trustgraph/tests/unit/test_base/test_flow_processor.py
cybermaggedon d35473f7f7
feat: workspace-based multi-tenancy, replacing user as tenancy axis (#840)
Introduces `workspace` as the isolation boundary for config, flows,
library, and knowledge data. Removes `user` as a schema-level field
throughout the code, API specs, and tests; workspace provides the
same separation more cleanly at the trusted flow.workspace layer
rather than through client-supplied message fields.

Design
------
- IAM tech spec (docs/tech-specs/iam.md) documents current state,
  proposed auth/access model, and migration direction.
- Data ownership model (docs/tech-specs/data-ownership-model.md)
  captures the workspace/collection/flow hierarchy.

Schema + messaging
------------------
- Drop `user` field from AgentRequest/Step, GraphRagQuery,
  DocumentRagQuery, Triples/Graph/Document/Row EmbeddingsRequest,
  Sparql/Rows/Structured QueryRequest, ToolServiceRequest.
- Keep collection/workspace routing via flow.workspace at the
  service layer.
- Translators updated to not serialise/deserialise user.

API specs
---------
- OpenAPI schemas and path examples cleaned of user fields.
- Websocket async-api messages updated.
- Removed the unused parameters/User.yaml.

Services + base
---------------
- Librarian, collection manager, knowledge, config: all operations
  scoped by workspace. Config client API takes workspace as first
  positional arg.
- `flow.workspace` set at flow start time by the infrastructure;
  no longer pass-through from clients.
- Tool service drops user-personalisation passthrough.

CLI + SDK
---------
- tg-init-workspace and workspace-aware import/export.
- All tg-* commands drop user args; accept --workspace.
- Python API/SDK (flow, socket_client, async_*, explainability,
  library) drop user kwargs from every method signature.

MCP server
----------
- All tool endpoints drop user parameters; socket_manager no longer
  keyed per user.

Flow service
------------
- Closure-based topic cleanup on flow stop: only delete topics
  whose blueprint template was parameterised AND no remaining
  live flow (across all workspaces) still resolves to that topic.
  Three scopes fall out naturally from template analysis:
    * {id} -> per-flow, deleted on stop
    * {blueprint} -> per-blueprint, kept while any flow of the
      same blueprint exists
    * {workspace} -> per-workspace, kept while any flow in the
      workspace exists
    * literal -> global, never deleted (e.g. tg.request.librarian)
  Fixes a bug where stopping a flow silently destroyed the global
  librarian exchange, wedging all library operations until manual
  restart.

RabbitMQ backend
----------------
- heartbeat=60, blocked_connection_timeout=300. Catches silently
  dead connections (broker restart, orphaned channels, network
  partitions) within ~2 heartbeat windows, so the consumer
  reconnects and re-binds its queue rather than sitting forever
  on a zombie connection.

Tests
-----
- Full test refresh: unit, integration, contract, provenance.
- Dropped user-field assertions and constructor kwargs across
  ~100 test files.
- Renamed user-collection isolation tests to workspace-collection.
2026-04-21 23:23:01 +01:00

263 lines
7.8 KiB
Python

"""
Unit tests for trustgraph.base.flow_processor
"""
import pytest
from unittest.mock import AsyncMock, MagicMock, patch
from unittest import IsolatedAsyncioTestCase
from trustgraph.base.flow_processor import FlowProcessor
# Patches needed to let AsyncProcessor.__init__ run without real
# infrastructure while still setting self.id correctly.
ASYNC_PROCESSOR_PATCHES = [
patch('trustgraph.base.async_processor.get_pubsub', return_value=MagicMock()),
patch('trustgraph.base.async_processor.ProcessorMetrics', return_value=MagicMock()),
patch('trustgraph.base.async_processor.Consumer', return_value=MagicMock()),
]
def with_async_processor_patches(func):
"""Apply all AsyncProcessor dependency patches to a test."""
for p in reversed(ASYNC_PROCESSOR_PATCHES):
func = p(func)
return func
class TestFlowProcessorSimple(IsolatedAsyncioTestCase):
"""Test FlowProcessor base class functionality"""
@with_async_processor_patches
async def test_flow_processor_initialization_basic(self, *mocks):
"""Test basic FlowProcessor initialization"""
config = {
'id': 'test-flow-processor',
'taskgroup': AsyncMock()
}
processor = FlowProcessor(**config)
assert processor.id == 'test-flow-processor'
assert processor.flows == {}
assert processor.specifications == []
@with_async_processor_patches
async def test_register_specification(self, *mocks):
"""Test registering a specification"""
config = {
'id': 'test-flow-processor',
'taskgroup': AsyncMock()
}
processor = FlowProcessor(**config)
mock_spec = MagicMock()
mock_spec.name = 'test-spec'
processor.register_specification(mock_spec)
assert len(processor.specifications) == 1
assert processor.specifications[0] == mock_spec
@patch('trustgraph.base.flow_processor.Flow')
@with_async_processor_patches
async def test_start_flow(self, *mocks):
"""Test starting a flow"""
mock_flow_class = mocks[-1]
config = {
'id': 'test-processor',
'taskgroup': AsyncMock()
}
processor = FlowProcessor(**config)
mock_flow = AsyncMock()
mock_flow_class.return_value = mock_flow
flow_name = 'test-flow'
flow_defn = {'config': 'test-config'}
await processor.start_flow("default", flow_name, flow_defn)
assert ("default", flow_name) in processor.flows
mock_flow_class.assert_called_once_with(
'test-processor', flow_name, "default", processor, flow_defn
)
mock_flow.start.assert_called_once()
@patch('trustgraph.base.flow_processor.Flow')
@with_async_processor_patches
async def test_stop_flow(self, *mocks):
"""Test stopping a flow"""
mock_flow_class = mocks[-1]
config = {
'id': 'test-processor',
'taskgroup': AsyncMock()
}
processor = FlowProcessor(**config)
mock_flow = AsyncMock()
mock_flow_class.return_value = mock_flow
flow_name = 'test-flow'
await processor.start_flow("default", flow_name, {'config': 'test-config'})
await processor.stop_flow("default", flow_name)
assert ("default", flow_name) not in processor.flows
mock_flow.stop.assert_called_once()
@with_async_processor_patches
async def test_stop_flow_not_exists(self, *mocks):
"""Test stopping a flow that doesn't exist"""
config = {
'id': 'test-flow-processor',
'taskgroup': AsyncMock()
}
processor = FlowProcessor(**config)
await processor.stop_flow("default", 'non-existent-flow')
assert processor.flows == {}
@patch('trustgraph.base.flow_processor.Flow')
@with_async_processor_patches
async def test_on_configure_flows_basic(self, *mocks):
"""Test basic flow configuration handling"""
mock_flow_class = mocks[-1]
config = {
'id': 'test-processor',
'taskgroup': AsyncMock()
}
processor = FlowProcessor(**config)
mock_flow = AsyncMock()
mock_flow_class.return_value = mock_flow
config_data = {
'processor:test-processor': {
'test-flow': '{"config": "test-config"}'
}
}
await processor.on_configure_flows("default", config_data, version=1)
assert ("default", 'test-flow') in processor.flows
mock_flow_class.assert_called_once_with(
'test-processor', 'test-flow', "default", processor,
{'config': 'test-config'}
)
mock_flow.start.assert_called_once()
@with_async_processor_patches
async def test_on_configure_flows_no_config(self, *mocks):
"""Test flow configuration handling when no config exists for this processor"""
config = {
'id': 'test-processor',
'taskgroup': AsyncMock()
}
processor = FlowProcessor(**config)
config_data = {
'processor:other-processor': {
'other-flow': '{"config": "other-config"}'
}
}
await processor.on_configure_flows("default", config_data, version=1)
assert processor.flows == {}
@with_async_processor_patches
async def test_on_configure_flows_invalid_config(self, *mocks):
"""Test flow configuration handling with invalid config format"""
config = {
'id': 'test-processor',
'taskgroup': AsyncMock()
}
processor = FlowProcessor(**config)
config_data = {
'other-data': 'some-value'
}
await processor.on_configure_flows("default", config_data, version=1)
assert processor.flows == {}
@patch('trustgraph.base.flow_processor.Flow')
@with_async_processor_patches
async def test_on_configure_flows_start_and_stop(self, *mocks):
"""Test flow configuration handling with starting and stopping flows"""
mock_flow_class = mocks[-1]
config = {
'id': 'test-processor',
'taskgroup': AsyncMock()
}
processor = FlowProcessor(**config)
mock_flow1 = AsyncMock()
mock_flow2 = AsyncMock()
mock_flow_class.side_effect = [mock_flow1, mock_flow2]
config_data1 = {
'processor:test-processor': {
'flow1': '{"config": "config1"}'
}
}
await processor.on_configure_flows("default", config_data1, version=1)
config_data2 = {
'processor:test-processor': {
'flow2': '{"config": "config2"}'
}
}
await processor.on_configure_flows("default", config_data2, version=2)
assert ("default", 'flow1') not in processor.flows
mock_flow1.stop.assert_called_once()
assert ("default", 'flow2') in processor.flows
mock_flow2.start.assert_called_once()
@with_async_processor_patches
@patch('trustgraph.base.async_processor.AsyncProcessor.start')
async def test_start_calls_parent(self, mock_parent_start, *mocks):
"""Test that start() calls parent start method"""
mock_parent_start.return_value = None
config = {
'id': 'test-flow-processor',
'taskgroup': AsyncMock()
}
processor = FlowProcessor(**config)
await processor.start()
mock_parent_start.assert_called_once()
async def test_add_args_calls_parent(self):
"""Test that add_args() calls parent add_args method"""
mock_parser = MagicMock()
with patch('trustgraph.base.async_processor.AsyncProcessor.add_args') as mock_parent_add_args:
FlowProcessor.add_args(mock_parser)
mock_parent_add_args.assert_called_once_with(mock_parser)
if __name__ == '__main__':
pytest.main([__file__])