
mock_opc_repository
|
|
):
|
|
"""
|
|
Create Activities instance with test dependencies.
|
|
|
|
This fixture creates a real Activities instance with:
|
|
- PostgreSQL database (via testcontainers)
|
|
- Mocked MinIO client
|
|
- Real NotificationHandler and MetricsController (with mocked underlying services)
|
|
"""
|
|
activities = Activities(
|
|
postgres_config={
|
|
'host': 'localhost',
|
|
'port': postgres_container.get_exposed_port(5432),
|
|
'user': 'test',
|
|
'password': 'test',
|
|
'dbname': 'test',
|
|
'min_connections': 1,
|
|
'max_connections': 5,
|
|
},
|
|
plugin_store=plugin_store_stub,
|
|
minio_config={
|
|
# Host:port only; Minio() prepends http(s):// from the secure flag.
|
|
'endpoint_url': 'localhost:9000',
|
|
'access_key': 'test',
|
|
'secret_key': 'test',
|
|
'default_bucket': 'test-bucket',
|
|
'retention_hours': 24,
|
|
'secure': False,
|
|
},
|
|
opc_config={},
|
|
pi_web_api_config={
|
|
'base_url': 'http://localhost:8080',
|
|
'auth_type': 'bearer',
|
|
'auth_token': 'test_token',
|
|
},
|
|
logger=mock_logger,
|
|
notification_handler=notification_handler,
|
|
metrics_controller=metrics_controller,
|
|
mlflow_repository=mlflow_repository_stub,
|
|
)
|
|
|
|
activities.opc_repository = {
|
|
'1': mock_opc_repository,
|
|
}
|
|
|
|
try:
|
|
yield activities
|
|
finally:
|
|
# Cleanup - ALWAYS runs, even if test fails
|
|
await activities.shutdown()
|
|
|
|
|
|
@pytest_asyncio.fixture(scope='function')
|
|
async def test_activities_real_minio(
|
|
postgres_engine,
|
|
postgres_container,
|
|
minio_container,
|
|
mock_logger,
|
|
notification_handler,
|
|
metrics_controller,
|
|
patch_create_engine,
|
|
mlflow_repository_stub,
|
|
plugin_store_stub,
|
|
patch_pi_web_api_repository,
|
|
mock_opc_repository,
|
|
):
|
|
"""
|
|
Activities with a real MinIO testcontainer (no MinioRepository patch) for offload tests.
|
|
"""
|
|
minio_client = minio_container.get_client()
|
|
if not minio_client.bucket_exists('test-bucket'):
|
|
minio_client.make_bucket('test-bucket')
|
|
minio_port = minio_container.get_exposed_port(9000)
|
|
activities = Activities(
|
|
postgres_config={
|
|
'host': 'localhost',
|
|
'port': postgres_container.get_exposed_port(5432),
|
|
'user': 'test',
|
|
'password': 'test',
|
|
'dbname': 'test',
|
|
'min_connections': 1,
|
|
'max_connections': 5,
|
|
},
|
|
plugin_store=plugin_store_stub,
|
|
minio_config={
|
|
'endpoint_url': f'localhost:{minio_port}',
|
|
'access_key': 'minioadmin',
|
|
'secret_key': 'minioadmin',
|
|
'default_bucket': 'test-bucket',
|
|
'retention_hours': 24,
|
|
'secure': False,
|
|
},
|
|
opc_config={},
|
|
pi_web_api_config={
|
|
'base_url': 'http://localhost:8080',
|
|
'auth_type': 'bearer',
|
|
'auth_token': 'test_token',
|
|
},
|
|
logger=mock_logger,
|
|
notification_handler=notification_handler,
|
|
metrics_controller=metrics_controller,
|
|
mlflow_repository=mlflow_repository_stub,
|
|
)
|
|
activities.opc_repository = {'1': mock_opc_repository}
|
|
try:
|
|
yield activities
|
|
finally:
|
|
await activities.shutdown()
|
|
|
|
|
|
def _worker_activity_list(test_activities: Activities):
|
|
return [
|
|
test_activities.load_custom_query,
|
|
test_activities.load_query_with_minio_offload,
|
|
test_activities.cleanup_minio_objects_expired,
|
|
test_activities.input_gate,
|
|
test_activities.request_transform,
|
|
test_activities.mlflow_response_gate,
|
|
test_activities.mlflow_content_gate,
|
|
test_activities.request_predict,
|
|
test_activities.repeat_last_prediction,
|
|
test_activities.format_prediction,
|
|
test_activities.format_transformed_data,
|
|
test_activities.format_default_prediction,
|
|
test_activities.write_pi_web_api_data,
|
|
test_activities.write_opc_data,
|
|
test_activities.export_data_to_postgres,
|
|
test_activities.export_payload_to_postgres,
|
|
test_activities.write_metrics,
|
|
]
|
|
|
|
|
|
@pytest_asyncio.fixture(scope='function')
|
|
async def temporal_test_env():
|
|
"""Create Temporal test environment."""
|
|
env = await WorkflowEnvironment.start_time_skipping()
|
|
async with env:
|
|
yield env
|
|
|
|
|
|
@pytest_asyncio.fixture(scope='function')
|
|
async def temporal_worker(temporal_test_env, test_activities):
|
|
"""Create Temporal worker with test activities."""
|
|
async with Worker(
|
|
temporal_test_env.client,
|
|
task_queue='test-queue',
|
|
workflows=[PredictionsBatch, PredictionProcess, FormatAndExportPrediction],
|
|
activities=_worker_activity_list(test_activities),
|
|
) as worker:
|
|
yield worker
|
|
|
|
|
|
@pytest_asyncio.fixture(scope='function')
|
|
async def temporal_worker_real_minio(temporal_test_env, test_activities_real_minio):
|
|
"""Temporal worker backed by Activities using real MinIO testcontainer."""
|
|
async with Worker(
|
|
temporal_test_env.client,
|
|
task_queue='test-queue',
|
|
workflows=[PredictionsBatch, PredictionProcess, FormatAndExportPrediction],
|
|
activities=_worker_activity_list(test_activities_real_minio),
|
|
) as worker:
|
|
yield worker
|