mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-04-25 08:26:21 +02:00
d35473f7f7
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.
144 lines
4.7 KiB
Python
144 lines
4.7 KiB
Python
"""
|
|
Tests for pipeline metadata preservation: DocumentMetadata and
|
|
ProcessingMetadata round-trip through translators, field preservation,
|
|
and default handling.
|
|
"""
|
|
|
|
import pytest
|
|
|
|
from trustgraph.schema import DocumentMetadata, ProcessingMetadata, Triple, Term, IRI
|
|
from trustgraph.messaging.translators.metadata import (
|
|
DocumentMetadataTranslator,
|
|
ProcessingMetadataTranslator,
|
|
)
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# DocumentMetadata translator
|
|
# ---------------------------------------------------------------------------
|
|
|
|
class TestDocumentMetadataTranslator:
|
|
|
|
def setup_method(self):
|
|
self.tx = DocumentMetadataTranslator()
|
|
|
|
def test_full_round_trip(self):
|
|
data = {
|
|
"id": "doc-123",
|
|
"time": 1710000000,
|
|
"kind": "application/pdf",
|
|
"title": "Test Document",
|
|
"comments": "No comments",
|
|
"metadata": [],
|
|
"workspace": "alice",
|
|
"tags": ["finance", "q4"],
|
|
"parent-id": "doc-100",
|
|
"document-type": "page",
|
|
}
|
|
obj = self.tx.decode(data)
|
|
assert obj.id == "doc-123"
|
|
assert obj.time == 1710000000
|
|
assert obj.kind == "application/pdf"
|
|
assert obj.title == "Test Document"
|
|
assert obj.workspace == "alice"
|
|
assert obj.tags == ["finance", "q4"]
|
|
assert obj.parent_id == "doc-100"
|
|
assert obj.document_type == "page"
|
|
|
|
wire = self.tx.encode(obj)
|
|
assert wire["id"] == "doc-123"
|
|
assert wire["workspace"] == "alice"
|
|
assert wire["parent-id"] == "doc-100"
|
|
assert wire["document-type"] == "page"
|
|
|
|
def test_defaults_for_missing_fields(self):
|
|
obj = self.tx.decode({})
|
|
assert obj.parent_id == ""
|
|
assert obj.document_type == "source"
|
|
|
|
def test_metadata_triples_preserved(self):
|
|
triple_wire = [{
|
|
"s": {"t": "i", "i": "http://example.org/s"},
|
|
"p": {"t": "i", "i": "http://example.org/p"},
|
|
"o": {"t": "i", "i": "http://example.org/o"},
|
|
}]
|
|
data = {"metadata": triple_wire}
|
|
obj = self.tx.decode(data)
|
|
assert len(obj.metadata) == 1
|
|
assert obj.metadata[0].s.iri == "http://example.org/s"
|
|
|
|
def test_none_metadata_handled(self):
|
|
data = {"metadata": None}
|
|
obj = self.tx.decode(data)
|
|
assert obj.metadata == []
|
|
|
|
def test_empty_tags_preserved(self):
|
|
data = {"tags": []}
|
|
obj = self.tx.decode(data)
|
|
wire = self.tx.encode(obj)
|
|
assert wire["tags"] == []
|
|
|
|
def test_falsy_fields_omitted_from_wire(self):
|
|
"""Empty string fields should be omitted from wire format."""
|
|
obj = DocumentMetadata(id="", time=0, workspace="")
|
|
wire = self.tx.encode(obj)
|
|
assert "id" not in wire
|
|
assert "workspace" not in wire
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# ProcessingMetadata translator
|
|
# ---------------------------------------------------------------------------
|
|
|
|
class TestProcessingMetadataTranslator:
|
|
|
|
def setup_method(self):
|
|
self.tx = ProcessingMetadataTranslator()
|
|
|
|
def test_full_round_trip(self):
|
|
data = {
|
|
"id": "proc-1",
|
|
"document-id": "doc-123",
|
|
"time": 1710000000,
|
|
"flow": "default",
|
|
"workspace": "alice",
|
|
"collection": "my-collection",
|
|
"tags": ["tag1"],
|
|
}
|
|
obj = self.tx.decode(data)
|
|
assert obj.id == "proc-1"
|
|
assert obj.document_id == "doc-123"
|
|
assert obj.flow == "default"
|
|
assert obj.workspace == "alice"
|
|
assert obj.collection == "my-collection"
|
|
assert obj.tags == ["tag1"]
|
|
|
|
wire = self.tx.encode(obj)
|
|
assert wire["id"] == "proc-1"
|
|
assert wire["document-id"] == "doc-123"
|
|
assert wire["workspace"] == "alice"
|
|
assert wire["collection"] == "my-collection"
|
|
|
|
def test_missing_fields_use_defaults(self):
|
|
obj = self.tx.decode({})
|
|
assert obj.id is None
|
|
assert obj.workspace is None
|
|
assert obj.collection is None
|
|
|
|
def test_tags_none_omitted(self):
|
|
obj = ProcessingMetadata(tags=None)
|
|
wire = self.tx.encode(obj)
|
|
assert "tags" not in wire
|
|
|
|
def test_tags_empty_list_preserved(self):
|
|
obj = ProcessingMetadata(tags=[])
|
|
wire = self.tx.encode(obj)
|
|
assert wire["tags"] == []
|
|
|
|
def test_workspace_and_collection_preserved(self):
|
|
"""Core pipeline routing fields must survive round-trip."""
|
|
data = {"workspace": "bob", "collection": "research"}
|
|
obj = self.tx.decode(data)
|
|
wire = self.tx.encode(obj)
|
|
assert wire["workspace"] == "bob"
|
|
assert wire["collection"] == "research"
|