mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-04-25 00:16:23 +02:00
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.
145 lines
No EOL
4.1 KiB
Python
145 lines
No EOL
4.1 KiB
Python
import pytest
|
|
from unittest.mock import AsyncMock, Mock, patch
|
|
from trustgraph.schema import TextDocument, Metadata
|
|
from trustgraph.chunking.recursive.chunker import Processor as RecursiveChunker
|
|
from trustgraph.chunking.token.chunker import Processor as TokenChunker
|
|
from prometheus_client import REGISTRY
|
|
|
|
|
|
@pytest.fixture
|
|
def mock_flow():
|
|
"""Mock flow function that returns a mock output producer."""
|
|
output_mock = AsyncMock()
|
|
flow_mock = Mock(return_value=output_mock)
|
|
return flow_mock, output_mock
|
|
|
|
|
|
@pytest.fixture
|
|
def mock_consumer():
|
|
"""Mock consumer with test attributes."""
|
|
consumer = Mock()
|
|
consumer.id = "test-consumer"
|
|
consumer.flow = "test-flow"
|
|
return consumer
|
|
|
|
|
|
@pytest.fixture
|
|
def sample_text_document():
|
|
"""Sample document with moderate length text."""
|
|
metadata = Metadata(
|
|
id="test-doc-1",
|
|
collection="test-collection"
|
|
)
|
|
text = "The quick brown fox jumps over the lazy dog. " * 20
|
|
return TextDocument(
|
|
metadata=metadata,
|
|
text=text.encode("utf-8")
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def long_text_document():
|
|
"""Long document for testing multiple chunks."""
|
|
metadata = Metadata(
|
|
id="test-doc-long",
|
|
collection="test-collection"
|
|
)
|
|
# Create a long text that will definitely be chunked
|
|
text = " ".join([f"Sentence number {i}. This is part of a long document." for i in range(200)])
|
|
return TextDocument(
|
|
metadata=metadata,
|
|
text=text.encode("utf-8")
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def unicode_text_document():
|
|
"""Document with various unicode characters."""
|
|
metadata = Metadata(
|
|
id="test-doc-unicode",
|
|
collection="test-collection"
|
|
)
|
|
text = """
|
|
English: Hello World!
|
|
Chinese: 你好世界
|
|
Japanese: こんにちは世界
|
|
Korean: 안녕하세요 세계
|
|
Arabic: مرحبا بالعالم
|
|
Russian: Привет мир
|
|
Emoji: 🌍 🌎 🌏 😀 🎉
|
|
Math: ∑ ∏ ∫ ∞ √ π
|
|
Symbols: © ® ™ € £ ¥
|
|
"""
|
|
return TextDocument(
|
|
metadata=metadata,
|
|
text=text.encode("utf-8")
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def empty_text_document():
|
|
"""Empty document for edge case testing."""
|
|
metadata = Metadata(
|
|
id="test-doc-empty",
|
|
collection="test-collection"
|
|
)
|
|
return TextDocument(
|
|
metadata=metadata,
|
|
text=b""
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def mock_message(sample_text_document):
|
|
"""Mock message containing a document."""
|
|
msg = Mock()
|
|
msg.value.return_value = sample_text_document
|
|
return msg
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def clear_metrics():
|
|
"""Clear metrics before each test to avoid duplicates."""
|
|
# Clear the chunk_metric class attribute if it exists
|
|
if hasattr(RecursiveChunker, 'chunk_metric'):
|
|
# Unregister from Prometheus registry first
|
|
try:
|
|
REGISTRY.unregister(RecursiveChunker.chunk_metric)
|
|
except KeyError:
|
|
pass # Already unregistered
|
|
delattr(RecursiveChunker, 'chunk_metric')
|
|
if hasattr(TokenChunker, 'chunk_metric'):
|
|
try:
|
|
REGISTRY.unregister(TokenChunker.chunk_metric)
|
|
except KeyError:
|
|
pass # Already unregistered
|
|
delattr(TokenChunker, 'chunk_metric')
|
|
yield
|
|
# Clean up after test as well
|
|
if hasattr(RecursiveChunker, 'chunk_metric'):
|
|
try:
|
|
REGISTRY.unregister(RecursiveChunker.chunk_metric)
|
|
except KeyError:
|
|
pass
|
|
delattr(RecursiveChunker, 'chunk_metric')
|
|
if hasattr(TokenChunker, 'chunk_metric'):
|
|
try:
|
|
REGISTRY.unregister(TokenChunker.chunk_metric)
|
|
except KeyError:
|
|
pass
|
|
delattr(TokenChunker, 'chunk_metric')
|
|
|
|
|
|
@pytest.fixture
|
|
def mock_async_processor_init():
|
|
"""Mock AsyncProcessor.__init__ to avoid taskgroup requirement."""
|
|
def init_mock(self, **kwargs):
|
|
# Set attributes that AsyncProcessor would normally set
|
|
self.config_handlers = []
|
|
self.specifications = []
|
|
self.flows = {}
|
|
self.id = kwargs.get('id', 'test-processor')
|
|
# Don't call the real __init__
|
|
|
|
with patch('trustgraph.base.async_processor.AsyncProcessor.__init__', init_mock):
|
|
yield |